Ponzi schemes, a more than a century-old fraud, have recently infiltrated blockchain-based cryptocurrency domain led by an explosion of such schemes in two most popular cryptocurrencies: Bitcoin and Ethereum. On these two platforms alone, the perpetrators of these frauds have fleeced gullible investors of billions of dollars annually. Smart Ponzi schemes are a hazard to these cryptocurrency ecosystems, diminishing investor confidence in these cutting-edge technologies, threatening their integrity, and hindering their growth and broader adaptation. These smart Ponzi schemes have also created a nightmare for law enforcement as tracking and taking countermeasures against fraudsters and recovering the victims’ investment is challenging. Over the years, researchers have utilized significant advances in machine learning and AI to detect and promptly caution users against investing in Ponzi schemes on Bitcoin and Ethereum. However, this research still exists in silos, and there is a lack of a detailed survey paper critically analyzing various aspects of the approaches focusing on the menace of smart Ponzi schemes. This article surveys the state-of-the-art techniques proposed in the literature to detect smart Ponzi schemes on two popular blockchain platforms: Bitcoin and Ethereum. We list, categorize, and discuss papers that contributed benchmark datasets, developed novel features concerning various aspects of smart Ponzi schemes, and proposed novel machine-learning approaches to detect them.

Fetal compromise is a significant global health issue that can result in severe long-term disability and mortality. Current fetal monitoring is predominantly performed using cardiotocography (CTG) machines in healthcare settings, limiting clinical oversight to routine hospital visits or during labor. CTG monitoring typically relies on intermittent visual interpretation, sometimes resulting in inconsistent clinical judgement and delayed intervention. Artificial intelligence (AI) has been proposed to assist in CTG interpretation, but conventional AI models require substantial computational resources, making them impractical for wearable, battery-powered devices designed for continuous monitoring. In this study, we propose a quantized Edge AI model for detecting fetal compromise (pH < 7.05) in a resource-constrained setting. Utilizing the low-power MAX78002 AI microcontroller, we demonstrate real-time fetal compromise detection with a deep learning model optimized for power efficiency. Our final model, trained using knowledge distillation combined with quantization-aware training on an internal dataset of 9,887 CTG recordings and tested on 552 CTG recordings from the public CTU-UHB dataset, achieves an AUC of 0.81 while consuming only 2 mJ of energy per 60 minutes of inference data. This represents comparable performance to a GPU-based model on the same dataset, while achieving a 94% reduction in energy consumption. This work demonstrates that deep learning models for fetal compromise detection can be quantized and deployed on low-power Edge AI hardware, paving the way for wearable devices capable of continuous, real-time monitoring.

Accurate segmentation of stroke lesions in diffusion-weighted imaging (DWI) is crucial for clinical decision-making. However, automated infarct segmentation remains challenging due to variable infarct sizes and locations, and it is labor-intensive, requiring expert manual annotations for training. We propose a zero-shot framework to eliminate the need for manual segmentation labels by leveraging weak supervision from class activation maps (CAMs) to guide segmentation using MedSAM2, a foundation model for 3D medical image segmentation. By extracting attention maps from a fine-tuned ResNet on DWI scans labeled with stroke etiology (cause) and combining them with intensity information, we identify key regions and generate bounding-box prompts for MedSAM2. Our method achieves a Dice score of 54.2 ± 5.3% without any manual segmentation labels or tuning of the MedSAM2 model, demonstrating its potential as a scalable solution for reliable pseudo-label generation.

Medical image synthesis addresses healthcare data scarcity by generating realistic samples for clinical support systems, AI training, and research. However, the field faces challenges due to the complexity of imaging data with its diverse modalities, characteristics, and disease variations. To produce high-quality images, medical image synthesis typically relies on conditional generation, where labels and annotations serve as essential conditions that provide critical guidance signals during the generation process to control desired semantics and fidelity. However, in the medical domain, labels are often inaccessible due to the high cost of annotation, requirements for clinical expertise, as well as ethical concerns. To address this critical challenge, we propose RepMedGAN, a novel self-supervised representation-guided image generation framework that enhances label-free medical image synthesis by leveraging self-supervised learning representations, enabling high-quality generation across different modalities without requiring labels or annotations. Our framework incorporates a Self-supervised Guidance Module that provides rich semantic knowledge during training and introduces a Guidance Representation Generator to bridge the train-inference disparity. Through extensive evaluation across four diverse medical datasets including brain MRI, chest X-ray, kidney CT, and eye glaucoma images, we demonstrate that RepMedGAN consistently achieves state-of-the-art results across multiple metrics and produces superior-quality medical images.

Ultrasound imaging serves as an important clinical diagnostic modality due to its non-invasive, radiation-free, and real-time capabilities. However, ultrasound images suffer from speckle noise that significantly compromises diagnostic accuracy and clinical interpretation. Traditional denoising methods are limited by speckle noise's signal-dependent nature, often removing important diagnostic features. While deep learning performs better, it requires large labelled datasets that are difficult to obtain due to privacy concerns and annotation costs. Self-supervised learning through masked image modeling (MIM) shows potential in addressing data scarcity, but conventional MIM, developed for high-level vision tasks, is unsuitable for low-level tasks like image denoising due to its framework architecture and learning strategy. To this end, we propose Image Denoising Masked Image Modeling (ID-MIM), the first MIM framework for ultrasound image denoising. ID-MIM incorporates a novel high-frequency oriented dual-branch masking and a specialized learning objective for noise reduction. Our encoder-only architecture features a multi-scale hierarchical transformer with dynamic skip connections, where the encoder directly performs denoising rather than relying on separate decoder reconstruction as in conventional MIM approaches. Extensive experiments demonstrate the superior performance of our ID-MIM framework across diverse noise scenarios, establishing new state-of-the-art results.

Knowledge distillation (KD) has proven effective for model compression by transferring knowledge from a larger network (teacher) to a smaller network (student). Current KD in time series is predominantly based on logit and feature aligning techniques originally developed for computer vision tasks. These methods do not explicitly account for temporal data and fall short in two key aspects. First, the mechanisms by which the transferred knowledge helps the student model’s learning process remain unclear, due to uninterpretability of logits and features. Second, these methods transfer only limited knowledge, primarily replicating the teacher’s predictive accuracy. As a result, student models often produce predictive distributions that differ significantly from those of their teachers, hindering their safe substitution for teacher models. In this work, we propose transferring interpretable knowledge by extending conventional logit transfer to convey not just the right prediction but also the right reasoning of the teacher. Specifically, we induce other useful knowledge from the teacher logits, termed temporal saliency, which captures the importance of each input timestep to the teacher’s prediction. By training the student with Temporal Saliency Distillation (TSD), we encourage it to make predictions based on the same input features as the teacher. TSD requires no additional parameters or architecture-specific assumptions. We demonstrate that TSD effectively improves the performance of baseline methods while also achieving desirable properties beyond predictive accuracy. We hope our work establishes a new paradigm for interpretable knowledge distillation in time series analysis.

Atrial fibrillation (AF) is a significant risk factor for ischemic stroke recurrence, yet its diagnosis remains challenging through short-term heart monitoring due to its often paroxysmal and silent nature. Despite its diagnostic superiority, prolonged cardiac monitoring is typically impractical and not cost-effective for widespread implementation. We propose a novel AF risk stratification framework using a multimodal deep learning approach that integrates diffusion-weighted imaging (DWI) of the brain with clinical patient data. Our methodology combines convolutional neural networks (CNNs) for image analysis and gradient-boosted decision trees (GBDT) for clinical data, leveraging an innovative fusion strategy and an auxiliary loss function based on infarct location. The proposed approach achieves an area under the receiver operating characteristic (AUROC) of 89.18%, outperforming unimodal counterparts. This work contributes to the field by enabling AF risk stratification from brain DWI, utilizing weak supervision, and introducing a novel early and late-stage data fusion approach. Our method easily integrates with existing workflows and can identify high-risk individuals requiring intensive cardiac monitoring.

Abstract In recent years, spatio-temporal graph neural networks (GNNs) have successfully been used to improve traffic prediction by modeling intricate spatio-temporal dependencies in irregular traffic networks. However, these approaches may not capture the intrinsic properties of traffic data and can suffer from overfitting due to their local nature. This paper introduces the Implicit Sensing Self-Supervised learning model (ISSS), which leverages a multi-pretext task framework for traffic flow prediction. By transforming data into an alternative feature space, ISSS effectively captures both specific and general representations through self-supervised tasks, including contrastive learning and spatial jigsaw puzzles. This enhancement promotes a deeper understanding of traffic features, improved regularization, and more accurate representations. Comparative experiments on six datasets demonstrate the effectiveness of ISSS in learning general and discriminative features in both supervised and unsupervised modes. ISSS outperforms existing models, demonstrating its capabilities in improving traffic flow predictions while addressing challenges associated with local operations and overfitting. Comprehensive evaluations across various traffic prediction datasets, have established the validity of the proposed approach. Unsupervised learning scenarios have shown the improvements in RMSE for the METR-LA and PEMSBAY datasets of 0.39 and 0.35 for location-dependent and location-independent tasks, respectively. In supervised learning scenarios, for the same datasets, the improvements were 1.16 for location-dependent tasks and 0.55 for location-independent tasks.

Self-supervised learning has achieved state-of-the-art performance in various tasks and applications. In computer vision, self-supervised learning often employs contrastive learning and masked image modeling, each with its limitations: contrastive learning heavily relies on strong data augmentation and large batch sizes, etc., while masked image modeling struggles to capture high-level semantics and discrimination. In this work, we introduce MAsked Contrastive Representation Learning (MACRL), a novel framework that integrates both paradigms through an asymmetric siamese network design. The online and momentum branches of the network receive asymmetric data augmentation operations and extract features through their encoders. The decoder in the online branch reconstructs the original image, while the projectors in both branches compute the contrastive loss. The online branch and the momentum branch are updated through gradient backpropagation and exponential moving average, respectively. MACRL jointly optimizes the reconstruction and the contrastive objectives to encourage representations with enhanced discrimination and semantics. Experimental results show that MACRL achieves competitive performance in downstream vision tasks, including image classification and semantic segmentation. Moreover, it demonstrates consistent performance across both large-scale and small-scale datasets.

Blockchain technology has been integrated into a wide range of applications in various sectors, such as finance, supply chain, health, and governance. However, the participation of a few actors with malicious intentions challenges law enforcement authorities, regulators and other users. These challenges revolve around dealing with an array of illegal activities such as asset trades in dark markets, receiving payments for cyber-attacks, and facilitating money laundering. Developing an efficient mechanism to identify malicious actors in blockchain networks is a pressing need to build confidence among the stakeholders and ensure regulatory adherence. The raw data of blockchain transactions do not readily reveal the dynamic behavioural changes and their interconnection between transactions and accounts. These behavioural patterns can be useful for identifying malicious actors. Machine Learning (ML)-based models for early warning and/or detection are considered one of the potential approaches. In ML, feature engineering plays a crucial role in enhancing the predictive performance of a model. This study proposes different categories of features and unified feature extraction approaches for raw Bitcoin and Ethereum transaction data and their interconnection information. As far as we are aware, there has been no study that considered a feature engineering approach for identifying malicious activities. The significance of the engineered features was validated against eight classifiers, including Random Forest (RF), XG-boost (XG), Silas, and neural network-based classifiers. The results showed that these features contribute to higher classification accuracy and higher Area Under the Receiver Operating Characteristic Curve (AUC) value for both Bitcoin and Ethereum transactions. This work also analysed the influence of engineered features in classification using the eXplainable Artificial Intelligence (XAI) technique SHapley Additive exPlanations (SHAP) values. The feature importance scores confirmed the significance of the proposed engineered features towards implementing classification models to identify, target and disrupt malicious activities in blockchain networks.

Fog/Edge computing is a novel computing paradigm supporting resource-constrained Internet of Things (IoT) devices by placement of their tasks on edge and/or cloud servers. Recently, several Deep Reinforcement Learning (DRL)-based placement techniques have been proposed in fog/edge computing environments, which are only suitable for centralized setups. The training of well-performed DRL agents requires manifold training data while obtaining training data is costly. Hence, these centralized DRL-based techniques lack generalizability and quick adaptability, thus failing to efficiently tackle application placement problems. Moreover, many IoT applications are modeled as Directed Acyclic Graphs (DAGs) with diverse topologies. Satisfying dependencies of DAG-based IoT applications incur additional constraints and increase the complexity of placement problem. To overcome these challenges, we propose an actor-critic-based distributed application placement technique, working based on the IMPortance weighted Actor-Learner Architectures (IMPALA). IMPALA is known for efficient distributed experience trajectory generation that significantly reduces exploration costs of agents. Besides, it uses an adaptive off-policy correction method for faster convergence to optimal solutions. Our technique uses recurrent layers to capture temporal behaviors of input data and a replay buffer to improve the sample efficiency. The performance results, obtained from simulation and testbed experiments, demonstrate that our technique significantly improves execution cost of IoT applications up to 30% compared to its counterparts.

Fog/Edge computing model allows harnessing of resources in the proximity of the Internet of Things (IoT) devices to support various types of latency-sensitive IoT applications.However, due to the mobility of users and a wide range of IoT applications with different resource requirements, it is a challenging issue to satisfy these applications' requirements.The execution of IoT applications exclusively on one fog/edge server may not be always feasible due to limited resources, while the execution of IoT applications on different servers requires further collaboration and management among servers.Moreover, considering user mobility, some modules of each IoT application may require migration to other servers for execution, leading to service interruption and extra execution costs.In this article, we propose a new weighted cost model for hierarchical fog computing environments, in terms of the response time of IoT applications and energy consumption of IoT devices, to minimize the cost of running IoT applications and potential migrations.Besides, a distributed clustering technique is proposed to enable the collaborative execution of tasks, emitted from application modules, among servers.Also, we propose an application placement technique to minimize the overall cost of executing IoT applications on multiple servers in a distributed manner.Furthermore, a distributed migration management technique is proposed for the potential migration of applications' modules to other remote servers as the users move along their path.Besides, failure recovery methods are embedded in the clustering, application placement, and migration management techniques to recover from unpredicted failures.The performance results demonstrate that our technique significantly improves its counterparts in terms of placement deployment time, average execution cost of tasks, the total number of migrations, the total number of interrupted tasks, and cumulative migration cost.

The evolution of ubiquitous sensors has led to the generation of copious amounts of waveform data. Human motion waveform analysis has found significance in clinical and home-based activity monitoring. Exploration of cluster structure in such waveform data prior to developing learning models is an important pattern recognition problem. A prominent category of algorithms in this direction, known as Visual Assessment of (cluster) Tendency (VAT), employs visual approaches to study cluster evolution through heat maps. This paper proposes shape-iVAT, a new relative of an improved VAT model, that captures local time-series characteristics through representative subsequences, known as shapelets, to identify interesting patterns in motion data. We propose an unsupervised method for shapelet extraction using maximin shape sampling and shape-based distance computation for selecting key shapelets representing characteristic motion patterns. These shapelets are used to transform waveform data into a dissimilarity matrix for VAT evaluation. We demonstrate that the proposed method outperforms standard VAT with global distance measures for identifying complex upper limb motion captured using a camera-based motion sensing device. We also show that our method has significance in efficient and interpretable cluster tendency assessment for anomaly detection and continuous motion monitoring.

Blockchain is a digital technology built on three pillars: decentralization, transparency and immutability. Bitcoin and Ethereum are two prevalent Blockchain platforms, where the participants are globally connected in a peer-to-peer manner and anonymously perform trade electronically. The vast number of decentralized transactions and the pseudo-anonymity of participants open the door for scams, cyber frauds, hacks, money laundering and fraudulent transactions. It is challenging to detect such fraudulent activities using traditional auditing techniques, since they need more processing power, time and memory for complex queries to join combinations of tables. This paper proposes several algorithms to extract the transaction- related features from the Bitcoin and Ethereum networks and to represent the features as graphs. Moreover, the paper discusses how visualisation of graphs can reflect the anomalies and patterns of fraudulent activities.

Internet of Things (IoT) enables the seamless integration of sensors, actuators, and communication devices for real-time applications. IoT systems require good quality sensor data in order to make real-time decisions. However, values are often missing from the sensor data collected owing to faulty sensors, a loss of data during communication, interference, and measurement errors. Considering the spatiotemporal nature of IoT data and the uncertainty of the data collected by sensors, we propose a new framework with which to impute missing values utilizing Bayesian maximum entropy (BME) as a convenient means to estimate the missing data from IoT applications. Missing sensor measurements adversely affect the quality of data, and consequently the performance and outcomes of IoT systems. Our proposed framework incorporates BME in order to impute missing values in diverse IoT scenarios by making use of the combination of low- and high-precision sensors. Our approach can incorporate the measurement errors of low-precision sensors as interval quantities along with the high-precision sensor measurements, making it highly suitable for real-time IoT systems. Our framework is robust to variations in data, requires less execution time, and requires only a single input parameter, thus outperforming existing IoT data imputation methods. The experimental results obtained for three IoT data sets demonstrate the superiority of the BME framework as regards accuracy, running time, and robustness. The framework can additionally be extended to distributed IoT nodes for the online imputation of missing values.

Online product reviews have become increasingly important in digital consumer markets where they play a crucial role in making purchasing decisions by most consumers. Unfortunately, spammers often take advantage of online reviews by writing fake reviews to promote/demote certain products. Most of the previous studies have focused on detecting fake reviews and individual fake reviewer-ids. However, to target a particular product, fake reviewers work collaboratively in groups and/or create multiple fake ids to write reviews and control the sentiments of the product. This article addresses the problem of finding such fake reviewer groups. More specifically, we propose a top-down framework for candidate fake reviewer groups’ detection based on the DeepWalk approach on reviewers’ graph data and a (modified) semisupervised clustering method, which can incorporate partial background knowledge. We validate our proposed framework on a real review dataset from the Google Play Store, which has partial ground-truth information about 2207 fraud reviewer-ids out of all 38 123 reviewer-ids in the dataset. Our experimental results demonstrate that the proposed approach is able to identify the candidate spammer groups with reasonable accuracy. The proposed approach can also be extended to detect groups of opinion spammers in social media (e.g. fake comments or fake postings) with temporal affinity, semantic characteristics, and sentiment analysis.

The widespread use of Internet-of-Things (IoT) technologies, smartphones, and social media services generates huge amounts of data streaming at high velocity. Automatic interpretation of these rapidly arriving data streams is required for the timely detection of interesting events that usually emerge in the form of clusters. This article proposes a new relative of the visual assessment of the cluster tendency (VAT) model, which produces a record of structural evolution in the data stream by building a cluster heat map of the entire processing history in the stream. The existing VAT-based algorithms for streaming data, called inc-VAT/inc-iVAT and dec-VAT/dec-iVAT, are not suitable for high-velocity and high-volume streaming data because of high memory requirements and slower processing speed as the accumulated data increases. The scalable iVAT (siVAT) algorithm can handle big batch data, but for streaming data, it needs to be (re)applied everytime a new datapoint arrives, which is not feasible due to the associated computation complexities. To address this problem, we propose an incremental siVAT algorithm, called inc-siVAT, which deals with the streaming data in chunks. It first extracts a small size smart sample using an intelligent sampling scheme, called maximin random sampling (MMRS), then incrementally updates the smart sample points on the fly, using our novel incremental MMRS (inc-MMRS) algorithm, to reflect changes in the data stream after each chunk is processed, and finally, produces an incrementally built iVAT image of the updated smart sample, using the inc-VAT/inc-iVAT and dec-VAT/dec-iVAT algorithms. These images can be used to visualize the evolving cluster structure and for anomaly detection in streaming data. Our method is illustrated with one synthetic and four real datasets, two of which evolve significantly over time. Our numerical experiments demonstrate the algorithm's ability to successfully identify anomalies and visualize changing cluster structure in streaming data.

Stroke survivors are often characterized by hemiparesis, i.e., paralysis in one half of the body, severely affecting upper limb movements. Monitoring the progression of hemiparesis requires manual observation of limb movements at regular intervals, and hence is a labour intensive process. In this work, we use wrist-worn accelerometers for automated assessment of hemiparesis in acute stroke. We propose novel measures of similarity and asymmetry in hand activities through bivariate Poincaré analysis between two-hand accelerometer data for quantifying hemiparetic severity. The proposed descriptors characterize the distribution of activity surrogates derived from acceleration of the two hands, on a 2D bivariate Poincaré Plot. Experiments show that while the descriptors CSD1 and CSD2 can identify hemiparetic patients from control subjects, their normalized difference CSDR and the descriptors Complex Cross-Correlation Measure ( C3M) and Activity Asymmetry Index ( AAI) can distinguish between mild, moderate and severe hemiparesis. These measures are compared with traditional measures of cross-correlation and evaluated against the National Institutes of Health Stroke Scale (NIHSS), the clinical gold standard for hemiparetic severity estimation. This study, undertaken on 40 acute stroke patients with varying levels of hemiparesis and 15 healthy controls, validates the use of short length ( 5 minutes) wearable accelerometry data for identifying hemiparesis with greater clinical sensitivity. Results show that the proposed descriptors with a hierarchical classification model outperform state-of-the-art methods with overall accuracy of 0.78 and 0.85 for 4-class and 3-class hemiparesis identification respectively.

Fog/Edge computing emerges as a novel computing paradigm that harnesses resources in the proximity of the Internet of Things (IoT) devices so that, alongside with the cloud servers, provide services in a timely manner. However, due to the ever-increasing growth of IoT devices with resource-hungry applications, fog/edge servers with limited resources cannot efficiently satisfy the requirements of the IoT applications. Therefore, the application placement in the fog/edge computing environment, in which several distributed fog/edge servers and centralized cloud servers are available, is a challenging issue. In this article, we propose a weighted cost model to minimize the execution time and energy consumption of IoT applications, in a computing environment with multiple IoT devices, multiple fog/edge servers and cloud servers. Besides, a new application placement technique based on the Memetic Algorithm is proposed to make batch application placement decision for concurrent IoT applications. Due to the heterogeneity of IoT applications, we also propose a lightweight pre-scheduling algorithm to maximize the number of parallel tasks for the concurrent execution. The performance results demonstrate that our technique significantly improves the weighted cost of IoT applications up to 65 percent in comparison to its counterparts.

A new support vector machine (SVM) variant, called CS++-SVM, is presented combining multiclass classification and anomaly detection in a single-step process to create a trained machine that can simultaneously classify test data belonging to classes represented in the training set and label as anomalous test data belonging to classes not represented in the training set. A theoretical analysis of the properties of the new method, showing how it combines properties inherited both from the conic-segmentation SVM (CS-SVM) and the $1$-class SVM (to which the method described reduces to in the case of unlabelled training data), is given. Finally, experimental results are presented to demonstrate the effectiveness of the algorithm for both simulated and real-world data.

Breathing rate (BR) is a significant bio marker that provides both prognostic and diagnostic information for monitoring physiological condition. In addition to vital bio markers, such as blood oxygen saturation and pulse rate, BR can be extracted from non-invasive and wearable pulse oximeter based photoplethysmogram (PPG). Empirical mode decomposition (EMD) and its noise-assisted variants are widely used for decomposing non-linear and non-stationary signals. In this work, the effect of all variants of EMD in extracting BR from PPG has been investigated. We have used an EMD family PCA based hybrid model in extracting BR from PPG, which is a natural extension of our previously developed ensemble EMD (EEMD) PCA hybrid model. The performance of each model has been tested using two different datasets: MIMIC and Capnobase. Median absolute error varied from 0 to 5.03 and from 2.47 to 10.55 breaths/min for MIMIC and Capnobase dataset, respectively. Among all the EMD variants, EEMD-PCA and improved complete EEMD with adaptive noise (ICEEMDAN) PCA hybrid model present better performance for both datasets. This is the first study to compare EMD variants performance for decomposing real world signal and determine that from current methods, ICEEMDAN and EEMD are optimal for estimating BR from PPG.

Dunn's internal cluster validity index is used to assess partition quality and subsequently identify a “best” crisp partition of n objects. Computing Dunn's index (DI) for partitions of n p-dimensional feature vector data has quadratic time complexity O(pn2), so its computation is impractical for very large values of n. This note presents six methods for approximating DI. Four methods are based on Maximin sampling, which identifies a skeleton of the full partition that contains some boundary points in each cluster. Two additional methods are presented that estimate boundary points associated with unsupervised training of one class support vector machines. Numerical examples compare approximations to DI based on all six methods. Four experiments on seven real and synthetic data sets support our assertion that computing approximations to DI with an incremental, neighborhood-based Maximin skeleton is both tractable and reliably accurate.

Real-time Internet of Things (IoT) applications have stringent delay requirements when implemented over distributed sensing and communication networks in smart traffic control. They require the system to reach a permissible neighbourhood of an optimum solution with a tolerable delay. The performance of such applications mostly depends on the delay introduced by the underlying optimization algorithms, with the localized computational capability. In this paper, we study a smart traffic control scenario-a real-time IoT application, where a group of autonomous vehicles independently decide on their lane velocities, in collaboration with road-side units to efficiently utilize intersections with minimal environmental impact. We decompose this problem as an unconstrained network utility maximization problem. A consensus-based, constant step-size gradient descent algorithm is proposed to obtain a near-optimal solution. We analyze the delay-accuracy tradeoff in reaching a near-optimal velocity. Delay is measured in terms of the number of iterations required before the scheduling operation can be done for a particular tolerance. The operation of the algorithm under quantized message passing is also studied. On contrary to the existing methods to intersection management problems, our approach studies the limit at which an optimization algorithm fails to cater for the requirements of a real-time application and must fall back for a pareto-optimal solution, due to the communication constraints. We used simulation of urban mobility to incorporate the microscopic behavior of traffic flows to our simulations and compared our solution with traditional and state-of-the-art intersection management techniques.

Trajectory prediction (TP) is of great importance for a wide range of location-based applications in intelligent transport systems, such as location-based advertising, route planning, traffic management, and early warning systems. In the last few years, the widespread use of GPS navigation systems and wireless communication technology enabled vehicles has resulted in huge volumes of trajectory data. The task of utilizing these data employing spatio-temporal techniques for TP in an efficient and accurate manner is an ongoing research problem. Existing TP approaches are limited to the short-term predictions. Moreover, they cannot handle a large volume of trajectory data for long-term prediction. To address these limitations, we propose a scalable clustering and Markov chain-based hybrid framework, called Traj-clusiVAT-based TP, for both short- and long-term TPs, which can handle a large number of overlapping trajectories in a dense road network. Traj-clusiVAT can also determine the number of clusters, which represent different movement behaviors in input trajectory data. In our experiments, we compare our proposed approach with a mixed Markov model-based scheme and a trajectory clustering, NETSCAN-based TP method for both short- and long-term TPs. We performed our experiments on two real, vehicle trajectory datasets, including a large-scale trajectory dataset consisting of 3.28 million trajectories obtained from 15 061 taxis in Singapore over a period of one month. The experimental results on two real trajectory datasets show that our proposed approach outperforms the existing approaches in terms of both short- and long-term prediction performances, based on the prediction accuracy and distance error (in km).

Clustering large volumes of high-dimensional data is a challenging task. Many clustering algorithms have been developed to address either handling datasets with a very large sample size or with a very high number of dimensions, but they are often impractical when the data is large in both aspects. To simultaneously overcome both the `curse of dimensionality' problem due to high dimensions and scalability problems due to large sample size, we propose a new fast clustering algorithm called FensiVAT. FensiVAT is a hybrid, ensemble-based clustering algorithm which uses fast data-space reduction and an intelligent sampling strategy. In addition to clustering, FensiVAT also provides visual evidence that is used to estimate the number of clusters (cluster tendency assessment) in the data. In our experiments, we compare FensiVAT with nine state-of-the-art approaches which are popular for large sample size or high-dimensional data clustering. Experimental results suggest that FensiVAT, which can cluster large volumes of high-dimensional datasets in a few seconds, is the fastest and most accurate method of the ones tested.

The problem of determining whether clusters are present in numerical data (tendency assessment) is an important first step of cluster analysis. One tool for cluster tendency assessment is the visual assessment of tendency (VAT) algorithm. VAT and improved VAT (iVAT) produce an image that provides visual evidence about the number of clusters to seek in the original dataset. These methods have been successful in determining potential cluster structure in various datasets, but they can be computationally expensive for datasets with a very large number of samples. A scalable version of iVAT called siVAT approximates iVAT images, but siVAT can be computationally expensive for big datasets. In this article, we introduce a modification of siVAT called siVAT+ which approximates cluster heat maps for large volumes of high dimensional data much more rapidly than siVAT. We compare siVAT+ with siVAT on six large, high dimensional datasets. Experimental results confirm that siVAT+ obtains images similar to siVAT images in a few seconds, and is 8 - 55 times faster than siVAT.

Dunn's internal cluster validity index and its generalizations assess partition quality. For partitions of n samples of p-dimensional feature vector data, all but two of the generalized Dunn's indices (GDIs) have quadratic time complexity O(pn2), so computation is untenable for very large values of n. In this paper, we present two methods for approximating GDIs based on Maximin (MM) Sampling. MM sampling identifies a skeleton of the full partition that usually contains some of the boundary points in each cluster which are used to compute GDIs. We compare our algorithms with a support vector machine based boundary extraction method and a random sampling based estimation method. Our experiments on four real and synthetic datasets show that computing approximations to (three) GDIs with the MM skeleton is both computationally tractable and reliably accurate.

Inliers (bridge points) between clusters degrade the ability of many algorithms to find clusters in numerical data. We present three new approaches to the detection and removal of inliers. Two approaches are based on Local Outlier Factor (LOF) scores. We also discuss using LOF scores for an isolation Nearest Neighbour Ensemble (iNNE) approach to inlier detection. The third approach uses MaxiMin (MM) sampling to remove both inliers and outliers. We compare the three approaches on a synthetic and two real-life datasets. The failure of single linkage clustering due to the existence of bridging points is used as a means for evaluating the relative effectiveness of the three methods. We also show how inliers can degrade the quality of images built by the improved Visual Assessment of Tendency (iVAT) algorithm, which provides a visual representation of potential single linkage clusters in the data.

Real-time environment monitoring and analysis is an important research area of Internet of Things (IoT). Understanding the behavior of the complex ecosystem requires analysis of detailed observations of an environment over a range of different conditions. One such example in urban areas includes the study of tree canopy cover over the microclimate environment using heterogeneous sensor data. There are several challenges that need to be addressed, such as obtaining reliable and detailed observations over monitoring area, detecting unusual events from data, and visualizing events in real-time in a way that is easily understandable by the end users (e.g., city councils). In this regard, we propose an integrated geovisualization framework, built for real-time wireless sensor network data on the synergy of computational intelligence and visual methods, to analyze complex patterns of urban microclimate. A Bayesian maximum entropy-based method and a hyperellipsoidal model-based algorithm have been build in our integrated framework to address above challenges. The proposed integrated framework was verified using the dataset from an indoor and two outdoor network of IoT devices deployed at two strategically selected locations in Melbourne, Australia. The data from these deployments are used for evaluation and demonstration of these components' functionality along with the designed interactive visualization components.

Random projection is a popular method for dimensionality reduction due to its simplicity and efficiency. In the past few years, random projection and fuzzy c-means based cluster ensemble approaches have been developed for high-dimensional data clustering. However, they require large amounts of space for storing a big affinity matrix, and incur large computation time while clustering in this affinity matrix. In this paper, we propose a new random projection, fuzzy c-means based cluster ensemble framework for high-dimensional data. Our framework uses cumulative agreement to aggregate fuzzy partitions. Fuzzy partitions of random projections are ranked using external and internal cluster validity indices. The best partition in the ranked queue is the core (or base) partition. Remaining partitions then provide cumulative inputs to the core, thus, arriving at a consensus best overall partition built from the ensemble. Experimental results with Gaussian mixture datasets and a variety of real datasets demonstrate that our approach outperforms three state-of-the-art methods in terms of accuracy and space-time complexity. Our algorithm runs one to two orders of magnitude faster than other state-of-the-arts algorithms.

For constrained end devices in Internet of Things, such as smart meters (SMs), data transmission is an energy-consuming operation. To address this problem, we propose an efficient and privacy-preserving aggregation system with the aid of Fog computing architecture, named PPFA, which enables the intermediate Fog nodes to periodically collect data from nearby SMs and accurately derive aggregate statistics as the fine-grained Fog level aggregation. The Cloud/utility supplier computes overall aggregate statistics by aggregating Fog level aggregation. To minimize the privacy leakage and mitigate the utility loss, we use more efficient and concentrated Gaussian mechanism to distribute noise generation among parties, thus offering provable differential privacy guarantees of the aggregate statistic on both Fog level and Cloud level. In addition, to ensure aggregator obliviousness and system robustness, we put forward a two-layer encryption scheme: the first layer applies OTP to encrypt individual noisy measurement to achieve aggregator obliviousness, while the second layer uses public-key cryptography for authentication purpose. Our scheme is simple, efficient, and practical, it requires only one round of data exchange among a SM, its connected Fog node and the Cloud if there are no node failures, otherwise, one extra round is needed between a meter, its connected Fog node, and the trusted third party.

The photoplethysmographic (PPG) signal measures the local variations of blood volume in tissues, reflecting the peripheral pulse modulated by cardiac activity, respiration, and other physiological effects. Therefore, PPG can be used to extract the vital cardiorespiratory signals like heart rate (HR), and respiratory rate (RR) and this will reduce the number of sensors connected to the patient's body for recording these vital signs. In this paper, we propose an algorithm based on ensemble empirical mode decomposition with principal component analysis (EEMD-PCA) as a novel approach to estimate HR and RR simultaneously from PPG signal. To examine the performance of the proposed algorithm, we used 310 (from 35 subjects) and 632 (from 42 subjects) epochs of simultaneously recorded electrocardiogram, PPG, and respiratory signal extracted from MIMIC (Physionet ATM data bank) and Capnobase database, respectively. Results of EEMD-PCA-based extraction of HR and RR from PPG signal showed that the median RMS error (1st and 3rd quartiles) obtained in MIMIC data set for RR was 0.89 (0, 1.78) breaths/min, for HR was 0.57 (0.30, 0.71) beats/min and in Capnobase data set it was 2.77 (0.50, 5.9) breaths/min and 0.69 (0.54, 1.10) beats/min for RR and HR, respectively. These results illustrated that the proposed EEMD-PCA approach is more accurate in estimating HR and RR than other existing methods. Efficient and reliable extraction of HR and RR from the pulse oximeter's PPG signal will help patients for monitoring HR and RR with low cost and less discomfort.

Clustering of large-scale vehicle trajectories is an important aspect for understanding urban traffic patterns, particularly for optimizing public transport routes and frequencies and improving the decisions made by authorities. Existing trajectory clustering schemes are not well suited to large numbers of trajectories in dense city road networks due to the difficulty in finding a representative distance measure between trajectories that can scale to very large datasets. In this paper, we propose a novel Dijkstra-based dynamic time warping distance measure, trajDTW between two trajectories, which is suitable for large numbers of overlapping trajectories in a dense road network as found in major cities around the world. We also propose a novel fast-clusiVAT algorithm that can suggest the number of clusters in a trajectory dataset and identify and visualize the trajectories belonging to each cluster. We conduct experiments on a large-scale taxi trajectory dataset consisting of 3.28 million trajectories obtained from the GPS traces of 15 061 taxis within Singapore over a period of one month. Our analysis finds 13 trajectory clusters spanning the major expressways of Singapore, each of which can be further divided into two sub-clusters based on the travel direction. For each cluster, we provide a time-based distribution of trajectories to yield insights into how urban mobility patterns change with the time of day. We compare the trajectory clusters obtained using our approach with those obtained using popular general and trajectory specific clustering frameworks: DBSCAN, OPTICS, NETSCAN, and NEAT. We demonstrate that the clusters obtained using our novel fast-clusiVAT framework are better than those obtained using other clustering schemes, evaluated based on two internal cluster validity measures: Dunn's and Silhouette indices. Moreover, our fast-clusiVAT algorithm achieves significant speedup over a comparable approach without loss of cluster quality.

The proliferation of wearable devices has contributed to the emergence of mobile crowdsensing, which leverages the power of the crowd to collect and report data to a third party for large-scale sensing and collaborative learning. However, since the third party may not be honest, privacy poses a major concern. In this paper, we address this concern with a two-stage privacy-preserving scheme called RG-RP: the first stage is designed to mitigate maximum a posteriori (MAP) estimation attacks by perturbing each participant's data through a nonlinear function called repeated Gompertz (RG); while the second stage aims to maintain accuracy and reduce transmission energy by projecting high-dimensional data to a lower dimension, using a row-orthogonal random projection (RP) matrix. The proposed RG-RP scheme delivers better recovery resistance to MAP estimation attacks than most state-of-the-art techniques on both synthetic and real-world datasets. For collaborative learning, we proposed a novel LSTM-CNN model combining the merits of Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). Our experiments on two representative movement datasets captured by wearable sensors demonstrate that the proposed LSTM-CNN model outperforms standalone LSTM, CNN and Deep Belief Network. Together, RG+RP and LSTM-CNN provide a privacy-preserving collaborative learning framework that is both accurate and privacy-preserving.

The existence of large volumes of time series data in many applications has motivated data miners to investigate specialized methods for mining time series data. Clustering is a popular data mining method due to its powerful exploratory nature and its usefulness as a preprocessing step for other data mining techniques. This article develops two novel clustering algorithms for time series data that are extensions of a crisp c-shapes algorithm. The two new algorithms are heuristic derivatives of fuzzy c-means (FCM). Fuzzy c-Shapes plus (FCS+) replaces the inner product norm in the FCM model with a shape-based distance function. Fuzzy c-Shapes double plus (FCS++) uses the shape-based distance, and also replaces the FCM cluster centers with shape-extracted prototypes. Numerical experiments on 48 real time series data sets show that the two new algorithms outperform state-of-the-art shape-based clustering algorithms in terms of accuracy and efficiency. Four external cluster validity indices (the Rand index, Adjusted Rand Index, Variation of Information, and Normalized Mutual Information) are used to match candidate partitions generated by each of the studied algorithms. All four indices agree that for these finite waveform data sets, FCS++ gives a small improvement over FCS+, and in turn, FCS+ is better than the original crisp c-shapes method. Finally, we apply two tests of statistical significance to the three algorithms. The Wilcoxon and Friedman statistics both rank the three algorithms in exactly the same way as the four cluster validity indices.

One of the most crucial tasks for utility companies is load forecasting in order to plan future demand for generation capacity and infrastructure. Improving load forecasting accuracy over a short period is a challenging open problem due to the variety of factors that influence the load, and the volume of data that needs to be considered. This paper proposes a new approach for short term load forecasting using an effective new combination of clustering and deep learning methods, along with a new weighted aggregation mechanism. Our evaluation using smart meter data from a publicly available real-life dataset demonstrates the improved accuracy of our approach over existing methods.

Anomaly detection is important for time-critical Internet of Things (IoT) applications, such as healthcare and emergency management. The recent introduction of Fog computing architecture provides an efficient platform for delay sensitive IoT applications. Exploiting the advantages of Fog computing for anomaly detection provides the ability to detect abnormal patterns in an accurate and timely manner. Use of Centralized and Distributed anomaly detection methods suffer from significant latency and energy consumption issues. Hence, we propose a novel anomaly detection method, called Fog-Empowered anomaly detection, by harnessing the processing power of the Fog computing platform and using an efficient hyperellipsoidal clustering algorithm. The end nodes in the Fog computing architecture do not perform any processing or clustering on the data. The Fog layer and the Cloud layer nodes perform the clustering and anomaly detection process, thus helping to achieve anomaly detection in a timely manner. The evaluation using synthetic and real datasets demonstrates that our proposed approach achieves a significant reduction in latency and energy consumption compared to the Distributed and Centralized schemes, while achieving a comparable detection accuracy compared to a Centralized scheme.

Multi-hop over-the-air reprogramming is essential for remote installation of software patches and upgrades in wireless sensor networks (WSNs). Several recent coding-based reprogramming protocols have been proposed to enable efficient code dissemination in high packet loss environments. An accurate and formal analysis of the performance of these protocols, however, has not been studied sufficiently in the literature. In this paper, we present a novel high-fidelity analytical model based on the shortest path algorithm to measure the completion time by incorporating overhearing and packet coding. This model can be applied to any coding-based reprogramming protocol by substituting the coding part with protocol specific operations. We conduct extensive testbed experiments to evaluate the performance of our proposed model. Based on the analytical and numerical experiments, we find that 1) overhearing causes significant reduction of the completion time in dense wireless sensor networks, particularly, it reduces 50-70 percent of the total completion time when the packet reception rate is 0.896; 2) coding delay plays a key role in the total completion time compared to the communication delay when the packet coding parameters are selected appropriately, for example, the communication delay is about 65 percent of the coding delay when the number of packets per page is 16 for the finite field size 28; 3) the total completion time can be minimized when the number of packets per page is close to 24 and the finite field size is close to 24.

With the advancement in the Internet of Things (IoT) technologies, variety of sensors including inexpensive, low-precision sensors with sufficient computing and communication capabilities are increasingly deployed for monitoring large geographical areas. One of the problems with the use of inexpensive sensors is that they often suffer from random or systematic errors such as drift. The sensor drift is the result of slow changes that occur in the measurement driven by aging, loss of calibration, and changes in the phenomena being monitored over a time period. These drifting sensors need to be calibrated automatically for continuous and reliable monitoring. Existing methods for drift detection and correction do not consider the measurement errors or uncertainties present in those inexpensive low-precision sensors, hence, resulting in unreliable drift estimates. In this article, we propose a novel framework to automatically detect and correct the drifts by employing Bayesian Maximum Entropy (BME) and Kalman filtering (KF) techniques. The BME method is a spatiotemporal estimation method that incorporates the measurement errors of low-precision sensors as interval quantities along with the high-precision sensor measurements in their computations. Our scheme can be implemented in a centralized as well as in a distributed manner to detect and correct the drift generated in the sensors. For the centralized scheme, we compare several Kriging-based estimation techniques in combination with KF, and show the superiority of our proposed BME-based method in detecting and correcting the drift. We also propose a multivariate BME framework for drift detection, in which multiple features can be used to improve the drift estimates. To demonstrate the applicability of our distributed approach on a real-world application scenario, we implemented our algorithm on each wireless sensor node in order to perform in-network drift detection. The evaluation on real IoT datasets gathered from an indoor and an outdoor deployments reveal the superiority of our method in correctly identifying and correcting the drifts that develop in the sensors, in real time, compared to the existing approaches in the literature.

Vision is one of the most advanced and important sensory input in humans. However, many people have vision problems due to birth defects, uncorrected errors, work nature, accidents, and aging. The white cane and guide dog are the most widely used means of navigation for the vision-impaired. With advancements in technology, electronic devices have been created using different sensors and technologies to help navigate the blind. Electronic Travel Aids (ETAs) assist in navigating a person by collecting information about the environment and relaying this information in a form that allows a blind or vision-impaired person to understand the nature of the environment. However, there is still a lack of devices to detect potholes and uneven pavements, which inhibits mobility after dark. This pilot study proposes a computer vision based pothole and uneven surface detection approach to assist blind people in meeting their mobility needs. The system includes projecting laser patterns, recording the patterns through a monocular video, analyzing the patterns to extract features and then providing path cues for the blind user. With over 90% accuracy in detecting potholes, the proposed system aims to assist blind people in real-time navigation.

Clustering of a large amount of taxi GPS mobility data helps to understand the spatio-temporal dynamics for the applications of urban planning and transportation. In this paper we cluster the origin-destination pairs of the passenger taxi rides to provide useful insight into the city mobility patterns, urban hot-spots, road network usage and general patterns of the crowd movement within the city of Singapore. We perform experiments on a large scale Singapore taxi dataset consisting of more than 10 million passenger origin-destination GPS points. We use the clusi VAT sampling scheme to obtain the sample trips which return coarse clusters describing the major crowd movement and reduce the data points that are not captured by the coarse clusters and may bring in noises during fine-grained clustering. After the sampling step we use the well known density based clustering algorithm DBSCAN to find cluster structure in the sampled data points and later extend it to the rest of the dataset using nearest prototype rule. We report 24 trip clusters from the dataset which are compact enough to draw meaningful conclusions about the city mobility patterns and the number of trips in each cluster is large enough to be representative of the general traffic movement.

Clustering of big data has received much attention recently. In this paper, we present a new clusiVAT algorithm and compare it with four other popular data clustering algorithms. Three of the four comparison methods are based on the well known, classical batch k -means model. Specifically, we use k -means, single pass k -means, online k -means, and clustering using representatives (CURE) for numerical comparisons. clusiVAT is based on sampling the data, imaging the reordered distance matrix to estimate the number of clusters in the data visually, clustering the samples using a relative of single linkage (SL), and then noniteratively extending the labels to the rest of the data-set using the nearest prototype rule. Previous work has established that clusiVAT produces true SL clusters in compact-separated data. We have performed experiments to show that k -means and its modified algorithms suffer from initialization issues that cause many failures. On the other hand, clusiVAT needs no initialization, and almost always finds partitions that accurately match ground truth labels in labeled data. CURE also finds SL type partitions but is much slower than the other four algorithms. In our experiments, clusiVAT proves to be the fastest and most accurate of the five algorithms; e.g., it recovers 97% of the ground truth labels in the real world KDD-99 cup data (4 292 637 samples in 41 dimensions) in 76 s.

Analyzing crowd events in a video is key to understanding the behavioral characteristics of people (humans). Detecting crowd events in videos is challenging because of articulated human movements and occlusions. The aim of this paper is to detect the events in a probabilistic framework for automatically interpreting the visual crowd behavior. In this paper, crowd event detection and classification in optical flow manifolds (OFMs) are addressed. A new algorithm to detect walking and running events has been proposed, which uses optical flow vector lengths in OFMs. Furthermore, a new algorithm to detect merging and splitting events has been proposed, which uses Riemannian connections in the optical flow bundle (OFB). The longest vector from the OFB provides a key feature for distinguishing walking and running events. Using a Riemannian connection, the optical flow vectors are parallel transported to localize the crowd groups. The geodesic lengths among the groups provide a criterion for merging and splitting events. Dispersion and evacuation events are jointly modeled from the walking/running and merging/splitting events. Our results show that the proposed approach delivers a comparable model to detect crowd events. Using the performance evaluation of tracking and surveillance 2009 dataset, the proposed method is shown to produce the best results in merging, splitting, and dispersion events, and comparable results in walking, running, and evacuation events when compared with other methods.

Epilepsy is one of the most common neurological disorders and patients suffer from unprovoked seizures. In contrast, psychogenic nonepileptic seizures (PNES) are another class of seizures that are involuntary events not caused by abnormal electrical discharges but are a manifestation of psychological distress. The similarity of these two types of seizures poses diagnostic challenges that often leads in delayed diagnosis of PNES. Further, the diagnosis of PNES involves high-cost hospital admission and monitoring using video-electroencephalogram machines. A wearable device that can monitor the patient in natural setting is a desired solution for diagnosis of convulsive PNES. A wearable device with an accelerometer sensor is proposed as a new solution in the detection and diagnosis of PNES. The seizure detection algorithm and PNES classification algorithm are developed. The developed algorithms are tested on data collected from convulsive epileptic patients. A very high seizure detection rate is achieved with 100% sensitivity and few false alarms. A leave-one-out error of 6.67% is achieved in PNES classification, demonstrating the usefulness of wearable device in the diagnosis of PNES.

In this study, a linear parametric modeling technique was applied to model ventricular repolarization (VR) dynamics. Three features were selected from the surface ECG recordings to investigate the changes in VR dynamics in healthy and cardiac autonomic neuropathy (CAN) participants with diabetes including heart rate variability (calculated from RR intervals), repolarization variability (calculated from QT intervals), and respiration [calculated by ECG-derived respiration (EDR)]. Surface ECGs were recorded in a supine resting position from 80 age-matched participants (40 with no cardiac autonomic neuropathy (NCAN) and 40 with CAN). In the CAN group, 25 participants had early/subclinical CAN (ECAN) and 15 participants were identified with definite/clinical CAN (DCAN). Detecting subclinical CAN is crucial for designing an effective treatment plan to prevent further cardiovascular complications. For CAN diagnosis, VR dynamics was analyzed using linear parametric autoregressive bivariate (ARXAR) and trivariate (ARXXAR) models, which were estimated using 250 beats of derived QT, RR, and EDR time series extracted from the first 5 min of the recorded ECG signal. Results showed that the EDR-based models gave a significantly higher fitting value (p < 0.0001) than models without EDR, which indicates that QT-RR dynamics is better explained by respiratory-information-based models. Moreover, the QT-RR-EDR model fitting values gradually decreased from the NCAN group to ECAN and DCAN groups, which indicate a decoupling of QT from RR and the respiration signal with the increase in severity of CAN. In this study, only the EDR-based model significantly distinguished ECAN and DCAN groups from the NCAN group (p < 0.05) with large effect sizes (Cohen's d > 0.75) showing the effectiveness of this modeling technique in detecting subclinical CAN. In conclusion, the EDR-based trivariate QT-RR-EDR model was found to be better in detecting the presence and severity of CAN than the bivariate QT-RR model. This finding also establishes the importance of adding respiratory information for analyzing the gradual deterioration of normal VR dynamics in pathological conditions, such as diabetic CAN.

Electromechanical coupling of the fetal heart can be evaluated noninvasively using doppler ultrasound (DUS) signal and fetal electrocardiography (fECG). In this study, an efficient model is proposed using K-means clustering and hybrid Support Vector Machine-Hidden Markov Model (SVM-HMM) modeling techniques. Opening and closing of the cardiac valves were detected from peaks in the high frequency component of the DUS signal decomposed by wavelet analysis. It was previously proposed to automatically identify the valve motion by hybrid SVM-HMM based on the amplitude and timing of the peaks. However, in the present study, six patterns were identified for the DUS components which were actually variable on a beat-to-beat basis and found to be different for the early gestation (16-32 weeks), compared to the late gestation fetuses (36-41 weeks). The amplitude of the peaks linked to the valve motion was different across the six patterns and this affected the precision of valve motion identification by the previous hybrid SVM-HMM method. Therefore in the present study, clustering of the DUS components based on K-means was proposed and the hybrid SVM-HMM was trained for each cluster separately. The valve motion events were consequently identified more efficiently by beat-to-beat attribution of the DUS component peaks. Applying this method, more than 98.6% of valve motion events were beat-to-beat identified with average precision and recall of 83.4% and 84.2% respectively. It was an improvement compared to the hybrid method without clustering with average precision and recall of 79.0% and 79.8%. Therefore, this model would be useful for reliable screening of fetal wellbeing.

Angiotensin converting enzyme (ACE) polymorphism has been shown to be important in hypertension progression and also in diabetes complications, especially associated with heart disease. Heart rate variability (HRV) is an established measure for classification of autonomic function regulating heart rate, based on the interbeat interval time series derived from a raw ECG recording. Results of this paper show that the length (number of interbeat intervals) and preprocessing of the tachogram affect the HRV analysis outcome. The comparison was based on tachogram lengths of 250, 300, 350, and 400 RR-intervals and five preprocessing approaches. An automated adaptive preprocessing method for the heart rate biosignal and tachogram length of 400 interbeat intervals provided the best classification. HRV results differed for the Type 2 Diabetes Mellitus (T2DM) group between the I/I genotype and the I/D and D/D genotypes, whereas for controls there was no significant difference in HRV between genotypes. Selecting an appropriate length of recording and automated preprocessing has confirmed that there is an effect of ACE polymorphism including the I/I genotype and that I/I should not be combined with I/D genotype in determining the extent of autonomic modulation of the heart rate.

The growth in pervasive network infrastructure called the Internet of Things (IoT) enables a wide range of physical objects and environments to be monitored in fine spatial and temporal detail. The detailed, dynamic data that are collected in large quantities from sensor devices provide the basis for a variety of applications. Automatic interpretation of these evolving large data is required for timely detection of interesting events. This article develops and exemplifies two new relatives of the visual assessment of tendency (VAT) and improved visual assessment of tendency (iVAT) models, which uses cluster heat maps to visualize structure in static datasets. One new model is initialized with a static VAT/iVAT image, and then incrementally (hence inc-VAT/inc-iVAT) updates the current minimal spanning tree (MST) used by VAT with an efficient edge insertion scheme. Similarly, dec-VAT/dec-iVAT efficiently removes a node from the current VAT MST. A sequence of inc-iVAT/dec-iVAT images can be used for (visual) anomaly detection in evolving data streams and for sliding window based cluster assessment for time series data. The method is illustrated with four real datasets (three of them being smart city IoT data). The evaluation demonstrates the algorithms’ ability to successfully isolate anomalies and visualize changing cluster structure in the streaming data.

The iVAT (asiVAT) algorithms reorder symmetric (asymmetric) dissimilarity data so that an image of the data may reveal cluster substructure. Images formed from incomplete data don't offer a very rich interpretation of cluster structure. In this paper, we examine four methods for completing the input data with imputed values before imaging. We choose a best method using contaminated versions of the complete Iris data, for which the desired results are known. Then, we analyze two real world data sets from social networks that are incomplete using the best imputation method chosen in the juried trials with Iris: (i) Sampson's monastery data, an incomplete, asymmetric relation matrix; and (ii) the karate club data, comprising a symmetric similarity matrix that is about 86 percent incomplete.

Cognitive radio (CR) provides the ability to sense the range of frequencies (spectrum) that are not utilized by the incumbent user (primary user) and to opportunistically use the unoccupied spectrum in a heterogeneous environment. This can use a collaborative spectrum sensing approach to detect the spectrum holes. However, this nature of the collaborative mechanism is vulnerable to security attacks and faulty observations communicated by the opportunistic users (secondary users). Detecting such malicious users in CR networks is challenging as the pattern of malicious behavior is unknown apriori. In this paper we present an unsupervised approach to detect those malicious users, utilizing the pattern of their historic behavior. Our evaluation reveals that the proposed scheme effectively detects the malicious data in the system and provides a robust framework for CR to operate in this environment.

Evolvable Takagi-Sugeno (T-S) models are fuzzy-rule-based models with the ability to continuously learn and adapt to incoming samples from data streams. The model adjusts both premise and consequent parameters to enhance the performance of the model. This paper introduces a new methodology for the estimation of the premise parameters in the evolvable T-S (eTS) model. Incremental updates for the weighted sample mean and inverse of the covariance matrix enable us to construct an evolvable fuzzy rule base that is used to detect outliers and regime changes in the input stream. We compare our model with Angelov's eTS+ model with artificial and real data.

Wireless sensor networks are often deployed in large numbers, over a large geographical region, in order to monitor the phenomena of interest. Sensors used in the sensor networks often suffer from random or systematic errors such as drift and bias. Even if they are calibrated at the time of deployment, they tend to drift as time progresses. Consequently, the progressive manual calibration of such a large-scale sensor network becomes impossible in practice. In this article, we address this challenge by proposing a collaborative framework to automatically detect and correct the drift in order to keep the data collected from these networks reliable. We propose a novel scheme that uses geospatial estimation-based interpolation techniques on measurements from neighboring sensors to collaboratively predict the value of phenomenon being observed. The predicted values are then used iteratively to correct the sensor drift by means of a Kalman filter. Our scheme can be implemented in a centralized as well as distributed manner to detect and correct the drift generated in the sensors. For centralized implementation of our scheme, we compare several kriging- and nonkriging-based geospatial estimation techniques in combination with the Kalman filter, and show the superiority of the kriging-based methods in detecting and correcting the drift. To demonstrate the applicability of our distributed approach on a real world application scenario, we implement our algorithm on a network consisting of Wireless Sensor Network (WSN) hardware. We further evaluate single as well as multiple drifting sensor scenarios to show the effectiveness of our algorithm for detecting and correcting drift. Further, we address the issue of high power usage for data transmission among neighboring nodes leading to low network lifetime for the distributed approach by proposing two power saving schemes. Moreover, we compare our algorithm with a blind calibration scheme in the literature and demonstrate its superiority in detecting both linear and nonlinear drifts.

Large scale monitoring applications require large numbers of sensors deployed in a region for accurate and high resolution spatio-temporal measurements and estimation. This can be achieved practically by deploying a mix of high capacity, high precision, expensive and low capacity, low precision, cheap sensors in the monitored region. However, the resource constrained nature of low-capacity sensors, and the availability of limited numbers of high-capacity sensors are a challenge to achieving highly accurate estimations. In this paper we propose a framework combining Bayesian compressive sensing and a robust Bayesian maximum entropy based spatio-temporal estimation technique to address this important problem. Evaluation on real wireless sensor network data reveals the trade-off between the spatio-temporal estimation accuracy and the communication overhead incurred in the network, and provides a mechanism to choose the right compressive ratios, such that a given estimation accuracy is achieved for a known communication overhead in the network.

Abstract Surface electromyogram (sEMG) is a technique in which electrodes are placed on the skin overlying a muscle to detect the electrical activity. Multiple electrical sensors are essential for extracting intrinsic physiological and contextual information from the corresponding sEMG signals. The reason, why more than just one sEMG signal capture has to be used, is as follows: Due to signal propagation inside the human body in terms of an electrical conductor, there cannot be a one‐to‐one mapping of activities between muscle fibre groups and corresponding sEMG sensing electrodes. Each of such electrodes rather records a composition of many, and widely activity‐independent signals, and such kind of raw signal capture cannot be efficiently used for pattern matching due to its linear dependency. On the other hand, Independent component analysis (ICA) provides the perfect answer of separating skin surface recordings into a set of independent muscle actions. Hence, there is a need for a method that indicates the quality of the sensor placements in sEMG. The purpose of this paper is to describe the use of source separation for sEMG using ICA. The actual use in practical sEMG experiments is demonstrated, when the number of recording channels for electrical muscle activities is varied.

Increasing population density in urban centers demands adequate provision of services and infrastructure to meet the needs of city inhabitants, encompassing residents, workers, and visitors. The utilization of information and communications technologies to achieve this objective presents an opportunity for the development of smart cities, where city management and citizens are given access to a wealth of real-time information about the urban environment upon which to base decisions, actions, and future planning. This paper presents a framework for the realization of smart cities through the Internet of Things (IoT). The framework encompasses the complete urban information system, from the sensory level and networking support structure through to data management and Cloud-based integration of respective systems and services, and forms a transformational part of the existing cyber-physical system. This IoT vision for a smart city is applied to a noise mapping case study to illustrate a new method for existing operations that can be adapted for the enhancement and delivery of important city services.

Increased levels of particulate matter (PM) in the atmosphere have contributed to an increase in mortality and morbidity in communities and are the main contributing factor for respiratory health problems in the population. Currently, PM concentrations are sparsely monitored; for instance, a region of over 2200 square kilometers surrounding Melbourne in Victoria, Australia, is monitored using ten sensor stations. This paper proposes to improve the estimation of PM concentration by complementing the existing high-precision but expensive PM devices with low-cost lower precision PM sensor nodes. Our evaluation reveals that local PM estimation accuracies improve with higher densities of low-precision sensor nodes. Our analysis examines the impact of the precision of the lost-cost sensors on the overall estimation accuracy.

Respiratory events during sleep induce cortical arousals and manifest changes in autonomic markers in sleep disorder breathing (SDB). Finger photoplethysmography (PPG) has been shown to be a reliable method of determining sympathetic activation. We hypothesize that changes in PPG signals are sufficient to predict the occurrence of respiratory-event-related cortical arousal. In this study, we develop a respiratory arousal detection model in SDB subjects by using PPG features. PPG signals from 10 SDB subjects (9 male, 1 female) with age range 43-75 years were used in this study. Time domain features of PPG signals, such as 1) PWA--pulse wave amplitude, 2) PPI--peak-to-peak interval, and 3) Area--area under peak, were used to detect arousal events. In this study, PWA and Area have shown better performance (higher accuracy and lower false rate) compared to PPI features. After investigating possible groupings of these features, combination of PWA and Area (PWA + Area) was shown to provide better accuracy with a lower false detection rate in arousal detection. PPG-based arousal indexes agreed well across a wide range of decision thresholds, resulting in a receiver operating characteristic with an area under the curve of 0.91. For the decision threshold (PC(thresh) = 25%) chosen for the final analyses, a sensitivity of 68.1% and a specificity of 95.2% were obtained. The results showed an accuracy of 84.68%, 85.15%, 86.93%, and 50.79% with a false rate of 21.80%, 55.41%, 64.78%, and 50.79% at PC(thresh) = 25% or PPI, PWA, Area , and PWA + Area features, respectively. This indicates that combining PWA and Area features reduced the false positive rate without much affecting the sensitivity of the arousal detection system. In conclusion, the PPG-based respiratory arousal detection model is a simple and promising alternative to the conventional electroencephalogram (EEG)-based respiratory arousal detection system.

In this paper, a new noninvasive method is proposed for automated estimation of fetal cardiac intervals from Doppler Ultrasound (DUS) signal. This method is based on a novel combination of empirical mode decomposition (EMD) and hybrid support vector machines-hidden Markov models (SVM/HMM). EMD was used for feature extraction by decomposing the DUS signal into different components (IMFs), one of which is linked to the cardiac valve motions, i.e. opening (o) and closing (c) of the Aortic (A) and Mitral (M) valves. The noninvasive fetal electrocardiogram (fECG) was used as a reference for the segmentation of the IMF into cardiac cycles. The hybrid SVM/HMM was then applied to identify the cardiac events, based on the amplitude and timing of the IMF peaks as well as the sequence of the events. The estimated timings were verified using pulsed doppler images. Results show that this automated method can continuously evaluate beat-to-beat valve motion timings and identify more than 91% of total events which is higher than previous methods. Moreover, the changes of the cardiac intervals were analyzed for three fetal age groups: 16-29, 30-35, and 36-41 weeks. The time intervals from Q-wave of fECG to Ac (Systolic Time Interval, STI), Ac to Mo (Isovolumic Relaxation Time, IRT), Q-wave to Ao (Preejection Period, PEP) and Ao to Ac (Ventricular Ejection Time, VET) were found to change significantly ( ) across these age groups. In particular, STI, IRT, and PEP of the fetuses with 36-41 week were significantly ( ) different from other age groups. These findings can be used as sensitive markers for evaluating the fetal cardiac performance.

ABSTRACT Two new incremental models for online anomaly detection in data streams at nodes inwireless sensor networksare discussed. These models are incremental versions of a model that uses ellipsoids to detect first, second, and higher‐ordered anomaliesin arrears. The incremental versions can also be used this way but have additional capabilities offered by processing data incrementally as they arrive in time. Specifically, they can detect anomalies ‘on‐the‐fly’ in near real time. They can also be used to track temporal changes in near real‐time because of sensor drift, cyclic variation, or seasonal changes. One of the new models has a mechanism that enables graceful degradation of inputs in the distant past (fading memory). Three real datasets from single sensors in deployed environmental monitoring networks are used to illustrate various facets of the new models. Examples compare the incremental version with the previous batch and dynamic models and show that the incremental versions can detect various types of dynamic anomalies in near real time. Copyright © 2012 John Wiley & Sons, Ltd.

Recent algorithmic and computational improvements have reduced the time it takes to build a minimal spanning tree (MST) for big data sets. In this paper we compare single linkage clustering based on MSTs built with the Filter-Kruskal method to the proposed clusiVAT algorithm, which is based on sampling the data, imaging the sample to estimate the number of clusters, followed by non-iterative extension of the labels to the rest of the big data with the nearest prototype rule. Numerical experiments with both synthetic and real data confirm the theory that clusiVAT produces true single linkage clusters in compact, separated data. We also show that single linkage fails, while clusiVAT finds high quality partitions that match ground truth labels very well. And clusiVAT is fast: it recovers the preferred c = 3 Gaussian clusters in a mixture of 1 million two-dimensional data points with 100% accuracy in 3.1 seconds.

Multicasting refers to the transmission of a message to multiple receivers at the same time. To enable authentication of sporadic multicast messages, a conventional digital signature scheme is appropriate. To enable authentication of a multicast data stream, however, an authenticated multicast or multicast authentication (MA) scheme is necessary. An MA scheme can be constructed from a conventional digital signature scheme or a multiple-time signature (MTS) scheme. A number of MTS-based MA schemes have been proposed over the years. Here, we formally analyze four MA schemes, namely BiBa, TV-HORS, SCU+ and TSV+. Among these MA schemes, SCU+ is an MA scheme we constructed from an MTS scheme designed for secure code update, and TSV+ is our patched version of TSV, an MA scheme which we show to be vulnerable. Based on our simulation-validated analysis, which complements and at places rectifies or improves existing analyses, we compare the schemes' computational and communication efficiencies relative to their security levels. For numerical comparison of the schemes, we use parameters relevant for a smart (power) grid component called wide-area measurement system. Our comparison shows that TV-HORS, while algorithmically unsophisticated and not the best performer in all categories, is the most balanced performer. SCU+, TSV+ and by implication the schemes from which they are extended do not offer clear advantages over BiBa, the oldest among the schemes.

The sustainable management of coastal and offshore ecosystems, such as for example coral reef environments, requires an energy efficient collection of accurate data across various temporal and spatial scales. To suitably address the energy supply of marine sensors, in this paper a novel energy harvesting device is proposed, based on a Tubular Permanent MagnetLinear Generator (TPM-LiG). The application is related to the sea wave energy conversion for small sensorized buoy. The optimization process is developed by means of evolutionary computation techniques. The advantage of these algorithms is in the wide exploration of the variables space and in the effective exploitation of the fitness function. The algorithm has been tested on a benchmark case and then applied to the optimization of a power-buoy prototype which has been realized in laboratory with potential significant implications in future marine environment applications.

Internet-of-Things (IoT) is a concept referring to interconnected people and objects and smart city is one of the many applications of IoT. Wireless Sensor Network (WSN) is a specific technology that helps to create “Smart Cities”. It aims at creating a distributed network of intelligent sensor nodes which can measure various parameters for efficient management of the city. The data thus collected through a range of sensors is processed and is delivered wirelessly in real-time to the citizens or the appropriate authorities. Since the application framework for smart city application is huge, it would require a large number of different types of sensors for its implementation and the project could be viable only if we use low resolution, low precision but inexpensive sensors. The sensors in sensor network can suffer from random or systematic errors. Most common problem with inexpensive sensors used in WSNs for smart city applications is of drift and bias. They can be calibrated at the time of deployment, but they develop drift, which is the slow change in the reading of sensor from actual value as time progresses. In this paper we have proposed a framework to automatically detect and correct the drift of the sensor nodes to keep the WSN usable. Kriging based interpolation of the sensor readings of neighboring sensors is used to predict actual value at the sensor node and the measured drift is then kalman filtered to get correct drift estimates. We have demonstrated the results of this algorithm on real sensor data obtained from Intel Research Berkeley Laboratory deployment and shown that our system is able to detect and correct smooth drift and bias generated in the sensors. We have also shown that our system is robust with respect to the number of sensor nodes drifting and significantly outperforms the traditional averaging based interpolation methods.

We discuss a new formulation of a fuzzy validity index that generalizes the Newman-Girvan (NG) modularity function. The NG function serves as a cluster validity functional in community detection studies. The input data is an undirected graph G = (V, E) that represents a social network. Clusters in V correspond to socially similar substructures in the network. We compare our fuzzy modularity to an existing modularity function using the well-studied Karate Club data set.

The iVAT algorithm reorders (symmetric) dissimilarity data so that an image of the data may reveal cluster substructure. This paper extends the method so that it can handle asymmetric dissimilarity data. The extension is based on replacing the asymmetric input data with its unique least-squared error approximation by a symmetric matrix. Examples are given to illustrate the new method, called asymmetric iVAT (asiVAT).

Multi-hop over-the-air reprogramming is essential for the remote installation of software patches and upgrades in wireless sensor networks (WSNs). Recently, coding-based reprogramming protocols are proposed to address efficient code dissemination in environments with high packet loss rate. The problem of analyzing the performance of these protocols, however, has not been explored in the literature. In this paper, we present a high-fidelity analytical model based on Dijkstra's shortest path algorithm to measure the completion time of coding-based reprogramming protocols. Our model takes into account not only page pipelining and negotiation, but also coding computation. Results from extensive simulations of a representative coding-based reprogramming protocol called Rateless Deluge are in good agreement with the performance predicted by our model, thus validating our approach. Our analytical results show both the number of packets per page and the finite field size have significant impact on completion time. Most notably, the time overhead of coding computation exceeds that of communication when the number of packets per page is 24 and the finite field size is at least 24.

It is essential for any highly trained cyclist to optimize his pedalling movement in order to maximize the performance and minimize the risk of injuries. Current techniques rely on bicycle fitting and off-line laboratory measurements. These techniques do not allow the assessment of the kinematics of the cyclist during training and competition, when fatigue may alter the ability of the cyclist to apply forces to the pedals and thus induce maladaptive joint loading. We propose a radically different approach that focuses on determining the actual status of the cyclist’s lower limb segments in real-time and real-life conditions. Our solution is based on body area wireless motion sensor nodes that can collaboratively process the sensory information and provide the cyclists with immediate feedback about their pedalling movement. In this paper, we present a thorough study of the accuracy of our system with respect to the gold standard motion capture system. We measure the knee and ankle angles, which influence the performance as well as the risk of overuse injuries during cycling. The results obtained from a series of experiments with nine subjects show that the motion sensors are within 2.2° to 6.4° from the reference given by the motion capture system, with a correlation coefficient above 0.9. The wireless characteristics of our system, the energy expenditure, possible improvements and usability aspects are further analysed and discussed.

We discuss a new formulation of a fuzzy validity index that generalizes the Newman-Girvan (NG) modularity function. The NG function serves as a cluster validity functional in community detection studies. The input data is an undirected weighted graph that represents, e.g., a social network. Clusters correspond to socially similar substructures in the network. We compare our fuzzy modularity with two existing modularity functions using the well-studied Karate Club and American College Football datasets.

This paper presents cluster validity for kernel fuzzy clustering. First, we describe existing cluster validity indices that can be directly applied to partitions obtained by kernel fuzzy clustering algorithms. Second, we show how validity indices that take dissimilarity (or relational) data D as input can be applied to kernel fuzzy clustering. Third, we present four propositions that allow other existing cluster validity indices to be adapted to kernel fuzzy partitions. As an example of how these propositions are used, five well-known indices are formulated.We demonstrate several indices for kernel fuzzy c-means (kFCM) partitions of both synthetic and real data.

One of the applications that motivates this research is a system for detection of the anomalies in wireless sensor networks (WSNs). Individual sensor measurements are converted to ellipsoidal summaries; a data matrix D is built using a dissimilarity measure between pairs of ellipsoids; clusters of ellipsoids are suggested by dark blocks along the diagonal of an iVAT (improved Visual Assessment of Tendency) image of D; and finally, the single linkage algorithm extracts clusters from D, using the iVAT image as a guide to the selection of an optimal partition. We illustrate this model for higher dimensional data with synthetic, real and benchmark data sets. Our examples show that two of the four measures, viz, Focal distance and Bhattacharyya distance, provide very similar and reliable bases for estimating cluster structures in sets of higher dimensional ellipsoids, that single linkage can successfully extract the indicated clusters, and that our model can find both first and second order anomalies in WSN data.

In this paper we propose a new multiclass SVM, the conic-segmentation SVM (CS-SVM), based on the direct mapping of points into a multidimensional target space segmented a-priori into conic class regions defined by generalized inequalities. We show that the CS-SVM is a natural multiclass analogue of the standard binary SVM in-so-far as it shares its motivation, simplicity of form, and many of its properties such as convexity, sparsity and kernelisation. We demonstrate that prior selection of the conic region structure can give both new and interesting multiclass formulations and also well-known multiclass formulations. Finally we present experimental results on artificial and real multiclass datasets to investigate the CS-SVM's performance.

Very large (VL) data or big data are any data that you cannot load into your computer's working memory. This is not an objective definition, but a definition that is easy to understand and one that is practical, because there is a dataset too big for any computer you might use; hence, this is VL data for you. Clustering is one of the primary tasks used in the pattern recognition and data mining communities to search VL databases (including VL images) in various applications, and so, clustering algorithms that scale well to VL data are important and useful. This paper compares the efficacy of three different implementations of techniques aimed to extend fuzzy c-means (FCM) clustering to VL data. Specifically, we compare methods that are based on 1) sampling followed by noniterative extension; 2) incremental techniques that make one sequential pass through subsets of the data; and 3) kernelized versions of FCM that provide approximations based on sampling, including three proposed algorithms. We use both loadable and VL datasets to conduct the numerical experiments that facilitate comparisons based on time and space complexity, speed, quality of approximations to batch FCM (for loadable data), and assessment of matches between partitions and ground truth. Empirical results show that random sampling plus extension FCM, bit-reduced FCM, and approximate kernel FCM are good choices to approximate FCM for VL data. We conclude by demonstrating the VL algorithms on a dataset with 5 billion objects and presenting a set of recommendations regarding the use of different VL FCM clustering schemes.

Cardiovascular autonomic neuropathy (CAN) has been frequently postulated to increase susceptibility to ventricular arrhythmias and sudden cardiac death in diabetic patients. The relation between the progression of CAN in diabetes and ventricular repolarization remains to be fully described. Therefore, this study examined QT interval variability and heart rate interbeat variability to identify any alterations of cardiac repolarization in diabetic patients in relation to severity of CAN. Seventy control participants without (CAN-) and 74 patients with CAN (CAN+) were enrolled in this study. Among 74 CAN + patients, 62 are early CAN + (eCAN +) , and 12 are definite CAN + (dCAN +) according to autonomic nervous system function tests as described by Ewing. The results showed that the QT variability index (QTVI) was significantly higher and positive in the dCAN + (0.51 ±1.32) group than in the eCAN + (-0.39 ±0.91) and CAN - (-0.54 ±0.72) groups. The QT variability to heart-rate variability ratio provides a measure of the balance between QT and heart interbeat variability. QTVI was more sensitive in identifying disease progression at all stages. Our study supports the hypothesis that QTVI could be used as a clinical test to identify early CAN and as a marker of CAN progression in diabetic patients and may help physicians in determining the best therapeutic strategy for these patients.

In a tree-based ZigBee network, ZigBee routers (ZRs) must schedule their beacon transmission time to avoid beacon collisions. The beacon schedule determines packet delivery latency from the end devices to the ZigBee coordinator at the root of the tree. Traditionally, beacon schedules are chosen such that a ZR does not reuse the beacon slots already claimed by its neighbors, or the neighbors of its neighbors. We observe, however, that beacon slots can be reused judiciously, especially when the risk of beacon collision caused by such reuse is low. The advantage of such reuse is that packet delivery latency can be reduced. We formalize our observation by proposing a node-pair classification scheme. Based on this scheme, we can easily assess the risk of slot reuse by a node pair. If the risk is high, slot reuse is disallowed; otherwise, slot reuse is allowed. This forms the essence of our ZigBee-compatible, distributed, risk-aware, probabilistic beacon scheduling algorithm. Simulation results show that on average the proposed algorithm produces a latency only 24 percent of that with conventional method, at the cost of 12 percent reduction in the fraction of associated nodes.

Emerging applications in Multihop Wireless Networks (MHWNs) require considerable processing power which often may be beyond the capability of individual nodes. Parallel processing provides a promising solution, which partitions a program into multiple small tasks and executes each task concurrently on independent nodes. However, multihop wireless communication is inevitable in such networks and it could have an adverse effect on distributed processing. In this paper, an adaptive intelligent task mapping together with a scheduling scheme based on a genetic algorithm is proposed to provide real-time guarantees. This solution enables efficient parallel processing in a way that only possible node collaborations with cost-effective communications are considered. Furthermore, in order to alleviate the power scarcity of MHWN, a hybrid fitness function is derived and embedded in the algorithm to extend the overall network lifetime via workload balancing among the collaborative nodes, while still ensuring the arbitrary application deadlines. Simulation results show significant performance improvement in various testing environments over existing mechanisms.

This note presents an analysis of the octonionic form of the division algebraic support vector regressor (SVR) first introduced by Shilton A detailed derivation of the dual form is given, and three conditions under which it is analogous to the quaternionic case are exhibited. It is shown that, in the general case of an octonionic-valued feature map, the usual "kernel trick" breaks down. The cause of this (and its interpretation) is discussed in some detail, along with potential ways of extending kernel methods to take advantage of the distinct features present in the general case. Finally, the octonionic SVR is applied to an example gait analysis problem, and its performance is compared to that of the least squares SVR, the Clifford SVR, and the multidimensional SVR.

Wireless Sensor Networks (WSNs) provide a low cost option for gathering spatially dense data from different environments. However, WSNs have limited energy resources that hinder the dissemination of the raw data over the network to a central location. This has stimulated research into efficient data mining approaches, which can exploit the restricted computational capabilities of the sensors to model their normal behavior. Having a normal model of the network, sensors can then forward anomalous measurements to the base station. Most of the current data modeling approaches proposed for WSNs require a fixed offline training period and use batch training in contrast to the real streaming nature of data in these networks. In addition they usually work in stationary environments. In this paper we present an efficient online model construction algorithm that captures the normal behavior of the system. Our model is capable of tracking changes in the data distribution in the monitored environment. We illustrate the proposed algorithm with numerical results on both real-life and simulated data sets, which demonstrate the efficiency and accuracy of our approach compared to existing methods.

This article presents an algorithm for decentralized (in-network) data mining of the movement pattern flock among mobile geosensor nodes. The algorithm DDIG (Deferred Decentralized Information Grazing) allows roaming sensor nodes to ‘graze’ over time more information than they could access through their spatially limited perception range alone. The algorithm requires an intrinsic temporal deferral for pattern mining, as sensor nodes must be enabled to collect, memorize, exchange, and integrate their own and their neighbors' most current movement history before reasoning about patterns. A first set of experiments with trajectories of simulated agents showed that the algorithm accuracy increases with growing deferral. A second set of experiments with trajectories of actual tracked livestock reveals some of the shortcomings of the conceptual flocking model underlying DDIG in the context of a smart farming application. Finally, the experiments underline the general conclusion that decentralization in spatial computing can result in imperfect, yet useful knowledge.

ABSTRACT Key management is the pillar of a security architecture. Body sensor networks (BSNs) pose several challenges–some inherited from wireless sensor networks (WSNs), some unique to themselves–that require a new key management scheme to be tailor‐made. The challenge is taken on, and the result is KALwEN, a new parameterized key management scheme that combines the best‐suited cryptographic techniques in a seamless framework. KALwEN is user‐friendly in the sense that it requires no expert knowledge of a user, and instead only requires a user to follow a simple set of instructions when bootstrapping or extending a network. One of KALwEN's key features is that it allows sensor devices from different manufacturers, which expectedly do not have any pre‐shared secret, to establish secure communications with each other. KALwEN is decentralized, such that it does not rely on the availability of a local processing unit (LPU). KALwEN supports secure global broadcast, local broadcast, and local (neighbor‐to‐neighbor) unicast, while preserving past key secrecy and future key secrecy (FKS). The fact that the cryptographic protocols of KALwEN have been formally verified also makes a convincing case. With both formal verification and experimental evaluation, our results should appeal to theorists and practitioners alike. Copyright © 2010 John Wiley & Sons, Ltd.

Proportional, TCP friendly (minimum potential delay) and max-min fairness are three most commonly used fairness criteria for resource allocation in communication networks. In this paper, we generalize the above fairness criteria in terms of utility and study the resource allocation problem for heterogeneous networks where contending users may have different Quality of Services (QoS) requirements and the utility functions may not necessarily satisfy the strict concavity condition, such as real-time applications. We propose a QoS based flow control algorithm and with different link price feedback mechanisms, utility weighted proportional, TCP friendly and max-min fairness is achieved in this unified approach. In addition, the new algorithm is not only suitable for elastic data traffic, but also capable of handling real-time applications, and therefore it can be treated as an efficient flow control mechanism to provide congestion control and QoS balance for Differentiated Services in the future Internet.

The capabilities of sensor networking devices are increasing at a rapid pace. It is therefore not impractical to assume that future sensing operations will involve real time (inelastic) traffic, such as audio and video surveillance, which have strict bandwidth constraints. This in turn implies that future sensor networks will have to cater for a mix of elastic (having no bandwidth constraint requirements) and inelastic traffic. Current state of the art rate control protocols for wireless sensor networks, are however designed with focus on elastic traffic. In this work, by adapting a recently developed theory of utilityproportional rate control for wired networks to a wireless setting, and combining it with a stochastic optimization framework that results in an elegant queue backpressure-based algorithm, we have designed the first-ever rate control protocol that can efficiently handle a mix of elastic and inelastic traffic in a wireless sensor network. We implement this novel protocol in a real world sensor network stack, the TinyOS-2.x communication stack for IEEE 802.15.4 radios and evaluate the real-world performance of this protocol through comprehensive experiments on 20 and 40-node subnetworks of USC's 94-node Tutornet wireless sensor network testbed.

Anomaly detection in wireless sensor networks is an important challenge for tasks such as intrusion detection and monitoring applications. This paper proposes two approaches to detecting anomalies from measurements from sensor networks. The first approach is a linear programming-based hyperellipsoidal formulation, which is called a centered hyperellipsoidal support vector machine (CESVM). While this CESVM approach has advantages in terms of its flexibility in the selection of parameters and the computational complexity, it has limited scope for distributed implementation in sensor networks. In our second approach, we propose a distributed anomaly detection algorithm for sensor networks using a one-class quarter-sphere support vector machine (QSSVM). Here a hypersphere is found that captures normal data vectors in a higher dimensional space for each sensor node. Then summary information about the hyperspheres is communicated among the nodes to arrive at a global hypersphere, which is used by the sensors to identify any anomalies in their measurements. We show that the CESVM and QSSVM formulations can both achieve high detection accuracies on a variety of real and synthetic data sets. Our evaluation of the distributed algorithm using QSSVM reveals that it detects anomalies with comparable accuracy and less communication overhead than a centralized approach.

In this paper, division algebras are proposed as an elegant basis upon which to extend support vector regression (SVR) to multidimensional targets. Using this framework, a multitarget SVR called epsilon(Z)-SVR is proposed based on an epsilon-insensitive loss function that is independent of the coordinate system or basis used. This is developed to dual form in a manner that is analogous to the standard epsilon-SVR. The epsilon(H)-SVR is compared and contrasted with the least-square SVR (LS-SVR), the Clifford SVR (C-SVR), and the multidimensional SVR (M-SVR). Three practical applications are considered: namely, 1) approximation of a complex-valued function; 2) chaotic time-series prediction in 3-D; and 3) communication channel equalization. Results show that the epsilon(H)-SVR performs significantly better than the C-SVR, the LS-SVR, and the M-SVR in terms of mean-squared error, outlier sensitivity, and support vector sparsity.

Network reprogramming is a crucial service in wireless sensor networks (WSNs) that relies on epidemic strategy for spreading software updates by just having a local view of the networks. Securing the process of network reprogramming is essential in some certain WSNs applications, state-of-the-art secure network reprogramming protocols for WSNs aim for the efficient source authentication and integrity verification of code image, however, due to the resource constrains of WSNs, existing secure network reprogramming protocols are vulnerable to Denial of Service (DoS) attacks when sensor nodes can be compromised (insider DoS attacks). In this paper, we identify different types of DoS attacks exploiting the epidemic propagation strategies used by Deluge and propose corresponding analysis models to attempt to quantify the cost of these attacks damage. Simulation further shows the impact of insider DoS attacks on network reprogramming in WSNs.

Wireless sensor networks (WSNs) are well suited for environment monitoring. However, some highly specialized sensors (e.g. hydrological sensors) have high power demand, and without due care, they can exhaust the battery supply quickly. Taking measurements with this kind of sensors can also overwhelm the communication resources by far. One way to reduce the power drawn by these high-demand sensors is adaptive sampling, i.e., to skip sampling when data loss is estimated to be low. Here, we present an adaptive sampling algorithm based on the Box-Jenkins approach in time series analysis. To measure the performance of our algorithms, we use the ratio of the reduction factor to root mean square error (RMSE). The rationale of the metric is that the best algorithm is the algorithm that gives the most reduction in the amount of sampling and yet the the smallest RMSE. For the datasets used in our simulations, our algorithm is capable of reducing the amount of sampling by 24% to 49%. For seven out of eight datasets, our algorithm performs better than the best in the literature so far in terms of the reduction/RMSE ratio.

Obstructive sleep apnea or hypopnea causes a pause or reduction in airflow with continuous breathing effort. The aim of this study is to identify individual apnea and hypopnea events from normal breathing events using wavelet-based features of 5-s ECG signals (sampling rate = 250 Hz) and estimate the surrogate apnea index (AI)/hypopnea index (HI) (AHI). Total 82,535 ECG epochs (each of 5-s duration) from normal breathing during sleep, 1638 ECG epochs from 689 hypopnea events, and 3151 ECG epochs from 1862 apnea events were collected from 17 patients in the training set. Two-staged feedforward neural network model was trained using features from ECG signals with leave-one-patient-out cross-validation technique. At the first stage of classification, events (apnea and hypopnea) were classified from normal breathing events, and at the second stage, hypopneas were identified from apnea. Independent test was performed on 16 subjects' ECGs containing 483 hypopnea and 1352 apnea events. The cross-validation and independent test accuracies of apnea and hypopnea detection were found to be 94.84% and 76.82%, respectively, for training set, and 94.72% and 79.77%, respectively, for test set. The Bland-Altman plots showed unbiased estimations with standard deviations of +/- 2.19, +/- 2.16, and +/- 3.64 events/h for AI, HI, and AHI, respectively. Results indicate the possibility of recognizing apnea/hypopnea events based on shorter segments of ECG signals.

Obstructive sleep apnea syndrome (OSAS) is associated with cardiovascular morbidity as well as excessive daytime sleepiness and poor quality of life. In this study, we apply a machine learning technique [support vector machines (SVMs)] for automated recognition of OSAS types from their nocturnal ECG recordings. A total of 125 sets of nocturnal ECG recordings acquired from normal subjects (OSAS - ) and subjects with OSAS (OSAS +), each of approximately 8 h in duration, were analyzed. Features extracted from successive wavelet coefficient levels after wavelet decomposition of signals due to heart rate variability (HRV) from RR intervals and ECG-derived respiration (EDR) from R waves of QRS amplitudes were used as inputs to the SVMs to recognize OSAS +/- subjects. Using leave-one-out technique, the maximum accuracy of classification for 83 training sets was found to be 100% for SVMs using a subset of selected combination of HRV and EDR features. Independent test results on 42 subjects showed that it correctly recognized 24 out of 26 OSAS + subjects and 15 out of 16 OSAS - subjects (accuracy = 92.85%; Cohen's kappa value of 0.85). For estimating the relative severity of OSAS, the posterior probabilities of SVM outputs were calculated and compared with respective apnea/hypopnea index. These results suggest superior performance of SVMs in OSAS recognition supported by wavelet-based features of ECG. The results demonstrate considerable potential in applying SVMs in an ECG-based screening device that can aid a sleep specialist in the initial assessment of patients with suspected OSAS.

Our mobility is an important daily requirement so much so that any disruption to it severely degrades our perceived quality of life. Studies in gait and human movement sciences, therefore, play a significant role in maintaining the well-being of our mobility. Current gait analysis involves numerous interdependent gait parameters that are difficult to adequately interpret due to the large volume of recorded data and lengthy assessment times in gait laboratories. A proposed solution to these problems is computational intelligence (CI), which is an emerging paradigm in biomedical engineering most notably in pathology detection and prosthesis design. The integration of CI technology in gait systems facilitates studies in disorders caused by lower limb defects, cerebral disorders, and aging effects by learning data relationships through a combination of signal processing and machine learning techniques. Learning paradigms, such as supervised learning, unsupervised learning, and fuzzy and evolutionary algorithms, provide advanced modeling capabilities for biomechanical systems that in the past have relied heavily on statistical analysis. CI offers the ability to investigate nonlinear data relationships, enhance data interpretation, design more efficient diagnostic methods, and extrapolate model functionality. These are envisioned to result in more cost-effective, efficient, and easy-to-use systems, which would address global shortages in medical personnel and rising medical costs. This paper surveys current signal processing and CI methodologies followed by gait applications ranging from normal gait studies and disorder detection to artificial gait simulation. We review recent systems focusing on the existing challenges and issues involved in making them successful. We also examine new research in sensor technologies for gait that could be combined with these intelligent systems to develop more effective healthcare solutions.

Patellofemoral pain syndrome (PFPS) is a common disorder that afflicts people across all age groups, and results in various degrees of knee pain. The diagnosis of PFPS is difficult since the exact biomechanical factors and the extent to which they are affected by the disorder are still unknown. Recent research has reported significant statistical differences in ground reaction forces (GRFs) and foot kinematics, which could be indicative of PFPS, but the interrelationship between many of these measures and the pathology have been absent so far. In this paper, we applied the support vector machines (SVMs) to detect PFPS gait based on 14 GRF and 16 foot kinematic features recorded from 27 subjects (14 healthy and 13 with PFPS). The influence of combined gait parameters on classification performance was investigated through the use of a feature-selection algorithm. The optimal feature set was then compared against the most statistically significant individual features (p < 0.05) found by previous study. Test results indicated that GRF features alone resulted in a higher leave-one-out (LOO) classification accuracy (85.15%) compared to 74.07% using only kinematic features. A hill-climbing feature-selection algorithm was applied to determine the subset of combined kinematic and kinetic features, which provided optimal classifier performance. This subset, which consists of six features (two from GRF and four from foot kinematic features), provided an improved LOO accuracy of 88.89% . The optimal feature set detected by the SVM, which best identified gait characteristics of PFPS, was found to be closely related to inferential statistical analysis with the added distinction that the SVM could potentially be deployed as an automated system for detecting gait changes in patients with PFPS.

A typical wireless sensor node has little protection against radio jamming. The situation becomes worse if energy-efficient jamming can be achieved by exploiting knowledge of the data link layer. Encrypting the packets may help to prevent the jammer from taking actions based on the content of the packets, but the temporal arrangement of the packets induced by the nature of the protocol might unravel patterns that the jammer can take advantage of, even when the packets are encrypted. By looking at the packet interarrival times in three representative MAC protocols, S-MAC, LMAC, and B-MAC, we derive several jamming attacks that allow the jammer to jam S-MAC, LMAC, and B-MAC energy efficiently. The jamming attacks are based on realistic assumptions. The algorithms are described in detail and simulated. The effectiveness and efficiency of the attacks are examined. In addition, we validate our simulation model by comparing its results with measurements obtained from actual implementation on our sensor node prototypes. We show that it takes little effort to implement such effective jammers, making them a realistic threat. Careful analysis of other protocols belonging to the respective categories of S-MAC, LMAC, and B-MAC reveals that those protocols are, to some extent, also susceptible to our attacks. The result of this investigation provides new insights into the security considerations of MAC protocols.

Anomalies in wireless sensor networks can occur due to malicious attacks, faulty sensors, changes in the observed external phenomena, or errors in communication. Defining and detecting these interesting events in energy-constrained situations is an important task in managing these types of networks. A key challenge is how to detect anomalies with few false alarms while preserving the limited energy in the network. In this article, we define different types of anomalies that occur in wireless sensor networks and provide formal models for them. We illustrate the model using statistical parameters on a dataset gathered from a real wireless sensor network deployment at the Intel Berkeley Research Laboratory. Our experiments with a novel distributed anomaly detection algorithm show that it can detect elliptical anomalies with exactly the same accuracy as that of a centralized scheme, while achieving a significant reduction in energy consumption in the network. Finally, we demonstrate that our model compares favorably to four other well-known schemes on four datasets.

A challenge in using machine learning for tasks such as network intrusion detection and fault diagnosis is the difficulty in obtaining clean data for training in order to model the normal behavior of the system. Unsupervised anomaly detection techniques such as one class support vector machines (SVMs) have been introduced to overcome this difficulty. One class support vector machines model the normal or target data using non-linear surfaces in the input space while ignoring the anomalous data. Our approach to this problem is based on fitting a hyperellipsoid with a minimal effective radius, centered at the origin, around a majority of the data vectors in a higher dimensional space. We formulate this as a linear optimisation problem, which is advantageous in terms of its computational complexity. We demonstrate using real data from the great duck Island Project that our approach achieves better detection performance and flexibility in terms of parameter selection, compared to an earlier detection scheme using a quarter sphere SVM.

License plate recognition usually contains three steps, namely license plate detection/localization, character segmentation and character recognition. When reading characters on a license plate one by one after license plate detection step, it is crucial to accurately segment the characters. The segmentation step may be affected by many factors such as license plate boundaries (frames). The recognition accuracy will be significantly reduced if the characters are not properly segmented. This paper presents an efficient algorithm for character segmentation on a license plate. The algorithm follows the step that detects the license plates using an AdaBoost algorithm. It is based on an efficient and accurate skew and slant correction of license plates, and works together with boundary (frame) removal of license plates. The algorithm is efficient and can be applied in real-time applications. The experiments are performed to show the accuracy of segmentation.

Fully-connected mesh networks that can potentially be employed in a range of applications, are inherently associated with major deficiencies in interference management and network capacity improvement. The tree-connected (routing based) mesh networks used in today's applications have major deficiencies in routing delays and reconfiguration delays in the implementation stage. This paper introduces a CDMA based fully-connected mesh network, which controls the transmission powers of the nodes in order to ensure that the communication channels remain interference-free and minimizes the energy consumption. Moreover, the bounds for the number of nodes and the spatial configuration are provided to ensures that the communication link satisfies the QoS (Quality of Service) requirements at all times.

Trip-related falls are a major problem in the elderly population and research in the area has received much attention recently. The focus has been on devising ways of identifying individuals at risk of sustaining such falls. The main aim of this work is to explore the effectiveness of models based on Support Vector Machines (SVMs) for the automated recognition of gait patterns that exhibit falling behavior. Minimum toe clearance (MTC) during continuous walking on a treadmill was recorded on 10 healthy elderly and 10 elderly with balance problems and with a history of tripping falls. Statistical features obtained from MTC histograms were used as inputs to the SVM model to classify between the healthy and balance-impaired subjects. The leave-one-out technique was utilized for training the SVM model in order to find the optimal model parameters. Tests were conducted with various kernels (linear, Gaussian and polynomial) and with a change in the regularization parameter, C, in an effort to identify the optimum model for this gait data. The receiver operating characteristic (ROC) plots of sensitivity and specificity were further used to evaluate the diagnostic performance of the model. The maximum accuracy was found to be 90% using a Gaussian kernel with σ2 = 10 and the maximum ROC area 0.98 (80% sensitivity and 100% specificity), when all statistical features were used by the SVM models to diagnose gait patterns of healthy and balance-impaired individuals. This accuracy was further improved by using a feature selection method in order to reduce the effect of redundant features. It was found that two features (standard deviation and maximum value) were adequate to give an improved accuracy of 95% (90% sensitivity and 100% specificity) using a polynomial kernel of degree 2. These preliminary results are encouraging and could be useful not only for diagnostic applications but also for evaluating improvements in gait function in the clinical/rehabilitation contexts.

Knowledge of the secondary structure and solvent accessibility of a protein plays a vital role in prediction of fold, and eventually the tertiary structure of the protein. This paper deals with prediction of relative solvent accessibility, given only the amino-acid sequence. In this paper, we use an improved support vector regression (SVR) and new kernels for real valued prediction of solvent accessibility. In this regard, two main issues are addressed. First we address the problem of e selection, which we found to be somewhat problematic in our earlier work (e is a parameter with significant influence on noise insensitivity and generalization of SVRs). In particular, rather than employ the standard trial and error based approach, we used an improved tube shrinking method to find e. Secondly, a novel kernel combining solvation model, electrostatic charge model and evolutionary information in the form of position specific scoring matrix (PSSM) is given. A new dataset of 472 proteins with less than 20% sequence identity is curated and used to evaluate the result. To make a more objective comparison with earlier methods, we use a standard dataset and show that the proposed scheme is better than the ones normally used in literature. We also report a lowest mean absolute error (MAE) so far of 0.12 on the standard dataset.

Anomaly detection is an important challenge for tasks such as fault diagnosis and intrusion detection in energy constrained wireless sensor networks. A key problem is how to minimise the communication overhead in the network while performing in-network computation when detecting anomalies. Our approach to this problem is based on a formulation that uses distributed, one-class quarter-sphere support vector machines to identify anomalous measurements in the data. We demonstrate using sensor data from the Great Duck Island Project that our distributed approach is energy efficient in terms of communication overhead while achieving comparable accuracy to a centralised scheme.

Active queue management (AQM) is an effective method to provide an early notification of network congestion by pro-actively dropping or marking packets. In this paper, we propose a novel algorithm called fuzzy control RED (FCRED) that overcomes the drawbacks of the original RED. FCRED uses a fuzzy controller to adjust the maximum drop probability to stabilize the average queue length around the target queue length. We demonstrate by simulation results that FCRED maintains its performance independent of traffic loads, round trip propagation delay, and bottleneck capacity. We also demonstrate that FCRED is robust to non-responsive UDP traffic and HTTP traffic, and it is effective for networks with multiple bottlenecks. Comparison with other well-known AQM algorithms like PI, REM and ARED demonstrates the superiority of FCRED in achieving faster convergence to queue length target, and smaller queue length jitter.

The consequence of tripping and falling in the elderly population is serious because of the life threatening fractures which occur and the high medical costs incurred. Recently, the minimum toe clearance (MTC) has been employed in gait analysis as a sensitive gait variable for early detection of elderly people at risk of falling. In previous work, we successfully applied statistical and wavelet analysis methods with Support Vector Machines (SVM) to model the risk of tripping in the elderly. In this work, we propose to model the MTC time series as a wide based stationary random signal using the autoregressive (AR) process. Initially, it was found that a fourth order AR model constructed from 512 MTC samples per subject on 23 subjects completely modelled the balance impaired gait (pathological) from normal gait. However, when the number of MTC samples were reduced to 32, the two groups became inseparable. We then proposed a hybrid system consisting of a SVM classifier with AR model coefficients as input features to separate the two classes. It was found that SVMs with linear and Gaussian kernels produced 100% leave one out accuracies without the need for prior feature selection algorithms. In contrast, SVM models built previously from the best set of wavelet features produced only 86.95% leave one out accuracies. These results suggest that pathological gait is best modelled by the AR process if sufficient MTC data is available. In the case of shorter MTC data, the AR model still provides powerful and robust discriminative features which can be used by the SVM to detect elderly people at risk of falling.

A k-connected wireless sensor network (WSN) allows messages to be routed via one (or more) of at least k node-disjoint paths, so that even if some nodes along one of the paths fail, or are compromised, the other paths can still be used. This is a much desired feature in fault tolerance and security, k-connectivity in this context is largely a well-studied subject. When we apply the random key pre-distribution scheme to secure a WSN however, and only consider the paths consisting entirely of secure (encrypted and/or authenticated) links, we are concerned with the secure k-connectivity of the WSN. This notion of secure k-connectivity is relatively new and no results are yet available. The random key pre-distribution scheme has two important parameters: the key ring size and the key pool size. While it has been determined before the relation between these parameters and 1-connectivity, our work in k-connectivity is new. Using a recently introduced random graph model called kryptograph, we derive mathematical formulae to estimate the asymptotic probability of a WSN being securely k-connected, and the expected secure k-connectivity, as a function of the key ring size and the key pool size. Finally, our theoretical findings are supported by simulation results.

False track discrimination performance of a target tracking algorithm in a heavy clutter environment depends on the track confirmation and the track termination thresholds. The optimum value of these thresholds depends on the environment, in particular on the given probability of detection and on the existing clutter density. When tracking ground targets the probability of target detection is nominally constant, whereas the clutter measurement density varies significantly. Previously it was shown that, for a wide range of target signal to noise (+clutter) ratio in a uniform clutter density environment, and given the opportunity to set signal detection thresholds, the optimum value of clutter measurement density is almost constant (and the probability of detection will vary). We propose a scheme where the feedback from the target tracking system corrects the detection thresholds for each sensor resolution cell to obtain the constant and optimal clutter measurement density in each cell, when the clutter statistics changes slowly. This results in better false track discrimination capabilities of the tracker and also replaces the CFAR block in the signal processing unit

Neural networks have been shown to be useful tools for density estimation. However, the training of neural network structures is time consuming and requires fast processors for practical applications. A new method with a generalized neuron (GN) for density estimation is presented in this paper. The GN is trained with the particle swarm optimization algorithm which is known to have fast convergence than the standard backpropagation algorithm. Results are presented to show that the GN can estimate the density functions for distribution functions with different means and variances. This density estimation method can also be applied to the multi-sensor data fusion process

The support vector machine (SVM) classifier has been a popular classification tool used for a variety of pattern recognition tasks. In this study, we compare the performance of a semiparametric SVM classifier derived using an inexact penalty method on the original SVM formulation. This semiparametric form can be easily solved using a sequential decomposition method. We compare the accuracy of the semiparametric SVM against the standard SVM classifier trained using the SMO algorithm. The results indicate that in some cases the semiparametric SVM can give better generalization results than a standard SVM. We also demonstrate several cases where our iterative algorithm solves the SVM problem faster than the SMO.

Knowledge of the secondary structure and solvent accessibility of a protein plays a vital role in the prediction of fold, and eventually the tertiary structure of the protein. A challenging issue of predicting protein secondary structure from sequence alone is addressed. Support vector machines (SVM) are employed for the classification and the SVM outputs are converted to posterior probabilities for multi-class classification. The effect of using Chou–Fasman parameters and physico-chemical parameters along with evolutionary information in the form of position specific scoring matrix (PSSM) is analyzed. These proposed methods are tested on the RS126 and CB513 datasets. A new dataset is curated (PSS504) using recent release of CATH. On the CB513 dataset, sevenfold cross-validation accuracy of 77.9% was obtained using the proposed encoding method. A new method of calculating the reliability index based on the number of votes and the Support Vector Machine decision value is also proposed. A blind test on the EVA dataset gives an average Q3accuracy of 74.5% and ranks in top five protein structure prediction methods. Supplementary material including datasets are available on .

An orthonormal Hilbert-pair consists of a pair of conjugate-quadrature-filter (CQF) banks such that the equivalent wavelet function of both banks are approximate Hilbert transforms of each other. We found that the celebrated orthonormal wavelets of Daubechies, which have maximum vanishing-moment (VM), cannot be used to construct good Hilbert-pairs. In this letter, we reduce the number of VM by one and construct a Hilbert-pair with almost maximum VM. Each pair of wavelets are time-reverse versions of each other, and the individual wavelets are of the least asymmetric type (i.e., approximate linear phase CQF)

The training of support vector machines using the decomposition method has one drawback; namely the selection of working sets such that convergence is as fast as possible. It has been shown by Lin that the rate is linear in the worse case under the assumption that all bounded support vectors have been determined. The analysis was done based on the change in the objective function and under a SVMlight selection rule. However, the rate estimate given is independent of time and hence gives little indication as to how the linear convergence speed varies during the iteration. In this initial analysis, we provide a treatment of the convergence from a gradient contraction perspective. We propose a necessary and sufficient condition which when satisfied provides strict linear convergence of the algorithm. The condition can also be interpreted as a basic requirement for a sequence of working sets in order to achieve such a convergence rate. Based on this condition, a time dependent rate estimate is then further derived. This estimate is shown to monotonically approach unity from below.

We propose a new Spectral text retrieval method using the Discrete Cosine Transform (DCT). By taking advantage of the properties of the DCT and by employing the fast query and compression techniques found in vector space methods (VSM), we show that we can process queries as fast as VSM and achieve a much higher precision.

We propose a new algorithm for the incremental training of support vector machines (SVMs) that is suitable for problems of sequentially arriving data and fast constraint parameter variation. Our method involves using a "warm-start" algorithm for the training of SVMs, which allows us to take advantage of the natural incremental properties of the standard active set approach to linearly constrained optimization problems. Incremental training involves quickly retraining a support vector machine after adding a small number of additional training vectors to the training set of an existing (trained) support vector machine. Similarly, the problem of fast constraint parameter variation involves quickly retraining an existing support vector machine using the same training set but different constraint parameters. In both cases, we demonstrate the computational superiority of incremental training over the usual batch retraining method.

Current information retrieval methods either ignore the term positions or deal with exact term positions; the former can be seen as coarse document resolution, the latter as fine document resolution. We propose a new spectral-based information retrieval method that is able to utilize many different levels of document resolution by examining the term patterns that occur in the documents. To do this, we take advantage of the multiresolution analysis properties of the wavelet transform. We show that we are able to achieve higher precision when compared to vector space and proximity retrieval methods, while producing fast query times and using a compact index.

This paper presents a new technique for designing pairs of filter banks whose corresponding wavelet functions are approximate Hilbert transforms of each other. The filters have exact linear phase which yields biorthogonal wavelets with exact symmetry. The technique is based on matching the frequency response of a given odd-length filter bank with an even-length filter bank. The class of EBFB (even-length Bernstein filter bank) is utilized in the matching design. The EBFB has perfect reconstruction and vanishing moments properties structurally imposed and this simplifies the design process. The design is achieved through a non-iterative least squares method.

The support vector machine classifier is a binary classifier applied to classify large datasets, which is ideal for the application of decomposition methods when processing memory is limited. However, the rates of convergence of the decomposition method are largely dependent on the sequence of decomposed problems solved. Unfortunately, choosing the optimal sequence of sub problems is difficult due to the inability of the algorithm to consider the entire variable space at once. We propose a measure of iteration that we call momentum and derive a prediction method to minimize the momentum of the updated iterates hitting the boundary constraints. Our prediction method uses a rough heuristic set to choose an approximately optimal subproblem to solve. We show that this rough heuristic set could greatly improve the speed of the popular sequential minimal optimization algorithm.

Current document retrieval methods use a vector space similarity measure to give scores of relevance to documents when related to a specific query. The central problem with these methods is that they neglect any spatial information within the documents in question. We present a new method, called Fourier Domain Scoring (FDS), which takes advantage of this spatial information, via the Fourier transform, to give a more accurate ordering of relevance to a document set. We show that FDS gives an improvement in precision over the vector space similarity measures for the common case of Web like queries, and it gives similar results to the vector space measures for longer queries.

A study of a family of biorthogonal wavelet filters for use in digital watermarking is presented. The filters are explicitly parametrized by two free parameters and can be used to provide diversity in watermarking. Diversity can be used to improve the security of the watermarking system from hostile attacks. Each filter has at least two vanishing moments, which is important for ensuring some degree of smoothness in the resulting wavelet function. Along with robustness and security, other factors, which impact upon the successful implementation of the filters in a watermarking application are analysed. The relationship between the strength of the inserted watermark and wavelet energy is also discussed.

We present a new training algorithm, which is capable of providing fast training for a new automatically biased SVM. We compare our algorithm to the well-known sequential minimal optimization (SMO) algorithm. We then show that this method allows for the application of acceleration methods which further increases the rates of convergence.

The traditional methods of spectral text retrieval (FDS,CDS) create an index of spatial data and convert the data to its spectral form at query time. We present a new method of implementing and querying an index containing spectral data which will conserve the high precision performance of the spectral methods, reduce the time needed to resolve the query, and maintain an acceptable size for the index. This is done by taking advantage of the properties of the discrete cosine transform and by applying ideas from vector space document ranking methods.

In radial basis function (RBF) networks, placement of centers is said to have a significant effect on the performance of the network. Supervised learning of center locations in some applications show that they are superior to the networks whose centers are located using unsupervised methods. But such networks can take the same training time as that of sigmoid networks. The increased time needed for supervised learning offsets the training time of regular RBF networks. One way to overcome this may be to train the network with a set of centers selected by unsupervised methods and then to fine tune the locations of centers. This can be done by first evaluating whether moving the centers would decrease the error and then, depending on the required level of accuracy, changing the center locations. This paper provides new results on bounds for the gradient and Hessian of the error considered first as a function of the independent set of parameters, namely the centers, widths, and weights; and then as a function of centers and widths where the linear weights are now functions of the basis function parameters for networks of fixed size. Moreover, bounds for the Hessian are also provided along a line beginning at the initial set of parameters. Using these bounds, it is possible to estimate how much one can reduce the error by changing the centers. Further to that, a step size can be specified to achieve a guaranteed, amount of reduction in error.

The conventional neural network approach has been found useful in predicting corporate distress from financial statements. We have adapted a support vector machine approach to the problem. A way of selecting bankruptcy predictors is shown, using the Euclidean distance based criterion calculated within the SVM kernel. A comparative study is provided using three classical corporate distress models and an alternative model based on the SVM approach.

This paper proposes using a model predictive control (MPC) incorporating a radial basis function (RBF) network observer for the fuel injection problem. Two new contributions are presented. First, an RBF Network is used as an observer for the volumetric efficiency of the air system. This allows for gradual adaptation of the observer, ensuring the control scheme is capable of maintaining good performance under changing engine conditions brought about by engine wear, variations between individual engines and other similar factors. The other is the rise of model predictive control algorithms to compensate for the fuel pooling effect on the intake manifold walls. Two MPC algorithms are presented which enforce input, and input and state constraints. A comparison between the two constrained MPC algorithms is qualitatively presented, and some conclusions drawn about the necessity of constraints for the fuel injection problem. Simulation and actual engine results are presented that demonstrate the effectiveness of the control scheme.

The problem of identification of nonlinear functions by neural networks is studied. An example of a simulation of the sinc-function by partially correlated networks is given. Construction of inverse mapping for a nonlinear map by neural networks is formulated.

After more than a decade of research, there now exist several neural-network techniques for solving NP-hard combinatorial optimization problems. Hopfield networks and self-organizing maps are the two main categories into which most of the approaches can be divided. Criticism of these approaches includes the tendency of the Hopfield network to produce infeasible solutions, and the lack of generalizability of the self-organizing approaches (being only applicable to Euclidean problems). This paper proposes two new techniques which have overcome these pitfalls: a Hopfield network which enables feasibility of the solutions to be ensured and improved solution quality through escape from local minima, and a self-organizing neural network which generalizes to solve a broad class of combinatorial optimization problems. Two sample practical optimization problems from Australian industry are then used to test the performances of the neural techniques against more traditional heuristic solutions.

A neural-network-based adaptive tracking control scheme is proposed for a class of nonlinear systems in this paper. It is shown that RBF neural networks are used to adaptively learn system uncertainty bounds in the Lyapunov sense, and the outputs of the neural networks are then used as the parameters of the controller to compensate for the effects of system uncertainties. Using this scheme, not only strong robustness with respect to uncertain dynamics and nonlinearities can be obtained, but also the output tracking error between the plant output and the desired reference output can asymptotically converge to zero. A simulation example is performed in support of the proposed neural control scheme.

We examine the problem of assigning calls in a cellular mobile network to channels in the frequency domain. Such assignments must be made so that interference between calls is minimized, while demands for channels are satisfied. A new nonlinear integer programming representation of the static channel assignment (SCA) problem is formulated. We then propose two different neural networks for solving this problem. The first is an improved Hopfield (1982) neural network which resolves the issues of infeasibility and poor solution quality which have plagued the reputation of the Hopfield network. The second approach is a new self-organizing neural network which is able to solve the SCA problem and many other practical optimization problems due to its generalizing ability. A variety of test problems are used to compare the performance of the neural techniques against more traditional heuristic approaches. Finally, extensions to the dynamic channel assignment problem are considered.

In this paper design details of a RISC neuro-processor are presented. Neural network applications of Hopfield networks, self-organizing feature maps and multilayer feedforward networks (MFNN) are used as benchmarks for performance evaluation of the neuro-processor. Extensive simulations have been carried out to study the cost performance issues of neuro-processor hardware architecture. A quantitative approach is employed in designing cost-effective implementation of the neuro-processor. Special instructions have been provided in the neuro-processor instruction-set to improve the speed of both implementation and execution of neural networks. Instruction-set usage measurements have been used to study the effectiveness of the instruction-set design. Branch behaviour statistics have been studied in order to adopt good branch prediction strategies.

This paper presents expressions for the optimal step length to use when training a vector quantizer by stochastic approximation. By treating each update as an estimation problem, it provides a unified framework covering both batch and incremental training, which were previously treated separately, and extends existing results to the semibatch case. In addition, the new results presented provide a measurable improvement over results which were previously thought to be optimal.

In this paper, Kohonen's self-organizing feature map is modified by a novel technique of allowing the neurons in the feature map to compete in a selective manner. The selective competition is achieved by grating the N-dimensional feature space using a spatial frequency and setting a criterion for the neurons to compete based on the region in which the input pattern resides. The spatial grating and selective competition are achieved by introducing a gated neuronal architecture in the feature map. As the selection criterion changes with time, it generates a time sequence of winning node indexes providing more input information and potentially allowing higher classification performance. These time sequences are then used to predict the class label of the input pattern more accurately. Three possible class label prediction algorithms are formulated based on evidential reasoning method and Bayes conditional probability theorem. These are tested on real world 8-class texture and a synthetic 12-class 3D object recognition problems. The classification performance is then compared with the results obtained by using a standard statistical linear discriminant analysis.

In this paper it is shown that the spatio-temporal signature generated for any input pattern on a topologically ordered feature map using a gated neuronal architecture is invariant over a neighbourhood of the input pattern provided the input patterns lie in the interior of the decision space and the regions of competition created by n-dimensional spatial grating function at any given spatial frequency are open. The spatio-temporal signature in a Gated Neuronal Architecture uniquely represents a collection of disjoint regions in the feature space. For pattern classification the labeling of the set of disjoint regions represented by the spatio-temporal signature is obtained by using Bayes conditional probabilities. Simulation results indicate improved performance.>

Doppler signatures of experimental radar targets have been obtained and processed using conventional signal processing techniques to extract characteristic features. Radar target recognition using adaptive resonance theory, learning vector quantiser, feedforward, and probabilistic neural networks has been attempted. The performance characteristics of the above neural architectures in classifying the experimental radar targets are discussed and the results of a comparative study presented.>