Advanced data-intensive services and applications in IoT scenarios require efficient access to external resources for data processing and computation. Fog computing addresses such a need by moving part of the activity closer to the edge, alleviating network congestion and improving responsiveness. A major problem in scheduling the workflow required by IoT applications for their execution in fog nodes is accounting for the many Quality of Service requirements that should be guaranteed, as well as possible deadlines for workflow completion imposed by the applications. In this paper, we present a novel meta-heuristic approach for solving a deadline-constrained many-objective workflow scheduling problem that enhances the Arithmetic Optimization Algorithm with dynamic evolutionary state estimation for selecting arithmetic operators and balancing exploration and exploitation in the search space. Our approach also accounts for parallelization in task allocation and includes a repairing mechanism for infeasible solutions. The extensive experimental evaluation on benchmarks of real-world workflows, comparing against alternative algorithms, demonstrates the effectiveness of our approach.

Scene geometry estimation from images plays a key role in robotics, augmented reality, and autonomous systems. In particular, Monocular Depth Estimation (MDE) focuses on predicting depth using a single RGB image, avoiding the need for expensive sensors. State-of-the-art approaches use deep learning models for MDE while processing images as a whole, sub-optimally exploiting their spatial information. A recent research direction focuses on smaller image patches, as depth information varies across different regions of an image. This approach reduces model complexity and improves performance by capturing finer spatial details. From this perspective, we propose a novel warp patch-based extraction method which corrects perspective camera distortions, and employ it in tailored training and inference pipelines. Our experimental results show that our patch-based approach outperforms its full-image-trained counterpart and the classical crop patch-based extraction. With our technique, we obtain a general performance enhancements over recent state-of-the-art models. Code is available at https://github.com/AntonioFusillo/PatchMDE . • We propose a novel patch-based approach for monocular depth estimation. • Our method extracts patches from wide-aspect images, preserving camera parameters. • The designed patch-based inference outperforms full-image models in depth accuracy. • The proposed warp-based patch extraction is superior to patch cropping. • Our approach can wrap existing models, improving their performance.

In complex$360^{\circ }$scenes, depth estimation is challenging for small objects and the depth of object boundaries, which cannot be effectively solved with existing works.$360^{\circ }$depth estimation is unable to produce uniform depth estimate findings in both indoor and outdoor settings due to the datasets. In this paper, the Useg-PanoDepth and PanoDepth dataset is proposed to improve the above problems effectively. The Diagonal-aware Attention Module (DAM) effectively estimates small objects in complex scenes. Enhanced Boundary Module (EBM), for enhancing boundary information,can also effectively solve the problem of depth unification of indoor and outdoor scenes. Extensive experiments on our constructed PanoDepth dataset, Useg-PanoDepth achieves SOTA results. The Relative accuracy (deltahttps://github.com/xjh6/Useg-PanoDepth.

The rapid expansion of IoT devices has transformed numerous industries by enabling extensive data collection and real-time analytics. Federated Learning (FL) offers a decentralized model training paradigm that ensures data privacy, making it particularly suitable for IoT environments. Yet, it remains vulnerable to poisoning attacks that can severely compromise model integrity, wherein malicious clients compromise the global model by injecting poisoned updates. Existing defenses, which focus primarily on global model performance, often fail to effectively integrate local anomaly detection with global weighting mechanisms, thus limiting their efficacy against such threats. Addressing this research gap, we propose FLIFRA (Federated Learning Isolation Forest with Robust Aggregation), a hybrid defense framework that combines client-side anomaly detection using Isolation Forest (iForest) with dynamic reputation-based robust aggregation at the server. This dual-layer approach filters out malicious updates before aggregation and adjusts client reputations to mitigate adversarial influence. Our evaluation of three cybersecurity datasets (CIC-IDS2018, BoT-IoT, and UNSW-NB15) under various intensities of poisoning (10%, 20%, 30%, and 40%) demonstrates that the proposed method outperforms the traditional aggregation schemes of FedAvg, Krum, Trimmed Mean, DRRA, and WeiDetect in the literature. In particular, our framework achieves higher detection accuracy, faster convergence, and improved stability, even in highly heterogeneous data environments.

Distributed denial-of-service (DDoS) attacks pose a significant threat to network security by overwhelming systems with malicious traffic, leading to service disruptions and potential data breaches. The traditional centralized machine learning (ML) methods for detecting DDoS attacks in Internet of Things (IoT) environments raise privacy and security concerns due to their collection and distribution of data to a central entity that may not be trusted to perform model training. Federated learning (FL) offers a privacy-preserving solution that enables distributed collaboration by training a model only on local clients, without data exchanges, where the central entity only performs global model aggregation. However, the current practice of random client selection, combined with the statistical heterogeneity of client data and the device heterogeneity encountered in IoT environments, requires many training rounds to reach optimal accuracy, increasing the imposed computational overhead. To address these challenges, we propose a multiobjective optimization-based FL with adaptive client selection (FELACS) approach that maximizes client importance scores while satisfying resource, performance, and data diversity constraints. Experiments are carried out on the CIC-IDS2018, CIC-DDoS2019, BoT-IoT, and CIC-IoT2023 datasets, demonstrating that FELACS improves upon the accuracy of the existing approaches while exhibiting increased convergence speed when training a model in an FL scenario, hence reducing the number of communication rounds required to achieve the target accuracy, making it highly effective for performing IoT-based DDoS attack detection in FL scenarios.

In industrial computer vision applications, anomaly detection (AD) is a critical task for ensuring product quality and system reliability. However, many existing AD systems follow a modular design that decouples classification from detection and localization tasks. Although this separation simplifies model development, it often limits generalizability and reduces practical effectiveness in real-world scenarios. Deep neural networks offer strong potential for unified solutions. Nonetheless, most current approaches still treat detection, localization and classification as separate components, hindering the development of more integrated and efficient AD pipelines. To bridge this gap, we propose OneN (One Network), a unified architecture that performs detection, localization, and classification within a single framework. Our approach distills knowledge from a high-capacity convolutional neural network (CNN) into an attention-based architecture trained under varying levels of supervision. The resulting attention maps act as interpretable pseudo-segmentation masks, enabling accurate localization of anomalous regions. To further enhance localization quality, we introduce a progressive focal loss that guides attention maps at each layer to focus on critical features. We validate our method through extensive experiments on both standardized and custom-defined industrial benchmarks. Even under weak supervision, it improves performance, reduces annotation effort, and facilitates scalable deployment in industrial environments.

Automatically detecting surface defects in prismatic battery is crucial for ensuring quality meets established standards. Traditional methods face challenges in accurately identifying these defects due to their minute and varied shapes and high density of distribution. To address these issues, we propose an innovative network for prismatic battery surface defect (PBSD-Net), which employs shunted dynamic snake convolution and focal modulation to detect surface defects in prismatic battery. This network is integrated into the 2D-AOI system. Firstly, we introduce sliding slice amplification (SSA) as a training strategy to enhance the network’s ability to recognize densely clustered tiny defects. Secondly, we develop a novel method using the shunted dynamic snake convolution (SDSC) module and focal modulation (FM) to improve the extraction of deformation features, thereby addressing complex and sporadically scattered surface defects. By integrating the SDSC module and FM mechanism, the receptive field of the defect feature extraction network is expanded, enabling the acquisition of comprehensive defect edge features. Additionally, we introduce the quality focal loss (QFL) function to effectively tackle the issue of imbalanced sample types. Experimental results on the PBSD-RGB dataset demonstrate that our method achieves a mAP@50 of 85.8%, representing an improvement of approximately 7.7% over the baseline network. We have applied the PBSD-Net to an automatic defect detection system in a well-known battery production company. This enhancement significantly boosts the accuracy of surface defect detection in prismatic battery. The relevant code is at the https://github.com/yikuizhai/PBSD-Net.

In recent years, object detection models have been extensively applied across various industries, leveraging learned samples to recognize and locate objects. However, industrial environments present unique challenges, including complex backgrounds, dense object distributions, object stacking, and occlusion. To address these challenges, we propose the Global Dynamic Matching Transformer Network (GMTNet). GMTNet partitions images into blocks and employs a sliding window approach to capture information from each block and their interrelationships, mitigating background interference while acquiring global information for dense object recognition. By reweighting key-value pairs in multi-scale feature maps, GMTNet enhances global information relevance and effectively handles occlusion and overlap between objects. Furthermore, we introduce a dynamic sample matching method to tackle the issue of excessive candidate boxes in dense detection tasks. This method adaptively adjusts the number of matched positive samples according to the specific detection task, enabling the model to reduce the learning of irrelevant features and simplify post-processing. Experimental results demonstrate that GMTNet excels in dense detection tasks and outperforms current mainstream algorithms. The code will be available athttp://github.com/yikuizhai/GMTNet.

With the rapid advancements in deep learning technology, the field of remote sensing change detection (RSCD) has witnessed significant improvements and innovations. In this context, bitemporal image processing, using features directly extracted by the backbone for subsequent fusion operations, may be obstructed by external environmental factors, potentially limiting the effective capture of complex feature variations. Moreover, overlooking local features during the fusion of bitemporal features can significantly affect the final detection results. As a result, achieving accurate change detection (CD) still encounters various challenges. To tackle these issues, this paper proposes a CD network (AEGL-Net) with Adaptive Multiscale Enhancement (AME) and Global-Local Feature Fusion (GLFF) modules. First, AME enhances features at each stage of backbone extraction through an adaptive strategy, balancing the enhancement of semantic information and texture details. Then, GLFF is used to fuse the bitemporal image features, which enhances the modeling of global dependencies while also fusing shared and context-aware weights to enhance the local features. Finally, the merged features are fed into the decoder to generate precise change maps. Experiments conducted with four open RSCD datasets (LEVIR-CD, S2Looking, SYSU-CD, and UAV-CD) demonstrate that our proposed AEGL-Net outperforms ten state-of-the-art models in the RSCD field. Our code is available at https://github.com/yikuizhai/AEGL-Net.

Recently, Unsupervised Domain Adaptation (UDA) methods have attracted considerable attention in Remote Sensing Images (RSI) semantic segmentation. However, cross-domain RSI exhibit diverse scales, imbalanced distributions within domains, and significant inter-domain variations. In response to these challenges, we combine Spatial reconstruction and Joint training with the Transformer Network (SJT-Net). This framework introduces a spatial reconstruction method to address the issue of inconsistent ground sampling distances in cross domain RSI, which is rarely considered in existing approaches. Transferring domain knowledge at a similar spatial scale improves the spatial representation ability of UDA models. Unlike traditional adversarial training using ResNet for feature extraction, the SJT-Net employs Segformer, which enhances the model’s ability to capture in-class features across domains and improves global dependency modeling. Transmitting these refined features to the discriminator allows for more precise feature-level domain alignment. To enhance feature decoding, an interactive global-local decoder is constructed to efficiently capture both global relationships and local details of landform objects. Our framework leverages adversarial training to generate highly confident model weights and pseudo-labels for self-training in the target domain. Through iterative updates, the model’s generalization capability is gradually improved, eventually achieving optimal segmentation performance. Experimental results demonstrate that SJT-Net outperforms current UDA approaches and accomplishes state-of-the-art (SOTA) segmentation accuracy. The repository can be accessed at https://github.com/AnsonD0820/SJT-Net.

Metal surface defect recognition (MSDR) based on deep learning encounters the challenge of few-shot expert-labeled data. In this study, we proposed a CLIP-vision guided self supervised learning (CVGSSL) framework for representation learning of unlabeled data, completing MSDR using few-shot labeled data. This framework initially generates rich and diverse representation information through multiple CLIP-Vs to ensure effective SSL pretraining, followed by the design of an MLP-adapter to distill knowledge and adapt these representations to recognition tasks. In addition, we constructed a self-constrained loss to address the inherent problem of intraclass and interclass distance ambiguity that causes the representation to fall into an equivocal decision margin. Following label-free pretraining of CVGSSL, the downstream model adapts to one-shot to four-shot defect recognition tasks through fine-tuning. Experimental results demonstrate that CVGSSL outperforms state-of-the-art SSL methods across three public metal surface defect datasets, with the efficacy of the approach validated through extensive ablation experiments.

Fog computing is characterized by its proximity to edge devices, allowing it to handle data near the source. This capability alleviates the computational burden on data centers and minimizes latency. Ensuring high throughput and reliability of services in Fog environments depends on the critical roles of load balancing of resources and task scheduling. A significant challenge in task scheduling is allocating tasks to optimal nodes. In this paper, we tackle the challenge posed by the dependency between optimally scheduled tasks and the optimal nodes for task scheduling and propose a novel bi-level multi-objective task scheduling approach. At the upper level, which pertains to task scheduling optimization, the objective functions include the minimization of makespan, cost, and energy. At the lower level, corresponding to load balancing optimization, the objective functions include the minimization of response time and maximization of resource utilization. Our approach is based on an Improved Multi-Objective Ant Colony algorithm (IMOACO). Simulation experiments using iFogSim confirm the performance of our approach and its advantage over existing algorithms, including heuristic and meta-heuristic approaches.

Explainable methods for understanding deep neural networks are currently being employed for many visual tasks and provide valuable insights about their decisions. While post-hoc visual explanations offer easily understandable human cues behind neural networks’ decision-making processes, comparing their outcomes still remains challenging. Furthermore, balancing the performance-explainability trade-off could be a time-consuming process and require a deep domain knowledge. In this regard, we propose a novel auxiliary module, built upon convolutional-based encoders, which acts on the final layers of convolutional neural networks (CNNs) to learn orthogonal feature maps with a more discriminative and explainable power. This module is trained via a disentangle loss which specifically aims to decouple the object from the background in the input image. To quantitatively assess its impact on standard CNNs, and compare the quality of the resulting visual explanations, we employ metrics specifically designed for semantic segmentation tasks. These metrics rely on bounding-box annotations that may accompany image classification (or recognition) datasets, allowing us to compare both ground-truth and predicted regions. Finally, we explore the impact of various self-supervised pre-training strategies, due to their positive influence on vision tasks, and assess their effectiveness on our considered metrics.

In the evolving cybersecurity landscape, the rising frequency of Distributed Denial of Service (DDoS) attacks requires robust defense mechanisms to safeguard network infrastructure availability and integrity. Deep Learning (DL) models have emerged as a promising approach for DDoS attack detection and mitigation due to their capability of automatically learning feature representations and distinguishing complex patterns within network traffic data. However, the effectiveness of DL models in protecting against evolving attacks depends also on the design of adaptive architectures, through the combination of appropriate models, quality data, and thorough hyperparameter optimizations, which are scarcely performed in the literature. Also, within adaptive architectures for DDoS detection, no method has yet addressed how to transfer knowledge between different datasets to improve classification accuracy. In this paper, we propose an innovative approach for DDoS detection by leveraging Convolutional Neural Networks (CNN), adaptive architectures, and transfer learning techniques. Experimental results on publicly available datasets show that the proposed adaptive transfer learning method effectively identifies benign and malicious activities and specific attack categories.

As the growing trends in technology continue to drive massive transformation throughout the automotive sector, connected and autonomous transportation has become the future vision. Many researchers and practitioners wonder how connected, and autonomous vehicles will affect future transportation. This Special Issue explores some issues in the transition towards autonomous vehicles and their future trends and developments with artificial intelligence (AI) and robotics.

This special issue comprises 12 articles, showcasing the latest advances in computational social systems research.

Synthetic Aperture Radar (SAR) target image acquisition presents challenges and incurs high annotation costs. The emergence of self-supervised contrastive learning shows promise for SAR automatic target recognition (ATR) with limited data. However, SAR images suffer from poor discriminability and high sample similarity, hindering instance discrimination in contrastive learning. To address this, we propose Low-confidence Discriminant Contrastive Learning (LDCL), which integrates group-instance contrast and batch mixed training for SAR ATR. LDCL consists of two branches: classical instance discrimination and group-instance discrimination. We refine the SAR-group instance discrimination loss function by incorporating distance calculations to guide feature vectors towards nearest clusters, enhancing discrimination within the feature space. Additionally, we introduce a batch image mixing training strategy to reduce confidence in SAR instance discrimination while preserving intra-class consistency. Experimental results on small sample MSTAR and FUSAR-Ship datasets demonstrate that LDCL outperforms traditional transfer learning and self-supervised learning methods, achieving significantly higher recognition rates in SAR ATR tasks.

Remote sensing change detection (RSCD) focuses on identifying regions that have undergone changes between two remote sensing images captured at different times. Recently, convolutional neural networks (CNNs) have shown promising results in the challenging task of RSCD. However, these methods do not efficiently fuse bitemporal features and extract useful information that is beneficial to subsequent RSCD tasks. In addition, they did not consider multilevel feature interactions in feature aggregation and ignore relationships between difference features and bitemporal features, which thus affects the RSCD results. To address the above problems, a difference-guided multiscale aggregation attention network, DGMA2-Net, is developed. Bitemporal features at different levels are extracted through a Siamese convolutional network and a multiscale difference fusion module (MDFM) is then created to fuse bitemporal features and extract, in a multiscale manner, difference features containing rich contextual information. After the MDFM treatment, two difference aggregation modules (DAMs) are used to aggregate difference features at different levels for multilevel feature interactions. The features through DAMs are sent to the difference-enhanced attention modules (DEAMs) to strengthen the connections between bitemporal features and difference features and further refine change features. Finally, refined change features are superimposed from deep to shallow and a change map is produced. In validating the effectiveness of DGMA2-Net, a series of experiments are conducted on three public RSCD benchmark datasets (LEVIR-CD, BCDD, and SYSU-CD). The experimental results demonstrate that DGMA2-Net surpasses the current eight state-of-the-art methods in RSCD. Our code is released at https://github.com/yikuizhai/DGMA2-Net.

With the advancement of deep learning (DL) technologies, remarkable progress has been achieved in change detection (CD). Existing DL-based methods primarily focus on the discrepancy in bitemporal images, while overlooking the commonality in bitemporal images. However, one of the reasons hindering the improvement of CD performance is the inadequate utilization of image information. To address the above issue, we propose a Deeply Supervised Hybrid Feature Aggregation Network (DS-HyFA-Net). This network predicts changes by integrating the distinctness and the commonality in bitemporal images. Specifically, the DS-HyFA-Net primarily consists of a set of encoders and a Hybrid Feature Aggregation (HyFA) module. It uses a Siamese encoder (or Encoder I) and a specialized encoder (or Encoder II) to extract distinct and common features (CFs) in bitemporal images, respectively. The HyFA module efficiently aggregates distinct and common features (or hybrid features) and generates a change map using a predictor. In addition, a common feature learning strategy (CFLS) is introduced, based on deeply supervised (DS) techniques, to guide Encoder II in learning CFs. Experimental results on three well-recognized datasets demonstrate the effectiveness of the innovative DS-HyFA-Net, achieving F1-Scores of 93.33% on WHU-CD, 90.98% on LEVIR-CD, and 81.14% on SYSU-CD. Our code is available athttps://github.com/yikuizhai/DS-HyFA-Net.

Remote sensing change detection (RSCD) aims to identify changes within bi-temporal registered images. However, existing deep learning (DL)-based RSCD networks often suffer from large numbers of parameters, high computational complexity, and low inference speed, making it challenging to achieve efficient inference in real-world deployments. In addition, current models lack robust feature-fitting capabilities, necessitating the development of an efficient and powerful RSCD model to address this issue. Therefore, we propose a novel RSCD network named efficient adjacent feature harmonizer network (EAFH-Net) with fast computational speed and lightweight design. It is based on MobileNetV2, considering that change maps of different sizes contain temporal information of bitemporal features and spatial information at various scales, we introduce a multiscale feature neighbor fusion module (MFNFM) to address the lack of interaction between sophisticated-level and elementary-level features, and spatial and channel feature harmonizer module (SCFHM) to harmonize the spatiotemporal information of the change maps. Moreover, data-driven DL algorithms face another challenge due to insufficient granularity and the need for more practical datasets. Therefore, we present unmanned aerial vehicle (UAV)-CD+, a dataset comprising 2002 pairs of bi-temporal UAV low-altitude images, each sized at$1024\times 1024$. We performed experiments on three publicly accessible datasets in conjunction with UAV-CD+, comparing the results with other state-of-the-art (SOTA) methods. EAFH-Net attains the utmost precision, obtaining 91.74% on LEVIR-CD, 84.28% on SYSU-CD, 95.07% on WHU-CD, 79.12% on CLCD, and 70.12% on UAV-CD+. We have our model code available at the following link:https://github.com/yikuizhai/UCSFH-Net.

Man-made workpiece counting is a routine job for manufactory workers; however, this is an error-prone task. In this article, we are interested in detecting and counting arbitrary workpieces in industrial manufacturing. Therefore, we construct a comprehensive and large-scale open-world public benchmark dataset for workpiece counting, called workpiece counting dataset, which includes 121 475 instances of workpieces from 351 different categories. We also propose a novel method for workpiece detection and counting, named two-stage workpiece counting network. The first stage of the network is to develop a class-agnostic detector to localize each workpiece instance, followed by the second stage to employ an unsupervised deep clustering strategy with the backbone network pretrained in a workpiece convolutional autoencoder for decision boundary prediction, achieving workpiece clustering under unknownKvalues. Finally, our experiments show that the proposed method outperforms current mainstream methods, greatly enhancing the efficiency of factory operations.

UAVs can collect vehicle data in high-altitude scenes, playing a significant role in intelligent urban management due to their wide of view. Nevertheless, the current datasets for UAV-based vehicle detection are acquired at altitude below 150 meters. This contrasts with the data perspective obtained from high-altitude scenes, potentially leading to incongruities in data distribution. Consequently, it is challenging to apply these datasets effectively in high-altitude scenes, and there is an ongoing obstacle. To resolve this challenge, we developed a comprehensive vehicle dataset named LH-UAV-Vehicle, specifically collected at flight altitudes ranging from 250 to 400 meters. Collecting data at higher flight altitudes offers a broader perspective, but it concurrently introduces complexity and diversity in the background, which consequently impacts vehicle localization and recognition accuracy. In response, we proposed the pyramid dual pooling attention path aggregation network (PDPA-PAN), an innovative framework that improves detection performance in high-altitude scenes by combining spatial and semantic information. Object attention integration in both spatial and channel dimensions is aimed by the pyramid dual pooling attention module (PDPAM), which is achieved through the parallel integration of two distinct attention mechanisms. Furthermore, we have individually developed the pyramid pooling attention module (PPAM) and the dual pooling attention module (DPAM). The PPAM emphasizes channel attention, while the DPAM prioritizes spatial attention. This design aims to enhance vehicle information and suppress background interference more effectively. Extensive experiments conducted on the LH-UAV-Vehicle conclusively demonstrate the efficacy of the proposed vehicle detection method. Our code and dataset can be found at https://github.com/yikuizhai/PDPA-PAN.

Synthetic defect generation is an important aid for advanced manufacturing and production processes. Industrial scenarios rely on automated image-based quality control methods to avoid time-consuming manual inspections and promptly identify products not complying with specific quality standards. However, these methods show poor performance in the case of ill-posed low-data training regimes, and the lack of defective samples, due to operational costs or privacy policies, strongly limits their large-scale applicability.To overcome these limitations, we propose an innovative architecture based on an unpaired image-to-image (I2I) translation model to guide a transformation from a defect-free to a defective domain for common industrial products and propose simultaneously localizing their synthesized defects through a segmentation mask. As a performance evaluation, we measure image similarity and variability using standard metrics employed for generative models. Finally, we demonstrate that inspection networks, trained on synthesized samples, improve their accuracy in spotting real defective products.

The increasing number of connected devices is fostering a rising frequency of cyber attacks, with Distributed Denial of Service (DDoS) attacks among the most common.To counteract DDoS, companies and large organizations are increasingly deploying anomaly-based Intrusion Detection Systems (IDS), which detect attack patterns by analyzing differences in malicious network traffic against a baseline of legitimate traffic.To differentiate malicious and normal traffic, methods based on artificial intelligence and, in particular, Deep Learning (DL) are being increasingly considered, due to their ability to automatically learn feature representations for the different traffic types, without need of explicit programming or handcrafted feature extraction.In this paper, we propose a novel methodology for simulating an anomaly-based IDS based on adaptive DL by designing multiple DL models working with both binary and multi-label classification on multiple datasets with different degrees of complexity.To make the DL models adaptable to different conditions, we consider adaptive architectures obtained by automatically tuning the number of neurons for each situation.Results on publicly-available datasets confirm the validity of our proposed methodology, with DL models adapting to the different conditions by increasing the number of neurons on more complex datasets and achieving the highest accuracy in the binary classification configuration.anomaly-based IDSs work by establishing a baseline of "normal" network traffic and detecting "malicious" traffic and hence possible attacks when significant differences from the baseline are detected.Recent

Internet of Medical Things (IoMT) is igniting many emerging smart health applications, by continuously streaming the big data for data-driven innovations. One critical obstacle in IoMT big data is the power hungriness of long-term data transmission. Targeting this challenge, we propose a novel framework called, IoMT big-data Bayesian-backward deep-encoder learning (IBBD), which mines deep autoencoder (AE) configurations for data sparsification and determines optimal tradeoffs between information loss and power overhead. More specifically, the IBBD framework leverages an additional external Bayesian-backward loop that recommends AE configurations, on top of a traditional deep learning loop that executes and evaluate the AE quality. The IBBD recommendation is based on confidence to further minimize the regularized metrics that quantify the quality of AE configurations, and it further leverages regularization techniques to allow adjusting error–power tradeoffs in the mining process. We have conducted thorough experiments on a cardiac data streaming application and demonstrated the superiority of IBBD over the common practices such as discrete wavelet transform, and we have further generalized IBBD through validating the optimal AE configurations determined on one user to other users. This study is expected to greatly advance IoMT big data streaming practices toward precision medicine.

Compared to other well-known biometric technologies based on physiological traits (e.g., fingerprint, iris, and face), heart biometrics are more robust to presentation attacks and are particularly suitable for continuous/periodic recognition.Most studies on heart biometrics concern electrocardiogram (ECG) and photoplethysmogram (PPG).While the reported results are encouraging, to the best of our knowledge, no studies have been conducted on the interoperability between ECG and PPG biometrics.We present a novel method that is capable of performing single-domain and multiple-domain identity verifications for ECG and PPG signals, providing interoperability between the heterogeneous cardiac signals.Our method does not require the computation of any reference/fiducial point and uses a compact representation of the given signals.We propose MultiCardioNet, a novel Siamese neural network trained by using an ad hoc learning algorithm.MultiCardioNet computes a similarity score between two spectrogram-based representations of cardiac signals.Our learning algorithm iteratively computes a balanced subset of genuine and impostor pairs during the training epochs.We performed experiments on a dataset containing 1,008 pairs of ECG and PPG samples, obtaining accuracy comparable to that of the state-of-the-art methods for single-domain scenarios and demonstrating only a relatively small performance decrease in the multiple-domain scenario.

Artificial intelligence (AI) continues demonstrating its positive impact on society and successful adoptions in data-rich domains including social computing systems. There are serious ethical and legal concerns about AI’s ability to make decisions in a responsible way. Many principles and guidelines for responsible AI (RAI) have been issued by governments, research organizations, and enterprises. For instance, the Institute for Ethical Machine Learning provides various RAI resources[1], including higher level guidelines and frameworks, tools, standards, regulations, course, and so on. However, high-level principles are far from ensuring the trustworthiness of AI systems.

The papers presented in this special issue focus on technological innovations in wearable, implantable, mobile, and remote healthcare that include Internet of Things (IoT), sensor informatics, and patient monitoring applications. These new technologies are used to track the key signs of people’s health to improve their lifestyle and health disorders. Innovations in IoT devices play a vital role in assisting patients in managing their health conditions. Thanks to the advent of modern communication technologies and Internet of Things (IoT) paradigms that have made the implementation of biomedical devices nearly universal. Now with the evolving industrial revolution, patients and healthcare providers are expecting something more. Practically speaking, healthcare wearables have experienced tremendous growth in the past few years, and it is expected to grow even more shortly, making it an ideal space for the biomedical informatics research community to solve complex healthcare problems and more informed decision making to improve human health.

introduction Share on Introduction to the Special Section on Internet of Behavior for Emerging Technologies Authors: Mu-Yen Chen National Cheng Kung University, Taiwan National Cheng Kung University, Taiwan 0000-0002-3945-4363View Profile , Vincenzo Piuri University of Milan, Italy University of Milan, Italy 0000-0003-3178-8198View Profile , Alireza Souri Haliç University, Turkey Haliç University, Turkey 0000-0001-8314-9051View Profile , Mohammad Shojafar University of Surrey, UK University of Surrey, UK 0000-0003-3284-5086View Profile Authors Info & Claims ACM Transactions on Sensor NetworksVolume 19Issue 2Article No.: 23pp 1–3https://doi.org/10.1145/3589021Published:16 May 2023Publication History 0citation21DownloadsMetricsTotal Citations0Total Downloads21Last 12 Months21Last 6 weeks21 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Recent advances in computation, communication, and control technologies have revolutionized the way that humans, smart things, and intelligent systems interact and exchange information. Intelligent cyber–physical systems (ICPSs), characterized by the deep complex intertwining process among cyber components for computation and control with intelligent technologies and the dynamic physical components, will fuel this revolution. Examples of ICPS include intelligent automotive and transportation systems, intelligent avionics systems, smart home, smart building, smart community, smart grid, smart healthcare systems, intelligent wearable systems, intelligent energy systems, robotic systems, etc. Bringing machine/deep-learning-based intelligence techniques into CPSs can improve the performance in many aspects. However, this also imposes new security, privacy, and trust challenges, which highlights the need to develop novel methodologies to tackle these challenges. In this special issue, we will publish the following articles.

Computational social systems (CSSs) focus on topics such as modeling, simulation, analysis, and understanding of social systems from the quantitative and/or computational perspective. “Systems” can be man–man, man–machine, and machine–machine organizations and adversarial situations as well as social media structures and their dynamics[1],[2]. With the advance of the Internet of Things and communication technologies, various kinds of data from diverse areas can be acquired nowadays. As a result, CSSs are becoming ever more complex. Data-driven CSSs aim to conduct pre-competitive research on architectures and design, modeling, and analysis techniques for cyber-physical systems, with emphasis on making full use of big data and artificial intelligence. These applications include transportation systems, automation, security, smart buildings, smart cities, medical systems, energy generation and distribution, water distribution, agriculture, military systems, process control, asset management, and robotics[3],[4],[5]. However, due to the progressive transformation from host-centric networking to information-centric networking, CSSs pose fundamental challenges in multiple aspects, such as heterogeneous data generation, efficient data sensing and collection, real-time data processing, and greater request arrival rates. Thus, there is a great need for a powerful way that can deal with emerging issues in data-driven CSSs more efficiently and effectively in the age of big data.

In recent years, impressive performance of deep learning technology has been recognized in synthetic aperture radar (SAR) automatic target recognition (ATR). Since a large amount of annotated data are required in this technique, it poses a trenchant challenge to the issue of obtaining a high recognition rate through less labeled data. To overcome this problem, inspired by the contrastive learning, we proposed a novel framework named batch instance discrimination and feature clustering (BIDFC). In this framework, different from that of the objective of general contrastive learning methods, embedding distance between samples should be moderate because of the high similarity between samples in the SAR images. Consequently, our flexible framework is equipped with adjustable distance between embedding, which we term as weakly contrastive learning. Technically, instance labels are assigned to the unlabeled data in per batch, and random augmentation and training are performedfewtimes on these augmented data. Meanwhile, a novel dynamic-weighted variance loss (DWV loss) function is also posed to cluster the embedding of enhanced versions for each sample. The experimental results on the moving and stationary target acquisition and recognition (MSTAR) database indicate a 91.25% classification accuracy of our method fine-tuned on only 3.13% training data. Even though a linear evaluation is performed on the same training data, the accuracy can still reach 90.13%. We also verified the effectiveness of BIDFC in OpenSarShip database, indicating that our method can be generalized to other data sets. Our code is available at:https://github.com/Wenlve-Zhou/BIDFC-master.

The Industrial Internet of Things (IoT) typically consists of several thousands of heterogeneous devices, such as sensors, actuators, access points, machinery, end-users' handheld equipment, and supply chain. In such an industrial environment, a multitude of data is generated from massive IoT devices, e.g., sensors for monitoring the environment, reading temperature, and gauging pressure. Most of the data are from delay-sensitive and computation-intensive applications, such as real-time manufacturing and automated diagnostics, which require big data analytics with low latency. Machine learning (ML) has been witnessed as an efficient solution for big data analytics. The majority of such ML algorithms are centralized methods, meaning that they first gather data from different users for use as a training dataset, which is placed on the ML server, and then build a model to classify the new data samples by applying the ML algorithms to this training dataset. However, the access to these datasets in the centralized ML methods raises concerns about data privacy for users. Federated learning (FL) was designed to protect data privacy to address a part of these issues. In FL, each participant uses a global training model without uploading their private data to a third-party server. Compared with the conventional ML, FL can preserve data security, especially in terms of participant data during the learning process. In particular, FL can also help in updating server-side data for the global model, and the participant is not required to provide their data. However, in FL, individual computing units may show abnormal actions, such as faulty software, hardware invasions, unreliable communication channels, and malicious samples deliberately crafting the model. To mitigate these challenges, we require robust policies to control the learning phases in FL. Motivated by the abovementioned issues, this special section solicits original research and practical contributions that advance the security and privacy of the FL solutions for industrial IoT applications as follows.

Intelligent transportation system (ITS) is a key enabler for future road traffic management systems. The core components of ITS include vehicles, roadside units, and traffic command centers. They generate a large amount of data flow that is made up of both mobility and service-related data. Therefore, some data science methods to handle the transportation data are very necessary for ITS. Although some attempts have been done to explore data science methods for ITS, there exist various scientific and engineering challenges including software and hardware development, computational complexity, data multi-source heterogeneity, and privacy protection. Consequently, to fully explore the benefits of ITS applications like connected and autonomous vehicles, traffic control and prediction, road safety, and accident prediction, advanced data science methodologies and applications are in great need.

Computer Aided Diagnosis (CAD) systems are increasingly utilizing image analysis and Deep Learning (DL) techniques, due to their high accuracy in several medical imaging fields, including the detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) from peripheral blood samples. However, no method in the literature has specifically analyzed the focus quality of ALL images or proposed a technique for sharpening the samples in an adaptive way for the purpose of classification. To address this issue, in this paper we propose the first machine learning-based approach able to enhance blood sample images by an adaptive unsharpening method. The method uses image processing techniques and DL to normalize the radius of the cell, estimate the focus quality, adaptively improve the sharpness of the images, and then perform the classification. We evaluated the methodology on a public database of ALL images, considering several state-of-the-art CNNs to perform the classification, with results showing the validity of the proposed approach. For a complete reproducibility of the work, the source code is available at: http://iebil.di.unimi.it/cnnALL/index.htm.

The unprecedented development of the Internet of Things (IoT), artificial intelligence (AI), and Big Data has stimulated a boom of social networks such as Twitter, WeChat, Facebook, etc., generating a huge amount of social data that are worth further analysis. Social computing has an important focus on mining the deep relationships between social organizations, networks, and media. The increasing volumes and complexities make big social data mining more and more difficult. Hybrid Human–Artificial Intelligence (H-AI) is an approach combining both human intelligence and AI, so as to handle demanding problems in a harmonious way. By adopting H-AI in social computing, it would provide more possibilities for social data analysis, relationship discovery, outlier detection, and prediction, and is proving to be an emerging and promising direction for AI and big data research.

When moving large and heterogeneous data collections to the cloud, a key requirement concerns the selection of the most suitable (set of) cloud service(s) for outsourcing. Not only can different resources have different characteristics and requirements, but different cloud providers can also offer different services and security guarantees, and can have different costs. Selecting a single service for outsourcing an entire data collection can result in a non-optimal solution, as a single service satisfying, at reasonable costs, all the requirements specified by the data owner might not exist. Selecting a set of services could instead ensure the satisfaction of the requirements, possibly with economic advantages. In this article, we address this problem and present a flexible and expressive, yet simple model for supporting data owners in identifying a proper allocation of their resources to a set of cloud services. Our model allows data owners to specify in an easy and intuitive way protection requirements operating at the granularity level of single resource (or class thereof), and representing the minimum security guarantees that a cloud service must offer to store resources. Resources can be outsourced in plaintext or encrypted form, depending on their requirements and on what is the most convenient allocation. Data owners can then also specify global allocation requirements that apply to the overall allocation, to reduce the burden on their side and to avoid excessive fragmentation of the resource collection. We solve the problem of finding an allocation that satisfies both the protection and the global allocation requirements, while minimizing economic costs, by formulating it as a binary programming problem, thus allowing the use of existing techniques for its efficient solution.

With the cloud emerging as a successful paradigm for conveniently storing, accessing, processing, and sharing information, the cloud market has seen an incredible growth. An ever-increasing number of providers offer today several cloud plans, with different guarantees in terms of service properties such as performance, cost, or security. While such a variety naturally corresponds to a diversified user demand, it is far from trivial for users to identify the cloud providers and plans that better suit their specific needs. In this paper, we address the problem of supporting users in cloud plan selection. We characterize different kinds of requirements that may need to be supported in cloud plan selection and introduce a very simple and intuitive, yet expressive, language that captures different requirements as well as preferences users may wish to express. The corresponding formal modeling permits to reason on requirements satisfaction to identify plans that meet the constraints imposed by requirements, and to produce a preference-based ranking among such plans.

Unsupervised Learning (UL) models are a class of Machine Learning (ML) which concerns with reducing dimensionality, data factorization, disentangling and learning the representations among the data. The UL models gain their popularity due to their abilities to learn without any predefined label, and they are able to reduce the noise and redundancy among the data samples. However, generalizing the UL models for different applications including image generation, compression, encoding, and recognition faces different challenges due to limited available data for learning, diversity, and complex dimensions. To overcome such challenges, we propose a partial learning procedure by utilizing the β-Non Negative Matrix Factorization (β-NMF), which maps the data into two complementary subspaces constituting generalized driven priors among the data. Moreover, we employ a dual-shallow Autoencoder (AE) to learn the subspaces separately or jointly for image reconstruction and visualization tasks, where our model performance shows superior results to the literary works when learning the model with a small amount of data and generalizing it for large-scale unseen data.

With significant and continuing advances in information and communication technologies, the Internet of Things (IoT) will play an increasingly important role in domains, such as healthcare, transportation, finance, and energy. In an IoT system, billions of devices (e.g., sensors, wearables, and smart appliances) are connected to the global network infrastructure, and one associated phenomenon is the generation of a large volume of data. Apart from data volume, the velocity, variety, and veracity of these data will pose a significant burden on conventional networking infrastructures. However, as sensor and fifth-generation (5G) cellular technologies advance, so will the pervasiveness of IoT deployment. Parallel to this trend, cloud computing has been integrated with IoT in order to address limitations in existing IoT networks (e.g., storage and computing resources), and examples include Google cloud dataflow and Amazon IoT. However, cloud-centric IoT solutions may not be suited for delay-sensitive and computationally intensive applications, for example, due to resource availability, end-to-end latency, bandwidth, etc. Increasingly, large-scale IoT deployments demand high connectivity, interoperability, and orchestration which are necessary for minimizing latency and maximizing throughput. This highlights the importance of a distributed computing platform that can support the interactions between IoT and cloud computing systems.

Renewable energy production is constantly growing worldwide, and some countries produce a relevant percentage of their daily electricity consumption through wind energy. Therefore, decision support systems that can make accurate predictions of wind-based power production are of paramount importance for the traders operating in the energy market and for the managers in charge of planning the nonrenewable energy production. In this paper, we present a decision support system that can predict electric power production, estimate a variability index for the prediction, and analyze the wind farm (WF) production characteristics. The main contribution of this paper is a novel system for long-term electric power prediction based solely on the weather forecasts; thus, it is suitable for the WFs that cannot collect or manage the real-time data acquired by the sensors. Our system is based on neural networks and on novel techniques for calibrating and thresholding the weather forecasts based on the distinctive characteristics of the WF orography. We tuned and evaluated the proposed system using the data collected from two WFs over a two-year period and achieved satisfactory results. We studied different feature sets, training strategies, and system configurations before implementing this system for a player in the energy market. This company evaluated the power production prediction performance and the impact of our system at ten different WFs under real-world conditions and achieved a significant improvement with respect to their previous approach.

Generative Adversarial Networks (GAN) are being increasingly used to perform face aging due to their capabilities of automatically generating highly-realistic synthetic images by using an adversarial model often based on Convolutional Neural Networks (CNN). However, GANs currently represent black box models since it is not known how the CNNs store and process the information learned from data. In this paper, we propose the first method that deals with explaining GANs, by introducing a novel qualitative and quantitative analysis of the inner structure of the model. Similarly to analyzing the common genes in two DNA sequences, we analyze the common filters in two CNNs. We show that the GANs for face aging partially share their parameters with GANs trained for heterogeneous applications and that the aging transformation can be learned using general purpose image databases and a fine-tuning step. Results on public databases confirm the validity of our approach, also enabling future studies on similar models.

Nowadays, for different purposes and contexts, we interact with a lot of different smart devices in our daily lives. Most of these devices are connected to the Internet and are therefore commonly referred to as the Internet of Things (IoT). Mobile edge computing (MEC) has recently evolved as an emerging technique by moving the computing and storage resources from the cloud to the edge of the network. The MEC supports IoT devices to improve their efficiency and scalability; helps to reduce latency delay for real-time applications, bandwidth bottlenecks, and energy consumption; and delivers contextual information processing. MEC offers many features and capabilities, such as access to a multitude of network interface (from 4G and 5G to Wi-Fi), support for device mobility, device context, geo-location awareness, and geographical distribution. Such attributes can support the real-time processing requirements of the Internet of Everything application, such as patient care, disaster management and detection (e.g., earthquakes), and flood monitoring. However, to fully exploit the potential of MEC in the IoT applications, many challenges need to be addressed, such as issues related to IoT Big Data, effective management of data storage and computing, privacy and security concerns, and innovative and emerging communication paradigm (e.g., 5G), require new architectures, applications, and methods.

Touchless palmprint recognition systems enable high-accuracy recognition of individuals through less-constrained and highly usable procedures that do not require the contact of the palm with a surface. To perform this recognition, methods based on local texture descriptors and convolutional neural networks (CNNs) are currently used to extract highly discriminative features while compensating for variations in scale, rotation, and illumination in biometric samples. In particular, the main advantage of CNN-based methods is their ability to adapt to biometric samples captured with heterogeneous devices. However, the current methods rely on either supervised training algorithms, which require class labels (e.g., the identities of the individuals) during the training phase, or filters pretrained on general-purpose databases, which may not be specifically suitable for palmprint data. To achieve a high-recognition accuracy with touchless palmprint samples captured using different devices while neither requiring class labels for training nor using pretrained filters, we introduce PalmNet, which is a novel CNN that uses a newly developed method to tune palmprint-specific filters through an unsupervised procedure based on Gabor responses and principal component analysis (PCA), not requiring class labels during training. PalmNet is a new method of applying Gabor filters in a CNN and is designed to extract highly discriminative palmprint-specific descriptors and to adapt to heterogeneous databases. We validated the innovative PalmNet on several palmprint databases captured using different touchless acquisition procedures and heterogeneous devices, and in all cases, a recognition accuracy greater than that of the current methods in this paper was obtained.

Image-based methods for estimating the particle size distribution (granulometry) usually analyze two-dimensional (2-D) samples of particles disposed on a conveyor belt. Such approaches have to deal with occlusions and cannot evaluate the thickness of each particle. Three-dimensional (3-D) vision systems can reduce the acquisition constraints and speed up the quality control process. This paper proposes a novel 3-D vision system for analyzing the granulometry of falling particles. The system is designed to work in real time and to compute a partial 3-D reconstruction of the particle from a single pair of two-view images, which is then enhanced by using a neural-based technique. The validation of the proposed approach has been performed by considering three application scenarios for which the system achieved satisfactory accuracy and robustness.

Touchless fingerprint recognition systems are being increasingly used for a fast, hygienic, and distortion-free recognition. However, due to the greater complexity of the algorithms required for processing touchless fingerprint samples, currently only Level 1 and Level 2 features are being used for recognition, and Level 3 features are used only in touch-based optical devices with about 1000 ppi resolution. In this paper, we propose the first innovative method in the literature able to extract Level 3 features, in particular sweat pores, from fingerprint images captured with a touchless acquisition using a commercial off-the-shelf camera. The method uses image processing algorithms to extract a set of candidate sweat pores. Then, computational intelligence techniques based on neural networks are used to learn the local features of the real pores, and select only the actual sweat pores from the set of candidate points. The results show the validity of the proposed methodology, with the majority of the pores correctly extracted, indicating that a touchless fingerprint recognition using Level 3 features is feasible.

editorial Free Access Share on Introduction to Special Issue on Multimedia Big Data: Networking Editors: Mianxiong Dong Muroran Institute of Technology, Japan Muroran Institute of Technology, JapanView Profile , Vincenzo Piuri Università degli Studi di Milano, Italy Università degli Studi di Milano, ItalyView Profile , Shueng-Han Gary Chan The Hong Kong University of Science and Technology, Hong Kong The Hong Kong University of Science and Technology, Hong KongView Profile , Ramesh Jain University of California, Irvine, CA University of California, Irvine, CAView Profile Authors Info & Claims ACM Transactions on Multimedia Computing, Communications, and ApplicationsVolume 12Issue 5sDecember 2016 Article No.: 70pp 1–3https://doi.org/10.1145/2989214Published:21 September 2016Publication History 1citation336DownloadsMetricsTotal Citations1Total Downloads336Last 12 Months17Last 6 weeks2 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

Touchless fingerprint recognition systems do not require contact of the finger with any acquisition surface and thus provide an increased level of hygiene, usability, and user acceptability of fingerprint-based biometric technologies. The most accurate touchless approaches compute 3-D models of the fingertip. However, a relevant drawback of these systems is that they usually require constrained and highly cooperative acquisition methods. We present a novel, fully touchless fingerprint recognition system based on the computation of 3-D models. It adopts an innovative and less-constrained acquisition setup compared with other previously reported 3-D systems, does not require contact with any surface or a finger placement guide, and simultaneously captures multiple images while the finger is moving. To compensate for possible differences in finger placement, we propose novel algorithms for computing 3-D models of the shape of a finger. Moreover, we present a new matching strategy based on the computation of multiple touch-compatible images. We evaluated different aspects of the biometric system: acceptability, usability, recognition performance, robustness to environmental conditions and finger misplacements, and compatibility and interoperability with touch-based technologies. The proposed system proved to be more acceptable and usable than touch-based techniques. Moreover, the system displayed satisfactory accuracy, achieving an equal error rate of 0.06% on a dataset of 2368 samples acquired in a single session and 0.22% on a dataset of 2368 samples acquired over the course of one year. The system was also robust to environmental conditions and to a wide range of finger rotations. The compatibility and interoperability with touch-based technologies was greater or comparable to those reported in public tests using commercial touchless devices.

This issue contains six papers presented during the Ninth IEEE RIVF International Conference onComputing and Communication Technologies (RIVF 2012), held in Ho Chi Minh City (Vietnam) in the period Feb. 27 -Mar.01, 2012.Since its inception in 2003, the RIVF conference -Research, Innovation, and Vision for the Future -has become a major international scientific event in the field of Computing, Communication and Information Technologies.RIVF 2012 received 141 papers from 26 countries, submitted to seven specialised tracks of the conference.Each submission was first evaluated by at least two reviewers, and over two third of them by three or four reviewers, followed by discussions with the track chairs.Finally, the program chairs had an overall review of the recommendations by the track chairs, and decided to accept 35 long papers and 24 short papers, resulting in the acceptance rates of 41.8%.The conference program also included a poster session for authors to present their on-going work.The authors of top ten papers that received the highest evaluation scores were invited to submit the extended versions of their contributions.After an additional review process (at least two reviewers for each paper), six papers were selected and included in this special issue.To help the reader to get a better insight into this special issue, we provide brief overviews for each of the papers of this issue.In the paper Quadratic Algorithms for Testing of Codes and ⋄-Codes, Nguyen Dinh Han, Ho Ngoc Vinh, Dang Quyet Thang and Phan Trung Huy present a modification of the Sardinas-Patterson's test that can deduce more effective testing algorithm for codes.As a consequence, for a given at input a regular language X defined by a tuple (ϕ, M, B), where ϕ : A * → M is a monoid morphism saturating X, M is a finite monoid, B ⊆ M , X = ϕ -1 (B), the authors established an algorithm that decides in time O(n 2 ) whether X is a code, where n = |M | can be chosen as the finite index of X.Also the quadratic algorithm for testing of ⋄-codes is also established.

Nowadays, biometrics is an important technological area receiving continuously growing interest from academia, industry, government, and the general public, due to the criticality and the social impact of its applications. Biometric systems are in fact rapidly being adopted in a wide variety of applications such as security, ambient intelligence, electronic and physical access control, digital rights management, background checking and defense, medical diagnosis as well as for adaptive environments.

An early wildfire detection is essential in order to assess an effective response to emergencies and damages. In this paper, we propose a low-cost approach based on image processing and computational intelligence techniques, capable to adapt and identify wildfire smoke from heterogeneous sequences taken from a long distance. Since the collection of frame sequences can be difficult and expensive, we propose a virtual environment, based on a cellular model, for the computation of synthetic wildfire smoke sequences. The proposed detection method is tested on both real and simulated frame sequences. The results show that the proposed approach obtains accurate results.

The estimation of the volume occupied by an object is an important task in the fields of granulometry, quality control, and archaeology. An accurate and well know technique for the volume measurement is based on the Archimedes' principle. However, in many applications it is not possible to use this technique and faster contact-less techniques based on image processing or laser scanning should be adopted. In this work, we propose a low-cost approach for the volume estimation of different kinds of objects by using a two-view vision approach. The method first computes a reduced three-dimensional model from a single couple of images, then extracts a series of features from the obtained model. Lastly, the features are processed using a computational intelligence approach, which is able to learn the relation between the features and the volume of the captured object, in order to estimate the volume independently of its position and angle, and without computing a full three-dimensional model. Results show that the approach is feasible and can obtain an accurate volume estimation. Compared to the direct computation of the volume from the three-dimensional models, the approach is more accurate and also less dependent to the position and angle of the measured objects with respect to the cameras.

Traditional biometric systems based on the fingerprint characteristics acquire the biometric samples using touch-based sensors. Some recent researches are focused on the design of touch-less fingerprint recognition systems based on CCD cameras. Most of these systems compute three-dimensional fingertip models and then apply unwrapping techniques in order to obtain images compatible with biometric methods designed for images captured by touch-based sensors. Unwrapped images can present different problems with respect to the traditional fingerprint images. The most important of them is the presence of deformations of the ridge pattern caused by spikes or badly reconstructed regions in the corresponding three-dimensional models. In this paper, we present a neural-based approach for the quality estimation of images obtained from the unwrapping of three-dimensional fingertip models. The paper also presents different sets of features that can be used to evaluate the quality of fingerprint images. Experimental results show that the proposed quality estimation method has an adequate accuracy for the quality classification. The performances of the proposed method are also evaluated in a complete biometric system and compared with the ones obtained by a well-known algorithm in the literature, obtaining satisfactory results.

Support vector regression (SVR) is based on a linear combination of displaced replicas of the same function, called a kernel. When the function to be approximated is nonstationary, the single kernel approach may be ineffective, as it is not able to follow the variations in the frequency content in the different regions of the input space. The hierarchical support vector regression (HSVR) model presented here aims to provide a good solution also in these cases. HSVR consists of a set of hierarchical layers, each containing a standard SVR with Gaussian kernel at a given scale. Decreasing the scale layer by layer, details are incorporated inside the regression function. HSVR has been widely applied to noisy synthetic and real datasets and it has shown the ability in denoising the original data, obtaining an effective multiscale reconstruction of better quality than that obtained by standard SVR. Results also compare favorably with multikernel approaches. Furthermore, tuning the SVR configuration parameters is strongly simplified in the HSVR model.

The visual analysis of peripheral blood samples is an important test in the procedures for the diagnosis of leukemia. Automated systems based on artificial vision methods can speed up this operation and increase the accuracy and homogeneity of the response also in telemedicine applications. Unfortunately, there are not available public image datasets to test and compare such algorithms. In this paper, we propose a new public dataset of blood samples, specifically designed for the evaluation and the comparison of algorithms for segmentation and classification. For each image in the dataset, the classification of the cells is given, as well as a specific set of figures of merits to fairly compare the performances of different algorithms. This initiative aims to offer a new test tool to the image processing and pattern matching communities, direct to stimulating new studies in this important field of research.

A multi-kernel Support Vector Machine model, called Hierarchical Support Vector Regression (HSVR), is proposed here. This is a self-organizing (by growing) multiscale version of a Support Vector Regression (SVR) model. It is constituted of hierarchical layers, each containing a standard SVR with Gaussian kernel, at decreasing scales. HSVR have been applied to a noisy synthetic dataset. The results illustrate their power in denoising the original data, obtaining an effective multiscale reconstruction of better quality than that obtained by standard SVR. Furthermore with this approach the well known problem of tuning the SVR parameters is strongly simplified.

Traditional fingerprint biometric systems capture the user fingerprint images by a contact-based sensor. Differently, contactless systems aim to capture the fingerprint images by an approach based on a vision system without the need of any contact of the user with the sensor. The user finger is placed in front of a special CCD-based system that captures the pattern of ridges and valleys of the fingertips. This approach is less constrained by the point of view of the user, but it requires much more capability of the system to deal with the focus of the moving target, the illumination problems and the complexity of the background in the captured image. During the acquisition procedure, the quality of each frame must be carefully evaluated in order to extract only the correct frames with valuable biometric information from the sequence. In this paper, we present a neural-based approach for the quality estimation of the contactless fingertips images. The application of the neural classification models allowed for a relevant reduction of the computational complexity permitting the application in real-time. Experimental results show that the proposed method has an adequate accuracy, and it can capture fingerprints at a distance up to 0.2 meters.

In this paper, a novel real-time online network model is presented. It is derived from the hierarchical radial basis function (HRBF) model and it grows by automatically adding units at smaller scales, where the surface details are located, while data points are being collected. Real-time operation is achieved by exploiting the quasi-local nature of the Gaussian units: through the definition of a quad-tree structure to support their receptive field local network reconfiguration can be obtained. The model has been applied to 3-D scanning, where an updated real-time display of the manifold to the operator is fundamental to drive the acquisition procedure itself. Quantitative results are reported, which show that the accuracy achieved is comparable to that of two batch approaches: batch HRBF and support vector machines (SVMs). However, these two approaches are not suitable to real-time online learning. Moreover, proof of convergence is also given.

The classification of wood types is needed in many industrial sectors, since it can provide relevant information concerning the features and characteristics of the final product (appearance, cost, mechanical properties, etc.). This analysis is typical in the furniture industries and the wood panel production. Usually, the analysis is performed by human experts, is not rapid, and has a nonuniform accuracy related mainly to the operator's experience and attention. This paper presents a methodology to effectively cope with the design of an automatic wood types classification system based on the analysis of the fluorescence spectra suitable for real-time applications. This paper presents an experimental set up based on a laser source, a spectrometer, and a processing system, and then, it discusses a set of techniques suitable to extract features from the spectra and how to exploit the extracted feature to train an inductive classification system capable to properly classify the wood types. Obtained experimental results show that the proposed approach can achieve a good accuracy in the classification and requires a limited computational power, hence allowing for the application in real-time industrial processes.

The detection of the iris boundaries is considered in the literature as one of the most critical steps in the identification task of the iris recognition systems. In this paper we present an iterative approach to the detection of the iris center and boundaries by using neural networks. The proposed algorithm starts by an initial random point in the input image, then it processes a set of local image properties in a circular region of interest searching for the peculiar transition patterns of the iris boundaries. A trained neural network processes the parameters associated to the extracted boundaries and it estimates the offsets in the vertical and horizontal axis with respect to the estimated center. The coordinates of the starting point are then updated with the processed offsets. The steps are then iterated for a fixed number of epochs, producing an iterative refinements of the coordinates of the pupils center and its boundaries. Experiments showed that the method is feasible and it can be exploited even in non-ideal operative condition of iris recognition biometric systems.

A serious concern in the design and use of biometric authentication systems is the privacy protection of the information derived from human biometric traits, especially since such traits cannot be replaced. Combining cryptography and biometrics, several recent works proposed to build the protection in the biometric templates themselves. While these solutions can increase the confidence in biometric systems when biometric information is stored for verification, they have been shown difficult to apply to real biometrics. In this work we present a biometric authentication technique that exploits multiple biometric traits. It is privacy-aware as it ensures privacy protection and allows the extraction of secure identifiers by means of cryptographic primitives. We also discuss the implementation of our approach by considering, as a significant example, the combination of iris and fingerprint biometrics and present experimental results obtained from real data. The implementation shows the feasibility of the scheme in practical applications.

In a Web-oriented society, organization, retrieval, and classification of digital images have become one of the major endeavors. In this paper, we study the mechanisms of fuzzy clustering and fuzzy clustering with partial supervision in the analysis and classification of images. It is demonstrated that the main features of fuzzy clustering become essential in revealing the structure in a collection of images and supporting their classification. The discussed operational framework of fuzzy clustering is realized by means of fuzzy c-means (FCM). When dealing with the mode of partial supervision, we augment an original objective function guiding the clustering process by an additional component expressing a level of coincidence between the membership degrees produced by the FCM and class allocation supplied by the user(s). The study also contrasts the use of the technology of fuzzy sets in image clustering with other approaches studied in this area. A suite of experiments deals with two collections of images, namely, Columbia object image library (COIL-20) and a database composed of 2000 outdoor images.

An online procedure for configuring the parameters of a hierarchical radial basis functions (HRBF) network is presented here. The proposed procedure has been implemented and applied to a problem of real-time surface reconstruction. Results show that the algorithm trained online well compares with the batch version.

Modern scanners are able to deliver huge quantities of three-dimensional (3-D) data points sampled on an object's surface, in a short time. These data have to be filtered and their cardinality reduced to come up with a mesh manageable at interactive rates. We introduce here a novel procedure to accomplish these two tasks, which is based on an optimized version of soft vector quantization (VQ). The resulting technique has been termed enhanced vector quantization (EVQ) since it introduces several improvements with respect to the classical soft VQ approaches. These are based on computationally expensive iterative optimization; local computation is introduced here, by means of an adequate partitioning of the data space called hyperbox (HB), to reduce the computational time so as to be linear in the number of data points N, saving more than 80% of time in real applications. Moreover, the algorithm can be fully parallelized, thus leading to an implementation that is sublinear in N. The voxel side and the other parameters are automatically determined from data distribution on the basis of the Zador's criterion. This makes the algorithm completely automatic. Because the only parameter to be specified is the compression rate, the procedure is suitable even for nontrained users. Results obtained in reconstructing faces of both humans and puppets as well as artifacts from point clouds publicly available on the web are reported and discussed, in comparison with other methods available in the literature. EVQ has been conceived as a general procedure, suited for VQ applications with large data sets whose data space has relatively low dimensionality.

The paper presents a novel approach to identify the minutiae present in a fingerprint image based on the analysis of the local properties. The typical patterns of minutiae called ridge termination and bifurcation are identified by studying the intensity along squared paths in the image. The presented algorithm works both on grey-level image and binarized image and, despite its simplicity, it achieves good accuracy and it can be a good candidate to be implemented in hardware or executed on simple hardware architectures, for example in biometric systems embedded in portable applications such as cellular phones and smart cards.

The automatic visual inspection (AVI) systems are nowadays used with good results in a wide broad of applications. In particular we considered the problem of the defect detection of particle boards by means of a visual inspection of the printed surface. We propose an innovative defect detection approach capable to automatically extract the repetitive patterns that are generally present in the printed-matters. The extracted patterns are then used in the proper defect detection phase that can thus achieve high defect detection performances. Real wood patterns prove that our defect detection system achieves very high classification capability.

Recent research has shown that fault diagnosis and possibly fault tolerance are important features when implementing cryptographic algorithms by means of hardware devices. In fact, some security attack procedures are based on the injection of faults. At the same time, hardware implementations of cryptographic algorithms, i.e. crypto-processors, are becoming widespread. There is however, only very limited research on implementing fault diagnosis and tolerance in crypto-algorithms. Fault diagnosis is studied for the RC5 crypto-algorithm, a recently proposed block-cipher algorithm that is suited for both software and hardware implementations. RC5 is based on a mix of arithmetic and logic operations, and is therefore a challenge for fault diagnosis. We study fault propagation in RC5, and propose and evaluate the cost/performance tradeoffs of several error detecting codes for RC5. Costs are estimated in terms of hardware overhead, and performances in terms of fault coverage. Our most important conclusion is that, despite its nonuniform nature, RC5 can be efficiently protected by using low-cost error detecting codes.

A procedure for real-time 3D meshing reconstruction from sparse data is presented. The approach is based on hierarchical radial basis functions networks, which allow for an effective reconstruction of multi-scale surfaces. This model is extended to provide not only the continuous surface description, but also real-time operation. To this purpose, the HRBF network differential properties have been exploited to produce a denser mesh in regions where geometry is more detailed.

The goal of the Advanced Encryption Standard (AES) is to achieve secure communication. The use of AES does not, however, guarantee reliable communication. Prior work has shown that even a single transient error occurring during the AES encryption (or decryption) process will very likely result in a large number of errors in the encrypted/decrypted data. Such faults must be detected before sending to avoid the transmission and use of erroneous data. Concurrent fault detection is important not only to protect the encryption/decryption process from random faults. It will also protect the encryption/decryption circuitry from an attacker who may maliciously inject faults in order to find the encryption secret key. In this paper, we first describe some studies of the effects that faults may have on a hardware implementation of AES by analyzing the propagation of such faults to the outputs. We then present two fault detection schemes: The first is a redundancy-based scheme while the second uses an error detecting code. The latter is a novel scheme which leads to very efficient and high coverage fault detection. Finally, the hardware costs and detection latencies of both schemes are estimated.

Spectral warping is a digital signal processing transform which shifts the frequencies contained within a signal along the frequency axis. The Fourier transform coefficients of a warped signal correspond to frequency-domain 'samples' of the original signal which are unevenly spaced along the frequency axis. This property allows the technique to be efficiently used for DSP-based analog and mixed-signal testing. The analysis and application of spectral warping for test signal generation, response analysis, filter design, frequency response evaluation, etc. are discussed in this paper along with examples of the software and hardware implementation.

Maximization of the catalyst efficiency in automotive fuel-injection engines requires the design of accurate control systems to keep the air-to-fuel ratio at the optimal stoichiometric value AF/sub S/. Unfortunately, this task is complex since the air-to-fuel ratio is very sensitive to small perturbations of the engine parameters. Some mechanisms ruling the engine and the combustion process are in fact unknown and/or show hard nonlinearities. These difficulties limit the effectiveness of traditional control approaches. In this paper, we suggest a neural based solution to the air-to-fuel ratio control in fuel injection systems. An indirect control approach has been considered which requires a preliminary modeling of the engine dynamics. The model for the engine and the final controller are based on recurrent neural networks with external feedbacks. Requirements for feasible control actions and the static precision of control have been integrated in the controller design to guide learning toward an effective control solution.

High reliability is a desirable property of any implementation of the Advanced Encryption Standard (AES). To achieve high reliability, all possible faults must be detected to avoid the use and transmission of erroneous encrypted/decrypted data. In this paper we first study the behavior of faults which may occur during the encryption and decryption procedures of AES, and the way such faults eventually propagate to the final result. We then describe an appropriate detection technique for these faults. This work extends our preliminary results (G. Bertoni et al, MPCS 2002) by considering more general fault models (e.g., permanent and multiple transient faults), and the possibility of fault masking.

Presents a low-cost approach to concurrent error correction in high-performance CORDIC processors by using time-shared triple modular redundancy. Operands are partitioned into three sets of disjoint digits and operations are performed three times on different hardware components to correct possible errors by majority voting. The approach has limited latency increase and throughput reduction. Pipelining can be used to maintain the same throughput as a conventional design.

A high-level synthesis strategy is proposed for design of semiconcurrently self-checking devices. Attention is mainly focused on data path design. After identifying the reference architecture against which cost and performance are evaluated, a simultaneous scheduling-and-allocation strategy is presented for linear-code data flow graphs, allowing resource sharing between nominal and checking data paths. The proposed strategy is actually independent from a specific scheduling-and-allocation algorithm since it is essentially concerned with the introduction of the fault tolerance issue at high-abstraction level in any design environment. Conventional duplication with comparison, even if considered in a high-level synthesis strategy, leads to high circuit complexity increase. The proposed approach provides that the required checking periodicity is satisfied while minimizing additional functional units by means of maximum reuse of the resources available for the nominal computation as long as error detection ability is preserved. The strategy is then extended to deal with branches and loops in the data path. Risk of error aliasing due to resource sharing is analyzed.

No abstract available.

There is an ever-increasing use of embedded systems; fast prototyping, time to market and severe implementation constraints must be faced to provide an effective - low cost - solution for a given application. To this end, several algorithmic formalisms are available to describe and validate complex systems at a behavioural level in order to minimise development costs and facilitate the integration of design and implementation constraints. Unfortunately, a soft-computing paradigm cannot be directly manipulated by conventional development environments for embedded systems unless an algorithmic description is available. In general, such a description is the result of a training procedure which, by following the selection of the most suitable soft-computing paradigm, configures it. The paper addresses the issues related to the integration of soft-computing paradigms within conventional development environments for embedded systems. The analysis is carried out at a behavioural abstraction level.

The Discrete Cosine and Inverse Discrete Cosine Transforms are widely used tools in many digital signal and image processing applications. The complexity of these algorithms often requires dedicated hardware support to satisfy the performance requirements of hard real-time applications. This paper presents the architecture of an efficient implementation of a two-dimensional DCT/IDCT transform processor via a serial-parallel systolic array that does not require transposition.

We propose a constructive approach to building single-hidden-layer neural networks for nonlinear function approximation using frequency domain analysis. We introduce a spectrum-based learning procedure that minimizes the difference between the spectrum of the training data and the spectrum of the network's estimates. The network is built up incrementally during training and automatically determines the appropriate number of hidden units. This technique achieves similar or better approximation with faster convergence times than traditional techniques such as backpropagation.

A high-level synthesis approach is proposed for the design of semi-concurrently self-checking devices; attention is focused on data path design. After identifying the reference architecture against which cost and performances should be evaluated, a simultaneous scheduling-and-allocation algorithm is presented, allowing resource sharing between nominal and checking data paths. The algorithm grants that the required checking periodicity is satisfied while minimizing additional costs in terms of functional units. Risk of error aliasing due to resource sharing is analysed.

Efficient implementation of neural networks requires high-performance architectures, while VLSI realization for mission-critical applications must include fault tolerance. Contemporaneous solution of such problems has not yet been completely afforded in the literature. This paper focuses both on data representation to support high-performance neural computation and on error detection to provide the basic information for fault tolerance by using the redundant binary representation with a three-rail logic implementation. Costs and performances are evaluated referring to multilayered feed-forward networks.

Testability analysis and test pattern generation for neural architectures can be performed at a very high abstraction level on the computational paradigm. In this paper, we consider the case of Hopfield's networks, as the simplest example of networks with feedback loops. A behavioral error model based on finite-state machines (FSM's) is introduced. Conditions for controllability, observability and global testability are derived to verify errors excitation and propagation to outputs. The proposed behavioral test pattern generator creates the minimum length test sequence for any digital implementation.

The FERMI is a data acquisition system for calorimetry experiments in high energy physics at the LHC, CERN. The system contains a large number of acquisition channels, with a precision of 16 bits and a sampling rate of 40 MHz. A large part of the information driven by the channels is processed locally, to reduce the amount of data. This requires to cluster several channels by adding them. The paper presents the design of a fast, low cost adder chip, based on the implementation of column compression techniques for the computation of integer addition. Since the system is operating in a radiation-hard environment, fault tolerance (namely fault detection) is implemented by means of arithmetic codes.

Event identification in photon counting ICCD detectors requires a high level image analysis which cannot be easily described algorithmically: neural networks are promising to approach this application. A system capable of identifying these events on board of satellites needs fault tolerant capabilities to certify result correctness. The rapid evolution of the problem specification, due to the increasing knowledge about the physics, makes attractive the availability and modifiability of prototypes: FPGA-based design is effective to realize these systems. The paper presents therefore an FPGA-based implementation of a fault tolerant neural architecture for event identification.

Neural network architecture optimization is often a critical issue, particularly when VLSI implementation is considered. This paper proposes a new minimization method for multilayered feedforward ANNs and an original approach to their synthesis, both based on the analysis of the information quantity (entropy) flowing through the network. A layer is described as an information filter which selects the relevant characteristics until the complete classification is performed. The basic incremental synthesis method, including the supervised training procedure, is derived to design application-tailored neural paradigms with good generalization capability.

Each coordinate rotation digital computer iteration selects the rotation direction by analyzing the results of the previous iteration. In this paper, we introduce two arctangent radices and show that about 2/3 of the rotation directions can be derived in parallel without any error. Some architectures exploiting these strategies are proposed.

On-line testing is a basic issue of any concurrent fault-tolerance policy. Error localisation within the neural network is necessary to provide information for hardware reconfiguration in order to achieve the system survival. In this paper, a concurrent approach for error localisation in digital neural networks is discussed and evaluated. Two techniques are applied: concurrent diagnosis with the use of data coding for error detection at neuron level and on-line localisation of the faulty neuron within the network.

The CORDIC algorithm is a powerful tool for computing trigonometric functions (sine and cosine) and some transcendental functions (hyperbolic sine and cosine) at a circuit complexity suited for physical implementation by using VLSI technologies. In this paper, we propose a family of architectures for high-throughput applications based on computation pipelining. The granularity of pipelining can be varied to increase the throughput at a cost of increased circuit complexity. The wide variety of solutions allows optimizing the trade-off between performance and circuit complexity, by taking into account the specific requirements and constraints of the application. The evaluations and the designer guidelines an also given.

A well-known scheme for obtaining high throughput adders is a pipeline in which each stage contains an array of half-adders performing a carry-save addition. This paper shows that other schemes can be designed, based on the idea of pipelining a serial-input adder or a ripple-carry adder. Such schemes offer a considerable savings of components while preserving high throughput. These schemes can be generalized by using (p,q) parallel counters to obtain pipelined adders for more than two numbers.

The paper presents a study on the introduction of pipelining in parallel VLSI multipliers, built according to the column compression (CC) design techniques. A number of CC multiplier schemes have been proposed in the literature, aimed at reducing the number of stages of adders necessary to compute a multiplication. More recently CC multiplier schemes aimed at optimising the required silicon area, the regularity and the locality of the interconnections among the adders, have been proposed. The paper affords the introduction of pipelining in these last structures and compares the obtained results with existing structures, in terms of required number of components and operation frequency.

The use of neural networks in mission-critical applications requires concurrent error detection and correction at architectural level to provide high consistency and reliability of system's outputs. Time redundancy allows for fault tolerance in digital realizations with low circuit complexity increase. In this paper, we propose the use of REcomputation with eXchanged Operands-an approach based on operands' rotation-to introduce concurrent error detection and correction, when timing constraints are not particularly strict. Different architectural approaches for neural design are considered to match the implementation constraints and to show the versatility of the proposed solutions.

Probability that an invalid sequence at an output of a device under test is not detected (error masking) is the measure of the effectiveness of compact testing methods. This paper evaluates and analyses the probability distribution of error masking for compact testing by exploiting the characteristics both of the Hamming code (i.e., the signature analysis) and of some modified Hamming codes. To study the effectiveness of these methods we derive also the analytical expressions for the number of code words of arbitrary weight. Finally, bounds for error masking probability are obtained.

Optimisation of a feed-forward neural paradigm for a given application involves problems such as maximisation of the generalisation ability (relevant to provide effectiveness) and structure minimisation (allowing for physical realisability by using dedicated VLSI devices). This paper proposes a contemporaneous solution of these conflicting goals. The globally-optimised structure is identified by using a covariance matrix transformation and layers of virtual neurons.

In mission-critical applications of artificial neural networks, error correction at the architectural level is often mandatory to guarantee consistency and reliability of the network's outputs. Time redundancy allows for fault tolerance with low circuit complexity overhead. In this paper, the application REcomputing with Triplication With Voting (RETWV) at the system level is proposed for concurrent error correction in neural networks. Feed-forward multi-layered neural networks are considered as an example, but the proposed technique can be easily extended to different neural paradigms.

This paper is dedicated to the presentation of the architecture of a VLSI butterfly processing element, for computing FFT in serial arithmetic. This butterfly PE uses complex samples and weights, with real and imaginary parts represented separately in full fractional two's complement form. The PE is based on a compact serial/parallel to serial complex multiplier, which optimises complex multiplication by merging the generation and accumulation of partial products. The structure of the multiplier and the PE is presented; their performances are evaluated, including the possibility of reconfiguration, fault detection and fault tolerance.>

A dedicated digital signal processor has been designed as part of a fully digital front-end for calorimetric detectors developed for experiments in high-energy particle physics to be carried out at CERN with the Large Hadron Collider. Its function is to evaluate the collision energy by analyzing the 16-bits samples (at 67 Msamples per second) contained in a time window through convolutions with 10-bits coefficients. In order to improve the time and amplitude accuracy of the evaluated pulse maximum, we adopted a scheme composed of three inner-product units followed by a sorting circuit which identifies the maximum, the minimum and the median value among the three inner-product outputs. Due to the massively radioactive environment in which the calorimeter operates, the fault tolerance issues have been particularly taken into account to provide both concurrent error detection through residue arithmetic and graceful degradation.>

A behavioral approach to the impact of errors due to faults in neural computation is analyzed. Starting from a geometrical description of errors affecting neural values, we derive the probability of error detection at the neuron's output and at the network's outputs.>

A scheme for a convolver design, called a multiparallel convolver, that is based on concurrent processing of p adjacent samples that are input simultaneously to the p-parallel convolver is presented. The scheme uses p units, each of which receives the input samples and produces one convolution every p samples; these are called p-phase subconvolvers. The detailed design of the p-phase subconvolvers and of the whole p-parallel convolver is presented and discussed. The scheme can be used for both the bit-parallel and the bit-serial input presentation of each sample. The input sample rate of the p-parallel convolver is p times the sample rate of a standard (1-parallel) convolver implemented using the same integration technology. The number of components required by a p-parallel convolver is approximately p times the number of components required by a standard convolver.>

The APES system for the design and evaluation of VLSI or WSI array processors is presented. APES makes it possible to study fault-tolerant array architectures and methodologies by simulating the behavior of the system when faults occur: the type and distribution of faults can be defined by the designer. A diagnostic tool is integrated in APES to evaluate the fault-detection and error-correction capabilities of the system under observation. Another tool makes it possible to perform and evaluate the array reconfiguration after fault occurrence by adopting a user-defined strategy. Features including data entry (using a graphic editor or a hardware description language), the simulation engine, the fault injector, the diagnostic evaluator, and the restructuring/reconfiguration manager are discussed.>

The authors present a novel approach to online error detection in an arithmetic array processor for very large computing applications. The use of redundant binary representation makes it possible to design strongly fault-secure architectures with respect to unidirectional stuck-at faults on multiple gate input and/or output lines. Online fault localization is also considered for fast array reconfiguration. Enhanced architectures have been proposed to identify the position of faulty elements in the regular array concurrently with the nominal computation. The proposed approach has been evaluated for a class of arrays which can be adopted in a wide spectrum of applications in digital signal and image processing and in matrix operations.>

Much attention has been recently given to VLSI and WSI processing arrays: systolic arrays are often adopted to execute a wide class of algorithms, e.g for matrix arithmetic or signal and image processing. In this paper a fault-tolerant architecture is proposed to allow reliable computation of systolic arrays by using physical redundancy and residue number coding. Such architecture supplies also information for fast reconfiguration.