We present iDT-diet, an intelligent digital twin prototype designed to model the long-term influence of diet quality on health biomarkers and chronic conditions. The system integrates three novel components: (i) a random forest learning model enhanced with Choquet LASSO feature selection for capturing complex, nonlinear interactions in temporal health data; (ii) a translation module that converts predictive outputs into natural language narratives of physical and biomarker states; and (iii) a generative 3D visualization engine that produces dynamic, personalized digital twins reflecting evolving health trajectories. This integration uniquely links advanced machine learning, interpretable communication, and immersive visualization within a single framework. While the current implementation focuses on retrospective digital twin generation, the system architecture supports real-time data integration, enabling continuous monitoring, predictive simulation, and personalized recommendation delivery for diet and lifestyle management.

Aggregating person-level data across multiple clinical study sites is often constrained by privacy regulations, necessitating the development of decentralized modeling approaches in biomedical research. To address this requirement, a federated nonlinear regression algorithm based on the Choquet integral has been introduced for outcome prediction. This approach avoids reliance on prior statistical assumptions about data distribution and captures feature interactions, reflecting the non-additive nature of biomedical data characteristics. This work represents the first theoretical application of Choquet integral regression to multisite longitudinal trial data within a federated learning framework. The Multiple Imputation Choquet Integral Regression with LASSO (MIChoquet-LASSO) algorithm is specifically designed to reduce overfitting and enable variable selection in federated learning settings. Its performance has been evaluated using synthetic datasets, publicly available biomedical datasets, and proprietary longitudinal randomized controlled trial data. Comparative evaluations were conducted against benchmark methods, including OLS regression and Choquet OLS regression, under various scenarios such as model misspecification and both linear and nonlinear data structures in non-federated and federated contexts. MSE was used as the primary performance metric. Results indicate that MIChoquet-LASSO outperforms compared models in handling nonlinear longitudinal data with missing values, particularly in scenarios prone to overfitting. In federated settings, Choquet OLS underperforms, whereas the federated variant of the model, FEDMIChoquet-LASSO, demonstrates consistently better performance. These findings suggest that FEDMIChoquet-LASSO offers a reliable solution for outcome prediction in multisite longitudinal trials, addressing challenges such as missing values, nonlinear relationships, and privacy constraints while maintaining strong performance within the federated learning framework.

Beamforming techniques are utilized in millimeter wave (mmWave) communication to address the inherent path loss limitation, thereby establishing and maintaining reliable connections. However, adopting standard defined beamforming approach in highly dynamic vehicular environments often incurs high beam training overheads and reduces the available airtime for communications, which is mainly due to exchanging pilot signals and exhaustive beam measurements. To this end, we present a multi-modal sensing and fusion learning framework as a potential alternative solution to reduce such overheads. In this framework, we first extract the features individually from the visual and GPS coordinates sensing modalities by modality specific encoders, and subsequently fuse the multimodal features to obtain predicted top-k beams so that the best line-of-sight links can be proactively established. To show the generalizability of the proposed framework, we perform a comprehensive experiment in four different vehicle-to-vehicle (V2V) scenarios from real-world multi-modal sensing and communication dataset. From the experiment, we observe that the proposed framework achieves up to 77.58% accuracy on predicting top-15 beams correctly, outperforms single modalities, incurs roughly as low as 2.32 dB average power loss, and considerably reduces the beam searching space overheads by 76.56% for top-15 beams with respect to standard defined approach.

Learning from massive amounts of domain-specific information requires new algorithms and models for parsing the ever-expanding field of big data. Such algorithms for exploring and identifying key features in vast databases require analysis of complex interactions to uncover critical features under a variety of circumstances. We study a comprehensive collection of health-related data, showing that our novel Choquet Integral activation function for deep neural networks transforms high-dimensional data into simpler sub-feature sets that better model complex interactions. While standard methods account for unitary feature tracking, they do not extend to multiple feature subsets, an impactful and necessary knowledge base. To this end, our novel activation function creates a sub-additive tool that better considers the weighted compilation of features within a robust set of standard benchmarks, advancing the synergistic and antagonistic relationships among features, capturing non-linear dependencies. We present the theoretical underpinnings, highlighting balanced fuzzy measures and sub-additivity for an optimized model based on real-world health data targeting weight loss. We further test different model settings, akin to hyper-parameter optimization. Despite computational time consumption, which could be improved via nowadays more powerful computing units, this novel method can be implemented as a pre-trained model using big data to identify heretofore unknown sub-additive feature interactions in a variety of fields such as biomedicine, fraud detection, cyber-security, and finance.

Beamforming techniques are essential to compensate for severe path loss in millimeter-wave (mmWave) communications. These techniques adopt large antenna arrays and formulate narrow beams to obtain satisfactory received powers. However, performing accurate beam alignment over such narrow beams for efficient link configuration by traditional beam selection approaches, mainly relied on channel state information and exhaustive search, typically impose significant latency and computing overheads, which is often infeasible in vehicle-to-vehicle (V2V) communications like highly dynamic scenarios. In contrast, utilizing out-of-band contextual information, such as vehicular position information, is a potential alternative to reduce such overheads. This paper proposes a solution that utilizes deep learning to predict the optimal beams for vehicular communication at 60 GHz. By analyzing vehicular position information, the solution can identify the beams that provide sufficient mmWave received powers, ensuring the best line-of-sight links for vehicle-to-vehicle (V2V) communications. The proposed solution was tested on real-world measured mmWave sensing and communication datasets, and the results show that it can achieve an average of 84.58% of received power of link status, making it a promising solution for beamforming in mmWave enabled V2V communications.

Vehicle-to-Vehicle (V2V) cooperative perception has become increasingly popular in the field of autonomous driving, effectively overcoming the inherent limitations of single-vehicle perception systems, such as limited range and susceptibility to occlusions. In a V2V system, vehicles in close proximity can share perception data. To fuse this data, which is collected from different viewpoints by each vehicle, accurate pose information (including position and heading direction) is essential to transform the received data to the receiving vehicle's viewpoint. However, pose errors, often caused by measurement noise or sensor failures, can lead to severe misalignment during data fusion, resulting in incorrect object detections and potentially hazardous decisions in autonomous driving systems. To address this challenge, we present BB-Align, a lightweight pose recovery framework that utilizes Lidar Bird's-eye View (BV) images and object bounding Boxes for relative pose estimation. Designed as a plug-and-play solution, the proposed method requires no additional model training, enabling effortless integration into existing V2V systems. Our approach uses Lidar-derived BV images with a Log-Gabor filter-based feature map for effective image matching despite image sparsity. To reduce errors from self-motion distortion, we also integrate object bounding boxes for finer alignment. The proposed method is rigorously evaluated on the V2V 4Real dataset-currently the only real-world V2V dataset. Our approach demonstrates high pose estimation accuracy, outperforming an existing graph-matching method. It achieves translation and rotation errors of less than 1 m and 1°, respectively, in 80 % of cases within a 70 m range between vehicles. Furthermore, by integrating the proposed framework into cooperative object detection models under serious pose error, the result shows up to a 2x increase in Average Precision (AP) compared to those without pose recovery, with more pronounced improvements in the short range.

The use of medical data for machine learning, including unsupervised methods such as clustering, is often restricted by privacy regulations such as the Health Insurance Portability and Accountability Act (HIPAA). Medical data is sensitive and highly regulated and anonymization is often insufficient to protect a patient's identity. Traditional clustering algorithms are also unsuitable for longitudinal behavioral health trials, which often have missing data and observe individual behaviors over varying time periods. In this work, we develop a new decentralized federated multiple imputation-based fuzzy clustering algorithm for complex longitudinal behavioral trial data collected from multisite randomized controlled trials over different time periods. Federated learning (FL) preserves privacy by aggregating model parameters instead of data. Unlike previous FL methods, this proposed algorithm requires only two rounds of communication and handles clients with varying numbers of time points for incomplete longitudinal data. The model is evaluated on both empirical longitudinal dietary health data and simulated clusters with different numbers of clients, effect sizes, correlations, and sample sizes. The proposed algorithm converges rapidly and achieves desirable performance on multiple clustering metrics. This new method allows for targeted treatments for various patient groups while preserving their data privacy and enables the potential for broader applications in the Internet of Medical Things.

In order to design effective public health policies to combat the COVID-19 pandemic, local governments and organizations must be able to forecast the expected number of cases in their area. Although researchers have developed individual models for predicting COVID-19 based on sensor data without requiring a test, less research has been conducted on how to leverage those individual predictions in forecasting virus spread for determining hierarchical predictions from the community level to the state level. The multilevel adaptive and dynamic biosensor epidemic model, or m-ADBio, is designed to improve on the traditional susceptible–exposed–infectious–recovered (SEIR) model used to forecast the spread of COVID-19. In this study, the predictive performance of m-ADBio is examined at the state, county, and community levels through numerical experimentation. We find that the model improves over SEIR at all levels, but especially at the community level, where the m-ADBio model with sensor-based initial values yielded no statistically significant difference between the forecasted cases and the true observed data meaning that the model was highly accurate. Therefore, the m-ADBio model is expected to provide a more timely and accurate forecast to help policymakers optimize the pandemic management strategy.

Wearable biosensors represent an opportunity to improve treatment and research into a variety of diseases, including substance use disorder. They provide continuous, real-time data about the wearer’s condition in their natural environment in an unobtrusive, increasingly capable, and cost-effective way. However, generating clinically relevant insights from high-velocity, noisy, multidimensional data streams requires new approaches in real-time anomaly machine learning (ML). We present a survey of the existing algorithms for substance use monitoring in wearable biosensor data streams and how the advent of 5G and 6G wireless communications will drive further changes in this field. Our work highlights trends that have emerged among the different efforts published to-date as well as identifying ongoing challenges not adequately addressed by existing ML algorithms.

The Intelligent Transportation System has become one of the most globally researched topics, with Connected and Autonomous Vehicles(CAV) at its core. The CAV applications can be improved by the study of vehicle platooning immune to real-time traffic and vehicular network losses. In this work, we explore the need to integrate the Network model and Platooning system model for highway environments. The proposed platoon model is designed to be adaptive in length, providing the node vehicles to merge and exit. This overcomes the assumption that all the platoon nodes should have a common source and destination. The challenges of the existing platoon model, such as relay selection, acceleration threshold, are addressed for highly modular platoon design. The presented algorithm for merge and exit events optimizes the trade-off between network parameters such as communication range and vehicle dynamic parameters such as velocity and acceleration threshold. It considers the network bounds like SINR and link stability and vehicle trajectory parameters like the duration of the vehicle in the platoon. This optimizes the traffic throughput while maintaining stability using the PID controller. The work tries to increase the vehicle inclusion time in the platoon while preserving the overall traffic throuahput.

Wireless Body Area Network (WBANs) would benefit reasonable after the introduction of mmWaves in the communication. The high frequency spectrum can enhance channel capacity and reduce the package area. It however makes the communication link susceptible to noise interference. As the noise level increases, it restricts the use of mmWave spectrum for high SNR level applications. The paper proposes a method of spectrum switching to tap into advantages of mmWave only when necessary thus minimizing the drawbacks on the overall performance. The hybrid approach of using multiple spectrum exploits the characteristics of high channel capacity and high noise immunity which are found at the extreme ends of the spectrum. This paper compares different threshold parameters to conclude SNR as a more reliable factor. We develop an algorithm based on this threshold and simulate spectrum switching from 5 GHz to 60 GHz where the User Equipment is in constant motion over a range of 100 m. We present the graphical results of variance of SNR, Friis model for path loss and numerically prove a significant increase in the average channel capacity using Shannon's theorem while maintaining SNR above the threshold limit. The paper also presents the challenges reflected by this spectrum switching on the supporting parameters like directivity, energy consumption and beamforming array structures.

Artificial intelligence (AI) is becoming a mainstream for telecommunication industry. With the utilization of millimeter-wave in 5G network, it becomes feasible to use beamforming techniques for on-body sensors in Wireless Body Area Network (WBAN) applications. Thus, there is a need for developing beamforming algorithms that can optimize WBAN network performance and a realistic dataset that can be used for training, testing, and benchmarking of the algorithms. Thus, we propose a dataset generation method for mmWave WBAN that utilizes computer vision and an adaptive deep learning-based algorithm for performance optimization of mmWave WBAN beamforming. Two major ideas are proposed: First, collecting human poses from estimation of 3D human poses in videos and generating more realistic poses using generative adversarial nets (GAN) are adopted; second, a GAN aims to predict the next beamforming directions using the previous set of directions as inputs. With available labeled human pose videos, the WBAN dataset we generate provides a sufficient amount of samples for training, testing, and benchmarking of beamforming algorithms. Additionally, the proposed adaptive beamforming algorithm does not require any intrusive data gathering methods. Our numerical studies show the advantages of our proposed approaches.

The rapid growth of Internet of Vehicles (IoV) has brought huge challenges for large data storage, intelligent management, and information security for the entire system. The traditional centralized management approach for IoV faces the difficulty in dealing with real-time response. The blockchain, as an effective technology for decentralized distributed storage and security management, has already showed great advantages in its application of Bitcoin. In this paper, we investigate how the blockchain technology could be extended to the application of vehicle networking, especially with the consideration of the distributed and secure storage of big data. We define several types of nodes such as vehicle and roadside for vehicle networks and form several sub-blockchain networks. In this paper, we present a model of the outward transmission of vehicle blockchain data, and then give detail theoretical analysis and numerical results. This paper has shown the potential to guide the application of blockchain for future vehicle networking.

Advancements in miniaturized electronics and smart sensors combined with a broad platform of smart phones, big data, cloud service, and wireless communication have not only empowered wearable technology, they have also increased users life expectancy. For example, a wearable system provides unobtrusive ambulatory, continuous, ubiquitous health measurement, and real-time solution for patients physical without hampering the natural movement of the wearer. However, the ability to measure one's Autonomic Nervous System (ANS) using wearable biosensors in healthcare applications has been limited due to several challenges related to a lack in wearability, accuracy, reliability, and low-power consumption. In this paper, we presented a novel wearable ring sensor for the continuous measurement of four ANS activities: 1) electrodermal activity; 2) heart rate; 3) skin temperature; and 4) locomotion. Detailed information is given regarding the development of the proposed ring sensor followed by a discussion of the evaluation that was done utilizing the wearable sensor on volunteers to gather data. Specifically, volunteers wore the ring sensor while being simultaneously monitored with real-time telemetry, the sensor values are processed and analyzed. This paper is a continuation and extension of earlier work by the authors. New validation, experimental results, and development of the mobile application have been added to improve the previous system. The experiment demonstrated accurate results, and data were collected from 43 participants of diverse age, body mass, height, and race. Additionally, to evaluate the performance of the developed ring sensor, we compared the results with a state-of-the-art open source device. This paper aims to improve the worn biomedical sensor market, specifically when it comes to size and accuracy of worn sensors.

In many applications of Internet of Things (IoT), the huge amount of data are generated by sensor nodes and processing them are complex. Offloading data classification and anomaly event detection tasks to sink nodes in sensor networks can reduce the computing complexity, lower remote communication loads, and improve the response time for the delay-sensitive IoT applications. Many existing classification and anomaly detection methods cannot be directly applied to these IoT applications, because the computing and energy resources of sensors are limited. In this paper, a new feature-based learning system for IoT applications is proposed to effectively classify data and detect anomaly event. Especially, based on the theory of distributed compression, the sparsity and relativity of the data are exploited to obtain the classification features, which can reduce the computation overhead and energy consumption. Further, an RBF-BP hybrid neural network is employed to detect the anomaly event based on the classification results, by which the training time of neural network can be significantly reduced and the accuracy can be improved for users' decisions.

Advancements in miniaturized electronics and smart sensors combined with a broad platform of smart phones, big data, cloud service and wireless communication have not only empowered wearable technology, they have also increased users life expectancy. This is done through a range of applications including; tracking physical activity, personalized health care, and recommendations for enhancing user experience. However, the ability to measure one's emotional state using wearable biosensors in healthcare applications has been limited due to several challenges related to a lack in comfort, accuracy, reliability and low-power consumption. In this paper, we presented a novel wearable ring sensor for the continuous measurement of four SNS activities: Electrodermal activity (EDA), heart rate, skin temperature and locomotion. Detailed information is given regarding the development of the proposed ring sensor followed by a discussion of the evaluation that was done utilizing the biosensor on volunteers to gather data. Specifically, volunteers wore the ring sensor while being simultaneously monitored with real- time telemetry and while going through different emotional states. The experiment demonstrated accurate results, and data were collected from 43 participants of diverse age, body mass, height, and race. Additionally, to evaluate the performance of the developed ring sensor, we compared the results with a state-of-the-art open source device. This research aims to improve the worn biomedical sensor market, specifically when it comes to size and accuracy of worn sensors.

Big longitudinal data provide more reliable information for decision making and are common in all kinds of fields. Trajectory pattern recognition is in an urgent need to discover important structures for such data. Developing better and more computationally-efficient visualization tool is crucial to guide this technique. This paper proposes an enhanced projection pursuit (EPP) method to better project and visualize the structures (e.g. clusters) of big high-dimensional (HD) longitudinal data on a lower-dimensional plane. Unlike classic PP methods potentially useful for longitudinal data, EPP is built upon nonlinear mapping algorithms to compute its stress (error) function by balancing the paired weights for between and within structure stress while preserving original structure membership in the high-dimensional space. Specifically, EPP solves an NP hard optimization problem by integrating gradual optimization and non-linear mapping algorithms, and automates the searching of an optimal number of iterations to display a stable structure for varying sample sizes and dimensions. Using publicized UCI and real longitudinal clinical trial datasets as well as simulation, EPP demonstrates its better performance in visualizing big HD longitudinal data.

Wireless Body Area Network (WBAN) applications are becoming popular today. To protect patients' private data during transportation, secure wireless communications are mandatory in WBANs. Encryptions and secret keys are the base of secure communications over insecure wireless environments. Given most wireless nodes in WBANs are resource-constrained, efficiency is an implicit requirement of the key generation methods for WBAN wireless communications. Finding secure and efficient key generation method for WBANs is the goal of this article. We propose a practical, pure software method in this article. The new method has been proved to be highly secure and efficient.

Particle Swarm Optimization (PSO) based Fuzzy c-means (FCM) methods typically use random initialization, and could incur substantial computation costs in processing big data, although PSO facilitates the global optimization, based on our previous work [1]. This paper further developed and evaluated our data density-pattern based algorithm to guide initialization and to achieve better computational efficiency of PSO-based FCM. Data density patterns vary over the entire data space and the data points in high density areas are more likely around the cluster centroids. Based on this fact, our new algorithm attempts to improve the computational efficiency by auto-fusing data characteristics around the cluster centroids to initialize our algorithm. We evaluated our method using real and simulated imbalanced big data, and found this new method achieved comparable clustering performance as PSO-based FCM in terms of clustering cost, consistency and accuracy, but not consistently better than simple FCM. In terms of computational efficiency for imbalanced big data, our method seems to be comparable with PSO-based methods in terms of iterations and computational time, but both seem not comparable to simple FCM for imbalanced big data processing. Our simulation indicates that the classical PSO based FCM is slightly better than FCM on computational efficiency, although the clustering performance seems comparable. These findings seem to further support the robustness of FCM in big data processing.

Wireless body area networks (WBANs) require lightweight and resource efficient security approaches. In the literature, biometric-based security approaches have been well studied for WBANs when each individual person may have unique biometric features. However, additional sensing hardware (e.g., ECG sensors) are usually required for every sensor in these approaches, which make them unpractical in real application settings. Unlike them, in this paper, we propose a physical layer-based security approach utilizing physical channel information and remove the extra hardware requirements. Especially, a group-based cooperation on symmetric secret key generation via physical or link layer received signal strength indicator (RSSI) data accumulating is investigated. We propose a practical cooperative group solution to increase the similarity, fluctuation and density of RSSI data for high efficient key generation. The major innovation is to make full use of multiple channels between a participant node and a group or between two groups to randomly synthesize RSSI data with multifold data density and improved data similarity and fluctuation. In addition, several group models are described with the details of their specific protocol design. Furthermore, a prototype is implemented and verified in an experimental environment to demonstrate the high practicality and efficiency of our solution.

This paper presents the design and prototype of a wireless health monitoring system using mobile phone accessories. We focus on measuring real-time electrocardiogram (ECG) and heart rate monitoring using a smartphone case. With the increasing number of cardiac patients worldwide, this design can be used for early detection of heart diseases. Unlike most of the existing methods that use an optical sensor to monitor heart rate, our approach is to measure real-time ECG with dry electrodes placed on smartphone case. The collected ECG signal can be stored and analyzed in real time through a smartphone application for prognosis and diagnosis. The proposed hardware system consists of a single chip microcontroller (RFduino) embedded with Bluetooth low energy, hence miniaturizing the size and prolonging battery life. The system called “smart case” has been tested in a laboratory environment. We also designed a 3-D printed smartphone case to validate the feasibly of the system. The results demonstrated that the proposed system could be comparable to medical grade devices.

Continuously monitoring the vital signs over a long period of time is important for heart diseases. However, a traditional wearable device may be inconvenient to carry. Therefore, the size of low power ICs and wireless modules in this device need to be minimized for healthcare system. In this paper, we proposed non-contact and low power sensors with integrated kinetic sensor for multiparameter real time monitoring. The proposed system consists of a non-contact electrocardiogram (ECG) sensor with fully integrated analog front end (AFE), a temperature sensor, an accelerometer, and a Bluetooth low energy (BLE) module. The system is small with the size of 50.5 x 15.2 x 6mm. The developed wearable glass in the system can be used by inpatient, outpatient or people with disability. The device could also be used by aging people who live alone, capable of sensing fall detection, temperature and monitoring ECG. An Android application is developed to perform data processing, and it also sends alerts to authorities in case of emergency.

This paper proposes a Contrarian Probabilistic Model (CPM) to evaluate the effectiveness of contrarians' investment in preferred stocks using big data from Tradeline. CPM accommodates the unique features of investment data which are often correlated, nested, heterogeneous, non-normal with missing values. The clustering and statistical inference are integrated in CPM, which enables joint investment behavior trajectory pattern recognition and risk analyses based on the entire variance-covariance structure between and within clusters. The empirical study using CPM provides a finer and comprehensive evaluation of contrarian investment in preferred stocks. Two distinctive investment behavior trajectory clusters were identified, showing a few high-risk-seeking contrarians achieved high returns over five year long-term investment, while the majority of contrarians did not outperform glamour stockholders in preferred stock investment. Although CPM was developed using historical data, it could be developed into an analytical tool for online near real time big investment data analyses.

Based on empirical studies, the feature of random initialization in Particle Swarm Optimization (PSO) based Fuzzy c-means (FCM) methods affects the computational performance especially in big data. As the data points in high-density areas are more likely near the cluster centroids, we design a new algorithm to guide the initialization according to the data density patterns. Our algorithm is initialized by fusing the data characteristics near the cluster centers. Our evaluation results from real data show that our approach can significantly improve the computational performance of PSO-based Fuzzy clustering methods, while preserving comparable clustering performance.

This paper proposes a visualization aided pattern validation to identify optimal number of clusters for big longitudinal web behavior intervention data. The proposed validation consists of two parts: The weighted validation index including overlap and separation measures, and visualization integrating a between-stress mapping and trajectory characterization. The proposed method is applied to a longitudinal web behavior intervention dataset and a set of simulated zero-inflated data using parameters from this web trial. Four engagement patterns for this web behavioral intervention are identified and validated using our proposed method.

Increasing population density, closer social contact and interactions make epidemic control difficult. Traditional offline epidemic control methods (e.g., using medical survey or medical records) or model-based approach are not effective due to its inability to gather health data and social contact information simultaneously or impractical statistical assumption about the dynamics of social contact networks, respectively. In addition, it is challenging to find optimal sets of people to be quarantined to contain the spread of epidemics for large populations due to high computational complexity. Unlike these approaches, in this paper, a novel cluster-based epidemic control scheme is proposed based on Smartphone-based body area networks. The proposed scheme divides the populations into multiple clusters based on their physical location and social contact information. The proposed control schemes are applied within the cluster or between clusters. Further, we develop a computational efficient approach called UGP to enable an effective cluster-based quarantine strategy using graph theory for large scale networks (i.e., populations). The effectiveness of the proposed methods is demonstrated through both simulations and experiments on real social contact networks.

Accurate and real-time tracing of epidemic sources is critical for epidemic origin analyses and control when outbreaks of epidemic diseases occur. Such tracing requires the simultaneous availability of information about social interactions among people as well as their body vital signs. Existing epidemic control methods are limited due to their inability to collect the above two types of information at the same time. In this paper, for the first time, we propose integrating wireless body area networks (WBANs) for body vital signs collection with mobile phones for social interaction sensing to achieve the desired epidemic source tracing. In particular, we design a mobile phone capability driven hierarchical social interaction detection framework integrated with WBANs. With this framework, we further propose a set of epidemic source tracing and control algorithms including genetic algorithm based search and dominating set identification algorithms to effectively identify epidemic sources and inhibit epidemic spread. We have also conducted extensive simulations, analyses, and case studies based on real data sets, which demonstrate the accuracy and effectiveness of our proposed solutions.

Wireless body area networks (BANs) have drawn much attention from research community and industry in recent years. Multimedia healthcare services provided by BANs can be available to anyone, anywhere, and anytime seamlessly. A critical issue in BANs is how to preserve the integrity and privacy of a person's medical data over wireless environments in a resource efficient manner. This paper presents a novel key agreement scheme that allows neighboring nodes in BANs to share a common key generated by electrocardiogram (ECG) signals. The improved Jules Sudan (IJS) algorithm is proposed to set up the key agreement for the message authentication. The proposed ECG-IJS key agreement can secure data communications over BANs in a plug-n-play manner without any key distribution overheads. Both the simulation and experimental results are presented, which demonstrate that the proposed ECG-IJS scheme can achieve better security performance in terms of serval performance metrics such as false acceptance rate (FAR) and false rejection rate (FRR) than other existing approaches. In addition, the power consumption analysis also shows that the proposed ECG-IJS scheme can achieve energy efficiency for BANs.

In this paper, we proposed an integrated biometric-based security framework for wireless body area networks, which takes advantage of biometric features shared by body sensors deployed at different positions of a person's body. The data communications among these sensors are secured via the proposed authentication and selective encryption schemes that only require low computational power and less resources (e.g., battery and bandwidth). Specifically, a wavelet-domain Hidden Markov Model (HMM) classification is utilized by considering the non-Gaussian statistics of ECG signals for accurate authentication. In addition, the biometric information such as ECG parameters is selected as the biometric key for the encryption in the framework. Our experimental results demonstrated that the proposed approach can achieve more accurate authentication performance without extra requirements of key distribution and strict time synchronization.

In this paper, we propose a new nonlinear classifier based on a generalized Choquet integral with signed fuzzy measures to enhance the classification power by capturing all possible interactions among two or more attributes. A special genetic algorithm is designed to implement this classification optimization with fast convergence. Instead of using a discrete misclassification rate, the objective function to be optimized in this research is a continuous Choquet distance with a penalty coefficient for misclassified points. The numerical experiment shows that the special genetic algorithm effectively solves the nonlinear classification problem and this nonlinear classifier accurately identifies classes.