Lightweight Multi-Class Support Vector Machine-Based Medical Diagnosis System with Privacy Preservation.

Machine learning, powered by cloud servers, has found application in medical diagnosis, enhancing the capabilities of smart healthcare services. Research literature demonstrates that the support vector machine (SVM) consistently demonstrates remarkable accuracy in medical diagnosis. Nonetheless, safeguarding patients' health data privacy and preserving the intellectual property of diagnosis models is of paramount importance. This concern arises from the common practice of outsourcing these models to third-party cloud servers that may not be entirely trustworthy. Few studies in the literature have delved into addressing these issues within SVM-based diagnosis systems. These studies, however, typically demand substantial communication and computational resources and may fail to conceal classification results and protect model intellectual property. This paper aims to tackle these limitations within a multi-class SVM medical diagnosis system. To achieve this, we have introduced modifications to an inner product encryption cryptosystem and incorporated it into our medical diagnosis framework. Notably, our cryptosystem proves to be more efficient than the Paillier and multi-party computation cryptography methods employed in previous research. Although we focus on a medical application in this paper, our approach can also be used for other applications that need the evaluation of machine learning models in a privacy-preserving way such as electricity theft detection in the smart grid, electric vehicle charging coordination, and vehicular social networks. To assess the performance and security of our approach, we conducted comprehensive analyses and experiments. Our findings demonstrate that our proposed method successfully fulfills our security and privacy objectives while maintaining high classification accuracy and minimizing communication and computational overhead.

A Federated Learning Model Based on Hardware Acceleration for the Early Detection of Alzheimer's Disease.

Alzheimer's disease (AD) is a progressive illness with a slow start that lasts many years; the disease's consequences are devastating to the patient and the patient's family. If detected early, the disease's impact and prognosis can be altered significantly. Blood biosamples are often employed in simple medical testing since they are cost-effective and easy to collect and analyze. This research provides a diagnostic model for Alzheimer's disease based on federated learning (FL) and hardware acceleration using blood biosamples. We used blood biosample datasets provided by the ADNI website to compare and evaluate the performance of our models. FL has been used to train a shared model without sharing local devices' raw data with a central server to preserve privacy. We developed a hardware acceleration approach for building our FL model so that we could speed up the training and testing procedures. The VHDL hardware description language and an Altera 10 GX FPGA are utilized to construct the hardware-accelerator approach. The results of the simulations reveal that the proposed methods achieve accuracy and sensitivity for early detection of 89% and 87%, respectively, while simultaneously requiring less time to train than other algorithms considered to be state-of-the-art. The proposed algorithms have a power consumption ranging from 35 to 39 mW, which qualifies them for use in limited devices. Furthermore, the result shows that the proposed method has a lower inference latency (61 ms) than the existing methods with fewer resources.

Real-Time Anomaly Detection for Water Quality Sensor Monitoring Based on Multivariate Deep Learning Technique.

With the increased use of automated systems, the Internet of Things (IoT), and sensors for real-time water quality monitoring, there is a greater requirement for the timely detection of unexpected values. Technical faults can introduce anomalies, and a large incoming data rate might make the manual detection of erroneous data difficult. This research introduces and applies a pioneering technology, Multivariate Multiple Convolutional Networks with Long Short-Term Memory (MCN-LSTM), to real-time water quality monitoring. MCN-LSTM is a cutting-edge deep learning technology designed to address the difficulty of detecting anomalies in complicated time series data, particularly in monitoring water quality in a real-world setting. The growing reliance on automated systems, the Internet of Things (IoT), and sensor networks for continuous water quality monitoring is driving the development and deployment of the MCN-LSTM approach. As these technologies become more widely used, the rapid and precise identification of unexpected or aberrant data points becomes critical. Technical difficulties, inherent noise, and a high data influx pose significant hurdles to manual anomaly detection processes. The MCN-LSTM technique takes advantage of deep learning by integrating Multiple Convolutional Networks and Long Short-Term Memory networks. This combination of approaches offers efficient and effective anomaly detection in multivariate time series data, allowing for identifying and flagging unexpected patterns or values that may signal water quality issues. Water quality data anomalies can have far-reaching repercussions, influencing future analyses and leading to incorrect judgments. Anomaly identification must be precise to avoid inaccurate findings and ensure the integrity of water quality tests. Extensive tests were carried out to validate the MCN-LSTM technique utilizing real-world information obtained from sensors installed in water quality monitoring scenarios. The results of these studies proved MCN-LSTM's outstanding efficacy, with an impressive accuracy rate of 92.3%. This high level of precision demonstrates the technique's capacity to discriminate between normal and abnormal data instances in real time. The MCN-LSTM technique is a big step forward in water quality monitoring. It can improve decision-making processes and reduce adverse outcomes caused by undetected abnormalities. This unique technique has significant promise for defending human health and maintaining the environment in an era of increased reliance on automated monitoring systems and IoT technology by contributing to the safety and sustainability of water supplies.

Enhancing Security in ZigBee Wireless Sensor Networks: A New Approach and Mutual Authentication Scheme for D2D Communication.

The latest version of ZigBee offers improvements in various aspects, including its low power consumption, flexibility, and cost-effective deployment. However, the challenges persist, as the upgraded protocol continues to suffer from a wide range of security weaknesses. Constrained wireless sensor network devices cannot use standard security protocols such as asymmetric cryptography mechanisms, which are resource-intensive and unsuitable for wireless sensor networks. ZigBee uses the Advanced Encryption Standard (AES), which is the best recommended symmetric key block cipher for securing data of sensitive networks and applications. However, AES is expected to be vulnerable to some attacks in the near future. Moreover, symmetric cryptosystems have key management and authentication issues. To address these concerns in wireless sensor networks, particularly in ZigBee communications, in this paper, we propose a mutual authentication scheme that can dynamically update the secret key value of device-to-trust center (D2TC) and device-to-device (D2D) communications. In addition, the suggested solution improves the cryptographic strength of ZigBee communications by improving the encryption process of a regular AES without the need for asymmetric cryptography. To achieve that, we use a secure one-way hash function operation when D2TC and D2D mutually authenticate each other, along with bitwise exclusive OR operations to enhance cryptography. Once authentication is accomplished, the ZigBee-based participants can mutually agree upon a shared session key and exchange a secure value. This secure value is then integrated with the sensed data from the devices and utilized as input for regular AES encryption. By adopting this technique, the encrypted data gains robust protection against potential cryptanalysis attacks. Finally, a comparative analysis is conducted to illustrate how the proposed scheme effectively maintains efficiency in comparison to eight competitive schemes. This analysis evaluates the scheme's performance across various factors, including security features, communication, and computational cost.