This paper proposed a simple but highly accurate feature extraction method for epilepsy detection from electroencephalogram (EEG) signals. Based on the combination of Discrete Wavelet Transform (DWT) and the newly proposed features Local Binary Pattern Transition Histogram (LBPTH) and Local Binary Pattern Mean Absolute Deviation (LBPMAD), our proposed feature extraction method can efficiently extract features from EEG signals for machine learning classification of epilepsy, achieving high classification accuracy with a feature size of only 18 for each signal. Tested on the publicly available University of Bonn Epilepsy EEG Dataset using a signal length of 4097 data points (23.61 seconds), the proposed method achieved larger than 99.6% accuracy results for Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) classification of ictal (set E) against any non-ictal (set A, B, C, or D) or combinations of non-ictal (set $\text{A}+\text{B}$ , set $\text{C}+\text{D}$ , or set $\text{A}+\text{B}+\text{C}+\text{D}$ ) EEG signals, which is among the best of currently published works. Our method can maintain high classification accuracy even with short input signals, achieving more than 99.1% SVM classification accuracy when input signal length is reduced to 512 data points (2.95 seconds). The high accuracy, small feature size, ability to work with short input signals and low computing requirements made the proposed method suitable for mobile, low power, and low-cost wearable medical devices.

In this paper, we proposed the implementation of a simple and lightweight Atrial Fibrillation detection based on an improved Variable Step Dynamic Threshold Local Binary Pattern algorithm. Using feature selection based on correlation and statistical significance, we can reduce the input feature size to just 44 features without significantly degrading classification accuracies. Tested on 15-second signal segments from the MIT-BIH Atrial Fibrillation Database and combined with a support vector machine classifier, the proposed method can achieve 99.14% sensitivity, 99.12% specificity, and 99.13% accuracy. When the input signal length is 60 seconds, the sensitivity, specificity, and accuracy are 99.49%, 99.46%, and 99.47%, respectively. The reduced input feature size results in a machine learning model size as small as 132.86kB when the input signal length is 60 seconds. When implemented on an Arm Cortex M4-based STM32F413ZHT3 microprocessor with 100MHz clock frequency, the proposed method can achieve similar performance as a PC-based system with an average current consumption of just 27mA. The embedded C program can fit in as small as 114.46kB of flash memory and complete one SVM inference as fast as 11.28ms. The results presented in this paper show that it is possible to do highly accurate machine learning classification that can detect Atrial Fibrillation from ECG signals on a low-power, constrained resource microcontroller. Our results will make developing a high quality, low cost, and low power wearable smart medical electronic device for detecting atrial fibrillation from ECG signal much easier.

The original queen honey bee migration (QHBM) was developed for independent action on solving efficient mobile routing in WSN. In this paper, we enhanced the original QHBM using Binary testing injection on the cooperative node’s selection on IoT system. We also added a new cost function for making nodes’ coalition, implementing the threshold value for modified QHBM (mQHBM for short), and demonstrating the mQHBM-CMIMO in fair comparison with another previous algorithms. Our research portrayed that mQHBM can perform better than its competitors such as Fuzzy- BT, Neuro Fuzzy and PSO in terms of network lifetime and the end to end delay.

This article proposes a new authentication method for vehicular monitoring Internet of Things (IoT) systems. Based on parallel hash chains, the proposed method is suitable for low-power and low-cost IoT devices. Encryption keys are continuously generated on identical parallel hash chains on both the IoT device and the server, removing the need to transmit secret keys over the network. The proposed method only needs two transmission handshakes for each authentication and data transmission. It does not need random number generation on the IoT device, reducing hardware requirements and potential security vulnerability. It minimizes power consumption and data transmission cost while providing mutual authentication of both the server and the device. Other merits of our proposed methods include: it provides device anonymity, allows message authentication, provides database integrity verification, is resistant to transmission loss, and is dynamically adaptable to disturbances in transmission network quality.

The vibration of the motor provides information for failure diagnostic and prediction through signal processing. In this paper, we present an IoT-based monitoring system for recording the vibration of the induction motor. A 27mm piezoelectric is used to collect the vibration data from the motor. Each self-powered IoT node is supplied by the motor vibration its self by utilizing two 27mm piezoelectrics in series. We conducted an experiment with 3 scenarios, which aims to collect the vibration data from different positions, they are bottom, top and at the coupling. For each scenario, the speed of the induction motor is changed from low, middle to high speed. Based on our results, the proposed system is a success to monitor the motor vibration clearly. The results can display on the smartphone. Each node can send the recorded vibration to the cloud with an average delay of about 1 s.