A Vehicle-to-Grid System for Controlling Parameters of Microgrid System.

The power system for large-scale adoption of hybrid electric vehicles can benefit from a distributed reserve provided by the vehicle-to-grid (V2G) concept. This study suggests a V2G technology that can effectively control frequency on a microgrid throughout a 24-h cycle. When usage is at its lowest in the spring or fall, a microgrid is intended to be large enough to simulate a community of 2000 households. A 1:5 ratio of cars to households is realized by modelling 400 electric vehicles (EVs) as a basic model, indicating a typical case in the future. An in-depth analysis of the voltage, current, reactive, and active power is carried out for a microgrid. By coordinating control of diesel generation, renewable energy source (RES) generation, power exchange, and EV generation, the system frequency of a microgrid can be managed by regulating load demand with V2G devices. The proposed microgrid with V2G effectively manages energy and reduces the uncertain and variable nature of RES power generation with enhanced performance. System parameter variations have been investigated for various operating scenarios, and it has been discovered that error is confined to less than 5%.

DWT-EMD Feature Level Fusion Based Approach over Multi and Single Channel EEG Signals for Seizure Detection.

Brain Computer Interface technology enables a pathway for analyzing EEG signals for seizure detection. EEG signal decomposition, features extraction and machine learning techniques are more familiar in seizure detection. However, selecting decomposition technique and concatenation of their features for seizure detection is still in the state-of-the-art phase. This work proposes DWT-EMD Feature level Fusion-based seizure detection approach over multi and single channel EEG signals and studied the usability of discrete wavelet transform (DWT) and empirical mode decomposition (EMD) feature fusion with respect to individual DWT and EMD features over classifiers SVM, SVM with RBF kernel, decision tree and bagging classifier for seizure detection. All classifiers achieved an improved performance over DWT-EMD feature level fusion for two benchmark seizure detection EEG datasets. Detailed quantification results have been mentioned in the Results section.

Channel Allocation for Connected Vehicles in Internet of Things Services.

Based on the existing Internet of Vehicles communication protocol and multi-channel allocation strategy, this paper studies the key issues with vehicle communication. First, the traffic volume is relatively large which depends on the environment (city, highway, and rural). When many vehicles need to communicate, the communication is prone to collision. Secondly, because the traditional multi-channel allocation method divides the time into control time slots and transmission time slots when there are few vehicles, it will cause waste of channels, also when there are more vehicles, the channels will not be enough for more vehicles. However, to maximize the system throughput, the existing model Enhanced Non-Cooperative Cognitive division Multiple Access (ENCCMA) performs amazingly well by connected the Cognitive Radio with Frequency Division Multiple Access (FDMA) and Time Division Multiple Access (TDMA) for a multi-channel vehicular network.However, this model induces Medium Access Control (MAC) overhead and does not consider the performance evaluation in various environmental conditions.Therefore, this paper proposes a Distributed Medium Channel Allocation (DMCA) strategy, by dividing the control time slot into an appointmentand a safety period in the shared channel network. SIMITS simulator was used for experiment evaluation in terms of throughput, collision, and successful packet transmission. However, the outcome shows that our method significantly improved the channel utilizationand reduced the occurrence of communication overhead.

A Multichannel Convolutional Neural Network Architecture for the Detection of the State of Mind Using Physiological Signals from Wearable Devices.

Detection of the state of mind has increasingly grown into a much favored study in recent years. After the advent of smart wearables in the market, each individual now expects to be delivered with state-of-the-art reports about his body. The most dominant wearables in the market often focus on general metrics such as the number of steps, distance walked, heart rate, oximetry, sleep quality, and sleep stage. But, for accurately identifying the well-being of an individual, another important metric needs to be analyzed, which is the state of mind. The state of mind is a metric of an individual that boils down to the activity of all other related metrics. But, the detection of the state of mind has formed a huge challenge for the researchers as a single biosignal cannot propose a particular decision threshold for detection. Therefore, in this work, multiple biosignals from different parts of the body are used to determine the state of mind of an individual. The biosignals, blood volume pulse (BVP), and accelerometer are intercepted from a wrist-worn wearable, and electrocardiography (ECG), electromyography (EMG), and respiration are intercepted from a chest-worn pod. For the classification of the biosignals to the multiple state-of-mind categories, a multichannel convolutional neural network architecture was developed. The overall model performed pretty well and pursued some encouraging results by demonstrating an average recall and precision of 97.238% and 97.652% across all the classes, respectively.

An Efficient Deep Learning Approach to Pneumonia Classification in Healthcare.

This study proposes a convolutional neural network model trained from scratch to classify and detect the presence of pneumonia from a collection of chest X-ray image samples. Unlike other methods that rely solely on transfer learning approaches or traditional handcrafted techniques to achieve a remarkable classification performance, we constructed a convolutional neural network model from scratch to extract features from a given chest X-ray image and classify it to determine if a person is infected with pneumonia. This model could help mitigate the reliability and interpretability challenges often faced when dealing with medical imagery. Unlike other deep learning classification tasks with sufficient image repository, it is difficult to obtain a large amount of pneumonia dataset for this classification task; therefore, we deployed several data augmentation algorithms to improve the validation and classification accuracy of the CNN model and achieved remarkable validation accuracy.

RUASN: a robust user authentication framework for wireless sensor networks.

In recent years, wireless sensor networks (WSNs) have been considered as a potential solution for real-time monitoring applications and these WSNs have potential practical impact on next generation technology too. However, WSNs could become a threat if suitable security is not considered before the deployment and if there are any loopholes in their security, which might open the door for an attacker and hence, endanger the application. User authentication is one of the most important security services to protect WSN data access from unauthorized users; it should provide both mutual authentication and session key establishment services. This paper proposes a robust user authentication framework for wireless sensor networks, based on a two-factor (password and smart card) concept. This scheme facilitates many services to the users such as user anonymity, mutual authentication, secure session key establishment and it allows users to choose/update their password regularly, whenever needed. Furthermore, we have provided the formal verification using Rubin logic and compare RUASN with many existing schemes. As a result, we found that the proposed scheme possesses many advantages against popular attacks, and achieves better efficiency at low computation cost.