Performance Analysis of Machine Learning Algorithms for Classifying Hand Motion-Based EEG Brain Signals

Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%.     

Improved quadtree image segmentation approach to region information

Images are full of information and most often, little information is desired for subsequent processing. Hence, region of interest has key importance in image processing. Quadtree image segmentation has been widely used in many image processing applications to locate the region of interest for further processing. There are also variable block-size image coding techniques to effectively reduce the number of transmitted parts. This paper presents quadtree partition technique as a pre-processing step in image processing to determine what part should be more heterogeneous than the others. It also introduces an idea to solve the problem of squared images. Finally, proposed approach is implemented and analysed. The simulation of the Matlab code of the quadtree is represented by all algorithms and the figures. Thus, achieved results are promising in the state of the art.     

A New Soft Switching qZSC Converter by Using Coupled Inductor

Solar energy is a very cost efficient energy in terms of construction and maintenance that has no pollution and can be found everywhere. So, various converter topologies are used as an interface converter for solar panels. The boost converter is the conventional converter used in photovoltaic (PV) application. But, it has several problems such as instability in Continuous Conduction Mode (CCM), input inrush currents, short circuit protection and etc. These problems, lead to use Z-Source and quasi Z-Source Converter (qZSC) which have higher gain compared to traditional boost converter, lower current ripple at the input without using any extra filters, buck and boost capability, lower output ripple and higher reliability. In this paper a soft switching technique for qZSC converter with coupled inductor and without any auxiliary switch is proposed for PV application. By adding an auxiliary circuit, which includes a coupled inductor, diode and capacitor, soft switching condition is provided for all semiconductor elements of the proposed converter. The proposed converter is theoretically analyzed and to confirm the validity of the theoretical analysis, it is simulated by ORCAD and a laboratory prototype is built. The proposed converter shows six percent efficiency improvement in comparison with hard switching counterpart.     

BiCMOS amplifier–discriminator integrated circuit for gas-filled detector readout

The paper presents a 16-channel amplifier-discriminator designed in BiCMOS technology. It will be used for the binary parallel readout of gas-filled detectors being designed at the European Synchrotron Radiation Facility. The circuit (named AMS211) has been manufactured. The measured transimpedance gain (400 KΩ), bandwidth (25 MHz) and noise (1570 e⁻+95 e⁻/pF ENC) well match the simulated results. The discriminator thresholds are individually controlled by built-in Digital to Analogue Converter. The experience gained with a first prototype of readout electronics indicates that the AMS211 should meet our requirements.     

Data center network architecture in cloud computing： review,taxonomy, and open research issues＊

The data center network （DCN）, which is an important component of data centers, consists of a large number of hosted servers and switches connected with high speed communication links. A DCN enables thc deployment of resources centralization and on-demand access of the information and services of data centers to users. In recent years, the scale of the DCN has constantly increased with the widespread use of cloud-based services and the unprecedented amount of data delivery in/between data centers, whereas the traditional DCN architecture lacks aggregate bandwidth, scalability, and cost effectiveness for coping with the increasing demands of tenants in accessing the services of cloud data centers. Therefore, the design of a novel DCN architecture with the features of scalability, low cost, robustness, and energy conservation is required. This paper reviews the recent research findings and technologies of DCN architectures to identify the issues in the existing DCN architectures for cloud computing. We develop a taxonomy for the classification of the current DCN architectures, and also qualitatively analyze the traditional and contemporary DCN architectures. Moreover, the DCN architectures are compared on the basis of the significant characteristics, such as bandwidth, fault tolerance, scalability, overhead, and deployment cost. Finally, we put forward open research issues in the deployment of scalable, low-cost, robust, and energy-efficient DCN architecture, for data centers in computational clouds.     

Numerical studies on the application of tuned liquid dampers with screens to control seismic response of structures

Tuned liquid damper (TLD) systems are nowadays increasingly being used as one of the economical and effective passive vibration absorbers. A TLD system consists of a water tank having the fundamental sloshing fluid frequency tuned to the frequency near to the natural frequency of structure. This research focuses on modelling tall buildings equipped with TLDs having inside screens subjected to strong ground motions. Strong excitation can cause wave‐breaking phenomenon and makes turbulent in shallow rectangular tanks which could also contribute to the additional damping due to TLDs. On the other hand, wire screens placed inside a liquid tank can play an important role in reducing the structural response due to increasing the inherent damping of the structure. Based on equalizing dissipated energies, a TLD equipped with internal screens can be modelled by equivalent amplitude‐dependent tuned mass damper (TMD). In this study, adopting this simple method, equations of motion for shear‐type buildings equipped with nonlinear amplitude‐dependent TMDs were developed. A complex modal analysis procedure was used to solve the governing equations. Coupling of TMD properties and structural response was solved with iteration on structural response and updating TMD properties. Performing a set of parametric studies on three proposed tall structures equipped with TLD subjected to different ground excitations showed that if the TLD is tuned to a frequency close to the natural frequency of the structure considering hardening behaviour of TLD, it could significantly reduce the seismic response (displacements and base shears) of the structures. Copyright © 2009 John Wiley & Sons, Ltd.     

Behavior of Aramid Fiber／Ultrahigh Molecular Weight Polyethylene Fiber Hybrid Composites under Charpy Impact and Ballistic Impact

The aramid fiber/UHMWPE(ultrahigh molecular weight polyethylene)fiber hybrid composites(AF/DF) were ma-nufactured.By Charpy impact,the low velocity impact behavior of AF/DF composite was studied.And the high velocity impact behavior under ballistic impact was also investigated.The influenct of hybrid ratio on the performances of low and high velocity impact was analyzed,and hybrid structures with good impact properties under low velocity impact and high velocity were optimized.For Charpy impact, the maximal impact load increased with the accretion of the AF layers for AF/DF hybrid composites.The total impact power was reduced with the decrease of DF layers and the delamination can result in the increase of total impact power.For ballistic impact ,the DF ballistic performance was better than that of the AF and the hybrid ratio had a crucial influence.The failure morphology of AF/DF hybrid composite under Charpy impact and ballistic impact was analyzed .The AF/DF hybrid composites in suitable hybrid ratio could attain better performance than AF or DF composites.     

Photoelectrochemical conversion of CO2 using nanostructured PbS–Si Photocathode

Journal of Applied Electrochemistry - A n-type nanostructured PbS thin films were prepared by chemical bath deposition onto flat Silicon (Si) and Silicon nanowires (SiNWs) which were derived from...