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%.     

An Algebraic QoS-Based Resource Allocation Model for Competitive Multimedia Applications

A new class of multimedia applications require new mechanisms to consider various Quality of Services with respect to resource constraints so that they could support reliable services and utilize available resources optimally. In this paper we present a new analytical and generic resource management model that is QoS-based. The approach for resource allocation and relevant algorithms is based on a mathematically proved model that manages resource and QoS allocation intelligently so that the total system utility of is maximized. We use the constructs of application benefit functions and resource demand functions to represent the system configuration and to solve the resource allocation problems. Extensive surveys on the related work including systematic and analytical approaches are also presented.     

Robust object tracking with background-weighted local kernels

Object tracking is critical to visual surveillance, activity analysis and event/gesture recognition. The major issues to be addressed in visual tracking are illumination changes, occlusion, appearance and scale variations. In this paper, we propose a weighted fragment based approach that tackles partial occlusion. The weights are derived from the difference between the fragment and background colors. Further, a fast and yet stable model updation method is described. We also demonstrate how edge information can be merged into the mean shift framework without having to use a joint histogram. This is used for tracking objects of varying sizes. Ideas presented here are computationally simple enough to be executed in real-time and can be directly extended to a multiple object tracking system.     

Experimental evaluation of loss perception in continuous media

Perception of multimedia quality, specified by quality-of-service (QoS) metrics, can be used by system designers to optimize customer satisfaction within resource bounds enforced by general-purpose computing platforms. Media losses, rate variations and transient synchronization losses have been suspected to affect human perception of multimedia quality. This paper presents metrics to measure such defects, and results of a series of user experiments that justify such speculations. Results of the study provide bounds on losses, rate variations and transient synchronization losses as a function of user satisfaction, in the form of Likert values. It is shown how these results can be used by algorithm designers of underlying multimedia systems.     

A simulation-based approach to study stochastic inventory-planning games

Non-cooperative decision-making problems in a decentralized supply chain can be characterized and studied using a stochastic game model. In an earlier paper, the authors developed a methodology that uses machine learning for finding (near) optimal policies for non-zero sum stochastic games, and applied their methodology on an N-retailer and W-warehouse inventory-planning problem. The focus of this paper is on making the methodology more amenable to practical applications by making it completely simulation-based. It is also demonstrated, through numerical example problems, how this methodology can be used to find (near) equilibrium policies, and evaluate short-term rewards of stochastic games. Short-term rewards of stochastic games could be, in many instances, more critical than equilibrium rewards. To our knowledge, no methodology exists in the open literature that can capture the short-term behaviour of non-zero sum stochastic games as examined in this paper.     

Test and evaluation of distributed information system networks

As information services become increasingly ubiquitous, and are being charged for, users are demanding the ability to choose the quality of an information service based on its cost. In this environment, delivering the right information to the right user at the right time, and with appropriate quality, is the challenge. In addition, resource optimizations must be performed to the degree possible. In this paper we introduce the concept of information quality based system evaluation. The key contribution is a framework in which user/application needs for information quality can be quantified in terms of rigorously defined metrics, existing systems can be evaluated against these metrics, and the tradeoffs between information quality and its cost of provisioning can be examined. Further, this provides an approach to developing information quality aware policies and mechanisms for the system. This framework has been partially validated by applying it to the provisioning of continuous media services, i.e., audio and video, in a distributed environment. This paper presents the case study in detail. Finally, the paper outlines a research program in the area of information quality based system evaluation. This revised version was published online in June 2006 with corrections to the Cover Date.     

Structural investigation and giant dielectric response of CaCu<Subscript>3</Subscript>Ti<Subscript>4</Subscript>O<Subscript>12</Subscript> ceramic by Nd/Zr co-doping for energy storage applications

High performance dielectric materials are highly required for practical application for energy storage technologies. In this work, high-k pristine and modified calcium copper titanate having nominal formula Ca_0.95Nd_0.05Cu₃Ti_4?xZr_xO₁₂ (x?=?0.01, 0.03 & 0.10) were synthesized and characterized for structural and dielectric properties. Single phase formation of the synthesized compositions was confirmed by X-ray diffraction patterns and further analysed using Rietveld refinement technique. Phase purity of the synthesized ceramics was further confirmed by Energy-dispersive X-ray Spectroscopy (EDX) analysis. SEM images demonstrated that grain size of the modified CCTO ceramics was controlled by Zr⁴⁺ ions due to solute drag effect. Impedance spectroscopy was employed to understand the grain, grain boundaries and electrode contribution to the dielectric response. Nyquist plots were fitted with a 2R-CPE model which confirms the non-ideality of the system. Substitution of specific concentration of Nd and Zr improved the dielectric properties of high dielectric permittivity (ε′ ~?16,902) and minimal tanδ (≤?0.10) over a wide frequency range. The giant ε′ of the investigated system was attributed to internal barrier layer capacitance (IBLC) effect and reduced tanδ accredited to enhanced grain boundaries resistance due to substitution of Zr⁴⁺ ions at Ti⁴⁺ site.     

Nano and micro architectures for self-propelled motors

Self-propelled micromotors are emerging as important tools that help us understand the fundamentals of motion at the microscale and the nanoscale. Development of the motors for various biomedical and environmental applications is being pursued. Multiple fabrication methods can be used to construct the geometries of different sizes of motors. Here, we present an overview of appropriate methods of fabrication according to both size and shape requirements and the concept of guiding the catalytic motors within the confines of wall. Micromotors have also been incorporated with biological systems for a new type of fabrication method for bioinspired hybrid motors using three-dimensional (3D) printing technology. The 3D printed hybrid and bioinspired motors can be propelled by using ultrasound or live cells, offering a more biocompatible approach when compared to traditional catalytic motors.