A Machine Learning Based Algorithm to Process Partial Shading Effects in PV Arrays

Solar energy is a widely used type of renewable energy. Photovoltaic arrays are used to harvest solar energy. The major goal, in harvesting the maximum possible power, is to operate the system at its maximum power point (MPP). If the irradiation conditions are uniform, the P-V curve of the PV array has only one peak that is called its MPP. But when the irradiation conditions are non-uniform, the P-V curve has multiple peaks. Each peak represents an MPP for a specific irradiation condition. The highest of all the peaks is called Global Maximum Power Point (GMPP). Under uniform irradiation conditions, there is zero or no partial shading. But the changing irradiance causes a shading effect which is called Partial Shading. Many conventional and soft computing techniques have been in use to harvest solar energy. These techniques perform well under uniform and weak shading conditions but fail when shading conditions are strong. In this paper, a new method is proposed which uses Machine Learning based algorithm called Opposition-Based-Learning (OBL) to deal with partial shading conditions. Simulation studies on different cases of partial shading have proven this technique effective in attaining MPP.     

A Framework for Systematic Classification of Assets for Security Testing

Over the last decade, a significant increase has been observed in the use of web-based Information systems that process sensitive information, e.g., personal, financial, medical. With this increased use, the security of such systems became a crucial aspect to ensure safety, integrity and authenticity of the data. To achieve the objectives of data safety, security testing is performed. However, with growth and diversity of information systems, it is challenging to apply security testing for each and every system. Therefore, it is important to classify the assets based on their required level of security using an appropriate technique. In this paper, we propose an asset security classification technique to classify the System Under Test (SUT) based on various factors such as system exposure, data criticality and security requirements. We perform an extensive evaluation of our technique on a sample of 451 information systems. Further, we use security testing on a sample extracted from the resulting prioritized systems to investigate the presence of vulnerabilities. Our technique achieved promising results of successfully assigning security levels to various assets in the tested environments and also found several vulnerabilities in them.     

Convolutional Neural Network for Histopathological Osteosarcoma Image Classification

Osteosarcoma is one of the most widespread causes of bone cancer globally and has a high mortality rate. Early diagnosis may increase the chances of treatment and survival however the process is time-consuming (reliability and complexity involved to extract the hand-crafted features) and largely depends on pathologists’ experience. Convolutional Neural Network (CNN—an end-to-end model) is known to be an alternative to overcome the aforesaid problems. Therefore, this work proposes a compact CNN architecture that has been rigorously explored on a Small Osteosarcoma histology Image Dataaseet (a high-class imbalanced dataset). Though, during training, class-imbalanced data can negatively affect the performance of CNN. Therefore, an oversampling technique has been proposed to overcome the aforesaid issue and improve generalization performance. In this process, a hierarchical CNN model is designed, in which the former model is non-regularized (due to dense architecture) and the later one is regularized, specifically designed for small histopathology images. Moreover, the regularized model is integrated with CNN’s basic architecture to reduce overfitting. Experimental results demonstrate that oversampling might be an effective way to address the imbalanced class problem during training. The training and testing accuracies of the non-regularized CNN model are 98% & 78% with an imbalanced dataset and 96% & 81% with a balanced dataset, respectively. The regularized CNN model training and testing accuracies are 84% & 75% for an imbalanced dataset and 87% & 86% for a balanced dataset.     

Automated Patient Discomfort Detection Using Deep Learning

The Internet of Things (IoT) has been transformed almost all fields of life, but its impact on the healthcare sector has been notable. Various IoT-based sensors are used in the healthcare sector and offer quality and safe care to patients. This work presents a deep learning-based automated patient discomfort detection system in which patients’ discomfort is non-invasively detected. To do this, the overhead view patients’ data set has been recorded. For testing and evaluation purposes, we investigate the power of deep learning by choosing a Convolution Neural Network (CNN) based model. The model uses confidence maps and detects 18 different key points at various locations of the body of the patient. Applying association rules and part affinity fields, the detected key points are later converted into six main body organs. Furthermore, the distance of subsequent key points is measured using coordinates information. Finally, distance and the time-based threshold are used for the classification of movements associated with discomfort or normal conditions. The accuracy of the proposed system is assessed on various test sequences. The experimental outcomes reveal the worth of the proposed system’ by obtaining a True Positive Rate of 98% with a 2% False Positive Rate.     

Deep Learning and Machine Learning-Based Model for Conversational Sentiment Classification

In the current era of the internet, people use online media for conversation, discussion, chatting, and other similar purposes. Analysis of such material where more than one person is involved has a spate challenge as compared to other text analysis tasks. There are several approaches to identify users’ emotions from the conversational text for the English language, however regional or low resource languages have been neglected. The Urdu language is one of them and despite being used by millions of users across the globe, with the best of our knowledge there exists no work on dialogue analysis in the Urdu language. Therefore, in this paper, we have proposed a model which utilizes deep learning and machine learning approaches for the classification of users’ emotions from the text. To accomplish this task, we have first created a dataset for the Urdu language with the help of existing English language datasets for dialogue analysis. After that, we have preprocessed the data and selected dialogues with common emotions. Once the dataset is prepared, we have used different deep learning and machine learning techniques for the classification of emotion. We have tuned the algorithms according to the Urdu language datasets. The experimental evaluation has shown encouraging results with 67% accuracy for the Urdu dialogue datasets, more than 10, 000 dialogues are classified into five emotions i.e., joy, fear, anger, sadness, and neutral. We believe that this is the first effort for emotion detection from the conversational text in the Urdu language domain.     

Weapons Detection for Security and Video Surveillance Using CNN and YOLO-V5s

In recent years, the number of Gun-related incidents has crossed over 250,000 per year and over 85% of the existing 1 billion firearms are in civilian hands, manual monitoring has not proven effective in detecting firearms. which is why an automated weapon detection system is needed. Various automated convolutional neural networks (CNN) weapon detection systems have been proposed in the past to generate good results. However, These techniques have high computation overhead and are slow to provide real-time detection which is essential for the weapon detection system. These models have a high rate of false negatives because they often fail to detect the guns due to the low quality and visibility issues of surveillance videos. This research work aims to minimize the rate of false negatives and false positives in weapon detection while keeping the speed of detection as a key parameter. The proposed framework is based on You Only Look Once (YOLO) and Area of Interest (AOI). Initially, the models take pre-processed frames where the background is removed by the use of the Gaussian blur algorithm. The proposed architecture will be assessed through various performance parameters such as False Negative, False Positive, precision, recall rate, and F1 score. The results of this research work make it clear that due to YOLO-v5s high recall rate and speed of detection are achieved. Speed reached 0.010 s per frame compared to the 0.17 s of the Faster R-CNN. It is promising to be used in the field of security and weapon detection.     

An atomistic investigation into water adsorption behavior on the surfaces of quartz (001) and calcite (001)

The adsorption measurement of various substances in presence of the reservoir minerals has been investigated in the last few years to describe the existing phenomena in the oil and gas energy-related sectors. However, there still needs further research to understand pure water adsorption behavior on reservoir minerals as the fundamental study. In this study, molecular dynamics simulation was carried out to investigate the adsorption behavior of water molecules on the surface of minerals. In this matter, composite integrated layers were built for quartz-water and calcite-water systems to conduct water adsorption calculations from ambient temperature to the reservoir temperature. Results illustrated less amount of water adsorption on quartz; however, the hydrophilicity of calcite surface by disturbing aqueous layers along with a distance of 1.5 Å–2.5 Å. In addition, the temperature effect was observed into lesser adsorption energy by heating up the water toward its’ boiling point. This study contributes to a wider insight into pure water adsorption features before designing complex microstructures.     

Ultrafast Sodium/Potassium‐Ion Intercalation into Hierarchically Porous Thin Carbon Shells

The large‐scale application of sodium/potassium‐ion batteries is severely limited by the low and slow charge storage dynamics of electrode materials. The crystalline carbons exhibit poor insertion capability of large Na⁺/K⁺ ions, which limits the storage capability of Na/K batteries. Herein, porous S and N co‐doped thin carbon (S/N@C) with shell‐like (shell size ≈20–30 nm, shell wall ≈8–10 nm) morphology for enhanced Na⁺/K⁺ storage is presented. Thanks to the hollow structure and thin shell‐wall, S/N@C exhibits an excellent Na⁺/K⁺ storage capability with fast mass transport at higher current densities, leading to limited compromise over charge storage at high charge/discharge rates. The S/N@C delivers a high reversible capacity of 448 mAh g^‐1 for Na battery, at the current density of 100 mA g^‐1 and maintains a discharge capacity up to 337 mAh g^‐1 at 1000 mA g^‐1. Owing to shortened diffusion pathways, S/N@C delivers an unprecedented discharge capacity of 204 and 169 mAh g^‐1 at extremely high current densities of 16 000 and 32 000 mA g^‐1, respectively, with excellent reversible capacity for 4500 cycles. Moreover, S/N@C exhibits high K⁺ storage capability (320 mAh g^‐1 at current density of 50 mA g^‐1) and excellent cyclic life.     

Enhancement of electrical properties by including nano-aluminum nitride to micro-silicon carbide/silicone elastomer composites for potential power module packaging applications

This paper reports an enhancement of the electrical properties of micro-silicon carbide/silicone elastomer (m-SiC/SE) composites by adding nano-aluminum nitride (n-AlN) for the next-generation power module encapsulation applications. The electrical properties, such as nonlinear conductivity, DC breakdown strength, dielectric spectroscopy, and thermally stimulated discharge current, of the pure SE, m-SiC/SE microcomposite, and m-SiC/n-AlN/SE hybrid composites added with 1 wt%, 3 wt%, and 5 wt% n-AlN fillers are investigated. The m-SiC/n-AlN/SE hybrid composites exhibit better nonlinear conductivity characteristics and enhanced DC breakdown strength than the m-SiC/SE microcomposite. Amongst all materials, the 3 wt% n-AlN addition in the hybrid composite has the best enhancement effect on the nonlinear conductivity characteristics and DC breakdown strength. However, it has the lowest low-frequency real and imaginary permittivities among the SE micro and hybrid composites. Furthermore, a m-SiC/n-AlN heterogenous interface model is proposed to explain the mechanism of enhanced electrical properties of the m-SiC/n-AlN/SE composites. It is found that higher m-SiC/n-AlN heterogenous interface barriers are constructed after adding n-AlN fillers, thereby inhibiting the charge carrier transport at low electric fields. In contrast, more conductive paths are activated at high electric fields by the contacted m-SiC fillers via n-AlN fillers, promoting the charge carrier transport at high electric fields.

     

A passive technique for detecting copy-move forgeries by image feature matching

Multimedia Tools and Applications - Due to the recent evolutions in the technologies various digital devices and image processing tools are available in the market. Consequently, crime rates are...