IJEER Vol no. 11, Issue 2


A Comprehensive Overview on Performance of Cascaded Three Tank Level System using Neural Network Predictive Controller

A Neural Network Predictive Controller (NNPC) is a deep learning-based controller (DLC) that uses artificial neural networks (ANN) to predict the future behavior of a system and accordingly control its outputs. In this paper, an NNPC was used to predict the level of the three cascaded tank and then adjust the inputs as flow rate to maintain the desired level in the tank. A three-tank level system is a system consisting of three interconnected tanks used to store liquids. To achieve the desired level, the NNPC first collects data on system behavior, including inputs and outputs, and uses this data to train the neural network

Read more

Deep Neural Learning based Deming Regression Adder Enhancement on Digital Multiplier for 3D Graphical Applications in VLSI Circuits

This work aims to investigate 3D Technology to provide better performance enhancement for several generations. The three-dimensional integrated circuit allows better integration density, faster on-chip communications, and heterogeneous integration. The goal of this research is to reduce time consumption and power consumption by introducing the Deep Neural Learnt Deming Regression Based Ladner-Fisher Adder Enhancement (DNLDR-LFAE) Technique in VLSI circuits. Input information (carry inputs) is taken for input layer and transmits to hidden layer 1. Deeming regression analysis has performed at hidden layer 1 to pre-process input data and it is send to hidden layer 2

Read more

Hybrid Optimization based Feature Selection with DenseNet Model for Heart Disease Prediction

The prevalence of cardiovascular diseases (CVD) makes it one of the leading reasons of death worldwide. Reduced mortality rates may result from early detection of CVDs and their potential prevention or amelioration. Machine learning models are a promising method for identifying risk variables. In order to make accurate predictions about cardiovascular illness, we would like to develop a model that makes use of transfer learning. Our proposed model relies on accurate training data, which was generated by careful Data Collecting, Data Pre-processing, and Data Transformation procedures

Read more

Parallel Mirrors Based Marine Predator Optimization Algorithm with Deep Learning Model for Quality and Shelf-Life Prediction of Shrimp

Automatic classification and assessment of shrimp freshness plays a major role in aquaculture industry. Shrimp is one of the highly perishable seafood, because of its flavor and excellent nutritional content. Given the high amount of industrial production, determining the freshness of shrimp quickly and precisely is difficult. Instead of using feature-engineering-based techniques, a novel hybrid classification approach is proposed by combining the strength of convolutional neural networks (CNN) and Marine Predators Algorithm (MPA) for shrimp freshness diagnosis

Read more

Integrated Energy Management System for Microgrid based on Renewable Energy Sources

An effective energy management strategy is crucial to ensure highest system reliability, stability, operation efficiency and cost-effective operation of renewable energy sources based standalone microgrid. This paper presents an efficient energy management system for microgrid incorporated with Photovoltaic system, PMSG based wind turbine and energy storages including battery, fuel cell-Electrolyzer. Implemented hybrid modified invasive weed optimization with perturbed and observed method for PV systems to harvest maximum energy during partial shading condition. A sliding mode controller is implemented for boost converter to work as maximum power point tracker for wind turbine.

Read more

Power Quality Improvement Grid Integrated Photovoltaic with LCL Filter Using DQ Controller

Grid-interactive solar photovoltaic (PV) systems are necessary for the current global scenario owing to their low cost and pollution-free energy source. The integration of PV systems in the power grid needs to be stabilized. To address this, this paper presents a composite controller that can synchronize Photovoltaic (PV) to the Grid, with bidirectional power flow in Grid. The proposed technique is explored with both RL and LCL filters. With grid synchronization of PV power generation, a control loop for power quality disturbance mitigation is simulated.

Read more

Power Quality Enhancement in Solar PV and Battery Integrated UPQC Grid Connected System

This paper discusses a distributed generation system consisting of grid-connected solar PV and a battery-integrated Unified Power Quality Conditioner (UPQC). Embedded in the PV array, the UPQC consists of a series and shunt converter connected back through a common DC link. In this system, power quality problems of clean energy, such as harmonics, voltage drops, ripples, are compensated by injecting active energy into the power grid. The shunt converter is controlled to maintain a constant DC link voltage and harmonic compensation of the load current. The main voltage problem is compensated by a series converter that injects the voltage during sag and swell.

Read more

Congestion Management of Power Systems by Optimal Allocation of FACTS devices using Hybrid Techniques

For system operators, Congestion management is a difficult task as the market’s security and reliability are protected by this methodology. As the magnitude of an electric transmission system is extremely dynamic, limits must be estimated much beforehand, in order to manage the congestion issues at the right time. Flexible AC transmission systems (FACTS) are used to control voltage fluctuation by adjusting the system's real and reactive power. A combination of Improved Remora Optimization (IRO) and Improved Radial Basis Function (IRBF) is used to allocate positions and sizes of the FACTS devices.

Read more

Attack Detection using DL based Feature Selection with Improved Convolutional Neural Network

Decentralized wireless networks that may connect without a central hub are named Mobile Ad-hoc Networks (MANET). Attacks and threats of the most common kind can easily penetrate MANETs. Malware, APTs, and Distributed Denial of Service (DDoS) assaults all work together to make Internet services less reliable and less secure. Existing methods have been created to counter these assaults, but they either need more hardware, result in significant delivery delays, or fall short in other key areas like as energy consumption. This research therefore provides an intelligent agent system that can automatically choose and classify features to identify DDoS assaults.

Read more

Congestion-Free Cluster Formation and Energy Efficient Path Selection in Wireless Sensor Networks using ButPCNN

Today, network congestion is a common occurrence that needs to be focused on and effectively addressed, particularly in Wireless Sensor Networks (WSN) for packed type networks. The main causes of congestion in WSN are a lack of channel capacity and energy waste. This study's major goal is to develop Energy Efficient Congestion Free Path Selection Protocol (ECFPSP) protocol, which aims to reduce network congestion. By selecting the most appropriate main cluster head (PCH) and secondary cluster head (SCH), the ECFPSP protocol is proposed to decrease end-to-end delay time and extend the network lifetime. The suggested protocol implements a routing protocol that provides security by avoiding hostile nodes and reducing data loss. It also routes the nodes.

Read more

Performance Analysis of Variable Threshold Voltage (ΔVth) Model of Junction less FinTFET

The work presented in this paper is a variable threshold voltage (ΔVth) model of junction less fin gate tunnel FET (JL FinTFET) in which there is a shift in threshold voltage. As a result, to improve drive current and subthreshold slope among other devices. At the same time, gradually decrease the random dopant fluctuations (RDF) effects on Vth, ambipolar leakage current by using this design. The threshold voltage in the junction less fin gate TFET may be modified using 2D numerical simulations by supplying a voltage to the variable gate. The effects of the threshold voltage change on the device's overall performance investigate.

Read more

Integration of Optical and Free Space Optics Network Architecture for High-Speed Communication in Adverse Weather using suitable Optical Bands

Free Space Optics (FSO) is a highly viable solution for high-speed wireless communication and is widely preferred over radio frequency communication systems because of its faster data transmission, no regulatory requirements and highly secure long-range operations. However, the capacity and availability of FSO optical bands are a significant concern in varying atmospheric conditions. Our objective is to enhance network flexibility and expand wireless network coverage in adverse weather conditions by combining optical and FSO links using optical bands C, S, and O. The study analyzed the performance of a hybrid 4 channels FSO-WDM system with a 100GHz or 0.8 nm channel spacing under different conditions, including adverse weather and varying data rates. An attenuation of 0.25 dB/km was fixed, and the system's performance was analyzed up to 3 km.

Read more

Bimodal-Shared Control Interface for Assisted Mobility Application

The paper presents (Electro-oculography) EOG- (Electroencephalography) EEG- Radio Frequency Identification (RFID) based Bimodal-Shared Control Interface for mobility assistance application by controlling a mobile robotic arm. EOG-EEG based bio-signal based bimodal interface has been used to move the robot following a predefined path to reach at an object placed at initial predefined position (Zone 1). RFID has been used as shared control interface for object identification and for sending trigger signal to gripper arm to pick the object and place it at another predefined position (Zone 2) automatically.

Read more

Multi-image Feature Map-Based Watermarking Techniques Using Transformer

Nowadays, protecting multimedia data is a significant challenge because of the advancement of technology and software. The embedding process heavily relies on watermarking to accomplish multimedia security in terms of content authentication, proof of ownership, and tamper detection. Our objective is to develop an invariant watermark that can survive different signal-processing attacks. We presented a unique hybrid technique (DWT-QR-SWT) and multi-image invariant features generated as a watermark using a Transformer encoder-decoder model. The encoded image features are subsampled using PCA in order to decrease the dimensionality of the watermark image.

Read more

Performance Enhancement of Boost Converter for Solar Panels System using Genetic Algorithm

Solar Panels System (SPS) is a renewable power source with an essential drawback of low output voltage due to the effect of aspects like the intensity of light and ambient temperature. The DC-DC boost converters are significantly used to boost up the SPS voltage under a certain set of conditions. The converter's output voltage and current are unstable, complex, and varied. A three-term controller (proportional, integral, and derivative) is often used because it can control the system’s behavior effectively. The challenge is the selection of the optimum gain parameters of the controller.

Read more

Investigation of Electromagnetic Shielding for Wire Mesh Composite for Aircraft against Lightning Strike

Nowadays, fly-wire is only used for flying-related things. All plane controls depend on electronics, but they also must deal with high-intensity radiated fields. This equipment might need an electromagnetic shield to protect it from outside electromagnetic pollution. The current work aims to develop a mesh around the operating equipment to protect and make it work better. AL6061 was used to create a shield with a metal matrix composite. Here three combinations of Metal Matrix Composite (MMCs) were considered to protect from the high-intensity radiated fields.

Read more

YOLO Based Deep Learning Model for Segmenting the Color Images

The first stage is to extract fine details from a picture using Red Green Blue (RGB) colour space is colour image segmentation. Most grayscale and colour picture segmentation algorithms use original or updated fuzzy c-means (FCM) clustering. However, due to two factors, the majority of these methods are inefficient and fail to produce the acceptable segmentation results for colour photos. The inclusion of local spatial information often results in a high level of computational complexity due to the repetitive distance computation between clustering centres and pixels within a tiny adjacent window. The second reason is that a typical neighbouring window tends to mess up the local spatial structure of images. Color picture segmentation has been improved by introducing Deep Convolution Neural Networks (CNNs) for object detection, classification and semantic segmentation.

Read more

A Novel Swarm Approach for Regulating Load Frequency in Two-Area Energy Systems

One of the most important strategies for running and controlling an electric power system is the load frequency controller. LFC can be used to solve a variety of issues, such as when a generating unit is rapidly turned off by protection equipment or when a heavy load is quickly connected or disconnected. When disturbances disrupt the natural power balance, the frequency deviates from what it should be. LFC is in charge of balancing the load and restoring the natural frequency to its proper level. In this case, load frequency control optimization techniques are used in the Multiple Connect Area System to provide reliable and quality operation on frequency and tie line power flow.

Read more

A Novel Swarm Approach for Regulating Load Frequency in Two-Area Energy Systems

Power quality is the primary issue to be taken into consideration in modern electrical systems, particularly on the distribution side, to protect sensitive loads. Long-term uses can never run out of renewable resources. Connecting STATCOM at the distribution side enhances the power factor by improving the quality of the current waveform. The reactive power range that needs adjustment by utilising PV arrays on the STATCOM's DC side. Increases due to the large rise in terms of the PV power plants' size and capacity. Cascaded H Bridge multilevel topologies can increase the flexibility and effectiveness of PV modules.

Read more

Performance Assessment of Customized LSTM based Deep Learning Model for Predictive Maintenance of Transformer

To improve predictive maintenance of transformers with small DGA datasets, customized LSTM network named C-LSTM is devised to circumvent the boundaries of the standard-LSTM network, which had an increased rate of classification error than conventional machine learning techniques. The study compares the performance of traditional machine learning algorithms with the customized LSTM model using various metrics such as validation accuracy, test accuracy, precision, recall, and F1-score.

Read more

A Fractional Order Tilt Integral Controller Based Load Frequency Control with Dispersed Generation and Electric Vehicle

The elevated level of entrance of decentralized power sources with their Intermittent and volatility gives us a accost task to control load frequency, moreover this quandary is getting worsen up with the Involvement of electric vehicles in the rundown. This paper presents a censorious robust fractional order operative established tilt integral derivative controller (FOTID) for regulating the frequency. To emulate distributed power sources a linearized model of a wind power plant is considered and a small signal model of EV is developed.

Read more

Detection and Segmentation of Meningioma Brain Tumors in MRI brain Images using Curvelet Transform and ANFIS

The detection of abnormal tumor region brain Magnetic Resonance Images (MRI) is complex task due to its similar structures between tumor and its surrounding regions. In this paper, Adaptive Neuro Fuzzy Inference System (ANFIS) classification method-based meningioma brain tumor detection is proposed. The proposed method consists of the following stages as preprocessing, transformation, feature extraction and classifications. The brain MR images are enhanced in preprocessing stage and this spatial domain image is converted into multi resolution image using Curvelet transform.

Read more

Non-invasive and Automatic Identification of Diabetes Using ECG Signals

Diabetes Mellitus is a chronic medical condition in which the body is unable to properly regulate the amount of glucose (a type of sugar) in the blood. It can cause serious consequences like heart disease, nerve damage, and kidney illness. Diabetes causes cardiac autonomic neuropathy, which affects the pattern of electrocardiogram (ECG) signals. ECG measures electrical activity of the hearts. In this paper, the features extraction method is proposed for the classification of diabetic ECG and normal ECG signals.

Read more

Hybridization of Machine Learning Techniques for WSN Optimal Cluster Head Selection

Wireless sensor networks (WSN) keep developing in recent days concerning the self-covered network, self-healing network, and association of system component circuit selections that enable the implementation process. Wireless sensor network lifetime stabilization is essential to providing a higher quality experience to consumers. The wireless sensor network is associated with classifiers that keep learning the data pattern and further modify the cluster selection to produce dynamic results.

Read more

Design and Analysis of Analog Feedback Communication System with Rayleigh Fading Channel Model

In this work, we mathematically model a wireless Analog feedback communication system (AFCS) using a Rayleigh fading channel. AFCS system is a new research area and has promising applications, especially in low-power devices such as sensors. Compared to AWGN, Rayleigh fading channel more closely models the real wireless environment. In this work, AFCS Rayleigh fading channel is considered in forward transmission while AWGN is considered in the feedback channel.

Read more

Performance Analysis of Energy Efficiency and Security Solutions of Internet of Things Protocols

The scientific and business communities are showing considerable interest in wireless sensor networks (WSN). The availability of low-cost, small-scale components like CPUs, radios, and sensors, which are often combined into a single chip, is crucial. Parallel to the evolution of WSNs, the concepts of the IoT have been evolving in recent years. Wireless communication technologies may play a significant role in the implementation of IoT, despite the fact that IoT does not need or require any particular technology for communication. WSN assisted IoT networks can drive several applications in many industries. The proposed research explores the possibility of enhancing energy efficiency in WSN-assisted IoTN by balancing various challenging sensor network performance metrics.

Read more

A Novel Hybrid Energy Efficient Model using Clustering in Wireless Sensor Networks

An innovative hybrid approach is presented in this paper aimed at rapid predicting the optimum routing path selection in WSNs using the Lagrangian method and Clustering. The main motive of this work proposed is to maximize the clustering productivity, reduce the congestion in routing system and optimize the energy range in the network. By combining the route prediction through clustering and energy flow estimates in the routing protocol design-based algorithm, this will combine both the objectives of rapid route prediction and energy flow estimation

Read more

Development and Application of an Energy Management System for Electric Vehicles Integrated with Multi-input DC-DC Bidirectional Buck-Boost Converter

The rise in environmental pollution, demand for fossil fuels, and higher fuel economy vehicles has raised concerns about the creation of new and efficient transportation vehicles in recent days. These days, most developments in electric vehicles concentrate on making the vehicles more pleasant to ride in. Nonetheless, the emphasis now should be on energy and its most efficient use. To do this, you must give your attention to the origin of the automobile. The answer to this problem may be found in hybrid energy storage systems (HESS). This work is concerned with the design and implementation of an effective energy management system in electric vehicles (EVs) equipped with an active HESS consisting of a battery and a super capacitor via the incorporation of load sharing into this hybridization under a variety of load demand scenarios.

Read more

Design and Control of a Tricycle with a Hybrid Electric Motor Cooling System Powered By Solar Photovoltaics

The power for a standard electric tricycle used for transportation comes from a battery, which can lose power after a certain amount of time. In this regard, the standard tricycle in the proposed concept will have a battery that will be charged by solar panels mounted on a stand on the rear of the tricycle. A solar-based renewable energy source is also used along with the traditional charging mechanism to make a hybrid system. The proposed tricycle is more stable in braking turns because it has a lower center of gravity compared to a bicycle. The proposed tricycle has movement in both directions, i.e., forward and reverse, for disabled persons. The proposed model was validated using the finite element analysis approach in solid work for different points of the frame and different types of loads.

Read more

Novel Low-Pass Filter Structures Using Spur-Lines to Generate Additional Attenuation Poles

We propose two novel low-pass filter (LPF) structures that have generated additional attenuation poles from applying spur-lines to typical open-stub LPFs. The first structure has the spur-lines added to the serial lines, and the second structure has the spur-lines added to the parallel open stub. From the characteristic analyses of the filters with the proposed design, it was confirmed that the length of the spur-line was an important variable for controlling the stopband bandwidth and attenuation depth. The two types of LPFs were fabricated and then validated by the agreement between the theoretical and measured results.

Read more

Power Circuit Design and Analysis of Controller For High-Power Axial Flux PMSM

Designing a high-power controller having high efficiency for permanent magnet motors is a challenge for developers in recent times and very few techniques are available. Design and analysis of power electronic drive for a high-power axial flux permanent magnet synchronous motor is presented in this paper. The motor under consideration here is having two outer stators and single permanent magnet rotor to drive the shaft. Control schemes and methodologies are the major concentration for research. Present paper explains a method to estimate the operational drive parameters and loss calculation according the selected power switches.

Read more

MCS Selection Based on Convolutional Neural Network in TDD System

In this paper, a convolutional neural network (CNN) is proposed for selecting modulation and coding schemes (MCSs) at the time of future transmission in time-division-duplex (TDD) systems. The proposed method estimates the signal-to-noise ratio (SNR) obtained by the average of the equalizer’s output in the orthogonal frequency division multiplexing (OFDM) system and records it to select the most suitable MCS for future transmission. Two methods are proposed: one that directly selects an MCS and one that predicts the SNR first before selecting an MCS. The conventional method commonly used is to select an MCS based on the SNR of the most recently received signal.

Read more

Amplify-and-Forward (AF) Relay Techniques in Wireless SC-FDE Systems to Enhance Diversity Gains

This paper introduces an amplify-and-forward (AF) relaying technique that employs phase dithering and intentional delay within single carrier-frequency domain equalizer (SC-FDE) systems. The proposed relaying technique aims to increase the gain of both frequency diversity and time diversity in slow fading channels. To achieve this, the proposed technique introduces random phase rotation and random intentional delay. The relaying scenario assumes two-hop communication with relaying between the source and destination. It is assumed that many nodes are densely distributed, allowing for many relay nodes to participate in relaying.

Read more

A Diagnostic Study of Content-Based Image Retrieval Technique for Studying the CT Images of Lung Nodules and Prediction of Lung Cancer as a Biometric Tool

Content Based Medical Image Retrieval (CBMIR) can be defined as a digital image search using the contents of the images. CBMIR plays a very important part in medical applications such as retrieving CT images and more accurately diagnosing aberrant lung tissues in CT images. The Content-Based Medical Image Retrieval (CBMIR) method might aid radiotherapists in examining a patient's CT image in order to retrieve comparable pulmonary nodes more precisely by utilizing query nodes. Intending a particular query node, the CBMIR system searches a large chest CT image database for comparable nodes.

Read more

Transmit Antenna Selection Based on SNR prediction in TDD Systems Using Convolutional Neural Network

This paper proposes a method for predicting future signal-to-noise ratio (SNR) in a time-division-duplexing (TDD) mobile communication environments using a convolutional neural network (CNN). The communication system uses multiple receive antennas and transmit using only one or two antennas among them. A CNN model is proposed to predict the SNR at a future transmission time based on past SNRs received from multiple antennas. The probability of reception at a certain is set to 10-100%. In case that SNR cannot be measured due to the absence of reception, linear interpolation is performed using two adjacent recorded SNRs. If even two adjacent SNRs do not exist, the SNR is set to 0dB. Comparing the predicted SNRs at multiple antennas, the antenna with the highest SNR value is selected for future transmission. To verify antenna selection accuracy, computer simulation is conducted.

Read more

Bi-Usage Energy Efficient Techniques (BUEET) for Energizing the Vehicle and Broadcasting the Information in Highway Scenario

The proposed technique BUEET is introduced mainly for two major reasons such as (i) RSU broadcast the emergency messages and the energy status to the vehicles without any interruption. It helps to shake hands with the neighboring node for energy sharing and (ii) RSU boost up the energy efficiency level with the help of energy sharing by the adjacent vehicles. Most of the self-organizing protocols in wireless sensor networks considers only initial energy consumption phase and neglects the maintenance phase of topology. The vehicles are cooperatively interacted to form a reliable network structure. RSU’s are placed in the roadway infrastructure and On-Board Units (OBU’s) are placed in the vehicles, then the communication takes place with the help of these devices.

Read more

Frequency Diversity Using Random Time Delay in Amplify-And-Forward Relay

In a tactical wireless communication environment, it is common for device-to-device communication to occur without a base station, but this can be problematic when the distance between the source and destination is too far. Relays are often used to improve transmission distance and reliability, but amplification-based relaying can result in lower communication performance compared to other methods. This paper proposes a method for obtaining diversity gain through the application of time delay during relaying. The proposed method is compared to a conventional method that uses phase rotation to obtain diversity gain.

Read more

Design of Three-valued Logic Based Adder and Multiplier Circuits using Pseudo N-type CNTFETs

This work presents a novel technique to develop the three-valued logic (TVL) circuit schematics for very large-scale integration (VLSI) applications. The TVL is better alternative technology over the two-valued logic because it provides decreased interconnect connections, fast computation speed and decreases the chip complexity. The TVL based complicated designs such as half-adder and multiplier circuits are designed utilizing the Pseudo N-type carbon nanotube field effect transistors (CNTFETs). The proposed TVL half adder multiplier schematics are developed in HSPICE tool.

Read more

A New Closed Loop Constant v/f Control of Induction Motor with Torque Control Based on DPWM

An easy sensor-less scalar control algorithm is described in this article as a method for controlling the speed of an induction motor. For developing a closed-loop v/f control of the induction motor drive, a torque controller with PI is implemented. The torque command was estimated by utilizing the voltage command, the feedback current, and a torque estimator. Additionally, a torque reference was provided for the Torque PI controller. Considering this, the purpose of this work is to investigate the closed-loop PI-based torque control of an induction motor drive that applies DPWM.

Read more

Performance Estimation of Improved Cooperative Spectrum Sensing under Fading Environment

To deal with spectrum scarcity, Cognitive radio has been considered as a resolving technology. Energy detection(ED) is the most preferable sensing technique due to its lower complexity, ease of working and non-dependency on primary user data requirements. Although having many advantages, ED has some practical limitations like low SNR, shadowing, erroneous reporting channels and multipath fading. Here, a comparative study is done to check the effect of such parameters. And with simulation, it is proven that Cooperative spectrum sensing can reduce the effect of these confines. In this paper, we have also simulated the improved version of ED where decision making is done cooperatively.

Read more

Alpha-Theta Correlations during the Different States of the Brain for a Designed Cognitive Task

Brain oscillations vary due to neurological activities that play an important role in designing a cognitive task. In the proposed study, 27 subjects experimented with different cognitive activities (rest, meditation, and arithmetic) and their alpha and theta bands of frequencies were analyzed. BIOPAC-MP-160 has performed the data acquisition and further processing of the acquired dataset was implemented in EEGLAB. The results illustrated that the cross-frequency correlation (alpha: theta: 1:2) between alpha and theta waves has been enhanced during effortful cognition (arithmetic state).

Read more

Power Quality Improvement using Dual Multilevel Converter for Micro Grid-Connected PV Energy Systems using ANFIS

This paper presents the implementation of dual voltage source inverter (DVSI) approach to improve the microgrid performance by enhancing the power quality. This paper also improves the power quality in photovoltaic (PV) generation interactive microgrids, respectively. The power generated from PV based distributive energy resources (DER) is perfectly applied to the microgrid through the two inverters, thus the nonlinear and unbalance load related problems are compensated. Thus, the power quality problems such as voltage sag, current drops, and power factor, active, and reactive powers are reduced by dual multilevel converter (DMLC).

Read more

Transfer Learning Technique for Covid-19 Screening from CT-Scan: An Empirical Approach

As a result of the Covid-19 pandemic, the field of Medical Sciences has been challenged with new challenges and benchmarks for development. Front line workers are overcoming the Covid-19 challenge with four steps: Screening and Diagnosis, Contact Tracing, Drug and Vaccine Development, and Prediction & Forecasting. Following the above segments carefully can save millions of lives. Artificial Intelligence has proven invaluable in predicting critical factors in many fields. With the ability of AI to process huge databases and conclude with high precision, we are motivated to use AI to screen and diagnose the Covid-19 pandemic.

Read more

A Hybrid Feature Selection Approach based on Random Forest and Particle Swarm Optimization for IoT Network Traffic Analysis

The complexity and volume of network traffic has increased significantly due to the emergence of the “Internet of Things” (IoT). The classification accuracy of the network traffic is dependent on the most pertinent features. In this paper, we present a hybrid feature selection method that takes into account the optimization of Particle Swarms (PSO) and Random Forests. The data collected by the security firm, CIC-IDS2017, contains a large number of attacks and traffic instances

Read more

Enhancing Gastric Cancer Lymph Node Detection through DL Analysis of CT Images: A Novel Approach for Improved Diagnosis and Treatment

Although gastric cancer is a prevalent disease worldwide, accurate diagnosis and treatment of this condition depend on the ability to detect the lymph nodes. Recently, the use of Deep learning (DL) techniques combined with CT imaging has led to the development of new tools that can improve the detection of this disease. In this study, we will focus on the use of CNNs, specifically those built on the “MobileNet” and “AlexNet” platforms, to improve the detection of gastric cancer lymph nodes. The study begins with an overview of gastric cancer and discusses the importance of detecting the lymph nodes in the disease management cycle. CT and DL are discussed as potential technologies that can improve the accuracy of this detection.

Read more

A Novel Approach to Cervical Cancer Detection Using Hybrid Stacked Ensemble Models and Feature Selection

Around the world, millions of women are diagnosed with cervical cancer each year. Early detection is very important to produce a better overall quality of life for those diagnosed with the disease and reduce the burden on the healthcare system. In recent years, the field of machine learning (ML) has been developing methods that can improve the accuracy of detecting cervical cancer. This paper presents a new approach to this problem by using a combination of image segmentation and feature extraction techniques. The proposed approach is divided into three phases. The first stage involves image segmentation, which is performed to extract the regions of interest from the input image.

Read more

Cancer Symptoms Detection from Liver CT Images Using Multistage Pre-Processors

Visually cancer is the abnormal pattern with predefined structure could be found in liver Computed Tomography (CT) images. Using deep convolution neural network computation and image processing, this detected abnormal pattern cluster can be classified in different liver issue types. Full size liver CT scan images consisting different body parts, and these are ultrasonic based gray scaled image construction. The primary challenge in the cancer symptoms detection process is to extract the liver area out of image then finding out the actual area of abnormality to conclude whether abnormality is cancer or any other issues on liver.

Read more

High Switching Speed and Low Power Applications of Hetro Junction Double Gate (HJDG) TFET

Tunnel field effect transistor (TFET) technology is unique of the prominent devices in low power applications. The band-to-band tunnel switching mechanism is sets TFET apart from traditional MOSFET technology. It helps to reduce leakage currents. The major advantage is the Sub threshold slope smaller than 60mv/decade. Newer technologies are expected to change the gate, architectures, channel materials and transport mechanisms.

Read more

VMLHST: Development of an Efficient Novel Virtual Reality ML Framework with Haptic Feedbacks for Improving Sports Training Scenarios

This paper presents the development of a novel virtual reality (VR) machine learning (ML) framework that incorporates haptic feedback to improve sports training scenarios. The framework uses You Look Only Once (YoLo) for object detection, and combines it with ensemble learning to analyze the performance of athletes in a simulated environment and provide real-time feedbacks. The system includes haptic feedback devices that are controlled via Grey Wolf Optimization (GWO) to simulate the physical sensation of a real-world sports scenario, allowing athletes to experience the sensation of force, impact, and movements.

Read more

A Diabetic Retinopathy Detection Using Customized Convolutional Neural Network

The disease, Diabetic Retinopathy (DR) causes due to damage to retinal blood vessels in diabetic patients. DR occurs if you have type 1 or 2 diabetes along with high blood sugar. When the retinal blood vessels are damaged, they can become clogged, some of which can block the blood supply to the retina leading to blood loss, these new blood vessels may leak, and the creation of scar tissue can lead to loss of vision. It takes a lot of time and effort to examine and analyse fundus images the old-fashioned way to find differences in how the eyes are shaped. In this modern era, technology has evolved so fleet which has the solution to every problem.

Read more

Anomaly Based Intrusion Detection through Efficient Machine Learning Model

Machine learning is commonly utilised to construct an intrusion detection system (IDS) that automatically detects and classifies network intrusions and host-level threats. Malicious assaults change and occur in high numbers, needing a scalable solution. Cyber security researchers may use public malware databases for research and related work. No research has examined machine learning algorithm performance on publicly accessible datasets.

Read more

IARMTS: Design of an Interference-Aware Routing Model with Time Synchronization Capabilities for Dense Wireless Sensor Network Deployments

Performance of dense wireless sensor networks is often degraded due to communication interference and time synchronization issues. Existing machine learning & deep learning models that propose bioinspired & pre-emptive packet-analysis solutions for these tasks either have high complexity, or high deployment costs. Moreover, these models cannot be scaled for heterogeneous node & traffic types, which limits their applicability when applied to real-time scenarios. To overcome these issues, this text proposes design of an interference-aware routing model with time synchronization capabilities for dense wireless sensor network deployments.

Read more

Image Forgery Detection Using Integrated Convolution-LSTM (2D) and Convolution (2D)

Digital forensics and computer vision must explore image forgery detection and their related technologies. Image fraud detection is expanding as sophisticated image editing software becomes more accessible. This makes changing photos easier than with the older methods. Convolution LSTM (1D) and Convolution LSTM (2D) + Convolution (2D) are popular deep learning models. We tested them using the public CASIA.2.0 image forgery database. ConvLSTM (2D) and its combination outperformed ConvLSTM (1D) in accuracy, precision, recall, and F1-score. We also provided a related work on image forgery detection models and methods. We also reviewed publicly available datasets used in picture forgery detection research, highlighting their merits and drawbacks.

Read more

Machine Learning Technique for Predicting Location

In the current era of internet and mobile phone usage, the prediction of a person's location at a specific moment has become a subject of great interest among researchers. As a result, there has been a growing focus on developing more effective techniques to accurately identify the precise location of a user at a given instant in time. The quality of GPS data plays a crucial role in obtaining high-quality results. Numerous algorithms are available that leverage user movement patterns and historical data for this purpose. This research presents a location prediction model that incorporates data from multiple users.

Read more