Articles published in IJEER


Performance Analysis of Feature Extraction Approach: Local Binary Pattern and Principal Component Analysis for Iris Recognition system

In this paper, feature extraction approaches like local binary pattern and principal component analysis assimilation has been offered. For classification, Support Vector Machine has been used. This paper compares the efficiency of two popular feature extraction methods Principal Component Analysis and Local Binary Pattern using two different iris databases CASIA and UBIRIS. The models were tested using 200 iris images. Statistical parameters like F1 score and Accuracy are tested for different threshold values. Our proposed method results with accuracy of 94 and 92%, is obtained for using Local Binary Pattern for CASIA and UBIRIS data set respectively. The Receiver Operating Characteristic Curve has been drawn and Area under Curve is also calculated. The experiment has been extended by varying the dataset sizes. The result shows that LBP achieves better performance with both CASIA and UBIRIS databases compared to PCA.

Read more

IoT-Based Sensor Shoes System for Gait Correction

This study aimed at determining the walking styles through pressure sensor. It uses a three-axis accelerometer and a gyro sensor to identify pigeon-toed walking and splay-footed walking. The system can monitor gait using the sensor data stored in the PC and smartphone applications transferred via Bluetooth. This can be visually confirmed through color changes in accordance with the sensor value with the neo-pixels. Research developments can analyze the type of gait as compared to the value for the case of incorrect gait based on normal pace with the acceleration value through the sensor. Through the experiment, the recognition rate capable of distinguishing in toeing gait was 56.25%, and out toeing gait was 81.25%. The system of this paper continuously collects gait data to enable monitoring whenever and wherever users want.

Read more

Optimizing QoS-Based Clustering Using a Multi-Hop with Single Cluster Communication for Efficient Packet Routing

Modern day communication systems have gained a revolutionized growth in long-distance wireless data transmission. High speed packet transfer impacts quality requirements. Critical factors that ruin service quality (Qos) are calculated by the primary factors involving power efficiency, packet delivery ratio, and overall transmission and reception delay. A well-developed routing protocol with unique attributes should be deployed to give improved QoS. The drawback of single path routing in delivering a packet at traffic is challenging since it does not have an alternative path in case of path failure. This problem can be targeted by a properly structured protocol with a multipath mechanism. In this article, Multi-hop with single cluster (SCMC) protocol is designed to increase the overall system efficiency by improving bandwidth, packet delivery ratio (PDR), reducing communication delay, and quality improvement.

Read more

Blockchain Technology to Handle Security and Privacy for IoT Systems: Analytical Review

With a large number of mobile terminals accessing IoT for information exchange and communication, security issues such as identity authentication, data transmission, and device failure are becoming more and more serious. Most of the traditional security technologies are based on centralized systems, and due to the limitation of IoT topology, traditional security technologies can only be applied to specific industries. Blockchain technology has the features of decentralization, data encryption, and tamper-proof, which are especially suitable for application in complex heterogeneous networks. This paper discusses for the first time the use of the block chain in many fields, providing an opportunity to address IoT security issues. Second, it discussed the IoT acceptance on various domains and the privacy issues IoT faces on limited resources.

Read more

Object Detection and Recognition in Real Time Using Deep Learning for Visually Impaired People

This paper aims at combining object detection at real time and recognition with suitable deep learning methods in order to detect and recognize objects position as well as the names of multiple objects detected by the camera using an object detector algorithm. This is to aid the visually impaired user without the help of any other person. The image and video processing algorithms were designed to take real-time inputs from the camera, Deep Neural Networks were used to predict the objects and uses Google’s famous Text-To-Speech (GTTS) API module for the anticipated voice output precisely detecting and recognizing the category or class of objects and locations contained. Our best result shows that the system recognizes 91 categories of outdoor objects and produces the output in speech i.e. in an audio format even when a reduced amount of spectral information from the data is available.

Read more

Cyber Defense in the Age of Artificial Intelligence and Machine Learning for Financial Fraud Detection Application

Cyber security comes with a combination of various security policies, AI techniques, network technologies that work together to protect various computing resources like computing networks, intelligent programs, and sensitive data from attacks. Nowadays, the shift to digital freedom had led to opened many new challenges for financial services. Cybercriminals have found the ability to leverage e- currency exchanges and other financial transactions to perform their fraudulent activities. The unregulated channel makes it essential for banks and financial institutions to deploy advanced AI & ML (DL) techniques to fight cybercrime. This can be implemented by deploying AI & ML (DL) techniques. Customers are experiencing an increase in the fraud-hit rate in financial banking operations. It is difficult to defend against dynamic cyber-attacks using conventional non- dynamic algorithms.

Read more

Enhanced Visual Analytics Technique for Content-Based Medical Image Retrieval

Content-based image retrieval (CBIR) is a method for searching that finds related images in a medical database. Furthermore, a clinical adaptation of CBIR is hampered in part by a contextual gap that is the disparity among the person characterization of the picture and the framework characterization of the image. This technique makes it tough for the user to validate the fetched images that are similar to the query image in addition to that it only fetches the images of top-ranked and ignores the low-ranking ones. Visual Analytics for Medical Image Retrieval is a novel procedure for medicinal CBIR proposed in this research (VAMIR).

Read more

Caries Detection from Dental Images using Novel Maximum Directional Pattern (MDP) and Deep Learning

Various machine learning technologies and artificial intelligence techniques were applied on different applications of dentistry. Caries detection in orthodontics is a very much needed process. Computer-aided diagnosis (CAD) method is used to detect caries in dental radiographs. The feature extraction and classification are involved in the process of caries detection in dental images. In the 2D images the geometric feature extraction methods are applied and the features are extracted and then applied to machine learning algorithms for classification. Different feature extraction techniques can also be combined and then the fused features can be used for classification. Different classifiers support vector machine (SVM), deep learning, decision tree classifier (DT), Naïve Bayes (NB) classifier, k-nearest neighbor classifier (KNN) and random forest (RF) classifier can be used for the classification process.

Read more

Intelligent Solutions for Manipulating Purchasing Decisions of Customers Using Internet of Things during Covid-19 Pandemic

It is a well-known fact that consumers may gain significant benefits from the effective use of IoT in pandemic and post-pandemic settings. Security vulnerabilities can be seen in the ever-increasing Internet of Things (IoT) ecosystem from cloud to edge, which is crucial to note in this particular circumstance. Most merchants, even luxury stores, have failed to implement robust IoT cyber security procedures. Therefore, the researchers sought to put forth secondary research methodologies to bring forward efficient scrutiny regarding this particular issue to properly comprehend the influence of IoT in various devices, including a smartwatch, power displaying metre, brilliant weight showing gadgets and many more.

Read more

Effective Cyber Security Using IoT to Prevent E-Threats and Hacking During Covid-19

This research work is conducted to make the analysis of digital technology is one of the most admired and effective technologies that has been applied in the global context for faster data management. Starting from business management to connectivity, everywhere the application of IoT and digital technology is undeniable. Besides the advancement of the data management, cyber security is also important to prevent the data stealing or accessing from the unauthorized data. In this context the IoT security technology focusing on the safeguarding the IoT devices connected with internet. Different technologies are taken under the consideration for developing the IoT based cyber security such as Device authentication, Secure on boarding, data encryption and creation of the bootstrap server. All of these technologies are effective to its ground for protecting the digital data.

Read more

Effect of Machine Learning Techniques for Efficient Classification of EMG Patterns in Gait Disorders

Gait disorder is very common in neurodegenerative diseases and differentiating among the same kinematic design is a very challenging task. The muscle activity is responsible for the creation of kinematic patterns. Hence, one optimal way to monitor this issue is to analyse the muscle pattern to identify the gait disorders. In this paper, we will investigate the possibility of identifying GAIT disorders using EMG patterns with the help of various machine learning algorithms. Twenty-five normal persons (13 male and 12 females, age around 28 years of age) and 21 persons having GAIT disorders (11 male and 10 females, age around 67 years of age). Four different machine learning algorithms have been used to identify EMG patterns to recognize healthy and unhealthy persons.

Read more

Image Steganography Technique based on Singular Value Decomposition and Discrete Wavelet Transform

Steganography is a technique of hiding information in digital media. In recent years plenty of work has been done in this domain, and the work can be compared on various parameters such as high robustness and large capacity to achieve a goal. This paper proposed the method of steganography in digital media using Singular Value Decomposition (SVD) and Discrete Wavelet Transform (DWT). The DWT is a frequency-domain technique comprising DWT which comparatively offers better robustness and high PSNR value of stego image over other techniques. The proposed method works well for information hiding against AWGN (additive white Gaussian noise) attack and fulfills the objective to achieve high robustness and high PSNR.

Read more

On the Connection of Matroids and Greedy Algorithms

Matroids are the combinatorial structure and Greedy algorithmic methods always produces optimal solutions for these mathematical models. A greedy method always selects the option that looks best at each step of process of finding optimal solution. In other words, it selects a choice which is optimal choice locally in such a strategy that this locally chosen option may direct to a solution that will be globally optimal. It is true that while selecting locally optimal solution at each stage, Greedy algorithms may not always yield optimal solutions [1-2], but if we can transform an unknown problem into matroid structure, then there must be a greedy algorithm that will always lead optimal solution for that unknown problem. The range of solutions provided by Greedy is large as compared to the applicability of the Matroid structure.

Read more

Optimization of Software Quality Attributes using Evolutionary Algorithm

Software quality is a multidimensional concept. Single attribute can’t define the overall quality of the software. Software developer aims to develop software that possesses maximum software quality which depends upon various software quality attributes such as understand ability, flexibility, reusability, effectiveness, extendibility, functionality, and many more. All these software quality attributes are linked with each other and conflicting in nature. Further, these quality attributes depend upon the design properties of the software. During the designing phase of software, developers must optimize the design properties to develop good software quality. To obtain the appropriate value optimization is done. This paper implemented two multi-objective evolutionary algorithms (NSGA-2 and MOEA/D) to optimize software design properties to enhance software quality.

Read more

Free Hold Price Predictor Using Machine Learning

People who want to buy a new home tend to save more on their budgets and market strategies. The current system includes real estate calculations without the necessary forecasts for future market trends and inflation. The housing market is one of the most competitive in terms of pricing and the same has varied greatly in terms of many factors. Asset pricing is an important factor in decision- making for both buyers and investors in supporting budget allocation, acquisition strategies and deciding on the best plans as a result, it is one of the most important areas in which machine learning ideas can be used to maximize and accurately anticipate prices. As a result, in this paper, we present the different significant factors that we employ to accurately anticipate property values.

Read more

A Cost-Effective and Scalable Processing of Heavy Workload with AWS Batch

Recent technological advancements in the IT field have pushed many products and technologies into the cloud. In the present scenario, the cloud service providers mainly focus on the delivery of IT services and technologies rather than throughput. In this research paper, we used a scalable cost-effective approach to configure AWS Batch with AWS Fargate and CloudFormation and implemented it in order to handle a heavy workload. The AWS service configuration procedure, GitHub repository, and Docker desktop applications have been clearly described in this work.

Read more

A New Fail-Stop Group Signature over Elliptic Curves Secure against Computationally Unbounded Adversary

If an adversary has unlimited computational power, then signer needs security against forgery. Fail Stop signature solves it. If the motive of the signature is to hide the identity of the signer who makes signature on behalf of the whole group then solution is Group signature. We combine these two features and propose “A new Fail Stop Group Signature scheme (FSGSS) over elliptic curves”. Security of our proposed FSGSS is based on “Elliptic curve discrete logarithm problem” (ECDLP). Use of elliptic curve makes our proposed FSGSS feasible to less bandwidth environment, Block chains etc. Due to security settings over elliptic curves, efficiency of proposed scheme increases in terms of computational complexity.

Read more

Application of Chaotic Increasing Linear Inertia Weight and Diversity Improved Particle Swarm Optimization to Predict Accurate Software Cost Estimation

Nowadays usage of software products is increases exponential in different areas in society, accordingly, the development of software products as well increases by the software organizations, but they are unable to focus to predict effective techniques for planning resources, reliable design, and estimation of time, budget, and high quality at the preliminary phase of the development of the product lifecycle. Consequently, it delivered improper software products. Hence, a customer loses the money, time, and not belief on the company as well as effort of teamwork will be lost. We need an efficient and effective accurate effort estimation procedure.

Read more

Compression of Medical Images Using Wavelet Transform and Metaheuristic Algorithm for Telemedicine Applications

Medical image compression becomes necessary to efficiently handle huge number of medical images for storage and transmission purposes. Wavelet transform is one of the popular techniques widely used for medical image compression. However, these methods have some limitations like discontinuity which occurs when reducing image size employing thresholding method. To overcome this, optimization method is considered with the available compression methods. In this paper, a method is proposed for efficient compression of medical images based on integer wavelet transform and modified grasshopper optimization algorithm. Medical images are pre-processed using hybrid median filter to discard noise and then decomposed using integer wavelet transform.

Read more

Performance Analysis of MIMO System Using Fish Swarm Optimization Algorithm

During the signal identification process, massive multiple-input multiple-output (MIMO) systems must manage a high quantity of matrix inversion operations. To prevent exact matrix inversion in huge MIMO systems, several strategies have been presented, which can be loosely classified into similarity measures and evolutionary computation. In the existing Neumann series expansion and Newton methods, the initial value will be taken as zero as a result wherein the closure speed will be slowed and the prediction of the channel state information is not done properly. In this paper, fish swarm optimization algorithm is proposed in which initial values are chosen optimally for ensuring the faster and accurate signal detection with reduced complexity. The optimal values are chosen between 0 to 1 value and the initial arbitrary values are chosen based on number of input signals.

Read more

FPGA Implementation of High-Performance s-box Model and Bit-level Masking for AES Cryptosystem

The inadequacies inherent in the existing cryptosystem have driven the development of exploit the benefits of cipher key characteristics and associated key generation tasks in cryptosystems for high-performance security systems. In this paper, cipher key-related issues that exists in conventional symmetric AES crypto system is considered as predominant issues and also discussed other problems such as lack of throughput rate, reliability and unified key management problems are considered and solved using appropriate hierarchical transformation measures. The inner stage pipelining is introduced over composite field based s-box transformation models to reduce the path delay. In addition to that, this work also includes some bit level masking technique for AES.

Read more

A Survey on Various Machine Learning Techniques for an Efficient Brain Tumor Detection from MRI Images

On account of the uncontrolled and quick growth of cells, Brain Tumor (BT) occurs. It may bring about death if not treated at an early phase. Brain Tumor Detection (BTD) has turned out to be a propitious research field in the current decennia. Precise segmentation along with classification sustains to be a difficult task in spite of several important efforts and propitious results in this field. The main complexity of BTD emerges from the change in tumor location, shape, along with size. Providing detailed literature on BTD via Magnetic Resonance Imaging (MRI) utilizing Machine Learning (ML) methods to aid the researchers is the goal of this review. Diverse datasets are mentioned which are utilized most often in the surveyed articles as a prime source of Brain Disease (BD) data.

Read more

Knowledge Management using IoT-Blockchain Technology: State of the Art

This research investigated the database of journal articles related to knowledge management and blockchain technology. Knowledge is the most important production factor in competition. The purpose of knowledge management is to improve the ability of knowledge to create value. Blockchain is a shared distributed database, and blockchain technology, as one of the most popular computer technologies in recent years, has received great attention from all over the world. Purpose/Significance: This article aims to review and comment on the domestic and foreign literature on the use of blockchain technology for knowledge management, outline the current research status in this field, and predict its future research directions.

Read more

Security and Privacy Challenges using IoT-Blockchain Technology in a Smart City: Critical Analysis

A smart city is a comprehensive concept created by multiple digital industries. Smart city is a new generation of information technologies such as the Internet of Things, cloud computing, big data, and geospatial information to promote smart new ideas for urban planning, construction, management and services, power city operation and administrative management, industrial development, and public services in various fields. It is a modern high-end urban development form. A smart city is to establish a city center system by connecting terminals, applying information technology and network, and ultimately promoting the efficiency improvement and economic structure optimization in various fields.

Read more

A Compact High-Gain Microstrip Patch Antenna with Improved Bandwidth for 5G Applications

This paper presents a High Gain, enhanced Bandwidth Patch antenna for 5G operations. The dual-band is achieved using an inset-fed feeding technique for the microstrip patch antenna, which operates at the 28/38GHz millimeter-wave band. The high gain of the patch is achieved by inserting two rectangular slots on the radiating element of the patch. The designed antenna Bandwidth is improved by incorporating three steps at the edge of the rectangular patch. The substrate used for the format is Rogers RT Duroid 5880, with a thickness of 0.508mm, loss tangent of 0.0009, and a relative permittivity constant of 2.2. Ansys HFSS software is used for the simulation.

Read more

FPGA Design of Real Time Hardware for Face Detection

This paper proposes the hardware architecture of face detection FPGA hardware system using the AdaBoost algorithm. The proposed structure of face detection hardware system is possible to work in 30 frames per second and in real time. And the AdaBoost algorithm is adopted to learn and generate the characteristics of the face data by MATLAB, and finally detected the face using this data. This paper describes the face detection hardware structure composed of image scaler, integral image extraction, face comparing, memory interface, data grouper and detected result display. The proposed circuit is so designed to process one point in one cycle that the proposed design can process full HD (1920x1080) image at 70MHz, which is approximate 2316087 x 30 cycle.

Read more

Analysis of Interior Permanent Magnet Synchronous Motor according to Winding Method

In this paper, the hairpin method is applied to an Electric Vehicle (EV) driving motor with a stator winding designed with a round copper wire. The hairpin method is a method to secure a high space factor by using round copper wire instead of round copper wire for the stator winding. The applicable model is a 300kW Interior Permanent Magnet Synchronous Motor (IPMSM), and the cooling method is water cooling. The current density has a proportional relationship with the thermal characteristics, and in the case of a round copper wire, a method of lowering the current density by using the stator winding as a stranded wire is used.

Read more

1-Dimensional Convolutional Neural Network Based Blood Pressure Estimation with Photo plethysmography Signals and Semi-Classical Signal Analysis

In this paper, we propose a 1-Dimensional Convolutional Neural Network (1D-CNN) based Blood Pressure (BP) estimation using Photo plethysmography (PPG) signals and their features obtained through Semi-classical Signal Analysis (SCSA). The procedure of the proposed BP estimation technique is as follows. First, PPG signals are divided into each beat. Then, 9 features are obtained through SCSA for the divided beats. In addition, 5 biometric data are used. The Biometrics data include Heart Rate (HR), age, sex, height, and weight. The total 14 features are used for training and validating the 1D-CNN BP estimation model. After testing three types of 1D-CNNs, the model with the most optimal performance is selected. The selected model structure consists of three convolutional layers and one fully connected layer.

Read more

A Study on Edge Board for Blur Image Judgment and Cluster Image Behavior Analysis: AI-Based Image Processing System Research

The purpose of this study is to solve the problem that the control center cannot cope with the situation properly due to the difficulty of analyzing the behavior in the case of cluster images or the occurrence of unclear images due to weather conditions and fine dust. Edge board development is necessary for cases in which the image sharpness check and overlap image check are inaccurate. In addition, evaluation techniques such as PSNR (; Peak Signal-to-Noise Ratio) and SSIM (; Structural Similarity Index) are used for the corresponding images to evaluate the degree of image improvement of the model with a validation dataset for each fixed image. After evaluating the model's inference speed in terms of FPS (; Frame Per Second), verification is performed for each stored model for each training, and the improvement rate of the image is calculated to evaluate which model is the most optimal for each weather condition.

Read more

Fan-Shaped Flooding in Wireless Sensor Networks

In a wireless sensor network, data flows in two main directions. There are flooding that transfers data from the sink node to the entire node and routing that transfers data sensed by each sensor node to the sink node. Transferring data from the sink node of the wireless sensor network to the entire sensor node is called flooding. In an energy-constrained environment, a more efficient method has been developed, because the most basic flooding technique contains a lot of data redundancy. In this paper, the combination of the distance-based approach and the neighboring node information method is proposed as a more energy-efficient method. Flood data can be transmitted by adjusting the angle of the transmission line within the transmission radius to the shape of a fan and limiting the distance within the communication radius.

Read more

Design of an Integrated Cryptographic SoC Architecture for Resource-Constrained Devices

One of the active research areas in recent years that has seen researchers from numerous related fields converging and sharing ideas and developing feasible solutions is the area of hardware security. The hardware security discipline deals with the protection from vulnerabilities by way of physical devices such as hardware firewalls or hardware security modules rather than installed software programs. These hardware security modules use physical security measures, logical security controls, and strong encryption to protect sensitive data that is in transit, in use, or stored from unauthorized interferences.

Read more

128-Bit LEA Block Encryption Architecture to Improve the Security of IoT Systems with Limited Resources and Area

The LEA block encryption algorithm is an architecture suitable for IoT systems with limited resources and space. It was developed by the National Security Technology Research Institute in 2013 and established as an international standard for cryptography by the International Electrotechnical Commission in 2019, drawing much attention from developers. In this paper, the 128-bit LEA block encryption algorithm was light weighted and implemented in a hardware environment. All modules share and reuse registers and are designed and implemented in a bottom area through the resource sharing function.

Read more

Analysis of Score Level Fusion of Biometric Features

Biometric systems have gained acceptance in a variety of industries in recent years, and they continue to improve security features for access control systems. Numerous types of monotonic biometric systems have been developed. On the other hand, these systems can only provide low- to mid-level security features. As a result, combining two or more collinear biometrics are necessitated for significantly greater functionality. In this paper, a multimodal biometric technology for iris, face, and fingerprint assimilation has offered. Here, an effective matching approach based on Principal Component Analysis that employs three biometric modes to solve this challenge: iris, face, and fingerprint.

Read more

Energy Management System and Enhancement of Power Quality with Grid Integrated Micro-Grid using Fuzzy Logic Controller

A modern hybrid model is introduced, which is a combination of PV, Wind turbine, converter components to improve Microgrid (MG) operation, to improve system dependability, effective efficiency, which are fundamental qualities. In view of renewable energy Maximum Power Point Tracking (MPPT) is frequently applied to improve PV efficiency in which randomness, flexibility of solar energy because of changes in temperature. To achieve MPPT P&O rule, Incremental conductance (IC) methods are implemented in this manuscript. The design, execution of EMS with Fuzzy Logic Controller (FLC) for AC/DC microgrid is implemented. Apart from designing of EMS the power quality of MG is improved. It proposes analysis, control of storage devices.

Read more

An Advanced and Efficient Cluster Key Management Scheme for Agriculture Precision IoT Based Systems

Things that connect to other devices & systems via Internet or communication networks are called IoT. It can also be said as a network of wireless sensors connected to a cloud and controlled by embedded devices. Considering the large framework of IoT, it becomes a little difficult to maintain security at each sensor node especially with limited information regarding hardware and deployment capabilities. Therefore, management of keys has become a point of concern peculiarly taking account of node capturing attack. This paper proposes an advanced cluster key management scheme for agriculture precision which involves EBS constructor and Chinese remainder theorem together.

Read more

A Novel Algorithm to Secure Data in New Generation Health Care System from Cyber Attacks Using IoT

The rise of digital technology has essentially enhanced the overall communication and data management system, facilitating essential medical care services. Considering this aspect, the healthcare system successfully managed patient requirements through online services and facilitated patient experience. However, the lack of adequate data security and increased digital activities during Covid-19 made the healthcare system a soft target for hackers to gain unauthorized access and steal crucial and sensitive information. Countries such as the UK and the US recently received such challenges, highlighting the need for effective data maintenance. IoT emerged as one of the critical solutions for data management systems in terms of addressing data security which certainly can enhance overall data collection, storage, maintenance, prediction of potential data security breaches and taking appropriate measurements.

Read more

Application of Internet of Things (IoT) and Artificial Intelligence in Unmanned Aerial Vehicles

In the current era, to upgrade the facilities and features of UAVs, the implementation of IoT and AI is mandatory. It helps the drone to provide accurate data after analysing a particular situation. Moreover, it also helps to access the drone from any device with the help of an android app. The application of AI and IoT has enhanced the popularity of drones worldwide. This study has analysed the application of IoT and AI in UAVs to make them more efficient. This research has evaluated IoT and AI's positive and negative impacts on UAVs. Moreover, it has determined solutions to mitigate them effectively.

Read more

PMSG Wind Turbine Based Current Fed Three Phase Inverter with Model Predictive Control

Design of an improved Permanent Magnet Synchronous Generator (PMSG) wind turbine power based Current Fed Inverter (CFI) using Model Predictive Controller (MPC) is proposed in this paper. Optimum torque control is proposed in wind energy conversion system, MPC is used to adjust the dynamic response time based on the application need. This model deals with torque control strategy of PMSG in the machine side controller. Impact of normal mode of operation by the copper losses and torque ripples are minimized by maximizing the average torque. Synthetization of adequate stator phase current are obtained naturally. Uncertainty of the steady state errors of the plant and parameter error are rectified in the system model. The designed CFI with MPC was implemented using medium range wind turbine in MATLAB /Simulink.

Read more

Multiport Converter for CubeSat

Maximizing solar energy harvesting and miniaturizing DC-to-DC converters will be a difficult task for the CubeSat that operates in low earth orbit (LEO), where size and weight are limited. To maximize solar energy collection, the electrical power system (EPS) architectures use numerous separate DC–DC converters, which will be problem for miniaturization of whole model because several inductors will be used in each converter. The key purpose of this article is to demonstrate a topology of multiport converter that requires only one inductor and a small number of components, reducing the overall system size.

Read more

Performance Analysis of Fault Tolerant Operation of PMSM using Direct Torque Control and Fuzzy Logic Control

Electromagnets have traditionally been used in all drives. Because they take up space, the size of the machine grows in tandem with increased torque and it’s rating thereby lowering its energy efficiency. If the rotor winding is replaced with permanent magnets, the motor will reverse. The recent improvement of magnetic materials resulted in a reduction in motor size and more effective use of redial space. Permanent Magnet Synchronous Motors (PMSM) have a high-power factor, are extremely durable, and require almost no maintenance. Such motors can be designed with power ranging from a few watts to a few kilowatts for applications ranging from fans to alternators including electric vehicles. This need reliable and safe operation of drives which would be fault tolerant.

Read more

A Comparison of Machine Learning and Deep Learning Models for Predicting Household Food Security Status

ML and DL algorithms are becoming more popular to predict household food security status, which can be used by the governments and policymakers of the country to provide a food supply for the needy in case of emergency. ML models, namely: k-Nearest Neighbor (kNN), Logistic Regression (LR), Support Vector Machine (SVM), Naive Bayes (NB), Multi-Layer Perceptron (MLP) and DL models, namely: Artificial Neural Network (ANN) and Convolutional Neural network (CNN) are investigated to predict household food security status in Household Income, Consumption and Expenditure (HICE) survey data of Ethiopia.

Read more

A Novel Medical Image Segmentation Model with Domain Generalization Approach

In deep learning-based computing vision for image processing, image segmentation is a prominent issue. There is promising generalisation performance in the medical image segmentation sector for approaches using domain generalisation (DG). Single domain generalisation (SDG) is a more difficult problem than conventional generalisation (DG), which requires numerous source domains to be accessible during network training, as opposed to conventional generalisation (DG). Color medical images may be incorrectly segmented because of the augmentation of the full image in order to increase model generalisation capacity. An arbitrary illumination SDG model for improving generalisation power for colour image segmentation approach for medical images through synthesizing random radiance charts is presented as a first solution to this challenge. Color medical images may be decomposed into reflectivity and illumination maps using retinex-based neural networks (ID-Nets).

Read more

Investigation analysis of open circuit and short circuit fault on cascaded H-bridged multilevel inverter using artificial neural network approach

Cascaded H-bridge multilevel inverters are becoming increasingly used in applications such as distribution systems, electrical traction systems, high voltage direct conversion systems, and many others. Despite the fact that multilevel inverters contain a large number of control switches, detecting a malfunction takes a significant amount of time. In the fault switch configurations diode included for freewheeling operation during open-fault condition. During short circuit fault conditions are carried out by the fuse, which can reveal the freewheeling current direction. The fault category can be identified independently and also failure of power switches harmed by the functioning and reliability of cascaded H-bridge multilevel inverters.

Read more

Performance Analysis of Heat Exchanger System Using Deep Learning Controller

Conventional PID controllers have utilised in most of the process industries. Despite being the most used controller, the traditional PID controller suffers from several disadvantages. Due to rapid development in the field of the process control system, various controllers have been developed that try to overcome the limitations of the PID controller. In this paper, a heat exchanger system has been simulated, and the generated data has been used to train a deep learning-based controller using Backpropagation. The obtained results are compared with the conventional controller on several metrics, including time response, performance indices, frequency response etc.

Read more

Implementation of Elliptical Curve Cryptography Based Diffie-Hellman Key Exchange Mechanism in Contiki Operating System for Internet of Things

Wireless Sensor Networks have gradually upgraded to Internet of Things (IoT) of embedded devices wherein the constrained devices have been connected directly onto the Internet. This transformation has not only facilitated the expansion in connectivity and accessibility of the sensor network but has also enabled one sensor network to interact with other through Internet. Security of IoT devices has been researched extensively. The challenge to transform the complex cryptographic algorithms into lighter and faster has kept researchers on their toes. Contiki-OS is one of the purest implementations of 6LoWPAN and IEEE 802.15.4. That makes Contiki-OS lightest and therefore preferred OS for implementation on ultra-low power sensor nodes. Elliptical Cryptography has proved to be the choice of most of the security researchers for constrained devices.

Read more

Design and Leakage Power Optimization of 6T Static Random Access Memory Cell Using Cadence Virtuoso

Reduction of Leakage power at nano meter regime has become a challenging factor for VLSI designers. This is owing to the need for low-power, battery-powered portable pads, high-end gadgets and various communication devices. Memories are made up of Static RAM and Dynamic RAM. SRAM has had a tremendous impact on the global VLSI industry and is preferred over DRAM because of its low read and write access time. This research study proposes a new method has been proposed of 6T Static Random Access Memory cell to decrease the leakage current at various technologies. Three source biasing methods are used to minimize the 6T SRAM cell leakage power. The three methods are NMOS diode clamping, PMOS diode clamping and NMOS-PMOS diode clamping at 45 nm and 90 nm technology nodes.

Read more

Short Term Load Forecasting of Residential and Commercial Consumers of Karnataka Electricity Board using CFNN

Electricity use and its access are correlated in the economic development of any country. Economically, electricity cannot be stored, and for stability of an electrical network a balance between generation and consumption is necessary. Electricity demand depends on various factors like temperature, everyday activities, time of day, days of the week days/Holidays. These parameters have led to price volatility and huge spikes in electricity prices. The research work proposes a short term Load prediction Model for LT2 (residential consumers), LT3 (Commercial Consumers) of Karnataka State Electricity Board using Cascaded Feed Forward Neural Network (CFNN). MATLAB software is utilized to design and test the forecasting model for predicting the power consumption.

Read more

Analysis of Price and Incentive Based Demand Response programs on Unit Commitment using Particle Swarm Optimization

The increase in power demand by various infrastructural development activities and industrial automations in recent years have made a vital effect with respect to the load demand. To effectively manage the load demand, several Load Management (LM) techniques has been adopted in all energy policy decisions. In the de-regulated power system, the Demand Side Management (DSM) owing to its advantages at economic environments are regarded as remarkable choice and has been extended to incorporate Demand Response Programs (DRPs) in the load management techniques. In this paper, a responsive load economic model is developed. This model is based on the two factors such as price elasticity of demand and welfare function of customers. A Demand Response (DR) based Unit Commitment (DRUC) problem is studied to execute the economic analysis of DRPs.

Read more

Indexed Steep Descent Fish Optimization with Modified Certificateless Signcryption for Secured IoT Healthcare Data Transmission

IoMT is a healthcare strategy and utilization connected with online computer networks for IoT. During data communication from machine to machine, Security is one of essential barriers. In order to improve security, Jaccardized Czekanowski Indexive, Steepest Descent Fish Optimization Based Kupyna Schmidt-Samoa Certificateless Signcryption (JCISDFO-KSSCS) is introduced. JCISDFO-KSSCS is used for enhancing authentication and secure Data Transmission. JCISDFO-KSSCS comprises two major processes, namely authentication, and secured data transmission. The discussed results indicate that proposed JCISDFO-KSSCS increases the performance results than the conventional approaches.

Read more

Detection and Severity Identification of Covid-19 in Chest X-ray Images Using Deep Learning

COVID-19 pandemic is causing a significant flare-up, seriously affecting the wellbeing and life of many individuals all around the world. One of the significant stages in battling COVID-19 is the capacity to recognize the tainted patients early and put them under exceptional consideration. In the proposed model we used deep learning-based exception Net under transfer learning paradigm. We trained the proposed model using chest-X rays collected from the open-source dataset (COVID -19 Dataset) using K10 cross-validation. We further calculated the severity in the covid classified images by the model using radiologist ground truth. We achieved an accuracy of 96.1% in the classification, and we are able to calculate the severity of the COVID -19 within the range of 75-100 % risk. Our proposed model successfully classified the COVID chest x-rays with severity measure.

Read more

Behavioral Dynamics of High Impedance Fault Under Different Line Parameters

Predominantly the impedance faults can be classified as Low Impedance Faults (LIF) and High Impedance Faults (HIF). The LIF can be detected and protected by a conventional protective device. However, if High impedance fault occurs in the system, it is difficult to detect because of the low magnitude current. The overcurrent relay, which smartly detects the Low impedance faults, fails to detect the High impedance faults. This research work is organized as two components. In the first component some literatures regrading high impedance fault have been reviewed. In the second component classical modified several Emmanuel arc model is taken as the test system. Feeder number four is taken as the candidate feeder for testing the high impedance faults. The simulation is done through MATLAB and the results are obtained. From the results certain investigations are proposed.

Read more

Performance Analysis of Quantum Classifier on Benchmarking Datasets

Quantum machine learning (QML) is an evolving field which is capable of surpassing the classical machine learning in solving classification and clustering problems. The enormous growth in data size started creating barrier for classical machine learning techniques. QML stand out as a best solution to handle big and complex data. In this paper quantum support vector machine (QSVM) based models for the classification of three benchmarking datasets namely, Iris species, Pumpkin seed and Raisin has been constructed. These QSVM based classification models are implemented on real-time superconducting quantum computers/simulators. The performance of these classification models is evaluated in the context of execution time and accuracy and compared with the classical support vector machine (SVM) based models.

Read more

Performance Analysis of 9T SRAM using 180nm, 90nm, 65nm, 32nm, 14nm CMOS Technologies

The growing markets for low-power electronic devices energized by battery have created the need for smaller power-efficient chips to prevent frequent charging of the source. Nowadays the market capitalization of low-power appliances is expected to grow from USD 4.9 billion by 2022 to USD 7.9 billion by 2027 as per global forecast to 2027 published by markets. The main factor leading to growth of low power electronics market includes demand of energy saving components, miniaturization, and entry of IoT (Internet of Things) devices. In addition, increased investment by automotive OEM (Original Equipment Manufacturer) and governments to promote the adoption of electric vehicles is expected to create more market opportunities.

Read more

A Classy Memory Management System (CyM2S) using an Isolated Dynamic Two-Level Memory Allocation (ID2LMA) Algorithm for the Real Time Embedded Systems

Due to an increased scalability, flexibility, and reduced cost complexity, the dynamic memory allocation models are highly preferred for the real-time embedded systems. For this purpose, the different types of dynamic models have been developed in the conventional works, which are highly focused on allocating the memory blocks with increased searching capability. However, it faced some of the problems and issues related to the factors of complex operations, high time consumption, memory overhead, and reduced speed of processing. Thus, this research work objects to design an advanced and intelligent dynamic memory allocation mechanism for the real-time embedded systems.

Read more

A High-Performance Infrastructure for Remote Sensing Data Applications Using HPC Paradigms

Individuals and businesses are currently involved in the administration of remote sensing data that was previously handled only by government agencies. There is a lot more information in remote sensing data than go through the eye, and retrieving it is time-consuming and computationally expensive. Clusters, distributed networks, and specialized hardware devices are essential to speeding up remote sensing data extraction calculations. HPC advances in remote sensing applications are examined in this research. High-performance computing (HPC) concepts for instance FPGAs and GPUs as well as large-scale and heterogeneous computer networks are examined (GPUs). Using HPC paradigms, remote sensing applications are examined in these sections.

Read more

Cross Layer Based Dynamic Traffic Scheduling Algorithm for Wireless Multimedia Sensor Network

The data traffic volume is generally huge in multimedia networks since it comprises multimodal sensor nodes also communication takes place with variable capacity during video transmission. The data should be processed in a collision free mode. Therefore, the packets should be scheduled and prioritized dynamically. Dynamic traffic scheduling and optimal routing protocol with cross layer design is proposed here to select the energy efficient nodes and to transmit the scheduled data effectively. At first, the optimal routes are discovered by selecting the best prime nodes then the packets are dynamically scheduled on the basis of severity of data traffic.

Read more

Automatic Framework for Vegetable Classification using Transfer-Learning

Globally, fresh vegetables are a crucial part of our lives and they provide most of the vitamins, minerals, and proteins, in short, every nutrition that a growing body need. They vary in colors like; red, green, and yellow but as our ancestors say that green vegetables are a must for every age. To identify the fresh vegetable that makes our body healthy and notion positive the proposed automatic multi-class vegetable classifier is used. In this paper, a framework based on a deep learning approach has been proposed for multi-class vegetable classification from scratch. The accuracy of the proposed model is further increased using the transfer-learning concept (DenseNet201). The whole process is divided into four modules; data collection and pre-processing, data splitting, CNN model training, and testing, and performance improvement using a pre-trained DenseNet201 network.

Read more