Showing papers by "Velagapudi Ramakrishna Siddhartha Engineering College published in 2021"
TL;DR: An ant colony optimization based QoS aware energy balancing secure routing (QEBSR) algorithm for WSNs is proposed and improved heuristics for calculating the end-to-end delay of transmission and the trust factor of the nodes on the routing path are proposed.
Abstract: Existing routing protocols for wireless sensor networks (WSNs) focus primarily either on energy efficiency, quality of service (QoS), or security issues. However, a more holistic view of WSNs is needed, as many applications require both QoS and security guarantees along with the requirement of prolonging the lifetime of the network. The limited energy capacity of sensor nodes forces a tradeoff to be made between network lifetime, QoS, and security. To address these issues, an ant colony optimization based QoS aware energy balancing secure routing (QEBSR) algorithm for WSNs is proposed in this article. Improved heuristics for calculating the end-to-end delay of transmission and the trust factor of the nodes on the routing path are proposed. The proposed algorithm is compared with two existing algorithms: distributed energy balanced routing and energy efficient routing with node compromised resistance. Simulation results show that the proposed QEBSR algorithm performed comparatively better than the other two algorithms.
77 citations
TL;DR: In this proposed methodology, the Integration of Distributed Autonomous Fashion with Fuzzy If-then Rules (IDAF-FIT) algorithm is proposed for clustering, and also the Cluster Head (CH) is elected in the meanwhile and the routing concept is initiated.
Abstract: In recent years, Wireless Sensor Network (WSN) became a key technology for monitoring and tracking applications in a wide application range. Still, an energy-efficient data gathering protocol has become the most challenging issue. This is because each sensor node in the network is equipped with limited energy resources. To achieve better energy efficiency, better network communication, and minimized delay, clustering is introduced. Therefore, the clustering-based techniques for data gathering play a vital role in terms of energy-saving and increasing the lifetime of the network due to cluster head election and data aggregation. In this proposed methodology, the Integration of Distributed Autonomous Fashion with Fuzzy If-then Rules (IDAF-FIT) algorithm is proposed for clustering, and also the Cluster Head (CH) is elected in the meanwhile. After that, to transmit the packet from source to the destination node by choosing an optimal path, the routing concept is initiated. For this purpose, an Adaptive Source Location Privacy Preservation Technique using Randomized Routes (ASLPP-RR) is presented for routing. Also, Secure Data Aggregation based on Principle Component Analysis (SDA-PCA) algorithm is performed with end-to-end confidentiality and integrity. Finally, the security of confidential data is analyzed properly to obtain a better result than the existing approaches. The overall performance of the proposed methodology when compared with existing is expressed in terms of 20% higher packet delivery ratio, 15% lower packet dropping ratio, 18% higher residual energy, 22% higher network lifetime, and 16% lower energy consumption.
55 citations
01 Jun 2021
TL;DR: An integrated fog and cloud computing framework is introduced to overcome the limitations of real-time analytics, latency and network congestion of basic cloud services for traffic monitoring and the results show the efficiency of the fog network in improving the performance of the cloud platform in terms of reducing the response time and increasing the bandwidth.
Abstract: Internet of Things (IoT) is changing the world by connecting billions of physical and virtual objects with distinctive identities to the Internet. This fusion results in generating huge volumes of data that might not be manageable using today's storage and data analytics technologies. Although cloud computing offers services to tackle this issue at infrastructural level, its efficiency for time sensitive applications (e.g. oil, gas, and traffic monitoring) is still questionable. Arguably, transferring massive amount of data to the cloud for storage and processing may lead to cloud overloading and saturation of network bandwidth. In this study, an integrated fog and cloud computing framework is introduced to overcome the limitations of real-time analytics, latency and network congestion of basic cloud services for traffic monitoring. The proposed approach is implemented to prototype a smart traffic monitoring system (STMS). The proposed monitoring system is designed for congestion monitoring and traffic light management. It can also be tuned to detect traffic incidents that requires immediate assistance during congestion. In this framework, a tiny computer-on-module serves as a fog node to collect real-time data from geographically distributed sensors and to transfer it to the cloud for storage and processing. The results show the efficiency of the fog network in improving the performance of the cloud platform in terms of reducing the response time and increasing the bandwidth. Furthermore, the proposed integrated fog and cloud framework is interfaced with Tweeter to send alerts about traffic congestion to be subscribed users in the form of Tweet messages .
51 citations
TL;DR: A deep learning model is designed by combining the idea of Convolutional Neural Network with Recurrent Neural Network for video saliency detection with improved performance than other state-of-the-art saliency models in terms of increased speed and reduced computational load.
Abstract: Salient object detection is a critical and active field that aims at the detection of objects in a video, however, it draws increased attention among researchers. With increasing dynamic video data, the performance of saliency object detection method has been degrading with conventional object detection methods. The challenges lie with blurry moving targets, rapid movement of objects and background occlusion or dynamic background change on foreground regions in video frames. Such challenges result in poor saliency detection. In this paper, we design a deep learning model to address the issues, which uses a novel framework by combining the idea of Convolutional Neural Network (CNN) with Recurrent Neural Network (RNN) for video saliency detection. The proposed method aims at developing a spatiotemporal model that exploits temporal, spatial and local constraint cues to achieve global optimization. The task of finding the salient objects in benchmark dynamic video datasets is then carried out by capturing the temporal, spatial and local constraint features with the Convolution Recurrent Neural Network (CRNN). The CRNN is evaluated on benchmark datasets against conventional video salient object detection methods in terms of precision, F-measure, mean absolute error (MAE) and computational load. The experiments reveal that the CRNN model achieves improved performance than other state-of-the-art saliency models in terms of increased speed and reduced computational load.
49 citations
TL;DR: In this article, the authors proposed a trust-based multipath routing protocol (TBSMR) to enhance the overall performance of MANETs by considering multiple factors like congestion control, packet loss reduction, malicious node detection, and secure data transmission.
Abstract: Mobile ad hoc network (MANET) is a miscellany of versatile nodes that communicate without any fixed physical framework. MANETs gained popularity due to various notable features like dynamic topology, rapid setup, multihop data transmission, and so on. These prominent features make MANETs suitable for many real-time applications like environmental monitoring, disaster management, and covert and combat operations. Moreover, MANETs can also be integrated with emerging technologies like cloud computing, IoT, and machine learning algorithms to achieve the vision of Industry 4.0. All MANET-based sensitive real-time applications require secure and reliable data transmission that must meet the required QoS. In MANET, achieving secure and energy-efficient data transmission is a challenging task. To accomplish such challenging objectives, it is necessary to design a secure routing protocol that enhances the MANET’s QoS. In this paper, we proposed a trust-based multipath routing protocol called TBSMR to enhance the MANET’s overall performance. The main strength of the proposed protocol is that it considers multiple factors like congestion control, packet loss reduction, malicious node detection, and secure data transmission to intensify the MANET’s QoS. The performance of the proposed protocol is analyzed through the simulation in NS2. Our simulation results justify that the proposed routing protocol exhibits superior performance than the existing approaches.
49 citations
TL;DR: In this paper, a type of convolutional neural network (CNN) was used with transfer learning approach for recognizing diseases in rice leaf images and obtained a good accuracy of 95.67%.
47 citations
TL;DR: A reformed capsule network is developed for the detection and classification of diabetic retinopathy using the convolution and primary capsule layer, the features are extracted from the fundus images and then using the class capsule layer and softmax layer the probability that the image belongs to a specific class is estimated.
Abstract: Nowadays, diabetic retinopathy is a prominent reason for blindness among the people who suffer from diabetes. Early and timely detection of this problem is critical for a good prognosis. An automated system for this purpose contains several phases like identification and classification of lesions in fundus images. Machine learning techniques based on manual extraction of features and automatic extraction of features with convolution neural network have been presented for diabetic retinopathy detection. The recent developments like capsule networks in deep learning and their significant success over traditional machine learning methods for a variety of applications inspired the researchers to apply them for diabetic retinopathy diagnosis. In this paper, a reformed capsule network is developed for the detection and classification of diabetic retinopathy. Using the convolution and primary capsule layer, the features are extracted from the fundus images and then using the class capsule layer and softmax layer the probability that the image belongs to a specific class is estimated. The efficiency of the proposed reformed network is validated concerning four performance measures by considering the Messidor dataset. The constructed capsule network attains an accuracy of 97.98%, 97.65%, 97.65%, and 98.64% on the healthy retina, stage 1, stage 2, and stage 3 fundus images.
46 citations
TL;DR: The authors collect the unstructured research data from a frequently used social media network by using a Twitter application program interface (API) stream and implement different machine classification algorithms like decision trees (DT), neural networks (NN), support vector machines (SVM), naive Bayes (NB), linear regression (LR), and k-nearest neighbor (K-NN) from the collected research data set.
Abstract: In broad, three machine learning classification algorithms are used to discover correlations, hidden patterns, and other useful information from different data sets known as big data. Today, Twitter, Facebook, Instagram, and many other social media networks are used to collect the unstructured data. The conversion of unstructured data into structured data or meaningful information is a very tedious task. The different machine learning classification algorithms are used to convert unstructured data into structured data. In this paper, the authors first collect the unstructured research data from a frequently used social media network (i.e., Twitter) by using a Twitter application program interface (API) stream. Secondly, they implement different machine classification algorithms (supervised, unsupervised, and reinforcement) like decision trees (DT), neural networks (NN), support vector machines (SVM), naive Bayes (NB), linear regression (LR), and k-nearest neighbor (K-NN) from the collected research data set. The comparison of different machine learning classification algorithms is concluded.
36 citations
TL;DR: In this article, recent advancement in high entropy alloy coatings achieved through the laser-assisted cladding process and its wear, erosion, and corrosion behavior were reviewed, and they showed that laser cladding is most beneficial due to many advantages such as high melting solidification rate, narrow heat-affected zone, better metallurgical bonding, optimum dilution, and accurate control over operating parameters of claddings process.
35 citations
TL;DR: Invariant feature concept is added to the existing Darknet Architecture of You Only Look Once (YOLO) and is combined with Faster Region-Based Convolutional Neural Networks (Faster R-CNN) to count the number of vehicles with different spatial locations and improves feature extraction step and vehicle classification process.
Abstract: Object detection and classification is important for video surveillance applications. Counting vehicles like cars, truck and vans is useful for intelligent transportation systems to identify dense and sparse roads, track loaded vehicles at the country borders. Even though many solutions such as appearance-based (Multi-block Local Binary Pattern) and model-based ((DATMO) algorithm) are proposed to classify the moving objects within the satellite images using machine learning and deep learning techniques, they either have over fitting problems or low performance. Hence these challenges have to be addressed during detecting and classifying the objects. Instead of training the classifiers with hand-crafted features, this paper uses neural network based object detection and classification to achieve promising accuracy better than the humans. Invariant feature concept is added to the existing Darknet Architecture of You Only Look Once (YOLO) and is combined with Faster Region-Based Convolutional Neural Networks (Faster R-CNN) to count the number of vehicles with different spatial locations. This combined model improves feature extraction step and vehicle classification process. The proposed system is tested on two benchmark datasets Cars Overhead with Context (COWC) and Vehicle Detection in Aerial Imagery (VEDAI) for counting the cars and trucks. Experimental results prove that the proposed system is better by 9% in detecting smaller objects than existing works.
34 citations
TL;DR: This work proposes a system that observes the crops’ growth and leaf diseases continuously for advising farmers in need and performs comparative analysis between various ML techniques, such as SVM, CNN, naïve Bayes, and $K$ -nearest neighbors.
Abstract: Internet of Things (IoT) in the agriculture field provides crops-oriented data sharing and automatic farming solutions under single network coverage. The components of IoT collect the observable data from different plants at different points. The data gathered through IoT components, such as sensors and cameras, can be used to be manipulated for a better farming-oriented decision-making process. This work proposes a system that observes the crops’ growth and leaf diseases continuously for advising farmers in need. To provide analytical statistics on plant growth and disease patterns, the proposed framework uses machine learning (ML) techniques, such as support vector machine (SVM) and convolutional neural network (CNN). This framework produces efficient crop condition notifications to terminal IoT components which are assisting in irrigation, nutrition planning, and environmental compliance related to the farming lands. In this regard, this work proposes ensemble classification and pattern recognition for crop monitoring system (ECPRC) to identify plant diseases at the early stages. The proposed ECPRC uses ensemble nonlinear SVM (ENSVM) for detecting leaf and crop diseases. In addition, this work performs comparative analysis between various ML techniques, such as SVM, CNN, naive Bayes, and $K$ -nearest neighbors. In this experimental section, the results show that the proposed ECPRC system works optimally compared to the other systems.
TL;DR: An Elfes Sugeno Fuzzy and Trust-based Neural Networks (ESF-TNN) approach enables 3-algorithms that enriches an adequate data storage capacity by considering the average classification ratio while processing regenerated data packets to pertain each interaction information via Trust Mechanism.
TL;DR: In this paper, a stacked ensemble of heterogenous pre-trained computer vision models was proposed for early detection of Coronavirus Disease 2019 (COVID-19) among symptomatic patients.
Abstract: One of the promising methods for early detection of Coronavirus Disease 2019 (COVID-19) among symptomatic patients is to analyze chest Computed Tomography (CT) scans or chest x-rays images of individuals using Deep Learning (DL) techniques. This paper proposes a novel stacked ensemble to detect COVID-19 either from chest CT scans or chest x-ray images of an individual. The proposed model is a stacked ensemble of heterogenous pre-trained computer vision models. Four pre-trained DL models were considered: Visual Geometry Group (VGG 19), Residual Network (ResNet 101), Densely Connected Convolutional Networks (DenseNet 169) and Wide Residual Network (WideResNet 50 2). From each pre-trained model, the potential candidates for base classifiers were obtained by varying the number of additional fully-connected layers. After an exhaustive search, three best-performing diverse models were selected to design a weighted average-based heterogeneous stacked ensemble. Five different chest CT scans and chest x-ray images were used to train and evaluate the proposed model. The performance of the proposed model was compared with two other ensemble models, baseline pre-trained computer vision models and existing models for COVID-19 detection. The proposed model achieved uniformly good performance on five different datasets, consisting of chest CT scans and chest x-rays images. In relevance to COVID-19, as the recall is more important than precision, the trade-offs between recall and precision at different thresholds were explored. Recommended threshold values which yielded a high recall and accuracy were obtained for each dataset.
TL;DR: In this paper, the authors proposed a novel Wilcoxon Signed-Rank Gain Preprocessing combined with Generative Deep Learning (WS-GDL) method for lung cancer disease diagnosis.
Abstract: Cancer is a complicated worldwide health issue with an increasing death rate in recent years. With the swift blooming of the high throughput technology and several machine learning methods that have unfolded in recent years, progress in cancer disease diagnosis has been made based on subset features, providing awareness of the efficient and precise disease diagnosis. Hence, progressive machine learning techniques that can, fortunately, differentiate lung cancer patients from healthy persons are of great concern. This paper proposes a novel Wilcoxon Signed-Rank Gain Preprocessing combined with Generative Deep Learning called Wilcoxon Signed Generative Deep Learning (WS-GDL) method for lung cancer disease diagnosis. Firstly, test significance analysis and information gain eliminate redundant and irrelevant attributes and extract many informative and significant attributes. Then, using a generator function, the Generative Deep Learning method is used to learn the deep features. Finally, a minimax game (i.e., minimizing error with maximum accuracy) is proposed to diagnose the disease. Numerical experiments on the Thoracic Surgery Data Set are used to test the WS-GDL method's disease diagnosis performance. The WS-GDL approach may create relevant and significant attributes and adaptively diagnose the disease by selecting optimal learning model parameters. Quantitative experimental results show that the WS-GDL method achieves better diagnosis performance and higher computing efficiency in computational time, computational complexity, and false-positive rate compared to state-of-the-art approaches.
TL;DR: In this article, the impact of lockdown on air quality has been studied and it is observed that the air pollutant concentration has reduced in every city of the world during the lockdown period and the PM2.5 and PM10 are the most affecting air concentrator which controlled the air quality of all the selected places during and after lockdown.
Abstract: The COVID-19 pandemic has significantly affected economic activities all around the world. Though it took a huge amount of human breathes as well as increases unemployment, it puts a positive impression on the environment. To stop the speedy extend of this disease, the maximum Government has imposed a strict lockdown on their citizens which creates a constructive impact on the atmosphere. Air pollutant concentration has been investigated in this study to analyze the impact of lockdown on the environment. Based on the air pollutant concentration, Air Quality Index (AQI) is deliberated. The Air Quality Index indicates the most and least polluted cities in the world. A higher value of AQI represents the higher polluted city and a lesser value of Air Quality Index represents a less polluted city. The impact of lockdown on air quality has been studied in this work and it is observed that the air pollutant concentration has reduced in every city of the world during the lockdown period. It has been also detected that the PM2.5 and PM10 are the most affecting air concentrator which controls the air quality of all the selected places during and after lockdown.
23 Aug 2021
TL;DR: In this paper, a machine learning (ML)-based approach is proposed to identify malicious users from URL data, an ML model is implemented using Logistic Regression to detect malicious URLs and the proposed framework is further evaluated against traditional malicious URL models and the results highlight positive steps forward of the proposed approach.
Abstract: One of the major challenges faced by the Internet in the present day is to deal with achieving web security from ever-rising diverse types of threats. Machine learning algorithms offer promising techniques to detect malicious websites performing unethical anonymous activities on the Internet. Attackers have been found to continuously evolve with updated techniques to attack web users using malicious Uniform Resource Locators (URLs). The main objective of such attacks is to gain financial benefits through acquiring personal information. In the present research, a machine learning (ML)-based approach is proposed to identify malicious users from URL data. An ML model is implemented using Logistic Regression to detect malicious URLs. The data set used in the study is collected from well-known sources like PhishTank, Kaggle.com, and Github.com. Our novel framework is further evaluated against traditional malicious URL models and our results highlight positive steps forward of the proposed approach.
TL;DR: The blockchain-defined networks with a grey wolf optimized modular neural network approach for managing the smart environment security is introduced, in which system ensures low latency, high security, compared to the multi-layer perceptron, and deep learning networks.
Abstract: Nowadays, next-generation networks such as the Internet of Things (IoT) and 6G are played a vital role in providing an intelligent environment. The development of technologies helps to create smart city applications like the healthcare system, smart industry, and smart water plan, etc. Any user accesses the developed applications; at the time, security, privacy, and confidentiality arechallenging to manage. So, this paper introduces the blockchain-defined networks with a grey wolf optimized modular neural network approach for managing the smart environment security. During this process, construction, translation, and application layers are created, in which user authenticated based blocks are designed to handle the security and privacy property. Then the optimized neural network is applied to maintain the latency and computational resource utilization in IoT enabled smart applications. Then the efficiency of the system is evaluated using simulation results, in which system ensures low latency, high security (99.12%) compared to the multi-layer perceptron, and deep learning networks.
TL;DR: In this article, a 2D-Ion Sensitive Field Effect Transistors (ISFET) pH sensor in two dimensions with integration of two models namely, semiconductor model and electrolyte model are represented using manageable global equations.
Abstract: Ion Sensitive Field Effect Transistors (ISFET) are most widely used in medical applications due to simple integration process, measurement of sensitivity and its dual properties. These ISFETs are originated from Metal Oxide Semiconductor Field Effect Transistors (MOSFET) with improvements in structure. ISFETs are used as bio-sensors for the detection of biomarkers in blood, DNA replication and several other medical applications. In this article, we design the ISFET pH sensor in two dimensions with integration of two models namely, semiconductor model and electrolyte model are represented using manageable global equations. The sensitivity of ISFET with different oxide layers is measured and compared. We also measure the sensitivity of the designed 2D-ISFET in two different solutions and compare it with different oxides to know the best oxide material to be used to design the device.
TL;DR: In this article, an ultrasensitive label free electrical device, the silicon nanowire field effect transistor (SiNW FET), was designed, simulated using COMSOL semiconductor module to identify the presence of different concentrations of cTnI present in human blood.
Abstract: This study evolves an ultrasensitive label free electrical device, the silicon nanowire field effect transistor (SiNW FET) for cardiac troponin I (cTnI) in acute myocardial infarction (AMI). In this work, SiNW FET is designed, simulated using COMSOL semiconductor module to identify the presence of different concentrations of cTnI present in human blood. The surface of the SiNW is functionalized with the cTnI monoclonal antibody (mAb-cTnI) on attached to detect cTnI antigen. The response of the device is also studied using cTnI at different concentrations with the lowest limit of detection of 0.002 ng/mL. The presented SiNW FET in this study shows considerable response than the earlier developed devices and signify impressive capability for subsequent implementation in point-of-care (PoC) detection.
17 Aug 2021
TL;DR: In this paper, the authors proposed a framework to detect malicious links on the web using a machine learning classification technique that would help users defend against cyber-crime attacks and related threats of the real world.
Abstract: Malicious websites predominantly promote the growth of criminal activities over the Internet restraining the development of web services. Furthermore, we see different types of devices being equipped with WiFi capabilities, that allow web traffic to pass through the device’s data systems with ease. The proposed framework in the present study analyzes the Uniform Resource Locator (URL) through which malicious users can gain access to the content of the websites. It thus eliminates issues of run-time latency and possibilities of users being subjected to browser oriented vulnerabilities. The primary objective of this paper is to detect malicious links on the web using a machine learning classification technique that would help users defend against cyber-crime attacks and related threats of the real world. This may be helpful in the newly expanding Intelligent Infrastructures, where we see more data availability almost daily. The embedding of malicious URLs is a predominant web threat faced by the Internet community in the present day and age. Attackers falsely claim of being a trustworthy entity and lure users to click on compromised links to extract confidential information, victimizing them towards identity theft. The present work explores the various ways of detecting malicious links from the host-based and lexical features of the URL in order to protect users from being subjected to identity theft attacks.
TL;DR: In this article, the authors proposed a novel stacked ensemble capable of detecting COVID-19 from a patient's chest CT scans with high recall and accuracy, using transfer learning (TL) to design a stacked ensemble from pre-trained computer vision models.
TL;DR: A fuzzy based MIP and Graph theory based Traffic Estimator are proposed system used to define New asymmetric multiprocessor heterogene framework on microprocessor (AHt-MPSoC) architecture and the bandwidths, energy consumption, wait and transmission range are better accomplished in this suggested technique than the standard technique.
Abstract: This Ensuing generation of FPGA circuit tolerates the combination of lot of hard and soft cores as well as devoted accelerators on a chip. The Heterogene Multi-Processor System-on-Chip (Ht-MPSoC) architecture accomplishes the requirement of modern applications. A compound System on Chip (SoC) system designed for single FPGA chip, and that considered for the performance/power consumption ratio. In the existing method, a FPGA based Mixed Integer Programming (MIP) model used to define the Ht-MPSoC configuration by taking into consideration the sharing hardware accelerator between the cores. However, here, the sharing method differs from one processor to another based on FPGA architecture. Hence, high number of hardware resources on a single FPGA chip with low latency and power targeted. For this reason, a fuzzy based MIP and Graph theory based Traffic Estimator (GTE) are proposed system used to define New asymmetric multiprocessor heterogene framework on microprocessor (AHt-MPSoC) architecture. The bandwidths, energy consumption, wait and transmission range are better accomplished in this suggested technique than the standard technique and it is also implemented with a multi-task framework. The new Fuzzy control-based AHt-MPSoC analysis proves significant improvement of 14.7 percent in available bandwidth and 89.8 percent of energy minimized to various traffic scenarios as compared to conventional method.
TL;DR: In this article, the phase evaluation and surface morphological features of prepared nanoparticles were examined using XRD and FE-SEM analysis and the average crystallite size ( DXRD >) was estimated and found to be 25.1 nm for cow urine and 29.9 nm for honey-assisted nanomaterials.
Abstract: Novel properties of green synthesis methods have paved the way for a new area of study in the scientific community. Systematic research was carried out in the current study for Ag-doped ZnO nanostructures prepared using cow urine and honey. The phase evaluation and surface morphological features of prepared nanoparticles were examined using XRD and FE-SEM analysis. From the XRD analysis, the average crystallite size ( DXRD >) was estimated and found to be 25.1 nm for cow urine and 29.9 nm for honey-assisted nanomaterial . FE-SEM confirms the presence of plate-like and spherical nanoparticles in the synthesized sample. Compositional analysis of Zn, Ag, and O from EDX spectra showed the reliability of present green synthesis. The thermal analysis of the nanostructures of Ag-ZnO has been investigated and the effect of these natural ingredients on thermal stability has also been analyzed. Antimicrobial activities were tested against two human pathogenic bacteria and their comparative results are presented.
TL;DR: In this article, the authors proposed a novel "Teeth Junctionless Gate All Around Field Effect Transistor" (TH-JLGAA FET) based on gate engineering method, to obtain finer electrical characteristics.
Abstract: In this paper, we propose a novel “Teeth Junctionless Gate All Around Field Effect Transistor” (TH-JLGAA FET) based on gate engineering method, to obtain finer electrical characteristics. A 3 nm TH-JLGAA FET is designed and was scaled up to 14 nm to observe the effect of scaling on device performance. The characteristics are revealed and compared with contemporary JLGAA FETs. The results show that the novel TH-JLGAA FET appears to have finer Sub-thresholdSlope (SS), Drain Induced Barrier Lowering (DIBL), transconductance (gm), Ion/Ioff current ratio and threshold voltage roll-off. Moreover, these remarkable characteristics can be controlled by engineering the structure and volume of the gate. In addition, the sensitivities of the novel TH-JLGAA FET device with respect to structural parameters are probed.
04 Feb 2021
TL;DR: In this article, a machine learning model for heart disease prediction was proposed and the proposed method was tested on two different datasets from Kaggle and UCI and achieved good accuracy with ensemble classifier.
Abstract: Cardiovascular diseases (heart-related diseases) are the reason for the deaths of 18 million people every year in the world. According to WHO,31% of the deaths worldwide are due to heart-related diseases. In this paper, we proposed a novel machine learning model for heart disease prediction. The proposed method was tested on two different datasets from Kaggle and UCI. We applied sampling techniques to the unbalanced dataset and feature selection techniques are used to find the best features. Later several classifier models were applied and achieved good accuracy with ensemble classifier. The experimentations on two datasets shown that the proposed model is effective for heart disease prediction. Python was used for all implementations.
TL;DR: In this paper, the experimental results of engineering properties obtained from GGBS stabilised black cotton soil (BCS) is presented in this paper, and the research was carried out using 0% to 50% GGBS content with 3M to 11m NaOH solution.
TL;DR: The usability of artificial intelligence is discussed, the implementation of AI and IoT analytics are systematically examined as a way of enhancing the health system in the IoT model and different AI-based and device algorithms are also explored.
Abstract: Artificial intelligence is intelligence revealed by software, as opposed to natural intelligence. It is the science and technology of intelligent machinery. It is also a technology that functions like people on the computer. The IoT Internet of Things is a web-based object network that can communicate and share data. AI and IoT are combined to achieve a more effective IoT process, namely AIoT, combined with the Internet and artificial intelligence. Recently, an efficient health care system was introduced with artificial intelligence (AI) and IoT research. In this paper, the usability of artificial intelligence is discussed, and the implementation of AI and IoT analytics are systematically examined as a way of enhancing the health system in the IoT model. Different AI-based and device algorithms are also explored. Edge Computing is a modern computer technology in which data are processed from the edge. Simulation result shows the accuracy, precision and specificity of decision tree approach than SVM and Naive Bayes. It offers lower bandwidth costs, more robust privacy and data security than cloud computing. Notably, advanced computing is easily used by artificial intelligence technologies.
TL;DR: An algorithm to the diagnosis of LVH using ECG signal based on machine learning techniques were designed and revealed that the proposed work can diagnose LVH successfully using neural network classifiers.
Abstract: This work proposes a novel method for the detection of Left Ventricular Hypertrophy (LVH) from a multi-lead ECG signal. Left Ventricle walls become thick due to prolonged hypertension which may fail to pump heart effectively. The imaging techniques can be used as an alternative diagnose LVH; however, they are more expensive and time-consuming than proposed LVH. To overcome this issue, an algorithm to the diagnosis of LVH using ECG signal based on machine learning techniques were designed. In LVH detection, the pathological attributes such as R wave, S wave, inversion of QRS complex, changes in ST segment noticed in the ECG signal. This clinical information extracted as a feature by applying continuous wavelet transform. The signals were reconstructed with the frequency between 10 and 50 Hz from the wavelet. This followed by the detection of R wave and S wave peaks to obtain the relevant LVH diagnostic features. The Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Ensemble of Bagged Tree, AdaBoost classifiers were employed and the results are compared with four neural network classifiers including Multilayer Perceptron (MLP), Scaled Conjugate Gradient Backpropagation Neural Network (SCG NN), Levenberg–Marquardt Neural Network (LMNN) and Resilient Backpropagation Neural network (RPROP). The data source includes Left Ventricular Hypertrophy and healthy ECG signal from PTB diagnostic ECG database and St Petersburg INCART 12-Lead Arrhythmia Database. The results revealed that the proposed work can diagnose LVH successfully using neural network classifiers. The accuracy in detecting LVH is 86.6%, 84.4%, 93.3%,75.6%, 95.6%, 97.8%, 97.8%, 88.9% using SVM, KNN, Ensemble of Bagged Tree, AdaBoost, MLP, SCG NN, LMNN and RPROP classifiers, respectively.
27 Aug 2021
TL;DR: In this paper, a smart door unlock system using face recognition is proposed, which consists of a camera sensor known as esp32-camera for storing the pictures of persons and for live streaming.
Abstract: The rapid growth of technology in the modern society has raised many questions on the terms like security and privacy. Due to the evolution in the technology and industrialization the terms like security and privacy has become imperative for a common person. Authentication is a key factor which helps for the identification of authorized people and helps in eradicating fraudulent activities, robberies, and many other social crimes. Most of the crimes are due to the vulnerabilities in the door locking systems which can be easily accessible by the outsiders. Though there are solutions like smart doorbells and video streaming, which have limitations like heavy cost, complex and have loopholes in the security issues. To diminish the limitations and to enhance the security Smart door unlock systems using face recognition is proposed. The proposed system consists of a camera sensor popularly known as esp32-cam for storing the pictures of persons and for live streaming. The proposed system recognizes the face of the person standing in front of the door with the help AI-Thinker in the esp32-cam. The face of the person is compared with the faces of the authorized persons which are stored in the SD card of esp32-cam. If the person is an authorized person then the door gets unlocked which can be achieved with the hardware component solenoid lock. If the person is an unauthorized person then the door will be locked. The proposed system helps in adapting from traditional mechanical lock methods to enhanced security methods. It also helps in case of losing keys and helpful for disabled persons with easier access.