Smart Wheelchair-An Effective Transport for Handicapped and Aged Citizens

R.; Gokul Santhosh; Sathya Preiya; V. D. Ashok

doi:https://doi.org/10.54216/JCHCI.040201

Journal of Artificial Intelligence and Metaheuristics | 2022

Evaluating the Effect of Optimized Voting Using Hybrid Particle Swarm and Grey Wolf Algorithm on the Classification of the Zoo Dataset

When there are numerous possible solutions for a given class in a given problem, majority voting or plurality voting is typically employed. One common technique for improving classification accuracy is bagging, which involves training many classifiers on slightly different datasets and then voting on the combined results. In this research, we examine how alternative voting procedures affect the efficiency of two distinct classification algorithms applied to datasets of varying complexity. Despite the increased computing cost associated with determining preference order, the results show that the single transferable vote can be a suitable alternative to plurality voting.

groups

Doaa S. Khafaga mail -

Hussein Alkattan mail -

Alhumaima A. Subhi mail

link https://doi.org/10.54216/JAIM.020101

Volume & Issue

Vol. Volume 2 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2022

Intelligent Wheat Types Classification Model Using New Voting Classifier

When assessing the quality of the grain supply chain's quality, it is essential to identify and authenticate wheat types, as this is where the process begins with the examination of seeds. Manual inspection by eye is used for both grain identification and confirmation. High-speed, low-effort options became available thanks to automatic classification methods based on machine learning and computer vision. To this day, classifying at the varietal level is still challenging. Classification of wheat seeds was performed using machine learning techniques in this work. Wheat area, wheat perimeter, compactness, kernel length, kernel width, asymmetry coefficient, and kernel groove length are the 7 physical parameters used to categorize the seeds. The dataset includes 210 separate instances of wheat kernels, and was compiled from the UCI library. The 70 components of the dataset were selected randomly and included wheat kernels from three different varieties: Kama, Rosa, and Canadian. In the first stage, we use single machine learning models for classification, including multilayer neural networks, decision trees, and support vector machines. Each algorithm's output is measured against that of the machine learning ensemble method, which is optimized using the whale optimization and stochastic fractal search algorithms. In the end, the findings show that the proposed optimized ensemble is achieving promising results when compared to single machine learning models.

groups

Abdelaziz A. Abdelhamid mail -

El-Sayed M. El-Kenawy mail -

Abdelhameed Ibrahim mail -

Marwa M. Eid mail

link https://doi.org/10.54216/JISIoT.070103

Volume & Issue

Vol. Volume 7 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2022

Detection and Classification of Malware Using Guided Whale Optimization Algorithm for Voting Ensemble

Malware is software that is designed to cause damage to computer systems. Locating malicious software is a crucial task in the cybersecurity industry. Malware authors and security experts are locked in a never-ending conflict. In order to combat modern malware, which often exhibits polymorphic behavior and a wide range of characteristics, novel countermeasures have had to be created. Here, we present a hybrid learning approach to malware detection and classification. In this scenario, we have merged the machine learning techniques of Random Forest and K-Nearest Neighbor Classifier to develop a hybrid learning model. We used current malware and an updated dataset of 10,000 examples of malicious and benign files, with 78 feature values and 6 different malware classes to deal with. We compared the model's results with those of current approaches after training it for both binary and multi-class classification. The suggested methodology may be utilized to create an anti-malware application that is capable of detecting malware on newly collected data.

groups

Marwa M. Eid mail -

M. I. Fath Allah mail

link https://doi.org/10.54216/JCIM.100102

Volume & Issue

Vol. Volume 10 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2021

Blockchain Communication Platform Selection in IoT Healthcare Industry using MARCOS

The Internet of Things (IoT) healthcare industry is under tremendous pressure to simplify its secure data communication processes. Patients are beginning to consider healthcare services, such as those relating to wellness promotion, illness prevention, diagnosis, care, and recovery, as ongoing cycles. With the prevalence of chronic illnesses on the rise and public perceptions of healthcare shifting, many people increasingly see modern health services as ongoing commitments. Using data provided through the most cutting-edge technology, efficient healthcare systems should reliably provide all their patients with access to the high-quality, comprehensive medical treatment they can afford. So, this study presents a neutrosophic multicriteria decision-making (MCDM) model to optimize the selection of blockchain communication platforms in IoT healthcare applications. To identify the best blockchain platform for use in healthcare, the Measurement of Alternatives and Ranking according to the Compromise Solution (MARCOS) technique was created. The proposed model improves the efficiency, accuracy, and reliability for better Blockchain secure communication in the IoT healthcare industry.  

groups

Mahmoud Zaher mail -

Nashaat EL-Khameesy ElGhitany mail

link https://doi.org/10.54216/IJWAC.020104

Volume & Issue

Vol. Volume 2 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2021

Reliable Data Communication Model for Fog Computing

To maintain data privacy and control who has access to what in the cloud, attribute-based encryption might be utilized. Attribute security is violated when apparent qualities are introduced to the encrypted message to assist people to identify necessary details in vast systems. To offer an effective attribute-based access control with an authorized search strategy, this research expands the anonymous key-policy attribute-based encryption (AKP-ABE) to provide fine-grained data retrieval while safeguarding attribute privacy (EACAS). In EACAS, data users may generate the trapdoor using the secret key supplied by data owners and conduct searches based on access restrictions to get the relevant data. Cryptographic protocols and trapdoor generation use a synthetic property devoid of syntactic significance to provide an attribute-based search on the exported encoded information in the fog. Data owners may implement granular access control on their outsourced data by establishing the search criteria that will be used by data consumers to locate relevant content based on protected attributes. We show that compared to the state-of-the-art methods, EACAS requires less time and space to process and store data. 

groups

Reem Atassi mail -

Aditi Sharma mail

link https://doi.org/10.54216/IJWAC.020202

Volume & Issue

Vol. Volume 2 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2022

An Edge Intelligence Framework for Elegant Power Management in IoT-enabled Power Grids

The Internet of Things (IoT) is a concept that has the potential to attract new audiences in fields as diverse as manufacturing, healthcare, and more. IoT devices included into the sensor were the primary drivers of the massive data collection. To successfully combine, assess, and comprehend all programme objects, thus, self-adaptive algorithms based on AI are necessary. The proliferation of both massive datasets and resource-intensive IoT devices makes stringent power management essential. The proliferation of both massive datasets and resource-intensive Internet of Things devices makes stringent energy management essential. Combining IoT with AI-based techniques is crucial for equitable power distribution to compact mobile devices. To this end, we offer an efficient way to communicate between power utilities and end users by forecasting future power usage over short periods of time. Innovations include a revolutionary convolutional recurrent model for lightweight prediction method with low duration intricacy and minimum margins of error, as well as massive energy administration for edge devices via a centralised cloud-based data supervisory server. To maintain the power consumption and supply paradox efficiently, the suggested scheme has mobile nodes interact with a central remote server via an IoT network and then on to the corresponding power grid. We use a number of preparation methods to accommodate the varied electrical data, and then we construct a powerful decision-making engine for quick prediction on devices with limited resources.

groups

Irina V. Pustokhina mail -

Denis A. Pustokhin mail

link https://doi.org/10.54216/JISIoT.060204

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2022

Federated Resistance Against Adversarial Attacks in Resource-constrained IoT

  Federated learning (FL) is a recently evolved distributed learning paradigm that gains increased research attention. To alleviate privacy concerns, FL fundamentally suggests that many entities can cooperatively train the machine/deep learning model by exchanging the learning parameters instead of raw data. Nevertheless, FL still exhibits inherent privacy problems caused by exposing the users’ data based on the training gradients. Besides, the unnoticeable adjustments on inputs done by adversarial attacks pose a critical security threat leading to damaging consequences on FL.  To tackle this problem, this study proposes an innovative Federated Deep Resistance (FDR) framework, to provide collaborative resistance against adversarial attacks from various sources in a Fog-assisted IIoT environment. The FDR is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures that contributors have no access to the data of each other, where class probabilities are protected utilizing a private identifier generated for each class.  The FDR mainly emphasizes convolutional networks for image recognition from the Food-101 and CIFAR-100 datasets. The empirical results have revealed that FDR outperformed the state-of-the-art adversarial attacks resistance approaches with 5% of accuracy improvements.

groups

Mahmoud A. Zaher mail -

Heba H. Aly mail

link https://doi.org/10.54216/JISIoT.060205

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2022

Automated System for Management of Exam Cell

These days, exam cell migration typically includes some manual computations and is primarily dependent on pen and paper.  The main objective of this extension is to bring it in a centralised manner.  By doing so, it will be possible to successfully supervise the actions taking place throughout an examination.  By entering their enrollment number, title, phone number, email address, semester, etc., the framework enables college or school students to register themselves with the system.  Typically accomplished by having students create their own unique points of interest for the exam cell to use as their login ID and password.

groups

Ajith R. mail -

Mercy Beullah mail

link https://doi.org/10.54216/JCHCI.040104

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2022

Accident Detection System Using GPS and GSM by IOT

The primary goal of accident detection implementation is to reduce traffic accidents that result in the loss of priceless human life and other valuable items. Accident detection systems that use GPS and GSM save lives by shortening the time it takes for emergency personnel to reach the scene of an accident. We made the decision to recognise an automobile collision and notify the emergency personnel as well as the driver's main contacts. The product's main goal was to increase security for consumers and their families. GPS (Global Positioning System) and GSM are its foundations (Global system of Mobile communication).

groups

R. Manish mail -

M. Sumithra mail -

Lokhitha D. mail -

Mahalakshmi L. mail -

Durga V. mail -

Nirmala G. mail

link https://doi.org/10.54216/JCHCI.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Cognitive Human-Computer Interaction | 2022

Smart Wheelchair-An Effective Transport for Handicapped and Aged Citizens

A wheelchair is a chair fitted with wheels. A survey says that around 132 million people use wheelchair around the world. But majority of them are dependent on others for their movements, especially people with some disorders. This dependent nature had hindered them from succeeding. To overcome this problem, they can use smart wheelchair, which is auto movable based on head tilt movements. It collects information from the patient through in built sensors and enhances the seating position. It is also designed with obstacle and fall detection system which reduces the chance of collision during their journey. This makes a physically challenged or dependent person as physically independent person. This wheelchair can also be used by aged people who lack motor skills. In this paper, we can review the art of smart wheelchair and the features of it.

groups

R. Venkatesan mail -

Gokul Santhosh Y. mail -

Sathya Preiya V. mail -

V. D. Ashok Kumar mail

link https://doi.org/10.54216/JCHCI.040201

Volume & Issue

Vol. Volume 4 / Iss. Issue 2

Details open_in_new