Journal of Intelligent Systems and Internet of Things

Journal DOI

Submit Your Paper

2690-6791ISSN (Online) 2769-786XISSN (Print)

Autism Spectrum Diagnosis using Adaptive Learning Algorithm for Multiple MLP Classifier

Fatemeh Safara

A medical condition that causes disability and early neurological and cognitive condition is autism spectrum disorder (ASD). Gene expression and environment have an impact on this medical condition. Development of diagnostic instruments and skills improved the autism recognition and increased the society awareness about it. To cope with this disorder collaboration between families, service providers, and autistic individuals is a necessity. Early diagnosis of ASD could help in lessening stress, increase adaptation, and support welfare in healthcare systems. Therefore, a large body of research is attempting to provide an intelligent medical diagnostic system to identify and diagnose ASD in early stages using machine learning methods. In this paper, several multilayer perceptron neural network is proposed for ASD detection in healthcare systems. The learning rate is adaptively tuned to achieve the best results. The results show that the approach proposed in this study achieved 99.6% accuracy, which indicates the superiority of the proposed method in identifying and detecting autism disorder in comparison with similar previous methods.

Read More


Vol. 2 Issue. 2 PP. 33-44, (2021)

ECG signal monitoring based on Covid-19 patients: Overview

Amine Saddik *, Rachid Latif and Abdoullah Bella

  ECG signal monitoring is a very important step for patients. Especially for those infected by covid-19. This pandemic has shown that the use of artificial intelligence helps to control the propagation of this virus. Particularly the high spread of this virus influences the number of the infected population. As well as the fact that this virus attacks the respiratory system which influences the cardiac system. Therefore, an ECG signal monitoring is mandatory. Our work presents an overview based on various approaches developed for ECG signal monitoring. These techniques are based on non-contact monitoring approaches. These approaches will help to avoid frequent contact with patients and doctors. As well as non-contact ECG signal monitoring is based on low-cost techniques, which reduces the price compared to other sensors. After the revision, we can conclude that the most suitable solution for heart rate monitoring is based on image processing using RGB cameras. These solutions are accurate, low cost, and protect the doctors.

Read More


Vol. 2 Issue. 2 PP. 45-54, (2021)

Solving the Problem of Target k-Coverage in WSNs Using Fuzzy Clustering Algorithm

Mohammad Hossein Shafiabadi , Zohre Ahmadi , Mohammad Reza Esfandyari

The purpose of the present research was to introduce an algorithm to solve the coverage problem in wireless multimedia networks that can be used to optimize energy consumption and network lifetime. In this regard, the problem of target k-coverage in WSNs was solved by dividing the environment into the proportional area and random selection. This can be done using a fuzzy clustering algorithm. It is worth noting that the results of the proposed algorithm were compared with previous methods such as genetic and annealing algorithm. The simulation results and comparison with other algorithms show a 27% superiority of the proposed algorithm. It is hoped that this method can be used in networks with larger dimensions in the future

Read More


Vol. 2 Issue. 2 PP. 55-76, (2021)

Smart Irrigation System with Predictive Analytics using Machine Learning and IoT

Ahmed Sleem , Ibrahim Elhenawy

Water scarcity is a significant issue in agriculture, making efficient irrigation practices crucial for sustainable farming.  Integration of Internet of Things (IoT) and machine learning technologies are becoming of great importance to improve irrigation efficiency and reduce water usage. In this paper, we propose an intelligent irrigation system that take the advantage of IoT to improve the predictive analytics of groundwater levels. Our system used a deep learning to estimate the groundwater level using convolutional recurrent model that analyzed the sensory measurements necessary to predict groundwater levels. The model is trained on a large dataset of time series records and corresponding groundwater levels, allowing it to learn the complex patterns and relationships between time series features and groundwater levels. The experimental predictive analytics provided accurate irrigation recommendations, and the remote monitoring capabilities allowed farmers to adjust the irrigation schedule as needed.

Read More


Vol. 2 Issue. 2 PP. 77-83, (2021)