IJISA Vol. 14, No. 6, Dec. 2022
Cover page and Table of Contents: PDF (size: 280KB)
Particularly compared to other diseases, heart disease (HD) claims the lives of the greatest number of people worldwide. Many priceless lives can be saved with the help of early and effective disease identification. Medical tests, an electrocardiogram (ECG) signal, heart sounds, computed tomography (CT) images, etc. can all be used to identify HD. Of all sorts, HD signal recognition from ECG signals is crucial. The ECG samples from the participants were taken into consideration as the necessary inputs for the HD detection model in this study. Many researchers analyzed the risk factors of heart disease and used machine learning or deep learning techniques for the early detection of heart patients. In this paper, we propose a modified version of the LeNet-5 model to be used as a transfer model for cardiovascular disease patients. The modified version is compared to the standard version using four evaluation metrics: accuracy, precision, recall, and F1-score. The achieved results indicated that when the LeNet-5 model was modified by increasing the number of used filters, this increased the model's ability to handle the ECGs dataset and extract the most important features from it. The results also showed that the modified version of the LeNet-5 model based on the ECGs image dataset improved accuracy by 9.14 percentage points compared to the standard LeNet-5 model.[...] Read more.
This study tries to gain insight into the effect of demographic and psychological variables on the Bottom of the Pyramid (BoP) consumers for making Packaging Influenced Purchase (PIP) decisions by focusing on two specific consumer behaviour theories - compensatory consumption and consumers’ resistance. Being the product's face, packaging contributes heavily to the above mentioned two streams of consumption behaviour. A collection of ten demographic variables and four psychological variables have been administered on a sample of 1400 BoP consumers to explore their effect behind making PIP of selected FMCG products. Various classification techniques have been deployed to capture the impact of these variables. This experimental research design revealed that both demographic and psychological variables affect the PIP. The comparison between urban and rural BoPs potentially comes with the guidelines for practical marketing implications.[...] Read more.
Drug interactions prediction is one of the health critical issues in drug producing and use. Proposing computational model for classifying and predicting interactions of drugs with high precision is a difficult problem. Medicines are classified into two classes: overlapping, non-overlapping. It was suggested an expert system for classifying and predicting interactions of drugs using various information about drugs, interference reasons and common factors between patients and active substance that causes interference, such as: effective dose of the drug, maximum dose, times of use per day and age of patients considering that only adult category selected. The proposed model can classify and predict interactions of drugs through patient's state taking into consideration that when changing one of mentioned factors, the effect of drugs will be changed and it may lead to appear new symptoms on the patients. There is a desktop application related with the mentioned model, which helps users to know drugs and drugs families and its interactions. Proposed model will be implemented in Python using following classifiers: Logistic Regression (LR), Support Vector Machine (SVM) and Neural Network (NN), which divided data according to their similarity related to the factors of occurrence of drug interference. As these techniques showed good results, NN technology is considered one of the best techniques in giving results where MLPClassifier achieved superior performance with 97.12%.[...] Read more.
A relatively effective training system and advancements in data science demonstrate their evolutionary algorithm power to discover defects and abnormalities in the specified learning process. This work employs a fast and precise fault modelling environment to enhance genetic input implantable devices defect diagnostics. We offer a genetic data technique that incorporates phylogenetic analysis operations and faulty efficiency analysis. This study contributes to fault training in three different ways: 1) it exposes communicative training categories of information formulating adhesion, 2) it introduces a hierarchical system dissemination processing principles to design the fault aggregative, and 3) it indicates forecasting the genetic data sector that corresponds to complicated fault training. The proposed algorithm analyses methods that combine automatically generated fault detection development with massive data testing by non-repetitive fault instances. Analyzing data from validation challenges, infrastructure blowouts, and failure uncertainty make our algorithm more productive in the health sector.[...] Read more.
Facemask wearing is becoming a norm in our daily lives to curb the spread of Covid-19. Ensuring facemasks are worn correctly is a topic of concern worldwide. It could go beyond manual human control and enforcement, leading to the spread of this deadly virus and many cases globally. The main aim of wearing a facemask is to curtail the spread of the covid-19 virus, but the biggest concern of most deep learning research is about who is wearing the mask or not, and not who is incorrectly wearing the facemask while the main objective of mask wearing is to prevent the spread of the covid-19 virus. This paper compares three state-of-the- art object detection approaches: Haarcascade, Multi-task Cascaded Convolutional Networks (MTCNN), and You Only Look Once version 4 (YOLOv4) to classify who is wearing a mask, who is not wearing a mask, and most importantly, who is incorrectly wearing the mask in a real-time video stream using FPS as a benchmark to select the best model. Yolov4 got about 40 Frame Per Seconds (FPS), outperforming Haarcascade with 16 and MTCNN with 1.4. YOLOv4 was later used to compare the two datasets using Intersection over Union (IoU) and mean Average Precision (mAP) as a comparative measure; dataset2 (balanced dataset) performed better than dataset1 (unbalanced dataset). Yolov4 model on dataset2 mapped and detected images of masks worn incorrectly with one correct class label rather than giving them two label classes with uncertainty in dataset1, this work shows the advantage of having a balanced dataset for accuracy. This work would help decrease human interference in enforcing the COVID-19 face mask rules and create awareness for people who do not comply with the facemask policy of wearing it correctly. Hence, significantly reducing the spread of COVID-19.[...] Read more.