Journal of Computational Science and Data Analytics

Message from the Editor-in-Chief

Surafel L Tilahun — Thu, 10 Oct 2024 00:00:00 +0000

A note from the editor-in-chief regarding the journal's launch and release of its first issue.

Identification Of Injera Mixture Using Computer Vision And Machine Learning Approach

Kibkab Setegn Alehegn, Abrham Debasu Mengistu — Thu, 10 Oct 2024 00:00:00 +0000

Injera is a culturally significant food in Ethiopia, and the majority of the population consumes it daily. It is usually made from teff flour and different variations can include barley, corn, rice, sorghum, wheat, or a combination of these flours. However, the adulteration of Injera with harmful substances poses significant problems. When bad ingredients are mixed with teff flour or other flour, it can lead to health issues for consumers, loss of cultural identity as the traditional preparation and authenticity of Injera, and it creates challenges in marketing and promoting genuine Injera, as consumers may become wary of purchasing products that are not guaranteed to be pure and safe. Addressing these problems is crucial to ensure the preservation of cultural heritage, protect public health, and maintain the integrity of the Injera market. Identification of Injera is difficult using the naked eye due to their similar features. In recent years, machine learning and deep learning algorithms have demonstrated impressive potential in image identification. This paper proposes a hybrid approach based on the best feature extraction algorithm to classify injera mixtures. Using traditional fermentation techniques, we prepared datasets consisting of Injera samples with various combinational ratios including 10:90 and 20:80 ratios. We captured hot Injera before 1 hour and cold Injera after 24 hours. In this study, we have used Grey Level Co-occurrence Matrix (GLCM), Convolutional Neural Network (CNN), and a combination of GLCM and CNN as a feature extraction technique. Also, we have used a Support Vector Machine (SVM) and Random Forest (RF) as a classifier to design the Injera mixture identification system. We have examined different combination ratios of hot and cold (after 24 hours) frontside and backside Injera. From the experimental results, we have registered an accuracy of a combinational ratio of 10:90 frontside hot Injera, 10:90 backside hot Injera, 10:90 frontside cold Injera, 10:90 backside cold Injera, 20:80 frontside hot Injera, 20:80 backside hot Injera, 20:80 frontside cold Injera, 20:80 backside cold Injera is 87%, 86%, 93%, 92%, 91%, 95%, 98%, and 98% for SVM and 88%, 87%, 91%, 91%, 93%, 94%, 98%, and 98% for RF respectively on combined features.

Feature Selection Methods for ICU Mortality Prediction Model

Girma Neshir Alemneh, Hirut Bekele Ashagrie, Lemlem Kassa — Mon, 07 Oct 2024 00:00:00 +0000

The goal of this research is to offer insightful information that can improve Ethiopia's intensive care unit (ICU) services. There is an increased risk of patients' death in Intensive Care Units (ICUs). This is because of several variables, including preexisting medical issues, lack of resources, and delayed decisions. Healthcare professionals can better prioritize their patients in need of intensive care, distribute resources more efficiently, and enhance patient outcomes by using predictive models to estimate ICU mortality. ICU data is collected from five Ethiopian public hospitals to develop a machine learning method for predicting ICU mortality. The data includes demographic features, vital signs, lab results, and discharge status of 10,798 ICU dataset records. We employed a range of feature selection techniques, such as filters, wrappers, and embedding methods, to identify the most crucial features for mortality prediction. We also compared the performance of two machine learning algorithms, Random Forest and Decision Tree. These models are trained using ICU data with features encompassing age, length of stay, temperature, neutrophil, Diagnosis (DX) condition, PH, and Lymphocite. These features are selected using Recursive Feature Elimination (RFE). Using a number of different evaluation methods, including accuracy (99.7%), precision (99.4%), recall (98.8%), F1 score (99.1%), and area under the curve (AUC) (99.3%), Random Forest performed better than Decision Tree. Based on our findings, we made recommendations for healthcare practitioners and policy makers. We also suggest key future research directions for researchers in the area.

Coverage and Performance Evaluation of Multibeam Stratospheric Platforms Wireless Broadband Services

Habib Mohammed — Thu, 10 Oct 2024 00:00:00 +0000

In this paper, the radiation pattern of 121 cell aperture antenna for a High-Altitude Platform (HAP) communication network via TV White Space (TVWS) spectrum is investigated. The HAP was placed 17 km above the ground with a coverage radius of 100 km and a cell radius of 10.5 km. For a co-channel cell group of 121 cells served by a payload of aperture antennas on a HAP, the effect of the antenna aperture function on co-channel interference has been explored. For each cell, the required antenna beam widths were derived from the cell’s subtended angles. The proposed system coverage, re-use distance, multibeam antenna pattern, Carrier-to-interference ratio (CIR), Carrier-to-interference-plus-noise-ratio (CINR), and side lobe level values for uniform apertures were investigated. To assess the system’s effectiveness, the CIR at each ground location (x, y) and the cumulative distribution function (CDF) of CINR were investigated for each co-channel cell category. The distribution of CIR levels as contour plots has been presented. The
CIR values are higher at cell centers and lower at cell edges. Furthermore, the importance of minimizing the average side lobe level has been investigated. This paper demonstrated that it is possible to get a good wireless broadband performance by exploiting TVWS spectrums from HAP.

Enhancing Mobility and Safety: A Smart Walking Cane for Visually Impaired Individuals with Ultrasonic Sensor, Infrared, and GSM Module

Anteneh Tesfaye — Thu, 10 Oct 2024 00:00:00 +0000

Traditionally, visually impaired individuals have relied on conventional walking canes to detect obstacles in their path. However, these canes have limitations in terms of efficiency. This paper focuses on the design and implementation of an electronic travel aid for visually impaired pedestrians, utilizing ultrasonic sensors, infrared technology, and a GSM module. The smart cane integrates ultrasonic sensors and IR technology to detect obstacles using ultrasonic waves and IR signals. When obstacles are detected, the sensor relays this information to a microcontroller (Atmega328P). The microcontroller processes the data and determines the proximity of the obstacle. If the obstacle is not closed, the system remains inactive. However, if the obstacle is close, the microcontroller activates a buzzer, generates continuous alarming sounds, and vibrates a motor, enabling the user to navigate the path more easily. Additionally, the system is equipped with a GSM module, allowing it to send SMS notifications to designated contacts in case of emergencies. By pressing an emergency button, a message is sent to a specified phone number. This integrated system provides both obstacle detection and emergency SMS notifications. The successful implementation of the system demonstrates its effectiveness and efficiency.

Rule based chatbot design methods: A review

Elsabeth Solomon, Surafel L Tilahun — Thu, 10 Oct 2024 00:00:00 +0000

The use of chatbots in various sectors including the health sector is becoming important. Rule based chatbots are one of the commonly used chatbots which is easier to implement and with less error. For example, in assisting by providing preliminary diagnostics to the youth and advising them to provide appropriate medical care and awareness creation. In resource limited environment where there is a shortage of medical experts as well as other resources, rule based chatbot can be a supportive tool to support patients and health workers. In addition, in infections like sexually transmitted infections, having an anonymous chatbot is ideal for supporting the youth who fear to openly visit health centers due to stigma and discrimination. Hence, a rule based chatbot can be designed to support them in providing preliminary diagnostics, advising them to visit health centers as well as creating awareness from reliable sources. Hence, this paper, reviews key rule based chatbot design approaches, their advantages and disadvantages.