Determinate Student Final Project Supervisor Based AHP and SAW
Teotino Gomes Soares,
Marcelo Fernandes Xavier Cham,
Abdullah Bin Zainol Abidin
Issue:
Volume 7, Issue 2, December 2023
Pages:
31-39
Received:
10 May 2023
Accepted:
6 June 2023
Published:
5 August 2023
Abstract: Determining competent supervisors for student research projects is one of the factors that play the most important role because it can affect the success of student education, so it deserves attention. However, the process of determining a supervisor is not an easy thing because it involves various complex criteria and sub-criteria for making decisions consistently and objectively. Therefore, we propose AHP and SAW methods be utilized simultaneously with the criteria for education level, educational background, guiding experience, lecturer experience area, publication, guide quota, and student concentration, along with Forty-Three (43) other sub-criteria. This research purpose is to provide knowledge about how the AHP-SAW methods can be utilized together to cover each other's weaknesses in determining supervisors for student research projects. Where the AHP method works to calculate the priority level of criteria and sub-criteria that will be used by the SAW method in forming a matrix of criteria and alternatives and calculates the consistency value of the criteria and sub-criteria, while the SAW method works to calculate the matrix normalization value and ranking value for each alternative by utilizing the value of priority level of the criteria obtained from work of AHP. The results showed that the two methods were able to complement each other in determining the main supervisor of student research projects, with a ranking score of 1,00 for alternative ALec_002 and a co-supervisor ranking score of 0,97 for alternative ALec_007 out of 35 candidates.
Abstract: Determining competent supervisors for student research projects is one of the factors that play the most important role because it can affect the success of student education, so it deserves attention. However, the process of determining a supervisor is not an easy thing because it involves various complex criteria and sub-criteria for making decis...
Show More
Research Article
Signed Language Translation into Afaan Oromo Text Using Deep-Learning Approach
Diriba Negash Tesso*,
Etana Fikadu Dinsa,
Hawi Fikadu Kenani
Issue:
Volume 7, Issue 2, December 2023
Pages:
40-51
Received:
17 October 2023
Accepted:
2 November 2023
Published:
17 November 2023
Abstract: A person who is unable to talk or hear anything can communicate via sign language. For those who have trouble hearing, sign language is a great way to communicate their thoughts and feelings. The vocabulary, grammar, and allied lexicons of sign language are well- defined. This study focuses primarily on Signed Afaan Oromo. The main issue in our society is the detection of Sign Language for the Afaan Oromo language. The construction of static word level, alphabet, and number translations into their equivalent Afaan Oromo text is the main focus of this thesis study. Video frames are used as the system's input, and Afaan Oromo text is used as the system's ultimate output. Data from 90 classes at the alphabet, number, and word level from five special needs instructors have been collected as part of an experiment and literature study to help answer the research objectives. Preprocessing, such as frame extraction, resizing, labeling, and splitting data using Roboflow, as well as the conversion of photos into Yolo model format, was done in order to train our model. Finally, based on the results of our experiment, we can quickly and effectively recognize and classify gestures using data sets of a medium size. The image, webcam, and video file's promising value and forecast results indicate that the yolov5 algorithm has a good chance of successfully detecting the sign in real-time. We trained and tested the model using a signed Afaan Oromo dataset. The YOLOv5s model was successful in obtaining accuracy of 90%, recall of 92.5%, mAP of 93.2% at 0.5 IoU, and a score of 71.5% at 0.5:0.95 IoU, which is suitable for real-time gesture translation.
Abstract: A person who is unable to talk or hear anything can communicate via sign language. For those who have trouble hearing, sign language is a great way to communicate their thoughts and feelings. The vocabulary, grammar, and allied lexicons of sign language are well- defined. This study focuses primarily on Signed Afaan Oromo. The main issue in our soc...
Show More
Research Article
Amazon Marketplace: An Analysis of External Factors and Machine Learning Models - Survey
Muneer Hazaa Alsurori,
Waheeb Abdo Almorhebi*
Issue:
Volume 7, Issue 2, December 2023
Pages:
52-59
Received:
21 September 2023
Accepted:
20 October 2023
Published:
29 November 2023
Abstract: This research endeavors to utilize diverse machine learning algorithms to forecast product prices on the Amazon marketplace. The primary objective of the study is to examine the impact of external factors, such as Google Trends and customer reviews, on future product prices and demand. The research process involves gathering unstructured product information and pricing data from Amazon using APIs and crawlers, followed by preprocessing the data through techniques like tokenization and stopword removal. Machine learning algorithms, including decision trees, support vector regression, and random forests, are employed to predict product prices. The study also explores the challenges associated with web scraping and explores potential applications of web harvesting in e-commerce enterprises. To ensure a comprehensive analysis, the research draws upon relevant literature in the field, encompassing the use of machine learning models for stock price forecasting, time series forecasting, and sentiment analysis. By building upon and leveraging existing methodologies, the study aims to contribute to the understanding of price dynamics within the Amazon marketplace. The significance of this research lies in the growing reliance on e-commerce platforms like Amazon for product purchasing. By investigating the relationship between product prices and various influencing variables, this study can provide valuable insights to both sellers and consumers in the ever-evolving online market. Ultimately, the research seeks to predict product prices on the Amazon marketplace using machine learning algorithms and shed light on the dynamics of e-commerce, benefiting sellers and consumers alike.
Abstract: This research endeavors to utilize diverse machine learning algorithms to forecast product prices on the Amazon marketplace. The primary objective of the study is to examine the impact of external factors, such as Google Trends and customer reviews, on future product prices and demand. The research process involves gathering unstructured product in...
Show More
