Articles

A Comparative Machine Learning Approach for Usability Evaluation of Localized Software in Afghanistan

/0 Comments/in /by

Usability is one of the most important software quality attributes in determining user satisfaction, productivity and system acceptance. Afghanistan is a multilingual country, and usability problems with localized software applications may occur due to linguistic diversity, cultural differences, and scarce resources for evaluating the usability of software applications. These traditional usability assessment techniques, such as heuristic evaluation and laboratory testing, are difficult to implement in a capacity-constrained environment, as they require significant time, expertise and funds. The study suggests an automatic usability evaluation framework by machine learning techniques for localized software systems in Afghanistan. Data were gathered from ISO 9241-11 usability framework-based structured questionnaires from users of localized software applications. After collecting the responses, they were subjected to a pre-processing procedure involving cleaning, encoding and normalizing. Three supervised machine learning algorithms Decision Tree (DT), K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) were trained and tested with 80:20 ratio of training and test data. Model performance was evaluated using the accuracy, precision, recall, F1-score and confusion matrix analysis. Experimental results indicate that the highest accuracy of 91.4% is obtained by DT followed by SVM with 90.0% accuracy and KNN with 88.7%. The results show that the Decision Tree is a good model for balancing the prediction accuracy and interpretation of local software environments. The proposed framework has been designed to be both scalable and cost-effective, and can be used to complement existing usability evaluation methods, and can also be used to aid in software quality improvement efforts in multilingual and developing country settings.

Virtual Mouse and Keyboard for Computer Interaction by Hand Gestures Using Machine Learning

/in /by

Human-computer interaction has changed since the advent of computer technology. Gestures are a useful way to communicate, and the Covid-19 era had an impact on us. Both the keyboard and the mouse are tools used to communicate with computers. Here, we’ve attempted to use hand gestures to interact with the mouse and keyboard. Eventually, get rid of the electronics. Consequently, use a virtual keyboard and your finger to move the mouse cursor. Using different hand gestures, actions like clicking, dragging, and typing data will be carried out.
A webcam is the IOT device required to accomplish this. The output from the camera will be displayed on the system’s screen so that the user can fine-tune it. We employ tools like Python, Media- Pipe, and Open-CV. The Media-Pipe library offers features that improve the model’s effectiveness and is particularly helpful in AI projects. The user will be able to move the computer cursor with various hand motions, type on the virtual keyboard while holding coloured caps or tapes, and left-click and drag objects. In this research, we suggest a hand gesture detection system for a natural human computer interface that can control a virtual mouse and keyboard.

Improving a Two-Way Interaction Customer Service Platform in Company X using AHP

/in /by

The Covid-19 Pandemic has accelerated mass digitalization in most human activities, including in the construction industry. As a response to the social restriction policy during the pandemic, customers and companies have preferred doing business online. Company X has already launched an online customer service platform that could be maximally used during the social restriction policy. This platform uses SST (Self-Service Technology) to let customers perform their service independently. However, the platform was ineffectively utilized due to a lack of sense of two-way interaction. The stakeholders suggested adding a new feature based on the customer’s aspirations and the company’s considerations. During the development, understanding the relationship between the user and the system must be learned through HCI (Human-Computer Interaction). This research is primarily focused on the factors that affect layout design. The method to obtain a new feature in this customer service platform is using Analytical Hierarchy Process (AHP) to minimize inconsistencies while considering the new features.