In this research, we developed an application that allows AR simulations to check safety ranges and operation details. Furthermore, we created a user-friendly GUI, suitable for individuals with limited knowledge in robot development. This application was developed using ARCore in Unity. By establishing communication between ROS (Robot Operating System) and Unity to control virtual robots, we achieved visualization of ROS-based robots in the AR environment. With this AR application, the need for physical safety design and verification of safety ranges during the introduction of robots in small and medium-sized enterprises has been significantly reduced. As a result, cost reduction in the implementation process can be expected, and it offers a potential solution to the labor shortage issues in such enterprises. In conclusion, the effectiveness of the AR application developed in this research has been confirmed.

View full abstract

Datasets are one of the key elements which determine the performance of a deep learning network. Urban environments datasets receive much attention nowadays due to the rise of autonomous cars but off-road environment on the other hand lacks quality datasets. Offroad environments need equal attention as only 55% of the world’s population lives in urban areas. This paper tackles this issue to close the gap of robotic visual perception on the beach, one of the common offroad environments that lack attention by presenting a real and synthetic dataset, namely BCRobo.

View full abstract

The aim of this project is to amplify the table tennis tournament analysis via Web-Based application. Typically, the tournament scores used to be collected and displayed manually. All the information used to be captured by the referees during the matches, while most of the competitors provided only basic information and real-time scores online. Over the years of technological advancements, the modern development of software applications has helped users perform useful tasks and retrieve useful data based on the requests. The objective of this project is to develop a functional web application that will retrieve or store table tennis tournament statistical data and visualize them using tables, bar charts, pie charts, histograms as a medium of demonstration for the user. Moreover, the application will perform specific analysis on the scores and display insightful data about the tournament for league structures investigation. The developed system will include a database to store and retrieve data for display on the user interface. The development of the project is fully stacked (front-end and back-end), so it is built with the appropriate web technologies to function in the background (PHP, MySQL, Apache) while displaying results (HTML, CSS, JavaScript) on the page for the user. The project is managed using effective project management methods to plan, design, implement, develop, and maintain the application.

View full abstract

An enhanced variant of the Grey Wolf Optimization (GWO) algorithm, known as the Improved Grey Wolf Optimization (IGWO), was introduced with the primary objective of improving the precision of apple's external quality assessment categorization using Support Vector Machine (SVM) as the underlying classifier.The IGWO algorithm incorporates several enhancements, including the utilization of Logistic chaos mapping, a nonlinear convergence factor, and Cauchy variation. Initially, diverse benchmark functions were employed to assess the efficacy of the IGWO methodology. The experimental outcomes demonstrated that the IGWO method significantly enhanced both the rate of convergence and precision. Subsequently, an image processing approach was employed to capture the exogenous characteristics of apples, which were then utilized as the dataset. The IGWO method was employed to fine-tune the regularization parameters and kernel parameters in the SVM, resulting in the optimal IGWO-SVM classification model. Finally, a comparative analysis was conducted between the classification results obtained from SVM, GMO-SVM, and IGWO-SVM. The findings revealed that the IGWO-SVM model achieved the peak accurate classification performance, surpassing the other methods.

View full abstract

One of the most popular sports in Asia is Table Tennis, it requires close supervision from a coach to assess the player's strengths and weaknesses. To address this need, a personal Table Tennis trainer in the form of a pitcher machine has been developed. The machine analyzes the player's practical performance by examining the trajectory path of the ball. The system incorporates a camera that tracks the movement of the table tennis ball. Images captured by the camera are processed using OpenCV software, enabling the prediction of the ball's flying trajectory based on its X and Y coordinates. This analysis allows for an evaluation of the player's performance in different directions. By utilizing a smartphone, the pitcher machine can be adjusted to target the direction where the player's performance is weak, thereby providing additional practice in that specific area. Although the proposed system does not currently include spinning serves, it offers a suitable platform for early-stage table tennis training. Experimental results demonstrate the system's ability to perform acceptable performance analysis in complex and cluttered environments.

View full abstract

TDD is a development methodology to improve software quality. In this study, we prototype the framework CATdd (Continuous Automated Test Driven Development), which supports continuous development with TDD. CATdd reduces the time of implementation step in TDD by generating new source code that passes tests using LLM. CATdd maintains consistency with other source code in the project by using existing source code and related source code to prompt. As a result of the evaluation experiments, the time for the implementation step in TDD was reduced by 94% for a simple task and by 56% for another more complex task. In conclusion, CATdd is useful to support continuous development.

View full abstract

This study investigated the potential of a hexacopter unmanned aerial vehicle (UAV) spraying system as one of the agricultural spraying methods in Malaysia. The altitude of the UAV he operated at 1.5 meters and under a wind speed of 1.15 meters per second he tested three different nozzles. The uniformity and spread of application in paddy field conditions were evaluated. ImageJ software was used for evaluation. The results showed that using an electrostatic centrifugal nozzle for droplet dispersion resulted in remarkable average droplet densities, especially 134.03 deposits/cm2 in the upper region and 153.93 deposits/cm2 in the lower region. Furthermore, in the electrostatic centrifugal nozzle, it was confirmed that 3478 droplets were deposited in the upper region and 3255 droplets were deposited in the lower region.

View full abstract

This paper discusses quasi-static grasp stability of frictionless enveloping grasps in two dimensions. The stability is investigated from the viewpoint of potential energy stored in the grasps. The system of the grasps is replaced with elastic property, in which joint position and link surface properties are represented by linear stiffness. The contact constraints between a grasped object and finger links are formulated. The potential energy of the grasp system is obtained from the stiffness and the joint and link surface displacements. A wrench (i.e., force and moment) vector and a stiffness matrix of the grasp system are derived from partial differentiations by the pose (i.e., translation and rotation) displacement of the object. The grasps are stable if both the wrench vector is zero and the matrix is positive definite. The stability is evaluated by the eigenvalues of the matrix. Since, in this paper, the wrench vector and the stiffness matrix are derived in an analytical way, the matrix is given as a function of grasp positions, grasp forces, local curvatures, joint and surface stiffnesses, and so on at contact points, explicitly. We investigate curvature and stiffness effects on the grasp system by partially differentiating the matrix by the curvatures and stiffnesses. The positive definiteness of the matrix differentiations is analyzed. Validity of our analysis is confirmed through numerical examples.

View full abstract

Haze is a prevalent term within the field of image processing, encompassing both naturally occurring phenomena and aerosols generated by human activities. It gives rise to light scattering and absorption, leading to reduced image visibility. This diminished clarity poses challenges for various photographic and computer vision applications, including object recognition and localization. Consequently, there is a growing need for a method to estimate haze density accurately. In this research paper, we introduce a novel model called the "haziness degree evaluator." This model enables the prediction of haze density from a single image, eliminating the necessity for a reference haze-free image. The proposed model quantifies haze density through the optimization of an objective function that encompasses haze-related features derived from correlation and computational analysis.

View full abstract

We realize we've misplaced our keys and are frustrated by a massive search of the house. This paper develops a simple IoT-based key discovery method that uses a NodeMCU, a buzzer, and a battery. The method involved creating a key management method designed for key installation and developing a website to assist with key location. With her Google Chrome browser on the user's mobile phone, she can pinpoint the location of the lost key. When the website presses the key search button, it will play an IoT key-related beep and save time by streamlining the process. If you misplace your keys, you may search all over the house, but in the end, you may not be able to find them. This paper is extremely important in that it has developed a method for quickly finding keys using the method described above.

View full abstract