Journal of Robotics, Networking and Artificial Life Volume10, Issue4,
March 2024

Research Article
1.Effect of Interlayer Anions with NiZn Hydroxy Double Salts on Adsorption of Selenite, Selenate and Arsenate
Kaoru Ohe, Ryosuke Tabuchi, Tatsuya Oshima
Faculty of Engineering, University of Miyazaki, 1-1 Gakuen Kibanadai-Nishi, Miyazaki, 889-2192, Japan
pp. 294–298
ABSTRACT
Development of adsorbents for selenium and arsenic, which are particularly toxic, is urgently needed. arsenic was prepared for adsorption and removal. The experimental data of adsorption isotherms of As and Se oxyanions by NiZn adsorbents were well fitted to the Langmuir adsorption model, which is characteristic of monolayer adsorption, with a coefficient of determination of R2>0.94. The maximum adsorption (qmax) of Se(IV) by NiZn-Cl and NiZn-NO3 was similar to that of NiZn-AcO, and no difference in adsorption due to interlayer ions was indicated. On the other hand, NiZn-Cl had the highest qmax for Se(VI) and As(V). qmax for As(V) by NiZn-Cl was about twice that of NiZn-AcO, As(V) and Se(VI) adsorption performance was greatly improved.

ARTICLE INFO
Article History
Received 24 November 2023
Accepted 11 April 2024

Keywords
NiZn hydroxy double salts
Langmuir adsorption model
Se(IV)
Se(VI)
As(V)

10401

Research Article
2.Coastal Litter Detection through Image Analysis-Employing Deep Learning to Identify Microplastics-
Yuto Okawach¹, Shintaro Ogawa¹, Takamasa Hayashi¹, Tan Chi Jie¹, Janthori Titan¹, Eiji Hayashi¹, Ayumu Tominaga²,
Satoko Seino^3
1Department of Mechanical Information Science and Technology, Kyushu Institute of Technology, 680-4, Kawazu, Iizuka-City, Fukuoka, 820-8502, Japan
²Department of Creative Engineering Robotics and Mechatronics Course, National Institute of Technology Kitakyushu Colllege, 5-20-1 Shii, Kokuraminamiku, Kitakyushu, Fukuoka, 802-0985, Japan
³Graduate School of Engineering, Kyushu University 744 Motooka, Nishiku, Fukuoka city, Fukuoka, 819-0395, Japan
pp. 299-303
ABSTRACT
The challenge of coastal litter accumulation led to the creation of a detection system powered by deep learning, aimed at identifying microplastics. The system harnessed the yolov7 [1] deep learning architecture, known for its proficiency in real-time object detection, and integrated the SAHI (Slicing Aided Hyper Inference) [2] vision library to augment its capabilities. Within the scope of our study, we conducted four separate evaluations using two versions of yolov7—the base model and the advanced yolov7-e6e—alongside SAHI. The performance of each setup was measured against a set of metrics, including Intersection over Union (IoU), Precision, Recall, F-measure, and Detection Time, recorded in seconds. The dataset for the study was composed of images sourced from real-world beach clean-up sites, including Hokuto Mizukumi Park. The detection algorithm was subjected to 700 rounds of training, with an initial learning rate of 0.001. Our findings indicated that the system was adept at identifying relatively small microplastics.

ARTICLE INFO
Article History
Received 30 November 2023
Accepted 08 April 2024

Keywords
Deep learning
Object detection
YOLOv7

10402

Research Article
3.Engineering of Autonomous Mobile Field Robot-Validating Precision in Self-Localization via Simulation -
Takamasa Hayashi¹, Shintaro Ogawa¹, Yuto Okawachi¹, Tan Chi Jie¹, Janthori Titan¹, Ayumu Tominaga², Eiji Hayashi¹,
Satoko Seino^3
1Graduate School of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka-city, Fukuoka, 820-8502, Japan
²Department of Creative Engineering Robotics and Mechatronics Course, National Institute of Technology, Kitakyushu College, 5-20-1, Kokuraminamiku, Kitakyushu Shii, Fukuoka, 802-0985, Japan
³Graduate School of Engineering, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka, 819-0395, Japan
pp. 304–307
ABSTRACT
In recent times, the escalation of marine debris has emerged as a formidable challenge, particularly in its retrieval. Among this, coastal debris, which falls under the broader category of marine debris, can indeed be manually picked up, yet the diversity in its forms and sizes limits the efficiency of solely human retrieval efforts. In response to this issue, my research concentrated on the development of an autonomous mobile robot. This study zeroes in on the critical task of self-localization, a fundamental requirement for autonomous navigation. Within our simulation, we meticulously recreated a real-world coastal cleanup site and assessed the self-localization precision utilizing an Extended Kalman Filter (EKF) alongside various sensors.

ARTICLE INFO
Article History
Received 30 November 2023
Accepted 13 April 2024

Keywords
Mobile field robot
Self-localization
Simulation
Extended Kalman Filter (EKF)

10403

Research Article
4.CAD Development of Moving Hula Costumes
Satoshi Ikeda¹, Taketo Kamasaka¹, Kaoru Ohe¹, Makoto Sakamoto¹, Amane Takei¹, Masahiro Yokomichi¹, Kenji Aoki¹, Tsutomu Ito², Takao Ito^3
1Faculty of Engineering, University of Miyazaki, Miyazaki-City, Miyazaki, Japan
²National Institute of Technology, Ube College, Ube-City, Yamaguchi, Japan
³Graduate School of Engineering, Hiroshima University, Higashi-Hiroshima, Hiroshima, Japan
pp. 308–312
ABSTRACT
In recent years, three-dimensional computer graphics (3DCG) technology has been applied in various fields. One problem with this technique is the problem of contact between clothing and other objects (such as the body). In this paper, we verified simple animations concerning of hula costumes using three calculation methods, and found that we were able to create simple and stable animations using the FB Euler method. This paper reports that we were able to create a simple animation.

ARTICLE INFO
Article History
Received November 25, 2020
Accepted 05 April 2024

Keywords
3DCG
C
C++
CAD
Collision detection
DirectX
Hula
Visual studio

10404

Research Article
5.MCU Based Edge Computing Platform for Liquid Level Measurement
Chung-Wen Hung¹, Chun-Liang Liu¹, Tai-Hsuan Wu¹, Chau-Chung Song^2
1National Yunlin University of Science and Technology, Taiwan, 123 University Road, Section 3, Douliou, Yunlin 64002, Taiwan, R.O.C
²National Formosa University, Taiwan, 64 Wenhua Road, Huwei Town, Yunlin County 632301, Taiwan, R.O.C
pp. 313–317
ABSTRACT
An MCU(microcontroller unit)-based edge computing system for assessing the height of liquids in containers in this paper. This system uses a solenoid valve to strike the bottle and a microphone to capture sound waves. Signals are transformed from the time domain to the frequency domain by FFT (Fast Fourier Transform) and used to predict the water level by using AI (artificial intelligence) model. A dynamic label smoothing method enhances label correlation, and an ANN (Artificial Neural Network) model is employed on the MCU for classification. The system accurately predicts water levels from 200 to 250 milliliters at 1-milliliter intervals. Hyperparameter optimization balances accuracy with MCU memory and computational constraints. Experimental results show that the system achieves an accuracy of 81% under the limits of edge computing, verifying its effectiveness in liquid level measurement applications.

ARTICLE INFO
Article History
Received 15 November 2023
Accepted 31 Julyl 2024

Keywords
Label smoothing
Edge computing
Audio process
Hyperparameter

10405

Research Article
6.A MBD-Based Dynamic Analysis Framework with a Viscoelastic Contact Model and Flexible Elements Toward Human Power Assistive Devices
Shintaro Kasai¹, Dondogjamts Batbaatar², Hiroaki Wagatsuma^1
1Kyushu Institute of Technology (Kyutech), 2-4 Hibikino, Wakamatsu-ku, Kitakyushu, Fukuoka, 808-0196, Japan
²Mongolian University of Science and Technology (MUST), 8th khoroo, Baga toiruu 34, Sukhbaatar Ulaanbaatar, Mongolia 14191
pp. 318–322
ABSTRACT
It is important for the analysis of human movement and rehabilitation to incorporate spring-damper components, flexible materials, and contact force into the joint model considering human dynamics. In this study, the absolute nodal coordination formula (ANCF) method is introduced to the analytical model for the viscoelastic properties of the musculoskeletal system which is essential for analyzing human walking motion, and the flexible characteristics of the human body is reproduced. The consideration of a contact force model makes it possible to simulate contact actions between elements of the human body and the interaction with the environment. The proposed integrated framework is applied to multibody dynamics (MBD) based slider-crank mechanisms to demonstrate the dynamics/inverse dynamics analysis of human joint biomechanics.

ARTICLE INFO
Article History
Received 25 November 2023
Accepted 05 September 2024

Keywords
Biomechanical systems
Multi-body dynamics (MBD)
Contact force and its modelling

10406

Research Article
7.Research on Improving Accuracy of Dynamic Visual SLAM Detection
Yufei Liu, Kazuo Ishii
Department of Human Intelligence Systems, Kyushu Institute of Technology, 2-4 Hibikino, Wakamatsu-ku, Kitakyushu, 808-0196, Japan
pp. 323–327
ABSTRACT
Currently, the application of SLAM systems in the field of navigation is quite active. However, the detection accuracy of classical SLAM systems when applied in dynamic environments is not high. This is because some dynamic objects in dynamic environments may occlude the environmental features that should have been extracted by the SLAM system. In order to solve this problem, my research conducts analysis on the detection process in dynamic environments and designs a solution: to identify and remove dynamic objects in dynamic environments to improve detection accuracy. In this research, an object detection algorithm YOLOv5 is first used to detect, identify, and remove dynamic objects in the environment extracted by the SLAM system. Then, the remaining static environmental features are passed into visual SLAM for conventional SLAM environment calculation and localization work. Finally, the modified integrated algorithm is validated and analyzed on the TUM dataset for feasibility. The results indicate that this approach successfully removes dynamic objects and effectively improves the robustness of visual SLAM applications in dynamic environments.

ARTICLE INFO
Article History
Received 04 December 2023
Accepted 17 April 2024

Keywords
Visual SLAM
Deep learning
Feature detection
Position estimation
YOLOv5

10407

Research Article
8.A Framework of Automatic Narrative Generation Game Based on the Russian Invasion of Ukraine
Jumpei Ono¹, Takashi Ogata^2
1Faculty of Software and Information Technology, Aomori University, 2-3-1, Kobata, Aomori, Aomori, 030-0943, Japan
²Faculty of informatics, Yamato University, 2-5-1, Katayama-cho, Suita, Osaka, 564-0082, Japan
pp. 328–335
ABSTRct
ABSTRACT
“Automatic narrative generation game” that we have been studying is a concept of game system for generating narratives through a game process. As this paper presents a game mechanism based on the concept of automatic narrative generation game, this research corresponds to an extension to a direction of the automatic narrative generation game. In particular, the proposed game uses ais the ongoing Russian invasion of Ukraine (beginning in February 2022) as the object. Moreover, our study of this kind of game refer to “tabletop role-playing game” or “table-talk role-playing game” (TRPG). TRPG is a type of analog game in which participants advance a shared storyline through dialog mainly. The proposed game system provides the knowledge of disinformation to the game user by simulating of the spread of disinformation. Through the game play, the game user can acquire knowledge for countering disinformation. We implemented two types of stories based on the timeline data of the Russian invasion of Ukraine. The first is a type of story in which Ukraine resists Russia and the second is a story of Ukraine’s collapse.

ARTICLE INFO
Article History
Received 30 November 2022
Accepted 21 April 2024

Keywords
Story generation
Automatic narrative generation game
Ukraine
Russia
Tabletop role-playing game
Disinformation
Russian Invasion of Ukraine
Russo-Ukrainian War

10408

Research Article
9.RAGESS: A Tool for Real-time Automatic Generation of SwiftDiagram to Support iOS Application Development
Haruki Onaga¹, Tetsuro Katayama¹, Yoshihiro Kita², Hisaaki Yamaba¹, Kentaro Aburada¹, Naonobu Okazaki^1
1Department of Computer Science and Systems Engineering, Faculty of Engineering, University of Miyazaki, 1-1 Gakuen-kibanadai nishi, Miyazaki, 889-2192 Japan
²Department of Information Security, Faculty of Information Systems, Siebold Campus, University of Nagasak, 1-1-1 Manabino, Nagayo-cho, Nishi-Sonogi-gun, Nagasaki, 851-2195 Japan
pp. 336–341
ABSTRACT
It is difficult for mobile application developers to understand the structure of large and complex mobile applications. To support iOS application development, we proposed SwiftDiagram: a visualization of the static structure of Swift source code, and demonstrated its usefulness. To further support them, this paper has implemented RAGESS(Real-time Automatic Generation of SwiftDiagram System), which is a software visualization tool. RAGESS performs static analysis on Swift source code and automatically generates the corresponding SwiftDiagram whenever the target project build succeeds.

ARTICLE INFO
Article History
Received 24 November 2023
Accepted 19 Junel 2024

Keywords
Software visualization
Mobile application
iOS
Swift

10409

Research Article
10.Systems Science: Digitalization of Transdisciplinary Research
Mykola Petrenko, Kyrylo Malakhov
Microprocessor technology lab, Glushkov Institute of Cybernetics of the National Academy of Sciences of Ukraine, Kyiv, Ukraine
pp. 342–352
ABSTRACT
The conceptual foundations of transdisciplinary researches with the use of methods and means of artificial intelligence, including ontological engineering, have been developed. The stages of formation of the theory of transdisciplinarity are defined, in which the processes of building the categorical level of concepts and integration of subject knowledge, the formation of clusters of convergence of subject disciplines, the scientific picture of the world and the corresponding global network of transdisciplinary knowledge take a special place. In this case, a special role belongs to informatics as a system-forming branch of knowledge. The development of the NBIC-cluster of convergence opens wide, so far completely not assessed, possibilities of a global knowledge-oriented Internet, but with it also the whole of modern civilization. Obviously, this development will follow first the path of creation of the applied distributed systems in specific subject areas (Internet of Things, Smart systems in telemedicine, environmental monitoring, information support of goods and services, energy systems, utilities, etc.). Grid-, Block-chain-technologies and Cloud-computing, as well as virtual organizations, structures and services will occupy the central place in them.

ARTICLE INFO
Article History
Received 03 April 2024
Accepted 07 May 2024

Keywords
Transdisciplinarity
Systems science
Ontology engineering
Digitalization
Convergence clusters
Scientific picture of the world

10410

Research Article
11.Design of Intelligent Handling Robot Based on AT89C52
Fangyv Liu, Jiaxin Wang, Hao He
College of Electronic Information and Automation, Tianjin University of Science and Technology, 300222, China
pp. 353–356
ABSTRACT
The rapid expansion of E-learning environments has highlighted the critical issue of cyberbullying within digital classrooms. This study introduces a novel approach for early detection of cyberbullying by analyzing student engagement and emotional states in real time. Our SER-YOLO model fuses an advanced You Only Look Once version 5 (YOLOv5) with a Student Emotion Recognition system, enriched by sophisticated methodological improvements. It features Soft NMS to refine the Non-Maximum Suppression (NMS) process, embeds the Channel Attention (CA) module to augment the network's backbone, and employs Enhanced Intersection over Union (EIOU) for bounding box regression. This method proactively detects changes in student engagement and emotional states, providing an effective mechanism for the early detection and management of cyberbullying in E-learning environments.

ARTICLE INFO
Article History
Received 28 November 2023
Accepted 18 July 2024

Keywords
Cyberbullying detection
Emotion recognition
Deep learning
E-learning
YOLO

10411

Research Article
12.YOLOv5 Based Student Engagement and Emotional States Detection in E-Classes
Shuai Wang^1,2, Abdul Samad Shibghatullah³, Kay Hooi Keoy⁴, Javid Iqbal^5
1Institute of Computer Science and Digital Innovation, UCSI University, Cheras, Kuala Lumpur, Malaysia
²Department of Physics and Electronic Engineering, Yuncheng University, Yuncheng, Shanxi, China
³College of Computing & Informatics, Universiti Tenaga Nasional, Kajang, Selangor, Malaysia
⁴Graduate Business School, UCSI University, Cheras, Kuala Lumpur, Malaysia
⁵Department of Computing and Information Systems, Sunway University, Petaling Jaya, Selangor, Malaysia
pp. 357–361
ABSTRACT
At present, manual logistics handling is inefficient and limited, Manual handling Most of the command and dispatch with experience, it is difficult to carry tasks in real time, confirm the location of the handling, cargo inventory and other work tasks time-consuming and laborious, manual operation is prone to error, workers labor intensity, resulting in greatly reduced work efficiency. This paper presents a logistics handling robot based on AT89C52 single chip microcomputer. The integration of the power module, sensor, and drive motor module enables automatic obstacle avoidance and information collection. Integrating an ultrasonic obstacle avoidance module alongside an infrared tracking module significantly boosts obstacle evasion and pathfinding capabilities, adeptly adapting to various work environments. Handling robot arm structure reference Yaskawa MPL manipulator, the Yaskawa MPL manipulator is highly suitable for high-speed and high-precision palletizing, picking, packaging, and other industries

ARTICLE INFO
Article History
Received 11 November 2023
Accepted 01 July 2024

Keywords
Logistics handling
Robot
MCU
Modularization
Obstacle avoidance

10412

Research Article
13.ASLA: Automatic Segmentation and Labeling by Deep Learning for Document Pictures
Kanta Kakinoki¹, Tetsuro Katayama¹, Yoshihiro Kita², Hisaaki Yamaba¹, Kentaro Aburada¹, Naonobu Okazaki^1
1Department of Computer Science and Systems Engineering, Faculty of Engineering, University of Miyazaki, 1-1 Gakuen-kibanadai nishi, Miyazaki, 889-2192, Japan
²Department of Information Security, Faculty of Information Systems, Siebold Campus, University of Nagasaki, 1-1-1 Manabino, Nagayo-cho, Nishi-Sonogi-gun, Nagasaki, 851-2195, Japanpp. 361–366
pp. 362–367
ABSTRACT
In this paper, we propose ASLA, a segmentation and label generation system for document pictures. ASLA reduces the duration needed for separating document pictures into areas and label generation. By using the application example, we have verified that ASLA operates properly. We have evaluated the usefulness of ASLA in regard to time and accuracy. We have assessed the efficacy of the rule-based area correction method. As a result, we have verified that ASLA is useful.

ARTICLE INFO
Article History
Received 24 November 2023
Accepted 22 July 2024

Keywords
Cyberbullying detection
Emotion recognition
Deep learning
E-learning
YOLO

10413

Research Article
14.The Antecedents of Michinoeki’s Efficiency in Japan: A Longitudinal Study
Satoshi Ikeda¹, Tsutomu Ito², Seigo Matsuno², Makoto Sakamoto¹, Rajiv Mehta³, Takao Ito^4
1Faculty of Engineering, University of Miyazaki, Japan
²Department of Business and Administration, Ube National College of Technology, Japan
³Martin Tuchman School of Management, New Jersey Institute of Technology, U.S.A
⁴Graduate School of advanced Science and Engineering, Hiroshima University, Japan
pp. 368–373
ABSTRACT
The expansion of Michinoeki along Japanese highway systems is widely considered to be a successful socio-economic experiment, which has enhanced interstate commerce as well as spurred tourism. Although descriptive studies on Michinoeki have been conducted, a review of the literature indicates that quantitative investigations are sparse. It is pivotal to identify the determinants that contribute to the success and efficiency of Michinoeki’s, which can provide insights to further augment their development, thus revitalizing the surrounding local economy. To address this gap in the literature, the present investigation drew data from the entire population of Michinoeki towards ascertaining their relative efficiency by employing the DEA model, which enables data-driven inferences as well as comparative analyses. Based on the findings of the study, managerial implications are identified and avenues for future research are forwarded.

ARTICLE INFO
Article History
Received 24 November 2023
Accepted 23 July 2024

Keywords
Michinoeki
Efficiency
DEA
Revitalization
PRC

10414

Research Article
15.Modeling of Contactless Ground Speed Sensor
Jakaria Mahdi Imam¹, Mohammad Aminul Islam¹, Norrima Mokhtar¹, S. F. W. Muhammad Hatta¹, Heshalini Rajagopal^2
1Department of Electrical Engineering, Faculty of Engineering, 50603 University of Malaya, Malaysia
²Department of Electrical & Electronic Engineering, Mila University, Negeri Sembilan, Malaysia
pp. 374–382
ABSTRACT
The proposed novel contactless speed sensor sounds intriguing and presents potential advantages over the conventional methods used in vessels, submarines, and aircraft. It is asserted that the utilization of a small-sized ball, dropped within a vacuum chamber, enables the direct measurement of the ground speed of these vehicles, as opposed to their speed relative to the water or air. This could be a significant improvement, as ground speed is often more relevant for navigation and operational purposes. A useful method for assessing the practicality and accuracy of the suggested sensor is to use simulation to verify its conceptual and mathematical model. However, it's important to note that simulations are different from real-world testing, and further experimental verification would be necessary to confirm the reliability of the sensor under various conditions and environments. One major advantage of this proposed sensor is its independence from the operational environment. Unlike current speed sensors that require contact with the air or water, the suggested sensor can be placed entirely inside the vehicle. By eliminating the necessity to mount the sensor externally, the risk of collision with external objects is minimized, resulting in an enhanced overall safety of the system.

ARTICLE INFO
Article History
Received 24 November 2023
Accepted 25 July 2024

Keywords
Contactless speed sensor
Vessels
Submarine
Aircraft
Navigation

10415