Pub Date : 2025-01-01Epub Date: 2025-11-06DOI: 10.1016/j.procs.2025.08.288
Nathanael Deciano Sugiharto , Darian Elbert , Ivan Sebastian Edbert
Vision-based surveillance system is used by major counties to monitor public spaces, namely face recognition to identify people and activity recognition to detect unwanted behaviour. The paper proposes a flexible and lightweight monitoring pipeline that runs both face and activity recognition at a time and is aimed for convenient deployment on closed spaces like schools or offices. The pipeline leverages popular vision models such as YOLOv8 for object detection, InsightFace for face recognition, and a vision- language model, CLIP, for zero-shot activity recognition that won’t need any model training. Testing the accuracy is done using two office footages, each with different complexities of camera angle and crowd distribution, one being far more complex than the other. The result is that YOLOv8 peaked at 95,73% accuracy, InsightFace at 96,56% accuracy, and CLIP at 53,25%. The testing provided an insight that the pipeline’s accuracy deteriorates at more complex footages with varying distances and angles of the object, and further research are needed on improving the pipeline’s optimization, known faces processing, and camera positioning.
{"title":"Employee monitoring system with computer vision: Face and activity recognition","authors":"Nathanael Deciano Sugiharto , Darian Elbert , Ivan Sebastian Edbert","doi":"10.1016/j.procs.2025.08.288","DOIUrl":"10.1016/j.procs.2025.08.288","url":null,"abstract":"<div><div>Vision-based surveillance system is used by major counties to monitor public spaces, namely face recognition to identify people and activity recognition to detect unwanted behaviour. The paper proposes a flexible and lightweight monitoring pipeline that runs both face and activity recognition at a time and is aimed for convenient deployment on closed spaces like schools or offices. The pipeline leverages popular vision models such as YOLOv8 for object detection, InsightFace for face recognition, and a vision- language model, CLIP, for zero-shot activity recognition that won’t need any model training. Testing the accuracy is done using two office footages, each with different complexities of camera angle and crowd distribution, one being far more complex than the other. The result is that YOLOv8 peaked at 95,73% accuracy, InsightFace at 96,56% accuracy, and CLIP at 53,25%. The testing provided an insight that the pipeline’s accuracy deteriorates at more complex footages with varying distances and angles of the object, and further research are needed on improving the pipeline’s optimization, known faces processing, and camera positioning.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"269 ","pages":"Pages 362-371"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-11-06DOI: 10.1016/j.procs.2025.09.182
S. Amihăesei , E.F. Olariu , C. Frăsinaru
This article presents an Ant Colony Optimization (ACO) algorithm, enhanced with problem-specific heuristics, for solving the Vertex Separator Problem (VSP). The VSP aims to find three disjoint subsets A, B, and C from the vertex set V of a graph G = (V, E), such that C forms a separator between A and B while minimizing |C| under cardinality constraints on A and B. The proposed method uses a colony of ants that construct solutions by assigning vertices probabilistically based on pheromone trails and problem-specific heuristics. A local search is introduced to refine these solutions, while adaptive pheromone updates and simulated annealing components are added to help escape local minima. Current studies concentrate on integer linear programming or heuristic approaches. This article details a novel metaheuristic solution, based on multiple heuristic functions, which are key to guiding the search process. We compare our solution to a greedy algorithm and heuristics from previous studies. The initial results proved encouraging, with ACO achieving better results compared to state-of-the-art heuristics on 15 of the 62 benchmarked problem instances.
{"title":"An Ant Colony Optimization approach to solving the Vertex Separator Problem","authors":"S. Amihăesei , E.F. Olariu , C. Frăsinaru","doi":"10.1016/j.procs.2025.09.182","DOIUrl":"10.1016/j.procs.2025.09.182","url":null,"abstract":"<div><div>This article presents an Ant Colony Optimization (ACO) algorithm, enhanced with problem-specific heuristics, for solving the Vertex Separator Problem (VSP). The VSP aims to find three disjoint subsets A, B, and C from the vertex set V of a graph G = (V, E), such that C forms a separator between A and B while minimizing |C| under cardinality constraints on A and B. The proposed method uses a colony of ants that construct solutions by assigning vertices probabilistically based on pheromone trails and problem-specific heuristics. A local search is introduced to refine these solutions, while adaptive pheromone updates and simulated annealing components are added to help escape local minima. Current studies concentrate on integer linear programming or heuristic approaches. This article details a novel metaheuristic solution, based on multiple heuristic functions, which are key to guiding the search process. We compare our solution to a greedy algorithm and heuristics from previous studies. The initial results proved encouraging, with ACO achieving better results compared to state-of-the-art heuristics on 15 of the 62 benchmarked problem instances.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"270 ","pages":"Pages 630-639"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-11-06DOI: 10.1016/j.procs.2025.08.294
Filo Alvian Ongky , Michael Efren Kartiyoso , Sie Reinhart Nathan Gunawan , Adhe Lingga Dewi , Ventje Jeremias Lewi Engel
This study was conducted with the aim of testing and implementing a microcontroller-based environmental monitoring system that measures temperature, humidity, and galvanic skin response (GSR) in real time resulting from changes in skin resistance due to sweat glands triggered by a person’s emotional condition. This system consists of a DHT11 sensor to detect temperature and humidity, and a GSR sensor to measure the level of skin conductivity as an indicator of a person’s stress or emotions. The data obtained is then displayed on a small LCD screen embedded in the top of the device. The experiment was carried out by the researcher inserting both of his fingers and the researcher while watching films with different genres to produce different emotional changes and the GSR sensor will work to detect changes in skin resistance resulting from the sweat glands and accumulate the results into a value. Then, variations in data obtained from experiments that have been carried out several times will be processed and the results obtained are in the form of a graph containing the interval of ups and downs of emotions based on time and the value of the GSR sensor and it is concluded how the situation in the surrounding conditions can affect changes in a person’s emotional condition.
{"title":"Optimizing Productivity: Internet of Things based Workload and Stress Monitoring using Galvanic Skin Response (GSR) Sensor Analysis and Microcontroller Arduino Uno","authors":"Filo Alvian Ongky , Michael Efren Kartiyoso , Sie Reinhart Nathan Gunawan , Adhe Lingga Dewi , Ventje Jeremias Lewi Engel","doi":"10.1016/j.procs.2025.08.294","DOIUrl":"10.1016/j.procs.2025.08.294","url":null,"abstract":"<div><div>This study was conducted with the aim of testing and implementing a microcontroller-based environmental monitoring system that measures temperature, humidity, and galvanic skin response (GSR) in real time resulting from changes in skin resistance due to sweat glands triggered by a person’s emotional condition. This system consists of a DHT11 sensor to detect temperature and humidity, and a GSR sensor to measure the level of skin conductivity as an indicator of a person’s stress or emotions. The data obtained is then displayed on a small LCD screen embedded in the top of the device. The experiment was carried out by the researcher inserting both of his fingers and the researcher while watching films with different genres to produce different emotional changes and the GSR sensor will work to detect changes in skin resistance resulting from the sweat glands and accumulate the results into a value. Then, variations in data obtained from experiments that have been carried out several times will be processed and the results obtained are in the form of a graph containing the interval of ups and downs of emotions based on time and the value of the GSR sensor and it is concluded how the situation in the surrounding conditions can affect changes in a person’s emotional condition.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"269 ","pages":"Pages 421-430"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-11-06DOI: 10.1016/j.procs.2025.09.005
Devan Lucian , Christian Alexander Alfen , Yosua Raffel Istianto , Anderies
Bahasa Isyarat Indonesia (BISINDO) is a sign language that aids in communicating with Indonesia’s deaf community by providing visual communication using hand movement and gestures. Unfortunately, advancements in this field remain stagnant and the quality of life of the Deaf and Hard-Hearing community in Indonesia lack progress, especially in the development of efficient computer models for sign language recognition to facilitate communication. In this paper, we aim to develop and compare several lightweight deep learning-based sign language recognition models using knowledge-distillation (KD), a model compression technique that distills knowledge from bigger deep learning models in various forms to a much smaller and more efficient lightweight models. The result from our experiments have shown EfficientNetB5’s superior performance in terms of pure effectiveness with the highest overall accuracy of 96.94% with an F1-Score of 0.9693, alongside its effectiveness at distilling knowledge to several lightweight deep learning models. As for the lightweight distilled models, MobileNetV3 displayed its excellent ability at balancing efficiency and effectiveness, where the distilled model trained with our KD loss function achieved an accuracy of 83.45% and F1-Score of 0.8331 with only a model size of 3.8 MB and 0.1186 GFLOPs, whereas ShuffleNetV2 provides the most effective result out of all student models, as the distilled model achieved an accuracy of 89.87% and F1-Score of 0.8987 with a slightly higher model size of 6.4 MB and 0.5391 GLOPs compared to MobileNetV3.
{"title":"Improving Indonesian sign language recognition using lightweight deep learning architectures with knowledge distillation method","authors":"Devan Lucian , Christian Alexander Alfen , Yosua Raffel Istianto , Anderies","doi":"10.1016/j.procs.2025.09.005","DOIUrl":"10.1016/j.procs.2025.09.005","url":null,"abstract":"<div><div>Bahasa Isyarat Indonesia (BISINDO) is a sign language that aids in communicating with Indonesia’s deaf community by providing visual communication using hand movement and gestures. Unfortunately, advancements in this field remain stagnant and the quality of life of the Deaf and Hard-Hearing community in Indonesia lack progress, especially in the development of efficient computer models for sign language recognition to facilitate communication. In this paper, we aim to develop and compare several lightweight deep learning-based sign language recognition models using knowledge-distillation (KD), a model compression technique that distills knowledge from bigger deep learning models in various forms to a much smaller and more efficient lightweight models. The result from our experiments have shown EfficientNetB5’s superior performance in terms of pure effectiveness with the highest overall accuracy of 96.94% with an F1-Score of 0.9693, alongside its effectiveness at distilling knowledge to several lightweight deep learning models. As for the lightweight distilled models, MobileNetV3 displayed its excellent ability at balancing efficiency and effectiveness, where the distilled model trained with our KD loss function achieved an accuracy of 83.45% and F1-Score of 0.8331 with only a model size of 3.8 MB and 0.1186 GFLOPs, whereas ShuffleNetV2 provides the most effective result out of all student models, as the distilled model achieved an accuracy of 89.87% and F1-Score of 0.8987 with a slightly higher model size of 6.4 MB and 0.5391 GLOPs compared to MobileNetV3.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"269 ","pages":"Pages 618-629"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-11-06DOI: 10.1016/j.procs.2025.09.200
Takuya Matsuzawa , Taiki Ito , Sumika Arima
In the semiconductor field, which is the primary focus of this study, the increasing demand has led to a supply shortage, necessitating the expansion of production capacity and the reinforcement of the manufacturing infrastructure. Among the various challenges, the issue of defective products is particularly critical, highlighting the importance of feature analysis for identifying defective factors. However, due to the large scale and complexity of semiconductor manufacturing data, feature analysis poses significant challenges.
In this study, we focus on Sparse Factorization Machines (SFM) as an interaction modeling approach for high-dimensional data, characterized by high computational efficiency and strong robustness to missing data. Our previous paper proposed an advanced SFM method denoted by SFM1A, which enhances both selections of main factors and interactions by employing a regularization and a new adaptive technique to SFM with Triangle inequality upper boundary. While SFM1A has demonstrated a significant reduction in false positives (FPs) (main: -99%, interaction: -97%), however, it is not yet at a practical level (e.g. target is less than a few hundred selections including FPs when input data dimension is 10000).
To address the issue, this study aims to develop an advanced method that minimizes incorrect interaction selections without compromising selection accuracy for true main factors and interactions. The first proposed method, SFM1A_SPC is to combine SPC criteria mathematically proved in the safe pruning method to SFM1A. SFM1A_SPC successfully reduces FPs of interactions. The second proposal, SFM1A_SPC_FP method, further improves the selection accuracy of main factors by applying a sequential selection method (FP) based on the properties of submodular optimization to perform dimensionality reduction.
Numerical evaluation of SFM1A_SPC_FP confirms that it maintains the interaction selection accuracy of SFM1A_SPC while further enhancing the categorical main factor selection. Finally, SFM1A_SPC_FP method achieves the target required for the practical application.
{"title":"The reduction of false positives in Sparse Factorization Machines","authors":"Takuya Matsuzawa , Taiki Ito , Sumika Arima","doi":"10.1016/j.procs.2025.09.200","DOIUrl":"10.1016/j.procs.2025.09.200","url":null,"abstract":"<div><div>In the semiconductor field, which is the primary focus of this study, the increasing demand has led to a supply shortage, necessitating the expansion of production capacity and the reinforcement of the manufacturing infrastructure. Among the various challenges, the issue of defective products is particularly critical, highlighting the importance of feature analysis for identifying defective factors. However, due to the large scale and complexity of semiconductor manufacturing data, feature analysis poses significant challenges.</div><div>In this study, we focus on Sparse Factorization Machines (SFM) as an interaction modeling approach for high-dimensional data, characterized by high computational efficiency and strong robustness to missing data. Our previous paper proposed an advanced SFM method denoted by SFM1A, which enhances both selections of main factors and interactions by employing a regularization and a new adaptive technique to SFM with Triangle inequality upper boundary. While SFM1A has demonstrated a significant reduction in false positives (FPs) (main: -99%, interaction: -97%), however, it is not yet at a practical level (e.g. target is less than a few hundred selections including FPs when input data dimension is 10000).</div><div>To address the issue, this study aims to develop an advanced method that minimizes incorrect interaction selections without compromising selection accuracy for true main factors and interactions. The first proposed method, SFM1A_SPC is to combine SPC criteria mathematically proved in the safe pruning method to SFM1A. SFM1A_SPC successfully reduces FPs of interactions. The second proposal, SFM1A_SPC_FP method, further improves the selection accuracy of main factors by applying a sequential selection method (FP) based on the properties of submodular optimization to perform dimensionality reduction.</div><div>Numerical evaluation of SFM1A_SPC_FP confirms that it maintains the interaction selection accuracy of SFM1A_SPC while further enhancing the categorical main factor selection. Finally, SFM1A_SPC_FP method achieves the target required for the practical application.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"270 ","pages":"Pages 802-811"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-11-06DOI: 10.1016/j.procs.2025.08.308
Melania Aprillyawati , Wahyu Setioko
Digital games offer significant potential for education, especially when purposefully designed to promote conceptual understanding and critical thinking. This study examines how the mobile game Where’s My Water? 2 integrates scientific and sustainability concepts through its game design. A qualitative content analysis identified 57 concepts, primarily in physics (fluid dynamics, energy transformation), along with environmental, chemical, and biological elements. These concepts are infused through the game’s gameplay, scenarios, interactive objects, characters, and challenges, which make science both intuitive and engaging. While the game shows strong educational potential, it also highlights the need for guided reflection to prevent misconceptions and maximize learning outcomes. The findings call for collaboration between game designers, educators, and computer scientists to develop interactive, adaptive, and narrative-driven elements that not only engage players but also deepen their learning experience.
数字游戏为教育提供了巨大的潜力，特别是当它被有意设计成促进概念理解和批判性思维时。本文分析了手机游戏《Where’s My Water?》2在游戏设计中融入了科学和可持续的理念。定性内容分析确定了57个概念，主要是物理概念（流体动力学、能量转换），以及环境、化学和生物要素。这些概念贯穿于游戏玩法、场景、互动对象、角色和挑战中，让科学变得既直观又吸引人。虽然游戏显示出强大的教育潜力，但它也强调了引导反思的必要性，以防止误解和最大化学习成果。研究结果呼吁游戏设计师、教育工作者和计算机科学家合作开发互动性、适应性和叙事驱动的元素，不仅要吸引玩家，还要加深他们的学习体验。
{"title":"Infusing Science and Sustainability Concepts in Game Design: A Qualitative Content Analysis of a Physics-Based Mobile Game","authors":"Melania Aprillyawati , Wahyu Setioko","doi":"10.1016/j.procs.2025.08.308","DOIUrl":"10.1016/j.procs.2025.08.308","url":null,"abstract":"<div><div>Digital games offer significant potential for education, especially when purposefully designed to promote conceptual understanding and critical thinking. This study examines how the mobile game <em>Where’s My Water? 2</em> integrates scientific and sustainability concepts through its game design. A qualitative content analysis identified 57 concepts, primarily in physics (fluid dynamics, energy transformation), along with environmental, chemical, and biological elements. These concepts are infused through the game’s gameplay, scenarios, interactive objects, characters, and challenges, which make science both intuitive and engaging. While the game shows strong educational potential, it also highlights the need for guided reflection to prevent misconceptions and maximize learning outcomes. The findings call for collaboration between game designers, educators, and computer scientists to develop interactive, adaptive, and narrative-driven elements that not only engage players but also deepen their learning experience.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"269 ","pages":"Pages 561-570"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In today’s digital era, online travel platforms serve as essential tools for users to conveniently book flights, with UI/UX design playing a crucial role in shaping user perceptions and interactions. As the competition between online travel agencies (OTAs) intensifies, platforms like Traveloka and Tiket.com are constantly improving their user interfaces and experiences to attract and retain users. This research aims to explore how UI/UX design affects user satisfaction and perceived usability in flight ticket booking services by conducting a comparative analysis between these two leading Indonesia OTAs. Using a quantitative approach, this study employed usability testing followed by the UMUX-LITE questionnaire to measure user perceptions on both platforms. From the responses of 31 participants, we found that while Tiket.com scores slightly higher in ease of use, Traveloka offers greater usefulness due to its more extensive filter options, such as student tickets and refundable flight. Overall, Traveloka achieved UMUX-LITE score of 79.570 (grade A-) compared to Tiket.com 77.957 (grade B+), showing that better functionality can positively impact the overall experience. However, Tiket.com cleaner and simpler interface led to more users (54.8%) to prefer it overall. These highlight the importance of balancing simplicity and functionality in UI/UX design, and offer insights for improving the user journey in digital travel platforms.
{"title":"Comparative Analysis of UI/UX Design in Flight Ticket Booking: A Case Study of Traveloka vs Tiket.com","authors":"Julian Alby Nathanael , Zaidan Tio Rahman , Reina Reina , Reinert Yosua Rumagit","doi":"10.1016/j.procs.2025.09.012","DOIUrl":"10.1016/j.procs.2025.09.012","url":null,"abstract":"<div><div>In today’s digital era, online travel platforms serve as essential tools for users to conveniently book flights, with UI/UX design playing a crucial role in shaping user perceptions and interactions. As the competition between online travel agencies (OTAs) intensifies, platforms like Traveloka and Tiket.com are constantly improving their user interfaces and experiences to attract and retain users. This research aims to explore how UI/UX design affects user satisfaction and perceived usability in flight ticket booking services by conducting a comparative analysis between these two leading Indonesia OTAs. Using a quantitative approach, this study employed usability testing followed by the UMUX-LITE questionnaire to measure user perceptions on both platforms. From the responses of 31 participants, we found that while Tiket.com scores slightly higher in ease of use, Traveloka offers greater usefulness due to its more extensive filter options, such as student tickets and refundable flight. Overall, Traveloka achieved UMUX-LITE score of 79.570 (grade A-) compared to Tiket.com 77.957 (grade B+), showing that better functionality can positively impact the overall experience. However, Tiket.com cleaner and simpler interface led to more users (54.8%) to prefer it overall. These highlight the importance of balancing simplicity and functionality in UI/UX design, and offer insights for improving the user journey in digital travel platforms.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"269 ","pages":"Pages 690-695"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-03-11DOI: 10.1016/j.procs.2025.02.118
Luís Carvalho , Telmo Adão , Raul Morais , António Rio Costa , Emanuel Peres
Precision Agriculture (PA) systems, crucial for modern farming, heavily rely on data gathered from various sensors often connected through an Internet of Things (IoT)-based environment, wherein cybersecurity challenges must not be neglected. To address such challenges, this paper explores conventional security approaches and Zero Trust (ZT) principles oriented to PA. To that end, a practical case-study focusing a precision viticulture device known as VineInspector is assessed in terms of susceptibilities, encompassing unauthorized physical access, manipulation of sensor readings, and tampering of data communication. As a result of that assessment, a set of recommendations are provided to ensure integrity, confidentiality, and availability of agricultural data, with applicability to PA devices operating in conditions similar to the one considered for the referred case-study.
{"title":"Conventional and Zero Trust Security Measures for Precision Agriculture Devices: the mySense’s VineInspector Case-study","authors":"Luís Carvalho , Telmo Adão , Raul Morais , António Rio Costa , Emanuel Peres","doi":"10.1016/j.procs.2025.02.118","DOIUrl":"10.1016/j.procs.2025.02.118","url":null,"abstract":"<div><div>Precision Agriculture (PA) systems, crucial for modern farming, heavily rely on data gathered from various sensors often connected through an Internet of Things (IoT)-based environment, wherein cybersecurity challenges must not be neglected. To address such challenges, this paper explores conventional security approaches and Zero Trust (ZT) principles oriented to PA. To that end, a practical case-study focusing a precision viticulture device known as VineInspector is assessed in terms of susceptibilities, encompassing unauthorized physical access, manipulation of sensor readings, and tampering of data communication. As a result of that assessment, a set of recommendations are provided to ensure integrity, confidentiality, and availability of agricultural data, with applicability to PA devices operating in conditions similar to the one considered for the referred case-study.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 246-254"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-03-11DOI: 10.1016/j.procs.2025.02.122
Sini Raj Pulari , Shomona Gracia Jacob
Dramatic progress in the use of AI for the design of smart learning systems has undoubtedly enhanced the professional competence of students across the globe. However, the sudden access to unlimited autonomy has posed unprecedented risks to moral and ethical practices in educational standards that far outweigh the rewards. In this research, the authors attempt to present a succinct review on the ethical implications of employing artificial intelligence in classroom education both from the educator and the student’s perspective. Summarizing the loopholes in establishing strong ethical practices by virtue of AI leverage, especially in the realm of education is of utmost importance. The findings of this study revealed two main spheres of educational transformation that need to be addressed in smart academic enterprises: (a) automated review generation based on student and evaluator scores (b)infallible system to ensure adherence to ethical practices during assessments.
{"title":"Research Insights on the Ethical Aspects of AI-Based Smart Learning Environments: Review on the Confluence of Academic Enterprises and AI","authors":"Sini Raj Pulari , Shomona Gracia Jacob","doi":"10.1016/j.procs.2025.02.122","DOIUrl":"10.1016/j.procs.2025.02.122","url":null,"abstract":"<div><div>Dramatic progress in the use of AI for the design of smart learning systems has undoubtedly enhanced the professional competence of students across the globe. However, the sudden access to unlimited autonomy has posed unprecedented risks to moral and ethical practices in educational standards that far outweigh the rewards. In this research, the authors attempt to present a succinct review on the ethical implications of employing artificial intelligence in classroom education both from the educator and the student’s perspective. Summarizing the loopholes in establishing strong ethical practices by virtue of AI leverage, especially in the realm of education is of utmost importance. The findings of this study revealed two main spheres of educational transformation that need to be addressed in smart academic enterprises: (a) automated review generation based on student and evaluator scores (b)infallible system to ensure adherence to ethical practices during assessments.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 284-291"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01Epub Date: 2025-06-10DOI: 10.1016/j.procs.2025.05.034
Jianbo He
In the urban water supply system, facing the problems of water shortage, demand fluctuation and water supply safety, the traditional scheduling method is difficult to meet the growing demand for intelligence. Therefore, this study aims to apply the fuzzy neural network algorithm to optimize the intelligent scheduling of the urban water supply system. First, a neural network model based on fuzzy logic is constructed, integrating multiple input factors such as water source, user demand, pipe network status and meteorological data. Then, through data preprocessing, historical water supply data is cleaned and standardized to ensure the accuracy of model training. Then, the model is trained with historical data, the model parameters are optimized by cross-validation method, and the fuzzy rules are automatically adjusted by genetic algorithm to achieve refined scheduling. In the experiment, the model is tested by water supply data from different locations. The average water supply efficiency of the optimized scheduling model is 1.51. The application of fuzzy neural network algorithm in the intelligent scheduling of urban water supply system effectively solves the shortcomings of traditional methods and provides a new idea for achieving more efficient and intelligent water supply management.
{"title":"The Application of Fuzzy Neural Network Algorithm in Intelligent Scheduling of Urban Water Supply System","authors":"Jianbo He","doi":"10.1016/j.procs.2025.05.034","DOIUrl":"10.1016/j.procs.2025.05.034","url":null,"abstract":"<div><div>In the urban water supply system, facing the problems of water shortage, demand fluctuation and water supply safety, the traditional scheduling method is difficult to meet the growing demand for intelligence. Therefore, this study aims to apply the fuzzy neural network algorithm to optimize the intelligent scheduling of the urban water supply system. First, a neural network model based on fuzzy logic is constructed, integrating multiple input factors such as water source, user demand, pipe network status and meteorological data. Then, through data preprocessing, historical water supply data is cleaned and standardized to ensure the accuracy of model training. Then, the model is trained with historical data, the model parameters are optimized by cross-validation method, and the fuzzy rules are automatically adjusted by genetic algorithm to achieve refined scheduling. In the experiment, the model is tested by water supply data from different locations. The average water supply efficiency of the optimized scheduling model is 1.51. The application of fuzzy neural network algorithm in the intelligent scheduling of urban water supply system effectively solves the shortcomings of traditional methods and provides a new idea for achieving more efficient and intelligent water supply management.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"262 ","pages":"Pages 108-114"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号