International Journal of Crowd Science最新文献

{"title":"Survey on AI-Assisted Power Transmission Line Fault Detection","authors":"Yue Zhang;Yonghui Xu;Lizhen Cui","doi":"10.26599/IJCS.2024.9100016","DOIUrl":"https://doi.org/10.26599/IJCS.2024.9100016","url":null,"abstract":"As the main channel for energy transmission, the stable operation of transmission lines is crucial for energy supply and economic development. However, various faults such as short circuits, overloads, and poor grounding contacts inevitably occur during the operation of transmission lines. These faults not only affect the power quality but also cause equipment damage, and even lead to fires and safety accidents. Therefore, the research on transmission line fault detection technology is of great significance. This paper analyzes the advantages and disadvantages of existing artificial intelligence-assisted transmission line fault detection technologies, aiming to provide valuable references for the comprehensive realization of intelligent transmission line fault detection and promote further development in this field.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 2","pages":"139-146"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943871","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}

{"title":"Lightweight Human Behavior Recognition Method for Visual Communication AGV Based on CNN-LSTM","authors":"Shuhua Zhao;Jianxin Zhu;Jiang Lu;Zhibo Ju;Dong Wu","doi":"10.26599/IJCS.2024.9100014","DOIUrl":"https://doi.org/10.26599/IJCS.2024.9100014","url":null,"abstract":"Behavior recognition uses deep learning network model to automatically extract the deep features of data, but traditional machine learning algorithms have some problems such as manual feature extraction and poor generalization ability of models. The S-MobileNet is proposed for human behavior recognition. Firstly, the 3D convolution to extract features is used to build a time series model to learn the long-term dependence of human behavior characteristics on time series. Secondly, Long Short-Term Memory (LSTM) is used as the input of multi-layer recurrent neural network time series model, so as to obtain individual dynamic features, and then individual features are aggregated by attention pooling mechanism to obtain corresponding group behavior features. At last, the recognition of individual behavior and group behavior is completed by relying on the characteristics of individual and group behavior. The experiments show that the network in this paper achieves high recognition accuracy on UCF101 and HMDB51 datasets, and the overall recognition rate of proposed model for 13 kinds of human behaviors is 95.3%.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 2","pages":"133-138"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11003456","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943872","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}

{"title":"Remote Monitoring System of Patient Status in Social IoT Environments Using Amazon Web Services Technologies and Smart Health Care","authors":"Amer Tahseen Abu-Jassar;Hani Attar;Ayman Amer;Vyacheslav Lyashenko;Vladyslave Yevsieiev;Ahmed Solyman","doi":"10.26599/IJCS.2023.9100019","DOIUrl":"https://doi.org/10.26599/IJCS.2023.9100019","url":null,"abstract":"This study investigates the problematic characteristics of contemporary methods for remote and portable patient monitoring. The consideration is based on recent breakthroughs in information technology and progressive strategies for processing and storing biomedical data. The proposed system represents the Medicine 4.0 concept's next technological leap. Existing methods for remote and portable monitoring of a patient's status have several vital disadvantages in system flexibility and the convenience of processing and evaluating biomedical data, according to an analysis of these systems. The authors have created a new concept for a Remote Patient Monitoring System (RPMS) that allows for undetectable wear during the patient's daily activities. Small modules comprising a microcontroller and a collection of medical sensors transfer data in real-time via wireless Internet of Things (IoT) technologies to a cloud service for the attending physician's processing and visualization convenience. Based on the proposed concept, the authors created a structural diagram of the experimental RPMS and its built prototype. Amazon Web Services (AWS) is used for the real-time processing of biomedical patient data and its subsequent analysis using a graph-based information visualization system. The performed experimental procedure confirmed that the developed experimental RPMS has minimal latency in transmitting data to AWS; it can alert both the patient and the physician about the need for emergency intervention or treatment adjustments, even if critical indicators are detected. Additionally, the proposed system can incorporate components of expert systems and Artificial Intelligence (AI) systems. The authors advocate using the accomplished system for functional diagnostics specialists, paramedics, and cardiologists in medical facilities and the military medical system for rapid diagnosis and direct monitoring of troops' health state on the battlefield.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 2","pages":"110-125"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11003454","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943929","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}

{"title":"Predictive Emojis for User Cognitive Response to Dynamic Behaviour of Webpages Using Pupil and Click Reinforcement","authors":"Fatima Isiaka","doi":"10.26599/IJCS.2023.9100004","DOIUrl":"https://doi.org/10.26599/IJCS.2023.9100004","url":null,"abstract":"The consequences of a poor user experience are based on the same principles that affect the user experience of any website. These principles span the gap between, for instance, a business webpage and a brick-motor company; the simple reason for this is whether online or in-store the cause or the cognitive processes of the users are similar in certain ways. The main steps towards improving the user experience of websites are through the understanding of the psychology of the users. This can be demonstrated using graphical-based emotion emojis. To understand the correlates and user affective response and how this changes by the dynamic behaviour of webpages, cognitive predictive markers such as bubble emojis are used to model users' emotions to the objects they view on different webpages presented to them. The psychology and website user experience are framed at first impressions, through processing fluency, loading race, the limits of attention, and age of anxiety. This paper demonstrates an effective way of understanding user cognition through eye movement from the webcam and mouse clicking movement from finger touch during the interaction. User-generated data are collected and used as biomakers in form of emojis that relay the users' emotion to the contents they view online. A computational test was carried out to determine the reliability of the proposed model (predictive dynamic control) with a standard artificial neural network and the results show compatibility as compared to state-of-the-art models. During process optimisation and flow, the bubbles seem to appear at undefined area of interest (AOI) of the visual webpages, and the selected URLs of some of these pages appear at random listings as defaults; these are some of the drawbacks of the proposed model. The originality of the project is its ability to automatically call up webpage in real-time with great processing speed and utilise the analytic control to predict users' mood from previous search generated data and at the same time control synchronisation link between pupil changes and click reinforcement kernel.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 2","pages":"126-132"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11003460","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943922","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}

{"title":"B5G Applications and Emerging Services in Smart IoT Environments","authors":"Hani Attar;Mohammed Alghanim;Jafar Ababneh;Khosro Rezaee;Ayat Alrosan;Mohanad A. Deif","doi":"10.26599/IJCS.2024.9100007","DOIUrl":"https://doi.org/10.26599/IJCS.2024.9100007","url":null,"abstract":"So far, the communication standard development requires specific parameters to achieve the requests of the desired application, most frequently, the connection speed rate. On the other hand, the term Beyond the Fifth Generation (B5G) symbolizes certain specifications required to succeed the future-proof of the Fifth Generation (5G), i.e., the predicted high-level parameters, such as ultra-reliable low-latency communications, massive machine-type communications, and improved mobile broadband, which are essential for the expected high-level future applications; consequently, 5G wireless (cellular) networks must be reconsidered precisely and in-depth to cope with the applications' required high-level standard parameters in B5G. Therefore, it is crucial to develop novel wireless access configurations and technologies that utilize additional spectrum. However, this alone is not sufficient for now. Incorporating technologies such as software-defined networking, cloud computing, machine learning, 3D networking, and network function virtualization into B5G networks is imperative due to raised concerns regarding decentralization, transparency, interoperability, privacy, and security. This page provides a comprehensive overview of B5G's design, functionality, and security, as well as its relationship to cloud computing. Furthermore, the proposed study examines the techniques employed for data transmission in B5G applications, such as Vehicle-to-Vehicle (V2V), Device-to-Device (D2D), and Machine to Machine (M2M) transmissions. Lastly, the proposed study focuses on essential technology based software services, such as healthcare, smart grid, tourism, and agricultural services. These services use the advantages of B5G communication networks and cloud computing. So, the proposed work collects all the necessary information for researches and developers in one article, supported by the most up-to-date references.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 2","pages":"79-95"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11003501","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943869","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}

{"title":"Monitoring Changes to Small-Sized Lakes Using Medium Spatial and Temporal Satellite Imagery in the Badain Jaran Desert from 2015 to 2020","authors":"Qinyu Zhao;Luyan Ji;Yonggang Su;Kai Yu;Yongchao Zhao","doi":"10.26599/IJCS.2024.9100025","DOIUrl":"https://doi.org/10.26599/IJCS.2024.9100025","url":null,"abstract":"The Badain Jaran Desert is the second-largest desert in China, and its lakes, which are generally small-sized and highly dynamic, play a significant role for plants and animals in this arid region. Therefore, long-term monitoring of the distribution of lakes in the Badain Jaran Desert with high spatial and temporal resolution is of great importance. However, due to the tradeoff between pixel size and swath width, currently no single satellite sensor can provide such a time series. Thereby, in this study, we focus on applying the deep learning based spatiotemporal fusion method (super-resolution based spatial fusion with Generative Adversarial Network (GAN)) to a low spatial yet high temporal resolution data (i.e., MODIS 250 m daily reflectance time series) and a high spatial yet low temporal resolution data (i.e., Landsat 30 m 16-day reflectance time series) to generate a daily 30 m time series for 37 selected lakes in the Badain Jaran Desert. Then, an automatic water extraction algorithm is proposed, and a daily 30 m water mapping production is generated for our study area from 2015 to 2020. The overall accuracy can reach 0.92, while the average error of lake areas is less than 9.21%, which is much higher than that derived from the MODIS time series. Moreover, based on our daily high spatial resolution results, it is possible to analyze the water phenology for all sizes of lakes in the Badain Jaran Desert. We have performed a detailed analysis of interannual variability and seasonal changes for the selected 37 lakes in the Badain Jaran Desert. The results show that from 2015 to 2020, the shrinkage of the small lakes (<0.5>2</sup>) is more severe than lakes with a larger size. As for seasonal changes, the lake area can be divided into four stages: quick increase due to ice melting from winter to spring, slow decrease due to evaporation from spring to summer, moderate recovery due to the arrival of the rainy season from summer to autumn, and quick decrease due to lake freezing from autumn to winter. Therefore, it is feasible to use spatiotemporal fusion algorithms to generate long-term time series for monitoring the dynamic changes of small lakes in desert areas.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 2","pages":"96-109"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11003457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943921","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}

{"title":"Development and Investigation of Vision System for a Small-Sized Mobile Humanoid Robot in a Smart Environment","authors":"Amer Tahseen Abu-Jassar;Hani Attar;Ayman Amer;Vyacheslav Lyashenko;Vladyslav Yevsieiev;Ahmed Solyman","doi":"10.26599/IJCS.2023.9100018","DOIUrl":"https://doi.org/10.26599/IJCS.2023.9100018","url":null,"abstract":"The conducted research aims to develop a computer vision system for a small-sized mobile humanoid robot. The decentralization of the servomotor control and the computer vision systems is investigated based on the hardware solution point of view, moreover, the required software level to achieve an efficient matched design is obtained. A computer vision system using the upgraded tiny-You Only Look Once (YOLO) network model is developed to allow recognizing and identifying objects and making decisions on interacting with them, which is recommended for crowd environment. During the research, a concept of a computer vision system was developed, which describes the interaction between the main elements, on the basis of which hardware modules were selected to implement the task. A structure of information interaction between hardware modules is proposed, and a connection scheme is developed, on the basis of which a model of a computer vision system is assembled for research, with the required algorithmic and software for solving the problem. To ensure the high speed of the computer vision system based on the ESP32-CAM module, the neural network was improved by replacing the Visual Geometry Group 16 (VGG-16) network as the base network for extracting the functions of the Single Shot Detector (SSD) network model with the tiny-YOLO lightweight network model, which made it possible to preserve the multidimensional structure of the network model feature graph, resulting in increasing the detection accuracy, while significantly reducing the amount of calculations generated by the network operation, thereby significantly increasing the detection speed, due to a limited set of objects. Finally, a number of experiments were carried out, both in static and dynamic environments, which showed a high accuracy of identifications.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 1","pages":"29-43"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10858027","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106333","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}

{"title":"Feature Selection in Socio-Economic Analysis: A Multi-Method Approach for Accurate Predictive Outcomes","authors":"Ahmad Al-Qerem;Ali Mohd Ali;Issam Jebreen;Ahmad Nabot;Mohammed Rajab;Mohammad Alauthman;Amjad Aldweesh;Faisal Aburub;Someah Alangari;Musab Alzgol","doi":"10.26599/IJCS.2023.9100035","DOIUrl":"https://doi.org/10.26599/IJCS.2023.9100035","url":null,"abstract":"Feature selection is a cornerstone in advancing the accuracy and efficiency of predictive models, particularly in nuanced domains like socio-economic analysis. This study explores nine distinct feature selection methods, utilizing a heart disease dataset as a representative model for complex socio-economic systems. Our findings identified four universally recognized features as critical across all selection methods. However, the divergence in significance attributed to other features by different methods underscores the inherent variability in selection techniques. When the top four features were incorporated into twelve classification models, a noticeable surge in predictive accuracy was observed, emphasizing their foundational role in enhancing model outcomes. The variations among methods stress the need for a methodical and discerning approach to feature selection, especially in data-rich socio-economic landscapes. As we venture further into an era defined by data-driven decision-making, rigour and precision in feature selection become indispensable. Future research should extend this approach to broader datasets, ensuring the robustness and adaptability of our findings.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 1","pages":"64-78"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10858028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106334","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}

{"title":"Improving Energy Harvesting System from Ambient RF Sources in Social Systems with Overcrowding","authors":"Ramy Agieb;Ayman Amer;Ibrahim Mansour;Ahmed Solyman;Khalid Yahya;Ahmed Samir","doi":"10.26599/IJCS.2023.9100022","DOIUrl":"https://doi.org/10.26599/IJCS.2023.9100022","url":null,"abstract":"This paper presents a novel approach to enhance energy harvesting systems from ambient Radio Frequency (RF) sources in overcrowded environments. In environments like shopping malls, coffee shops, and airports, where wireless devices are prevalent, the electromagnetic energy emitted by these devices can be harvested and converted into electrical energy to power small devices, specifically those associated with the Social Internet of Things (SIoT). However, due to the high density of devices in such environments, the RF signals can be weak, resulting in low energy harvesting efficiency. This study focuses on developing technologies for wireless power transfer through a radio frequency ambient energy harvesting scheme, specifically designing to improve energy harvesting systems in crowded social environments. Recognizing the growing importance of energy harvesting for low-power devices in intelligent environments, our proposed method utilizes the ambient environment to capture energy in the downlink radio frequency range of the GSM-900 band. The system architecture comprises four main stages: a supercapacitor, a Villard voltage doubler circuit with seven stages, a lumped element matching network, and a microstrip patch antenna. The voltage doubler circuit is designed and simulated using the Agilent Advanced Design System (ADS) 2014 environment, and simulations and tests are conducted across different input power levels. Throughout the study, several key factors are identified as crucial to the system's efficiency, including the frequency band, input power level, voltage doubler circuit design, impedance matching, diode selection, number of rectification stages, and load resistance. The proposed method demonstrates significant potential in enhancing the energy harvesting efficiency from ambient RF sources in crowded social environments. By providing a sustainable power source for SIoT devices in such settings, our approach contributes to the advancement of energy harvesting capabilities and supports the practical implementation of energy-efficient technologies in intelligent and socially interconnected environments.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 1","pages":"13-28"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10858031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106224","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}

{"title":"Long-Term Vital Sign Tracking Study of Depression Patients Based on Wearable Devices","authors":"Yuebo Jin;Yadong Huang","doi":"10.26599/IJCS.2024.9100044","DOIUrl":"https://doi.org/10.26599/IJCS.2024.9100044","url":null,"abstract":"Depression is a critical mental health issue that increasingly affects millions worldwide. Traditional monitoring methods, relying on self-reported symptoms and periodic clinical assessments, are often subjective and infrequent. Wearable devices, offering continuous and real-time data on various physiological parameters, present a promising alternative. These devices provide a comprehensive picture of a patient's condition by tracking vital signs such as heart rate, sleep patterns, and physical activity. Our study utilized wearable devices to monitor 302 hospitalized depression patients over six months. We collected data on heart rate, sleep conditions, and physical activity, which were then correlated with Hamilton Anxiety (HAMA) and Hamilton Depression (HAMD) scales. The results showed significant differences in these vital signs between mild and severe depression cases. The logistic regression model yielded promising results, with an Area Under the Curve (AUC) value of 0.84 on the Receiver Operating Characteristic (ROC) curve, indicating a high level of classification accuracy. The model's performance suggests that the selected features are significantly correlated with depression severity and can effectively aid in clinical classification. In conclusion, wearable devices offer significant advancements in monitoring and managing depression. By integrating continuous physiological data with clinical assessments, these devices can improve the understanding and treatment of depression, potentially transforming mental health care into a more precise, personalized, and proactive field.","PeriodicalId":32381,"journal":{"name":"International Journal of Crowd Science","volume":"9 1","pages":"56-63"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10858029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106301","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}