EAI Endorsed Transactions on Pervasive Health and Technology最新文献

{"title":"A New Deepfake Detection Method Based on Compound Scaling Dual-Stream Attention Network","authors":"Shuya Wang, Chenjun Du, Yunfang Chen","doi":"10.4108/eetpht.10.5912","DOIUrl":"https://doi.org/10.4108/eetpht.10.5912","url":null,"abstract":"INTRODUCTION: Deepfake technology allows for the overlaying of existing images or videos onto target images or videos. The misuse of this technology has led to increasing complexity in information dissemination on the internet, causing harm to personal and societal public interests. OBJECTIVES: To reduce the impact and harm of deepfake as much as possible, an efficient deepfake detection method is needed. METHODS: This paper proposes a deepfake detection method based on a compound scaling dual-stream attention network, which combines a compound scaling module and a dual-stream attention module based on Swin Transformer to detect deepfake videos. In architectural design, we utilize the compound scaling module to extract shallowlevel features from the images and feed them into the deep-level feature extraction layer based on the dual-stream attention module. Finally, the obtained features are passed through a fully connected layer for classification, resulting in the detection outcome. RESULTS: Experiments on the FF++ dataset demonstrate that the deepfake detection accuracy is 95.62%, which shows its superiority to some extent.CONCLUSION: The method proposed in this paper is feasible and can be used to detect deepfake videos or images.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141826837","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":"An Innovative CBR-Enhanced Approach for Skin Cancer Classification using Cascade Forest Model and Convolutional Neural Network with Attention Mechanism","authors":"Safa Gasmi, Akila Djebbar, H. Merouani, Hanene Djedi","doi":"10.4108/eetpht.10.3875","DOIUrl":"https://doi.org/10.4108/eetpht.10.3875","url":null,"abstract":"INTRODUCTION: In recent years, skin cancer has emerged as a pressing concern, necessitating advanced diagnostic and classification techniques.OBJECTIVES: This paper introduces an innovative hybrid approach that combines deep learning and machine learning to enhance the retrieval phase of the Case-Based Reasoning (CBR) system for skin cancer classification.METHODS: The proposed approach leverages a Convolutional Neural Network (CNN) with an attention mechanism for feature extraction, which is used to build the case base. Additionally, it uses a modified cascade forest model, augmented with traditional machine learning classifiers for classification. This modified cascade forest model incorporates the XGBoost model in its initial layer to facilitate more effective ensemble learning and bolster predictive performance. Subsequently, in the following layers, it use the random forest model to capitalize on its ability to handle high-dimensional feature spaces and maintain diversity within the ensemble.RESULTS: Rigorous experimentation on the balanced HAM10000 dermoscopic image dataset, employing the Synthetic Minority Oversampling Technique (SMOTE), demonstrates the superiority of the modified cascade forest model in multi-class skin cancer classification. This model consistently achieves the highest metrics, including accuracy (95.40%), precision (95.49%), F1-Score (95.38%), and recall (95.44%).CONCLUSION: This research highlights the efficacy of the proposed model compared to other classifiers, emphasizing the significance of the modified cascade forest model in enhancing the accuracy and reliability of skin cancer classification.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":" 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141824306","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":"Analysis of the use of electronic medical records and its effect on improving patient care","authors":"Lenka Angelita Kolevic Roca, Carlos Víctor Mora Aguilar, Rosaria Luz Diaz Ramos, Dimna Zoila Alfaro Quezada, Mirelly Velásquez Orellana","doi":"10.4108/eetpht.10.5702","DOIUrl":"https://doi.org/10.4108/eetpht.10.5702","url":null,"abstract":"Introduction: One of the most important contemporary events related to the health field is the implementation of the electronic health record (EHR), which allows the logical and chronological consolidation of information concerning a patient.\u0000Objective: To analyze the influence of the implementation of electronic medical records on the improvement of patient care.\u0000Method: The study corresponds to a quantitative approach, non-experimental design, and causal correlational scope. The population and sample were 94 health and administrative workers of a health center in Metropolitan Lima. The questionnaire had 30 items, with response options using a Likert-type scale.\u0000Results: The use of electronic medical records was found to be 78.7% high, and patient care was found to be 70.2% efficient. It was found that the use of EHRs significantly influences patient care, given that p-value is 0.047<0.05. The dimensions of patient care, reliability, responsiveness, safety, empathy, and tangible aspects also obtained a p-value<0.05.\u0000Conclusions: It was found that most workers positively perceive the use of electronic medical records and that the existence of this system has beneficial effects on patient care, considering that the staff perceives high levels of reliability, responsiveness, safety, empathy, and tangible aspects.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"45 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140981160","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":"Suicidal Ideation Detection and Influential Keyword Extraction from Twitter using Deep Learning (SID)","authors":"Xie-Yi. G.","doi":"10.4108/eetpht.10.6042","DOIUrl":"https://doi.org/10.4108/eetpht.10.6042","url":null,"abstract":"INTRODUCTION: This paper focuses on building a text analytics-based solution to help the suicide prevention communities to detect suicidal signals from text data collected from online platform and take action to prevent the tragedy. \u0000OBJECTIVES: The objective of the paper is to build a suicide ideation detection (SID) model that can classify text as suicidal or non-suicidal and a keyword extractor to extracted influential keywords that are possible suicide risk factors from the suicidal text. \u0000METHODS: This paper proposed an attention-based Bi-LSTM model. An attention layer can assist the deep learning model to capture influential keywords of the model classifying decisions and hence reflects the important keywords from text which highly related to suicide risk factors or reason of suicide ideation that can be extracted from text. \u0000RESULTS: Bi-LSTM with Word2Vec embedding have the highest F1-score of 0.95. Yet, attention-based Bi-LSTM with word2vec embedding that has 0.94 F1-score can produce better accuracy when dealing with new and unseen data as it has a good fit learning curve. \u0000CONCLUSION: The absence of a systematic approach to validate and examine the keyword extracted by the attention mechanism and RAKE algorithm is a gap that needed to be resolved. The future work of this paper can focus on both systematic and standard approach for validating the accuracy of the keywords.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"10 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140982076","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":"Optimal control in models of virus propagation","authors":"Xiuxiu Liu, Elena Gubar","doi":"10.4108/eetpht.10.6041","DOIUrl":"https://doi.org/10.4108/eetpht.10.6041","url":null,"abstract":"Based on the SEIRD model, we consider that when multiple viruses of different virulence coexist, the more virulent virus will reinfect nodes already infected by the less virulent virus, which we call here Superexposed. Based on the state transitions, the corresponding differential equations and cost functions are established, then building the corresponding optimal control problem, where the vaccine efficiency and drug efficiency are controlled variables. This nonlinear optimal control problem is solved by Pontryagin’s maximum principle to finding the structure of the optimal control strategies. Based on the definition of the basic regeneration number, yielding the R0 value for the model, then discussed the final epidemic size. In the numerical analysis section, we validate the accuracy of the structure, fitting the behavior of each state and the effect of different parameter values.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"17 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140982607","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":"Analysis Method of Special Physical Training Mode of Basketball Teams in Colleges Based on WeChat Applet and FTTA Optimised LSTM","authors":"Gang Chen, Shuaishuai Zhang","doi":"10.4108/eetpht.10.5853","DOIUrl":"https://doi.org/10.4108/eetpht.10.5853","url":null,"abstract":"OBJECTIVE: this paper proposes a basketball special physical training mode analysis method based on WeChat applet and optimization algorithm to improve the deep learning network.METHODS: Using the applet data set and the coaches' record data as model input data, the proposed method is used to analyse and thus improve the performance of the basketball team's special physical training pattern.RESULTS: Comparing the analysis effect between FTTA-Attention-LSTM analysis model and LSTM, FTTA-LSTM, FTTA-GRU, FTTA-BiLSTM models, the WeChat mini-program oriented basketball team's special physical fitness training mode analysis index system contains 14 factors affecting the analysis model; in analysing the relationship between the size of FTTA population and Attention-LSTM network hidden layer node number experiments, it was found that the selection of the population size of 80, the number of hidden layer nodes for 90; by analysing the FTTA-Attention-LSTM analysis model and other comparative models, it was found that the analysis accuracy of the FTTA-Attention-LSTM analysis model is the smallest, and the analysis time meets the real-time requirements, controlled within 0.001s.CONCLUSION: In the future, principal component analysis technology can be introduced for feature selection to further achieve intelligence and improve the analysis efficiency of the model.\u0000 ","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"48 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141014909","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":"Designing and Analysing an APP based on \"Internet+\" for Integrating Health Data of University Physical Classes","authors":"Shuaishuai Zhang, Gang Chen","doi":"10.4108/eetpht.10.5856","DOIUrl":"https://doi.org/10.4108/eetpht.10.5856","url":null,"abstract":"INTRODUCTION: University physical education programs still largely use traditional methods without significant innovation in teaching or health evaluation. With the growing capabilities of Internet technology and artificial intelligence, there's a critical need to leverage these advancements to enhance the physical health assessments of college students.OBJECTIVES: The study proposes an integrated APP design for health data collection and analysis both inside and outside physical education classes, utilizing Internet technologies and intelligent learning algorithms. This is aimed at precisely analyzing and improving the health outcomes of university students by fostering more tailored and responsive physical education experiences..METHODS: The method involves constructing an app design analysis index system, integrating a vulture search heuristic optimization algorithm with a convolutional neural network (CNN). This setup uses smart sports APP behavioral data as input to refine and optimize health data integration, aiming to enhance the analysis and feedback mechanisms within university sports programs.RESULTS: The implementation of this method showed that it meets real-time requirements while significantly improving the accuracy and efficiency of integrated APP design analyses for health data. The use of smart algorithms allows for more precise adjustments and feedback in physical education programs, suggesting a substantial improvement over traditional physical health monitoring and evaluation methods.CONCLUSION: The proposed APP design successfully integrates and analyzes health data, enhancing the management and evaluation of physical education programs. It represents a significant step forward in utilizing modern technology to address the stagnation in physical education health monitoring, with potential implications for broader educational and health management practices in universities. Future iterations of the APP could incorporate more diverse data inputs and advanced analytical features to further refine its effectiveness and usability.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"73 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141016665","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":"Bibliometric analysis of publications on neuroscience and noncommunicable diseases in the Scopus database","authors":"Antony Paul Espiritu-Martinez, Miriam Zulema Espinoza-Véliz, Melvi Janett Espinoza-Egoavil, Katerine Karen Gomez-Perez, Karina Liliana Espinoza-Véliz, Linda Flor Villa-Ricapa, Eva Luisa Núñez-Palacios","doi":"10.4108/eetpht.10.5699","DOIUrl":"https://doi.org/10.4108/eetpht.10.5699","url":null,"abstract":"Introduction: The present study aimed to perform a bibliometric analysis of neuroscience and noncommunicable diseases in the Scopus database between 2003 and 2023. Bibliometric analysis served as the main tool to analyze academic production.Methods: 867 papers were selected for the study based on English keywords (\"neuroscience,\" \"noncommunicable,\" and \"diseases\"). Results: The period from 2015 to 2023 accounted for 58% of the total publications, with 503 academic publications, which had the most significant influence on scientific production in terms of percentage increase. The United States accounted for 35.9% of the production. The most relevant publication sources, with n=10 each, were Neuromethods and Neuroscientist. Farooqui, A.A. obtained the most citations (105) in his four papers. Of the total number of papers, 21% were scientific articles, of which 32% pertained to medicine and 20% to neuroscience. Neuroscience and noncommunicable diseases have advanced significantly in terms of thematic variety, authorship, sources, and accessible resources.Conclusions: This bibliometric study provides a solid foundation for future research in the field of neuroscience and noncommunicable diseases, highlighting the importance of this area and its growth in the academic realm..","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"54 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140664655","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":"Status of high-impact scientific publication in nursing in Latin America","authors":"Miriam Zulema Espinoza-Véliz, A. P. Espíritu-Martínez, Melvi Janett Espinoza-Egoavil, Maribel Nerida Usuriaga-Palacios, Enzo Renatto Bazualdo-Fiorini, Jorge Luis Hilario Rivas, David Hugo Bernedo-Moreira","doi":"10.4108/eetpht.10.5705","DOIUrl":"https://doi.org/10.4108/eetpht.10.5705","url":null,"abstract":"INTRODUCTION: The aim of this study was to analyze the situation of high-impact scientific publication in nursing in Latin America between 2003 and 2024\u0000OBJECTIVES: Determine Status of high-impact scientific publishing in nursing.\u0000METHODS: The method quantified scientific productivity using bibliometric data.\u0000RESULTS: A total of 298 Scopus documents were selected for the study based on relevance and English keywords (scientific AND publishing, publication AND nursing). The largest substantial growth in scientific production occurred between 2019 and 2023 (n=112; 37.6%), with Brazil as the most prominent country (n=250 publications; 83.9%). The source Revista Brasileira de Enfermagem presented 33 publications, and Marziale, M.H.P. was the most cited author (103 citations; 4 papers). Most of these papers were scientific papers (85%) in the area of nursing (61%) and medicine (20%). It is concluded that the thematic diversity, authorship, sources and resources have increased, with respect to high impact scientific publication in nursing in Latin America, which allows a broader characterization of scientific production in the region according to its impacts, visibility and importance.\u0000CONCLUSION: Thus, this bibliometric analysis provides a framework for future research documenting a key support that aspires to transform Latin American society into a more just, free and healthy state.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"51 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140667966","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":"Use of wearable technologies in health promotion in Human Medicine students","authors":"Javier Eduardo Curo Yllaconza, Renee Amparo Valle Elescano, Tania Luz Vilchez Cuevas, Mirelly Velásquez Orellana, José Hugo Tezén Campos, Jaime Salazar Montenegro, Dr. Pablo Riquez Livia, Eleazar Fidel Peralta Loayza","doi":"10.4108/eetpht.10.5701","DOIUrl":"https://doi.org/10.4108/eetpht.10.5701","url":null,"abstract":"INTRODUCTION: In the current era marked by rapid technological advances, the integration of wearable devices into everyday life has been a remarkable phenomenon. These devices, ranging from smart watches to physical activity monitors, have gained popularity and have become ubiquitous tools that track various aspects of health and wellness.\u0000OBJECTIVE: To characterize the use of wearable technologies in health promotion in Human Medicine students.\u0000METHODS: The research is characterized by its cross-sectional and quantitative nature, with a basic and descriptive non-experimental design. The study population consisted of 128 students of Human Medicine at a private university located in Arequipa, Peru. Data collection was carried out through the use of surveys and questionnaires.\u0000RESULTS: Regarding the adoption and use of wearable technologies, 35.94% (46) reported a moderate level, 32.81% (42) indicated a high level, while 31.25% (40) indicated a low level. This finding suggests a balanced and non-extreme adoption of wearable technologies among the students examined in the context of health promotion.\u0000CONCLUSIONS: We were able to determine a moderate level of adoption and use of wearable technologies among Human Medicine students to promote health and wellness. This result points to the relevance of these technologies in health-related activities, highlighting a particular emphasis on a moderate level of use.","PeriodicalId":506478,"journal":{"name":"EAI Endorsed Transactions on Pervasive Health and Technology","volume":"39 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140667128","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}