A widespread bacterial or viral infection of the respiratory tract, pneumonia affects many people. particularly in developing and impoverished countries where pollution, unsanitary living conditions, and overcrowding are all too common, as well as a lack of medical infrastructure. Pneumonia produces pleural effusion, which is a condition in which fluids fill the lungsand create breathing problems. Early detection of pneumonia is critical for ensuring a cure and improving survival rates. The most common method for detecting pneumonia is chest X-ray imaging. As opposed to that, examining chest X-rays can be challenging and vulnerable to subjective fluctuation. A computer-aided diagnosis method for automatic pneumonia detection utilizing This research includes the creation of chest Images from X-rays. To evaluate which model is superior, an experiment was conducted utilizing a publicly accessible database on all three models. A Convolutional Neural Network (CNN) model was developed to address the lack of readily available data. together using transfer learning strategies like Mobile Net and VCG. On a dataset of accessible pneumonia X-rays, the method was tested. This research shows which neural network algorithm is optimal for detecting pneumonia, and how medical practitioners might use it in the actual world. Keywords: Pneumonia, Chest X-ray, Deep Learning, Convolutional Neural Network (CNN), Mobile Net, VCG, ReLU, Max pooling.
肺炎是一种广泛存在于呼吸道的细菌或病毒感染，影响着许多人，尤其是在发展中国家和贫困国家，污染、不卫生的生活条件和拥挤不堪的环境以及医疗基础设施的缺乏非常普遍。肺炎会产生胸腔积液，积液会充满肺部，造成呼吸困难。早期发现肺炎对于确保治愈和提高存活率至关重要。检测肺炎最常用的方法是胸部 X 光成像。与之相比，检查胸部 X 光片可能具有挑战性，而且容易受到主观波动的影响。利用计算机辅助诊断方法自动检测肺炎的研究包括从 X 光片创建胸部图像。为了评估哪种模型更优越，我们利用一个可公开访问的数据库对所有三种模型进行了实验。为了解决缺乏现成数据的问题，我们开发了一个卷积神经网络（CNN）模型。该方法在可获取的肺炎 X 光片数据集上进行了测试。这项研究显示了哪种神经网络算法最适合检测肺炎，以及医疗从业人员在实际工作中如何使用这种算法。关键词肺炎、胸部 X 光片、深度学习、卷积神经网络（CNN）、移动网络、VCG、ReLU、最大池化。
{"title":"Comparative Analysis of Pneumonia Detection from Chest X-Ray Images Using CNN And Transfer Learning","authors":"Naveen Kumar M, Ushasree, Che Fuzlina Fuad","doi":"10.61453/jods.v2024no20","DOIUrl":"https://doi.org/10.61453/jods.v2024no20","url":null,"abstract":"A widespread bacterial or viral infection of the respiratory tract, pneumonia affects many people. particularly in developing and impoverished countries where pollution, unsanitary living conditions, and overcrowding are all too common, as well as a lack of medical infrastructure. Pneumonia produces pleural effusion, which is a condition in which fluids fill the lungsand create breathing problems. Early detection of pneumonia is critical for ensuring a cure and improving survival rates. The most common method for detecting pneumonia is chest X-ray imaging. As opposed to that, examining chest X-rays can be challenging and vulnerable to subjective fluctuation. A computer-aided diagnosis method for automatic pneumonia detection utilizing This research includes the creation of chest Images from X-rays. To evaluate which model is superior, an experiment was conducted utilizing a publicly accessible database on all three models. A Convolutional Neural Network (CNN) model was developed to address the lack of readily available data. together using transfer learning strategies like Mobile Net and VCG. On a dataset of accessible pneumonia X-rays, the method was tested. This research shows which neural network algorithm is optimal for detecting pneumonia, and how medical practitioners might use it in the actual world. Keywords: Pneumonia, Chest X-ray, Deep Learning, Convolutional Neural Network (CNN), Mobile Net, VCG, ReLU, Max pooling.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141850520","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}
Tri Susilowati, Sri Hartati, Mardiyanto, Bimo Bagus Prabowo
Every Government Institution cannot be separated from carrying out daily administrative activities. Manuscripts or recordings of documents or information, including text, images,and sound recordings, are called archives because archives are records of every activity carried out. Currently, the East Pringsewu sub-district office for filing letters and other activities still uses manual methods. The implementation of E-Government is expected to enable all service activities to the community to be carried out electronically, thereby simplifying policy and service functions. The data collection methods used in this writing are observation, documentation, interviews, and literature study. The SDLC (System Development Life Cycle) method is used in this research, namely a systematic approach to planning, designing, developing, testing,and maintaining software systems. Based on needs analysis, the system developed focuses on managing population data, archiving,and correspondence related to village authority. Before implementing the system, it is necessary to design the system. When designing a system, use the Unified Modeling Language (UML) approach using Use Case Diagrams, Activity Diagrams, and Class Diagrams. Use case diagrams to describe the interaction between users and the system being developed. This research uses the PHP programming language and Visual Studio Code as a text editor and MySQL DBMS. Applications can be used as a medium for implementing subdistrict or village development with information technology and supporting the progress of subdistricts or villages byGovernment recommendations in developing E-Government.
每个政府机构都离不开日常行政活动。文件或信息的手稿或记录，包括文本、图像和录音，都被称为档案，因为档案是每项活动的记录。目前，东普林西乌分区办公室的信件归档和其他活动仍采用手工方式。电子政务的实施有望使社区的所有服务活动以电子方式进行，从而简化政策和服务功能。本文采用的数据收集方法包括观察法、文献法、访谈法和文献研究法。本研究采用了 SDLC（系统开发生命周期）方法，即规划、设计、开发、测试和维护软件系统的系统方法。根据需求分析，所开发的系统侧重于管理人口数据、档案和与村级权力有关的信函。在实施系统之前，有必要对系统进行设计。在设计系统时，应使用统一建模语言（UML）方法，使用用例图、活动图和类图。用例图用于描述用户与正在开发的系统之间的交互。本研究使用 PHP 编程语言和 Visual Studio Code 作为文本编辑器，并使用 MySQL DBMS。政府在发展电子政务方面的建议：应用软件可用作利用信息技术实施分区或村庄发展的媒介，并支持分区或村庄的进步。
{"title":"Improving the Community Services through Electronic Management of East Pringsewu Subdistrict Administration","authors":"Tri Susilowati, Sri Hartati, Mardiyanto, Bimo Bagus Prabowo","doi":"10.61453/jods.v2024no18","DOIUrl":"https://doi.org/10.61453/jods.v2024no18","url":null,"abstract":"Every Government Institution cannot be separated from carrying out daily administrative activities. Manuscripts or recordings of documents or information, including text, images,and sound recordings, are called archives because archives are records of every activity carried out. Currently, the East Pringsewu sub-district office for filing letters and other activities still uses manual methods. The implementation of E-Government is expected to enable all service activities to the community to be carried out electronically, thereby simplifying policy and service functions. The data collection methods used in this writing are observation, documentation, interviews, and literature study. The SDLC (System Development Life Cycle) method is used in this research, namely a systematic approach to planning, designing, developing, testing,and maintaining software systems. Based on needs analysis, the system developed focuses on managing population data, archiving,and correspondence related to village authority. Before implementing the system, it is necessary to design the system. When designing a system, use the Unified Modeling Language (UML) approach using Use Case Diagrams, Activity Diagrams, and Class Diagrams. Use case diagrams to describe the interaction between users and the system being developed. This research uses the PHP programming language and Visual Studio Code as a text editor and MySQL DBMS. Applications can be used as a medium for implementing subdistrict or village development with information technology and supporting the progress of subdistricts or villages byGovernment recommendations in developing E-Government.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141850020","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}
Achmad Nopransyah, Tri Basuki Kurniawan, Misinem, Izman Hardiansyah, E. S. Negara
Urbanization frequently gives rise to substantial environmental issues, namely in waste management and water quality maintenance. Gross Pollutant Traps (GPTs) are essential in urban stormwater management as they effectively capture substantial pollutants before they enterthe centralwater bodies. Nevertheless, the irregular buildup of trash caused by fluctuating rainfall intensity hinders the effective transfer of garbage from GPTs to their ultimate disposal locations. This research presents a holistic approach toenhancing the efficiency of waste transportation by improving route and load planning. The model utilizes machine learning techniques to forecast the quantity of waste collected by GPTs. We have created an optimization algorithm that usesthe forecast outcome from a prior research dataset. This algorithm is designed to efficiently plan the routes and loads for trucks responsible for transporting waste to its final disposal location. The optimization process consideredthe estimated amounts of garbage, the capacities of the vehicles, and the locations of the disposal sitesto reduce transportation expenses and save time. The system adaptively optimized routes using real-time data on the vehicle'sorigin and destination, ensuring effective allocation of resources and prompt garbage removal. Installingthis approach resulted in a substantial decrease in transportation expenses and enhanced compliance with waste pickup timetables. The integration of predictive modelingand route optimization is enhancing urban trash management. Accurate garbage quantity forecasts and optimized transportation logistics can enable municipalities to deploy resources more effectively, decrease operational costs, and improve environmental protection. We chose a subset of 7 days, equivalent to one week, from the projected dataset for our experiment.Subsequently, we conductednumerous trials involving various waste disposalfrequencies. The findings suggest that waste disposalevery four(4) days is the most advantageous approach. Still, itperforms similarlyto waste disposalevery three (3)days and has negligible environmental consequences. Hence, we select to execute the optimal solution for three(3) days, as it provides exceptional performancewhen consideringthe influence of natural pollution.
{"title":"Efficient Model for Waste Load and RouteOptimization","authors":"Achmad Nopransyah, Tri Basuki Kurniawan, Misinem, Izman Hardiansyah, E. S. Negara","doi":"10.61453/jods.v2024no21","DOIUrl":"https://doi.org/10.61453/jods.v2024no21","url":null,"abstract":"Urbanization frequently gives rise to substantial environmental issues, namely in waste management and water quality maintenance. Gross Pollutant Traps (GPTs) are essential in urban stormwater management as they effectively capture substantial pollutants before they enterthe centralwater bodies. Nevertheless, the irregular buildup of trash caused by fluctuating rainfall intensity hinders the effective transfer of garbage from GPTs to their ultimate disposal locations. This research presents a holistic approach toenhancing the efficiency of waste transportation by improving route and load planning. The model utilizes machine learning techniques to forecast the quantity of waste collected by GPTs. We have created an optimization algorithm that usesthe forecast outcome from a prior research dataset. This algorithm is designed to efficiently plan the routes and loads for trucks responsible for transporting waste to its final disposal location. The optimization process consideredthe estimated amounts of garbage, the capacities of the vehicles, and the locations of the disposal sitesto reduce transportation expenses and save time. The system adaptively optimized routes using real-time data on the vehicle'sorigin and destination, ensuring effective allocation of resources and prompt garbage removal. Installingthis approach resulted in a substantial decrease in transportation expenses and enhanced compliance with waste pickup timetables. The integration of predictive modelingand route optimization is enhancing urban trash management. Accurate garbage quantity forecasts and optimized transportation logistics can enable municipalities to deploy resources more effectively, decrease operational costs, and improve environmental protection. We chose a subset of 7 days, equivalent to one week, from the projected dataset for our experiment.Subsequently, we conductednumerous trials involving various waste disposalfrequencies. The findings suggest that waste disposalevery four(4) days is the most advantageous approach. Still, itperforms similarlyto waste disposalevery three (3)days and has negligible environmental consequences. Hence, we select to execute the optimal solution for three(3) days, as it provides exceptional performancewhen consideringthe influence of natural pollution.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"1989 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141852164","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}
Tam/Do Thi Thanh, Thuy/Nguyen Thi Thu, Trang/Nguyen Thi Van
In Vietnam, digital transformation has been taking place strongly in all fields, especially education. Universities are very interested and focused on promoting digital transformation activities at their facilities. Students are individuals who participateand directly benefit from this process. The question is how competent students are when participating in digital transformation at the institution. This article focuses on researching the digital transformation competencyof Vietnamese students in general, and at Commerce Universityin particular. From there, it provides educational institutions with theperspective of the digital transformation competencyof students. Especially, based on experiments conducted with 405 students at the Universities of Commerce, the research group applied the Exploratory Factor Analysis (EFA) method and multiple linear regression to identify seven factors influencingdigital transformation competence: "Interest", "Usefulness", "Importance", "Personal capacity", "Relationship", "University"and these seven factors explained 71.7% of the variation in digital transformation competence. In summary, the research provides support for educational institutions to develop plans for enhancing the digital transformation competency of studentsin general and at Thuongmai University in particular.
{"title":"Analyzing the Digital Transformation Competence of Vietnamese Students Using Exploratory Factor Analysis (EFA)","authors":"Tam/Do Thi Thanh, Thuy/Nguyen Thi Thu, Trang/Nguyen Thi Van","doi":"10.61453/jods.v2024no15","DOIUrl":"https://doi.org/10.61453/jods.v2024no15","url":null,"abstract":"In Vietnam, digital transformation has been taking place strongly in all fields, especially education. Universities are very interested and focused on promoting digital transformation activities at their facilities. Students are individuals who participateand directly benefit from this process. The question is how competent students are when participating in digital transformation at the institution. This article focuses on researching the digital transformation competencyof Vietnamese students in general, and at Commerce Universityin particular. From there, it provides educational institutions with theperspective of the digital transformation competencyof students. Especially, based on experiments conducted with 405 students at the Universities of Commerce, the research group applied the Exploratory Factor Analysis (EFA) method and multiple linear regression to identify seven factors influencingdigital transformation competence: \"Interest\", \"Usefulness\", \"Importance\", \"Personal capacity\", \"Relationship\", \"University\"and these seven factors explained 71.7% of the variation in digital transformation competence. In summary, the research provides support for educational institutions to develop plans for enhancing the digital transformation competency of studentsin general and at Thuongmai University in particular.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"21 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141846124","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}
M. F. F. Mardianto, Fajri Juli Rahman Nur Zendrato, Suci Rahmadani, Filzah Syakirah
Zero hunger is one of the goals that is still being realized in the Sustainable Development Goals (SDGs). With conditions in Indonesia, which currently occupies fourth place in the amount of food waste worldwide, with a weight reaching 20.93 tons per year. This is certainly a serious enough problem to realize sustainable development. Indonesia, which is currently dominated by Gen Z, certainly needs to pay more attention to this food waste so that it doesn't continue in the future. This problem makes it important to analyze the factors that influence Gen Z Indonesia in reducing food waste. This research aims to form a structural model that explains the factors that influence Gen Z in reducing food waste. The variables used in this research are the influence of social media content, millennial eating manners, food consumption efficiency, the role of social demographics, and commitment to reducing food waste. which was analyzed using the Structural Equation Modeling Partial Least Square (SEM-PLS) method. The research results show that the factors that influence Gen Z are the influence of social media content and the role of social demographics. Through this research, recommendations for activities related to efforts to reduce food waste based on SEM-PLS can be formulated torealize one of the goals of sustainable development.
零饥饿是可持续发展目标（SDGs）中仍在实现的目标之一。目前，印度尼西亚的食物浪费量在全球排名第四，每年达到 20.93 吨。要实现可持续发展，这无疑是一个足够严重的问题。印尼目前以 Z 世代为主，当然需要更加关注这些食物浪费问题，以免将来继续发生。因此，分析影响印尼 Z 世代减少食物浪费的因素就显得尤为重要。本研究旨在形成一个结构模型，解释影响 Z 世代减少食物浪费的因素。本研究中使用的变量包括社交媒体内容的影响、千禧一代的饮食习惯、食物消费效率、社会人口统计学的作用以及减少食物浪费的承诺，并使用结构方程模型部分最小二乘法（SEM-PLS）进行分析。研究结果表明，影响 Z 世代的因素是社交媒体内容的影响和社会人口统计学的作用。通过这项研究，可以在 SEM-PLS 的基础上为减少食物浪费的相关活动提出建议，以实现可持续发展的目标之一。
{"title":"Analyzing Factors That Influence the Indonesia’s Gen Z in Reducing Food Waste","authors":"M. F. F. Mardianto, Fajri Juli Rahman Nur Zendrato, Suci Rahmadani, Filzah Syakirah","doi":"10.61453/jods.v2024no14","DOIUrl":"https://doi.org/10.61453/jods.v2024no14","url":null,"abstract":"Zero hunger is one of the goals that is still being realized in the Sustainable Development Goals (SDGs). With conditions in Indonesia, which currently occupies fourth place in the amount of food waste worldwide, with a weight reaching 20.93 tons per year. This is certainly a serious enough problem to realize sustainable development. Indonesia, which is currently dominated by Gen Z, certainly needs to pay more attention to this food waste so that it doesn't continue in the future. This problem makes it important to analyze the factors that influence Gen Z Indonesia in reducing food waste. This research aims to form a structural model that explains the factors that influence Gen Z in reducing food waste. The variables used in this research are the influence of social media content, millennial eating manners, food consumption efficiency, the role of social demographics, and commitment to reducing food waste. which was analyzed using the Structural Equation Modeling Partial Least Square (SEM-PLS) method. The research results show that the factors that influence Gen Z are the influence of social media content and the role of social demographics. Through this research, recommendations for activities related to efforts to reduce food waste based on SEM-PLS can be formulated torealize one of the goals of sustainable development.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"79 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141841417","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}
Trang/Nguyen Thi Van, Thuy/Nguyen Thi Thu, Tam/Do Thi Thanh
In recent years, Tiktok Shop, a social networking platform thatwas born, has been changing the landscape of the e-commerce market. The way of shopping through short videos is a new method of shopping and the key to the success of TikTok. When customers watch short videos, TikTok will build on consumer habits and journeys to better meet user needs. The article analyzed the influence of 9 factors on the purchase intention of users based on the combination of the Theory of Reasoned Action (TRA) and the Technology Acceptance Model (TAM). The result shows that there are 4 factors that directly and positively affect shopping behavior: "Opinion of the reference group", "My own beliefs", "Videomaker", and "Perceived value". Thus, the article proposes appropriate and practical solutions to help sellers better understand customer psychology and have strategies to keep the consumers and increase sales efficiency.
{"title":"Researching Factors that Affect the Shopping Decisions of Shopping in Tiktok","authors":"Trang/Nguyen Thi Van, Thuy/Nguyen Thi Thu, Tam/Do Thi Thanh","doi":"10.61453/jods.v2024no16","DOIUrl":"https://doi.org/10.61453/jods.v2024no16","url":null,"abstract":"In recent years, Tiktok Shop, a social networking platform thatwas born, has been changing the landscape of the e-commerce market. The way of shopping through short videos is a new method of shopping and the key to the success of TikTok. When customers watch short videos, TikTok will build on consumer habits and journeys to better meet user needs. The article analyzed the influence of 9 factors on the purchase intention of users based on the combination of the Theory of Reasoned Action (TRA) and the Technology Acceptance Model (TAM). The result shows that there are 4 factors that directly and positively affect shopping behavior: \"Opinion of the reference group\", \"My own beliefs\", \"Videomaker\", and \"Perceived value\". Thus, the article proposes appropriate and practical solutions to help sellers better understand customer psychology and have strategies to keep the consumers and increase sales efficiency.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"1 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141845283","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}
Akbar rizki Ramadhan, Tri Basuki Kurniawan, Misinem, Izman Hardiansyah, E. S. Negara
The Sultan Mahmud Badaruddin (SMB) II Palembang Meteorological Station is a technical implementation unit (UPT) of the Meteorology, Climatology, and Geophysics Agency (BMKG) that plays a role in disseminating actual weather information, particularly at SMBII Palembang Airport. Various weather parameters are observed, one of which is wind speed. During the take-off and landing processes, wind speed is a crucial parameter used by airport personnel, including pilots and air traffic controllers (ATC). This study focuses on analyzingand evaluating three deep learning methods using the architectures of LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), and BiLSTM (Bidirectional Long Short Term Memory). Time series data such as air pressure, rainfall, humidity, and temperature are used as predictors. The data is sourced from the AWOS (Automatic Weather Observation System) device. After processing the data using deep learning methods with the architectures above, an analysis will be conducted to determine which architecture model is the most accurate based on the lowest loss error rate in forecasting wind speed at SMB II Palembang Airport. The results show that the GRU deep learning architecture has the lowest loss value compared to the LSTM and BiLSTM architectures so that it can produce better wind speed forecasts in the next 12 hours and 24 hours, with RMSE of 1.62 and 1.77, respectively
{"title":"Deep Learning Techniques for Wind Speed Forecasting at Palembang Airport","authors":"Akbar rizki Ramadhan, Tri Basuki Kurniawan, Misinem, Izman Hardiansyah, E. S. Negara","doi":"10.61453/jods.v2024no23","DOIUrl":"https://doi.org/10.61453/jods.v2024no23","url":null,"abstract":"The Sultan Mahmud Badaruddin (SMB) II Palembang Meteorological Station is a technical implementation unit (UPT) of the Meteorology, Climatology, and Geophysics Agency (BMKG) that plays a role in disseminating actual weather information, particularly at SMBII Palembang Airport. Various weather parameters are observed, one of which is wind speed. During the take-off and landing processes, wind speed is a crucial parameter used by airport personnel, including pilots and air traffic controllers (ATC). This study focuses on analyzingand evaluating three deep learning methods using the architectures of LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), and BiLSTM (Bidirectional Long Short Term Memory). Time series data such as air pressure, rainfall, humidity, and temperature are used as predictors. The data is sourced from the AWOS (Automatic Weather Observation System) device. After processing the data using deep learning methods with the architectures above, an analysis will be conducted to determine which architecture model is the most accurate based on the lowest loss error rate in forecasting wind speed at SMB II Palembang Airport. The results show that the GRU deep learning architecture has the lowest loss value compared to the LSTM and BiLSTM architectures so that it can produce better wind speed forecasts in the next 12 hours and 24 hours, with RMSE of 1.62 and 1.77, respectively","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"2018 31","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141851621","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}
Aqil Azmi Reswara, Nadhira Safa Kamiilah, Marshanda Aprilia, Shalwa Oktavrilia Kusuma, M. F. Fadillah Mardianto, Ardi Kurniawan
Globalization has removed barriers between countries, particularly in the field of food. One of the main impacts of this phenomenon is the entry of foreign food and beverage brands into domestic markets, including brands from the United States. The United States (US) supports Israel in its conflict with Palestine, which is contrary to Indonesia's stance. Therefore, an analysis was conducted on the perception of Indonesian society towards American brands and how this affects the bilateral cooperation betweenthe two countries. The method used was descriptive quantitative, and data analysis was performed using Structural Equation Modeling Partial Least Square (SEM-PLS) with a sample of 200 respondents. The results of this study showed an R-square value of 10.22% without a mediating variable and 49.87% when including a mediating variable. This value indicates that incorporating the mediating variable into the model increases the explained variability of the model to 49.87%, while the remainder can be explained by other variables.
{"title":"Analysis of Indonesian Public Perception on the Influence of American Food Brands with the Indonesia-America Cooperation Relationship Using SEM-PLS","authors":"Aqil Azmi Reswara, Nadhira Safa Kamiilah, Marshanda Aprilia, Shalwa Oktavrilia Kusuma, M. F. Fadillah Mardianto, Ardi Kurniawan","doi":"10.61453/jods.v2024no13","DOIUrl":"https://doi.org/10.61453/jods.v2024no13","url":null,"abstract":"Globalization has removed barriers between countries, particularly in the field of food. One of the main impacts of this phenomenon is the entry of foreign food and beverage brands into domestic markets, including brands from the United States. The United States (US) supports Israel in its conflict with Palestine, which is contrary to Indonesia's stance. Therefore, an analysis was conducted on the perception of Indonesian society towards American brands and how this affects the bilateral cooperation betweenthe two countries. The method used was descriptive quantitative, and data analysis was performed using Structural Equation Modeling Partial Least Square (SEM-PLS) with a sample of 200 respondents. The results of this study showed an R-square value of 10.22% without a mediating variable and 49.87% when including a mediating variable. This value indicates that incorporating the mediating variable into the model increases the explained variability of the model to 49.87%, while the remainder can be explained by other variables.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"65 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141841566","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}
Classification is a process of grouping or placing data into appropriate categories or classes based on specificattributes or features to predict labels or classes of new data based on patternsobserved from previously trained data. Implementing this process uses classification algorithms such asNaïve Bayes, Support Vector Machine,and Random Forest. However, the classification algorithm cannotclassify data optimally due to the challenges in dealing with variousdata sets. Not all available featureswillmake a solidcontribution to the label of the data class, often in the form of noise or interference. For this reason, it is necessary to carry out a feature selection process. Currently, many feature selection processes have been carried out using correlation values from chi-square and gain-information, but the accuracy of the resultsis often still not good enough. This is because the chi-square and gain-information values are fixed. So,the selection of features is minimaland is not based on the previous learning process or what is known as heuristics. For this reason, in this research,several auxiliary algorithms are introduced to improve the performance of the classification algorithm, namely the meta-heuristic algorithm. Meta-heuristic algorithms are search techniques used to solve complexoptimization problems, and these algorithms can help provide reasonable solutions in a shorter time thanexact methods. In its operation, the metaheuristic algorithm optimizes the feature selection process,which will later be processed using the classification algorithm.Three (3) meta-heuristics were implemented, namely Genetic Algorithm, Particle Swarm Optimization, and Cuckoo Search Algorithm; the experiment was conducted, and the results were collected and analyzed. The result shows that combining Naive Bayes and Genetic Algorithmgives the best performance regarding higher accuracy improvementat +23.77%.
{"title":"Enhancing Classification Algorithms with Metaheuristic Technique","authors":"","doi":"10.61453/jods.v2024no22","DOIUrl":"https://doi.org/10.61453/jods.v2024no22","url":null,"abstract":"Classification is a process of grouping or placing data into appropriate categories or classes based on specificattributes or features to predict labels or classes of new data based on patternsobserved from previously trained data. Implementing this process uses classification algorithms such asNaïve Bayes, Support Vector Machine,and Random Forest. However, the classification algorithm cannotclassify data optimally due to the challenges in dealing with variousdata sets. Not all available featureswillmake a solidcontribution to the label of the data class, often in the form of noise or interference. For this reason, it is necessary to carry out a feature selection process. Currently, many feature selection processes have been carried out using correlation values from chi-square and gain-information, but the accuracy of the resultsis often still not good enough. This is because the chi-square and gain-information values are fixed. So,the selection of features is minimaland is not based on the previous learning process or what is known as heuristics. For this reason, in this research,several auxiliary algorithms are introduced to improve the performance of the classification algorithm, namely the meta-heuristic algorithm. Meta-heuristic algorithms are search techniques used to solve complexoptimization problems, and these algorithms can help provide reasonable solutions in a shorter time thanexact methods. In its operation, the metaheuristic algorithm optimizes the feature selection process,which will later be processed using the classification algorithm.Three (3) meta-heuristics were implemented, namely Genetic Algorithm, Particle Swarm Optimization, and Cuckoo Search Algorithm; the experiment was conducted, and the results were collected and analyzed. The result shows that combining Naive Bayes and Genetic Algorithmgives the best performance regarding higher accuracy improvementat +23.77%.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"89 S1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141842543","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}
Most studies have failed to focus on geriatric diseases in the present era of quick advancement in medical science. Diseases like Parkinson’s display their symptoms at a later stage and make a complete recovery almost doubtful. Parkinson’s disease is a neurodegenerative disorder that affects movement and motor control systems. It is named after Dr. James Parkinson, the first person affected by this disease. Parkinson’s slowly worsens over time, leading to a variety of syndromes that can impact a person’s daily life activities. More than 95% of Parkinson’s Disease (PD) patients stated that they have exhibited voice impairment and micrographic disability. This model takes advantage of both advanced machine learning algorithms and modern image processing techniques, resulting in effectiveand efficient predictionPD. To further enhance the accuracy of the model, we have incorporated additional algorithms such as Random Forest and K-nearest Neighbour. Random forest classifier has a detection accuracy of 92%and sensitivity of 0.95%. The performance has been assessed with a reliable dataset from the University of California Irvine Machine Learning repository for voice parameters and a dataset from Kaggle for Handwriting images which includes wavy images and spiral images. Our proposed model has achieved the highest accuracy of 95% which outperformed the previous model or experiment on the same dataset.
{"title":"Predicting Parkinson’s Disease Using Machine Learning with Voice Parameters and Handwriting Images","authors":"Pruthvi H.C., U. R., Harprith Kaur","doi":"10.61453/jods.v2024no19","DOIUrl":"https://doi.org/10.61453/jods.v2024no19","url":null,"abstract":"Most studies have failed to focus on geriatric diseases in the present era of quick advancement in medical science. Diseases like Parkinson’s display their symptoms at a later stage and make a complete recovery almost doubtful. Parkinson’s disease is a neurodegenerative disorder that affects movement and motor control systems. It is named after Dr. James Parkinson, the first person affected by this disease. Parkinson’s slowly worsens over time, leading to a variety of syndromes that can impact a person’s daily life activities. More than 95% of Parkinson’s Disease (PD) patients stated that they have exhibited voice impairment and micrographic disability. This model takes advantage of both advanced machine learning algorithms and modern image processing techniques, resulting in effectiveand efficient predictionPD. To further enhance the accuracy of the model, we have incorporated additional algorithms such as Random Forest and K-nearest Neighbour. Random forest classifier has a detection accuracy of 92%and sensitivity of 0.95%. The performance has been assessed with a reliable dataset from the University of California Irvine Machine Learning repository for voice parameters and a dataset from Kaggle for Handwriting images which includes wavy images and spiral images. Our proposed model has achieved the highest accuracy of 95% which outperformed the previous model or experiment on the same dataset.","PeriodicalId":15636,"journal":{"name":"Journal of data science","volume":"82 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141842686","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：