Yang Zhang, Hangyu Xie, Shikai Zhuang, Xiaoan Zhan
This paper introduces the application of generative adversarial networks (GANs) in image processing and optimization. GANs model can generate realistic images by co-training generator and discriminator, and achieve remarkable results in image restoration tasks. CATGAN and DCGAN are two commonly used GAN models applied to image classification and image restoration respectively. In addition, the global and local image patching methods can effectively fill the missing areas in the image and show good results in the restoration of large images. In conclusion, the image processing and optimization method based on GANs has shown great potential in practice and provides beneficial insight for future research and application in the field of image processing.
本文介绍了生成式对抗网络（GANs）在图像处理和优化中的应用。GANs 模型可以通过联合训练生成器和判别器生成逼真的图像，并在图像复原任务中取得显著效果。CATGAN 和 DCGAN 是两种常用的 GAN 模型，分别应用于图像分类和图像修复。此外，全局和局部图像修补方法能有效填补图像中的缺失区域，在大图像的修复中表现出良好的效果。总之，基于 GANs 的图像处理和优化方法在实践中展现出了巨大的潜力，为今后图像处理领域的研究和应用提供了有益的启示。
{"title":"Image Processing and Optimization Using Deep Learning-Based Generative Adversarial Networks (GANs)","authors":"Yang Zhang, Hangyu Xie, Shikai Zhuang, Xiaoan Zhan","doi":"10.60087/jaigs.v5i1.163","DOIUrl":"https://doi.org/10.60087/jaigs.v5i1.163","url":null,"abstract":"This paper introduces the application of generative adversarial networks (GANs) in image processing and optimization. GANs model can generate realistic images by co-training generator and discriminator, and achieve remarkable results in image restoration tasks. CATGAN and DCGAN are two commonly used GAN models applied to image classification and image restoration respectively. In addition, the global and local image patching methods can effectively fill the missing areas in the image and show good results in the restoration of large images. In conclusion, the image processing and optimization method based on GANs has shown great potential in practice and provides beneficial insight for future research and application in the field of image processing.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"7 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141357158","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}
Shuying Dai, Keqin Li, Zhuolun Luo, Peng Zhao, Bo Hong, Armando Zhu, Jiabei Liu
This paper delves into the practical applications and effectiveness of two prominent text representation methods, the Bag-of-Words (BoW) model and Term Frequency-Inverse Document Frequency (TF-IDF), in the realm of Natural Language Processing (NLP). It commences with an introductory overview of NLP and its pivotal role in the broader field of Artificial Intelligence (AI), elucidating the importance of enabling computers to comprehend and manipulate human language. Subsequently, a comprehensive elucidation of the underlying principles and implementation of these two methods is provided. By conducting a comparative analysis of their respective strengths and weaknesses, the paper endeavors to ascertain the most suitable model for a diverse range of scenarios. The study reveals that while the BoW model proves to be effective for tasks involving short text classification, TF-IDF emerges as the preferred choice for applications such as search engines and keyword extraction. This is attributed to TF-IDF's ability to discern the significance of words within a document in relation to a corpus, thereby mitigating the influence of common but less meaningful words. In conclusion, the paper highlights the significance of AI advancements in shaping the future landscape of NLP. The integration of neural networks and deep learning has revolutionized the field, enabling more sophisticated text representations and enhancing performance in areas such as speech recognition, machine translation, and sentiment analysis. The paper underscores the dynamic nature of NLP and its continual evolution in tandem with AI technologies, offering promising prospects for future research and application development.
{"title":"AI-based NLP section discusses the application and effect of bag-of-words models and TF-IDF in NLP tasks","authors":"Shuying Dai, Keqin Li, Zhuolun Luo, Peng Zhao, Bo Hong, Armando Zhu, Jiabei Liu","doi":"10.60087/jaigs.v5i1.149","DOIUrl":"https://doi.org/10.60087/jaigs.v5i1.149","url":null,"abstract":"This paper delves into the practical applications and effectiveness of two prominent text representation methods, the Bag-of-Words (BoW) model and Term Frequency-Inverse Document Frequency (TF-IDF), in the realm of Natural Language Processing (NLP). It commences with an introductory overview of NLP and its pivotal role in the broader field of Artificial Intelligence (AI), elucidating the importance of enabling computers to comprehend and manipulate human language. Subsequently, a comprehensive elucidation of the underlying principles and implementation of these two methods is provided. By conducting a comparative analysis of their respective strengths and weaknesses, the paper endeavors to ascertain the most suitable model for a diverse range of scenarios. The study reveals that while the BoW model proves to be effective for tasks involving short text classification, TF-IDF emerges as the preferred choice for applications such as search engines and keyword extraction. This is attributed to TF-IDF's ability to discern the significance of words within a document in relation to a corpus, thereby mitigating the influence of common but less meaningful words. In conclusion, the paper highlights the significance of AI advancements in shaping the future landscape of NLP. The integration of neural networks and deep learning has revolutionized the field, enabling more sophisticated text representations and enhancing performance in areas such as speech recognition, machine translation, and sentiment analysis. The paper underscores the dynamic nature of NLP and its continual evolution in tandem with AI technologies, offering promising prospects for future research and application development.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"62 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141280106","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}
Peng Zhao, Keqin Li, Bo Hong, Armando Zhu, Jiabei Liu, Shuying Dai
In order to cope with the task allocation in national economic mobilization, a task allocation planning method based on Hierarchical Task Network (HTN) for national economic mobilization is proposed. An HTN planning algorithm is proposed to solve and optimize task allocation, and an algorithm is designed to solve resource shortage. Finally, a case study verifies the effectiveness of the proposed method based on a real task allocation case in national economic mobilization.
{"title":"Task allocation planning based on hierarchical task network for national economic mobilization","authors":"Peng Zhao, Keqin Li, Bo Hong, Armando Zhu, Jiabei Liu, Shuying Dai","doi":"10.60087/jaigs.v5i1.150","DOIUrl":"https://doi.org/10.60087/jaigs.v5i1.150","url":null,"abstract":"In order to cope with the task allocation in national economic mobilization, a task allocation planning method based on Hierarchical Task Network (HTN) for national economic mobilization is proposed. An HTN planning algorithm is proposed to solve and optimize task allocation, and an algorithm is designed to solve resource shortage. Finally, a case study verifies the effectiveness of the proposed method based on a real task allocation case in national economic mobilization.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"23 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141274494","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}
Background Robot-assisted therapy has the potential to enhance therapy doses post-stroke, addressing the often insufficient treatment of hand function in clinical settings and after discharge. Traditionally, these systems have been complex and required therapist supervision. To better leverage robot-assisted therapy, we propose a platform designed for minimal therapist supervision and present a preliminary evaluation of its immediate usability, addressing a key challenge often neglected in real-world applications. This approach could increase therapy doses by enabling a single therapist to train multiple patients simultaneously, as well as supporting independent training in clinics or at home. Methods We implemented design changes on a hand rehabilitation robot, focusing on enabling minimally-supervised therapy. This involved developing new physical and graphical user interfaces and creating two functional therapy exercises aimed at training hand motor coordination, somatosensation, and memory. Ten participants with chronic stroke evaluated the platform's usability and reported their perceived workload during a minimally-supervised therapy session. The ability to use the platform independently was assessed using a checklist. Results After a brief familiarization period, participants were able to independently perform the therapy session, needing assistance in only 13.46% (range: 7.69–19.23%) of the tasks. They rated the user interface and exercises highly on the System Usability Scale, with scores of 85.00 (75.63–86.88) and 73.75 (63.13–83.75) out of 100, respectively. Nine participants indicated they would use the platform frequently. The perceived workload was within acceptable ranges. The most challenging tasks identified were object grasping with simultaneous control of forearm pronosupination and stiffness discrimination. Discussion Our findings indicate that a robot-assisted therapy device can be safely and intuitively used with minimal supervision upon first exposure by adhering to usability and workload requirements. The preliminary usability evaluation highlighted specific challenges that need to be addressed to enable real-world minimally-supervised use. This platform could complement conventional therapy, providing increased therapy doses with existing resources and establishing a continuum of care that transitions from the clinic to the home.
{"title":"Towards a Platform for Robot-Assisted Minimally Supervised Hand Therapy: Design and Pilot Usability Evaluation","authors":"Venkata dinesh Reddy kalli","doi":"10.60087/jaigs.v4i1.137","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.137","url":null,"abstract":"Background \u0000 \u0000Robot-assisted therapy has the potential to enhance therapy doses post-stroke, addressing the often insufficient treatment of hand function in clinical settings and after discharge. Traditionally, these systems have been complex and required therapist supervision. To better leverage robot-assisted therapy, we propose a platform designed for minimal therapist supervision and present a preliminary evaluation of its immediate usability, addressing a key challenge often neglected in real-world applications. This approach could increase therapy doses by enabling a single therapist to train multiple patients simultaneously, as well as supporting independent training in clinics or at home. \u0000 \u0000 Methods \u0000 \u0000We implemented design changes on a hand rehabilitation robot, focusing on enabling minimally-supervised therapy. This involved developing new physical and graphical user interfaces and creating two functional therapy exercises aimed at training hand motor coordination, somatosensation, and memory. Ten participants with chronic stroke evaluated the platform's usability and reported their perceived workload during a minimally-supervised therapy session. The ability to use the platform independently was assessed using a checklist. \u0000 \u0000Results \u0000 \u0000After a brief familiarization period, participants were able to independently perform the therapy session, needing assistance in only 13.46% (range: 7.69–19.23%) of the tasks. They rated the user interface and exercises highly on the System Usability Scale, with scores of 85.00 (75.63–86.88) and 73.75 (63.13–83.75) out of 100, respectively. Nine participants indicated they would use the platform frequently. The perceived workload was within acceptable ranges. The most challenging tasks identified were object grasping with simultaneous control of forearm pronosupination and stiffness discrimination. \u0000 \u0000Discussion \u0000 \u0000Our findings indicate that a robot-assisted therapy device can be safely and intuitively used with minimal supervision upon first exposure by adhering to usability and workload requirements. The preliminary usability evaluation highlighted specific challenges that need to be addressed to enable real-world minimally-supervised use. This platform could complement conventional therapy, providing increased therapy doses with existing resources and establishing a continuum of care that transitions from the clinic to the home.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"39 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141109566","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}
Artificial Intelligence (AI) powered machines are increasingly mediating our work and many of our managerial, economic, and cultural interactions. While technology enhances individual capabilities in many ways, how can we ensure that the sociotechnical system as a whole—comprising a complex web of hundreds of human–machine interactions—is exhibiting collective intelligence? Research on human–machine interactions has been conducted within different disciplinary silos, resulting in social science models that underestimate technology and vice versa. Integrating these diverse perspectives and methods is crucial at this juncture. To truly advance our understanding of this important and rapidly evolving area, we need frameworks to facilitate research that bridges disciplinary boundaries. This paper advocates for establishing an interdisciplinary research domain—Collective Human-Machine Intelligence (COHUMAIN). It outlines a research agenda for a holistic approach to designing and developing the dynamics of sociotechnical systems. To illustrate the approach we envision in this domain, we describe recent work on a sociocognitive architecture, the transactive systems model of collective intelligence, which articulates the critical processes underlying the emergence and functioning of collective intelligence in human–AI collaborations.
{"title":"Advancing Collective Intelligence in Human–AI Collaboration: Foundations for the COHUMAIN Framework","authors":"Sohana Akter","doi":"10.60087/jaigs.v4i1.140","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.140","url":null,"abstract":"Artificial Intelligence (AI) powered machines are increasingly mediating our work and many of our managerial, economic, and cultural interactions. While technology enhances individual capabilities in many ways, how can we ensure that the sociotechnical system as a whole—comprising a complex web of hundreds of human–machine interactions—is exhibiting collective intelligence? Research on human–machine interactions has been conducted within different disciplinary silos, resulting in social science models that underestimate technology and vice versa. Integrating these diverse perspectives and methods is crucial at this juncture. To truly advance our understanding of this important and rapidly evolving area, we need frameworks to facilitate research that bridges disciplinary boundaries. \u0000This paper advocates for establishing an interdisciplinary research domain—Collective Human-Machine Intelligence (COHUMAIN). It outlines a research agenda for a holistic approach to designing and developing the dynamics of sociotechnical systems. To illustrate the approach we envision in this domain, we describe recent work on a sociocognitive architecture, the transactive systems model of collective intelligence, which articulates the critical processes underlying the emergence and functioning of collective intelligence in human–AI collaborations.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"49 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141112029","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}
Despite the persistent security challenges inherent in cloud systems, a distributed cloud environment necessitates an access control model that is contextually aware to effectively manage these challenges. This model should incorporate a role activation process based on the user's contextual information. Within this role activation process, the rationale behind data collection and usage is disclosed, enabling administrators to establish context-based policies. Consequently, role permissions are dynamically activated based on the association of roles with context. To mitigate complications in the role-based access control model, users are categorized into classes or groups, each with its own access control standards. Access to specific resources is determined by the user's identity upon request. Traditional access control models often fall short in cloud environments due to their inability to address all aspects of the diverse entities, resources, and users present. In the proposed access control system with perception reasoning, entities are expanded using Extensible Access Control Markup Language (XACML), while a trust module monitors user behavior dynamically, detecting and restricting malicious users attempting illegal data access. This includes assigning an identity tag to malicious users, which involves task and data classification along with database tagging.
{"title":"DNA Cryptography for Enhanced Data Storage Security in Cloud Environments","authors":"Mithun Sarker","doi":"10.60087/jaigs.v4i1.141","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.141","url":null,"abstract":"Despite the persistent security challenges inherent in cloud systems, a distributed cloud environment necessitates an access control model that is contextually aware to effectively manage these challenges. This model should incorporate a role activation process based on the user's contextual information. Within this role activation process, the rationale behind data collection and usage is disclosed, enabling administrators to establish context-based policies. Consequently, role permissions are dynamically activated based on the association of roles with context. To mitigate complications in the role-based access control model, users are categorized into classes or groups, each with its own access control standards. Access to specific resources is determined by the user's identity upon request. \u0000 \u0000Traditional access control models often fall short in cloud environments due to their inability to address all aspects of the diverse entities, resources, and users present. In the proposed access control system with perception reasoning, entities are expanded using Extensible Access Control Markup Language (XACML), while a trust module monitors user behavior dynamically, detecting and restricting malicious users attempting illegal data access. This includes assigning an identity tag to malicious users, which involves task and data classification along with database tagging.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"67 36","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141109965","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 recent years, the rapid expansion of Artificial Intelligence (AI) and its integration into various aspects of daily life have ignited significant discourse on the ethical considerations governing its application. This study addresses these concerns by swiftly reviewing multiple frameworks designed to guide the development and utilization of Responsible AI (RAI) applications. Through this exploration, we analyze each framework's alignment with the Software Development Life Cycle (SDLC) phases, revealing a predominant focus on the Requirements Elicitation phase, with limited coverage of other stages. Furthermore, we note a scarcity of supportive tools, predominantly offered by private entities. Our findings underscore the absence of a comprehensive framework capable of accommodating both technical and non-technical stakeholders across all SDLC phases, thus revealing a notable gap in the current landscape. This study sheds light on the imperative need for a unified framework encompassing all RAI principles and SDLC phases, accessible to users of varying expertise and objectives.
近年来，人工智能（AI）的快速发展及其与日常生活各方面的融合，引发了有关其应用伦理问题的重要讨论。本研究针对这些问题，迅速审查了多个旨在指导负责任的人工智能（RAI）应用开发和使用的框架。通过这一探索，我们分析了每个框架与软件开发生命周期（SDLC）各阶段的一致性，发现其主要侧重于需求征询阶段，对其他阶段的覆盖范围有限。此外，我们还注意到支持性工具很少，主要由私营实体提供。我们的研究结果表明，在 SDLC 的所有阶段，都缺乏一个能够兼顾技术和非技术利益相关者的综合框架，从而揭示了目前存在的一个显著差距。本研究揭示了一个统一框架的迫切需要，该框架应涵盖所有 RAI 原则和 SDLC 阶段，并可供不同专业知识和目标的用户使用。
{"title":"An Expedited Examination of Responsible AI Frameworks: Directing Ethical AI Development","authors":"Jeff Shuford","doi":"10.60087/jaigs.v4i1.138","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.138","url":null,"abstract":"In recent years, the rapid expansion of Artificial Intelligence (AI) and its integration into various aspects of daily life have ignited significant discourse on the ethical considerations governing its application. This study addresses these concerns by swiftly reviewing multiple frameworks designed to guide the development and utilization of Responsible AI (RAI) applications. Through this exploration, we analyze each framework's alignment with the Software Development Life Cycle (SDLC) phases, revealing a predominant focus on the Requirements Elicitation phase, with limited coverage of other stages. Furthermore, we note a scarcity of supportive tools, predominantly offered by private entities. Our findings underscore the absence of a comprehensive framework capable of accommodating both technical and non-technical stakeholders across all SDLC phases, thus revealing a notable gap in the current landscape. This study sheds light on the imperative need for a unified framework encompassing all RAI principles and SDLC phases, accessible to users of varying expertise and objectives.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"51 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141111144","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}
Current ethical debates on the use of artificial intelligence (AI) in healthcare approach AI technology in three primary ways. First, they assess the risks and potential benefits of current AI-enabled products using ethical checklists. Second, they propose ex ante lists of ethical values relevant to the design and development of assistive technologies. Third, they advocate for incorporating moral reasoning into AI's automation processes. These three perspectives dominate the discourse, as evidenced by a brief literature summary. We propose a fourth approach: viewing AI as a methodological tool to aid ethical reflection. This involves an AI simulation concept informed by three elements: 1) stochastic human behavior models based on behavioral data for simulating realistic scenarios, 2) qualitative empirical data on value statements regarding internal policy, and 3) visualization components to illustrate the impact of variable changes. This approach aims to inform an interdisciplinary field about anticipated ethical challenges or trade-offs in specific settings, prompting a re-evaluation of design and implementation plans. This is particularly useful for applications involving complex values and behaviors or limited communication resources, such as dementia care or care for individuals with cognitive impairments. While simulation does not replace ethical reflection, it allows for detailed, context-sensitive analysis during the design process and before implementation.Finally, we discuss the quantitative analysis methods enabled by stochastic simulations and the potential for these simulations to enhance traditional thought experiments and future-oriented technology assessments.
{"title":"Ethical Considerations in AI Simulations for Designing Assistive Technologies","authors":"Evin Miser, Orcun Sarioguz","doi":"10.60087/jaigs.v4i1.135","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.135","url":null,"abstract":"Current ethical debates on the use of artificial intelligence (AI) in healthcare approach AI technology in three primary ways. First, they assess the risks and potential benefits of current AI-enabled products using ethical checklists. Second, they propose ex ante lists of ethical values relevant to the design and development of assistive technologies. Third, they advocate for incorporating moral reasoning into AI's automation processes. These three perspectives dominate the discourse, as evidenced by a brief literature summary. We propose a fourth approach: viewing AI as a methodological tool to aid ethical reflection. This involves an AI simulation concept informed by three elements: 1) stochastic human behavior models based on behavioral data for simulating realistic scenarios, 2) qualitative empirical data on value statements regarding internal policy, and 3) visualization components to illustrate the impact of variable changes. This approach aims to inform an interdisciplinary field about anticipated ethical challenges or trade-offs in specific settings, prompting a re-evaluation of design and implementation plans. This is particularly useful for applications involving complex values and behaviors or limited communication resources, such as dementia care or care for individuals with cognitive impairments. While simulation does not replace ethical reflection, it allows for detailed, context-sensitive analysis during the design process and before implementation.Finally, we discuss the quantitative analysis methods enabled by stochastic simulations and the potential for these simulations to enhance traditional thought experiments and future-oriented technology assessments.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"60 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121773","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 the realm of computing, data science has revolutionized cybersecurity operations and technologies. The key to creating automated and intelligent security systems lies in extracting patterns or insights from cybersecurity data and building data-driven models. Data science, encompassing various scientific approaches, machine learning techniques, processes, and systems, studies real-world occurrences through data analysis. Machine learning techniques, known for their flexibility, scalability, and adaptability to new and unknown challenges, have been applied across many scientific fields. Cybersecurity is rapidly expanding due to significant advancements in social networks, cloud and web technologies, online banking, mobile environments, smart grids, and more. Various machine learning techniques have effectively addressed a wide range of computer security issues. This article reviews several machine learning applications in cybersecurity, including phishing detection, network intrusion detection, keystroke dynamics authentication, cryptography, human interaction proofs, spam detection in social networks, smart meter energy consumption profiling, and security concerns associated with machine learning techniques themselves. The methodology involves collecting a large dataset of phishing and legitimate instances, extracting relevant features such as email headers, content, and URLs, and training a machine learning model using supervised learning algorithms. These models can effectively identify phishing emails and websites with high accuracy and low false positive rates. To enhance phishing detection, it is recommended to continuously update the training dataset to include new phishing techniques and employ ensemble methods that combine multiple machine learning models for improved performance
{"title":"Revolutionizing Cybersecurity with Machine Learning: A Comprehensive Review and Future Directions","authors":"Bhuvi Chopra","doi":"10.60087/jaigs.v4i1.133","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.133","url":null,"abstract":"In the realm of computing, data science has revolutionized cybersecurity operations and technologies. The key to creating automated and intelligent security systems lies in extracting patterns or insights from cybersecurity data and building data-driven models. Data science, encompassing various scientific approaches, machine learning techniques, processes, and systems, studies real-world occurrences through data analysis. Machine learning techniques, known for their flexibility, scalability, and adaptability to new and unknown challenges, have been applied across many scientific fields. Cybersecurity is rapidly expanding due to significant advancements in social networks, cloud and web technologies, online banking, mobile environments, smart grids, and more. Various machine learning techniques have effectively addressed a wide range of computer security issues. This article reviews several machine learning applications in cybersecurity, including phishing detection, network intrusion detection, keystroke dynamics authentication, cryptography, human interaction proofs, spam detection in social networks, smart meter energy consumption profiling, and security concerns associated with machine learning techniques themselves. The methodology involves collecting a large dataset of phishing and legitimate instances, extracting relevant features such as email headers, content, and URLs, and training a machine learning model using supervised learning algorithms. These models can effectively identify phishing emails and websites with high accuracy and low false positive rates. To enhance phishing detection, it is recommended to continuously update the training dataset to include new phishing techniques and employ ensemble methods that combine multiple machine learning models for improved performance","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"120 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141124163","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}
This paper introduces an innovative method for safeguarding user privacy in digital marketing campaigns through the application of deep learning techniques on a data monetization platform. This framework empowers users to maintain authority over their personal data while enabling marketers to pinpoint suitable target audiences. The system consists of several key stages Data representation learning in hyperbolic space captures latent user interests across various data sources with hierarchical structures. Subsequently, Generative Adversarial Networks generate synthetic user interests from these embedding. To preserve user privacy, Federated Learning is utilized for decentralized user monetization, Data privacy, modeling training, ensuring data remains undisclosed to marketers. Lastly, a hyperbolic embedding, Federated learning targeting strategy, rooted in recommendation systems, utilizes learned user interests to identify optimal target audiences for digital marketing campaigns. In sum, this approach offers a comprehensive solution for privacy-preserving user modeling in digital marketing.
{"title":"Towards Improved Privacy in Digital Marketing: A Unified Approach to User Modeling with Deep Learning on a Data Monetization Platform","authors":"Bhuvi Chopra, Vinayak Raja","doi":"10.60087/jaigs.v4i1.130","DOIUrl":"https://doi.org/10.60087/jaigs.v4i1.130","url":null,"abstract":"This paper introduces an innovative method for safeguarding user privacy in digital marketing campaigns through the application of deep learning techniques on a data monetization platform. This framework empowers users to maintain authority over their personal data while enabling marketers to pinpoint suitable target audiences. The system consists of several key stages Data representation learning in hyperbolic space captures latent user interests across various data sources with hierarchical structures. Subsequently, Generative Adversarial Networks generate synthetic user interests from these embedding. To preserve user privacy, Federated Learning is utilized for decentralized user monetization, Data privacy, modeling training, ensuring data remains undisclosed to marketers. Lastly, a hyperbolic embedding, Federated learning targeting strategy, rooted in recommendation systems, utilizes learned user interests to identify optimal target audiences for digital marketing campaigns. In sum, this approach offers a comprehensive solution for privacy-preserving user modeling in digital marketing.","PeriodicalId":517201,"journal":{"name":"Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023","volume":"41 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140984013","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：