International Journal of Network Dynamics and Intelligence最新文献

{"title":"Can AI See Bias in X-ray Images?","authors":"Maciej Szankin, A. Kwaśniewska","doi":"10.53941/ijndi0101005","DOIUrl":"https://doi.org/10.53941/ijndi0101005","url":null,"abstract":"Article\u0000Can AI See Bias in X-ray images?\u0000\u0000Kwasniewska Alicja *, and Szankin Maciej *\u0000\u0000\u00001 SiMa Technologies Inc. 226 Airport Parkway, Suite 550 San Jose, CA 95110, United States\u00002 Intel Corporation 16409 W Bernardo Dr Suite 100, San Diego, CA 92127, United States\u0000* Correspondence: alicja.kwasniewska@sima.ai; maciej.szankin@intel.com\u0000 \u0000 \u0000Received: 8 November 2022\u0000Accepted: 13 November 2022\u0000Published: 22 December 2022\u0000 \u0000\u0000Abstract: Recent advances in artificial intelligence (AI) have shown promising results in various image-based systems, improving accuracy and throughput, while reducing latency. All these factors are crucial in healthcare and have generated increased interest in this technology. However, there are also multiple challenges integrating AI in existing systems, such as poor explainability, data imbalance and bias. These challenges affect the reliability of the neural networks used in AI applications. The limitations may significantly affect the quality and cost of medical care by introducing false positive diagnosis. The false positives subsequently lead to increased stress in patients and necessitate additional testing and procedures. Lack of rich data representing all socio-economic groups can also undermine reliable decisions for underrepresented groups. Although various studies discussed techniques that may help with bias mitigation, to the best of our knowledge, no practical experiments have been conducted so far that compare different reweighting approaches using convolutional neural networks (CNN). This work focuses on in-depth explanatory analysis of chest X-ray datasets to understand and quantify the problem of class imbalance and bias. After that, various topologies of binary classifications are compared, followed by practical applications of loss reweighting techniques and comparison of their influence of privileged, underprivileged, and overall population. Experiments proved that high classification accuracy can be achieved using an efficient model topology suitable for embedded devices, making it possible to run locally without the need for cloud processing. Preliminary results showed that performance of the model for the underprivileged class can be improved by 15% if proper weighting factors are obtained and applied during the training procedure.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122048689","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":"A Survey on Evolved LoRa-Based Communication Technologies for Emerging Internet of Things Applications","authors":"Fang Yao, Yulong Ding, Shen Hong, Shuanghua Yang","doi":"10.53941/ijndi0101002","DOIUrl":"https://doi.org/10.53941/ijndi0101002","url":null,"abstract":"Survey/review study\u0000A Survey on Evolved LoRa-Based Communication Technologies for Emerging Internet of Things Applications\u0000\u0000Fang Yao 1,3, Yulong Ding 2,3,*, Shengguang Hong 2,4, and Shuang-Hua Yang 2,5,*\u0000\u0000\u00001 The Ta-tech company, Nanjing 210009, China\u00002 Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet, Department of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China\u00003 Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China\u00004 The School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150006, China\u00005 Department of Computer Science, University of Reading, West Berkshire RG6 6UR, United Kingdom\u0000* Correspondence: dingyl@sustech.edu.cn; Shuang-hua.yang@reading.ac.uk \u0000 \u0000 \u0000Received: 17 September 2022\u0000Accepted: 17 October 2022\u0000Published: 22 December 2022\u0000 \u0000\u0000Abstract: The concept of Internet of Things (IoT) greatly extends the coverage area that human being is able to perceive, access, and even control. By connecting various “Things” to the Internet, the IoT makes it possible to measure and manage the physical world as needed. As one of the most widely adopted Low Power Wide Area network technologies, the Long-Range-Radio (LoRa) has the features of long range, low power, and robustness, and thus plays an important role in building IoT applications where IoT objects are connected to the internet at affordable costs. Since the development of LoRa, many IoT applications have adopted LoRa and achieved success in the market. Currently, IoT technologies keep evolving towards different fields, giving rise to multifarious IoT applications including industrial IoT, smart city IoT, healthcare IoT, and direct-to-satellite IoT. In the meantime, LoRa also keeps developing and finding its position in various IoT applications either as a main or complementary player. The objective of this survey is to (1) provide a fundamental understanding of the LoRa technology; (2) explore research activities studying LoRa based communication systems for new IoT applications; and (3) demonstrate how the LoRa technology works together with other technologies to deliver better IoT services to end users.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115316015","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":"The Cooperative Output Regulation by the Distributed Observer Approach","authors":"Youfeng Su, He Cai, Jie Huang","doi":"10.53941/ijndi0101003","DOIUrl":"https://doi.org/10.53941/ijndi0101003","url":null,"abstract":"Survey/review study\u0000The Cooperative Output Regulation by the Distributed Observer Approach\u0000\u0000Youfeng Su 1, He Cai 2, and Jie Huang 3,*\u0000\u0000\u00001 College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China\u00002 School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China\u00003 Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China\u0000* Correspondence: jhuang@mae.cuhk.edu.hk\u0000 \u0000 \u0000Received: 7 November 2022\u0000Accepted: 13 November 2022\u0000Published: 22 December 2022\u0000 \u0000\u0000Abstract: The cooperative output regulation problem (CORP) is an extension of the leader-following consensus problem of multi-agent systems (MASs), and has been studied by two approaches, namely, the distributed observer (DO) approach and the distributed internal model (DIM) approach. The two approaches are, respectively, the extensions of the classical feedforward control approach and the classical internal model approach (for a single system) to the MASs. This paper overviews the CORP by the DO approach with the emphasis on linear MASs. After formulating the CORP, we present the evolution process of three types of DOs and the corresponding solutions to the CORP. Furthermore, some variants and extensions of the DO approach are also briefly surveyed for completeness.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"30 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113974476","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":"From Emotion AI to Cognitive AI","authors":"Guoying Zhao, Yante Li, Qianru Xu","doi":"10.53941/ijndi0101006","DOIUrl":"https://doi.org/10.53941/ijndi0101006","url":null,"abstract":"Survey/review study\u0000From Emotion AI to Cognitive AI\u0000\u0000Guoying Zhao *, Yante Li , and Qianru Xu\u0000\u0000\u0000University of Oulu, Pentti Kaiteran Katu 1, Linnanmaa 90570, Finland\u0000* Correspondence: guoying.zhao@oulu.fi\u0000 \u0000 \u0000Received: 22 September 2022\u0000Accepted: 28 November 2022\u0000Published: 22 December 2022\u0000 \u0000\u0000Abstract: Cognitive computing is recognized as the next era of computing. In order to make hardware and software systems more human-like, emotion artificial intelligence (AI) and cognitive AI which simulate human intelligence are the core of real AI. The current boom of sentiment analysis and affective computing in computer science gives rise to the rapid development of emotion AI. However, the research of cognitive AI has just started in the past few years. In this visionary paper, we briefly review the current development in emotion AI, introduce the concept of cognitive AI, and propose the envisioned future of cognitive AI, which intends to let computers think, reason, and make decisions in similar ways that humans do. The important aspect of cognitive AI in terms of engagement, regulation, decision making, and discovery are further discussed. Finally, we propose important directions for constructing future cognitive AI, including data and knowledge mining, multi-modal AI explainability, hybrid AI, and potential ethical challenges.","PeriodicalId":183984,"journal":{"name":"International Journal of Network Dynamics and Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116364553","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}