Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454167
S. S, B. Kailath
Spiking Neural Network can adapt to the environment if it has the capacity to learn based on spike timing-dependent plasticity (STDP) by which the synaptic weight gets modified based on time difference between pre and postsynaptic spikes. The classical pair-based STDP model which considers only a pair of pre and post spikes has failed to account for synaptic activity when driven by a series of spikes. Whereas, Triplet based STDP model provides best fit for the experimental data as well as maps on to the Bienenstock-Cooper-Munro (BCM) learning rule. Implementation of plasticity rules at circuit level is necessary for realizing efficient computational very large scale integration (VLSI) systems which incorporates learning and memory functions. The analog VLSI implementation of TSTDP available in literature so far requires external circuitry to identify precise timing between two immediate successive pre and post spikes. The TSTDP circuit proposed in this paper is capable of identifying precise time difference between any two spikes, provides potentiation or depression based on sign and strength of the time difference, and also inherits the BCM rule when driven with Poisson spike trains. The circuit has been simulated in LTspice-XVII with the “TSMC 180nm” technology library.
{"title":"Bistable-Triplet STDP circuit without external memory for Integrating with Silicon Neurons","authors":"S. S, B. Kailath","doi":"10.1109/AIIoT52608.2021.9454167","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454167","url":null,"abstract":"Spiking Neural Network can adapt to the environment if it has the capacity to learn based on spike timing-dependent plasticity (STDP) by which the synaptic weight gets modified based on time difference between pre and postsynaptic spikes. The classical pair-based STDP model which considers only a pair of pre and post spikes has failed to account for synaptic activity when driven by a series of spikes. Whereas, Triplet based STDP model provides best fit for the experimental data as well as maps on to the Bienenstock-Cooper-Munro (BCM) learning rule. Implementation of plasticity rules at circuit level is necessary for realizing efficient computational very large scale integration (VLSI) systems which incorporates learning and memory functions. The analog VLSI implementation of TSTDP available in literature so far requires external circuitry to identify precise timing between two immediate successive pre and post spikes. The TSTDP circuit proposed in this paper is capable of identifying precise time difference between any two spikes, provides potentiation or depression based on sign and strength of the time difference, and also inherits the BCM rule when driven with Poisson spike trains. The circuit has been simulated in LTspice-XVII with the “TSMC 180nm” technology library.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123631814","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454233
Madhuvanthi Srivatsav R, B. Kailath
In an effort to address the issue of low power and area constraints which are important pre-requisites to many applications in the field of signal processing, this work focuses on the implementation of a novel biphasic neuron architecture, that is proven to be energy efficient, and highly compact. The low power Adaptive exponential integrate and fire neuron (ADEx I&F), is implemented as a biphasic encoder in 180 nm CMOS Technology, and a SER of upto 60 dB and a figure of merit (FOM) of 0.26 pJ/conversion is achieved. The proposed biphasic encoder is found to exhibit similar performance characteristics with respect to the existing architectures while comprising of 52 % lesser number of transistors than the conventional biphasic neuron encoder models.
{"title":"A Novel Biphasic Neuron Encoder Implementation","authors":"Madhuvanthi Srivatsav R, B. Kailath","doi":"10.1109/AIIoT52608.2021.9454233","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454233","url":null,"abstract":"In an effort to address the issue of low power and area constraints which are important pre-requisites to many applications in the field of signal processing, this work focuses on the implementation of a novel biphasic neuron architecture, that is proven to be energy efficient, and highly compact. The low power Adaptive exponential integrate and fire neuron (ADEx I&F), is implemented as a biphasic encoder in 180 nm CMOS Technology, and a SER of upto 60 dB and a figure of merit (FOM) of 0.26 pJ/conversion is achieved. The proposed biphasic encoder is found to exhibit similar performance characteristics with respect to the existing architectures while comprising of 52 % lesser number of transistors than the conventional biphasic neuron encoder models.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132246918","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454205
Abdelfettah Elaanba, Mohammed Ridouani, L. Hassouni
Tubes and Catheters are very important devices for saving patients' lives. There is a variety of tubes and Catheters; those especially used during this study are: Endotracheal tube (ETT), Nasogastric (NG)], and Swan Ganz catheter. Errors in positioning these kinds of devices, if not detected early my caused crucial complications (even death). Airway tube malposition in adult patients intubated is seen in up to 25% of cases. Doctors and nurses use checklists to make sure the medical procedure goes smoothly, but these steps take a long time and more resources with the possibility of human errors during verification protocols especially when hospitals are at full capacity. In this article, we propose using transfer learning to train and compare several Keras applications on classification tube problems; the best-selected networks can help in the development of CAD (Computer Aided Detection). The main advantage of using a single Deep Convolutional Neural Network DCNN to detect abnormal positioning of several lines based on chest X-ray image processing is to avoid the complexity caused by using a DCNN (Deep Convolutional Neural Network) network for each type of line. Efficient DCNN can detect abnormal positioning in real-time and immediately notify doctors to adjust tube position. All tested networks during this work are improved after augmentations and parameters tuning, we get the best score for Resnet50V2 model AUC (80%).
{"title":"Automatic detection Using Deep Convolutional Neural Networks for 11 Abnormal Positioning of Tubes and Catheters in Chest X-ray Images","authors":"Abdelfettah Elaanba, Mohammed Ridouani, L. Hassouni","doi":"10.1109/AIIoT52608.2021.9454205","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454205","url":null,"abstract":"Tubes and Catheters are very important devices for saving patients' lives. There is a variety of tubes and Catheters; those especially used during this study are: Endotracheal tube (ETT), Nasogastric (NG)], and Swan Ganz catheter. Errors in positioning these kinds of devices, if not detected early my caused crucial complications (even death). Airway tube malposition in adult patients intubated is seen in up to 25% of cases. Doctors and nurses use checklists to make sure the medical procedure goes smoothly, but these steps take a long time and more resources with the possibility of human errors during verification protocols especially when hospitals are at full capacity. In this article, we propose using transfer learning to train and compare several Keras applications on classification tube problems; the best-selected networks can help in the development of CAD (Computer Aided Detection). The main advantage of using a single Deep Convolutional Neural Network DCNN to detect abnormal positioning of several lines based on chest X-ray image processing is to avoid the complexity caused by using a DCNN (Deep Convolutional Neural Network) network for each type of line. Efficient DCNN can detect abnormal positioning in real-time and immediately notify doctors to adjust tube position. All tested networks during this work are improved after augmentations and parameters tuning, we get the best score for Resnet50V2 model AUC (80%).","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130103556","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454196
Sahar A. Moussa, A. Aziz, Rania Magdy Ahmed, Nada Adel Hendawy, Hesham Ayman Nasr, Mohamed Adel Shalaby
This work focuses on the potential of expert System(ES) in solving complicated and Contradicting problems in the field of power system planning. Conventional optimization methods are inappropriate in many cases of optimization problem solutions. Artificial Intelligence (AI) albeit rather Convenient for solution of some optimization problems of power systems, however, the need for good starting point helps greatly for achieving proper and fast conversion. Experience of professional engineers is very crucial in reaching the optimal solution. In this paper we introduce ES technique as a helpful tool in Micro Power grid (MPG) planning by suggesting a strong starting point for optimization techniques in both conventional and AI methods. A knowledge base chain rules for two major problems are investigated; distributed generators(DG) and capacitor allocation. Effectiveness of the proposed knowledgebase is tested through the standard IEEE 14-bus system.
{"title":"Expert System In MicroPower Grid Planning","authors":"Sahar A. Moussa, A. Aziz, Rania Magdy Ahmed, Nada Adel Hendawy, Hesham Ayman Nasr, Mohamed Adel Shalaby","doi":"10.1109/AIIoT52608.2021.9454196","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454196","url":null,"abstract":"This work focuses on the potential of expert System(ES) in solving complicated and Contradicting problems in the field of power system planning. Conventional optimization methods are inappropriate in many cases of optimization problem solutions. Artificial Intelligence (AI) albeit rather Convenient for solution of some optimization problems of power systems, however, the need for good starting point helps greatly for achieving proper and fast conversion. Experience of professional engineers is very crucial in reaching the optimal solution. In this paper we introduce ES technique as a helpful tool in Micro Power grid (MPG) planning by suggesting a strong starting point for optimization techniques in both conventional and AI methods. A knowledge base chain rules for two major problems are investigated; distributed generators(DG) and capacitor allocation. Effectiveness of the proposed knowledgebase is tested through the standard IEEE 14-bus system.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131813413","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454194
Hosam Alamleh, A. A. AlQahtani
Remote electronic voting refers to the use of the computer and Internet to collocate votes in an election. Remote e-voting is convenient and provides easy access for voters. On other hand, it makes it easier to count the votes and generate reports for election operators. Over time, e-voting systems were developed until it reaches the level that we have today, and it is expected that they will continue to improve in the future. Nevertheless, recently there has been increasing criticism of remote e-voting systems' security and integrity. Also, concerns were raised about whether these systems can defend against cyber attacks. An effective remote e-voting system must meet a set of standards required from regulatory bodies. This paper discusses remote e-voting systems' design requirements as discussed in current literature. Then, we examine whether the current public infrastructure is capable of supporting an effective remote e-voting system that meets the design requirements. We found that the current technology infrastructure is not sufficient to support efficient remote e-voting systems, as the technologies that need to be implemented to meet the design requirements are victims of different cyber attacks.
{"title":"Analysis of the Design Requirements for Remote Internet-Based E-Voting Systems","authors":"Hosam Alamleh, A. A. AlQahtani","doi":"10.1109/AIIoT52608.2021.9454194","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454194","url":null,"abstract":"Remote electronic voting refers to the use of the computer and Internet to collocate votes in an election. Remote e-voting is convenient and provides easy access for voters. On other hand, it makes it easier to count the votes and generate reports for election operators. Over time, e-voting systems were developed until it reaches the level that we have today, and it is expected that they will continue to improve in the future. Nevertheless, recently there has been increasing criticism of remote e-voting systems' security and integrity. Also, concerns were raised about whether these systems can defend against cyber attacks. An effective remote e-voting system must meet a set of standards required from regulatory bodies. This paper discusses remote e-voting systems' design requirements as discussed in current literature. Then, we examine whether the current public infrastructure is capable of supporting an effective remote e-voting system that meets the design requirements. We found that the current technology infrastructure is not sufficient to support efficient remote e-voting systems, as the technologies that need to be implemented to meet the design requirements are victims of different cyber attacks.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131065043","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454202
M. Roopaei, Justine Horst, Emilee Klaas, Gwen Foster, Tammy J. Salmon-Stephens, Jodean E. Grunow
The inclusion of women into the development and implementation of artificial intelligence and machine learning in the world is critical. The underrepresentation and lack of representation of women results in lower quality AI products. The AI consumer group is very diverse and the lack of diversity within the AI leadership and workforce creates a crisis within the AI industry. Additionally, because AI is fast-paced and has a high societal impact, not addressing this disparity has the potential to increase stereotypes, underrepresentation, and discrimination in career fields everywhere. This paper discusses the importance of women in the AI field, the barriers that they face, and a few solutions to eliminate gender-discrimination and gender-inequality for women of all ages. Women may experience increased discrimination in fields of underrepresentation, and this can discourage their desire to purse these career paths. The workplace needs to be aware of these struggles, provide resources for both men and women to address this, and invest in support for women to encourage their participation. As an emerging industry, the AI industry has an opportunity to address this gender gap before it becomes more pervasive and ingrained into the culture of AI. Together, we can have a significant impact on the future of AI, the community, and the products that consumers use.
{"title":"Women in AI: Barriers and Solutions","authors":"M. Roopaei, Justine Horst, Emilee Klaas, Gwen Foster, Tammy J. Salmon-Stephens, Jodean E. Grunow","doi":"10.1109/AIIoT52608.2021.9454202","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454202","url":null,"abstract":"The inclusion of women into the development and implementation of artificial intelligence and machine learning in the world is critical. The underrepresentation and lack of representation of women results in lower quality AI products. The AI consumer group is very diverse and the lack of diversity within the AI leadership and workforce creates a crisis within the AI industry. Additionally, because AI is fast-paced and has a high societal impact, not addressing this disparity has the potential to increase stereotypes, underrepresentation, and discrimination in career fields everywhere. This paper discusses the importance of women in the AI field, the barriers that they face, and a few solutions to eliminate gender-discrimination and gender-inequality for women of all ages. Women may experience increased discrimination in fields of underrepresentation, and this can discourage their desire to purse these career paths. The workplace needs to be aware of these struggles, provide resources for both men and women to address this, and invest in support for women to encourage their participation. As an emerging industry, the AI industry has an opportunity to address this gender gap before it becomes more pervasive and ingrained into the culture of AI. Together, we can have a significant impact on the future of AI, the community, and the products that consumers use.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133226236","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454207
Koketso Ntshabele, Bassey Isong, A. Abu-Mahfouz
Low Power Wide Area Network (LPWAN) is a network technology that emanated from the swift advancement of the Internet of Things (IoT) market. It is characterized by low cost, long-range communications, low power consumptions, and better area coverage. However, LPWAN is faced with several challenges such as scalability, security, coexistence, management, and adoption. Recently, Cognitive Radio-LPWAN (CR-LPWAN) has been introduced to address some of these challenges to preserve the benefits of LPWAN. Therefore, this paper surveys and analyses recent works on CR-LPWAN to identify the existing challenges, possible solutions and open issues as research directions. This paper specifically focused on relevant works that addressed issues in standardization, design, development, and architecture and identified research directions for improving CR-LPWAN. About twenty (20) relevant articles were explored, and the findings revealed the existence of several issues and proposed solutions in the CR-LPWAN realm. The findings also revealed CR-LPWAN as a promising wireless communication technology and with more research attention, CR-LPWAN can be improved significantly.
{"title":"CR-LPWAN: issues, solutions and research directions","authors":"Koketso Ntshabele, Bassey Isong, A. Abu-Mahfouz","doi":"10.1109/AIIoT52608.2021.9454207","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454207","url":null,"abstract":"Low Power Wide Area Network (LPWAN) is a network technology that emanated from the swift advancement of the Internet of Things (IoT) market. It is characterized by low cost, long-range communications, low power consumptions, and better area coverage. However, LPWAN is faced with several challenges such as scalability, security, coexistence, management, and adoption. Recently, Cognitive Radio-LPWAN (CR-LPWAN) has been introduced to address some of these challenges to preserve the benefits of LPWAN. Therefore, this paper surveys and analyses recent works on CR-LPWAN to identify the existing challenges, possible solutions and open issues as research directions. This paper specifically focused on relevant works that addressed issues in standardization, design, development, and architecture and identified research directions for improving CR-LPWAN. About twenty (20) relevant articles were explored, and the findings revealed the existence of several issues and proposed solutions in the CR-LPWAN realm. The findings also revealed CR-LPWAN as a promising wireless communication technology and with more research attention, CR-LPWAN can be improved significantly.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114438889","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454229
Md. Ali Azam, Shawon Dey, H. Mittelmann, Shankarachary Ragi
We develop a decentralized control method for a UAV swarm for a multitarget tracking application using the theory of decentralized Markov decision processes (Dec-MDPs). This study develops a UAV control strategy to maximize the overall target tracking performance in a decentralized setting. Motivation for this case study comes from the surveillance applications using UAV swarms. Decision-theoretic approaches are very difficult to solve due to high dimensionality and being computationally expensive. We extend an approximate dynamic programming method called nominal belief-state optimization (NBO) to solve the UAV swarm control problem for target tracking application. We also implement a centralized MDP approach as a benchmark to compare the performance of the Dec-MDP approach.
{"title":"Decentralized UAV Swarm Control for Multitarget Tracking using Approximate Dynamic Programming","authors":"Md. Ali Azam, Shawon Dey, H. Mittelmann, Shankarachary Ragi","doi":"10.1109/AIIoT52608.2021.9454229","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454229","url":null,"abstract":"We develop a decentralized control method for a UAV swarm for a multitarget tracking application using the theory of decentralized Markov decision processes (Dec-MDPs). This study develops a UAV control strategy to maximize the overall target tracking performance in a decentralized setting. Motivation for this case study comes from the surveillance applications using UAV swarms. Decision-theoretic approaches are very difficult to solve due to high dimensionality and being computationally expensive. We extend an approximate dynamic programming method called nominal belief-state optimization (NBO) to solve the UAV swarm control problem for target tracking application. We also implement a centralized MDP approach as a benchmark to compare the performance of the Dec-MDP approach.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116398849","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454172
S. K. Singh, L. Yang, Hao Ma
Enhancement in the efficiency of surgical proficiency training system requires a continuous effort in surgical care atmosphere without any risk factor and it is known as a complex and challenging task nowadays. The process is exclusively relevant in training of technical skills specific to modern Minimally Invasive System (MIS) based procedures like keyhole surgery. However, modern surgical training systems are more intensive on the improvement of technical skills for dexterity, imagining and accurateness of the surgeons which are lacking in aspects of context-awareness and intra-operative real-time supervision. Context-aware intelligent training systems interpret the modern surgical condition and help surgeons to train on surgical tasks. Motivated by the development aspects and needs, this paper presents in depth review and highlights of the major challenging factors for haptic control interfacing, which are required to overcome in the future development of intelligent and highly integrated surgical training system for robotic surgery.
{"title":"Recent Challenges for Haptic Interface and Control for Robotic Assisted Surgical Training System: A Review","authors":"S. K. Singh, L. Yang, Hao Ma","doi":"10.1109/AIIoT52608.2021.9454172","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454172","url":null,"abstract":"Enhancement in the efficiency of surgical proficiency training system requires a continuous effort in surgical care atmosphere without any risk factor and it is known as a complex and challenging task nowadays. The process is exclusively relevant in training of technical skills specific to modern Minimally Invasive System (MIS) based procedures like keyhole surgery. However, modern surgical training systems are more intensive on the improvement of technical skills for dexterity, imagining and accurateness of the surgeons which are lacking in aspects of context-awareness and intra-operative real-time supervision. Context-aware intelligent training systems interpret the modern surgical condition and help surgeons to train on surgical tasks. Motivated by the development aspects and needs, this paper presents in depth review and highlights of the major challenging factors for haptic control interfacing, which are required to overcome in the future development of intelligent and highly integrated surgical training system for robotic surgery.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123628326","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}
Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454183
Henri Hegemier, Jaimie Kelley
Mobile robots are increasingly common in society and are increasingly being used for complex and high-stakes tasks such as search and rescue. The growing requirements for these robots demonstrate a need for systems which can review and react in real time to environmental hazards, which will allow robots to handle environments that are both dynamic and dangerous. We propose and test a system which allows mobile robots to reclassify environmental objects during operation in conjunction with an edge system. We train an image classification model with 99 percent accuracy and deploy it in conjunction with an edge server and JSON-based ruleset to allow robots to react to and avoid hazards.
{"title":"Image Classification with Knowledge-Based Systems on the Edge for Real-Time Danger Avoidance in Robots","authors":"Henri Hegemier, Jaimie Kelley","doi":"10.1109/AIIoT52608.2021.9454183","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454183","url":null,"abstract":"Mobile robots are increasingly common in society and are increasingly being used for complex and high-stakes tasks such as search and rescue. The growing requirements for these robots demonstrate a need for systems which can review and react in real time to environmental hazards, which will allow robots to handle environments that are both dynamic and dangerous. We propose and test a system which allows mobile robots to reclassify environmental objects during operation in conjunction with an edge system. We train an image classification model with 99 percent accuracy and deploy it in conjunction with an edge server and JSON-based ruleset to allow robots to react to and avoid hazards.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129782232","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：