Juliana M. de Oliveira, Roberto Muñoz, J. B. F. Duarte, A. V. L. Neto, José Wally M. Menezes, V. H. C. Albuquerque
Rehabilitation is the process related to the recovery, maintenance or improvement of physical mental and / or cognitive skills necessary to carry out daily activities. Virtual reality therapy, virtual reality (VR) immersion therapy, simulation therapy or virtual reality exposure therapy is an intervention method of using virtual reality technology for psychological or occupational therapy. The possibility of simulating situations necessary for the treatment, controlling variables and reducing the patient’s exposure to risks are popular factors for this tool. Many studies indicate that therapy with the aid of virtual reality brings great benefits to the patient. In this article, we present, through a review of 117 articles, the feasibility of applying VR in treatments with clinical trial methodology, identifying through the "Patient, Intervention, Comparison and Outcomes" the characteristics, population, treatment time, forms of comparison and if the results obtained are effective. The characteristics identified during the process show that virtual reality applied to therapies can be used without negative interference in the treatment. In addition, the results show that VR in rehabilitation treatments are motivating and show better results than traditional treatments.
{"title":"Intelligent Virtual Reality Therapy Systems for Motor and Cognitive Rehabilitation: A Survey based on Clinical Trial Studies","authors":"Juliana M. de Oliveira, Roberto Muñoz, J. B. F. Duarte, A. V. L. Neto, José Wally M. Menezes, V. H. C. Albuquerque","doi":"10.33969/ais.2021.31009","DOIUrl":"https://doi.org/10.33969/ais.2021.31009","url":null,"abstract":"Rehabilitation is the process related to the recovery, maintenance or improvement of physical mental and / or cognitive skills necessary to carry out daily activities. Virtual reality therapy, virtual reality (VR) immersion therapy, simulation therapy or virtual reality exposure therapy is an intervention method of using virtual reality technology for psychological or occupational therapy. The possibility of simulating situations necessary for the treatment, controlling variables and reducing the patient’s exposure to risks are popular factors for this tool. Many studies indicate that therapy with the aid of virtual reality brings great benefits to the patient. In this article, we present, through a review of 117 articles, the feasibility of applying VR in treatments with clinical trial methodology, identifying through the \"Patient, Intervention, Comparison and Outcomes\" the characteristics, population, treatment time, forms of comparison and if the results obtained are effective. The characteristics identified during the process show that virtual reality applied to therapies can be used without negative interference in the treatment. In addition, the results show that VR in rehabilitation treatments are motivating and show better results than traditional treatments.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133000004","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}
H. Kaur, D. Koundal, Virendar Kadyan, N. Kaur, K. Polat
In medical domain, various multimodalities such as Computer tomography (CT) and Magnetic resonance imaging (MRI) are integrated into a resultant fused image. Image fusion (IF) is a method by which vital information can be preserved by extracting all important information from the multiple images into the resultant fused image. The analytical and visual image quality can be enhanced by the integration of different images. In this paper, a new algorithm has been proposed on the basis of guided filter with new fusion rule for the fusion of different imaging modalities such as MRI and Fluorodeoxyglucose images of brain for the detection of tumor. The performance of the proposed method has been evaluated and compared with state-of-the-art image fusion techniques using various qualitative as well as quantitative evaluation metrics. From the results, it has been observed that more information has achieved on edges and content visibility is also high as compared to the other techniques which makes it more suitable for real applications. The experimental results are evaluated on the basis of with-reference and without-references metric such as standard deviation, entropy, peak signal to noise ratio, mutual information etc.
{"title":"Automated Multimodal image fusion for brain tumor detection","authors":"H. Kaur, D. Koundal, Virendar Kadyan, N. Kaur, K. Polat","doi":"10.33969/AIS.2021.31005","DOIUrl":"https://doi.org/10.33969/AIS.2021.31005","url":null,"abstract":"In medical domain, various multimodalities such as Computer tomography (CT) and Magnetic resonance imaging (MRI) are integrated into a resultant fused image. Image fusion (IF) is a method by which vital information can be preserved by extracting all important information from the multiple images into the resultant fused image. The analytical and visual image quality can be enhanced by the integration of different images. In this paper, a new algorithm has been proposed on the basis of guided filter with new fusion rule for the fusion of different imaging modalities such as MRI and Fluorodeoxyglucose images of brain for the detection of tumor. The performance of the proposed method has been evaluated and compared with state-of-the-art image fusion techniques using various qualitative as well as quantitative evaluation metrics. From the results, it has been observed that more information has achieved on edges and content visibility is also high as compared to the other techniques which makes it more suitable for real applications. The experimental results are evaluated on the basis of with-reference and without-references metric such as standard deviation, entropy, peak signal to noise ratio, mutual information etc.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129740793","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 view of the situation of violence faced in Brazil, several actors, from the most diverse areas of knowledge, have been dedicated to studying, analyzing and proposing solutions for public security. The great challenge of much of what is produced is to combine theory with practice. In addition, the fact that we do not have State policies, but Government policies contribute significantly to the lack of long-term studies. Discontinuities, whether due to the ineffectiveness of what is proposed, or due to cultural and organizational changes in crime, preclude a cycle of planning, execution, evaluation and correction. This brings us to the first observation of modern public security: volatility. Thus, it is impossible to imagine modern management without the use of technology for the quick and assertive analysis of the problems faced. In this sense, the use of the intelligence, strategy, and technology triad becomes essential for accurate monitoring of these changes, providing guidelines and subsidies for the modernization of public security management and security and policing matrix. Given these statements, the present study has the general objective of presenting the Policy to Combat the Mobility of Crime and its effects on the Public Security of the State of Cear[Pleaseinsert“PrerenderUnicode–˝intopreamble] (Brazil), referring to the period from 2017 to 2019. Through an empirical analysis, statistical data were collected to present a direct scenario of the implementation and the results achieved and present the theoretical relationship between the actions and the results, thus providing an exploratory depth of the facts and their impacts. In order to show the positive results achieved, a quantitative and qualitative method was used to correlate aspects and concepts in the large area of the humanities with practical policing and technological applications. As a result of the implementation of the Combating the Mobility of Crime, the State of Cear[Pleaseinsert“PrerenderUnicode–˝intopreamble] managed to place the number of robberies and homicides among the lowest rates of the decade, gaining national prominence of strategy and technology employed. Thus, the Policy to Combat the Mobility of Crime changed the policing matrix, allowing greater efficiency of the resources used and better monitoring the indicators.
{"title":"Intelligent Technology to Enhance Policing and Public Accountability","authors":"V. Aloisio, Brazil Ce","doi":"10.33969/AIS.2021.31004","DOIUrl":"https://doi.org/10.33969/AIS.2021.31004","url":null,"abstract":"In view of the situation of violence faced in Brazil, several actors, from the most diverse areas of knowledge, have been dedicated to studying, analyzing and proposing solutions for public security. The great challenge of much of what is produced is to combine theory with practice. In addition, the fact that we do not have State policies, but Government policies contribute significantly to the lack of long-term studies. Discontinuities, whether due to the ineffectiveness of what is proposed, or due to cultural and organizational changes in crime, preclude a cycle of planning, execution, evaluation and correction. This brings us to the first observation of modern public security: volatility. Thus, it is impossible to imagine modern management without the use of technology for the quick and assertive analysis of the problems faced. In this sense, the use of the intelligence, strategy, and technology triad becomes essential for accurate monitoring of these changes, providing guidelines and subsidies for the modernization of public security management and security and policing matrix. Given these statements, the present study has the general objective of presenting the Policy to Combat the Mobility of Crime and its effects on the Public Security of the State of Cear[Pleaseinsert“PrerenderUnicode–˝intopreamble] (Brazil), referring to the period from 2017 to 2019. Through an empirical analysis, statistical data were collected to present a direct scenario of the implementation and the results achieved and present the theoretical relationship between the actions and the results, thus providing an exploratory depth of the facts and their impacts. In order to show the positive results achieved, a quantitative and qualitative method was used to correlate aspects and concepts in the large area of the humanities with practical policing and technological applications. As a result of the implementation of the Combating the Mobility of Crime, the State of Cear[Pleaseinsert“PrerenderUnicode–˝intopreamble] managed to place the number of robberies and homicides among the lowest rates of the decade, gaining national prominence of strategy and technology employed. Thus, the Policy to Combat the Mobility of Crime changed the policing matrix, allowing greater efficiency of the resources used and better monitoring the indicators.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"23 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130980224","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}
Human emotion recognition through artificial intelligence is one of the most popular research fields among researchers nowadays. The fields of Human Computer Interaction (HCI) and Affective Computing are being extensively used to sense human emotions. Humans generally use a lot of indirect and non-verbal means to convey their emotions. The presented exposition aims to provide an overall overview with the analysis of all the noteworthy emotion detection methods at a single location. To the best of our knowledge, this is the first attempt to outline all the emotion recognition models developed in the last decade. The paper is comprehended by expending more than hundred papers; a detailed analysis of the methodologies along with the datasets is carried out in the paper. The study revealed that emotion detection is predominantly carried out through four major methods, namely, facial expression recognition, physiological signals recognition, speech signals variation and text semantics on standard databases such as JAFFE, CK+, Berlin Emotional Database, SAVEE, etc. as well as self-generated databases. Generally seven basic emotions are recognized through these methods. Further, we have compared different methods employed for emotion detection in humans. The best results were obtained by using Stationary Wavelet Transform for Facial Emotion Recognition , Particle Swarm Optimization assisted Biogeography based optimization algorithms for emotion recognition through speech, Statistical features coupled with different methods for physiological signals, Rough set theory coupled with SVM for text semantics with respective accuracies of 98.83%,99.47%, 87.15%,87.02% . Overall, the method of Particle Swarm Optimization assisted Biogeography based optimization algorithms with an accuracy of 99.47% on BES dataset gave the best results.
{"title":"Emotion Recognition and Detection Methods: A Comprehensive Survey","authors":"Anvita Saxena, Ashish Khanna, Deepak Gupta","doi":"10.33969/ais.2020.21005","DOIUrl":"https://doi.org/10.33969/ais.2020.21005","url":null,"abstract":"Human emotion recognition through artificial intelligence is one of the most popular research fields among researchers nowadays. The fields of Human Computer Interaction (HCI) and Affective Computing are being extensively used to sense human emotions. Humans generally use a lot of indirect and non-verbal means to convey their emotions. The presented exposition aims to provide an overall overview with the analysis of all the noteworthy emotion detection methods at a single location. To the best of our knowledge, this is the first attempt to outline all the emotion recognition models developed in the last decade. The paper is comprehended by expending more than hundred papers; a detailed analysis of the methodologies along with the datasets is carried out in the paper. The study revealed that emotion detection is predominantly carried out through four major methods, namely, facial expression recognition, physiological signals recognition, speech signals variation and text semantics on standard databases such as JAFFE, CK+, Berlin Emotional Database, SAVEE, etc. as well as self-generated databases. Generally seven basic emotions are recognized through these methods. Further, we have compared different methods employed for emotion detection in humans. The best results were obtained by using Stationary Wavelet Transform for Facial Emotion Recognition , Particle Swarm Optimization assisted Biogeography based optimization algorithms for emotion recognition through speech, Statistical features coupled with different methods for physiological signals, Rough set theory coupled with SVM for text semantics with respective accuracies of 98.83%,99.47%, 87.15%,87.02% . Overall, the method of Particle Swarm Optimization assisted Biogeography based optimization algorithms with an accuracy of 99.47% on BES dataset gave the best results.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127879281","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}
User interface has special importance in immersive virtual environments. Interactions based on the simple and conceivable gestures of a hand may enhance immersivity of a Virtual Environment (VE). However, due to the structural issues like small size and complex shape of human hand, recognition of hand gestures are more challenging. This work introduces a novel interaction technique to perform the basic interaction tasks by the simple movement of hand instead of distinct gestures. With an ordinary camera, the fist posture of hand is segmented out from the image stream using the optimal segmentation model. Like pressing a button with a thumb, the status of thumb is traced for the activation or deactivation of the interactions. After the activation of interaction, the trajectory of hand is followed to manipulate a virtual object about an arbitrary axis. Without training and comparison of gestures, the basic interactions required in a VE are performed by the perceptive movement of a hand. By incorporating image processing in the realm of VE, the technique is implemented in a case-study project; FIRST (Feasible Interaction by Recognizing the Status of Thumb). A group of 12 users evaluated the system in a moderate lighting condition. Outcomes of the evaluation revealed that the technique is suitable for Virtual Reality (VR) applications.
{"title":"GIST: Gesture-free Interaction by the Status of Thumb; an interaction technique for Virtual Environments","authors":"Muhammad Raees, S. Ullah, S. Rahman","doi":"10.33969/ais.2019.11008","DOIUrl":"https://doi.org/10.33969/ais.2019.11008","url":null,"abstract":"User interface has special importance in immersive virtual environments. Interactions based on the simple and conceivable gestures of a hand may enhance immersivity of a Virtual Environment (VE). However, due to the structural issues like small size and complex shape of human hand, recognition of hand gestures are more challenging. This work introduces a novel interaction technique to perform the basic interaction tasks by the simple movement of hand instead of distinct gestures. With an ordinary camera, the fist posture of hand is segmented out from the image stream using the optimal segmentation model. Like pressing a button with a thumb, the status of thumb is traced for the activation or deactivation of the interactions. After the activation of interaction, the trajectory of hand is followed to manipulate a virtual object about an arbitrary axis. Without training and comparison of gestures, the basic interactions required in a VE are performed by the perceptive movement of a hand. By incorporating image processing in the realm of VE, the technique is implemented in a case-study project; FIRST (Feasible Interaction by Recognizing the Status of Thumb). A group of 12 users evaluated the system in a moderate lighting condition. Outcomes of the evaluation revealed that the technique is suitable for Virtual Reality (VR) applications.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131464487","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}
Tanveer Hussain, Khan Muhammad, Salman Khan, Amin Ullah, Mi Young Lee, S. Baik
Mainstream Internet of Things (IoT) techniques for smart homes focus on appliances and surveillance in smart cities. Most of the researchers utilize vision sensors in IoT environment targeting only adult users for various applications such as abnormal activity recognition. This paper introduces a new paradigm in vision sensor IoT technologies by analyzing the behavior of baby through an intelligent multimodal system. Traditional wearable sensors such as heartbeat if attached to any body part of the baby make him uncomfortable and also some babies are paranoid toward sensors. Our vision based baby monitoring framework employs one of the process improvement techniques known as control charts to analyze the baby behavior. We construct control chart in a specific interval for real-time frames generated by Raspberry Pi (RPi) with attached vision sensor. Baby motion is represented through points on control chart, if it exceeds upper control limit (UCL) or falls from lower control limits (LCL), it indicates abnormal behavior of the baby. Whenever such a behavior is encountered, a signal is transmitted to the interconnected devices in IoT as an alert to baby care takers in smart health care centers. Our proposed framework is adaptable, a single RPi can be used to monitor a baby in home or a network of RPi’s for an IoT in a children nursery for multiple babies monitoring. Performance evaluation on our own created dataset indicates the better accuracy and efficiency of our proposed framework.
{"title":"Intelligent Baby Behavior Monitoring using Embedded Vision in IoT for Smart Healthcare Centers","authors":"Tanveer Hussain, Khan Muhammad, Salman Khan, Amin Ullah, Mi Young Lee, S. Baik","doi":"10.33969/ais.2019.11007","DOIUrl":"https://doi.org/10.33969/ais.2019.11007","url":null,"abstract":"Mainstream Internet of Things (IoT) techniques for smart homes focus on appliances and surveillance in smart cities. Most of the researchers utilize vision sensors in IoT environment targeting only adult users for various applications such as abnormal activity recognition. This paper introduces a new paradigm in vision sensor IoT technologies by analyzing the behavior of baby through an intelligent multimodal system. Traditional wearable sensors such as heartbeat if attached to any body part of the baby make him uncomfortable and also some babies are paranoid toward sensors. Our vision based baby monitoring framework employs one of the process improvement techniques known as control charts to analyze the baby behavior. We construct control chart in a specific interval for real-time frames generated by Raspberry Pi (RPi) with attached vision sensor. Baby motion is represented through points on control chart, if it exceeds upper control limit (UCL) or falls from lower control limits (LCL), it indicates abnormal behavior of the baby. Whenever such a behavior is encountered, a signal is transmitted to the interconnected devices in IoT as an alert to baby care takers in smart health care centers. Our proposed framework is adaptable, a single RPi can be used to monitor a baby in home or a network of RPi’s for an IoT in a children nursery for multiple babies monitoring. Performance evaluation on our own created dataset indicates the better accuracy and efficiency of our proposed framework.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127863943","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 medical field, the analysis and processing of medical images plays an important auxiliary role in the diagnosis of diseases. In recent years, more and more researchers have begun to pay attention to such processing technologies as pattern recognition, classification and segmentation in medical image processing. Cardiovascular disease is one of the most important diseases that endanger human health at present. It is very meaningful to diagnose and treat cardiovascular disease by means of in-depth learning. In order to make deep learning better applied to cardiovascular diseases, this paper first outlines the development and causes of cardiovascular diseases, then describes several theoretical models of deep learning, and then summarizes the application of deep learning in heart image segmentation, classification and other aspects combined with existing technologies. Finally, the future direction of development is prospected.
{"title":"Deep Learning Methods for Cardiovascular Image","authors":"Yankun Cao, Zhi Liu, Pengfei Zhang, Yushuo Zheng, Yongsheng Song, Li-zhen Cui","doi":"10.33969/ais.2019.11006","DOIUrl":"https://doi.org/10.33969/ais.2019.11006","url":null,"abstract":"In the medical field, the analysis and processing of medical images plays an important auxiliary role in the diagnosis of diseases. In recent years, more and more researchers have begun to pay attention to such processing technologies as pattern recognition, classification and segmentation in medical image processing. Cardiovascular disease is one of the most important diseases that endanger human health at present. It is very meaningful to diagnose and treat cardiovascular disease by means of in-depth learning. In order to make deep learning better applied to cardiovascular diseases, this paper first outlines the development and causes of cardiovascular diseases, then describes several theoretical models of deep learning, and then summarizes the application of deep learning in heart image segmentation, classification and other aspects combined with existing technologies. Finally, the future direction of development is prospected.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122726360","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}
A. G. Medeiros, Francisco H. S. Silva, E. F. Ohata, S. A. Peixoto, P. P. R. Filho
This work proposes a new adaptive approach to left ventricle segmentation based on a non-parametric adaptive active contour method called Fast Morphological Geodesic Active Contour (FGAC) combined with adaptive external energy via deep learning model. The evaluation methodology considered echocardiogram exams obtained from volunteers. Beyond the manual segmentations made by two specialists medical as ground truth. The new approach is compared with three other segmentation methods, also based on the active contour method: pSnakes, radial snakes with derivative (RSD), and radial snakes with Hilbert energy (RSH). The FGAC combined with adaptive external energy showed better Precision (99.53%, 99.72%) against RSD (99.46%, 99.68%), RSH (99.51%, 99.71%) and pSnakes (99.52%, 99.72%). Besides, it achieved a relevant Jaccard similarity index (67.40%, 62.02%), and promising accuracy (98.64%, 98.46%). Even though the metrics differences are low, the proposed approach is fully automatic. Therefore, these results suggest the potential of the proposed approach to aid medical diagnosis systems in echocardiology.
本文提出了一种基于非参数自适应活动轮廓法的左心室分割新方法——快速形态测地线活动轮廓法(Fast Morphological Geodesic active contour, FGAC),结合深度学习模型的自适应外部能量。评估方法考虑了志愿者的超声心动图检查结果。超越手工分割,由两位专家医学作为地面真相。将该方法与其他三种基于活动轮廓法的分割方法进行了比较:pSnakes、径向导数蛇(RSD)和径向希尔伯特能量蛇(RSH)。与RSD(99.46%、99.68%)、RSH(99.51%、99.71%)和pSnakes(99.52%、99.72%)相比,FGAC结合自适应外源能的检测精度分别为99.53%、99.72%。此外,该方法获得了相关的Jaccard相似度指数(67.40%,62.02%),准确率为98.64%,98.46%。尽管度量差异很小,但所建议的方法是完全自动的。因此,这些结果表明,所提出的方法的潜力,以协助医疗诊断系统的超声心动学。
{"title":"An Automatic Left Ventricle Segmentation on Echocardiogram Exams via Morphological Geodesic Active Contour with Adaptive External Energy","authors":"A. G. Medeiros, Francisco H. S. Silva, E. F. Ohata, S. A. Peixoto, P. P. R. Filho","doi":"10.33969/ais.2019.11005","DOIUrl":"https://doi.org/10.33969/ais.2019.11005","url":null,"abstract":"This work proposes a new adaptive approach to left ventricle segmentation based on a non-parametric adaptive active contour method called Fast Morphological Geodesic Active Contour (FGAC) combined with adaptive external energy via deep learning model. The evaluation methodology considered echocardiogram exams obtained from volunteers. Beyond the manual segmentations made by two specialists medical as ground truth. The new approach is compared with three other segmentation methods, also based on the active contour method: pSnakes, radial snakes with derivative (RSD), and radial snakes with Hilbert energy (RSH). The FGAC combined with adaptive external energy showed better Precision (99.53%, 99.72%) against RSD (99.46%, 99.68%), RSH (99.51%, 99.71%) and pSnakes (99.52%, 99.72%). Besides, it achieved a relevant Jaccard similarity index (67.40%, 62.02%), and promising accuracy (98.64%, 98.46%). Even though the metrics differences are low, the proposed approach is fully automatic. Therefore, these results suggest the potential of the proposed approach to aid medical diagnosis systems in echocardiology.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130642105","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 study addressed the output regulation issue of linear heterogeneous multi-agent systems under switching topology. All agents excluding the external system are divided into two groups with measurable agents or unmeasurable agents. The agents’ states in the first group can be available for measurement while the agents’ states in the second group are unmeasurable. For the second group, a full-order Luenberger observer is devised to recover these agents’ states. Moreover, there are some agents that can not receive the information from the exosystem directly, thus, a dynamic compensator is constructed for these agents. Based on the proposed observer and compensator, a hybrid feedback control strategy is put forward to settle the output regulation issue. Furthermore, the information interaction among agents is expressed by the switching topology, and the topology is assumed to be jointly connected. Finally, two numerical examples are given to illustrate the feasibility of the theoretical results. The results show that whether the states are measurable or not, the proposed control strategy can address the output regulation issue of linear heterogeneous MASs under switching topology. Moreover, the comparative experiment indicates that our method obtains superior performance in terms of convergence speed, and is more efficient in dealing with practical problems.
{"title":"Full-order observer-based output regulation for linear heterogeneous multi-agent systems under switching topology","authors":"Yuliang Cai, Qiang He, Jie Duan, Zhiyun Gao","doi":"10.33969/AIS.2019.11002","DOIUrl":"https://doi.org/10.33969/AIS.2019.11002","url":null,"abstract":"This study addressed the output regulation issue of linear heterogeneous multi-agent systems under switching topology. All agents excluding the external system are divided into two groups with measurable agents or unmeasurable agents. The agents’ states in the first group can be available for measurement while the agents’ states in the second group are unmeasurable. For the second group, a full-order Luenberger observer is devised to recover these agents’ states. Moreover, there are some agents that can not receive the information from the exosystem directly, thus, a dynamic compensator is constructed for these agents. Based on the proposed observer and compensator, a hybrid feedback control strategy is put forward to settle the output regulation issue. Furthermore, the information interaction among agents is expressed by the switching topology, and the topology is assumed to be jointly connected. Finally, two numerical examples are given to illustrate the feasibility of the theoretical results. The results show that whether the states are measurable or not, the proposed control strategy can address the output regulation issue of linear heterogeneous MASs under switching topology. Moreover, the comparative experiment indicates that our method obtains superior performance in terms of convergence speed, and is more efficient in dealing with practical problems.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117081253","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}
color rgb, text-indent px, letter-spacing normal, font-family Helvetica, font-size px, font-style normal, font-weight, word-spacing px, display inline important, white-space normal, orphans, widows, background-color rgb, font-variant-ligatures normal, font-variant-ligatures normal, webkit-text-stroke-width px, text-decoration-style initial, text-decoration-color initial, P. H. F. D. Sousa, Navar de Medeiros M. e Nascimento sup, Jefferson S. Almeida sup, Pedro P. Rebouças Filho sup, Victor Hugo C. de Albuquerque sup, span
The eagerness and necessity to develop so-called smart applications has taken the Internet of Things (IoT) to a whole new level. Industry has been implementing services that use IoT to increase productivity as well as management systems over the past couple of years. Such services are now encroaching on wind energy, which nowadays is the most acceptable source among renewable energies for electricity generation. This work proposes an intelligent system to identify incipient faults in the electric generators of wind turbines to improve maintenance routines. Four feature extraction methods were applied to vibration signals, and different classifiers were used to predict the running status of the wind turbine. We correctly identified 94.44% of normal conditions, reducing the false positive and negative rates to 0.4% and 1.84%, respectively; a better result than other approaches already reported in the literature.
{"title":"Intelligent Incipient Fault Detection in Wind Turbines based on Industrial IoT Environment","authors":"color rgb, text-indent px, letter-spacing normal, font-family Helvetica, font-size px, font-style normal, font-weight, word-spacing px, display inline important, white-space normal, orphans, widows, background-color rgb, font-variant-ligatures normal, font-variant-ligatures normal, webkit-text-stroke-width px, text-decoration-style initial, text-decoration-color initial, P. H. F. D. Sousa, Navar de Medeiros M. e Nascimento sup, Jefferson S. Almeida sup, Pedro P. Rebouças Filho sup, Victor Hugo C. de Albuquerque sup, span","doi":"10.33969/AIS.2019.11001","DOIUrl":"https://doi.org/10.33969/AIS.2019.11001","url":null,"abstract":"The eagerness and necessity to develop so-called smart applications has taken the Internet of Things (IoT) to a whole new level. Industry has been implementing services that use IoT to increase productivity as well as management systems over the past couple of years. Such services are now encroaching on wind energy, which nowadays is the most acceptable source among renewable energies for electricity generation. This work proposes an intelligent system to identify incipient faults in the electric generators of wind turbines to improve maintenance routines. Four feature extraction methods were applied to vibration signals, and different classifiers were used to predict the running status of the wind turbine. We correctly identified 94.44% of normal conditions, reducing the false positive and negative rates to 0.4% and 1.84%, respectively; a better result than other approaches already reported in the literature.","PeriodicalId":273028,"journal":{"name":"Journal of Artificial Intelligence and Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116232586","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}