Pub Date : 2022-02-13DOI: 10.1080/0952813X.2021.1960628
Xi Wang, Yu Zhao, Guangping Zeng, Peng Xiao, Zhiliang Wang
ABSTRACT This paper applies machine learning technology to the Satir theory model and intelligently classifies the communication stances of the second layer according to the language and behaviour information of the first layer. We arranged a large number of dialogical language materials from a TV interview programme and used the ICTCLAS Chinese word segmentation system to create a ‘psychological consultation database’. We construct the word training set by part of making use of speech filtering and text word vectorisation, and construct the semantic training set by annotating the original data with the Satir model. These two sets form the Satir communication posture classification training set. Experimental results show that the success rate of classification of four inconsistent coping stances reached 70.37%, 75.92%, 83.33%, and 77.78%.
{"title":"Study on the classification problem of the coping stances in the Satir model based on machine learning","authors":"Xi Wang, Yu Zhao, Guangping Zeng, Peng Xiao, Zhiliang Wang","doi":"10.1080/0952813X.2021.1960628","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960628","url":null,"abstract":"ABSTRACT This paper applies machine learning technology to the Satir theory model and intelligently classifies the communication stances of the second layer according to the language and behaviour information of the first layer. We arranged a large number of dialogical language materials from a TV interview programme and used the ICTCLAS Chinese word segmentation system to create a ‘psychological consultation database’. We construct the word training set by part of making use of speech filtering and text word vectorisation, and construct the semantic training set by annotating the original data with the Satir model. These two sets form the Satir communication posture classification training set. Experimental results show that the success rate of classification of four inconsistent coping stances reached 70.37%, 75.92%, 83.33%, and 77.78%.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"83 1","pages":"129 - 149"},"PeriodicalIF":2.2,"publicationDate":"2022-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86947946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-13DOI: 10.1080/0952813X.2021.1960625
Enjie Ding, Dawei Xu, Yingfei Zhao, Zhongyu Liu, Yafeng Liu
ABSTRACT Being simple and portable, the three-dimensional (3D) convolution network has achieved great success in action recognition. However, its applicability in spatiotemporal feature learning is not evident. This study aims to improve the 3D convolution model and propose a flexible and significant attention module for the extraction of spatiotemporal information. Our first contribution is a self-additive attention module and a feature-based attention module, which is a simple yet effective method for measuring the spatiotemporal importance of a video. In self-additive attention, the spatiotemporal fusion between the frames is defined intuitively, where we set equivalent weights between the video frames manually. Further, the feature-based attention that is trained adaptively by the 3D convolution process combines the spatiotemporal information from the feature map. This study also focuses on attention fusion in learning the spatiotemporal characteristics for 3D convolution. The proposed attention fusion method exhibits outstanding performance in comparison to the recently developed attention modules and the latest 3D networks when applied to the data from the UCF101 and HMDB51 datasets. The experiments show consistent improvements, affirming the robustness of the method in extracting spatiotemporal attention.
{"title":"Attention-based 3D convolutional networks","authors":"Enjie Ding, Dawei Xu, Yingfei Zhao, Zhongyu Liu, Yafeng Liu","doi":"10.1080/0952813X.2021.1960625","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960625","url":null,"abstract":"ABSTRACT Being simple and portable, the three-dimensional (3D) convolution network has achieved great success in action recognition. However, its applicability in spatiotemporal feature learning is not evident. This study aims to improve the 3D convolution model and propose a flexible and significant attention module for the extraction of spatiotemporal information. Our first contribution is a self-additive attention module and a feature-based attention module, which is a simple yet effective method for measuring the spatiotemporal importance of a video. In self-additive attention, the spatiotemporal fusion between the frames is defined intuitively, where we set equivalent weights between the video frames manually. Further, the feature-based attention that is trained adaptively by the 3D convolution process combines the spatiotemporal information from the feature map. This study also focuses on attention fusion in learning the spatiotemporal characteristics for 3D convolution. The proposed attention fusion method exhibits outstanding performance in comparison to the recently developed attention modules and the latest 3D networks when applied to the data from the UCF101 and HMDB51 datasets. The experiments show consistent improvements, affirming the robustness of the method in extracting spatiotemporal attention.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"13 1","pages":"93 - 108"},"PeriodicalIF":2.2,"publicationDate":"2022-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83486113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-13DOI: 10.1080/0952813X.2021.1960639
A. Saffari, S. Zahiri, M. Khishe
ABSTRACT In this paper, a radial basis function neural network (RBF-NN) automatic sonar target recognition system is proposed. For the RBF-NN training phase, a whale optimisation algorithm (WOA) developed with a fuzzy system has been used (which is called FWOA). The reason for using the fuzzy system is the lack of correct identification of the boundary between the two stages of exploration and exploitation. Thus, the tuning of the effective parameters of the WOA is left to the fuzzy system of the Mamdani type. RBF-NN was trained by chimp optimisation algorithm (ChOA), genetic algorithm (GA), Evolution Strategy (ES), league championship algorithm (LCA), grey wolf algorithms (GWO), gravitational search algorithm (GSA), and WOA to compare the proposed algorithm. The measured criteria are convergence speed, ability to avoid local optimisation, and classification rate. The simulation results showed that FWOA with 97.49% classification accuracy rate in sonar data performed better than the other seven benchmark algorithms.
{"title":"Fuzzy whale optimisation algorithm: a new hybrid approach for automatic sonar target recognition","authors":"A. Saffari, S. Zahiri, M. Khishe","doi":"10.1080/0952813X.2021.1960639","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960639","url":null,"abstract":"ABSTRACT In this paper, a radial basis function neural network (RBF-NN) automatic sonar target recognition system is proposed. For the RBF-NN training phase, a whale optimisation algorithm (WOA) developed with a fuzzy system has been used (which is called FWOA). The reason for using the fuzzy system is the lack of correct identification of the boundary between the two stages of exploration and exploitation. Thus, the tuning of the effective parameters of the WOA is left to the fuzzy system of the Mamdani type. RBF-NN was trained by chimp optimisation algorithm (ChOA), genetic algorithm (GA), Evolution Strategy (ES), league championship algorithm (LCA), grey wolf algorithms (GWO), gravitational search algorithm (GSA), and WOA to compare the proposed algorithm. The measured criteria are convergence speed, ability to avoid local optimisation, and classification rate. The simulation results showed that FWOA with 97.49% classification accuracy rate in sonar data performed better than the other seven benchmark algorithms.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"83 9 1","pages":"309 - 325"},"PeriodicalIF":2.2,"publicationDate":"2022-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89601179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-09DOI: 10.1080/0952813X.2021.1960635
A. S. Rashid
ABSTRACT The purpose of this study to utilising Machine learning to discover knowledge which is called supervised and unsupervised learning when it is taught the actual outcome for the training instances like progressed or non-progressed performance and investigate the impact of the quality assurance process on the teacher’s academic performance utilising teaching methods, student feedback, teacher portfolio, and academic benchmarks. Moreover, it aims to assess and improve the academic staff members performing the Accreditation Evaluation System (AES) that involves Student Feedback System (SFS), Teacher Portfolio Assessment (TPA), as well as Continuous Academic Development (CAD) for the academic year (2016–2017) which compiled of (1556) academic staff at the University of Sulaimani. Overall, the conclusions of this study confirmed that the quality assurance has progressed, and enhanced the quality of the teacher performance, also reinforces all dimensions of the teaching, academic, and research performance of teachers by applying the K-Means Clustering Algorithm methodology to analyse and assemble a big data according to the teacher academic titles. In addition, the binary logistic regression analysis was executed to reveal and prophesy the significant influences of academic titles on the teacher progression of the Accreditation Evaluation System performance. The K-Means Clustering Algorithm showed better results than Logistic regression by having 90% testing accuracy. In the future, Un-Supervised Learning can be used for better accuracy.
{"title":"The extent of the teacher academic development from the accreditation evaluation system perspective using machine learning","authors":"A. S. Rashid","doi":"10.1080/0952813X.2021.1960635","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960635","url":null,"abstract":"ABSTRACT The purpose of this study to utilising Machine learning to discover knowledge which is called supervised and unsupervised learning when it is taught the actual outcome for the training instances like progressed or non-progressed performance and investigate the impact of the quality assurance process on the teacher’s academic performance utilising teaching methods, student feedback, teacher portfolio, and academic benchmarks. Moreover, it aims to assess and improve the academic staff members performing the Accreditation Evaluation System (AES) that involves Student Feedback System (SFS), Teacher Portfolio Assessment (TPA), as well as Continuous Academic Development (CAD) for the academic year (2016–2017) which compiled of (1556) academic staff at the University of Sulaimani. Overall, the conclusions of this study confirmed that the quality assurance has progressed, and enhanced the quality of the teacher performance, also reinforces all dimensions of the teaching, academic, and research performance of teachers by applying the K-Means Clustering Algorithm methodology to analyse and assemble a big data according to the teacher academic titles. In addition, the binary logistic regression analysis was executed to reveal and prophesy the significant influences of academic titles on the teacher progression of the Accreditation Evaluation System performance. The K-Means Clustering Algorithm showed better results than Logistic regression by having 90% testing accuracy. In the future, Un-Supervised Learning can be used for better accuracy.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"16 1","pages":"535 - 555"},"PeriodicalIF":2.2,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73894843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-09DOI: 10.1080/0952813X.2021.1960634
Aysha Shabbir, Maryam Shabbir, A. R. Javed, M. Rizwan, C. Iwendi, Chinmay Chakraborty
ABSTRACT The proportion of COVID-19 patients is significantly expanding around the world. Treatment with serious consideration has become a significant problem. Identifying clinical indicators of succession towards severe conditions is desperately required to empower hazard stratification and optimise resource allocation in the pandemic of COVID-19. Consequently, the classification of severity level is significant for the patient’s triaging. It is required to categorise the severity level as mild, moderate, severe, and critical based on the patients’ symptoms. Various symptomatic parameters may encourage the evaluation of infection seriousness. Likewise, with the rapid spread and transmissibility of COVID-19 patients, it is crucial to utilise telemonitoring schemes for COVID-19 patients. Telemonitoring mediation encourages remote data and information exchange among medicinal services, suppliers, and patients, furthermore, risk mitigation and provision of appropriate medical facilities. This paper provides explorative data analysis of symptoms, comorbidities, and other parameters, comparing different machine learning algorithms for case severity detection. This paper also provides a system (based on the degree of truthfulness) for case severity detection that might be utilised to stratify risk levels for anticipated moderate and severe COVID-19 patients. Finally, we provide a telemonitoring model of COVID-19 patients to ensure the remote and continuous monitoring of case severity progression and appropriate risk mitigation strategies.
{"title":"Exploratory data analysis, classification, comparative analysis, case severity detection, and internet of things in COVID-19 telemonitoring for smart hospitals","authors":"Aysha Shabbir, Maryam Shabbir, A. R. Javed, M. Rizwan, C. Iwendi, Chinmay Chakraborty","doi":"10.1080/0952813X.2021.1960634","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960634","url":null,"abstract":"ABSTRACT The proportion of COVID-19 patients is significantly expanding around the world. Treatment with serious consideration has become a significant problem. Identifying clinical indicators of succession towards severe conditions is desperately required to empower hazard stratification and optimise resource allocation in the pandemic of COVID-19. Consequently, the classification of severity level is significant for the patient’s triaging. It is required to categorise the severity level as mild, moderate, severe, and critical based on the patients’ symptoms. Various symptomatic parameters may encourage the evaluation of infection seriousness. Likewise, with the rapid spread and transmissibility of COVID-19 patients, it is crucial to utilise telemonitoring schemes for COVID-19 patients. Telemonitoring mediation encourages remote data and information exchange among medicinal services, suppliers, and patients, furthermore, risk mitigation and provision of appropriate medical facilities. This paper provides explorative data analysis of symptoms, comorbidities, and other parameters, comparing different machine learning algorithms for case severity detection. This paper also provides a system (based on the degree of truthfulness) for case severity detection that might be utilised to stratify risk levels for anticipated moderate and severe COVID-19 patients. Finally, we provide a telemonitoring model of COVID-19 patients to ensure the remote and continuous monitoring of case severity progression and appropriate risk mitigation strategies.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"1 1","pages":"507 - 534"},"PeriodicalIF":2.2,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77218882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-09DOI: 10.1080/0952813X.2021.1960636
Mohammed Al-Nehari, Guoxing Liang, Yonggui Huang, M. Lv, Waled Yahya
ABSTRACT The high-speed grinding and polishing machine can not only significantly increase the performance of grinding but also improve the consistency of processing effectively. It is one of the most significant guidelines for the advancement of grinding technology today. Since the high-speed grinding technology has been booming these days, this study develops intermittent high-speed grinding technique for feed which has been under the basic high-speed grinding process. Using a simple list of a straight line, a piece of work can be easily retreated and fed. By affordable arrangement distance of feed-in single grinding, time of action on grinding work piece and grinding wheel has been reduced, it will affect the process of grinding heat sending that does not get fixed sate, it was decreasing grinding temperature at the time of single grinding, the surface temperature was freezer to the closed room temperature throughout the room. The lower grinding temperature was achieved according to this path. The simulation study and experiment were performed on TC4 titanium alloy materials in intermittent high-speed feed grinding, and critics of grinding elements considered grinding temperature along with grinding force have been implemented as end production using finite element analysis of the particle swarm optimization (PSO) basis.
{"title":"Intelligent computational of Experimental Study of Intermittent Feed High-speed Grinding Method utilising PSO basis FEM Solver","authors":"Mohammed Al-Nehari, Guoxing Liang, Yonggui Huang, M. Lv, Waled Yahya","doi":"10.1080/0952813X.2021.1960636","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960636","url":null,"abstract":"ABSTRACT The high-speed grinding and polishing machine can not only significantly increase the performance of grinding but also improve the consistency of processing effectively. It is one of the most significant guidelines for the advancement of grinding technology today. Since the high-speed grinding technology has been booming these days, this study develops intermittent high-speed grinding technique for feed which has been under the basic high-speed grinding process. Using a simple list of a straight line, a piece of work can be easily retreated and fed. By affordable arrangement distance of feed-in single grinding, time of action on grinding work piece and grinding wheel has been reduced, it will affect the process of grinding heat sending that does not get fixed sate, it was decreasing grinding temperature at the time of single grinding, the surface temperature was freezer to the closed room temperature throughout the room. The lower grinding temperature was achieved according to this path. The simulation study and experiment were performed on TC4 titanium alloy materials in intermittent high-speed feed grinding, and critics of grinding elements considered grinding temperature along with grinding force have been implemented as end production using finite element analysis of the particle swarm optimization (PSO) basis.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"10 1","pages":"557 - 571"},"PeriodicalIF":2.2,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78483252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-09DOI: 10.1080/0952813X.2021.1960641
Anup Patnaik, Banitamani Mallik, M. Krishna
ABSTRACT The new emerging blockchain (BC) technology integrated with the IoT ecosystem revolutionised the IoT world. Classic BC with bitcoin method was realised as very expensive operations difficult to adopt for smart IoT applications; therefore, we integrated IoT network with overlay BC with distributed ledger capability to provide a secure trust management system, which can address access control issues of devices on resources. Further, the R-LEACH protocol followed by the same group urges additional cluster head requirement to establish trust between nodes is not considered in our proposed approach. The main advantage of this method is utilising ledgers for holding the trust and IoT information ensuring tamper-proof data. The miners of blockchain layer perform the trust value calculations based on trust evidence and achieved fast trust convergence, accuracy, and resilience against adversary attacks. Our proposed approach enhances privacy, reliability, availability, and more importantly, sharing and storage of trust information and also followed the consensus mechanism Proof-of-Authority (PoA) to approve the synthesis trust value of related transactions by the pre-authenticated miners/validators, from which we can take more accurate trust-based decisions. Performance results of our blockchain-based trust management approach outperformed literature review trust mechanisms for protecting trust data manipulation against the malicious nodes.
{"title":"Blockchain based holistic trust management protocol for ubiquitous and pervasive IoT network","authors":"Anup Patnaik, Banitamani Mallik, M. Krishna","doi":"10.1080/0952813X.2021.1960641","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960641","url":null,"abstract":"ABSTRACT The new emerging blockchain (BC) technology integrated with the IoT ecosystem revolutionised the IoT world. Classic BC with bitcoin method was realised as very expensive operations difficult to adopt for smart IoT applications; therefore, we integrated IoT network with overlay BC with distributed ledger capability to provide a secure trust management system, which can address access control issues of devices on resources. Further, the R-LEACH protocol followed by the same group urges additional cluster head requirement to establish trust between nodes is not considered in our proposed approach. The main advantage of this method is utilising ledgers for holding the trust and IoT information ensuring tamper-proof data. The miners of blockchain layer perform the trust value calculations based on trust evidence and achieved fast trust convergence, accuracy, and resilience against adversary attacks. Our proposed approach enhances privacy, reliability, availability, and more importantly, sharing and storage of trust information and also followed the consensus mechanism Proof-of-Authority (PoA) to approve the synthesis trust value of related transactions by the pre-authenticated miners/validators, from which we can take more accurate trust-based decisions. Performance results of our blockchain-based trust management approach outperformed literature review trust mechanisms for protecting trust data manipulation against the malicious nodes.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"124 1","pages":"629 - 648"},"PeriodicalIF":2.2,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87889817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-08DOI: 10.1080/0952813X.2021.1960640
W. Farag
ABSTRACT In this paper, the Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithm is employed to enable a double-jointed robot arm to reach continuously changing target locations. The experimentation of the algorithm is carried out by training an agent to control the movement of this double-jointed robot arm. The architectures of the actor and cretic networks are meticulously designed and the DDPG hyperparameters are carefully tuned. An enhanced version of the DDPG is also presented to handle multiple robot arms simultaneously. The trained agents are successfully tested in the Unity Machine Learning Agents environment for controlling both a single robot arm as well as multiple simultaneous robot arms. The testing shows the robust performance of the DDPG algorithm for empowering robot arm manoeuvring in complex environments.
{"title":"Robot arm navigation using deep deterministic policy gradient algorithms","authors":"W. Farag","doi":"10.1080/0952813X.2021.1960640","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960640","url":null,"abstract":"ABSTRACT In this paper, the Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithm is employed to enable a double-jointed robot arm to reach continuously changing target locations. The experimentation of the algorithm is carried out by training an agent to control the movement of this double-jointed robot arm. The architectures of the actor and cretic networks are meticulously designed and the DDPG hyperparameters are carefully tuned. An enhanced version of the DDPG is also presented to handle multiple robot arms simultaneously. The trained agents are successfully tested in the Unity Machine Learning Agents environment for controlling both a single robot arm as well as multiple simultaneous robot arms. The testing shows the robust performance of the DDPG algorithm for empowering robot arm manoeuvring in complex environments.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"1 1","pages":"617 - 627"},"PeriodicalIF":2.2,"publicationDate":"2022-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89576481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-06DOI: 10.1080/0952813X.2021.2021300
Dilbag Singh, Vijay Kumar, Manjit Kaur, R. Kumari
ABSTRACT Coronavirus disease-19 (COVID-19) has rapidly spread all over the world. It is found that the low sensitivity of reverse transcription-polymerase chain reaction (RT-PCR) examinations during the early stage of COVID-19 disease. Thus, efficient models are desirable for early-stage testing of COVID-19 infected patients. Chest X-ray (CXR) images of COVID-19 infected patients have shown some bilateral changes. In this paper, deep transfer learning and a deep forest-based model are proposed to diagnose COVID-19 infection from CXR images. Initially, features of X-ray images are extracted using the well-known deep transfer learning model (i.e., ResNet101), which does not require tuning many parameters compared to the deep convolutional neural network (CNN). After that, the deep forest model is utilised to predict COVID-19 infected patients. The deep forest is based upon ensemble learning and requires a small number of hyper-parameters. Additionally, the proposed model is trained on a multi-class dataset that contains four different classes as COVID-19 (+), pneumonia, tuberculosis, and healthy patients. The comparisons are drawn among the proposed deep transfer learning and deep forest-based models, the competitive models. The obtained results show that the proposed model effectively diagnoses COVID-19 infection with an accuracy of 99.4%.
{"title":"Early diagnosis of COVID-19 patients using deep learning-based deep forest model","authors":"Dilbag Singh, Vijay Kumar, Manjit Kaur, R. Kumari","doi":"10.1080/0952813X.2021.2021300","DOIUrl":"https://doi.org/10.1080/0952813X.2021.2021300","url":null,"abstract":"ABSTRACT Coronavirus disease-19 (COVID-19) has rapidly spread all over the world. It is found that the low sensitivity of reverse transcription-polymerase chain reaction (RT-PCR) examinations during the early stage of COVID-19 disease. Thus, efficient models are desirable for early-stage testing of COVID-19 infected patients. Chest X-ray (CXR) images of COVID-19 infected patients have shown some bilateral changes. In this paper, deep transfer learning and a deep forest-based model are proposed to diagnose COVID-19 infection from CXR images. Initially, features of X-ray images are extracted using the well-known deep transfer learning model (i.e., ResNet101), which does not require tuning many parameters compared to the deep convolutional neural network (CNN). After that, the deep forest model is utilised to predict COVID-19 infected patients. The deep forest is based upon ensemble learning and requires a small number of hyper-parameters. Additionally, the proposed model is trained on a multi-class dataset that contains four different classes as COVID-19 (+), pneumonia, tuberculosis, and healthy patients. The comparisons are drawn among the proposed deep transfer learning and deep forest-based models, the competitive models. The obtained results show that the proposed model effectively diagnoses COVID-19 infection with an accuracy of 99.4%.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"14 1","pages":"365 - 375"},"PeriodicalIF":2.2,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89236639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-31DOI: 10.1080/0952813X.2021.1970239
Francesco Percassi, A. Gerevini, Enrico Scala, I. Serina, M. Vallati
ABSTRACT Automated planning is a prominent Artificial Intelligence (AI) challenge that has been extensively studied for decades, which has led to the development of powerful domain-independent planning systems. The performance of domain-independent planning systems are strongly affected by the structure of the search space, that is dependent on the application domain and on its encoding. This paper proposes and investigates a novel way of combining machine learning and heuristic search to improve domain-independent planning. On the learning side, we use learning to predict the plan cost of a good solution for a given instance. On the planning side, we propose a bound-sensitive heuristic function that exploits such a prediction in a state-space planner. Our function combines the input prediction (derived inductively) with some pieces of information gathered during search (derived deductively). As the prediction can sometimes be grossly inaccurate, the function also provides means to recognise when the provided information is actually misguiding the search. Our experimental analysis demonstrates the usefulness of the proposed approach in a standard heuristic best-first search schema.
{"title":"Improving Domain-Independent Heuristic State-Space Planning via plan cost predictions","authors":"Francesco Percassi, A. Gerevini, Enrico Scala, I. Serina, M. Vallati","doi":"10.1080/0952813X.2021.1970239","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1970239","url":null,"abstract":"ABSTRACT Automated planning is a prominent Artificial Intelligence (AI) challenge that has been extensively studied for decades, which has led to the development of powerful domain-independent planning systems. The performance of domain-independent planning systems are strongly affected by the structure of the search space, that is dependent on the application domain and on its encoding. This paper proposes and investigates a novel way of combining machine learning and heuristic search to improve domain-independent planning. On the learning side, we use learning to predict the plan cost of a good solution for a given instance. On the planning side, we propose a bound-sensitive heuristic function that exploits such a prediction in a state-space planner. Our function combines the input prediction (derived inductively) with some pieces of information gathered during search (derived deductively). As the prediction can sometimes be grossly inaccurate, the function also provides means to recognise when the provided information is actually misguiding the search. Our experimental analysis demonstrates the usefulness of the proposed approach in a standard heuristic best-first search schema.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"91 1","pages":"849 - 875"},"PeriodicalIF":2.2,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73558074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：