In order to evaluate the effectiveness of exoskeleton design, a detailed evaluation of human biomechanics is necessary. In this paper, an unpowered exoskeleton of the knee joint is designed. A simplified 5-bar model of the lower limb is used to establish a walking kinematics model, and the change equation of knee angle is obtained. The curve of the knee angle is obtained through Matlab simulation and Visual 3D software. The simulation results are similar to the experiment, and the change curve of knee angle is consistent with the test results of human walking. It shows that the simplified model and simulation test is reasonable and effective, and conform to the walking process of human lower limbs. The activation and metabolism of lower limb muscles in three wearing states were obtained by using the OpenSim software, and the muscle activation was compared with the EMG test. The experimental results show that the exoskeletons in the gait cycle have different effects on the muscles of the lower limbs. The exoskeletons can provide assisted force for walking, reducing muscle activity and metabolic rate.
{"title":"Simulation and biomechanical evaluation of unpowered knee assisted exoskeleton","authors":"Xinyao Tang, Xupeng Wang, Yawen Zhou","doi":"10.1145/3570773.3570882","DOIUrl":"https://doi.org/10.1145/3570773.3570882","url":null,"abstract":"In order to evaluate the effectiveness of exoskeleton design, a detailed evaluation of human biomechanics is necessary. In this paper, an unpowered exoskeleton of the knee joint is designed. A simplified 5-bar model of the lower limb is used to establish a walking kinematics model, and the change equation of knee angle is obtained. The curve of the knee angle is obtained through Matlab simulation and Visual 3D software. The simulation results are similar to the experiment, and the change curve of knee angle is consistent with the test results of human walking. It shows that the simplified model and simulation test is reasonable and effective, and conform to the walking process of human lower limbs. The activation and metabolism of lower limb muscles in three wearing states were obtained by using the OpenSim software, and the muscle activation was compared with the EMG test. The experimental results show that the exoskeletons in the gait cycle have different effects on the muscles of the lower limbs. The exoskeletons can provide assisted force for walking, reducing muscle activity and metabolic rate.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132173125","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}
Purpose of review: Artificial intelligence (AI), a hot area of research today, has been attempted to be applied in various fields of clinical medicine. This paper reviews the current status of research on AI in mental health and mental illness, including applications in the prevention, supplementary diagnosis, treatment and rehabilitation of mental illness. It also discusses the advantages, shortcomings and prospects of AI applications in the field of mental disorders, in order to provide references for research related to mental health applications based on AI technology. Research methods: The literature on the application of AI in mental illness interventions in recent years was searched through literature navigation. The aspects of mental illness prevention, diagnosis and treatment interventions were analyzed. Research conclusion: AI technology is developing rapidly and can complement the advantages of artificial diagnosis and treatment. However, AI still has a lot of room for development and has shortcomings at this stage that may bring some problems, such as algorithm bias, ethical aspects and difficulty in promotion at this stage. As mental health practitioners, we should actively adapt to and promote the further development of AI in the mental health field.
{"title":"Application of artificial intelligence in mental health and mental illnesses","authors":"Xishuang Feng, Maorong Hu, Wanhui Guo","doi":"10.1145/3570773.3570834","DOIUrl":"https://doi.org/10.1145/3570773.3570834","url":null,"abstract":"Purpose of review: Artificial intelligence (AI), a hot area of research today, has been attempted to be applied in various fields of clinical medicine. This paper reviews the current status of research on AI in mental health and mental illness, including applications in the prevention, supplementary diagnosis, treatment and rehabilitation of mental illness. It also discusses the advantages, shortcomings and prospects of AI applications in the field of mental disorders, in order to provide references for research related to mental health applications based on AI technology. Research methods: The literature on the application of AI in mental illness interventions in recent years was searched through literature navigation. The aspects of mental illness prevention, diagnosis and treatment interventions were analyzed. Research conclusion: AI technology is developing rapidly and can complement the advantages of artificial diagnosis and treatment. However, AI still has a lot of room for development and has shortcomings at this stage that may bring some problems, such as algorithm bias, ethical aspects and difficulty in promotion at this stage. As mental health practitioners, we should actively adapt to and promote the further development of AI in the mental health field.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128284887","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}
Cardiovascular disease has been a major killer threatening human life and health. This paper is devoted to studying the characteristics of patients with cardiovascular diseases and classifying them by physical examination indicators. K-means algorithm is uesd to analyze the characteristics and xgboost is used to form a better classifier. The effect of the models are evaluated by relevant indexes. The experimental results show that, compared with normal people, patients with cardiovascular diseases have three characteristics: an older age, higher blood pressure, and heavier weight. Meanwhile, systolic blood pressure, cholesterol, and age are three important indicators for the classification of cardiovascular diseases.
{"title":"Identification of Cardiovascular Diseases Based on Machine Learning","authors":"Yubin Wang","doi":"10.1145/3570773.3570855","DOIUrl":"https://doi.org/10.1145/3570773.3570855","url":null,"abstract":"Cardiovascular disease has been a major killer threatening human life and health. This paper is devoted to studying the characteristics of patients with cardiovascular diseases and classifying them by physical examination indicators. K-means algorithm is uesd to analyze the characteristics and xgboost is used to form a better classifier. The effect of the models are evaluated by relevant indexes. The experimental results show that, compared with normal people, patients with cardiovascular diseases have three characteristics: an older age, higher blood pressure, and heavier weight. Meanwhile, systolic blood pressure, cholesterol, and age are three important indicators for the classification of cardiovascular diseases.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128565396","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}
Jixian Zheng, Sufei Song, Anni Zheng, Cui Cong, T. Sun, Qiu-ling Xu, Tao Liu
Introduction: Metabolism-associated lipid disorders (MAFLD) are the most common form of liver disease. Traditional Chinese medicine (TCM) has obvious efficacy in the treatment of MAFLD, but its therapeutic mechanism is unclear. The dosage regimen and potential mechanism of action of TCM for the treatment of MAFLD can be investigated using data mining methods. Methods: The literature related to TCM for the treatment of MAFLD in China Knowledge Network (CNKI), WANFANG Data and PUBMED in the last ten years were searched. The the frequency of drug use and its efficacy, flavour, and attribution were counted, and an analysis of high-frequency drug associations, cluster analysis, and factor analysis were conducted, respectively. Results: The top 6 single herbs of frequency are Poria, Licorice, Atractylodes Macrocephala, Bupleurum, Alisma, and Dried Tangerine Peel; the top 3 in frequency are tonic drugs, diuretic and dampening drugs, and blood stasis-activating drugs. The correlation analysis produced 4 association rules for drug combinations, 30 association rules for the three-flavour group and 18 association rules for the four-flavour group, which are related to Sijunzi Decoction, Erchen Decoction, Chaihu Shugan Powder. Hierarchical cluster analysis divides TCM into 5 categories, which are related to Taohong Siwu Decoction, Gegen Qinlian Decoction, Sini Powder, etc. The 8 drug groups obtained from the factor analysis reflect the treatment methods of strengthening spleen and soothing liver, eliminating dampness, and eliminating phlegm. Conclusion: Chinese drugs with the effects of strengthening the spleen, soothing the liver, dissipating humidity, toning the blood and lowering lipids, play a major role in the treatment of MAFLD.
{"title":"Data Mining-Based Analysis of Chinese Medicinal Herb Formulae in Metabolic associated fatty liver Disease Treatment","authors":"Jixian Zheng, Sufei Song, Anni Zheng, Cui Cong, T. Sun, Qiu-ling Xu, Tao Liu","doi":"10.1145/3570773.3570842","DOIUrl":"https://doi.org/10.1145/3570773.3570842","url":null,"abstract":"Introduction: Metabolism-associated lipid disorders (MAFLD) are the most common form of liver disease. Traditional Chinese medicine (TCM) has obvious efficacy in the treatment of MAFLD, but its therapeutic mechanism is unclear. The dosage regimen and potential mechanism of action of TCM for the treatment of MAFLD can be investigated using data mining methods. Methods: The literature related to TCM for the treatment of MAFLD in China Knowledge Network (CNKI), WANFANG Data and PUBMED in the last ten years were searched. The the frequency of drug use and its efficacy, flavour, and attribution were counted, and an analysis of high-frequency drug associations, cluster analysis, and factor analysis were conducted, respectively. Results: The top 6 single herbs of frequency are Poria, Licorice, Atractylodes Macrocephala, Bupleurum, Alisma, and Dried Tangerine Peel; the top 3 in frequency are tonic drugs, diuretic and dampening drugs, and blood stasis-activating drugs. The correlation analysis produced 4 association rules for drug combinations, 30 association rules for the three-flavour group and 18 association rules for the four-flavour group, which are related to Sijunzi Decoction, Erchen Decoction, Chaihu Shugan Powder. Hierarchical cluster analysis divides TCM into 5 categories, which are related to Taohong Siwu Decoction, Gegen Qinlian Decoction, Sini Powder, etc. The 8 drug groups obtained from the factor analysis reflect the treatment methods of strengthening spleen and soothing liver, eliminating dampness, and eliminating phlegm. Conclusion: Chinese drugs with the effects of strengthening the spleen, soothing the liver, dissipating humidity, toning the blood and lowering lipids, play a major role in the treatment of MAFLD.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128682271","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}
Triple-negative breast cancer has high reoccurrence rates after chemotherapy treatment. This kind of cancer easily transfers from its first position to other organs, and the death rates increase a lot during this process. New therapies targeting multiple signaling nodes are being explored nowadays. Previous studies have reported that BAG3 can interact with components of a different signaling pathway to promote tumor cell proliferation. In this paper, we explored whether protein ERK1/2, a component in the EGFR pathway, has a physical interaction with BAG3 and the effect of silencing BAG3 using SiBAG3 on activating ERK1/2 and tumor cell proliferation in vivo conditions. Six possible results are proposed to illustrate the relation between BAG3, ERK, and tumor cell proliferation. The study's results will provide theoretical evidence on whether preventing the interaction between BAG3 and ERK could be a potential treatment method for TNBC.
{"title":"Silencing BAG3 Inhibits Tumor Cell Proliferation by reducing the Activation of ERK in TNBC","authors":"Zeqian Li","doi":"10.1145/3570773.3570886","DOIUrl":"https://doi.org/10.1145/3570773.3570886","url":null,"abstract":"Triple-negative breast cancer has high reoccurrence rates after chemotherapy treatment. This kind of cancer easily transfers from its first position to other organs, and the death rates increase a lot during this process. New therapies targeting multiple signaling nodes are being explored nowadays. Previous studies have reported that BAG3 can interact with components of a different signaling pathway to promote tumor cell proliferation. In this paper, we explored whether protein ERK1/2, a component in the EGFR pathway, has a physical interaction with BAG3 and the effect of silencing BAG3 using SiBAG3 on activating ERK1/2 and tumor cell proliferation in vivo conditions. Six possible results are proposed to illustrate the relation between BAG3, ERK, and tumor cell proliferation. The study's results will provide theoretical evidence on whether preventing the interaction between BAG3 and ERK could be a potential treatment method for TNBC.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"693 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133970492","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}
Multi-omics clustering aims to supplement a single omics with data information from multiple omics, assigning samples into their respective clusters without supervision. The existing multi-omics clustering methods tend to use the similarity measure function to construct the similarity network between samples, and then fuse the various omics networks together for clustering by some fusion methods. These methods relies heavily on the original features of the data and the similarity measure function. This paper proposes a novel multi-omics clustering method. The proposed model first uses neural networks to extract the feature embeddings of omics, and then aligns the feature embeddings of different omics in subspaces through contrastive learning. Finally, the feature embeddings are mapped to clustered soft labels, and the soft labels are aligned again using contrastive learning. Experiments show that our method outperforms the baseline methods.
{"title":"Multi-omics clustering based on dual contrastive learning for cancer subtype identification","authors":"Yuxin Chen","doi":"10.1145/3570773.3570883","DOIUrl":"https://doi.org/10.1145/3570773.3570883","url":null,"abstract":"Multi-omics clustering aims to supplement a single omics with data information from multiple omics, assigning samples into their respective clusters without supervision. The existing multi-omics clustering methods tend to use the similarity measure function to construct the similarity network between samples, and then fuse the various omics networks together for clustering by some fusion methods. These methods relies heavily on the original features of the data and the similarity measure function. This paper proposes a novel multi-omics clustering method. The proposed model first uses neural networks to extract the feature embeddings of omics, and then aligns the feature embeddings of different omics in subspaces through contrastive learning. Finally, the feature embeddings are mapped to clustered soft labels, and the soft labels are aligned again using contrastive learning. Experiments show that our method outperforms the baseline methods.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122085926","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}
COVID-19 has a huge impact on the economic and social development of the world. In this paper, a simulation model of virus transmission was developed using the netlogo platform based on the characteristics of humans developing acquired immunity to a virus they once had, and predicted the prospects of achieving herd immunity under two scenarios: no vaccination and vaccination of a certain percentage of the population. The results show that failure to vaccinate leads to a longer duration of the outbreak, as well as an increase in the number of infected individuals and overall mortality. If vaccination is administered, the time to achieve herd immunity will be substantially reduced.
{"title":"Predicting the Future of Achieving Herd Immunity in New York City","authors":"Qi Zhuo","doi":"10.1145/3570773.3570885","DOIUrl":"https://doi.org/10.1145/3570773.3570885","url":null,"abstract":"COVID-19 has a huge impact on the economic and social development of the world. In this paper, a simulation model of virus transmission was developed using the netlogo platform based on the characteristics of humans developing acquired immunity to a virus they once had, and predicted the prospects of achieving herd immunity under two scenarios: no vaccination and vaccination of a certain percentage of the population. The results show that failure to vaccinate leads to a longer duration of the outbreak, as well as an increase in the number of infected individuals and overall mortality. If vaccination is administered, the time to achieve herd immunity will be substantially reduced.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125857460","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}
Asthma is a common chronic disease that has various causes. Patients feel dyspnea and chest tightness when asthma is an outbreak. The mortality rate is decreasing due to the development of medicine to treat asthma. The primary two drugs are Montelukast sodium and Tiotropium bromide. They have different pH values but similar chemical characteristics, such as charge. These two drugs work similarly as well; both alleviate asthma by blocking specific receptors. They are both orally taken, but Montelukast is made to a tablet, while Tiotropium needs a handihaler to use. This difference creates a price difference.
{"title":"Comparison Between Montelukast Sodium and Tiotropium Bromide for Asthma Treatment","authors":"Chenyi Zhang","doi":"10.1145/3570773.3570848","DOIUrl":"https://doi.org/10.1145/3570773.3570848","url":null,"abstract":"Asthma is a common chronic disease that has various causes. Patients feel dyspnea and chest tightness when asthma is an outbreak. The mortality rate is decreasing due to the development of medicine to treat asthma. The primary two drugs are Montelukast sodium and Tiotropium bromide. They have different pH values but similar chemical characteristics, such as charge. These two drugs work similarly as well; both alleviate asthma by blocking specific receptors. They are both orally taken, but Montelukast is made to a tablet, while Tiotropium needs a handihaler to use. This difference creates a price difference.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124736003","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 order to evaluate the comfort of knee joint protector more accurately, the paper proposes a comfort evaluation method, which is based on pressure distribution on type value points of knee joint protector. In this research, a 26-year-old healthy male postgraduate was used as the subject. Firstly, the point cloud data of knee morphology of the subject was obtained by 3D scanning and morphological reconstruction was performed. Secondly, the relationship during knee morphology, protector morphology as well as pressure was established, and the morphological mapping curves of the flexible knee joint protector were constructed. Thirdly, the pressure distribution calculation on the key data points were carried out, and were classified with high, normal and low pressure values. Then, by changing the morphology of knee joint protector, not only is the high value of regional pressure reduced and the comfort improved, but also the low value of regional pressure is increased in order to improve the function of the protector. The research results provide theoretical reference for the study of the comfort of flexible knee joint protector.
{"title":"Evaluation study on comfort of flexible Knee Joint Protector","authors":"Jiaxin Zhao, Xupeng Wang","doi":"10.1145/3570773.3570863","DOIUrl":"https://doi.org/10.1145/3570773.3570863","url":null,"abstract":"In order to evaluate the comfort of knee joint protector more accurately, the paper proposes a comfort evaluation method, which is based on pressure distribution on type value points of knee joint protector. In this research, a 26-year-old healthy male postgraduate was used as the subject. Firstly, the point cloud data of knee morphology of the subject was obtained by 3D scanning and morphological reconstruction was performed. Secondly, the relationship during knee morphology, protector morphology as well as pressure was established, and the morphological mapping curves of the flexible knee joint protector were constructed. Thirdly, the pressure distribution calculation on the key data points were carried out, and were classified with high, normal and low pressure values. Then, by changing the morphology of knee joint protector, not only is the high value of regional pressure reduced and the comfort improved, but also the low value of regional pressure is increased in order to improve the function of the protector. The research results provide theoretical reference for the study of the comfort of flexible knee joint protector.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124938534","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}
With the rapid development of information technology such as artificial intelligence and big data, the organic combination of these new technologies with traditional psychological research paradigms can effectively improve the research logic, research methods and research tools of traditional psychological measurement, improve the objectivity, accuracy and efficiency of traditional psychological measurement, and thus improve the limitations of traditional psychological evaluation methods. Based on the big data of 25214 community correctional prisoners SCL-90 symptom self-assessment scale samples in a province, this paper first uses the machine learning XGB algorithm to generate the importance ranking of the items (features) of the self-assessment scale, carry out dimension reduction processing and feature selection, and then constructs a fusion algorithm model for classification prediction. This model takes GBDT, RF, AdaBoost as the baseline model, and uses Voting algorithm for fusion processing, In order to avoid the error bias caused by a single model, through performance comparison and analysis, the accuracy of the fusion processing results is the highest, reaching 0.974, and the recall and F1 score are also the highest, reaching 0.90 and 0.92 respectively.
{"title":"Research on Prisoner Psychological Symptoms Quick Screening Model Based on Ensemble Learning","authors":"Zhifei Xu, Yan Wang, Bo Jiang","doi":"10.1145/3570773.3570870","DOIUrl":"https://doi.org/10.1145/3570773.3570870","url":null,"abstract":"With the rapid development of information technology such as artificial intelligence and big data, the organic combination of these new technologies with traditional psychological research paradigms can effectively improve the research logic, research methods and research tools of traditional psychological measurement, improve the objectivity, accuracy and efficiency of traditional psychological measurement, and thus improve the limitations of traditional psychological evaluation methods. Based on the big data of 25214 community correctional prisoners SCL-90 symptom self-assessment scale samples in a province, this paper first uses the machine learning XGB algorithm to generate the importance ranking of the items (features) of the self-assessment scale, carry out dimension reduction processing and feature selection, and then constructs a fusion algorithm model for classification prediction. This model takes GBDT, RF, AdaBoost as the baseline model, and uses Voting algorithm for fusion processing, In order to avoid the error bias caused by a single model, through performance comparison and analysis, the accuracy of the fusion processing results is the highest, reaching 0.974, and the recall and F1 score are also the highest, reaching 0.90 and 0.92 respectively.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130038933","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：