Gabriella Casalino, Giovanna Castellano, O. Hryniewicz, Daniel Leite, Karol Opara, Weronika Radziszewska, Katarzyna Kaczmarek-Majer
Abstract Acoustic features of speech are promising as objective markers for mental health monitoring. Specialized smartphone apps can gather such acoustic data without disrupting the daily activities of patients. Nonetheless, the psychiatric assessment of the patient’s mental state is typically a sporadic occurrence that takes place every few months. Consequently, only a slight fraction of the acoustic data is labeled and applicable for supervised learning. The majority of the related work on mental health monitoring limits the considerations only to labeled data using a predefined ground-truth period. On the other hand, semi-supervised methods make it possible to utilize the entire dataset, exploiting the regularities in the unlabeled portion of the data to improve the predictive power of a model. To assess the applicability of semi-supervised learning approaches, we discuss selected state-of-the-art semi-supervised classifiers, namely, label spreading, label propagation, a semi-supervised support vector machine, and the self training classifier. We use real-world data obtained from a bipolar disorder patient to compare the performance of the different methods with that of baseline supervised learning methods. The experiment shows that semi-supervised learning algorithms can outperform supervised algorithms in predicting bipolar disorder episodes.
{"title":"Semi–Supervised vs. Supervised Learning for Mental Health Monitoring: A Case Study on Bipolar Disorder","authors":"Gabriella Casalino, Giovanna Castellano, O. Hryniewicz, Daniel Leite, Karol Opara, Weronika Radziszewska, Katarzyna Kaczmarek-Majer","doi":"10.34768/amcs-2023-0030","DOIUrl":"https://doi.org/10.34768/amcs-2023-0030","url":null,"abstract":"Abstract Acoustic features of speech are promising as objective markers for mental health monitoring. Specialized smartphone apps can gather such acoustic data without disrupting the daily activities of patients. Nonetheless, the psychiatric assessment of the patient’s mental state is typically a sporadic occurrence that takes place every few months. Consequently, only a slight fraction of the acoustic data is labeled and applicable for supervised learning. The majority of the related work on mental health monitoring limits the considerations only to labeled data using a predefined ground-truth period. On the other hand, semi-supervised methods make it possible to utilize the entire dataset, exploiting the regularities in the unlabeled portion of the data to improve the predictive power of a model. To assess the applicability of semi-supervised learning approaches, we discuss selected state-of-the-art semi-supervised classifiers, namely, label spreading, label propagation, a semi-supervised support vector machine, and the self training classifier. We use real-world data obtained from a bipolar disorder patient to compare the performance of the different methods with that of baseline supervised learning methods. The experiment shows that semi-supervised learning algorithms can outperform supervised algorithms in predicting bipolar disorder episodes.","PeriodicalId":502322,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"245 1","pages":"419 - 428"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139345754","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}
Abstract An event-triggered adaptive control algorithm is proposed for cooperative tracking control of high-order nonlinear multi-agent systems (MASs) with prescribed performance and full-state constraints. The algorithm combines dynamic surface technology and the backstepping recursive design method, with radial basis function neural networks (RBFNNs) used to approximate the unknown nonlinearity. The barrier Lyapunov function and finite-time stability theory are employed to prove that all agent states are semi-globally uniform and ultimately bounded, with the tracking error converging to a bounded neighborhood of zero in a finite time. Numerical simulations are provided to demonstrate the effectiveness of the proposed control scheme.
{"title":"Event–Triggered Cooperative Control for High–Order Nonlinear Multi–Agent Systems with Finite–Time Consensus","authors":"Shiyin Gong, Meirong Zheng, Jing Hu, Anguo Zhang","doi":"10.34768/amcs-2023-0032","DOIUrl":"https://doi.org/10.34768/amcs-2023-0032","url":null,"abstract":"Abstract An event-triggered adaptive control algorithm is proposed for cooperative tracking control of high-order nonlinear multi-agent systems (MASs) with prescribed performance and full-state constraints. The algorithm combines dynamic surface technology and the backstepping recursive design method, with radial basis function neural networks (RBFNNs) used to approximate the unknown nonlinearity. The barrier Lyapunov function and finite-time stability theory are employed to prove that all agent states are semi-globally uniform and ultimately bounded, with the tracking error converging to a bounded neighborhood of zero in a finite time. Numerical simulations are provided to demonstrate the effectiveness of the proposed control scheme.","PeriodicalId":502322,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"100 1","pages":"439 - 448"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139346937","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}
Abstract We show a turnpike result for problems of optimal control with possibly nonlinear systems as well as pointwise-in-time state and control constraints. The objective functional is of integral type and contains a tracking term which penalizes the distance to a desired steady state. In the optimal control problem, only the initial state is prescribed. We assume that a cheap control condition holds that yields a bound for the optimal value of our optimal control problem in terms of the initial data. We show that the solutions to the optimal control problems on the time intervals [0,T ] have a turnpike structure in the following sense: For large T the contribution to the objective functional that comes from the subinterval [T/2,T ], i.e., from the second half of the time interval [0,T ], is at most of the order 1/T . More generally, the result holds for subintervals of the form [rT,T ], where r ∈ (0, 1/2) is a real number. Using this result inductively implies that the decay of the integral on such a subinterval in the objective function is faster than the reciprocal value of a power series in T with positive coefficients. Accordingly, the contribution to the objective value from the final part of the time interval decays rapidly with a growing time horizon. At the end of the paper we present examples for optimal control problems where our results are applicable.
{"title":"Optimal Control Problems without Terminal Constraints: The Turnpike Property with Interior Decay","authors":"M. Gugat, Martin Lazar","doi":"10.34768/amcs-2023-0031","DOIUrl":"https://doi.org/10.34768/amcs-2023-0031","url":null,"abstract":"Abstract We show a turnpike result for problems of optimal control with possibly nonlinear systems as well as pointwise-in-time state and control constraints. The objective functional is of integral type and contains a tracking term which penalizes the distance to a desired steady state. In the optimal control problem, only the initial state is prescribed. We assume that a cheap control condition holds that yields a bound for the optimal value of our optimal control problem in terms of the initial data. We show that the solutions to the optimal control problems on the time intervals [0,T ] have a turnpike structure in the following sense: For large T the contribution to the objective functional that comes from the subinterval [T/2,T ], i.e., from the second half of the time interval [0,T ], is at most of the order 1/T . More generally, the result holds for subintervals of the form [rT,T ], where r ∈ (0, 1/2) is a real number. Using this result inductively implies that the decay of the integral on such a subinterval in the objective function is faster than the reciprocal value of a power series in T with positive coefficients. Accordingly, the contribution to the objective value from the final part of the time interval decays rapidly with a growing time horizon. At the end of the paper we present examples for optimal control problems where our results are applicable.","PeriodicalId":502322,"journal":{"name":"International Journal of Applied Mathematics and Computer Science","volume":"29 1","pages":"429 - 438"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139343872","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：