{"title":"Implicit Wiener Filtering for Speech Enhancement In Non-Stationary Noise","authors":"R. Jaiswal, Daniel Romero","doi":"10.1109/ICIST52614.2021.9440639","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440639","url":null,"abstract":"Speech quality is degraded in the presence of background noise, which reduces the quality of experience (QoE) of the end-user and therefore motivates the usage of speech enhancement algorithms. A large number of approaches have been proposed in this context. However most of them have focused on the case where the noise is stationary, an assumption that seldom holds in practice. For instance, in mobile telephony, noise sources with a marked non-stationary spectral signature include vehicles, machines, and other speakers to name a few. On the other hand, the usage of frequency-domain information in existing algorithms for speech enhancement in non-stationary noise environments can be made more effective by leveraging the increased flexibility introduced by implicit Wiener filters, which allow the control of the spectral reconstruction of the speech signal through the adjustment of hyperparameters. To address these limitations, the present paper develops an algorithm that recursively estimates the noise power spectral density and reconstructs the target speech signal in the frequency domain by means of an implicit Wiener filter with judiciously selected hyperparameters. The recursive noise estimation approach relies on the past and the present power spectral values. To evaluate the performance of the speech enhancement algorithm, speech uttered by a male and a female speaker degraded by non-stationary noise produced e.g. by babbling, cars, street noise, trains, restaurants, and airport noise. To this end, the NOIZEUS corpus is used. Objective speech quality measures such as the log-likelihood ratio (LLR), the cepstral distance (CD), and the weighted spectral slope distance (WSS) are evaluated for the enhanced speech signals and compared to the conventional spectral subtraction method. Results demonstrate that the proposed algorithm provides consistent and improved enhancement performance with all tested noise types.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128404370","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}
Shuhao Zhang, Lei Mu, Wei Xiao, Huanhuan Huang, Yan Xiang
{"title":"A Prediction Method of Elderly Cognitive Impairment Based on Edge Intelligence and Multimodal Perception","authors":"Shuhao Zhang, Lei Mu, Wei Xiao, Huanhuan Huang, Yan Xiang","doi":"10.1109/ICIST52614.2021.9440583","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440583","url":null,"abstract":"The situation of population aging in our country is severe, and the incidence of cognitive impairment in the elderly is gradually increasing, which seriously affects the lives of the elderly. Monitoring the daily behavior of the elderly in the early stage of cognitive impairment, proactively finding out the signs of cognitive impairment, and providing corresponding cognitive training in time can effectively delay the development of cognitive impairment. To find a prediction method which can identify the signs of cognitive impairment under the premise of protecting user privacy, this article uses the Internet of Things system to monitor and record the daily activities of the elderly. Then Back Propagation Neural Network (BPNN) is utilized to assist the diagnosis of cognitive impairment. This paper carried out experiments to verify the accuracy rate of acquisition and that of recognition by BPNN. The experimental results show that the system has better feasibility and higher recognition accuracy.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130914295","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}
Enhong Liu, Dan Su, Liangming Chen, Long Jin, Xiuchun Xiao, Dongyang Fu
{"title":"An attempt of applying the Lagrange-type 1-step-ahead numerical differentiation method to optimize the SGD algorithm in deep learning","authors":"Enhong Liu, Dan Su, Liangming Chen, Long Jin, Xiuchun Xiao, Dongyang Fu","doi":"10.1109/ICIST52614.2021.9440607","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440607","url":null,"abstract":"The form of the original stochastic gradient descent (SGD) algorithm accords with the definition of forward Euler method, which has some inherent defects. Thus, in order to improve the original SGD algorithm, a Lagrange-type 1-step-ahead numerical differentiation method based parameter update algorithm is presented and validated. Instinctively, the new algorithm can fix some inherent flaws of the SGD algorithm. However, a series of experimental results show that the Lagrange-type 1-step-ahead numerical differentiation method cannot be applied to reduce the computational error of SGD. In addition, this method makes the model appear the phenomenon of non-convergence. Finally, on the basis of comparative experiments, the divergence phenomenon is analyzed and explained.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"699 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133983819","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}
Zhiguang Wang, Zhaoyu Wei, Yuehui Teng, Caoyang Yu, Baoheng Yao, L. Lian
{"title":"Research and design of a new hybrid energy positive buoyancy autonomous vehicle","authors":"Zhiguang Wang, Zhaoyu Wei, Yuehui Teng, Caoyang Yu, Baoheng Yao, L. Lian","doi":"10.1109/ICIST52614.2021.9440610","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440610","url":null,"abstract":"This paper presents the research and design of a hybrid energy positive buoyancy autonomous vehicle. Its working mode, shape design, working principle, main components, and control system are described. The hybrid energy positive buoyancy autonomous vehicle overcomes its own positive buoyancy by generating negative lift from its wing and combines its dynamic control surface to realize underwater motion. The hybrid energy technology of solar cell and lithium battery is adopted to improve the endurance of the positive buoyancy autonomous vehicle. The performance and control response of the prototype of the hybrid energy positive buoyancy autonomous vehicle is studied through the pool test. The results of the pool test show that the hybrid energy positive buoyancy autonomous vehicle has strong adaptability to the environment, excellent performance, high safety, and a bright future.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123622688","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}
{"title":"A Two-Timescale Neurodynamic Approach to Minimax Portfolio Optimization","authors":"Man-Fai Leung, Jun Wang","doi":"10.1109/ICIST52614.2021.9440640","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440640","url":null,"abstract":"This paper is concerned with asset allocation based on two-timescale neurodynamic optimization. The portfolio optimization in classical mean-variance framework is reformulated as a minimax portfolio selection problem and a two-timescale neurodynamic approach is developed to solve the problem. The neurodynamic approach incorporates a recurrent neural network (RNN) operating on two different timescales. Computational results show the efficacy and performance of the developed approach to asset allocation.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123838052","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}
{"title":"Robust Fault Tolerant Control of Dynamic Positioning Ships based on Typical Actuator Constraints","authors":"Fu Mingyu, Jiyan, XuYujie","doi":"10.1109/ICIST52614.2021.9440578","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440578","url":null,"abstract":"In this paper, a fault-tolerant control method of dynamic positioning(DP) ship under time-varying external disturbance and actuator faults is proposed. A general fault model is established to describe the typical actuator faults modes (loss-of-effectiveness, jamming and interruption). Without using the speed acceleration, a finite time nonlinear disturbance observer is designed to estimate time-varying bounded disturbance and compensate fault error. Then a nonlinear PD fault-tolerant control law is developed, which can guarantee finite time uniform boundedness of all states of the closed-loop system. The effectiveness of the fault-tolerant control method is verified by simulation of \"Offshore Oil 201\" dynamic positioning ship.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124853381","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}
Xiangfei Meng, Mengmeng Lv, Qiang Zhang, Yan Zhang, Yancai Hu, Wen-Li Su
{"title":"Path Following Control Of Ship Based On Concise Nonlinear Feedback Technique","authors":"Xiangfei Meng, Mengmeng Lv, Qiang Zhang, Yan Zhang, Yancai Hu, Wen-Li Su","doi":"10.1109/ICIST52614.2021.9440599","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440599","url":null,"abstract":"In view of the difficulty of system debugging in ship path following control and excessive controller energy output, this paper proposes a concise nonlinear path following control scheme driven by a sine function. This scheme used indirect control to separate the guidance and control. In the control stage, the closed-loop gain-shaping algorithm is combined to design the control law, and the sine function is used to non-linearly decorate the controller, which reduces the energy output. Finally, by adopting the international standard ship model KCS for actual ship verification, experimental results show that the concise nonlinear path following control scheme proposed in this paper is effective and has good robust performance.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125088309","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}
Wencong Zhao, Renqian Zhang, Xiaoxiang Yuan, Kaiping Luo
{"title":"An improved variable neighborhood search algorithm for the solid waste collection and transportation problem with split deliveries","authors":"Wencong Zhao, Renqian Zhang, Xiaoxiang Yuan, Kaiping Luo","doi":"10.1109/ICIST52614.2021.9440629","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440629","url":null,"abstract":"This study addresses the solid waste collection and transportation problem with split deliveries (SWCTPSD). To minimize the total fleet costs, a mixed-integer programming model is proposed. An improved variable neighborhood search (VNS) algorithm is proposed to obtain a high-quality collection and transportation plan quickly. To enhance the local exploitive ability, the VNS algorithm is hybridized with simulated annealing. The experimental results show that the proposed VNS algorithm is effective.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127561665","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}
{"title":"Distributed Event-Triggered Projection Subgradient Algorithm over Unbalanced Digraphs Based on Row-Stochastic Matrices","authors":"Xiwen Bao, Bo Zhou, Huiwei Wang","doi":"10.1109/ICIST52614.2021.9440630","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440630","url":null,"abstract":"In this paper, we address the convex optimization problem on the multi-agent network, where the objective function is the summation of individual objectives of all agents. The communication graph among the agents is assumed to be directed and unbalanced with row-stochastic adjacency matrix. We devise a distributed projection sub-gradient algorithm with event-triggered communications, which is proved to asymptotically solve the convex optimization problem under diminishing stepsizes and mild triggering conditions. Finally, a numerical experiment is illustrated to demonstrate the reasonableness and validity of the theoretical analysis.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116970787","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}
{"title":"A Water Wave Optimization Algorithm for Order Selection and Delivery Path Optimization for Takeaway Deliverymen","authors":"Jia-Yu Wu, Min-Xia Zhang, Xue Wu, Yujun Zheng","doi":"10.1109/ICIST52614.2021.9440616","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440616","url":null,"abstract":"Over the last years, the food delivery market has seen significant growth and provide a lot of jobs for deliverymen. The revenue of a takeaway deliveryman depends on not only reasonable order taking but also efficient delivery path planning. However, it is challenging to select among a large number of candidate orders and plan an efficient route passing all involved pickup points and service points. In this paper, we present a problem integrating order selection and delivery path optimization for takeaway deliverymen. The objective is to maximize the revenue per unit time subject to overtime penalty and high-workload reward. To efficiently solve this problem, we propose a hybrid intelligent algorithm, which adapts the water wave optimization (WWO) metaheuristic to evolve solutions to the main order selection problem and employs tabu search to optimize the path for each order selection solution. Experimental results on test instances demonstrate the performance advantages of the proposed algorithm compared to a set of popular metaheuristic optimization algorithms.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124024895","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}