Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263556
Yulong Song, Wenming Ma, Tongtong Liu
Today’s group recommender systems rarely consider the trust relationship between users, but the interaction between users often has a significant impact on each other’s preferences. A group recommendation model based on deep learning and user interaction is proposed, which has stronger representational capability than previous models. In addition, an improved weight fusion method based on user implicit vector is applied to the preference fusion of group members. Epinions data set shows that this model is superior to other comparison algorithms in RMSE and hit ratio.
{"title":"Deep Group Recommender System Model Based on User Trust","authors":"Yulong Song, Wenming Ma, Tongtong Liu","doi":"10.1109/CISP-BMEI51763.2020.9263556","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263556","url":null,"abstract":"Today’s group recommender systems rarely consider the trust relationship between users, but the interaction between users often has a significant impact on each other’s preferences. A group recommendation model based on deep learning and user interaction is proposed, which has stronger representational capability than previous models. In addition, an improved weight fusion method based on user implicit vector is applied to the preference fusion of group members. Epinions data set shows that this model is superior to other comparison algorithms in RMSE and hit ratio.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116823587","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263621
Jianhong Zhang, Ke Li, Leitong Lin, Boqiang Liu, Na Wei
This study was designed to test the hypothesis that the patients with Alzheimer's disease (AD) may have deficits in their movement planning and execution of rapid target oriented arm movements. This exploratory study evaluated movement dynamics in grasping movements between AD and controls. Studies have used a paradigm in which the visual feedback of the object are different, this paradigm required subjects to grasp and lift with the index finger and the thumb a symmetrically shaped object. Eleven AD patients and age-matched controls participated in this work. Movement times, absolute distance errors, forces and force-rate profiles were analyzed. Results show a marked group effect on a subset of conditions, in particular when the patients could not rely on the visual feedback of hand movement. Our results support the hypothesis that the ability to recall and use visuo-spatial associations might underlie the impairment in complex motor behavior that has been reported in AD patients. Importantly, the sensory-motor deterioration (the declines in fine motor control and coordination) observed in the tasks of grasping, thus, could be used as an additional assessment tool in evaluating patients who might have MCI or AD. Quantifying the specific characteristics of motor performance in AD patients may help further our understanding of the possible mechanisms underlying the motor and cognitive deficits of AD.
{"title":"Hand-oriented tasking assessment of fine movement control deficits in Alzheimer’s Disease","authors":"Jianhong Zhang, Ke Li, Leitong Lin, Boqiang Liu, Na Wei","doi":"10.1109/CISP-BMEI51763.2020.9263621","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263621","url":null,"abstract":"This study was designed to test the hypothesis that the patients with Alzheimer's disease (AD) may have deficits in their movement planning and execution of rapid target oriented arm movements. This exploratory study evaluated movement dynamics in grasping movements between AD and controls. Studies have used a paradigm in which the visual feedback of the object are different, this paradigm required subjects to grasp and lift with the index finger and the thumb a symmetrically shaped object. Eleven AD patients and age-matched controls participated in this work. Movement times, absolute distance errors, forces and force-rate profiles were analyzed. Results show a marked group effect on a subset of conditions, in particular when the patients could not rely on the visual feedback of hand movement. Our results support the hypothesis that the ability to recall and use visuo-spatial associations might underlie the impairment in complex motor behavior that has been reported in AD patients. Importantly, the sensory-motor deterioration (the declines in fine motor control and coordination) observed in the tasks of grasping, thus, could be used as an additional assessment tool in evaluating patients who might have MCI or AD. Quantifying the specific characteristics of motor performance in AD patients may help further our understanding of the possible mechanisms underlying the motor and cognitive deficits of AD.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124220667","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263547
Weijun Tian, Yezi Hui, Ju Wang, Yu Xiong, Lei Jiang, Ming Li
Aiming at the impact vibration of the robot caused by the unstructured ground collision, a cam slot stiffness functional bionic buffer joint is proposed. The stiffness function of the buffer joint is analyzed by the analytical method, and the accurate function expression equation of buffer joint stiffness is obtained. The design of the cam slot buffer joint is carried out based on the rigidity functional feature. The rigidity function feature of the buffer joint is analyzed by Adams simulation. The results show that the designed bionic buffer joints have the characteristic of stiffness function.
{"title":"Bionic design of buffer joint with functional stiffness","authors":"Weijun Tian, Yezi Hui, Ju Wang, Yu Xiong, Lei Jiang, Ming Li","doi":"10.1109/CISP-BMEI51763.2020.9263547","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263547","url":null,"abstract":"Aiming at the impact vibration of the robot caused by the unstructured ground collision, a cam slot stiffness functional bionic buffer joint is proposed. The stiffness function of the buffer joint is analyzed by the analytical method, and the accurate function expression equation of buffer joint stiffness is obtained. The design of the cam slot buffer joint is carried out based on the rigidity functional feature. The rigidity function feature of the buffer joint is analyzed by Adams simulation. The results show that the designed bionic buffer joints have the characteristic of stiffness function.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128947347","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}
MRI is widely used in clinical medical diagnosis, because of its non-ionizing radiation, arbitrary section imaging, multimodal imaging and high resolution of soft tissue. However, many patients are turned away by MRI because of various contraindications, such as ferromagnetic crown and pacemaker. Hypertension is a common basic disease for middle aged and elderly people, and patient often complicated with other disease such as joint disease and lumbar disease which need MRI examination to make a detailed assessment of the patient's health condition. Traditionally, it is considered clinically that it is safe for hypertensive patient to perform MRI examination, nevertheless, the statistic data on academic papers that support the proposition is rare to be found. MRI examination is a 10 to 30 minutes long time of process full of strong magnetic field, RF electromagnetic wave and harsh equipment running noises, does the blood pressure of hypertensive patient fluctuate to increase direction? To examine this proposition, our team has carried out a change study of systolic blood pressure, diastolic blood pressure, pulse rate and oxygen saturation before and after MRI examination with sufficient samples of 291 patients including of 100 hypertension patients. This study divided the measurement into three occasions, i.e., occasion A(before the patient enter the MRI examination room), occasion B (After the patient entered the MRI examination room and before examination) and occasion C(After the patient finished MRI examination program and left the examination room). Statistics of experimental data above revealed no significant increasing difference in measurements of these physiological parameters between A and B (or C). So, excluding psychological factors and other interference, hypertension patients is safe to carry out MRI examination. In addition, correlation analysis of four parameters showed that the correlation between systolic pressure and diastolic pressure was considerable high with Pearson correlation coefficient value of 0.636, and the correlation between other parameters are relatively low and negligible. These results and data are believed to contribute to the development of clinical medicine.
{"title":"Is It Safe for Hypertensive Patient to Be Examined by MRI : Change Research of Some Physiological Parameters before and after MRI Examination","authors":"Hongbin Li, Hongli Ren, ChanChan Qiao, Meng Wang, Zhaoguo Zhang","doi":"10.1109/CISP-BMEI51763.2020.9263666","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263666","url":null,"abstract":"MRI is widely used in clinical medical diagnosis, because of its non-ionizing radiation, arbitrary section imaging, multimodal imaging and high resolution of soft tissue. However, many patients are turned away by MRI because of various contraindications, such as ferromagnetic crown and pacemaker. Hypertension is a common basic disease for middle aged and elderly people, and patient often complicated with other disease such as joint disease and lumbar disease which need MRI examination to make a detailed assessment of the patient's health condition. Traditionally, it is considered clinically that it is safe for hypertensive patient to perform MRI examination, nevertheless, the statistic data on academic papers that support the proposition is rare to be found. MRI examination is a 10 to 30 minutes long time of process full of strong magnetic field, RF electromagnetic wave and harsh equipment running noises, does the blood pressure of hypertensive patient fluctuate to increase direction? To examine this proposition, our team has carried out a change study of systolic blood pressure, diastolic blood pressure, pulse rate and oxygen saturation before and after MRI examination with sufficient samples of 291 patients including of 100 hypertension patients. This study divided the measurement into three occasions, i.e., occasion A(before the patient enter the MRI examination room), occasion B (After the patient entered the MRI examination room and before examination) and occasion C(After the patient finished MRI examination program and left the examination room). Statistics of experimental data above revealed no significant increasing difference in measurements of these physiological parameters between A and B (or C). So, excluding psychological factors and other interference, hypertension patients is safe to carry out MRI examination. In addition, correlation analysis of four parameters showed that the correlation between systolic pressure and diastolic pressure was considerable high with Pearson correlation coefficient value of 0.636, and the correlation between other parameters are relatively low and negligible. These results and data are believed to contribute to the development of clinical medicine.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129955444","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263500
Yang Zhu, Zhaowei Liu, Yuanqing Ma
CP-nets are one of the powerful tools for learning uncertain relations in the field of artificial intelligence, in which learning problems are the main research content. So far, there are many learning methods about CP-nets, which are widely used in information retrieval, user decision-making, recommendation systems and other fields. This paper attempts to propose a new solution, using an algorithm based on the combination of conditional independence and scoring search to learn the structure of CP-nets, it combines local learning, constraint-based and search scoring techniques, which is principled and effective. Firstly, this paper using the MMPC algorithm to get CPC(candidate parent-child node), and then selecting the appropriate search algorithm as a measurement standard, and perform a scoring search to obtain the optimal network structure. Based on the idea of simulated annealing in the search phase, this paper combines the probability jump feature to perform random search in the solution space to avoid falling into the local optimal solution, obtain better search results, and compare with several search algorithms. In the experimental part, it is compared with other hybrid algorithms such as sparse candidate algorithm, and the agreement is used as a measurement standard to verify the effectiveness of the algorithm.
{"title":"Structure Learning of CP-nets Based on Constraint and Scoring Search","authors":"Yang Zhu, Zhaowei Liu, Yuanqing Ma","doi":"10.1109/CISP-BMEI51763.2020.9263500","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263500","url":null,"abstract":"CP-nets are one of the powerful tools for learning uncertain relations in the field of artificial intelligence, in which learning problems are the main research content. So far, there are many learning methods about CP-nets, which are widely used in information retrieval, user decision-making, recommendation systems and other fields. This paper attempts to propose a new solution, using an algorithm based on the combination of conditional independence and scoring search to learn the structure of CP-nets, it combines local learning, constraint-based and search scoring techniques, which is principled and effective. Firstly, this paper using the MMPC algorithm to get CPC(candidate parent-child node), and then selecting the appropriate search algorithm as a measurement standard, and perform a scoring search to obtain the optimal network structure. Based on the idea of simulated annealing in the search phase, this paper combines the probability jump feature to perform random search in the solution space to avoid falling into the local optimal solution, obtain better search results, and compare with several search algorithms. In the experimental part, it is compared with other hybrid algorithms such as sparse candidate algorithm, and the agreement is used as a measurement standard to verify the effectiveness of the algorithm.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131045895","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263544
Lijuan Duan, Yao Wang, Ying Xiao, Yuanhua Qiao, Changming Wang
Two seizure prediction models are built based on a decision fusion strategy and residual network by using spatial coupling features and introducing an attention mechanism. First, eight frequency bands are filtered, and the correlation matrices are computed for each frequency of eighteen channels. Second, the eight 18x18 matrices are input to the residual module for classification, and the results are concatenated to form a vector. A fully connected layer is used for decision fusion. Third, to emphasize the coupling relationship among the different frequency bands, a cubic matrix formed by the eight 18x18 matrices is inputted to an attention network, resulting in the enhanced features. A seizure prediction model is thus proposed by combining the nine decisions. The performance of the model is compared with those from state-of-the-art methods, and the sensitivity of the proposed model is improved by 4.45%.
{"title":"Prediction of Seizure via Residual Networks Based on Decision Fusion","authors":"Lijuan Duan, Yao Wang, Ying Xiao, Yuanhua Qiao, Changming Wang","doi":"10.1109/CISP-BMEI51763.2020.9263544","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263544","url":null,"abstract":"Two seizure prediction models are built based on a decision fusion strategy and residual network by using spatial coupling features and introducing an attention mechanism. First, eight frequency bands are filtered, and the correlation matrices are computed for each frequency of eighteen channels. Second, the eight 18x18 matrices are input to the residual module for classification, and the results are concatenated to form a vector. A fully connected layer is used for decision fusion. Third, to emphasize the coupling relationship among the different frequency bands, a cubic matrix formed by the eight 18x18 matrices is inputted to an attention network, resulting in the enhanced features. A seizure prediction model is thus proposed by combining the nine decisions. The performance of the model is compared with those from state-of-the-art methods, and the sensitivity of the proposed model is improved by 4.45%.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131017842","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263582
Nan Nan, Ruipeng Gang, Ruixia Song
For images with sky region, we propose a method of image defogging based on pattern recognition and dark channel priori. First, the transmittance is obtained by reducing the minimum filter window, and then the edge of transmittance is smoothed by V transformation. Since the transmittance histogram has the feature of two peaks, we used Fisher linear classifier to identify sky and non-sky regions, and then recalculated the transmittance of sky regions. Finally, the atmospheric scattering model is used to get the new luminance component, and the gamma correction is carried out. After the saturation component is adjusted appropriately, the defogged image is converted back to RGB space. The experiment shows that the proposed algorithm can get better haze removal effect compared with the traditional defogging algorithm based on dark channel prior and other state-of-the-art methods developed in recent years, and to a certain extent has solved the problem of color distortion and the whole brightness being darker in the sky region when using the DCP based algorithm.
{"title":"Image Defogging Algorithm Based on Fisher Criterion Function and Dark Channel Prior","authors":"Nan Nan, Ruipeng Gang, Ruixia Song","doi":"10.1109/CISP-BMEI51763.2020.9263582","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263582","url":null,"abstract":"For images with sky region, we propose a method of image defogging based on pattern recognition and dark channel priori. First, the transmittance is obtained by reducing the minimum filter window, and then the edge of transmittance is smoothed by V transformation. Since the transmittance histogram has the feature of two peaks, we used Fisher linear classifier to identify sky and non-sky regions, and then recalculated the transmittance of sky regions. Finally, the atmospheric scattering model is used to get the new luminance component, and the gamma correction is carried out. After the saturation component is adjusted appropriately, the defogged image is converted back to RGB space. The experiment shows that the proposed algorithm can get better haze removal effect compared with the traditional defogging algorithm based on dark channel prior and other state-of-the-art methods developed in recent years, and to a certain extent has solved the problem of color distortion and the whole brightness being darker in the sky region when using the DCP based algorithm.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128634852","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}
Electron density is one of the important parameters of plasma. In the aerospace field, the density distribution of plasma on the surface of an aircraft will have an important effect on it. In this field, the current research mostly stays in the laboratory stage or static electron density diagnosis stage, and there is still a certain distance from the actual application. This study is based on the traditional Langmuir probe theory and follows the assumptions of the Langmuir probe theory to make a qualitative analysis of its voltammetric characteristics. Based on the above analysis, a single flush-probe was designed, and a method for diagnosing electron density for low pressure was proposed. It was verified by experiments that the method can accurately obtain parameters of plasma such as electron density in the low pressure range, which can provide a certain reference for future electronic density diagnosis in the aerospace.
{"title":"Research on Low Pressure Electronic Density Diagnostic Method of Single Paperback Probe Based on Langmuir Probe Theory","authors":"Heng Wang, Xinyi Guo, Weihe Shen, Hai Jiang, Yanrong Yuan, Tongkai Cui, Jintian Tang","doi":"10.1109/CISP-BMEI51763.2020.9263611","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263611","url":null,"abstract":"Electron density is one of the important parameters of plasma. In the aerospace field, the density distribution of plasma on the surface of an aircraft will have an important effect on it. In this field, the current research mostly stays in the laboratory stage or static electron density diagnosis stage, and there is still a certain distance from the actual application. This study is based on the traditional Langmuir probe theory and follows the assumptions of the Langmuir probe theory to make a qualitative analysis of its voltammetric characteristics. Based on the above analysis, a single flush-probe was designed, and a method for diagnosing electron density for low pressure was proposed. It was verified by experiments that the method can accurately obtain parameters of plasma such as electron density in the low pressure range, which can provide a certain reference for future electronic density diagnosis in the aerospace.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122840057","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263555
X. Ye, Bisheng Ji, Xueting Chen, Dingwei Qian, Zhijing Zhao
By the multi-layer nonlinear mapping and the semantic feature extraction of the deep learning, a deep learning network is proposed for video face detection to overcome the challenge of detecting faces rapidly and accurately in video with changeable background. Particularly, a pre-training procedure is used to initialize the network parameters to avoid falling into the local optimum, and the greedy layer-wise learning is introduced in the pre-training to avoid the training error transfer in layers. Key to the network is that the probability of neurons models the status of human brain neurons which is a continuous distribution from the most active to the least active and the hidden layer’s neuron number decreases layer-by-layer to reduce the redundant information of the input data. Moreover, the skin color detection is used to accelerate the detection speed by generating candidate regions. Experimental results show that, besides the faster detection speed and robustness against face rotation, the proposed method possesses lower false detection rate and lower missing detection rate than traditional algorithms.
{"title":"Probability Boltzmann Machine Network for Face Detection on Video","authors":"X. Ye, Bisheng Ji, Xueting Chen, Dingwei Qian, Zhijing Zhao","doi":"10.1109/CISP-BMEI51763.2020.9263555","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263555","url":null,"abstract":"By the multi-layer nonlinear mapping and the semantic feature extraction of the deep learning, a deep learning network is proposed for video face detection to overcome the challenge of detecting faces rapidly and accurately in video with changeable background. Particularly, a pre-training procedure is used to initialize the network parameters to avoid falling into the local optimum, and the greedy layer-wise learning is introduced in the pre-training to avoid the training error transfer in layers. Key to the network is that the probability of neurons models the status of human brain neurons which is a continuous distribution from the most active to the least active and the hidden layer’s neuron number decreases layer-by-layer to reduce the redundant information of the input data. Moreover, the skin color detection is used to accelerate the detection speed by generating candidate regions. Experimental results show that, besides the faster detection speed and robustness against face rotation, the proposed method possesses lower false detection rate and lower missing detection rate than traditional algorithms.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114159525","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}
Pub Date : 2020-10-17DOI: 10.1109/CISP-BMEI51763.2020.9263529
Yu Wang, Zhen Su
The new generation video coding standard HEVC has as many as 35 prediction modes and more flexible coding unit (CU) sizes. Although HEVC has better coding performance, it has high computational complexity and long coding time. In real-time signal processing systems, the algorithm must be further optimized. This paper proposes an efficient, fast intra-prediction algorithm for HEVC intra-coding. For the CU size decision, we use the depth information of the adjacent CUs to terminate the division in advance. For the intra-prediction mode selection, we use the parent CU's best prediction mode and the most probable modes (MPMs) to reduce the modes in the rate-distortion optimization process. Experimental results show that the proposed algorithm reduces encoding time by 47.21% on average, BD-BR increases by 1.81%, BD-PSNR decreases by 0.01dB, and SSIM decreases by 0.011. Comparing the proposed algorithm's RD curves with the existing algorithm, the proposed algorithm's rate-distortion performance has not changed significantly. The proposed algorithm does not significantly change the encoding performance and image quality while reducing the encoding time. The research method in this paper has theoretical guiding significance for HEVC intra-coding algorithm.
{"title":"An Efficient Intra Prediction Algorithm for HEVC Intra-coding","authors":"Yu Wang, Zhen Su","doi":"10.1109/CISP-BMEI51763.2020.9263529","DOIUrl":"https://doi.org/10.1109/CISP-BMEI51763.2020.9263529","url":null,"abstract":"The new generation video coding standard HEVC has as many as 35 prediction modes and more flexible coding unit (CU) sizes. Although HEVC has better coding performance, it has high computational complexity and long coding time. In real-time signal processing systems, the algorithm must be further optimized. This paper proposes an efficient, fast intra-prediction algorithm for HEVC intra-coding. For the CU size decision, we use the depth information of the adjacent CUs to terminate the division in advance. For the intra-prediction mode selection, we use the parent CU's best prediction mode and the most probable modes (MPMs) to reduce the modes in the rate-distortion optimization process. Experimental results show that the proposed algorithm reduces encoding time by 47.21% on average, BD-BR increases by 1.81%, BD-PSNR decreases by 0.01dB, and SSIM decreases by 0.011. Comparing the proposed algorithm's RD curves with the existing algorithm, the proposed algorithm's rate-distortion performance has not changed significantly. The proposed algorithm does not significantly change the encoding performance and image quality while reducing the encoding time. The research method in this paper has theoretical guiding significance for HEVC intra-coding algorithm.","PeriodicalId":346757,"journal":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122708791","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：