Pub Date : 2017-07-01DOI: 10.1109/ISSCS.2017.8034938
Vasilica-Daniela Andries, L. Goras, Andi Buzo, G. Pelz
The paper presents an approach based on gain scheduling technique for improving the transient performances of a digitally controlled DC-DC Buck Converter working over a large area of operating conditions. In order to determine optimal settings for the control parameters under different test scenarios, an adaptive mechanism based on machine learning algorithms is used. The experimental results, obtained after using this approach are presented as well. An improvement of 20% is observed in the case of using this gain scheduling controller instead of a controller with constant values for the parameters.
{"title":"Automatic tuning for a DC-DC Buck Converter with adaptive controller","authors":"Vasilica-Daniela Andries, L. Goras, Andi Buzo, G. Pelz","doi":"10.1109/ISSCS.2017.8034938","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034938","url":null,"abstract":"The paper presents an approach based on gain scheduling technique for improving the transient performances of a digitally controlled DC-DC Buck Converter working over a large area of operating conditions. In order to determine optimal settings for the control parameters under different test scenarios, an adaptive mechanism based on machine learning algorithms is used. The experimental results, obtained after using this approach are presented as well. An improvement of 20% is observed in the case of using this gain scheduling controller instead of a controller with constant values for the parameters.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130023671","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034913
S. M. Feraru, M. Zbancioc
In this paper, we made the emotion recognition for Romanian language using EMO-IIT database with seven emotions (joy, sadness, fury, neutral tone, anxiety, disgust and boredom). Compared to our previous studies we introduced two new emotions: disgust and boredom and a new set of sentences in order to express better the emotional states. The best recognition rate of emotions is around 75% and was obtained for feature vectors which includes MFCC (Mel Frequency Cepstral Coefficients) + PARCOR (Partial Correlations Coefficients) + LAR (Log Area Ratios Coefficients). The accuracy rates are closed to the other studies from the literatures. For example, for the German emotional database EMO-DB which contains all seven emotions, the accuracy recognition rate reported by the researchers was around 85%. The disgust is often recognized as boredom (15%) or neutral tone (10%). The sadness is confused with the neutral tone (12%) and disgust (9%). The main difference between the two databases is that the EMO-IIT contains unprofessional voices with recordings provided by students and EMO-DB contains professional voices, recorded from actors.
{"title":"Emotion recognition for disgust and boredom states","authors":"S. M. Feraru, M. Zbancioc","doi":"10.1109/ISSCS.2017.8034913","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034913","url":null,"abstract":"In this paper, we made the emotion recognition for Romanian language using EMO-IIT database with seven emotions (joy, sadness, fury, neutral tone, anxiety, disgust and boredom). Compared to our previous studies we introduced two new emotions: disgust and boredom and a new set of sentences in order to express better the emotional states. The best recognition rate of emotions is around 75% and was obtained for feature vectors which includes MFCC (Mel Frequency Cepstral Coefficients) + PARCOR (Partial Correlations Coefficients) + LAR (Log Area Ratios Coefficients). The accuracy rates are closed to the other studies from the literatures. For example, for the German emotional database EMO-DB which contains all seven emotions, the accuracy recognition rate reported by the researchers was around 85%. The disgust is often recognized as boredom (15%) or neutral tone (10%). The sadness is confused with the neutral tone (12%) and disgust (9%). The main difference between the two databases is that the EMO-IIT contains unprofessional voices with recordings provided by students and EMO-DB contains professional voices, recorded from actors.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131526495","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034932
Radu Tănase, C. Cazacu, D. Faur, D. Sacaleanu, M. Datcu
The overall goal of this paper is to assess the potential of fully polarimetric SAR data for land-use mapping in the field of ecosystem monitoring. State of the art ecosystems' studies aim at integrating in-situ measurements acquired by smart sensor networks with Earth observation data analysis to ensure data quality services to multiple applications. The near real time observation using optical and SAR data contributes to evaluation of biodiversity threats in a very dynamic environment, Danube floodplain and inland delta. This paper addresses the need for consolidated approaches to extract biodiversity features from polarimetric SAR data. Two overlapping PolSAR images (L-band PALSAR and C-band RadarSAT 2) were classified in an unsupervised manner using the EntropyAnisotropyAlpha-Wishart algorithm in order to differentiate between various types of vegetation in the region of Braila Island, Romania, and then the results were assessed in a scientific manner, as a function of the acquisition sensors characteristics.
{"title":"Potential of polarimetric SAR data use for ecosystems monitoring","authors":"Radu Tănase, C. Cazacu, D. Faur, D. Sacaleanu, M. Datcu","doi":"10.1109/ISSCS.2017.8034932","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034932","url":null,"abstract":"The overall goal of this paper is to assess the potential of fully polarimetric SAR data for land-use mapping in the field of ecosystem monitoring. State of the art ecosystems' studies aim at integrating in-situ measurements acquired by smart sensor networks with Earth observation data analysis to ensure data quality services to multiple applications. The near real time observation using optical and SAR data contributes to evaluation of biodiversity threats in a very dynamic environment, Danube floodplain and inland delta. This paper addresses the need for consolidated approaches to extract biodiversity features from polarimetric SAR data. Two overlapping PolSAR images (L-band PALSAR and C-band RadarSAT 2) were classified in an unsupervised manner using the EntropyAnisotropyAlpha-Wishart algorithm in order to differentiate between various types of vegetation in the region of Braila Island, Romania, and then the results were assessed in a scientific manner, as a function of the acquisition sensors characteristics.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129802191","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034937
Ioan-Catalin Dragoi, D. Coltuc, H. Coanda
This paper revisits the recently proposed adaptive pairwise reversible watermarking scheme of IEEE Trans. on Image Processing 2016 and investigates a different pairing that favors the grouping in the horizontal direction. The horizontal grouping imposes a new prediction scheme, a different complexity measure, a new pixel selection procedure and several other adjustments. For some test images, the newly proposed scheme outperforms the 2016 adaptive pairwise approach.
{"title":"Adaptive pairwise reversible watermarking with horizontal grouping","authors":"Ioan-Catalin Dragoi, D. Coltuc, H. Coanda","doi":"10.1109/ISSCS.2017.8034937","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034937","url":null,"abstract":"This paper revisits the recently proposed adaptive pairwise reversible watermarking scheme of IEEE Trans. on Image Processing 2016 and investigates a different pairing that favors the grouping in the horizontal direction. The horizontal grouping imposes a new prediction scheme, a different complexity measure, a new pixel selection procedure and several other adjustments. For some test images, the newly proposed scheme outperforms the 2016 adaptive pairwise approach.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130226703","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034904
I. Pirnog, R. Preda, C. Oprea, R. Dobre
This work presents the use of digital watermarking for applications of automated pigmented skin lesions assessment. Automated skin lesion assessment by digital image processing of macroscopic pigmented skin lesion (MPLS) images uses lesion characteristics for malignant risk computation. The accuracy of the computed risk level is increased when additional information is taken into consideration: age, gender, skin type, position of the lesions on body, and the presence of multiple and similar lesions. We propose a digital watermarking scheme for embedding relevant patient information into the color MPSL image. The preliminary experimental results are promising, and suggest that the proposed watermarking scheme is suitable for this type of application.
{"title":"Digital watermarking and segmentation of macroscopic pigmented skin lesions images","authors":"I. Pirnog, R. Preda, C. Oprea, R. Dobre","doi":"10.1109/ISSCS.2017.8034904","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034904","url":null,"abstract":"This work presents the use of digital watermarking for applications of automated pigmented skin lesions assessment. Automated skin lesion assessment by digital image processing of macroscopic pigmented skin lesion (MPLS) images uses lesion characteristics for malignant risk computation. The accuracy of the computed risk level is increased when additional information is taken into consideration: age, gender, skin type, position of the lesions on body, and the presence of multiple and similar lesions. We propose a digital watermarking scheme for embedding relevant patient information into the color MPSL image. The preliminary experimental results are promising, and suggest that the proposed watermarking scheme is suitable for this type of application.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129411916","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034896
Carmine Cappetta, G. Licciardo, L. Di Benedetto
A bi-dimensional filter for high accuracy image processing is implemented by using a novel partitioning method. The method is based on a number theory theorem, which permits to reduce the complexity of the operation to that of an adder chain and also the amount of the coefficients stored in memory, improving the memory organization. To show the advantage of such method, we implemented a Floating Point 32 (FP32) in hardware filtering applications and, in particular, for 2D FIR filters. Using Xilinx Virtex 7 Field Programmable Gate Array (FPGA) we obtain a critical path delay of 4.7ns which is comparable with the state-of-art.
{"title":"Hardware architecture for 2D Gaussian filtering of HD images on resource constrained platforms","authors":"Carmine Cappetta, G. Licciardo, L. Di Benedetto","doi":"10.1109/ISSCS.2017.8034896","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034896","url":null,"abstract":"A bi-dimensional filter for high accuracy image processing is implemented by using a novel partitioning method. The method is based on a number theory theorem, which permits to reduce the complexity of the operation to that of an adder chain and also the amount of the coefficients stored in memory, improving the memory organization. To show the advantage of such method, we implemented a Floating Point 32 (FP32) in hardware filtering applications and, in particular, for 2D FIR filters. Using Xilinx Virtex 7 Field Programmable Gate Array (FPGA) we obtain a critical path delay of 4.7ns which is comparable with the state-of-art.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"13 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123651345","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034941
Razvan Puscasu, G. Brezeanu
This paper presents a performance comparison between two current sense amplifiers (CSA) architectures, designed, simulated and implemented in a typical low cost BCD technology. The evaluation was done considering the main parameters that affect the sensing accuracy and both proposed low power circuits have been benchmarked against market available products.
{"title":"Low cost, wide common mode range amplifiers for current sensing applications - a comparison","authors":"Razvan Puscasu, G. Brezeanu","doi":"10.1109/ISSCS.2017.8034941","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034941","url":null,"abstract":"This paper presents a performance comparison between two current sense amplifiers (CSA) architectures, designed, simulated and implemented in a typical low cost BCD technology. The evaluation was done considering the main parameters that affect the sensing accuracy and both proposed low power circuits have been benchmarked against market available products.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125876672","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034888
F. Rotaru, S. Bejinariu, M. Luca, R. Luca, C. Nita
A procedure for laboratory rats tracking using image and video processing techniques is proposed. A plastic box split into three chambers by two walls is the analyzed scene. Each experiment starts with a sequence during at least eight minutes with a free rat placed in the middle area with the closed doors to the box marginal locations. The proposed method determines for each sequence frame the location of the rat head. For the second part of the experiment, with open doors, the procedure will be completed later on with the computation of free rat overall motion parameters and identification of specific rat behaviors.
{"title":"Video processing for rat behavior analysis","authors":"F. Rotaru, S. Bejinariu, M. Luca, R. Luca, C. Nita","doi":"10.1109/ISSCS.2017.8034888","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034888","url":null,"abstract":"A procedure for laboratory rats tracking using image and video processing techniques is proposed. A plastic box split into three chambers by two walls is the analyzed scene. Each experiment starts with a sequence during at least eight minutes with a free rat placed in the middle area with the closed doors to the box marginal locations. The proposed method determines for each sequence frame the location of the rat head. For the second part of the experiment, with open doors, the procedure will be completed later on with the computation of free rat overall motion parameters and identification of specific rat behaviors.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133662821","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034929
Radu Grigoraş, I. Ciocoiu
The paper reports comparative performances of five distinct algorithms used for rain removal from single images. Both synthetic and real images are considered, while taking into account standard figures of merit such as PSNR, VIF and SSIM. The experiments revealed that the Gaussian Mixture Model based approach yields best performances in terms of visual quality.
{"title":"Comparative analysis of deraining algorithms","authors":"Radu Grigoraş, I. Ciocoiu","doi":"10.1109/ISSCS.2017.8034929","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034929","url":null,"abstract":"The paper reports comparative performances of five distinct algorithms used for rain removal from single images. Both synthetic and real images are considered, while taking into account standard figures of merit such as PSNR, VIF and SSIM. The experiments revealed that the Gaussian Mixture Model based approach yields best performances in terms of visual quality.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"241 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030208","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034865
C. Nafornita, A. Isar, Norbert Matanie, Cristian Caba
We here present a solution to solve a big data problem in the context of satellite image processing. We conceived a simulator for denoising Sentinel 1 SAR Single Look Complex images, by using block processing together with a method based on the Hurst parameter estimation in the wavelet domain. We compare our method with traditional denoising filters.
{"title":"Solution of a big data problem. Simulator for denoising of Single Look Complex SAR images","authors":"C. Nafornita, A. Isar, Norbert Matanie, Cristian Caba","doi":"10.1109/ISSCS.2017.8034865","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034865","url":null,"abstract":"We here present a solution to solve a big data problem in the context of satellite image processing. We conceived a simulator for denoising Sentinel 1 SAR Single Look Complex images, by using block processing together with a method based on the Hurst parameter estimation in the wavelet domain. We compare our method with traditional denoising filters.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114650434","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：