Ibtissem Cherfa, Anissa Zergaïnoh-Mokraoui, A. Mekhmoukh, K. Mokrani
{"title":"Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering Algorithm Using Particle Swarm Optimization for Medical Image Segmentation","authors":"Ibtissem Cherfa, Anissa Zergaïnoh-Mokraoui, A. Mekhmoukh, K. Mokrani","doi":"10.23919/spa50552.2020.9241242","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241242","url":null,"abstract":"This paper is concerned with Magnetic Resonance (MR) brain image segmentation using Adaptively Regularized Kernel-Based Fuzzy C-Means (ARKFCM) clustering algorithm. However this algorithm is sensitive to the random initialization of the clusters’ centers and moreover its optimal solution can be trapped into a local rather than a global solution. To overcome these drawbacks, this paper proposes the Particle Swarm Optimization (PSO) strategy to compute the clusters’ centroids instead of using directly the derived analytic expression of the centroids given by the ARKFCM algorithm. Experimental results, carried out on MR brain images from the BrainWeb database, show that the revisited ARKFCM algorithm improves the performance of its original version.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133785929","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":"Stationary environment models for Advanced Driver Assistance Systems","authors":"Marek Szlachetka, D. Borkowski, Jarosław Wąs","doi":"10.23919/spa50552.2020.9241306","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241306","url":null,"abstract":"The vision of a fully self-driving autonomous car is year by year closer to be achieved. The crucial part of this vision is the perception which is carried by complex algorithms processing signals coming from a set of different sensors. A selfdriving car has to know locations of stationary obstacles in its surrounding. This paper is an overview of existing models used to describe the stationary environment. Grid models like 1D, 2D or 3D discrete maps, primitive structures and free space boundary contours are described with some illustrative examples. Models are compared from the point of view of description completeness as well as applications. Estimates of memory consumption are also given.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115652579","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}
A. Dąbrowska, Michal Adamski, A. Dabrowski, T. Jankowski, Michał Kliczkowski
{"title":"Environmental quality monitoring with unmanned aircraft vehicle","authors":"A. Dąbrowska, Michal Adamski, A. Dabrowski, T. Jankowski, Michał Kliczkowski","doi":"10.23919/spa50552.2020.9241299","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241299","url":null,"abstract":"The paper discusses issues related to the possibility of using unmanned aerial vehicles (UAV) as an alternative to stationary analyses in the assessment of environmental quality, with particular emphasis on air pollutants such as particulate matter (PM), volatile organic compounds (VOCs), formaldehyde and SO2. In the course of the study, a simple mobile and automated measuring equipment was developed, with a miniaturized and lightweight design, which made it possible to place it on board of an unmanned aircraft. The applied solutions, including electrochemical sensors, allow to measure concentrations of specific substances or aspiration of samples from selected places for further analyses in a stationary laboratory. Thanks to communication with web server, the results can be collected online. Unlike stationary measurement methods, the mobility of unmanned aerial vehicles allows to obtain a larger number of measurement points from a larger area, which in turn allows to map zones particularly exposed to emissions and to assess the existing hazards on an ongoing basis.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121113015","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":"Efficient detection of specific language impairment in children using ResNet classifier","authors":"K. Kotarba, Michal Kotarba","doi":"10.23919/spa50552.2020.9241289","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241289","url":null,"abstract":"Specific language impairment (SLI), also known as developmental dysphasia, is a developmental language disorder that affects approximately 7% of the preschool population. It has long-term impact on children’s academic performance and educational progress. Moreover, SLI negatively affects children’s communication skills and social interactions. It is therefore essential to diagnose the condition at the early stage and conduct appropriate speech therapy. However, SLI often remains undetected due to the great variability of the symptoms and lack of optimal diagnostic indicators. In this paper, we propose an efficient approach to automatic SLI detection based on log-power spectra of speech samples. The LANNA children speech corpus containing utterances of healthy controls and SLI-diagnosed children was used during the algorithm development. The utterances were used to calculate the normalized log-power spectrograms. Deep neural network algorithm based on ResNet architecture was used to perform the classification task. The accuracy rate of proposed SLI detection method exceeds 99% in the speakerindependent scenario. Presented algorithm outperforms most of the state-of-the-art algorithms in terms of accuracy rate and requires low computational power due to its simplicity.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"51 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124536161","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}
J. Balcerek, A. Konieczka, Karol Piniarski, P. Pawlowski
{"title":"Classification of road surfaces using convolutional neural network","authors":"J. Balcerek, A. Konieczka, Karol Piniarski, P. Pawlowski","doi":"10.23919/spa50552.2020.9241254","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241254","url":null,"abstract":"In this paper a classifier of road surfaces, visible from the front of the car, is presented. It is intended to use in the driver assistance or the autonomous car systems. The classifier was prepared, tuned and tested using AlexNet/CaffeNet convolutional neural network. To perform experiments, an original database of about 500 surface images was prepared. Nine classes of road surfaces were recorded: asphalt, concrete, two types of concrete paver blocks, granite paver blocks, openwork surface, gravel, sand, and grass. Using this database, two groups of testing experiments were performed: recognition of a particular type of road surface and determination of the general condition of the surface. Classification results show accuracy over 85% in the first experiment and over 91% in the second experiment. The results are promising, especially that, e.g. the sensitivity of recognition of bad surfaces reaches 95%, what indicates the potential possibilities of usage of the proposed classifier in real cars.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129149773","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":"Optimisation of the PointPillars network for 3D object detection in point clouds","authors":"Joanna Stanisz, K. Lis, T. Kryjak, M. Gorgon","doi":"10.36227/techrxiv.12593555","DOIUrl":"https://doi.org/10.36227/techrxiv.12593555","url":null,"abstract":"In this paper we present our research on the optimisation of a deep neural network for 3D object detection in a point cloud. Techniques like quantisation and pruning available in the Brevitas and PyTorch tools were used. We performed the experiments for the PointPillars network, which offers a reasonable compromise between detection accuracy and calculation complexity. The aim of this work was to propose a variant of the network which we will ultimately implement in an FPGA device. This will allow for real-time LiDAR data processing with low energy consumption. The obtained results indicate that even a significant quantisation from 32-bit floating point to 2-bit integer in the main part of the algorithm, results in 5%-9% decrease of the detection accuracy, while allowing for almost a 16-fold reduction in size of the model.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131136126","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}