Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161438
Turan Goktug Altundogan, M. Karakose
Noise is a generic term for data loss or corruption due to hardware or software causes on the signal. Since the images are two-dimensional signals, there are noises in this type of signal due different reasons. In addition, fuzzy cognitive maps (FCM) have a structure based on a graph theory that can produce many probing solutions today. Fuzzy cognitive maps can provide their iterations as static (fixed neighborhood values) or dynamic (variable neighborhood values) depending on the solution, which belong to interested problem. In this study, a method is presented using fuzzy cognitive maps for noise reduction in images and mean filter, which is a widely used method for noise reduction. The proposed method provide to minimize the loss of data in the noise reduction process with the average filter. In this work, FCM takes noisy and average filtered noisy image masks and accepts each pixel value in these masks as nodes. Then we update the neighborhood weights between these nodes in each iteration. The developed method has been tested primarily with different images and the performance obtained only by the method in which the average filter is applied is quite high. Then, the proposed method was tested on images of traffic monitoring systems taken from vehicle cameras. The results obtained are very successful.
{"title":"A Noise Reduction Approach Using Dynamic Fuzzy Cognitive Maps for Vehicle Traffic Camera Images","authors":"Turan Goktug Altundogan, M. Karakose","doi":"10.1109/ZINC50678.2020.9161438","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161438","url":null,"abstract":"Noise is a generic term for data loss or corruption due to hardware or software causes on the signal. Since the images are two-dimensional signals, there are noises in this type of signal due different reasons. In addition, fuzzy cognitive maps (FCM) have a structure based on a graph theory that can produce many probing solutions today. Fuzzy cognitive maps can provide their iterations as static (fixed neighborhood values) or dynamic (variable neighborhood values) depending on the solution, which belong to interested problem. In this study, a method is presented using fuzzy cognitive maps for noise reduction in images and mean filter, which is a widely used method for noise reduction. The proposed method provide to minimize the loss of data in the noise reduction process with the average filter. In this work, FCM takes noisy and average filtered noisy image masks and accepts each pixel value in these masks as nodes. Then we update the neighborhood weights between these nodes in each iteration. The developed method has been tested primarily with different images and the performance obtained only by the method in which the average filter is applied is quite high. Then, the proposed method was tested on images of traffic monitoring systems taken from vehicle cameras. The results obtained are very successful.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"2 1","pages":"15-20"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86819638","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161439
Igor Kolak, Ž. Lukač, M. Knezic, Stefan Končar
Automotive vision systems represent a fast-growing application area and offer the potential of significant enhancements to automotive safety. In order to train ADAS (Advanced driver-assistance systems) algorithms with real-world data, high amount of video data needs to be captured. In this paper, we present one solution to capture high resolution and high frequency video data. Specifically, we capture 2 MPx (Megapixel) video data at 60 FPS (Frames per second) without compression and store it in real-time for later reproduction.
{"title":"Realization of automotive video data acquisition system for usage in evolution of autonomous vehicles","authors":"Igor Kolak, Ž. Lukač, M. Knezic, Stefan Končar","doi":"10.1109/ZINC50678.2020.9161439","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161439","url":null,"abstract":"Automotive vision systems represent a fast-growing application area and offer the potential of significant enhancements to automotive safety. In order to train ADAS (Advanced driver-assistance systems) algorithms with real-world data, high amount of video data needs to be captured. In this paper, we present one solution to capture high resolution and high frequency video data. Specifically, we capture 2 MPx (Megapixel) video data at 60 FPS (Frames per second) without compression and store it in real-time for later reproduction.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"31 3","pages":"160-164"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91469468","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161775
Mahendra Rathor, A. Sengupta
Digital signal processor (DSP) hardware accelerators are integrated in consumer electronics (CE) systems to facilitate image, audio and video processing applications. However, DSP hardware accelerators are vulnerable to hardware Trojan insertion threat because of involvement of untrusted offshore entities in the design chain. This leads to integration of Trojan infected designs into consumer electronics products, hence causing reliability and safety concerns for end consumers. Structural obfuscation is a security mechanism which offers a preventive control against Trojan insertion threat. This paper presents a pseudo operations mixing (POM) based novel structural obfuscation technique to secure DSP hardware accelerators against reverse engineering (RE), causing Trojan insertion threat. The proposed approach yielded a robust security at minimal design cost overhead than similar previous work.
{"title":"Obfuscating DSP Hardware Accelerators in CE Systems Using Pseudo Operations Mixing","authors":"Mahendra Rathor, A. Sengupta","doi":"10.1109/ZINC50678.2020.9161775","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161775","url":null,"abstract":"Digital signal processor (DSP) hardware accelerators are integrated in consumer electronics (CE) systems to facilitate image, audio and video processing applications. However, DSP hardware accelerators are vulnerable to hardware Trojan insertion threat because of involvement of untrusted offshore entities in the design chain. This leads to integration of Trojan infected designs into consumer electronics products, hence causing reliability and safety concerns for end consumers. Structural obfuscation is a security mechanism which offers a preventive control against Trojan insertion threat. This paper presents a pseudo operations mixing (POM) based novel structural obfuscation technique to secure DSP hardware accelerators against reverse engineering (RE), causing Trojan insertion threat. The proposed approach yielded a robust security at minimal design cost overhead than similar previous work.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"45 1","pages":"218-221"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88081510","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161443
D. Rodić, Marin Gostimirović, M. Sekulić, Branislav Batinić, Nikola M. Laković
The research investigated the optimization of various performance features on the basis of a gray-fuzzy analysis. The goal was to generate an intelligent system for the optimization of electrical discharge machining based on fuzzy logic and gray analysis. Taguchi's L9 experimental design was used as the research methodology. Two input parameters were selected, namely, discharge current and pulse duration. On the other hand, the material removal rate and surface roughness were taken as output machining performances. Depending on the response of the output performances, the input parameters are selected by applying the gray relation grade and signal-to-noise ratio strategy as performance index. The system is set up according to the following criteria: maximum material removal rate and minimum surface roughness. Based on these criteria, the optimal parameters were obtained, i.e. a discharge current of 5 A and a pulse duration of 5 μ. This combination results in a high gray fuzzy degree of 0.521, which is close to the reference value. Considering the results of the validation experiments, it is concluded that a gray-fuzzy approach can be successfully applied to obtain the optimal combination of influential control parameters.
{"title":"Optimization of EDM process using grey-fuzzy approach","authors":"D. Rodić, Marin Gostimirović, M. Sekulić, Branislav Batinić, Nikola M. Laković","doi":"10.1109/ZINC50678.2020.9161443","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161443","url":null,"abstract":"The research investigated the optimization of various performance features on the basis of a gray-fuzzy analysis. The goal was to generate an intelligent system for the optimization of electrical discharge machining based on fuzzy logic and gray analysis. Taguchi's L9 experimental design was used as the research methodology. Two input parameters were selected, namely, discharge current and pulse duration. On the other hand, the material removal rate and surface roughness were taken as output machining performances. Depending on the response of the output performances, the input parameters are selected by applying the gray relation grade and signal-to-noise ratio strategy as performance index. The system is set up according to the following criteria: maximum material removal rate and minimum surface roughness. Based on these criteria, the optimal parameters were obtained, i.e. a discharge current of 5 A and a pulse duration of 5 μ. This combination results in a high gray fuzzy degree of 0.521, which is close to the reference value. Considering the results of the validation experiments, it is concluded that a gray-fuzzy approach can be successfully applied to obtain the optimal combination of influential control parameters.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"42 1","pages":"307-312"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86549768","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：