2021 IEEE 18th India Council International Conference (INDICON)最新文献_第3页

Implementation and Performance Analysis of Indian Sign Language Recognition on various Computing Devices 印度手语识别在不同计算设备上的实现与性能分析

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691542

Eshaan Rathi, Jatin Luthra, Abhishek Sharma

引用次数: 1

Novel Approach for Detection, Localization, and Mitigation of Malicious Node in NoC based SoC 基于NoC的SoC中恶意节点检测、定位和缓解的新方法

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691753

Sachin Bagga, Ruchika Gupta

{"title":"Novel Approach for Detection, Localization, and Mitigation of Malicious Node in NoC based SoC","authors":"Sachin Bagga, Ruchika Gupta","doi":"10.1109/INDICON52576.2021.9691753","DOIUrl":"https://doi.org/10.1109/INDICON52576.2021.9691753","url":null,"abstract":"System-on-chip (SoC) uses Network-on-chip(NoC) concept to connect different components. With increasing applications of the Internet of things, chips have become more vulnerable due to the involvement of multiple third party vendor providing various Intellectual Property (IP) during manufacturing process. Hardware Trojan (HT) is one of the security vulnerabilities of the chip that makes the underlying NoC unsafe and degrades system performance. In the proposed work we model one of such HT attacks that create nuisance across NoC by its malicious behaviour. We propose an HT detection, localization, and shielding mechanism that safeguards the underlying interconnect, saves NoC resources from wasteful computation, and improve the overall system performance in terms of essential parameters. Re-routing after shielding is also proposed that nullifies the attacks impacts and helps a packet reaches to its destination with marginal increase in the hop count. The study takes both the delay of service and denial of service case scenario imposed by HT and empirical evaluation supports the claim by providing improved statistics.","PeriodicalId":106004,"journal":{"name":"2021 IEEE 18th India Council International Conference (INDICON)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133296933","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}

引用次数: 1

Traffic Management using Computer Vision and SUMO 使用计算机视觉和相扑的交通管理

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691665

Bodicherla Digvijay Sri Sai, Ramisetty Nikhil, Payarda Santosh Babu, Nenavath Srinivas Naik

{"title":"Traffic Management using Computer Vision and SUMO","authors":"Bodicherla Digvijay Sri Sai, Ramisetty Nikhil, Payarda Santosh Babu, Nenavath Srinivas Naik","doi":"10.1109/INDICON52576.2021.9691665","DOIUrl":"https://doi.org/10.1109/INDICON52576.2021.9691665","url":null,"abstract":"Traffic signals play a crucial role in the transportation system. They guarantee a safe drive at the road intersections. Traffic signals reduces traffic flow as the traditional signal scheduling gives green light to each direction for a predetermined time. In traditional signal scheduling, Green signal is allocated to all directions, one after another. If there is heavy traffic in one direction and less in another, Traditional scheduling method does not show any bias among them. This results in over traffic accumulation and traffic congestion at the road intersections. To give priority to the directions that has the maximum vehicle count, we propose an algorithm. The proposed algorithm takes vehicle count of all directions into consideration and gives immediate attention to direction where traffic is getting accumulated. The signal allocation does not only consider vehicle count. It is done in such a way that no direction gets to wait too long. Hence, the algorithm we propose gives equal importance to both Traffic density and Waiting Time. Moreover, it aims to minimize total waiting time of all the vehicles. We performed various experiments, from the obtained results, we were able to highly reduce the overall waiting time of vehicles in all directions.","PeriodicalId":106004,"journal":{"name":"2021 IEEE 18th India Council International Conference (INDICON)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133654101","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}

引用次数: 0

A Script Independent Hybrid Feature Extraction Technique for Offline Handwritten Devanagari and Bangla Character Recognition 一种脱机手写体德文、孟加拉文识别的独立于文字的混合特征提取技术

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691708

Raghunath Dey, Rakesh Chandra Balabantarayy, Jayashree Piriz

{"title":"A Script Independent Hybrid Feature Extraction Technique for Offline Handwritten Devanagari and Bangla Character Recognition","authors":"Raghunath Dey, Rakesh Chandra Balabantarayy, Jayashree Piriz","doi":"10.1109/INDICON52576.2021.9691708","DOIUrl":"https://doi.org/10.1109/INDICON52576.2021.9691708","url":null,"abstract":"Recognizing handwritten characters plays a significant role in different applications of pattern recognition. That is why the digital representation of character images is much necessary to design an efficient offline Optical Handwritten Character Recognition System (Offline HCR). Here a hybrid feature representation method is suggested for two Indic scripts, such as Devanagari and Bangla. The method utilizes three different features to represent any character images. Those are angular motion of character shape-based feature, center to the thin text of character shape-based feature, and center to edge text of character shape-based feature. After collecting all these three features, these are applied to various machine learning algorithms, including two modified neural network models. One simple traditional convolutional neural network is also designed which takes immediate images and recognizes the character images. Although the two modified neural network models are unable to hit the peak in terms of accuracy like the traditional CNN, it is found that two of our modified NN models take quite less time to execute upon the character datasets.","PeriodicalId":106004,"journal":{"name":"2021 IEEE 18th India Council International Conference (INDICON)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127640088","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}

引用次数: 1

UDE based RISE Controller for Active Flutter Suppression of 2D Aerofoil 基于UDE的二维翼型主动颤振抑制RISE控制器

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691535

Balraj Sharma, A. Dixit, Pooja Agrawal, A. Misra

{"title":"UDE based RISE Controller for Active Flutter Suppression of 2D Aerofoil","authors":"Balraj Sharma, A. Dixit, Pooja Agrawal, A. Misra","doi":"10.1109/INDICON52576.2021.9691535","DOIUrl":"https://doi.org/10.1109/INDICON52576.2021.9691535","url":null,"abstract":"In this paper, active flutter suppression (AFS) of a typical two dimensional aerofoil using a new continuous control technique, called Robust Integral of Signum of Error (RISE) is proposed. The aerofoil model involves two degrees of freedom of motion i.e. pitch and plunge. To enhance the performance of controller in presence of parametric uncertainty and external disturbances, RISE controller has been robustified by designing an uncertainty and disturbance estimator (UDE), which will estimate the total lumped disturbances. The controller does not require any knowledge of plant model or information of uncertainty and disturbances. The efficacy of UDE based RISE controller has been illustrated by simulations using parametric uncertainty, external disturbances, time delay, variation in free stream velocity and constraint of control surface deflection. Results show that proposed controller has enhanced the performance of closed loop system by 68% beyond critical flutter speed. Performance comparison of proposed design has been carried out with UDE based SMC controller which prove the effectiveness of proposed design. Lastly, results indicate that UDE based RISE controller has drastically reduced the rise time, settling time and also, control efforts have been reduced by upto 75% in comparison to UDE based SMC controller.","PeriodicalId":106004,"journal":{"name":"2021 IEEE 18th India Council International Conference (INDICON)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127651946","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}

引用次数: 2

Autopilot Design for Vision Assisted Autonomous Fixed Wing Micro Air Vehicle 视觉辅助自主固定翼微型飞行器的自动驾驶仪设计

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691662

Shuvrangshu Jana, M. Shewale, Susheel Balasubramaniam, Sidhant Dhall, M. Bhat

引用次数: 0

Estimating Power Supply Induced Jitter using S-Parameter based Modeling of Transmission Media 基于s参数的传输介质建模估计电源诱发抖动

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691639

Diksha Singh, V. Verma, J. N. Tripathi

引用次数: 0

Character Segmentation from Handwritten Gujarati isolated words using Deep Learning 使用深度学习的古吉拉特语手写孤立词的字符分割

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691590

Riya P. Javia, Mukesh M Goswami, S. Mitra

{"title":"Character Segmentation from Handwritten Gujarati isolated words using Deep Learning","authors":"Riya P. Javia, Mukesh M Goswami, S. Mitra","doi":"10.1109/INDICON52576.2021.9691590","DOIUrl":"https://doi.org/10.1109/INDICON52576.2021.9691590","url":null,"abstract":"Information retrieval from scanned handwritten digital copies is a very challenging task especially in Indian scripts like Gujarati due to the presence of joint and conjuct characters as well as matras, cursive nature and varying size of the characters. There are two methods namely recognition-based and recognition-free for document image retrieval. The difference in both approaches lies in the level of segmentation. There are two levels of segmentation namely Fine and Coarse Grain. In Fine-Grain segmentation, the base character and the matras are considered as separate and are two different units of segmentation. In Coarse-Grain segmentation, the base character and matras are considered as a single unit of segmentation. The accuracy of the segmentation highly affects the result of information retrieval. The research here heads towards addressing these issues. Deep learning has been very effective in many domains but has not been used much in this domain. In this research, we propose a Coarse Grain segmentation method using the object detection model Faster RCNN and a Fine Grain segmentation method using a combination of Connected Component Analysis and Faster RCNN. The annotation of the dataset for training these models has been carried out manually using LabelImg tool.","PeriodicalId":106004,"journal":{"name":"2021 IEEE 18th India Council International Conference (INDICON)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114940556","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}

引用次数: 1

A Novel Decoder Design for Logic Computation in SRAM: CiM-SRAM 一种新的SRAM逻辑计算解码器设计:CiM-SRAM

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691664

Kanika Monga, Sahil Aggarwal, N. Chaturvedi, S. Gurunarayanan

引用次数: 2

Classification of Seizure Types Based on Statistical Variants and Machine Learning 基于统计变量和机器学习的癫痫类型分类

2021 IEEE 18th India Council International Conference (INDICON) Pub Date : 2021-12-19 DOI: 10.1109/INDICON52576.2021.9691717

Anand Shankar, S. Dandapat, S. Barma

{"title":"Classification of Seizure Types Based on Statistical Variants and Machine Learning","authors":"Anand Shankar, S. Dandapat, S. Barma","doi":"10.1109/INDICON52576.2021.9691717","DOIUrl":"https://doi.org/10.1109/INDICON52576.2021.9691717","url":null,"abstract":"The majority of the research works are successfully applying advanced machine learning algorithms to classify epileptic seizures using electroencephalograms (EEG). Certainly, the accurate classification of epileptic seizure types can play a significant role in the prognosis and treatment of epileptic patients’ conditions. In this work, machine learning classifiers — artificial neural network, decision tree, k–nearest neighbor, random forest, and eXtreme boosting gradient have been employed to classify complex partial seizure, focal non-specific seizure, generalized non-specific seizure types, and seizure-free. For this purpose, statistical variants — mean, skewness, kurtosis, standard deviation, approximate entropy, and energy have been extracted from EEG segments. Thenceforth, machine learning algorithms performed multi-class epileptic seizure type classification based on these variants. Furthermore, using the principal components analysis methodology, the classification of epileptic seizure types has been analyzed using the lower dimensions of statistical variants sets. For evaluation of the proposed method, a publically available EEG dataset contributed by the Temple university hospital (TUH, v1.5.2) has been taken into consideration. The classification accuracy of multi-class epileptic seizure types has achieved up to 100%. The experimental performances demonstrated that the proposed work can efficiently and accurately classify the seizure types.","PeriodicalId":106004,"journal":{"name":"2021 IEEE 18th India Council International Conference (INDICON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117228958","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}

引用次数: 4