Shilalipi Sahoo, Samuel Amde Gebereselassie, Ankit Tiwari, B. K. Roy
{"title":"Secure Image Encryption using a New Bowl-shaped Chaotic Attractor","authors":"Shilalipi Sahoo, Samuel Amde Gebereselassie, Ankit Tiwari, B. K. Roy","doi":"10.1109/GCON58516.2023.10183594","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183594","url":null,"abstract":"Image encryption using a chaotic signal is significant because it provides high security for digital images. Chaotic signals are highly unpredictable and difficult to replicate. Thus, they are suitable for the image encryption process. A new chaotic system is developed in this paper. The new system generates a bowl shape, chaotic attractor. The properties of the new chaotic system are studied by using the Lyapunov exponent diagram and bifurcation diagram. Then, the developed system is used to encrypt images of cameraman, apple, and peppers. Subsequently, the security analysis is done for the cameraman image. The resulting security level is investigated through correlation coefficient, histogram analysis, entropy analysis, signal-to-noise ratio, and differential attack analysis. It is found that the proposed encryption algorithm based on the developed chaotic system is efficient in protecting the vital image information transmitted through a communication channel.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127624316","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":"Object Detection Based Approaches in Image Classification: A Brief Overview","authors":"Akshima Aggarwal, Vaneet Kumar, Ruchika Gupta","doi":"10.1109/GCON58516.2023.10183609","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183609","url":null,"abstract":"Several methods have been put out in the past few years in the field of computer vision for the goal of obj ect detection. The offered methods carry out the task of classifying and locating an object inside an image or a series of photos. Modern object detection frameworks and techniques are referred to as evolutionary approaches. The challenges of obj ect detection in numerous photos and movies are addressed through evolutionary techniques. Using the spatial information of the object in the image frames, the evolutionary approach based approaches may detect objects. By sliding a window across the object instances in the given image sequence, these algorithms can extract the features of the objects. In this paper, we have reviewed the object detection field's evolutionary strategy. The backend CNN architectures, CNN-based object identification techniques, and common object detection databases are discussed in this paper. This paper primarily focus on dataset detection and finding suitable object detection method. We have also provided a list of open source frameworks for academics and students who may be interested in using them to create object identification methods and algorithms.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127745815","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":"Fault-tolerant Mutual Visibility for ASYNC Mobile Robots with Local Coordinate","authors":"Subhajit Pramanick, P. Mandal","doi":"10.1109/GCON58516.2023.10183479","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183479","url":null,"abstract":"We aim to solve the mutual visibility problem using n autonomous, indistinguishable, homogeneous, oblivious and opaque point robots where the number of robots that can be faulty is at most one. The fault may occur anytime. The faulty robot cannot move from the time it becomes faulty. Initially from any arbitrary configuration, the problem of mutual visibility using robots aims to reach a configuration where any two robots can see each other. The challenge is to reach to such a configuration in presence of obstructed visibility where two robots see each other only if the line segment joining them does not have any robots. Every robot operates in the conventional Look-Compute-Move cycles. Robots have no agreement in their coordinate system. We, in this paper, propose a distributed asynchronous algorithm for mutual visibility in presence of at most one faulty robot where robots has no agreement on any global coordinate axes.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127919700","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":"Explainable AI for Bearing Fault Detection Systems: Gaining Human Trust","authors":"Aparna Sinha, Shaik Fayaz Ahmed, Debanjan Das","doi":"10.1109/GCON58516.2023.10183502","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183502","url":null,"abstract":"In modern industrial processes, monitoring the health of rotating machinery is an important task. Many machine learning (ML) and deep learning (DL)-based models have shown good fault detection and diagnosis results. However, these models need to provide explanations and insights to users and experts in order to increase the adoption and spread of these technologies. Another common problem is the lack of labeled historical data, which makes it impossible to use supervised models. Therefore, we propose a new approach for fault detection and diagnosis (FDD) systems to overcome these challenges. In this approach, we used a vibration signal dataset and converted it into a statistical dataset by extracting the required features. An ML model, CatBoost, is used to detect and predict any faults in the machine and classify the fault type with an accuracy of 89.18%. To understand and explain the implemented model, we used an explainable AI method, SHapley Additive exPlanations (SHAP). Using SHAP, we obtained the dependency of the model on each of the features to predict the different classes of faults, thus making the model trustworthy for the users.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128598659","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}
Saquib Mazhar, Nadeem Atif, M. Bhuyan, S. R. Ahamad
{"title":"Improving Semantic Segmentation Performance of Deep Networks for Autonomous Driving through Loss Functions","authors":"Saquib Mazhar, Nadeem Atif, M. Bhuyan, S. R. Ahamad","doi":"10.1109/GCON58516.2023.10183416","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183416","url":null,"abstract":"Semantic segmentation of images for autonomous driving is a dense pixel-level prediction task. Present-day algorithms make extensive use of deep learning models for parsing the image. A large number of classes and class imbalance in the autonomous driving dataset make accurate labeling of pixels challenging. Cross- Entropy(Ce)loss function is mainly used to optimize the network parameters during training. The overall performance gain resulting from CE loss comes from large object classes. In contrast, the segmentation accuracy of smaller classes and object boundaries remains inferior, even with increased overall accuracy. To address this limitation, task- specific custom loss functions have been developed and used for various applications like biomedical image processing. However, they have rarely been used for road scene segmentation in an autonomous driving context. To fill this gap, we develop a composite loss function by linearly combining the CE loss and boundary/region-based loss to improve the existing state- of-the-art model. We give empirical evidence that our custom loss function improves the segmentation scores on smaller object categories and object boundaries. Through extensive experiments on the Cityscapes dataset, we show that Deep networks trained with our loss function see a gain of more than 2 % on the overall $m$ IoU score. In some smaller classes, these scores are increased by more than 20%.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129100952","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":"Quasi-predefined-time control and its comparison with nonlinear active control for hybrid synchronization of identical chaotic systems","authors":"Shilalipi Sahoo, B. K. Roy","doi":"10.1109/GCON58516.2023.10183441","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183441","url":null,"abstract":"Synchronization of chaotic systems provides a promising approach for controlling and regulating complex systems due to its potential in fields ranging from physics to engineering and from biology to finance. Here, a chaotic system for two different initial conditions is synchronized with the help of nonlinear active control and predefined-time control. In the case of nonlinear active control, two control inputs are used, whereas, in predefined-time control, three inputs are considered for convergence of the error dynamics. However, it is found that the control energy requirement is less in the predefined-time control within a comparable convergence time. In addition to the above investigation, a hybrid synchronization, i.e., a combination of phase-synchronization, anti-synchronization, and projective synchronization, is performed by designing a switching control law using a quasi-predefined control technique.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"50 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116282585","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":"Adaptive Filter Based Control Method for Performance Improvement of Hybrid Energy Storage System in DC Microgrid","authors":"Biks Alebachew Taye, N. Choudhury","doi":"10.1109/GCON58516.2023.10183437","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183437","url":null,"abstract":"Energy storage devices are required to store energy for constant and consistent operation of microgrid. Batteries are the common energy storage system in microgrid applications. However, due to low power density, it cannot handle high-frequency charging and discharging. To improve power quality, reduce power fluctuation, and ensure power balance, a hybrid energy storage system with high energy density storage devices and high power density storage devices is used. A hybrid energy storage system comprised of batteries and supercapacitors is proposed in this paper. For intermittent power, the hybrid energy storage management system is critical for ensuring system stability and maintaining constant DC bus voltage. This paper proposes an adaptive filter-based method (AFBM) control strategy for a DC microgrid that focuses on smooth and stable operation while mitigating storage device safety and degradation issues. Based on the recent state of charge of storage device in the DC microgrid, the control strategy proposes a charging and discharging current distribution. The proposed method and the conventional filter-based method are both simulated in MATLAB/Simulink with the same configuration, value, and operation mode. The results show that the proposed system outperforms the traditional method in terms of voltage stability, proportional load sharing, and proper charging/discharging of storage devices.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"21 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123567061","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":"A Novel Pipeline for Improving Optical Character Recognition through Post-processing Using Natural Language Processing","authors":"Aishik Rakshit, Samyak Mehta, Anirban Dasgupta","doi":"10.1109/GCON58516.2023.10183509","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183509","url":null,"abstract":"Optical Character Recognition (OCR) technology finds applications in digitizing books and unstructured documents, along with applications in other domains such as mobility statistics, law enforcement, traffic, security systems, etc. The state-of-the-art methods work well with the OCR with printed text on license plates, shop names, etc. However, applications such as printed textbooks and handwritten texts have limited accuracy with existing techniques. The reason may be attributed to similar-looking characters and variations in handwritten characters. Since these issues are challenging to address with OCR technologies exclusively, we propose a post-processing approach using Natural Language Processing (NLP) tools. This work presents an end-to-end pipeline that first performs OCR on the handwritten or printed text and then improves its accuracy using NLP.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"306 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121697024","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}
Tanmay Bhowmik, Jegyasu Gupta, Bodhan Chakraborty, Ashish Kr. Chowdhary, D. Sikdar
{"title":"Tunable Metasurface based Polarization-insensitive Electro-Optic Amplitude Modulator for Nanophotonic Systems","authors":"Tanmay Bhowmik, Jegyasu Gupta, Bodhan Chakraborty, Ashish Kr. Chowdhary, D. Sikdar","doi":"10.1109/GCON58516.2023.10183590","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183590","url":null,"abstract":"Electrooptic modulators are crucial elements in the photonic systems to encode electrical signal into optical carrier. However, realization of polarization-insensitive optical modulators with low power consumption remains a challenging task. In this study, we report a gap-plasmon resonance based electrically-tunable metasurface that can be operated with random polarization angles of incident optical signal. With 1.5 V external bias-voltage, we achieve ~15 dB extinction ratio at the telecommunication wavelength (i.e., 1550 nm) and a very low energy-consumption of 213 fJ/bit. Thus, the proposed device could find applications in the power-hungry nanophotonic systems.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121719804","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}
Sahana A R, Chiraag V, Gautham Suresh, T. P, Sukumar Nandi
{"title":"Application of Error Detection and Correction Techniques to Self-Checking VLSI Systems: An Overview","authors":"Sahana A R, Chiraag V, Gautham Suresh, T. P, Sukumar Nandi","doi":"10.1109/GCON58516.2023.10183449","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183449","url":null,"abstract":"Currently, the focus of VLSI industry has shifted towards circuit testability, as the advancements in technology yield more intricate and highly compact chips. With the increasing complexity of modern circuits, it is crucial to ensure that VLSI circuits yield accurate and reliable results. The use of self-checking circuits, which incorporate built-in error detection mechanism offers a promising solution to this challenge. This paper presents a comparative study of various error detection and correction techniques for self-checking circuits from existing research papers. The study's findings indicate that usage of modulo 3 residue code as self-checking circuits can be an efficient way to detect 99.8% errors and provide reliable results.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124793695","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}