{"title":"Fusion of Feature Selection Techniques and Machine learning Algorithms for Attack Classification on 802.11 Wi-Fi AWID Dataset","authors":"Sofia Jamil, Mayank Agarwal","doi":"10.1109/GCON58516.2023.10183427","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183427","url":null,"abstract":"Vulnerabilities pertaining to the Media Access Control (MAC) layer are the primary reason for the existence of attacks in 802.11 Wi-Fi networks. In this paper, we aim to explore the Aegean Wi-Fi intrusion dataset (AWID) and design a model for detection and classification of network intrusions. There are three classes of attacks present in the dataset: impersonation, flooding, and injection. In intrusion detection systems (IDS), machine learning classifiers are one of the most effective solutions for preventing unauthorised access to resources. The key aspect of building a model based on machine learning is feature selection. In this paper, we have used four machine learning classifiers, namely Decision Tree, Random Forest, Gaussian NB, and Bernoulli Naive Bayes, for the classification of data as normal or intrusive. We have further applied filter methods and wrapper methods for feature selection. To the best of our knowledge, machine learning along with feature selection has never been used on the AWID-CLS-R dataset. The proposed work achieved the highest accuracy of 95.2% using a random forest classifier in 104 seconds using filter methods as the feature selection technique. In addition, we have used a confusion matrix and model building time for evaluating other machine-learning classifiers.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"1 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":"126279532","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":"First Principle based Studies for Efficient NO2 Gas Sensors on MoSe2 and WSe2","authors":"P. Kalita, Asifa Khatun, B. Mondal","doi":"10.1109/GCON58516.2023.10183568","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183568","url":null,"abstract":"Crude oil exploitation, air pollution has driven serious concern related to environmental and human health issues worldwide. For this, the continuous detection and monitoring of the air quality has become of vital importance. It is imperative to develop effective gas sensors for detection of hazardous gases. Two-dimensional (2D) transition metal dichalcogenide (TMDC) is a promising material for real-time gas monitoring and instantaneous detection of harmful and dangerous gases. This work presents theoretical simulation based on first principle calculations on Molybdenum diselenide (MoSe2) and Tungsten diselenide (WSe2) for its large surface-to-volume ratio, tunable gaps and reactive surface sites. Band diagram, Density of states (DOS) of the sensors were studied. Utilizing the QUANTUM-ESPRESSO programme package and BURAI software which is a graphical user interface (GUI) programme of QUANTUM-ESPRESSO, the absorption behaviours of Nitrogen dioxide (NO2), Nitric oxide (NO), and Ammonia (NH3) on the sensing materials (MoSe2 and WSe2) have been examined. Defects were even introduced for better understanding of the sensing mechanism. In this work, simulations were done by both using defects and without defects. The results, thus, obtained from the first principle calculations gives better theoretical insight of absorption and sensing mechanism between the target gas and the sensing layer which later aids during the experimental measurements and make the experiments cost effective. This theoretical results conclude that MoSe2 and WSe2 are good candidates for detecting NO2 gas, which will lead to the development of NO2 gas sensors for environmental monitoring in domestic and industrial applications.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"14 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":"131153378","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}
Shivashish Gour, Rohit Kumar Kasera, W. N. Singh, T. Acharjee
{"title":"Low Cost IoT Based Smart Irrigation System for Potato Cultivation","authors":"Shivashish Gour, Rohit Kumar Kasera, W. N. Singh, T. Acharjee","doi":"10.1109/GCON58516.2023.10183589","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183589","url":null,"abstract":"In today's world Smart agriculture is playing vital role to enhance quality and quantity of food production with optimum utilization of farmers' time and efforts. Smart irrigation is an important component of it. Potato cultivation needs regular irrigation for maintaining the required soil moisture. Potato plants are normally grown in dry season. Therefore, scarcity of water for irrigation is observed in many potato fields. Here we have proposed a smart irrigation system for optimum usage of water during irrigation in potato fields. Prior to performing smart irrigation, various soil parameters were monitored, like soil type, humidity, and temperature of the atmosphere. To ensure the quality of water that is to be supplied to the potato plants, the water pH was also checked. Data from the sensors were transferred to the edge server using Low-Power Wide Area Network (LPWAN) technology and from the edge server to the cloud using the Message Queuing Telemetry Transport (MQTT) protocol. Machine learning classification models and Deep belief neural network (DBNN) are employed to create intelligent irrigation systems, and a quick comparative analysis has been done with earlier studies. The results obtained helped us to conclude that our system achieved optimum use of water for irrigation.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"30 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":"133128890","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}
Lakshman S V Sri, A. Karthick, S. Akash, R. Anuradha
{"title":"Traffic Prediction Using Graph Neural Network","authors":"Lakshman S V Sri, A. Karthick, S. Akash, R. Anuradha","doi":"10.1109/GCON58516.2023.10183504","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183504","url":null,"abstract":"Traffic prediction is an important and challenging task in transportation management. Accurately predicting traffic patterns is crucial for reducing congestion, improving safety, and optimizing travel time. In recent years, graph neural networks (GNNs) have shown great potential in predicting traffic by taking into account the graph structure of road networks. In this project, we propose to develop a traffic prediction system using GNNs. The proposed system consists of three main components: data pre-processing, model development, and model evaluation. We first collect traffic data from various sources and pre-process it to remove noise and inconsistencies, and convert it into a suitable format for GNNs. We then develop a GNN model designed to capture the graph structure of the traffic network and use it to predict traffic patterns for a given time interval. The proposed model is trained and optimized using a loss function and evaluated using standard metrics such as root mean squared error (RMSE). The proposed traffic prediction system has the potential to significantly improve traffic management and reduce congestion by providing accurate traffic predictions. The GNN model can capture complex traffic patterns and dependencies between different parts of the road network, leading to more accurate predictions. Overall, this project aims to provide a better understanding of the potential of GNNs in traffic prediction and contribute to the development of more efficient and effective transportation management systems","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"31 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":"133437754","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":"Development of the Co-reference Resolution Tagged Data set in Assamese @ A Semi-Automated Approach","authors":"Mridusmita Das, Apurbalal Senapati","doi":"10.1109/GCON58516.2023.10183580","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183580","url":null,"abstract":"Co-reference resolution (CR) is an essential task in several Natural Language Processing (NLP) applications. It implies finding all the linguistic expressions (known as mentions) in a given text and the references of those mentioned. Consider the following text: Ishwar Chandra Bandyopadhyay was a great man in India in the nineteenth century. He received the honorable title Vidyasagar. In this text, each italics phrase is a mention and all are co-references. That means both expressions He and Vidyasagar refer to the same discourse entity Ishwar Chandra Bandyopadhyay. It is used in various NLP applications like Text Summarization, Information Retrieval (IR), Question Answering systems, Machine Translation (MT), etc. To develop a co-reference system using any algorithm must be needed the data. For a resource-scarce language like Assamese, there is no such data set or supportive tools to prepare the data. So, the data preparation is the primary task of the research in co-reference resolution. This paper attempt a semi-automated approach to develop a tagged data set for the co-reference resolution. This resource will boost the researchers in NLP research in Assamese languages.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"5 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":"116435239","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":"Translation of Low Illumination On-road Images to Well Illuminated Ones for Assisting Driving using Deep Auto-Encoders","authors":"R. R, Ravindra, Anirban Dasgupta","doi":"10.1109/GCON58516.2023.10183480","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183480","url":null,"abstract":"Low illumination can be dangerous for driving, as human perception depends upon ambient illumination. This paper attempts to aid driving in poor illumination using illumination-correction techniques. We propose an approach of low-light image enhancement using a de-noising convolutional auto-encoder (DNCAE) dedicated to on-road conditions. We prepare a custom data set consisting of paired images of well-lit and synthetically darkened images. A sample of this data set is used to train a neural network model that produces a better-illuminated estimate of the scene. We solve the color constancy issue of our model using a color space conversion designed for human perception of vision. The method has shown effectiveness against existing illumination correction techniques regardlna specific metrics viz. PSNR, SSIM, MSE and MAE.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"27 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":"124920131","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":"Study of an air-activated flat vertical axis wind turbine","authors":"Dhriti Rudrapal, Shantanu Acharya","doi":"10.1109/GCON58516.2023.10183452","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183452","url":null,"abstract":"The growing energy demand and scarcity of fossil fuels turning the present world towards renewable energy sources. Wind energy can be a solution that can meet the demand up to a certain extent. The giant turbines come with many limitations. Meanwhile, several new turbine designs are coming with individual as well as commercial solutions. Most of the existing wind turbines are either lift or drag-driven with their individual merits and demerits. In the present study, an air-activated hybrid-type flat vertical axis wind turbine has been investigated. The turbine model and its functioning have been described here. The mathematical model is developed to address the behaviour of the turbine. To justify the hybrid nature, individual drag, and lift force components are examined. Further, the torque and resulting output power from the turbine have been calculated and presented. The turbine showed a cut-in speed of 4.59 m/s. At a wind speed of 7 m/s, the maximum drag and lift forces are found as 2.401 and 0.065 N, respectively. At the same wind speed available torque is observed as 0.028 N-m and the resulting output power is 6.41 W.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"199 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":"114557666","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":"Transformer based multimodal similarity search method for E-Commerce platforms","authors":"Chandan Charchit Sahoo, D. Tomar, J. Bharti","doi":"10.1109/GCON58516.2023.10183514","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183514","url":null,"abstract":"Multimodal similarity search has been attracting much attention from scholars in recent times. The intensification of research into Multimodal search lies in the motive to understand the context of the multiple modes associated with the data and the interdependency of these modes. Multimodal data can be in the form of audio, video, images, texts, and any combination of them. For relevant extraction of features from them can take too much time and thus it may cause the whole process of learning the features and searching for them time-consuming. In this work, a deep neural network uses Convolutional neural network and Bidirectional Encoder Representations from Transformers to learn features from text and image data. A K nearest neighbor along with KD Tree has been used to search for similar image-text pairs. Evaluations based on several image-text multimodal retrieval procedures show the effectiveness of the proposed multimodal search method and its higher speed performance compared to existing algorithms.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"1 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":"128196750","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":"Memory and CPU utilization-aware Energy-Efficient VM Placement and Consolidation in Cloud Data Centers","authors":"Alok Choudhury, Kaustav Kumar Nath, Manojit Ghose, Yogita Thakran","doi":"10.1109/GCON58516.2023.10183444","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183444","url":null,"abstract":"Virtualization is one of the key techniques applied in Cloud data centers for seamlessly hosting and managing several applications together. However, the system performance level may get deteriorated if there exist co-located high resource utilization virtual machines (VMs). On the other hand, in order to reduce the growing energy consumption of the data centers, VMs are typically consolidated. This further deteriorates the system performance. Therefore, to tackle such problems, an efficient VM consolidation method using multiple parameters such as CPU, and memory associated with the VM is proposed. Our main contribution includes considering a weighted summation of CPU and memory utilization for VM consolidation with the objective to reduce energy consumption. The approach is based on the symbiotic association between hosts and VMs which is analogous to the biological interaction between parasites and host organisms, also termed symbionts in a biological ecosystem. A comparative analysis with the existing method states that a considerable amount of energy consumption got reduced using our proposed technique.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"53 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":"128582688","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":"DGA domain detection using pretrained character based transformer models","authors":"Bronjon Gogoi, Tasiruddin Ahmed","doi":"10.1109/GCON58516.2023.10183602","DOIUrl":"https://doi.org/10.1109/GCON58516.2023.10183602","url":null,"abstract":"DGAs (Domain Generation Algorithms) are a class of algorithms used by Malwares for generating pseudorandom domain names. The generated pseudorandom domain names are used by Malwares for communicating with C&Cs (Command and Control Centre) to receive updates and other critical information. The pseudorandom nature of the generated domain names makes it harder for traditional security measures like firewalls to detect the communication between Malwares and the C&Cs. Other traditional defense mechanisms like blocklists are also not effective as it is difficult and time-consuming to maintain an ever-growing list of malicious domains. To eliminate these deficiencies of the traditional approach, many machine learning and deep learning approach have been proposed for the detection of DGA-generated domain names. In this paper, we proposed a pretrained transformer-based approach to detecting DGA-generated domain names. Our approach aims to see if a given domain name is a DGA-generated domain name or a benign domain name based only on the domain name. The proposed approach was tested on a 1 million dataset containing DGA-generated and benign domain names. The results demonstrated a remarkable accuracy of 0.99, affirming the effectiveness of pretrained transformer-based models in the binary classification of domain names into benign and DGA categories.","PeriodicalId":445700,"journal":{"name":"2023 IEEE Guwahati Subsection Conference (GCON)","volume":"23 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":"128373448","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}