{"title":"Comparison of Pre-Trained Models Using Transfer Learning for Detecting Plant Disease","authors":"Bincy Chellapandi, M. Vijayalakshmi, Shalu Chopra","doi":"10.1109/ICCCIS51004.2021.9397098","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397098","url":null,"abstract":"Artificial Intelligence has been proving a great boon in almost all the sector of industries. In recent times the demand for food has increased, whereas the supply still lacks. In order to meet these increasing demands, prevention and early detection of crop disease are some of the measures that must be inculcated in farming to save the plants at an early stage and thereby reducing the overall food loss. In this paper, we use a deep learning-based model and transfer learning-based models to classifying images of diseased plant leaves into 38 categories of plant disease based on its defect on a Plant Village dataset. Eight pre-trained models namely VGG16, VGG19, ResNet50, InceptionV3, InceptionResnetV2, MobileNet, MobileNetV2, DenseNet along with the one self-made model were used in our study. We found that DenseNet achieves the best result on the test data with an accuracy of 99%.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123343731","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}
Muhammad Yunis Daha, M. Zahid, Khaleel Husain, Firas Ousta
{"title":"Performance Evaluation of Software Defined Networks with Single and Multiple Link Failure Scenario under Floodlight Controller","authors":"Muhammad Yunis Daha, M. Zahid, Khaleel Husain, Firas Ousta","doi":"10.1109/ICCCIS51004.2021.9397125","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397125","url":null,"abstract":"Software-Defined Networking (SDN) breaks the barrier of traditional networks and upgrades the current network infrastructures. SDN eliminates the vertical bonding between the control plane from the data plane which forwards the data traffic. Moreover, SDN translates the traditional IP networks into programmable IP networks. However, one of the key research challenges in SDN is link failure that may lead to the disruption of network service and its performance. Link failure issues in SDN further lead toward data packet loss, recovery time delay, message overhead, backup resource consumption, and network congestion problems. This paper investigates single and multiple link failure recovery scenarios in SDN and reflects the SDN performance in reacting with such conditions. To monitor and control the behavior of the network traffic, Dijkstra based rerouting algorithm of the Floodlight controller will be used during the occurrence of single and multiple link failures. The Mininet tool along with the Java-based SDN Floodlight controller to analyze the single and multiple link failure scenarios for OpenFlow-based custom network topology. This work also measures and analyzes the performance of SDN without link failure scenarios in single, linear, and tree topologies. The performance of SDN for basic network topologies and OpenFlow based custom network topology is measured in terms of the average round-trip and the average throughput","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120937863","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":"Ubiquitous Sensor based Intelligent System for Net Houses","authors":"Neha Jain, Yogesh Awasthi, RK Jain","doi":"10.1109/ICCCIS51004.2021.9397080","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397080","url":null,"abstract":"The increment in the production from the agricultural sector is very important for the development of any country. However, the country like India, where the major population is dependent on the agriculture as their primary occupation and the only source of earning. This research paper proposes a model for the development of an Intelligent system for the net houses, which is designed by using the best available ubiquitous sensor in the market. This system works on the Internet of things (IoT) based wireless system which transmits the fundamental parameters in real time perceivable through a series of ubiquitous sensors placed inside the net house. The designed system will function to monitor the various crucial parameters like soil moisture, humidity, temperature, lighting in the net house which is further transmitted to the cloud server using the IoT based dedicated framework. The data analysis is carried out in the cloud server. The analysis is based on the ideal big data available for each crop suitable for cultivation in the net houses. The transmitted data from the net house is analyzed using a machine learning (ML) algorithm executing over the cloud server. This intelligent system drives the actuating device on crossing the threshold value, which regulates the important parameter and keep them at the optimum level inside the net house. The overall activity of the system is accessible by the farm manager using a dedicated mobile application. This technique will fully discard the requirement of man power and will also provide the maximum efficiency with the use of optimum resources.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121557342","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":"An Efficient Criminal Segregation Technique Using Computer Vision","authors":"Harshavardhan Dammalapati, M. Swamy Das","doi":"10.1109/ICCCIS51004.2021.9397174","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397174","url":null,"abstract":"In the contemporary world, where the population has been growing rapidly, it has become difficult to identify suspicious persons. Given the abundance of population in public places, it is difficult to identify a culprit post-crime activity because one (in general, the investigator) has to go through the entire CCTV footage to track and pin down people who seem suspicious for further investigation. These traditional methods are very time-consuming and laborious since each footage can be at least hours long. This proposed method takes advantage of the fact that the culprit tries to hide their identity by either evading the camera or by masking themselves. In places like shopping malls, movie theaters, restaurants, etc. these cameras are placed at the entrance and at security checks. Hence, it is not plausible for them to completely evade the cameras. This shifts our concentration to the latter idea that they hide their identity by masking themselves. We build our model on this flaw and combine video surveillance with machine intelligence to provide an efficient interface than unprocessed video feed. Furthermore, this system is not only useful for post-crime scenarios but can also be deployed for real-time analysis.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122666970","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":"Classification of Textures Using Pixel Range Calculation Method","authors":"Abadhan Ranganath, M. Senapati, Pradip Kumar Sahu","doi":"10.1109/ICCCIS51004.2021.9397155","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397155","url":null,"abstract":"A good texture classification algorithm can easily detect and classify different types of objects. Several texture classification techniques are there to match the similar objects and distinguish different types of objects or surfaces. In this article an improvised version of texture classification technique called Pixel Range Calculation (PRC) technique has been presented. The PRC method provides better classification accuracy and takes less time for computation as compared to other discussed methods. In this article the proposed method has been compared with two state of art methods called Multi Fractal Spectrum (MFS) and Gliding Box Method (GBM). The textural dataset of Brodatz, CUReT (Columbia-Utrecht Reflectance and Texture Database) and Describable Textures Dataset (DTD) have been taken for experiment. From experimental result it has been observed that, the PRC method outperforms other two methods by its matching accuracy of 98.54%, 97.44% and 97.19% for Brodatz, CUReT and DTD dataset respectively. From confusion matrix it is observed that the PRC method is most accurate one for classification.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"520 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134440478","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 Cost-Efficient QCA XOR-XNOR Topology for Nanotechnology Applications","authors":"D. Tripathi, Subodh Wairya","doi":"10.1109/ICCCIS51004.2021.9397215","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397215","url":null,"abstract":"Quantum-dot cellular automata (QCA) is an inventive nano level computation that suggests less dimension, less power consumption, with more speed and premeditated as an amplification to the scaling obstacle with CMOS methodology. One of the newest and rising nanotechnologies used today is QCA based on the repulsion of Coulomb. One of the newest and rising nanotechnologies used today is QCA based on the repulsion of Coulomb. Surmised computing is a successful paradigm for energy efficient hardware design in nano-scale. In this article, we proposed a proficient, low complex 2-bit and 3-bit QCA XOR gate has been suggested. Further the suggested QCA XOR gates are utilized to design XOR/XNOR gates and cost efficient 4:2 Encoder and 4:1 Encoder using QCA Designer tool. The proposed QCA XOR gate contains very less number of quantum cells as well as areas as related to its best previous existing QCA layouts. The simulation outcomes illustrate that the suggested architecture outperforms in comparison to best existing counterpart layouts in terms of quantum cell count, area, latency and quantum cost.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134445333","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}
Adil Ahmad Rather, Tasawor Ahmed Sofi, Nowreen Mukhtar
{"title":"A Survey on Fatigue and Drowsiness Detection Techniques in Driving","authors":"Adil Ahmad Rather, Tasawor Ahmed Sofi, Nowreen Mukhtar","doi":"10.1109/ICCCIS51004.2021.9397224","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397224","url":null,"abstract":"Drowsiness and fatigue could be fatal during driving as it can lead to accidents. So, there is an acute demand and need of drowsiness cum fatigue detection of drivers during driving sessions. In this paper some important and possible techniques are presented to give reader a comprehensive idea of how technology could save millions from traffic accidents. This paper presents the state-of-the-art review of various potent techniques which are presently in use. Various techniques used till date are majorly based on eye/head tracking and wheel steering pattern tracking. These techniques are categorized into five different categories i.e., Subjective reporting, biological characteristics, physical characteristics, vehicular characteristics, and hybrid characteristics. This paper also discusses the problems faced by the current technology which need to be addressed in future. We believe that this study offers a clear understanding of drowsiness and fatigue detection techniques and contribute to the improvements of the current technology in near future.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134467942","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":"User Profiling in Travel Recommender System using Hybridization and Collaborative Method","authors":"A. Anjali, Jasminder Kaur Sandhu, D. Goyal","doi":"10.1109/ICCCIS51004.2021.9397099","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397099","url":null,"abstract":"The recommender system is improving with the increase in the information obtained from numerous application domains. Recommendation or the prediction of an item depends on the rating and review given by an individual or a group of customers. New user information can also be predicted using the searching history or the profile information of the customer. In Travel Recommender System, the locations of interest are figured out based on the activities carried out by the user or the preference of that particular user. It also helps in exploring the diverse geographical areas of interest of the user. The increasing demands of this system enhances the scope in development of user behaviour that is based on recommendation approaches. It also effectively deals with the sparsity problem by searching through a large amount of data to provide users with individual contents and services. This article explores the various aspects and potentiality of existing approaches in the Travel Recommender System based on user profiles for future research directions and recommendation framework.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130367853","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":"Gradient Based Optimization Approach to solve Reliability Allocation System","authors":"Zubair Ashraf, Mohammad Shahid, Faisal Ahmad","doi":"10.1109/ICCCIS51004.2021.9397197","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397197","url":null,"abstract":"This paper proposes a solution approach to solve the reliability redundancy allocation problem (RRAP) of a series-parallel framework using a Gradient-based optimizer (GBO). In RRAP, the objective is to optimize the total system's reliability considering different nonlinear constraints (cost, volume, weight, etc.) by simultaneously determining the number of redundancies and the component reliabilities of each subsystem. A parameter-free penalty approach allows the proposed GBO based solution algorithm to benefit the approach to investigate within the feasible search space and the nearby achievable area and prevent incompetent solutions. To prove the effectiveness of the presented solution approach, the data of the pharmaceutical plant with the RRAP parameters are used, and the results are obtained. Comparative study indicates0.044% superior performance of proposed GBO approach to Particle Swarm optimization (PSO) basedapproach.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"369 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124627963","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 Approach to Scene Graph Vectorization","authors":"Vinod Kumar, Deepanshu Aggarwal, Vinamra Bathwal, Saurabh Singh","doi":"10.1109/ICCCIS51004.2021.9397230","DOIUrl":"https://doi.org/10.1109/ICCCIS51004.2021.9397230","url":null,"abstract":"In recent times due to the advancement in perceptual applications, focus in computer vision has been inclined towards tasks that require a significant level of semantic understanding of scenes. Combination of textual and visual information has resulted in a great improvement in performance on tasks like retrieval, captioning and visual q/a etc. In this regard, scene graphs have become a popular form of structural knowledge. But unlike Word embedding, general-purpose scene graph embedding has not been explored significantly. In this work, we propose a general-purpose scene graph embedding model that combines linguistic and graph processing techniques through a reconstruction based learning network to learn a low-dimensional data-driven vectorized embedding of scene graphs. Visualization of embedding of COCO dataset has shown to possess semantic separability and distance-based abstraction of scenes. When applied to a retrieval task and evaluated using Med-r and recall metric on COCO-stuff and VRD dataset, our model showed promising results.","PeriodicalId":316752,"journal":{"name":"2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134028110","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}