PhD Thesis by Research Scholars of CE department http://10.9.150.37:8080/dspace//handle/atmiyauni/1286 2026-04-27T19:00:35Z 2026-04-27T19:00:35Z Desai, Nirav Harshadrai Dr. Parag, Shukla http://10.9.150.37:8080/dspace//handle/atmiyauni/1348 2024-02-23T10:21:08Z 2023-08-22T00:00:00Z

Title: Design and Development of a Model for Classification and Mapping of Land Use and Land Cover Using Multi Spectral Space Born Remote Sensing Images Authors: Desai, Nirav Harshadrai; Dr. Parag, Shukla Abstract: Remote sensing (RS) is the technique of finding and understanding information from a long distance or remote location using sensors. Land use and land cover mapping are fundamental tasks for planning and management. Identification of land cover and measurement of area under cultivation for various land use land cover is a very important task. However, techniques available for the above mention purpose are labor incentives, time- consuming, and costly. Remote sensing plays an important role in the mappings and classification of land cover features. Remote sensing provides very significant and sensed information. The deep neural network was used to perform the study. This study shows the semantic segmentation of LISS-III multispectral image using a fully convolutional network (FCN): U-net, Tiramisu, and Deeplabv3+. A multispectral image captures image data within specific wavelength ranges across the electromagnetic spectrum (EM). It has more than 100 nm resolution and less the 10 bands. Semantic Segmentation aims at a pixel-level classification of remote sensing images where every pixel is allotted to an individual class. We present an innovative dataset, based on these LISS-III images that contained 4 different spectral bands (Band-2 (Blue), Band-3 (Green), Band-4(Red), and Band-5 (Nearly Infrared), the false color composite (FCC) images and the ground truth mask images to classify total 4 classes (Water Bodies, Vegetation, Uncultivated Land, and Residential arcas). U-Net, Tiramisu, and DeepLabv3+ were used to perform classification on 3 datasets of different sizes and seasons (Dataset 1:1470 images, Dataset 2:13500 images Dataset - 3: 940 images). A total of 4 classes were successfully identified in the present study (Water Bodies, Vegetation, Uncultivated Land, and Residential areas). The experiment showed that the U-Net algorithm has a very good capability for the classification of LISS-III images for land use land cover class detection. U-Net performs better than DeeplabV3+. U-net achieved an accuracy of 81% for dataset-1, 84% for dataset-2, and 77% for dataset-3 respectively, Deeplabv3+ achieved an accuracy of 31% for dataset-1, and 26% for dataset -2 and 25% for dataset-3 whereas Tiramisu achieved 51% for dataset-1, 37% for dataset-2 and 33% for dataset -3.

2023-08-22T00:00:00Z Rayjada, Hardiksinh Hardevsinh Dr. Parag Shukla http://10.9.150.37:8080/dspace//handle/atmiyauni/1343 2024-02-23T09:48:42Z 2022-10-30T00:00:00Z

Title: Designing Data Centre for Providing Services to Small Industrial Area Authors: Rayjada, Hardiksinh Hardevsinh; Dr. Parag Shukla Abstract: The Cloud Data Center it's not a Data Center or Server room, Cloud is a Third-party services provider that provides servers for rent via the Internet it’s called a cloud. The data centre it's a typical server room, anyone can deploy as per requirement. There are numerous factors to consider when deciding on the knowledge of a data centre. Data centre design is the process of improvement of modelling and planning a data centre's Information Technology properties architectural arrangement and perfect arrangement. It allows the logical idea of a data centre preceding to increase or employment in an organization or IT background. I was identified at an early stage in the Small and Medium industry to use on-premises server rooms or also use a Cloud Data centre. In both scenarios Small and medium enterprise businesses can't afford it. In this research, I have comparative services displayed in some data centre. Server room and Data centre working functionality same as like require power, cooling, cabling, and technical maintenance and management. Additionally, mission-critical applications require 24x7x365 support. I compare cloud data center and local server room costs estimated in this research the Small and MSME are using the data center facelift at a cost-effective rate. Various academic and scientific research work has been done around the green energy data center, challenges. Herewith we research about re-thinking data center design then it is required for data center services, hardware and maintenance cost, and energy cost. Data center also consumes more energy to air condition. The major research work is on green energy and energy-sufficient data center design and some research work is on network architects in the data center. Every data center service is required today all the digitization is online. Rajkot Industrial area has more than a thousand Industrial units. Out of thousands, in metoda GIDC Hundreds of industrial units have their data centre installed. These industries are daily surviving and dependent on data Security, Hardware Issues, Networking Issues, Data Backup, and Cyber-attack, in time solution, depend on third-party services and support. Many industries units are medium or small, it does not afford to own a data centre, and they simply use ERP for normal functions & routine tasks. His not migrated cloud-based services because of server cost, and Internet cost, and due to that, they cannot get better performance. They can't trust any cloud-based services and also, he requires one employee for a cloud solution or third-party support. Many industries use local ERP only for uses SAP or International standard Production Software. The local industry has many other thins regarding data centre such as Data Security issues, Server Host and Storage Costs, Local ISP Bandwidth costs, and Dependency on Bandwidth. As GLIA METODA no competition increases between data centre colocation providers, so not require more value-added services and facilities. The Centre of Excellence in These might include conference rooms, offices, and access to office equipment. Our purpose is to design a datacentre for small industries or users to the nearest geographic location and provide a connection Fibber Optical Cable or Wireless Connection network architecture. All units’ direct connection to the data center same as a local server. Data centre design and architecture to near industrial areas and provide services to Small and medium industries. Proposed the data centre to Industrial area is strong bonding and trust to users his data security and stable connection to the server. GLIA Industrial Units requirements to On-Premise Data centre or Local Data centre with Security and Cost-effective as well as technical support. The town Data Centre site is nearest to an Industries Unit or organization. The users who wish to visit the centre or supervise the on-site staff from a Data centre are required. The data centre location in nears GIDC is Security is trusted. Proposed the planning of Town Data Centre in GLIA Metoda. Server and Rack sizing, PGVCL Power supply grids, EPBX and telecommunications, Internet Leased Line networking services, Local transportation, and technical emergency support and services required can affect costs, risk, security, and other features that need to be data centre deployment. The Town Data Center has a cost-efficient substantially lower lease rate compared to the market. Reliable Service Level Agreement 99.99% availability of the overall system. Industry-leading SLAs and Hyper-scale servers offer upgrades within the same facility. Flexible commercial approach. Our basic survey of the need of industries for data centre requirements is very difficult to convey without any demo or practical scenario to industry users are agree with the town data centre model. The limitation of the study is we propose the model of the Town Data Centre in the logical scenario in practice we need financial help or any IT Company are agree to work as a pilot project, its design to deploy the nearest Industrial area and provide data centre connection throw Optical fibber cable or wireless connection. Rajkot City are educated employees with computer talent and expertise. With the influx of technology jobs appearing in Rajkot city smaller markets have seen an increase in the number of technical experts are increase. The main advantage of this research is our proposed model for the data centre is designed as per the requirement of the town and a town using zero-latency connectivity and cost-effective data centre felicity with nearest to geography location. Town data centres are located closer to the end-user than the public cloud. Herewith using this research Machine learning hybrid recommendation model using data centre services recommend to users. This model uses Item Based, Supervised, Unsupervised, Hybrid recommendation algorithms. Random forest Supervised ML Algorithms in this all are used fully to predict and statistical

2022-10-30T00:00:00Z Naik, Akruti Narendrakumar Dr. Hetal Thaker http://10.9.150.37:8080/dspace//handle/atmiyauni/1342 2024-02-23T09:49:24Z 2022-11-17T00:00:00Z

Title: Design and Development of A Model to Classify Crop Foliar Diseases Authors: Naik, Akruti Narendrakumar; Dr. Hetal Thaker Abstract: Food security is a main apprehension in a modern society. Plant disease is critically disturbing the yield of agricultural crops and it is a massive threat to food security. Early identification of plant disease can reduce the influence of disease on crop yield. Agriculture has become much more than just a means to nourish continually increasing populations. Plants have become an important source of energy, and also plays an important role to solve global warming issue. There are numerous diseases that distress plants with the hidden to cause disturbing economical, social and ecological losses. Therefore, detecting diseases in a precise and timely way is of the most significance task. In tropical countries like India, incomes of agricultural crops are enormously affected by several plant diseases. Early identification of these diseases can be valuable to eliminate the effect of disease on crop yield. Empirical techniques of identification is time consuming and lengthy. It is remarkable that most of the plant dieses produce different symptoms on the surface of the leaves. Most diseases, though, generate some kind of appearance in the visible range. In the vast majority of the cases, the diagnosis, or at least a first guess about the disease, is performed visually by humans. Symptoms developed generally on every organ of a plant. However, symptoms developed on a foliage creates great effect on electromagnet symptoms. These symptoms can be identified using various digital image analysis techniques. Image analysis techniques can be useful to resolve this problem. A relationship between digital numbers in various pixels can be identified from the image. Pixel wise classification techniques can be applied to identify disease symptoms on the leaves of plant. The overall process involves various stages namely, image acquisition, image segmentation, feature selection / extraction, and classification. This study incorporates a model that Classifies a Mung (Vigna mungo L.) leaf to check whether it is healthy or infected with a disease with the aid of Machine Learning and Deep Learning algorithms. For this work, researcher used a self-created dataset of Mung leaf. The leaf samples have been collected from the South Gujarat Region. The images have been captured from Navsari Agriculture University, Gujarat and other crop fields of nearer villages. Images has been captured using various smart phones like Mi Note 8 Pro which has 64MP camera and Oppo A5 13MP camera. The dataset is created in a three different environments namely controlled environment, uncontrolled environment and combined environment, where Page | XIX a controlled environment is a data item (image) that comprises only a single subject (leaf) and a white background. In an uncontrolled environment, an image contains the Mung leaf, background noise like stems, ground, other Mung leaves, etc. In combined environment images of both the controlled and uncontrolled environments are merged together. Seven different classifiers namely Support Vector Machine (SVM), KNN (K Nearest Neighbor), AdaBoost (Adaptive Boosting), GaussianNB (Gaussian Naive Bayes), DTC (Decision Tree Classifier), LogisticRegression and Custom CNNs with different architectures have been trained and compared to each other. Researcher aims at detecting 3 mung leaf disease categories and a healthy leaf category. The model extracts complex features of various diseases. Early detection will help farmers to improve their productivity. The main objective was to automate Mung Leaf disease identification using advanced machine learning and deep learning approaches and image data. Among all the classifiers the custom CNN achieved performs well and achieved highest accuracy in all the three environments. Custom CNN achieves 99.24% of training and 95.05% of testing accuracy in controlled environment. In uncontrolled environment custom CNN achieves 99.69% training and 87.88% of testing accuracy. In combined environment custom CNN achieves 98.81% of training and 90.68% of testing accuracy. The results shows high potentiality of machine vision for recognition of diseased leaves. An interface is developed where user can input and image. Here are user can select image from either single leaf (controlled environment), photo captured from the field itself (uncontrolled environment). Image given as input by interface will be given to model for classification whether it is healthy or having disease and if it is affected by disease then which disease the leaf has i.e. amongst the three Cercospora Leaf Spot, Powdery Mildew, and Yellow Mosaic Virus. Interface is just a medium to interact with model, and model works as an engine that does classification in background.

2022-11-17T00:00:00Z