http://10.9.150.37:8080/dspace//handle/atmiyauni/511 Sun, 10 May 2026 15:03:18 GMT 2026-05-10T15:03:18Z http://10.9.150.37:8080/dspace//handle/atmiyauni/966 A study of recommendation system in E-commerce Gohel, Divyesh; Vanjara, Pratik Recommendation Systems (RS) are commonly employed in the e-commerce business to deal with the problem of information overload. Because there is so much information available these days, users are having trouble discovering relevant product and service information that matches their tastes and interests. The technique of obtaining relevant knowledge from enormous databases is known as data mining (DM). DM's job is to describe and forecast data so that information may be retrieved. Information retrieval (IR) is a subfield of RS, which is a subfield of data mining (DM). Recommendation engines are essentially data filtering and information retrieval tools that employ algorithms and data to suggest the most relevant item to a given user. Content-based (CB) filtering, Collaborative Filtering (CF), and hybrid filtering techniques are some of the strategies and methodologies employed by RS. This study explains the function of data mining in recommendation systems and provides an RS process. Also includes a methodological overview, RS difficulties, and a comparison of several e-commerce website recommendation systems. Sat, 01 Jan 2022 00:00:00 GMT http://10.9.150.37:8080/dspace//handle/atmiyauni/966 2022-01-01T00:00:00Z http://10.9.150.37:8080/dspace//handle/atmiyauni/965 A survey: Cyber security facet for machine learning algorithms Gohel, Amit M.; Vanjara, Pratik A. It is undeniably true that right now data is a really huge presence for all organizations or associations. In this way ensuring its security is vital and the security models driven by genuine datasets has become very significant. The activities dependent on military, government, business and regular citizens are connected to the security and accessibility of PC frameworks and organization. Starting here of safety, the organization security is a critical issue on the grounds that the limit of assaults is constantly ascending throughout the long term and they transform into be more modern and circulated. The target of this audit is to clarify and look at the most usually utilized datasets. This paper centers cyber security aspect to the various machine learning approaches such as Random Forest, SVM and KDD. Sat, 01 Jan 2022 00:00:00 GMT http://10.9.150.37:8080/dspace//handle/atmiyauni/965 2022-01-01T00:00:00Z http://10.9.150.37:8080/dspace//handle/atmiyauni/963 Crop price data interpretation: A comparison of machine learning Hirpara, Jignesh; Vanjara, Pratik Machine learning and its methodologies are used in agribusiness domains to predict edit costs based on stock availability and generation. On a daily basis, a massive amount of data is generated through the display of farming products. Horticulture has a large amount of data, but unfortunately, much of it isn't able to find out inconspicuous details in information. Edit cost estimates are more beneficial to agriculturists and the agriculture society since they demand proper timing. Information mining procedures that have progressed play a critical role in the discovery of hidden design in data. Following Designs, Cluster Analysis, and visualization methodologies are used to provide a unique representation to predict the horticultural edit cost. Past trim cost, climate, current advertise cost, stock accessibility, and up and coming trim generation in current year or season are all used to compare information mining procedure execution.Recently, the most often used programmer has been designed for cost inquiry rather than cost determination. When compared to individual agriculturists in various countries with stable environments, India's agribusiness generation is exceptionally instable, and without appropriate MSP, it will not benefit agriculturists and farming crew. If ranchers and agribusiness personnel are given the opportunity to appropriate alter costs, destitution in India can be reduced. Sat, 01 Jan 2022 00:00:00 GMT http://10.9.150.37:8080/dspace//handle/atmiyauni/963 2022-01-01T00:00:00Z http://10.9.150.37:8080/dspace//handle/atmiyauni/960 Hybrid machine learning in classification methods for HCR in gujarati language Doshi, Priyank D.; Vanjara, Pratik The problem of recognizing Gujarati Handwritten character with vowels opening new future scope where one can use smart phone, website or any handy scanner to convert hand written Gujarati Language into text. It will be very effective to give education in mother language at primary level. Public, Private and Government sectors will be benefited when they get any hand written Guajarati Script and they can directly convert it into softcopy or into text form. There are many methods used to solve this problem.Using CNN we can improve new algorithm depending on training data set, mathematical model and other intricacy. Convolutional Neural Network or machine learning is very useful for this. Still there are more chances for improvement and rising accuracy using Machine learning in combination of Deep Learning as a hybrid model. Sat, 01 Jan 2022 00:00:00 GMT http://10.9.150.37:8080/dspace//handle/atmiyauni/960 2022-01-01T00:00:00Z