Papers by Hasan Phudinawala
International Journal For Multidisciplinary Research, May 7, 2024
International Journal For Multidisciplinary Research, Mar 21, 2023
The process of utilizing statistical models to forecast the price at which a house will be sold i... more The process of utilizing statistical models to forecast the price at which a house will be sold in the future is known as house price prediction. In most cases, this is accomplished by analyzing the data from previous sales, in addition to various aspects of the house, such as the total square footage, the number of bedrooms, the location, and so on. The ability of house price predictions to assist individuals and organizations in making well-informed decisions regarding the purchase, sale, and investment of property is one of the primary reasons for their significance. For instance, a homebuyer might use house price prediction to figure out how much money they should offer for a house, while a real estate agent might use it to figure out how much money they should ask for a house that they are selling. In addition, investors may use house price prediction to determine regions that are likely to experience an increase in housing prices and then base their investment decisions on that information. Predicting house prices is a crucial task in the real estate industry, as it can help buyers, sellers, and investors make informed decisions. In the real estate market, one of the most important tasks is to accurately predict house prices, as this information can assist buyers and sellers in making more educated decisions about the value of their respective properties. In this investigation, we investigate the application of deep learning (DL) strategies for forecasting housing prices and evaluate how well these strategies perform in comparison to more conventional machine learning approaches. We found that DL models outperformed traditional machine learning methods in terms of prediction accuracy and were able to capture complex patterns in the data. Our results demonstrate the potential of for predicting house prices and highlight the importance of using advanced machine learning techniques in the real estate market. .
International Journal of Advanced Research in Science, Communication and Technology, Feb 24, 2022
The bike-sharing system allows people to rent a bike at one of the rental stations, use them for ... more The bike-sharing system allows people to rent a bike at one of the rental stations, use them for their journey, and return them to any other or the same station. In recent years, such systems encourage people to use bikes as a good complement to travel using modes of transport. The main purpose of this article is to predict the demand for shared bikes using multiple linear regression. Moreover, the article presents data cleaning process and data visualization for better understanding and to get useful insights from data. The results we get after visualization is that count of bike sharing is least for spring, the number of bikes increased in year 2019 and count of total rental bikes including both casual and registered increases in summer and are less in holidays. To understand which attributes needs to get dropped we used RFE (Recursive Feature Elimination) and VIF (Variance Inflation Factor) to drop columns with high p-values and to check the multicollinearity respectively. Now the model is able to predict the future demand for shared bikes in a city.
International journal of computer sciences and engineering, Apr 30, 2019
International Journal For Multidisciplinary Research
In the real estate market, one of the most important tasks is to accurately predict house prices,... more In the real estate market, one of the most important tasks is to accurately predict house prices, as this information can assist buyers and sellers in making more educated decisions about the value of their respective properties. In this investigation, we investigate the application of deep learning (DL) strategies for forecasting housing prices and evaluate how well these strategies perform in comparison to more conventional machine learning approaches.
International Journal of Advanced Research in Science, Communication and Technology, Mar 29, 2022
The aim of the paper is to develop application for vehicle parking management. As you can see lot... more The aim of the paper is to develop application for vehicle parking management. As you can see lot of increase in number of vehicles which is the major problem for traffic control and below standard parking management. Another issue to vehicle owner is to get availability of space to park vehicle. So we intent to create an application that user can book or pre-book parking slot for their vehicle at parking areas. The user can use the application by signing up and then selecting the space or slot for vehicle according to vehicle type at parking area. This application can be applicable in big multi-national companies, shopping centres, airports and event at large public parking areas etc.
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2022
Educational Data Mining (EDM) research has risen to prominence because it aids in the discovery o... more Educational Data Mining (EDM) research has risen to prominence because it aids in the discovery of relevant knowledge from educational data sets that can be used for a variety of reasons, such as forecasting students' academic performance and outcomes. Predicting student accomplishment may be beneficial in the development and implementation of a variety of improvements in education settings as a response to current educational systems. Machine learning has been used to predict students' achievement in a huge amount of existing research, which has taken a variety of factors into account, including family income, students' gender, students' absence, and stage-by-stage characteristics. In this proposal, an attempt is made to investigate the usefulness of applying the Deep Learning Algorithm (DLA), more specifically the Optimal Deep Neural Network (ODNN), to forecast students' progress, which could aid in determining whether or not students would be able to complete ...
International Journal of Advanced Research in Science, Communication and Technology, Mar 29, 2022
Industries have to manufacture products in large scale with respect to time in order to compete o... more Industries have to manufacture products in large scale with respect to time in order to compete others but while producing small electronic components goods in bulk where it is automated at some point. Sometimes due to malfunction in automation it produces defects in product which impact negatively in some percentages of production. So, we propose them with our project which will identify the product before getting out of manufacturing unit surveillance camera’s with highly trained model to specific task in detection can opt out defects from it. After placing them in required position they detect the products with defects or for particular detection which will make manufacturer hectic & complex work easy especially detecting micro components in it. In can be also cost reduction as we use raspberry pi. Infact all small industrial markets were facing issues to defects detection in small parts of electronic item like semiconductor with mobility devices. Are article is proposing a defect detection algorithm for micro components that are based on a single short detector network (SSD) and deep learning.
2020 International Conference on Convergence to Digital World - Quo Vadis (ICCDW), 2020
Due to the increasing population in urban cities, there is an exponential rise in the number of v... more Due to the increasing population in urban cities, there is an exponential rise in the number of vehicles which is leading to major problems leading to poor traffic management and congestion. Another major problem faced by the vehicle owners is the availability of parking space. The idea of Smart Cities is slowly gaining pace with the ever increasing technologies. Therefore, in the proposed parking system we are integrating the Wireless Sensor Technology with the Android Application so that the user can book or pre-book a slot. The vehicle owner will be able to reserve a slot for his/her vehicle from anywhere and will be provided with a QR code which will be scanned on the entry of the parking area. Another feature our system provides is providing information about the near-by parking areas which comes handy when the current parking area is full.
International Journal of Advanced Research in Science, Communication and Technology, 2022
The bike-sharing system allows people to rent a bike at one of the rental stations, use them for ... more The bike-sharing system allows people to rent a bike at one of the rental stations, use them for their journey, and return them to any other or the same station. In recent years, such systems encourage people to use bikes as a good complement to travel using modes of transport. The main purpose of this article is to predict the demand for shared bikes using multiple linear regression. Moreover, the article presents data cleaning process and data visualization for better understanding and to get useful insights from data. The results we get after visualization is that count of bike sharing is least for spring, the number of bikes increased in year 2019 and count of total rental bikes including both casual and registered increases in summer and are less in holidays. To understand which attributes needs to get dropped we used RFE (Recursive Feature Elimination) and VIF (Variance Inflation Factor) to drop columns with high p-values and to check the multicollinearity respectively. Now th...
International Journal of Computer Sciences and Engineering, 2019
Uploads
Papers by Hasan Phudinawala