Harsh Parikh

Harsh Parikh

Climate Technology and Computer Science.

Publications

Cryptocurrency Price Prediction Using Machine Learning

Published in 6th International Conference on Advance Computing and Intelligent Engineering, 2023

Globally, the use of cryptocurrencies to purchase goods and services has been rising. They rely on a secure distributed ledger data structure; mining is an integral part of such systems. The rise of cryptocurrencies’ value on the market and the growing popularity around the world open several challenges and concerns for business and industrial economics. Cryptocurrencies have been triggered by the substantial changes in their prices, claims that the market for cryptocurrencies is a bubble without any fundamental value and also concerns about evasion of regulatory and legal oversight. Machine learning is part of artificial intelligence that can make future forecastings based on previous experience. In this paper, methods have been proposed to construct machine learning algorithm-based models such as linear regression, K-nearest neighbour(KNN), and also statistical models like Auto-ARIMA and Facebook’s Prophet (Fbprophet). This paper presents a comparative performance of machine learning and statistical modelling algorithms for cryptocurrency forecasting.

Recommended citation: Parikh, H., Panchal, N., Sharma, A. (2023). Cryptocurrency Price Prediction Using Machine Learning. Proceedings of the 6th International Conference on Advance Computing and Intelligent Engineering. Lecture Notes in Networks and Systems, vol 428. Springer, Singapore. https://link.springer.com/chapter/10.1007/978-981-19-2225-1_25

Price Prediction for Pharmaceutical Stocks During Covid-19 Pandemic

Published in International Conference on Applications of Machine Intelligence and Data Analytics, 2023

Dramatic price changes in pharmaceutical equities reflect unexpected scientific information gained throughout the pharmaceutical R&D process, such as clinical trial results, recalls and withdrawals, and the approval of new treatments. During the Covid19 shutdown, major pharmaceutical firms were studying and producing vaccinations, pills, and other medicines to combat the coronavirus outbreak. This activity has a substantial impact on the global and Indian markets. Stock price prediction is an important issue in finance and economics that has piqued the interest of scholars throughout the years in developing better predictive algorithms. To evaluate Sun Pharma Ltd. data, we employed machine learning techniques such as K-nearest neighbor (KNN), Linear Regression, and Fbprophet during the time frame 2016 to 2020. It is the second-largest Indian pharmaceutical firm in terms of stock volume. Statistical modeling algorithm Fbprophet outperforms standard regressing algorithms like K-nearest neighbor and Linear regression on time series data.

Recommended citation: Parikh, H., Padariya, K. V., Sharma, A. (2023). Price Prediction for Pharmaceutical Stocks During Covid-19 Pandemic. Proceedings of the International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA 2022), 61-68. Atlantis Press. https://www.atlantis-press.com/proceedings/icamida-22/125986299

Autonomous Mobile Robot for Inventory Management in Retail Industry

Published in Futuristic Trends in Networks and Computing Technologies., 2022

In recent years, the idea of autonomous vehicles is on pace as some automobile companies have decided to develop their autonomous cars. Autonomous mobile robots (AMR) are currently being used in a variety of intra-logistics operations, such as warehousing, terminals, manufacturing, hospitals, and cross-docks. Their advanced control software and hardware allow autonomous operations in dynamic environments. In this paper, we have implemented a differential drive robot equipped with a depth camera and an RP LIDAR. This robot is capable of autonomous navigation through the warehouse environment by processing the data obtained through the sensors in real time. It can navigate to a particular shelf and then count the no. of cartons present on the shelf and compare it with previous data to give us an idea about the present inventory. It uses deep learning-based object detection models for the detection of cardboard boxes on a shelf.

Recommended citation: Parikh, H., Saijwal, I., Panchal, N., Sharma, A. (2022). Autonomous Mobile Robot for Inventory Management in Retail Industry. Futuristic Trends in Networks and Computing Technologies. Lecture Notes in Electrical Engineering, vol 936. Springer, Singapore. https://link.springer.com/chapter/10.1007/978-981-19-5037-7_7