Browsing by Author "Islam, Md. Tanvir"

Now showing 1 - 4 of 4

Automated Dhaka City Vehicle Detection for Traffic Flow Analysis Using Deep Learning
(Daffodil International University, 2021-06-13) Islam, Md. Tanvir
There are many ways to stop traffic jams from spreading, and one of the most effective is to detect the vehicle. The uniqueness of Dhaka's traffic situation creates a complicated and difficult occurrence, with over eight million passengers passing through the city every day in a 306 square kilometer area. To address this issue, our research includes a deep learning methodology for autonomous vehicle detection and localization from optical scans. Data preparation was done using annotated data from PoribohonBD with vehicle images. Vehicle detection is a critical step in the development of intelligent transportation systems (ITS). The challenges of vehicle detection on urban roads arise from the camera position, context variations, obstruction, multiple current frame objects, and transportation pose. The current study provides a synopsis of state-of-the-art vehicle detection techniques, which are classified thus according to motion and aesthetics techniques, beginning with frame differencing and background subtraction and progressing to feature extraction, a more complicated model in comparative analysis. The pre-processed data, as well as the fine-tuning hyper parameter, then input into the cutting-edge YOLOv5s deep learning model for autonomous vehicle detection and recognition. In the end, the training accuracy averaged 0.79% to detect vehicles in all classes.
Hotel Review Analysis for the Prediction of Business Using Deep Learning Approach
(IEEE, 2021-04-12) Hossen, Md.Sagar; Jony, Anik Hassan; Tabassum, Tasfia; Islam, Md. Tanvir; Rahman, Md Mahfujur; Khatun, Tania
Sentiment analysis is a widely used topic in Natural Language Processing that allows identifying the opinions or sentiments from a given text. Social media is the scope for the customers to share their opinion over the products or services as part of customer reviews. Dissect this review has become an important factor for business analysis since online business is exponentially growing in today's techno-friendly competitive market. A large number of algorithms have been found in recent articles. Among those deep learning is an important approach. In the proposed methodology, long short-term memory (LSTM) and Gated recurrent units (GRUs) have been used to train the hotel review data where the accuracy rate of identifying customer opinion is 86%, and 84% respectively. The dataset is also tested by using Naïve Bayes, Decision Tree, Random Forest, and SVM. For Naïve Bayes obtains an accuracy of 75%, for Decision Tree obtains an accuracy of 71%, for Random Forest the accuracy is 82% and for SVM our accuracy result is 71%. Deep learning is used to obtain better business performance and also get the review from customers and also to predict the sentiment about customer review. Our algorithm works properly and gives better accuracy.
Hotel Review Analysis for the Prediction of Business Using Deep Learning Approach
(International Conference on Artificial Intelligence and Smart Systems (ICAIS), IEEE, 2021-04-12) Hossen, Md. Sagar; Jony, Anik Hassan; Tabassum, Tasfia; Islam, Md. Tanvir; Rahman, Md Mahfujur; Khatun, Tania
Sentiment analysis is a widely used topic in Natural Language Processing that allows identifying the opinions or sentiments from a given text. Social media is the scope for the customers to share their opinion over the products or services as part of customer reviews. Dissect this review has become an important factor for business analysis since online business is exponentially growing in today's techno-friendly competitive market. A large number of algorithms have been found in recent articles. Among those deep learning is an important approach. In the proposed methodology, long short-term memory (LSTM) and Gated recurrent units (GRUs) have been used to train the hotel review data where the accuracy rate of identifying customer opinion is 86%, and 84% respectively. The dataset is also tested by using Naïve Bayes, Decision Tree, Random Forest, and SVM. For Naïve Bayes obtains an accuracy of 75%, for Decision Tree obtains an accuracy of 71%, for Random Forest the accuracy is 82% and for SVM our accuracy result is 71%. Deep learning is used to obtain better business performance and also get the review from customers and also to predict the sentiment about customer review. Our algorithm works properly and gives better accuracy.
Power Generation, Transmission & Protection Systems of Mymensingh Power Station.
(East West University, 9/1/2012) Islam, Md. Tanvir; Kazi, Nayma Moustari; Rashid, Muhammed Injamanur
We completed our internship at Mymensingh Power Station (MPS) located at Shambhugonj, Mymensingh on the bank of the river Bhramaputra from 11th to 31th August, 2012 and this internship report is the result of those 16 days attachment with the MPS. During our internship period we gathered practical experiences on topics related to power generation, protection and power transmission which we have theoretically learned in courses. In this report we have focused on the processes which are used in MPS. Mymensingh Power Station (MPS) has combined cycle power plant which has been supplying 210 MW of electricity to the national grid. With the help of the plant engineers we observed the power plant, control room and protective equipments very closely and understood the functions and controlling systems of those equipments. We acquired knowledge about various types of transformers, isolators, circuit breakers, lightning arresters, current transformers, potential transformers, gas turbines, steam turbines, boilers, gas skid, gas booster and other equipments of the power station.