Dipta Gomes

Mr. Dipta Gomes

Computer Science, American International University-Bangladesh, Dhaka, Bangladesh
Assistant Professor, Dept of CS, American International Univ...

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2024
Verified
Book Chapter
Closed access
Dipta GomesDipta Gomes
Dipta Gomes
Intelligent tutoring systems offer personalized, adaptive learning experiences through digital platforms, contrasting with traditional methods. The integration of AI enhances ITS capabilities, providing dynamic adaptation, real-time feedback, and optimized outcomes. Ethical considerations, including privacy and bias mitigation, are paramount. Comparative analysis reveals AI's potential to reshape education, with future directions including sophisticated algorithms, diverse educational settings, and innovative pedagogical approaches. Practical implementation and evaluation will drive advancements, empowering students and educators in personalized learning journeys. The integration of AI in ITS represents a significant advancement, enabling systems to analyze vast amounts of data and tailor educational experiences to meet the unique needs and preferences of each learner. Through a comparative analysis, this chapter highlights the distinctive features and benefits of ITS compared to traditional learning methods.

10 January 2020
Verified
Conference Paper
Open access
Dipta GomesDipta Gomes
Dipta Gomes
ASA. F. M. Saifuddin Saif
A. F. M. Saifuddin Saif
DNDip Nandi
Dip Nandi
Underwater Object Detection had been one of the most challenging research fields of Computer Vision and Image Processing. Before Computer Vision techniques were used for underwater imaging, all the tasks associated with object detection had to be done manually by marine scientists making the task one of the most tedious and error prone. For this case, Underwater Autonomous Vehicles (UAV) has been developed to capture real time videos for specific object detection. Using different hardware improvements and using many varied forms of algorithms, classification of objects, mainly living objects had been carried with different AUVs and high-resolution cameras. Conventional object detection methods of Computer Vision fail to provide accurate detection results due to some challenges faced underwater. For such reasons, object detection underwater needs to be robust, real time and fast also being accurate, for which deep learning approaches are introduced. In this paper, all the works here all the trending underwater object detection techniques are discussed in details and a comprehensive comparative study is carried out.

1 April 2024 in International Journal of Education and Management Engineering
Verified
Journal Article
Open access
PDF file
Dipta GomesDipta Gomes
Dipta Gomes
With the advancements of Deep Learning technologies, its application has broadened into the fields of food classification from image recognition using Convolutional Neural Network, since food ingredient classification is a very important aspect for eating habit recognition and also reducing food waste. This research is an addition to the previous research with a clear illustration for deep learning approaches and how to maximize the classification accuracy to get a more profound framework for food ingredient classification. A fine-tuned model based on the Xception Convolutional Neural Network model trained with transfer learning has been proposed with a promising accuracy of 95.20% which indicates a greater scope of accurately classifying food objects with Xception deep learning model. Higher rate of accuracy opens the door of further research of identifying various new types of food objects through a robust approach. The main contribution in the research is better fine-tuning features of food classification. The dataset used in this research is the Food-101 Dataset containing 101 classes of food object images in the dataset.

20 December 2024
Verified
Conference Paper
Closed access
JIJahidul Islam
Jahidul Islam
SKSayem Kabir
Sayem Kabir
KKK. M Tahsin Kabir
K. M Tahsin Kabir
TSTasnim Sultana Sintheia
Tasnim Sultana Sintheia
KTKazi Tanvir
Kazi Tanvir
Dipta GomesDipta Gomes
Dipta Gomes
Watermelon, Citrullus lanatus, is an edible fruit of the flowering plant species of the Cucurbitaceae family. This South African fruit is highly cultivated worldwide with more than 1000 varieties. Like all fruits, watermelon also has some major diseases such as Downy Mildew, Anthracnose, and Mosaic Virus which are caused by Pseudoperonospora cubensis, Colletotrichum orbiculare, and Watermelon mosaic virus respectively. While watermelon exportation and cultivation helps with huge economic sectors, these diseases are continuing to hold the production back, making it difficult for the farmers as well. Traditional methods for detecting these diseases are expensive, time-consuming, and require years of experience, whereas Deep learning offers promising solutions for early and accurate detection, which are cheap, less time consuming, and standard maintained procedure. Proposed deep learning model is DenseEfficient which combines the strengths of DenseNet121 and EfficientnetV2B0. DenseNet121 achieves high accuracy and efficiency by connecting each layer to every other layer, with up to 121 or 201 layers, enhancing feature reuse. Additionally, it incorporates the stability and accuracy of EfficientnetV2B0’s progressive learning rate and advanced neural architecture search to enhance the image recognition tasks. Image Resize, Color inversion Image Augmentation and Outlier handling has been used as pre-processing techniques. In this study, the dataset had 1,115 images of five different classes of watermelon. Using the DenseEfficient model, the generated accuracy was 98.45% where the precision, recall, and F1-score were 0.9993, 0.9981, and 0.9991 respectively. These results inform that DenseEfficient can correctly categorize watermelon diseases and due to its quick performance in classification, it can be very useful tool for increasing watermelon cultivation.

8 June 2021 in International Journal of Image, Graphics and Signal Processing
Verified
Journal Article
Closed access
PDF file
Dipta GomesDipta Gomes
Dipta Gomes
ASA.F.M. Saifuddin Saif
A.F.M. Saifuddin Saif

1 January 2020
Verified
Conference Paper
Closed access
Dipta GomesDipta Gomes
Dipta Gomes
RNRashidul Hasan Nabil
Rashidul Hasan Nabil
KNKamruddin Nur
Kamruddin Nur
Prediction using different machine learning approaches have been applied in the last few decades in different areas and research fields. Waiting time is an undeniable fact for every queue and it is very important to develop a system that predicts its duration in real life with minimum error. In this paper we applied several machine learning algorithms and among them we chose Support Vector Regression (SVR) in a real-life Banking queue dataset that contains real-life queues of multiple Banks where we predicted waiting time for everyone in the queue. Moreover, we have compared the result of prediction using SVR with different classifications and clustering methods such as K-nearest-neighbor and K means Clustering. We have shown the feasibility of applying SVR in prediction of waiting time in banking queues of developing countries for everyone, which is applicable, and it performs well in queue analysis.