Imrus Salehin

Mr. Imrus Salehin

Information Convergence Engineering (AI), Pusan National University, Busan, Republic of Korea
+2
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
17 July 2023 in Electronics
Verified
Journal Article
Open access
PDF file
Imrus SalehinImrus Salehin
Imrus Salehin
Dae-Ki KangDae-Ki Kang
Dae-Ki Kang
Dropout is one of the most popular regularization methods in the scholarly domain for preventing a neural network model from overfitting in the training phase. Developing an effective dropout regularization technique that complies with the model architecture is crucial in deep learning-related tasks because various neural network architectures have been proposed, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), and they have exhibited reasonable performance in their specialized areas. In this paper, we provide a comprehensive and novel review of the state-of-the-art (SOTA) in dropout regularization. We explain various dropout methods, from standard random dropout to AutoDrop dropout (from the original to the advanced), and also discuss their performance and experimental capabilities. This paper provides a summary of the latest research on various dropout regularization techniques for achieving improved performance through “Internal Structure Changes”, “Data Augmentation”, and “Input Information”. We can see that proper regularization with respect to structural constraints of network architecture is a critical factor to facilitate overfitting avoidance. We discuss the strengths and limitations of the methods presented in this work, which can serve as valuable references for future research and the development of new approaches. We also pay attention to the scholarly domain in the discussion in order to meet the overwhelming increase of scientific research outcomes by providing an analysis of several important academic scholarly issues of neural networks.

18 October 2023 in Journal of Information and Intelligence
Verified
Journal Article
Open access
Imrus SalehinImrus Salehin
Imrus Salehin
Md. Shamiul IslamMd. Shamiul Islam
Md. Shamiul Islam
PSPritom Saha
Pritom Saha
SNS.M. Noman
S.M. Noman
ATAzra Tuni
Azra Tuni
ABAbu Baten
Abu Baten

26 December 2020
Verified
Conference Paper
Closed access
Imrus SalehinImrus Salehin
Imrus Salehin
ITIftakhar Mohammad Talha
Iftakhar Mohammad Talha
MHMehedi Hasan
Mehedi Hasan
SDSadia Tamim Dip
Sadia Tamim Dip
MSMohd. Saifuzzaman
Mohd. Saifuzzaman
NMNazmun Nessa Moon
Nazmun Nessa Moon
The most difficult task of meteorology is to predict rainfall. In our study, we proposed an amount of rainfall prediction model that can be easily determined using artificial intelligence and LSTM techniques. This is an advanced method to find out the rainfall. The deep learning approach is most valuable for this type of method implementation and its accuracy finds out. A long short-term memory algorithm is applied to memory sequence data measurement and calculate previous data very fast and create the best prediction. The people of this country are mostly dependent on agriculture so that this prediction system is very necessary. Timely rainfall assessment will increase crop yields and reduce costs in agriculture. Considering all these factors, we have created our model which will help us to determine the amount of rainfall. We have collected data from 6 regions to do this. To predict, we have taken 6 parameters (temperature, dew point, humidity, wind pressure, wind speed, and wind direction). After analyzing all our data, we got 76% accuracy in our work. We also focus on a vast dataset in long time weather for the better result.

1 November 2021 in Current Research in Behavioral Sciences
Verified
Journal Article
Open access
NMNazmun Nessa Moon
Nazmun Nessa Moon
ITIftakhar Mohammad Talha
Iftakhar Mohammad Talha
Imrus SalehinImrus Salehin
Imrus Salehin

1 January 2023 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
Imrus SalehinImrus Salehin
Imrus Salehin
SIShamiul Islam
Shamiul Islam
NANazrul Amin
Nazrul Amin
ABAbu Baten
Abu Baten
SNS M Noman
S M Noman
SYSerdar Yazmyradov
Serdar Yazmyradov
In the domain of modern deep learning and classification techniques, the convolutional neural network (CNN) stands out as a highly successful and preferred method for image classification in artificial intelligence. Especially in the medical field, CNN has proven to be an ideal approach for analyzing medical data and accurately identifying diseases. Over the recent years, CNN has demonstrated significant potential and success in various computer vision tasks, with medical image classification being one of the prominent applications. In our study, we introduce a novel custom CNN model called MedvCNN, designed for classifying different types of classes. We conduct experiments with various image sizes to explore their versatility. In addition, long short‐term memory (LSTM), a type of recurrent neural network (RNN), is incorporated into our approach. LSTM is specifically tailored to handle sequential data, making it ideal for time series analysis. However, its capabilities extend beyond time series data and are effectively applied to various sequential data types, including sequential vectors derived from image data. One of the key advantages of utilizing LSTM for image classification is its ability to effectively memorize and capture important features in the image data. This feature is particularly advantageous in medical image processing, where precise and accurate identification of key attributes is crucial for successful diagnosis and analysis. Furthermore, our experiments reveal that the hybrid custom LSTM model, MedvLSTM, a RNN algorithm, surpasses other methods in the domain of medical image classification. Our study places significant emphasis on attaining robust classification performance for medical image data through a sophisticated, parameter free approach, complemented by an ablation study, and comprehensive statistical analysis. This comprehensive analysis and evaluation allow us to gain a deeper understanding of the model’s effectiveness and its potential impact in the field of medical image analysis. We compare these two approaches to a baseline CNN architecture, aiming to streamline the classification process, reduce time consumption, and improve cost efficiency. Additionally, we present a real‐time web‐based AutoML framework along with a practical demonstration. Ultimately, our research provides a thorough investigation of the current state‐of‐the‐art in medical image analysis accuracy, focusing on the utilization of neural networks and LSTM.

1 November 2021 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
Imrus SalehinImrus Salehin
Imrus Salehin
SNS. M. Noman
S. M. Noman
BUBaki Ul-Islam
Baki Ul-Islam
ILIsrat Jahan Lopa
Israt Jahan Lopa
Prodipto Bishnu AngonProdipto Bishnu Angon
Prodipto Bishnu Angon
NMNazmun Nessa Moon
Nazmun Nessa Moon
The agricultural and technological combination is blessed for modern world life. Internet of things (IoT) is essential for comfort and development to our agriculture side. In our study, we detected the various pest using different types of sensors and this information has automatically sent to the farmer's mobile for the alert. All these sensors had a central database. Those sensors collect all the data and display the results compared to the central data. The High-image sensor will be able to detect all the rays emitted from the plant and another one is the gas sensor which is able to detect all the gases coming from the diseased plant. We mainly use sound sensor, MQ138, CMOSOV-7670, AMG-8833 for a better automation system. We test it with real-time environment conditions (40°C≤TA≤14°C). Crop pest detection automatic process is more efficient than the other detection process according to testing output. As a result, far-reaching changes in the agricultural sector are possible. To reduce extra cost and increasing more farming ability we need to IoT and Agriculture combinations more.