Md. Monirul Islam | Hankuk University of Foreign Studies (original) (raw)
Papers by Md. Monirul Islam
MDPI, 2023
Oral lesions are a prevalent manifestation of oral disease, and the timely identification of oral... more Oral lesions are a prevalent manifestation of oral disease, and the timely identification of oral lesions is imperative for effective intervention. Fortunately, deep learning algorithms have shown great potential for automated lesion detection. The primary aim of this study was to employ deep learning-based image classification algorithms to identify oral lesions. We used three deep learning models, namely VGG19, DeIT, and MobileNet, to assess the efficacy of various categorization methods. To evaluate the accuracy and reliability of the models, we employed a dataset consisting of oral pictures encompassing two distinct categories: benign and malignant lesions. The experimental findings indicate that VGG19 and MobileNet attained an almost perfect accuracy rate of 100%
, while DeIT achieved a slightly lower accuracy rate of 98.73%. The results of this study indicate that deep learning algorithms for picture classification demonstrate a high level of effectiveness in detecting oral lesions by achieving 100%
for VGG19 and MobileNet and 98.73%
for DeIT. Specifically, the VGG19 and MobileNet models exhibit notable suitability for this particular task.
Sensors, 2023
The Internet of Things (IoT) has positioned itself globally as a dominant force in the technology... more The Internet of Things (IoT) has positioned itself globally as a dominant force in the technology sector. IoT, a technology based on interconnected devices, has found applications in various research areas, including healthcare. Embedded devices and wearable technologies powered by IoT have been shown to be effective in patient monitoring and management systems, with a particular focus on pregnant women. This study provides a comprehensive systematic review of the literature on IoT architectures, systems, models and devices used to monitor and manage complications during pregnancy, postpartum and neonatal care. The study identifies emerging research trends and highlights existing research challenges and gaps, offering insights to improve the well-being of pregnant women at a critical moment in their lives. The literature review and discussions presented here serve as valuable resources for stakeholders in this field and pave the way for new and effective paradigms. Additionally, we outline a future research scope discussion for the benefit of researchers and healthcare professionals.
Microprocessors and Microsystems, 2023
Aquaculture involves cultivating various marine and freshwater aquatic creatures within regulated... more Aquaculture involves cultivating various marine and freshwater aquatic creatures within regulated environments. Monitoring the aquatic environmental conditions in real-time is crucial for successful fish farming.
The Internet of Things (IoT) offers significant potential for real-time monitoring, and this paper introduces
an IoT framework designed for efficient monitoring and effective control of various water-related aquatic
environmental parameters. The proposed system is implemented as an embedded system utilizing sensors
and an Arduino microcontroller. In cultivating pond water, diverse sensors such as pH, temperature, and
turbidity sensors are deployed, with each sensor connected to an Arduino Uno-based microcontroller board.
These sensors collect data from the water, which is then stored as a CSV file in an IoT cloud platform called
ThingSpeak through the Arduino microcontroller. To gather data for analysis, we conducted measurements
across five ponds, varying in size and environmental conditions. After getting the real-time data, we compared
our experimental results with the standard reference values. As a result, we could take the decision of whether
a pond is suitable for cultivating fish or not. After that, we labeled the data with 11 fish categories: Katla,
sing, prawn, shrimp, rui, tilapia, pangas, karpio, magur, silver carp, and koi. The data was analyzed using 10
machine learning (ML) algorithms, including J48, Random Forest, K Nearest Neighbors (K-NN), K*, Logistic
Model Tree (LMT), Reduced Error Pruning Tree (REPTree), Jumping Rule Inference with Pruned Search
(JRIP), Partial Decision Trees (PART), Decision Table, and Logit boost. After experimental analyses, it was
discovered that only three of the five ponds were ideal for fish farming, and those three ponds only met
the required standards for pH, Temperature, Turbidity, and Conductivity. Among the state-of-art machine
learning algorithms, Random Forest achieved the highest score of performance metrics as accuracy 94.42%,
kappa statistics 93.5%, and Avg. TP Rate 94.4%. In addition, we calculated the Biochemical Oxygen Demand
(BOD), Chemical Oxygen Demand (COD), and Dissolved Oxygen (DO) for one scenario. This study includes
prototype hardware details of the proposed IoT system.
Journal of Advanced Research in Applied Sciences and Engineering Technology, 2024
Rapid urbanization and industrialization have raised concerns about environmental quality and su... more Rapid urbanization and industrialization have raised concerns about environmental
quality and sustainability in recent years. The Internet of Things (IoT) has played an
important role in monitoring physical phenomena by generating data that can be sent
and preserved in the cloud. This work explores an IoT-based environmental monitoring
system's potential, using an Arduino-based device for real-time tracking of
environmental parameters including sound levels, humidity, dust concentration, total
volatile organic compounds (TVOC), carbon dioxide (CO2), and carbon monoxide (CO).
Real-time data are collected from various semi-residential and marketplace locations
named in Pach raster More, Tomaltola, DowamoyiMore, Fojdarimore, and station road
in Jamalpur district of Mymensingh Division, Bangladesh on non-holiday days,
providing a representative snapshot of typical environmental conditions. The collected
data is stored in a cloud server named firebase database. The implemented monitoring
system offers several key features including accuracy and reliability, real-time
monitoring data analytics alerts and notifications historical data as well as it can lead to
various benefits and impacts of Improved Air and Water Quality Healthier Urban
Environment (IAWUE) to enable local authorities and individuals to make educated
decisions for a healthier and more sustainable urban environment. Graphical
representations of the data revealed distinct patterns and trends, offering valuable
insights into air quality variations across different areas. Interestingly, the results
showed sound levels slightly below the standard range, indicating a relative control of
noise pollution in the sampled regions. The findings of the work will serve as a vital
resource for further research and guide policy-making for environmental improvement
and sustainable practices in urban settings.
Elsevier , 2024
Our emotional, psychological, and social well-being are all parts of our mental health, influenci... more Our emotional, psychological, and social well-being are all parts of our mental health, influencing our thoughts, emotions, and behaviors. Mental health also influences how we respond to stress, interact with others, and make good or bad decisions. There has been growing interest in the use of machine learning for the early detection of mental illness. This study reviews the machine learning models, algorithms, and applications for the early detection of mental disease, particularly emphasizing the data modalities. We further propose a comprehensive methodology for assessing mental health that synergistically combines social media monitoring, data analytics from wearable devices, verbal polls, and individualized support. We provide an overview of the field's current state, highlight the potential benefits and challenges of using machine learning in mental health care, and a new taxonomy of mental disorders issues based on five domains of data types. We review existing research on using machine learning to detect and treat mental illness and discuss the implications for future research. Finally, the value of this work lies in its potential to provide a fast and accurate method for predicting the mental health status of a person, which may assist in the diagnosis and treatment of mental illness.
MDPI, 2023
Cyber-Physical System (CPS) is a symbol of the fourth industrial revolution (4IR) by integrating ... more Cyber-Physical System (CPS) is a symbol of the fourth industrial revolution (4IR) by integrating physical and computational processes which can associate with humans in various ways. In short, the relationship between Cyber networks and the physical component is known as CPS, which is assisting to incorporate the world and influencing our ordinary life significantly. In terms of practical utilization of CPS interacting abundant difficulties. Currently, CPS is involved in modern society very vastly with many uptrend perspectives. All the new technologies by using CPS are accelerating our journey of innovation. In this paper, we have explained the research areas of 14 important domains of Cyber-Physical Systems (CPS) including aircraft transportation systems, battlefield surveillance, chemical production, energy, agriculture (food supply), healthcare, education, industrial automation, manufacturing, mobile devices, robotics, transportation, and vehicular. We also demonstrated the challenges and future direction of each paper of all domains. Almost all articles have limitations on security, data privacy, and safety. Several projects and new dimensions are mentioned where CPS is the key integration. Consequently, the researchers and academicians will be benefited to update the CPS workspace and it will help them with more research on a specific topic of CPS. 158 papers are studied in this survey as well as among these, 98 papers are directly studied with the 14 domains with challenges and future instruction which is the first survey paper as per the knowledge of authors.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Elsevier, 2024
Leukemia is a type of cancer characterized by the exponential growth of abnormal blood cells, whi... more Leukemia is a type of cancer characterized by the exponential growth of abnormal blood cells, which damages
white blood cells and disrupts the function of the human body’s bone marrow. It is very challenging to
classify because blood smear images are complicated, and there is a lot of variation between each class. Acute
Lymphoblastic Leukemia (B-ALL) is one of the subtypes of leukemia. It is a rapidly progressing cancer that
originates in B lymphocytes, characterized by the overproduction of immature B lymphoblasts. The purpose
of this work is to classify different types of B-ALL subtypes such as Benign, Malignant Early Pre-B, Malignant
Pre-B, and Malignant Pro-B from the peripheral blood smear images effectively. To accomplish this task, a novel
deep-learning technique based on a fine-tuned ResNet-50 model has been developed. Our fine-tuned ResNet50 model integrates several additional customized fully connected layers, including dense and dropout layers.
Various data augmentation techniques such as flipping, rotation, and zooming have been applied to mitigate the
risk of overfitting. In addition, a five-fold cross-validation technique has been employed to enhance the model’s
generalization. The performance of our proposed technique is compared with several other methods, including
VGG-16, DenseNet-121, and EfficientNetB0, as well as existing baselines, using different performance metrics.
Experimental results demonstrate the superiority of the fine-tuned ResNet-50 model, achieving the highest
accuracy and an F1-score of 99.38%. It also outperforms existing state-of-the-art approaches by a significant
margin. The proposed fine-tuned ReNet-50 model achieves such performance without the need for microscopic
image segmentation which indicates its potential utility in healthcare sectors in enhancing precise leukemia
diagnosis.
IAES International Journal of Artificial Intelligence (IJ-AI), 2021
In the real world, it is very difficult for fish farmers to select the perfect fish species for a... more In the real world, it is very difficult for fish farmers to select the perfect fish species for aquaculture in a specific aquatic environment. The main goal of this research is to build a machine learning that can predict the perfect fish species in an aquatic environment. In this paper, we have utilized a model using random forest (RF). To validate the model, we have used a dataset of aquatic environment for 11 different fishes. To predict the fish species, we utilized the different characteristics of aquatic environment including pH, temperature, and turbidity. As a performance metrics, we measured accuracy, true positive (TP) rate, and kappa statistics. Experimental results demonstrate that the proposed RF-based prediction model shows accuracy 88.48%, kappa statistic 87.11% and TP rate 88.5% for the tested dataset. In addition, we compare the proposed model with the state-of-art models J48, RF, k-nearest neighbor (k-NN), and classification and regression trees (CART). The propose...
Algorithms
Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, br... more Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, bridges, and highways, which in turn causes further damage and is thus regarded as a serious safety concern. Early detection of it can assist in preventing further damage and can enable safety in advance by avoiding any possible accident caused while using those infrastructures. Machine learning-based detection is gaining favor over time-consuming classical detection approaches that can only fulfill the objective of early detection. To identify concrete surface cracks from images, this research developed a transfer learning approach (TL) based on Convolutional Neural Networks (CNN). This work employs the transfer learning strategy by leveraging four existing deep learning (DL) models named VGG16, ResNet18, DenseNet161, and AlexNet with pre-trained (trained on ImageNet) weights. To validate the performance of each model, four performance indicators are used: accuracy, recall, precision, and...
Elsevier, 2022
COVID-19 cases are putting pressure on healthcare systems all around the world. Due to the lack o... more COVID-19 cases are putting pressure on healthcare systems all around the world. Due to the lack of available testing kits, it is impractical for screening every patient with a respiratory ailment using traditional methods (RT-PCR). In addition, the tests have a high turnaround time and low sensitivity. Detecting suspected COVID-19 infections from the chest X-ray might help isolate high-risk people before the RT-PCR test. Most healthcare systems already have X-ray equipment, and because most current X-ray systems have already been computerized, there is no need to transfer the samples. The use of a chest X-ray to prioritize the selection of patients for subsequent RT-PCR testing is the motivation of this work. Transfer learning (TL) with fine-tuning on deep convolutional neural network-based ResNet50 model has been proposed in this work to classify COVID-19 patients from the COVID-19 Radiography Database. Ten distinct pre-trained weights, trained on varieties of large-scale datasets using various approaches such as supervised learning, self-supervised learning, and others, have been utilized in this work. Our proposed 2021_ _ _1 model, pre-trained on the iNat2021 Mini dataset using the SwAV algorithm, outperforms the other ResNet50 TL models. For COVID instances in the two-class (Covid and Normal) classification, our work achieved 99.17% validation accuracy, 99.95% train accuracy, 99.31% precision, 99.03% sensitivity, and 99.17% F1-score. Some domain-adapted (_ ℎ − 14) and in-domain (ChexPert, ChestX-ray14) models looked promising in medical image classification by scoring significantly higher than other models.
MDPI, 2022
Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, br... more Cracks in concrete cause initial structural damage to civil infrastructures such as buildings,
bridges, and highways, which in turn causes further damage and is thus regarded as a serious safety
concern. Early detection of it can assist in preventing further damage and can enable safety in advance
by avoiding any possible accident caused while using those infrastructures. Machine learning-based
detection is gaining favor over time-consuming classical detection approaches that can only fulfill the
objective of early detection. To identify concrete surface cracks from images, this research developed a
transfer learning approach (TL) based on Convolutional Neural Networks (CNN). This work employs
the transfer learning strategy by leveraging four existing deep learning (DL) models named VGG16,
ResNet18, DenseNet161, and AlexNet with pre-trained (trained on ImageNet) weights. To validate
the performance of each model, four performance indicators are used: accuracy, recall, precision, and
F1-score. Using the publicly available CCIC dataset, the suggested technique on AlexNet outperforms
existing models with a testing accuracy of 99.90%, precision of 99.92%, recall of 99.80%, and F1-score
of 99.86% for crack class. Our approach is further validated by using an external dataset, BWCI,
available on Kaggle. Using BWCI, models VGG16, ResNet18, DenseNet161, and AlexNet achieved the
accuracy of 99.90%, 99.60%, 99.80%, and 99.90% respectively. This proposed transfer learning-based
method, which is based on the CNN method, is demonstrated to be more effective at detecting cracks
in concrete structures and is also applicable to other detection tasks.
IEEE, 2020
This research attempts to forecast the yearly electricity demand of Bangladesh using a multivaria... more This research attempts to forecast the yearly electricity demand of Bangladesh using a multivariate time series model. As the univariate time series cannot include the external factors, so we introduced two exogenous variables including Population and GDP per capita as exogenous variables to get better performance. The model has been developed on the yearly data collected from1994 to 2018. For the tested dataset, the Autoregressive Integrated Moving Average with Exogenous ARIMAX (0, 1, 1) model shows comparatively better performance than the state-ofart model with the lowest Akaike Information Criterion (AIC) values. The model has validated using the data from 2014 to 2018. The model shows Mean Absolute Error (MAE) 591.07, Mean Absolute Percent Error (MAPE) 5.43 and Root Mean Square (RMS) 782.28. Using this model, we forecast the energy demand for the period 2019 to 2021 and we found that the demand for electricity will be increased for each of every year.
J Multidisciplinary Scientific Journal, 2021
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
2021 International Conference on Computer Communication and Informatics (ICCCI -2021), Jan. 27-29, 2021, Coimbatore, INDIA, 2021
To form a WSN properly is very important with the desired throughput and lifetime. Properly formi... more To form a WSN properly is very important with the desired throughput and lifetime. Properly forming of WSN with desired output is the key of successful operation of WSN. To main factor (throughput and lifetime) prediction based on various inputs can help the management to design the network. This paper introduced a new approach to predict class based on throughput and lifetime of LEACH based clustering protocol. The various supervised machine learning algorithm is used to predict classification and compare with them. The simulation results show that logistic regression can predict with 80% accuracy.
In this age of world, everything is going to fourth revolution of industries. According to this, ... more In this age of world, everything is going to fourth revolution of industries. According to this, Bangladesh is going to be prompt in every sector. In this paper, we have proposed a system of cultivating fish farming using IoT devices. After simulating design, we implement it by hardware. Here we use water temperature, turbidity, PH, Water Level, CO3 gas. The objective of this research is to design and develop a real-time smart-based water temperature, PH and turbidity monitoring system. The system implementation resulted in a monitoring system that collects the current water temperature, PH, turbidity from the core-controller in real-time. Also, the system provides and displays information that includes normal range, maximum, minimum, average and findings of the collected data which figured by thing speak IoT analytics platform. It provides decision support to assist and guide fisher folks in avoiding distress to grow fish and obtaining the optimum water monitoring data such as temperature, ph and turbidity range.
Springer, 2021
This paper presents an Internet of Things (IoT) system using K Nearest Neighbors Machine Learning... more This paper presents an Internet of Things (IoT) system using K Nearest Neighbors Machine Learning Model for selection fish species by analyzing a fish data set. For storing real time data from used sensors, we used a cloud server. We make a dynamic website for giving information of various fish species living in an aquatic environment. This website is connected with cloud server; anyone can easily watch it on a web application. Therefore, they can easily decide what should follow the next step, which kinds of fish are surviving in the water. For constructing the proposed IoT system, we utilized 5 sensors including mq7, ph, temperature, ultrasonic and turbidity. These sensors are connected with an Arduino Uno. The real time data of water environment using sensor is obtained in the cloud server as a csv format file. In this study, we have utilized a server of thingspeak. The end user of fish farming can monitor easily remotely using the proposed IoT system.
IAES International Journal of Artificial Intelligence (IJ-AI), 2021
In the real world, it is very difficult for fish farmers to select the perfect fish species for a... more In the real world, it is very difficult for fish farmers to select the perfect fish species for aquaculture in a specific aquatic environment. The main goal of this research is to build a machine learning that can predict the perfect fish species in an aquatic environment. In this paper, we have utilized a model using random forest. To validate the model, we have used a dataset of aquatic environments for 11 different fishes. To predict the fish species, we utilized the different characteristics of the aquatic environment including pH, temperature, and turbidity. As for performance metrics, we measured accuracy, TP rate, and kappa statistics. Experimental results demonstrate that the proposed random forest-based prediction model shows an accuracy of 88.48%, kappa statistic 87.11%, and TP rate 88.5% for the tested dataset. In addition, we compare the proposed model with the state-of-art models-J48, random forest, KNN, classification, and regression (CART). The proposed model outperforms the existing models by exhibiting a higher accuracy score, TP rate, and kappa statistics.
International Journal of Electrical and Computer Engineering (IJECE), 2022
Aquaculture is the farming of aquatic organisms in natural, controlled marine and freshwater envi... more Aquaculture is the farming of aquatic organisms in natural, controlled marine and freshwater environments. The real-time monitoring of aquatic environmental parameters is very important in fish farming. Internet of things (IoT) can play a vital role in the real-time monitoring. This paper presents an IoT framework for the efficient monitoring and effective control of different aquatic environmental parameters related to the water. The proposed system is implemented as an embedded system using sensors and an Arduino. Different sensors including pH, temperature, and turbidity, ultrasonic are placed in cultivating pond water and each of them is connected to a common microcontroller board built on an Arduino Uno. The sensors read the data from the water and store it as a comma-separated values (CSV) file in an IoT cloud named ThingSpeak through the Arduino microcontroller. To validate the experiment, we collected data from 5 ponds of various sizes and environments. After experimental evaluation, it was observed among 5 ponds, only three ponds were perfect for fish farming, where these 3 ponds only satisfied the standard reference values of pH (6.5-8.5), temperature (16-24 °C), turbidity (below 10 ntu), conductivity (970-1825 μS/cm), and depth (1-4) meter. At the end of this paper, a complete hardware implementation of this proposed IoT framework for a real-time aquatic environment monitoring system is presented.
MDPI, 2023
Oral lesions are a prevalent manifestation of oral disease, and the timely identification of oral... more Oral lesions are a prevalent manifestation of oral disease, and the timely identification of oral lesions is imperative for effective intervention. Fortunately, deep learning algorithms have shown great potential for automated lesion detection. The primary aim of this study was to employ deep learning-based image classification algorithms to identify oral lesions. We used three deep learning models, namely VGG19, DeIT, and MobileNet, to assess the efficacy of various categorization methods. To evaluate the accuracy and reliability of the models, we employed a dataset consisting of oral pictures encompassing two distinct categories: benign and malignant lesions. The experimental findings indicate that VGG19 and MobileNet attained an almost perfect accuracy rate of 100%
, while DeIT achieved a slightly lower accuracy rate of 98.73%. The results of this study indicate that deep learning algorithms for picture classification demonstrate a high level of effectiveness in detecting oral lesions by achieving 100%
for VGG19 and MobileNet and 98.73%
for DeIT. Specifically, the VGG19 and MobileNet models exhibit notable suitability for this particular task.
Sensors, 2023
The Internet of Things (IoT) has positioned itself globally as a dominant force in the technology... more The Internet of Things (IoT) has positioned itself globally as a dominant force in the technology sector. IoT, a technology based on interconnected devices, has found applications in various research areas, including healthcare. Embedded devices and wearable technologies powered by IoT have been shown to be effective in patient monitoring and management systems, with a particular focus on pregnant women. This study provides a comprehensive systematic review of the literature on IoT architectures, systems, models and devices used to monitor and manage complications during pregnancy, postpartum and neonatal care. The study identifies emerging research trends and highlights existing research challenges and gaps, offering insights to improve the well-being of pregnant women at a critical moment in their lives. The literature review and discussions presented here serve as valuable resources for stakeholders in this field and pave the way for new and effective paradigms. Additionally, we outline a future research scope discussion for the benefit of researchers and healthcare professionals.
Microprocessors and Microsystems, 2023
Aquaculture involves cultivating various marine and freshwater aquatic creatures within regulated... more Aquaculture involves cultivating various marine and freshwater aquatic creatures within regulated environments. Monitoring the aquatic environmental conditions in real-time is crucial for successful fish farming.
The Internet of Things (IoT) offers significant potential for real-time monitoring, and this paper introduces
an IoT framework designed for efficient monitoring and effective control of various water-related aquatic
environmental parameters. The proposed system is implemented as an embedded system utilizing sensors
and an Arduino microcontroller. In cultivating pond water, diverse sensors such as pH, temperature, and
turbidity sensors are deployed, with each sensor connected to an Arduino Uno-based microcontroller board.
These sensors collect data from the water, which is then stored as a CSV file in an IoT cloud platform called
ThingSpeak through the Arduino microcontroller. To gather data for analysis, we conducted measurements
across five ponds, varying in size and environmental conditions. After getting the real-time data, we compared
our experimental results with the standard reference values. As a result, we could take the decision of whether
a pond is suitable for cultivating fish or not. After that, we labeled the data with 11 fish categories: Katla,
sing, prawn, shrimp, rui, tilapia, pangas, karpio, magur, silver carp, and koi. The data was analyzed using 10
machine learning (ML) algorithms, including J48, Random Forest, K Nearest Neighbors (K-NN), K*, Logistic
Model Tree (LMT), Reduced Error Pruning Tree (REPTree), Jumping Rule Inference with Pruned Search
(JRIP), Partial Decision Trees (PART), Decision Table, and Logit boost. After experimental analyses, it was
discovered that only three of the five ponds were ideal for fish farming, and those three ponds only met
the required standards for pH, Temperature, Turbidity, and Conductivity. Among the state-of-art machine
learning algorithms, Random Forest achieved the highest score of performance metrics as accuracy 94.42%,
kappa statistics 93.5%, and Avg. TP Rate 94.4%. In addition, we calculated the Biochemical Oxygen Demand
(BOD), Chemical Oxygen Demand (COD), and Dissolved Oxygen (DO) for one scenario. This study includes
prototype hardware details of the proposed IoT system.
Journal of Advanced Research in Applied Sciences and Engineering Technology, 2024
Rapid urbanization and industrialization have raised concerns about environmental quality and su... more Rapid urbanization and industrialization have raised concerns about environmental
quality and sustainability in recent years. The Internet of Things (IoT) has played an
important role in monitoring physical phenomena by generating data that can be sent
and preserved in the cloud. This work explores an IoT-based environmental monitoring
system's potential, using an Arduino-based device for real-time tracking of
environmental parameters including sound levels, humidity, dust concentration, total
volatile organic compounds (TVOC), carbon dioxide (CO2), and carbon monoxide (CO).
Real-time data are collected from various semi-residential and marketplace locations
named in Pach raster More, Tomaltola, DowamoyiMore, Fojdarimore, and station road
in Jamalpur district of Mymensingh Division, Bangladesh on non-holiday days,
providing a representative snapshot of typical environmental conditions. The collected
data is stored in a cloud server named firebase database. The implemented monitoring
system offers several key features including accuracy and reliability, real-time
monitoring data analytics alerts and notifications historical data as well as it can lead to
various benefits and impacts of Improved Air and Water Quality Healthier Urban
Environment (IAWUE) to enable local authorities and individuals to make educated
decisions for a healthier and more sustainable urban environment. Graphical
representations of the data revealed distinct patterns and trends, offering valuable
insights into air quality variations across different areas. Interestingly, the results
showed sound levels slightly below the standard range, indicating a relative control of
noise pollution in the sampled regions. The findings of the work will serve as a vital
resource for further research and guide policy-making for environmental improvement
and sustainable practices in urban settings.
Elsevier , 2024
Our emotional, psychological, and social well-being are all parts of our mental health, influenci... more Our emotional, psychological, and social well-being are all parts of our mental health, influencing our thoughts, emotions, and behaviors. Mental health also influences how we respond to stress, interact with others, and make good or bad decisions. There has been growing interest in the use of machine learning for the early detection of mental illness. This study reviews the machine learning models, algorithms, and applications for the early detection of mental disease, particularly emphasizing the data modalities. We further propose a comprehensive methodology for assessing mental health that synergistically combines social media monitoring, data analytics from wearable devices, verbal polls, and individualized support. We provide an overview of the field's current state, highlight the potential benefits and challenges of using machine learning in mental health care, and a new taxonomy of mental disorders issues based on five domains of data types. We review existing research on using machine learning to detect and treat mental illness and discuss the implications for future research. Finally, the value of this work lies in its potential to provide a fast and accurate method for predicting the mental health status of a person, which may assist in the diagnosis and treatment of mental illness.
MDPI, 2023
Cyber-Physical System (CPS) is a symbol of the fourth industrial revolution (4IR) by integrating ... more Cyber-Physical System (CPS) is a symbol of the fourth industrial revolution (4IR) by integrating physical and computational processes which can associate with humans in various ways. In short, the relationship between Cyber networks and the physical component is known as CPS, which is assisting to incorporate the world and influencing our ordinary life significantly. In terms of practical utilization of CPS interacting abundant difficulties. Currently, CPS is involved in modern society very vastly with many uptrend perspectives. All the new technologies by using CPS are accelerating our journey of innovation. In this paper, we have explained the research areas of 14 important domains of Cyber-Physical Systems (CPS) including aircraft transportation systems, battlefield surveillance, chemical production, energy, agriculture (food supply), healthcare, education, industrial automation, manufacturing, mobile devices, robotics, transportation, and vehicular. We also demonstrated the challenges and future direction of each paper of all domains. Almost all articles have limitations on security, data privacy, and safety. Several projects and new dimensions are mentioned where CPS is the key integration. Consequently, the researchers and academicians will be benefited to update the CPS workspace and it will help them with more research on a specific topic of CPS. 158 papers are studied in this survey as well as among these, 98 papers are directly studied with the 14 domains with challenges and future instruction which is the first survey paper as per the knowledge of authors.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Elsevier, 2024
Leukemia is a type of cancer characterized by the exponential growth of abnormal blood cells, whi... more Leukemia is a type of cancer characterized by the exponential growth of abnormal blood cells, which damages
white blood cells and disrupts the function of the human body’s bone marrow. It is very challenging to
classify because blood smear images are complicated, and there is a lot of variation between each class. Acute
Lymphoblastic Leukemia (B-ALL) is one of the subtypes of leukemia. It is a rapidly progressing cancer that
originates in B lymphocytes, characterized by the overproduction of immature B lymphoblasts. The purpose
of this work is to classify different types of B-ALL subtypes such as Benign, Malignant Early Pre-B, Malignant
Pre-B, and Malignant Pro-B from the peripheral blood smear images effectively. To accomplish this task, a novel
deep-learning technique based on a fine-tuned ResNet-50 model has been developed. Our fine-tuned ResNet50 model integrates several additional customized fully connected layers, including dense and dropout layers.
Various data augmentation techniques such as flipping, rotation, and zooming have been applied to mitigate the
risk of overfitting. In addition, a five-fold cross-validation technique has been employed to enhance the model’s
generalization. The performance of our proposed technique is compared with several other methods, including
VGG-16, DenseNet-121, and EfficientNetB0, as well as existing baselines, using different performance metrics.
Experimental results demonstrate the superiority of the fine-tuned ResNet-50 model, achieving the highest
accuracy and an F1-score of 99.38%. It also outperforms existing state-of-the-art approaches by a significant
margin. The proposed fine-tuned ReNet-50 model achieves such performance without the need for microscopic
image segmentation which indicates its potential utility in healthcare sectors in enhancing precise leukemia
diagnosis.
IAES International Journal of Artificial Intelligence (IJ-AI), 2021
In the real world, it is very difficult for fish farmers to select the perfect fish species for a... more In the real world, it is very difficult for fish farmers to select the perfect fish species for aquaculture in a specific aquatic environment. The main goal of this research is to build a machine learning that can predict the perfect fish species in an aquatic environment. In this paper, we have utilized a model using random forest (RF). To validate the model, we have used a dataset of aquatic environment for 11 different fishes. To predict the fish species, we utilized the different characteristics of aquatic environment including pH, temperature, and turbidity. As a performance metrics, we measured accuracy, true positive (TP) rate, and kappa statistics. Experimental results demonstrate that the proposed RF-based prediction model shows accuracy 88.48%, kappa statistic 87.11% and TP rate 88.5% for the tested dataset. In addition, we compare the proposed model with the state-of-art models J48, RF, k-nearest neighbor (k-NN), and classification and regression trees (CART). The propose...
Algorithms
Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, br... more Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, bridges, and highways, which in turn causes further damage and is thus regarded as a serious safety concern. Early detection of it can assist in preventing further damage and can enable safety in advance by avoiding any possible accident caused while using those infrastructures. Machine learning-based detection is gaining favor over time-consuming classical detection approaches that can only fulfill the objective of early detection. To identify concrete surface cracks from images, this research developed a transfer learning approach (TL) based on Convolutional Neural Networks (CNN). This work employs the transfer learning strategy by leveraging four existing deep learning (DL) models named VGG16, ResNet18, DenseNet161, and AlexNet with pre-trained (trained on ImageNet) weights. To validate the performance of each model, four performance indicators are used: accuracy, recall, precision, and...
Elsevier, 2022
COVID-19 cases are putting pressure on healthcare systems all around the world. Due to the lack o... more COVID-19 cases are putting pressure on healthcare systems all around the world. Due to the lack of available testing kits, it is impractical for screening every patient with a respiratory ailment using traditional methods (RT-PCR). In addition, the tests have a high turnaround time and low sensitivity. Detecting suspected COVID-19 infections from the chest X-ray might help isolate high-risk people before the RT-PCR test. Most healthcare systems already have X-ray equipment, and because most current X-ray systems have already been computerized, there is no need to transfer the samples. The use of a chest X-ray to prioritize the selection of patients for subsequent RT-PCR testing is the motivation of this work. Transfer learning (TL) with fine-tuning on deep convolutional neural network-based ResNet50 model has been proposed in this work to classify COVID-19 patients from the COVID-19 Radiography Database. Ten distinct pre-trained weights, trained on varieties of large-scale datasets using various approaches such as supervised learning, self-supervised learning, and others, have been utilized in this work. Our proposed 2021_ _ _1 model, pre-trained on the iNat2021 Mini dataset using the SwAV algorithm, outperforms the other ResNet50 TL models. For COVID instances in the two-class (Covid and Normal) classification, our work achieved 99.17% validation accuracy, 99.95% train accuracy, 99.31% precision, 99.03% sensitivity, and 99.17% F1-score. Some domain-adapted (_ ℎ − 14) and in-domain (ChexPert, ChestX-ray14) models looked promising in medical image classification by scoring significantly higher than other models.
MDPI, 2022
Cracks in concrete cause initial structural damage to civil infrastructures such as buildings, br... more Cracks in concrete cause initial structural damage to civil infrastructures such as buildings,
bridges, and highways, which in turn causes further damage and is thus regarded as a serious safety
concern. Early detection of it can assist in preventing further damage and can enable safety in advance
by avoiding any possible accident caused while using those infrastructures. Machine learning-based
detection is gaining favor over time-consuming classical detection approaches that can only fulfill the
objective of early detection. To identify concrete surface cracks from images, this research developed a
transfer learning approach (TL) based on Convolutional Neural Networks (CNN). This work employs
the transfer learning strategy by leveraging four existing deep learning (DL) models named VGG16,
ResNet18, DenseNet161, and AlexNet with pre-trained (trained on ImageNet) weights. To validate
the performance of each model, four performance indicators are used: accuracy, recall, precision, and
F1-score. Using the publicly available CCIC dataset, the suggested technique on AlexNet outperforms
existing models with a testing accuracy of 99.90%, precision of 99.92%, recall of 99.80%, and F1-score
of 99.86% for crack class. Our approach is further validated by using an external dataset, BWCI,
available on Kaggle. Using BWCI, models VGG16, ResNet18, DenseNet161, and AlexNet achieved the
accuracy of 99.90%, 99.60%, 99.80%, and 99.90% respectively. This proposed transfer learning-based
method, which is based on the CNN method, is demonstrated to be more effective at detecting cracks
in concrete structures and is also applicable to other detection tasks.
IEEE, 2020
This research attempts to forecast the yearly electricity demand of Bangladesh using a multivaria... more This research attempts to forecast the yearly electricity demand of Bangladesh using a multivariate time series model. As the univariate time series cannot include the external factors, so we introduced two exogenous variables including Population and GDP per capita as exogenous variables to get better performance. The model has been developed on the yearly data collected from1994 to 2018. For the tested dataset, the Autoregressive Integrated Moving Average with Exogenous ARIMAX (0, 1, 1) model shows comparatively better performance than the state-ofart model with the lowest Akaike Information Criterion (AIC) values. The model has validated using the data from 2014 to 2018. The model shows Mean Absolute Error (MAE) 591.07, Mean Absolute Percent Error (MAPE) 5.43 and Root Mean Square (RMS) 782.28. Using this model, we forecast the energy demand for the period 2019 to 2021 and we found that the demand for electricity will be increased for each of every year.
J Multidisciplinary Scientific Journal, 2021
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
2021 International Conference on Computer Communication and Informatics (ICCCI -2021), Jan. 27-29, 2021, Coimbatore, INDIA, 2021
To form a WSN properly is very important with the desired throughput and lifetime. Properly formi... more To form a WSN properly is very important with the desired throughput and lifetime. Properly forming of WSN with desired output is the key of successful operation of WSN. To main factor (throughput and lifetime) prediction based on various inputs can help the management to design the network. This paper introduced a new approach to predict class based on throughput and lifetime of LEACH based clustering protocol. The various supervised machine learning algorithm is used to predict classification and compare with them. The simulation results show that logistic regression can predict with 80% accuracy.
In this age of world, everything is going to fourth revolution of industries. According to this, ... more In this age of world, everything is going to fourth revolution of industries. According to this, Bangladesh is going to be prompt in every sector. In this paper, we have proposed a system of cultivating fish farming using IoT devices. After simulating design, we implement it by hardware. Here we use water temperature, turbidity, PH, Water Level, CO3 gas. The objective of this research is to design and develop a real-time smart-based water temperature, PH and turbidity monitoring system. The system implementation resulted in a monitoring system that collects the current water temperature, PH, turbidity from the core-controller in real-time. Also, the system provides and displays information that includes normal range, maximum, minimum, average and findings of the collected data which figured by thing speak IoT analytics platform. It provides decision support to assist and guide fisher folks in avoiding distress to grow fish and obtaining the optimum water monitoring data such as temperature, ph and turbidity range.
Springer, 2021
This paper presents an Internet of Things (IoT) system using K Nearest Neighbors Machine Learning... more This paper presents an Internet of Things (IoT) system using K Nearest Neighbors Machine Learning Model for selection fish species by analyzing a fish data set. For storing real time data from used sensors, we used a cloud server. We make a dynamic website for giving information of various fish species living in an aquatic environment. This website is connected with cloud server; anyone can easily watch it on a web application. Therefore, they can easily decide what should follow the next step, which kinds of fish are surviving in the water. For constructing the proposed IoT system, we utilized 5 sensors including mq7, ph, temperature, ultrasonic and turbidity. These sensors are connected with an Arduino Uno. The real time data of water environment using sensor is obtained in the cloud server as a csv format file. In this study, we have utilized a server of thingspeak. The end user of fish farming can monitor easily remotely using the proposed IoT system.
IAES International Journal of Artificial Intelligence (IJ-AI), 2021
In the real world, it is very difficult for fish farmers to select the perfect fish species for a... more In the real world, it is very difficult for fish farmers to select the perfect fish species for aquaculture in a specific aquatic environment. The main goal of this research is to build a machine learning that can predict the perfect fish species in an aquatic environment. In this paper, we have utilized a model using random forest. To validate the model, we have used a dataset of aquatic environments for 11 different fishes. To predict the fish species, we utilized the different characteristics of the aquatic environment including pH, temperature, and turbidity. As for performance metrics, we measured accuracy, TP rate, and kappa statistics. Experimental results demonstrate that the proposed random forest-based prediction model shows an accuracy of 88.48%, kappa statistic 87.11%, and TP rate 88.5% for the tested dataset. In addition, we compare the proposed model with the state-of-art models-J48, random forest, KNN, classification, and regression (CART). The proposed model outperforms the existing models by exhibiting a higher accuracy score, TP rate, and kappa statistics.
International Journal of Electrical and Computer Engineering (IJECE), 2022
Aquaculture is the farming of aquatic organisms in natural, controlled marine and freshwater envi... more Aquaculture is the farming of aquatic organisms in natural, controlled marine and freshwater environments. The real-time monitoring of aquatic environmental parameters is very important in fish farming. Internet of things (IoT) can play a vital role in the real-time monitoring. This paper presents an IoT framework for the efficient monitoring and effective control of different aquatic environmental parameters related to the water. The proposed system is implemented as an embedded system using sensors and an Arduino. Different sensors including pH, temperature, and turbidity, ultrasonic are placed in cultivating pond water and each of them is connected to a common microcontroller board built on an Arduino Uno. The sensors read the data from the water and store it as a comma-separated values (CSV) file in an IoT cloud named ThingSpeak through the Arduino microcontroller. To validate the experiment, we collected data from 5 ponds of various sizes and environments. After experimental evaluation, it was observed among 5 ponds, only three ponds were perfect for fish farming, where these 3 ponds only satisfied the standard reference values of pH (6.5-8.5), temperature (16-24 °C), turbidity (below 10 ntu), conductivity (970-1825 μS/cm), and depth (1-4) meter. At the end of this paper, a complete hardware implementation of this proposed IoT framework for a real-time aquatic environment monitoring system is presented.