Browsing by Author "Khatun, Tania"

Now showing 1 - 14 of 14

A New Approach to Hiding Data in the Images Using Steganography Techniques Based on AES and RC5 Algorithm Cryptosystem
(IEEE, 2020-09) Hossen, Md. Sagar; Islam, Md. Ashiqul; Khatun, Tania; Hossain, Shahed; Rahman, Md. Mahfujur
In the new era of modern science and technology is developing day by day, data confidentiality is risky, all over the world and it increases rapidly. In this paper, a new approach to hiding the data using steganography techniques is proposed based on AES and RC5 algorithm cryptosystem. Steganography is the beauty of hiding secret data behind the digital images, videos, audios and text to cover the secret communication. A cryptosystem is the process which given our method more perfection. The visual quality of the cover image nice, no one can think about it how confidential data are transmitted using this method. This proposed method and algorithm capacity is highly flexible than other published algorithm. The AES and RC5 algorithm had no complexity and it looks like very well to hide the confidential data.
An Automated Convolutional Neural Network Based Approach for Paddy Leaf Disease Detection
(International Journal of Advanced Computer Science and Applications(IJACSA), 2021) Islam, Md. Ashiqul; Shuvo, Md. Nymur Rahman; Shamsojjaman, Muhammad; Hasan, Shazid; Hossain, Md. Shahadat; Khatun, Tania
Bangladesh and India are significant paddy-cultivation countries in the globe. Paddy is the key producing crop in Bangladesh. In the last 11 years, the part of agriculture in Bangladesh's Gross Domestic Product (GDP) was contributing about 15.08 percent. But unfortunately, the farmers who are working so hard to grow this crop, have to face huge losses because of crop damages caused by various diseases of paddy. There are approximately more than 30 diseases of paddy leaf and among them, about 7-8 diseases are quite common in Bangladesh. Paddy leaf diseases like Brown Spot Disease, Blast Disease, Bacterial Leaf Blight, etc. are very well known and most affecting one among different paddy leaf diseases. These diseases are hampering the growth and productivity of paddy plants which can lead to great ecological and economical losses. If these diseases can be detected at an early stage with great accuracy and in a short time, then the damages to the crops can be greatly reduced and the losses of the farmers can be prevented. This paper has worked on 4 types of diseases and one healthy leaf class of the paddy. The main goal of this paper is to provide the best results for paddy leaf disease detection through an automated detection approach with the deep learning CNN models that can achieve the highest accuracy instead of the traditional lengthy manual disease detection process where the accuracy is also greatly questionable. It has analyzed four models such as VGG-19, Inception-Resnet-V2, ResNet-101, Xception, and achieved better accuracy from Inception-ResNet-V2 is 92.68%.
An Automated Convolutional Neural Network Based Approach for Paddy Leaf Disease Detection
(Scopus, 2021) Islam, Md. Ashiqul; Shuvo, Md. Nymur Rahman; Shamsojjaman, Muhammad; Hasan, Shazid; Hossain, Md. Shahadat; Khatun, Tania
Abstract: Bangladesh and India are significant paddy-cultivation countries in the globe. Paddy is the key producing crop in Bangladesh. In the last 11 years, the part of agriculture in Bangladesh's Gross Domestic Product (GDP) was contributing about 15.08 percent. But unfortunately, the farmers who are working so hard to grow this crop, have to face huge losses because of crop damages caused by various diseases of paddy. There are approximately more than 30 diseases of paddy leaf and among them, about 7-8 diseases are quite common in Bangladesh. Paddy leaf diseases like Brown Spot Disease, Blast Disease, Bacterial Leaf Blight, etc. are very well known and most affecting one among different paddy leaf diseases. These diseases are hampering the growth and productivity of paddy plants which can lead to great ecological and economical losses. If these diseases can be detected at an early stage with great accuracy and in a short time, then the damages to the crops can be greatly reduced and the losses of the farmers can be prevented. This paper has worked on 4 types of diseases and one healthy leaf class of the paddy. The main goal of this paper is to provide the best results for paddy leaf disease detection through an automated detection approach with the deep learning CNN models that can achieve the highest accuracy instead of the traditional lengthy manual disease detection process where the accuracy is also greatly questionable. It has analyzed four models such as VGG-19, Inception-Resnet-V2, ResNet-101, Xception, and achieved better accuracy from Inception-ResNet-V2 is 92.68%.
An Extensive Real-World in Field Tomato Image Dataset Involving Maturity Classification and Recognition of Fresh and Defect Tomatoes
(Elsevier, 2023-10-15) Khatun, Tania; Razzak, Abdur; Md. Shofiul Islam, Md. Shofiul; Uddin, Mohammad Shorif
Tomato, a fruiting plant species within the Solanaceae family, is a widely used ingredient in culinary dishes due to its sweet and acidic flavor profile, as well as its rich nutritional content. Recognized for its potential health benefits, including reducing the risk of coronary artery disease and specific types of cancer, tomatoes have become a staple in global cuisine. Traditional methods for tomato maturity assessment, harvesting, quality grading, and packaging are often labor-intensive and economically inefficient. This paper introduces an extensive dataset of high-resolution tomato images collected over an eight-month period from the demonstration fields of Sher-E-Bangla Agricultural University in Dhaka, Bangladesh, in collaboration with plant breeding experts of the same university. The dataset was meticulously curated to ensure precision and consistency, encompassing various stages of tomato maturity, including images of both fresh and defective tomatoes. This dataset is a valuable resource for researchers, stakeholders, and individuals interested in tomato production in Bangladesh, providing a robust foundation for leveraging computer vision and deep learning techniques in the agriculture sector. The dataset's potential applications extend to automating tasks such as robotic harvesting, quality assessment, and packaging systems, ultimately enhancing the efficiency of tomato production processes.
Examining The Risk Factors of Liver Disease
(Daffodil International University, 2022-06-20) Hossen, Md. Sagar; Haque, Imdadul; Sarkar, Puja Rani; Islam, Md. Ashiqul; Fahim, Wasik Ahmed; Fahim, ,Wasik Ahmmed; Khatun, Tania
Nowadays, Liver Disease (LD) is a very common clinical problem for human health and is related to morbidity and mortality. Nevertheless, an earlier prognosis of LD patients gets a scope to avoid, prior diagnosis and subsequent treatment. This research work attempts to implement a high qualified performer machine learning design to predict LD, the most wanted and unwanted risk factor of LD which could help physicians in classifying risky patients and create an analysis to restrict and control LD. The proposed research study has included all patients, who were identified as having liver diseases. Totally, 6 (six) machine learning algorithms such as Decision Tree(DT), Logistic Regression(LR), Multilayer Perceptron(MLP), Artificial Neural Network(ANN), Random Forest(RF), K Nearest Neighbor classifier(KNN) are selected to predict LD. The location underneath had been utilized to evaluate the accuracy among the six applied models. An overall total of 583 instances had been included in this scholarly research; of the 416 patients are affected by liver illness. The location which defines the receiver operating characteristic (AU ROC) of Logistic Regression, Decision Tree, Multilayer Perceptron, Random Forest, Artificial Neural Network, and K-Nearest Neighbor classifier with 10-fold-cross validation was performed. Furthermore, the reliability of LR, DT, MLP, RF, ANN and KNN with accuracy 72.89%, 81.32%, 60.24%, 86.14%, 75.61%, and 65.52%. The utilization of woodland which is certainly arbitrary within the medical setting may help doctors to detect and classify liver patients for major avoidance, surveillance, quick treatment, and management. LR, DT, MLP, RF, ANN, and KNN formulas are acclimatized to forecast and after analyzing the data set, an increased price of accuracy is achieved.
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.
IOT Security Perspectives and Probable Solution
(2021 Fifth World Conference on Smart Trends in Systems Security and Sustainability (WorldS4), IEEE, 2021-08-19) Newaz, Nishat Tasnim; Haque, Mohammad Rafiqul; Akhund, Tajim Md. Niamat Ullah; Khatun, Tania; Biswas, Milon; Yousuf, Mohammad Abu
Nowadays the Internet of Things (IoT) is a buzzword. In numerous fields, we are using it. So, the security and privacy of the Internet of Things are very important for today’s mankind. In this paper, we have analyzed many Internet of Things systems. We found various vulnerabilities and security faults in some systems. We found various previous works and models to solve the security issues. But those are not enough. This paper has an aim to establish a new model that may be applied to IoT systems to acquire more security. Finally, we have proposed a model for secure IoT systems. We have analyzed that model from various perspectives and found that it may be a solution to the security threats for IoT.
PAPR Reduction of OFDM Signal by Scrutiny of BER Assessment and SPS-SLM Method via AWGN Channel
(2021 6th International Conference on Inventive Computation Technologies (ICICT), IEEE, 2021-01-26) Ohidujjaman; Zannat, Raihana; Khatun, Tania; Rahman, Mahfujur; Raza, Salim; Huda, Mohammad Nurul
Orthogonal Frequency Division Multiplexing (OFDM) has been presently underneath powerful exploration for broadband radio transmission owing to its strength in opposition to multi-path diminishing. Nevertheless, implementation of the OFDM method necessitates numerous complications. The foremost downside is high Peak-to-Average Power Ratio (PAPR) that hints to rise Bit Error Rate (BER) on account of nonlinearity of the peak ability amplifier. The Selected Mapping (SLM) technique is prominent method to lessen PAPR of OFDM signal. With SLM technique, lateral evidence bits are required to recuperate actual data which lead to increase the proportion of data damage. In our article, an exact set of sequential phase sequences (SPS) has been developed to perform SLM technique along OFDM transceiver without requiring of side information. SPS based SLM (SPS-SLM) technique has been able to reduce almost same PAPR compared to the conventional SLM technique. Moreover, the BER performance has been studied considering different number of sub-carriers as well as modulation order.
Performance Analysis of Breast Cancer
(2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), IEEE, 2021-10) Khatun, Tania; Utsho, Md. Mahfuzur Rahman; Islam, Md. Ashiqul; Zohura, Mst. Fatematuz; Hossen, Md. Sagar; Rimi, Robaiya Akter; Anni, Sabiha Jannat
Nowadays, breast cancer is the most emerging disease among women both in developed as well as developing countries. Due to increased life prospects, increased urbanization, and the relinquishment of western societies, the rareness of breast cancer is supersizing in the developing world. Even it became a second popular cause of cancer that has already been announced. It's very hard to identify the early symptom of this type of cancer for reducing numerous death. Different methods of machine learning and data mining techniques are using for medical diagnosis. In this study, four machine-learning algorithms are applying to analyze breast cancer in the inflammation stage and dig up the most cabbalistic and non-cabbalistic risk factors. To analyze breast cancer data from the Coimbra dataset from the UCI machine learning repository to create accurate prediction models for breast cancer. For getting better performance and to get higher accuracy Naïve Bayes (NB), Random Forest (RF), Multilayer Perceptron (MLP), Simple Logistic Regression (SLR) are using to find out some higher accuracy sequentially 70%, 68%, 85%, and 75%. Among all the above algorithms a better accuracy was achieved using Multi-layer Perceptron. Linear Regression (LiR) models are applying to dig up the most cabbalistic and non-cabbalistic risk factors of breast cancer. These results will help the doctor to detect breast cancer easily in the early stage and take the necessary steps.
Performance Analysis of Diabetic Retinopathy Prediction Using Machine Learning Models
(2021 6th International Conference on Inventive Computation Technologies (ICICT), IEEE, 2021-02-26) Emon, Minhaz Uddin; Zannat, Raihana; Khatun, Tania; Rahman, Mahfujur; Keya, Maria Sultana
Diabetic Retinopathy (DR) is a symptom of diabetes that affects the eyes. The blood vessels of the light tissue behind the eyes are damaged (retina). Machine Learning (ML) techniques play a vital role in computer aid diagnosis and discover successful systems for detecting life-threatening diseases. This research aimed to predict diabetic retinopathy and also implement feature extraction to figure out some features. In this research, the data is collected from the UCI machine learning repository. Several Machine Learning (ML) techniques are used for analysis this dataset and find out the best performance and sensitivity, selectivity, true positive (tp) rate, false negative (fn) rate and receiver operating characteristic (roc) curve. In this study, some machine learning algorithms are used such as Naive Bayes, Sequential Minimal Optimization (SMO), logistic regression, Stochastic Gradient Descent (SGD), bagging classifier, J48 classifier, decision tree classifier, and random forest classifier. The overall performance of logistic regression shows the best result.
Recognizing Human Emotions from Eyes and Surrounding Features: A Deep Learning Approach
(Scopus, 2021) Shuvo, Md Nymur Rahman; Akter, Shamima; Islam, Md. Ashiqul; Hasan, Shazid; Shamsojjaman, Muhammad; Khatun, Tania
Abstract: The need for an efficient intelligent system to detect human emotions is imperative. In this study, we proposed an automated convolutional neural network-based approach to recognize the human mental state from eyes and their surrounding features. We have applied deep convolutional neural network based Keras applications with the help of transfer learning and fine-tuning. We have worked with six universal emotions (i.e., happiness, disgust, sadness, fear, anger, and surprise) with a dataset containing 588 unique double eye images. In this study, we considered the eyes and their surrounding areas (Upper and lower eyelid, glabella, and brow) to detect the emotional state. The state and movement of the iris and pupil can vary with the various mental states. The common features found within the entire eyes during different mental states can help to capture human expression. The dataset was trained with pre-trained weights and used a confusion matrix to analyze the prediction to achieve better accuracy. The highest accuracy was achieved by DenseNet-201 is 91.78%, whereas VGG-16 and Inception-ResNet-v2 show 90.43% and 89.67%, respectively. This study will provide an insight into the current state of research to obtain better facial recognition.
Road Object Detection in Bangladesh Using Faster R-CNN
(Scopus, 2020) Datta, Anik; Meghla, Tamara Islam; Khatun, Tania; Bhuiya, Mehedi Hasan; Shuvo, Shakilur Rahman; Rahman, Md. Mahfujur
The importance of object detection in our lives is increasing day by day. The role of object detection is very important in autonomous cars, intelligent driving assistance, and advanced traffic analysis. In the case of traffic analysis and intelligent driving assistance in Bangladesh, it is very important to properly identify all the objects from real-time video. Because in both cases the main responsibility of the system is to give the driver or authority a clear idea about the road or the environment around the vehicle. And for this, we need to use modern algorithms and architecture based neural network models with much better object detection accuracy such as Faster R-CNN. There are currently a couple of algorithms that work faster than Faster R-CNN but cannot detect objects accurately, as is the case with small-to-medium objects. We used Faster R-CNN on our data to analyze the environment around the road and the environment around the car. We trained the network for 19 object classes and tested its ability to detect objects with real-time video analysis with an accuracy of 86.42%. Moreover, FPR(false positive rate) and FNR(false negative rate) is calculated to evaluate the proposed model from confusion matrices. In this study, the FPR of the Faster R-CNN model is 15.97% and the FNR of the Faster R-CNN model is 12.2%
Smart Environmental Solution for Modern Urbanization Using Mobile Application
(2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), IEEE, 2021-03-31) Fahim, Wasik Ahmmed; Sarkar, Puza Rani; Tonmoy, Shakib Salim; Pranto, Atiqur Rahman; Islam, Md. Ashiqul; Khatun, Tania
Nowadays modern civilization having a huge development in technology but we do not get obviate pollution due to the huge amount of population. Behind this, the most of the problem is continuously throwing the garbage's outside and have become stuck up anywhere. There are tons of applications supported the environment and pollution but don't have any effective solution. This paper attempts to develop a flutter based Mobile Application with Google maps API to help the users to reduce the pollution in their locality. User can mark the locations of garbage and can also mail or call the closest authority. In order that the authority can clean or take necessary steps counting on the user's report. For increasing people's awareness, it shows real-time air quality and pollution level supported on web scrapping data from different websites and IoT based systems. During this modern technology era, mobile applications are the foremost popular. So this application may be a very effective to reduce pollution by public awareness or by making communication between user and the authority.