Browsing by Author "Saifuzzaman, Mohd."

Now showing 1 - 20 of 26

A Comparative Study on Prediction of Dengue Fever Using Machine Learning Algorithm
(Springer, 2020-06-12) Dourjoy, Saif Mahmud Khan; Rafi, Abu Mohammed Golam Rabbani; Tumpa, Zerin Nasrin; Saifuzzaman, Mohd.
Dengue is the most common viral fever for the people. This is also known as life-threatening disease. Dengue has become more and more evident this year in Bangladesh. It has taken the lives of many in our country. And the number of dengue fever patients is increasing day by day. There are many people at risk from dengue. Early forecast of dengue can spare individual’s life by cautioning them to take legitimate conclusion and care. But it is difficult to say in advance whether this will happen or not. The aim of this piece of research work is to analysis the symptoms of dengue fever and early prediction of the symptoms that can be seen in years ahead. For predicting the symptoms, two different machine learning algorithms have been used. Support vector machine (SVM) and random forest classifier algorithm have been used. Finally, the accuracy of these two has been evaluated and the confusion matrix has been shown. And then, we have talked about the algorithm which is better for our dataset.
A Comparative Study on Prediction of Dengue Fever Using Machine Learning Algorithm
(Springer, 2021) Dourjoy, Saif Mahmud Khan; Rafi, Abu Mohammed Golam Rabbani; Tumpa, Zerin Nasrin; Saifuzzaman, Mohd.
Dengue is the most common viral fever for the people. This is also known as life-threatening disease. Dengue has become more and more evident this year in Bangladesh. It has taken the lives of many in our country. And the number of dengue fever patients is increasing day by day. There are many people at risk from dengue. Early forecast of dengue can spare individual’s life by cautioning them to take legitimate conclusion and care. But it is difficult to say in advance whether this will happen or not. The aim of this piece of research work is to analysis the symptoms of dengue fever and early prediction of the symptoms that can be seen in years ahead. For predicting the symptoms, two different machine learning algorithms have been used. Support vector machine (SVM) and random forest classifier algorithm have been used. Finally, the accuracy of these two has been evaluated and the confusion matrix has been shown. And then, we have talked about the algorithm which is better for our dataset.
A Survey of Botnet in Cyber Security
(Scopus, 2019-09-29) Shetu, Syeda Farjana; Saifuzzaman, Mohd.; Moon, Nazmun Nessa
Botnets is one of the most critical cyber security threats that confronted by organizations day by day. Botnet has used distinctive strategies, topologies and communication protocol in specific levels in their life cycle. Identifying of botnets has emerged as a very challenging topic, particularly for the reason that they can improve their method at any time. Nowadays, most of the recent botnet detection techniques cannot locate modern botnets in an early stage. Mainly, botnets follow command and control infrastructure. Nowadays, botnet is an interesting and very vital research topic for researchers in our cyber security. This Paper represents a completely comprehensive evaluation that extensively discusses the botnet problem; this survey classifies all of the possible botnet detection methods, also summarizes previously published studies and recent works.
An Advanced Method of Treating Agricultural Crops Using Image Processing Algorithms and Image Data Processing Systems
(2020-10) Salehin, Imrus; Talha, Iftakhar Mohammad; Saifuzzaman, Mohd.; Moon, Nazmun Nessa; Nur, Fernaz Narin
Smart agriculture has involved evolution, judgment, and application of new methods of using modern technology. Technological advances in agriculture will enable farmers to enhance their skills in farming. We planned technology for farming by combining an app and a SMS system through the mobile phone. Different types of virus, fungus, and bacterial infection causes a great loss of farming product. Modern technologies in various computer science fields such as image processing, data mining can be applied in this infrastructure. We use the Scale-Invariant Feature Transform (SIFT) algorithm in this paper to identify crop diseases based on various types of datasets. The SFT technique is a well-known method that is applied to find the image data with pixel integrated. Firstly, we find out all key points and store all unique data from image for next steps. After processing every pixel, we match the main key point for major disease detection. In this study, our contribution is that we are trying to identify all diseases. We are trying to provide some solutions with the help of a solution bank using SMS services and live web portals.
An Artificial Intelligence Based Rainfall Prediction Using LSTM and Neural Network
(IEEE, 2020-12) Salehin, Imrus; Talha, Iftakhar Mohammad; Hasan, Md. Mehedi; Dip, Sadia Tamim; Saifuzzaman, Mohd.; Moon, Nazmun Nessa
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.
Ascertaining the Fluctuation of Rice Price in Bangladesh Using Machine Learning Approach
(IEEE, 2020-07) Hasan, Md. Mehedi; Zahara, Muslima Tuz; Sykot, Md. Mahamudunnobi; Nur, Arafat Ullah; Saifuzzaman, Mohd.; Hafiz, Rubaiya
Rice is the most grown crop in Bangladesh. It is consumed as the main food course in Bangladesh. The price of rice makes a difference in whether people will eat or starve. To know what's going to happen in the rice market using pen and paper is a far cry as well as time-consuming. Machine Learning (ML) provides the facilities to predict the price of any products to prevent a future collapse in the market. The goal of this paper is to predict the price of rice using Machine learning approach. Data collected from the Ministry of Agriculture website, Bangladesh was used to predict the price. Several machine learning algorithms were used to make this prediction i.e. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes, Decision Tree and Random Forest. All these algorithms are analyzed to find out which algorithm provides the best performance. Now, we can predict the price of rice, whether it is reasonable, low, or high based on the results achieved by the mentioned algorithms.
Breathe Safe
(ICECE 2018 - 10th International Conference on Electrical and Computer Engineering, IEEE, 2018-12-22) Siddique, Md. Junayed; Islam, Mohammad Aynul; Nur, Fernaz Narin; Moon, Nazmun Nessa; Saifuzzaman, Mohd.
Recently, garbage management is the most buzzing word to ensure a healthy environment. The dustbins are placed across an open place which are actually over burden and leads an unhygienic environment as well as spreads different types of unnamed diseases. In the present scenario as the population of Bangladesh is increasing day by day, we should maintain a clean and hygienic environment to avoid this problem. So, we propose a system by which all dustbins are interfaced with microcontroller based system having Ultrasonic sensor for waste level detection and Wi-Fi module to connect to the internet. Realtime status of all dustbins will be shown on an Android application and also shortest direction will be provided on map. Main goal is of this research is to maintain a healthy environment in our city and reduce human sufferings.
BSSID Based Monitoring Class Attendance System Using Wifi
(Proceedings of the 3rd International Conference on I-SMAC IoT in Social, Mobile, Analytics and Cloud, IEEE, 2019-12-14) Hasan, Mahadi; Saha, Dipto; Ferdosh, Jannatul; Nur, Fernaz Narin; Moon, Nazmun Nessa; Saifuzzaman, Mohd.
Recent advancements in wireless technologies have evolved the growth of smart systems in day to day life. Nowadays, people are using WiFi connectivity for accessing the Internet or local hub inside home or office. A smart phone based checking system for monitoring class attendance through WiFi signal is developed in this work. Student, Teacher & Admin need to be installing the application. Most challenging part in this system is to make software design and send notification in smartphone. When Admin set specific time and students Smartphone connected with specific WiFi that time then they get notification for class attendance.
Enjoy and Learn with Educational Game Likhte Likhte Shikhi Apps for Child Education
(Advances in Intelligent Systems and Computing, Springer, 2018-12-12) Dipu, Md. Hasanuzzaman; Moon, Nazmun Nessa; Aunkon, Md. Walid Bin Khalid; Saifuzzaman, Mohd.; Nur, Fernaz Narin
Nowadays, children (under age 2–6 years) become so much affected to smartphone. It is impossible to take back the device when they play a game on that device. So, we realized if this affection is possible to convert to an educational game, it can be better. We decide to build an educational game that can help to teach them how to write and read a letter. A child can easily learn the technique how to write a letter properly by this game. After completing the writing part this app will play the actual pronunciation of that letter. The Graphical User Interface of this game is very attractive as well as user friendly. A child can learn both Bangla and English letter writing and reading by this game. This game is completely offline and dynamic game app. The game size is smaller than other games. And it can run smoothly on any of Android Device such as Smartphone, Tab and Smart TV.
Enjoy and Learn with Educational Game: Likhte Likhte Shikhi Apps for Child Education
(Springer Nature Singapore Pte Ltd., 2018-12-12) Aunkon, Md. Walid Bin Khalid; Dipu, Md. Hasanuzzaman; Moon, Nazmun Nessa; Saifuzzaman, Mohd.; Nur, Fernaz Narin
Nowadays, children (under age 2–6 years) become so much affected to smartphone. It is impossible to take back the device when they play a game on that device. So, we realized if this affection is possible to convert to an educational game, it can be better. We decide to build an educational game that can help to teach them how to write and read a letter. A child can easily learn the technique how to write a letter properly by this game. After completing the writing part this app will play the actual pronunciation of that letter. The Graphical User Interface of this game is very attractive as well as user friendly. A child can learn both Bangla and English letter writing and reading by this game. This game is completely offline and dynamic game app. The game size is smaller than other games. And it can run smoothly on any of Android Device such as Smartphone, Tab and Smart TV.
Expert Cancer Model Using Supervised Algorithms with a Lasso Selection Approach
(International Journal of Electrical and Computer Engineering (IJECE), 2021) Ghosh, Pronab; Karim, Asif; Atik, Syeda Tanjila; Afrin, Saima; Saifuzzaman, Mohd.
One of the most critical issues of the mortality rate in the medical field in current times is breast cancer. Nowadays, a large number of men and women is facing cancer-related deaths due to the lack of early diagnosis systems and proper treatment per year. To tackle the issue, various data mining approaches have been analyzed to build an effective model that helps to identify the different stages of deadly cancers. The study successfully proposes an early cancer disease model based on five different supervised algorithms such as logistic regression (henceforth LR), decision tree (henceforth DT), random forest (henceforth RF), Support vector machine (henceforth SVM), and K-nearest neighbor (henceforth KNN). After an appropriate preprocessing of the dataset, least absolute shrinkage and selection operator (LASSO) was used for feature selection (FS) using a 10-fold cross-validation (CV) approach. Employing LASSO with 10-fold cross-validation has been a novel steps introduced in this research. Afterwards, different performance evaluation metrics were measured to show accurate predictions based on the proposed algorithms. The result indicated top accuracy was received from RF classifier, approximately 99.41% with the integration of LASSO. Finally, a comprehensive comparison was carried out on Wisconsin breast cancer (diagnostic) dataset (WBCD) together with some current works containing all features.
Expert Cancer Model Using Supervised Algorithms with a Lasso Selection Approach
(International Journal of Electrical and Computer Engineering (IJECE), Elsevier, 2021) Ghosh, Pronab; Karim, Asif; Atik, Syeda Tanjila; Afrin, Saima; Saifuzzaman, Mohd.
One of the most critical issues of the mortality rate in the medical field in current times is breast cancer. Nowadays, a large number of men and women is facing cancer-related deaths due to the lack of early diagnosis systems and proper treatment per year. To tackle the issue, various data mining approaches have been analyzed to build an effective model that helps to identify the different stages of deadly cancers. The study successfully proposes an early cancer disease model based on five different supervised algorithms such as logistic regression (henceforth LR), decision tree (henceforth DT), random forest (henceforth RF), Support vector machine (henceforth SVM), and K-nearest neighbor (henceforth KNN). After an appropriate preprocessing of the dataset, least absolute shrinkage and selection operator (LASSO) was used for feature selection (FS) using a 10-fold cross-validation (CV) approach. Employing LASSO with 10-fold cross-validation has been a novel steps introduced in this research. Afterwards, different performance evaluation metrics were measured to show accurate predictions based on the proposed algorithms. The result indicated top accuracy was received from RF classifier, approximately 99.41% with the integration of LASSO. Finally, a comprehensive comparison was carried out on Wisconsin breast cancer (diagnostic) dataset (WBCD) together with some current works containing all features.
Human Behaviour Impact to Use of Smartphones with the Python Implementation Using Naive Bayesian
(11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020, IEEE, 2020-10-15) Talha, Iftakhar Mohammad; Salehin, Imrus; Debnath, Susanta Chandra; Saifuzzaman, Mohd.; Moon, Nazmun Nessa; Nur, Fernaz Narin
A change of behavior in special groups and many sustainable smart populations increasing day by day for excessive uses of smartphones. In recent years, the use of smartphones and mental imbalances have become a major problem with increasing negative effects. In our study, we find out the major problem of the negative side and its different sources like mental imbalance, stress, depression, loneliness, etc. Bayes' theorem and classifier, support vector machine, special data set of human behavior, and probability are used to calculate accuracy. For collecting data from three major sections, we use the physical methods, virtual methods, and medical reports. So, a vast data set is trained by data to compare method, and also probability is used for predicting the validity of the data model. Naive Bayes' theorem accurate 71% positive which is indicated the negative impact of human behavior. Based on the SVM classifier, we separate the barrier between the impact of positive and negative data. In SVM, we set up a parameter to measure negative and positive values. Python library function is a major component to calculate all instructions and also use for data training. Finally, we compare the results obtained by our proposed specialization with the results obtained from the three baseline landmarks.
Implementation of Low Cost Real-time Attendance Management System
(ICRITO 2020 - IEEE 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), IEEE, 2020-09-15) Hasan, Rakib; Islam, Sajedul; Rahman, Md. Habibur; Saifuzzaman, Mohd.; Shetu, Syeda Farjana; Moon, Nazmun Nessa
In this research, a systematic approach was adopted to expand the level of service to the real-time attendance system. The test was performed to assess the efficiency of the attendance system, which would be quite cost-effective but accurate. To that the expense of linking our biometric attendance system to a central server where the data is changed instantly. So, the possibility of data loss is nothing at all. Our proposed prototype may cost around 30$ while the available existing devices are high priced. Moreover, most devices generate abundant data in favor of an individual user where our proposed model provides well organized data to track down the attendance. Furthermore, a very low amount of energy is needed to run the entire system. The entire system can be installed anywhere with a very low expense
IoT based street lighting and traffic management system
(IEEE, 2018-02-12) Saifuzzaman, Mohd.; Moon, Nazmun Nessa; Nur, Fernaz Narin
In this modern era where energy is the major concern worldwide, it is our prior responsibility & liability to save energy effectively. With the development of technology, where automation system plays a vital role in daily life experience and also it is being preferred over the traditional manual system today. The main purpose of this project is to invent an intelligent system which can make decisions for luminous control (ON/OFF/DIM) considering the light intensity. Here the day and night mode can be identified by fixing a particular intensity value on LDR sensor and street light can be controlled by IR sensor. The interesting part of this paper is the installation of solar cell for the power supply but in course of circumstances, if the solar cell is unable to do so, a secondary backup DC current will maintain the situation immediately. Another remarkable part of this project is to maintain the traffic signal automatically without any help of traffic police and monitor the entire system through internet by installing surveillance camera. All the components of this project are very simple and cost effective but efficient to make a reliable intelligence system.
IOT Based Street Lighting Using Dual Axis Solar Tracker and Effective Traffic Management System Using Deep Learning
(11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020. IEEE, 2020-10) Saifuzzaman, Mohd.; Shetu, Syeda Farjana; Moon, Nazmun Nessa; Nur, Fernaz Narin; Hanif Ali, Mohammad
With the rapid increase of population, nonrenewable energy loss has become one of the prior concerns worldwide in recent years. Researchers are working on the proper utilization of renewable energy to save the rest of the non-renewable energy sources for future generations. One of the purposes of this research is to develop an intelligent automation system that can decide luminous control operation based on light intensity. Here, LDR sensor is installed in such a way that it can be able to identify Night and Day mode using a certain intensity value, and as well as IR sensors take over the control of street light. The solar cell will be used for power supply here and DC current will work as a secondary backup. The article also involves automatic monitoring of traffic controls through a video system. The camera incorporates automatic text retrieval from video data utilizing lip reading by decoding facial expression utilizing deep learning methods. The proposed solution includes a test data collection, an interpretation of the picture frame, and a text production of the specified words. The test data collection will be structured in the proposed methodology by integrating all potential facial expressions of different words.
IOT Waiter Bot
(ICRITO 2020 - IEEE 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) IEEE, 2020-09) Akhund, Tajim Md. Niamat Ullah; Siddik, Md. Abu Bakkar; Hossain, Md. Rakib; Rahman, Md. Mazedur; Newaz, Nishat Tasnim; Saifuzzaman, Mohd.
The modern era is Robotic and IOT era. Robots are reducing human works. Robots are broadly using in Restaurants, Farming, Hospitals and various fields now a days. This work results a low cost IOT Robot that can work like a waiter in a restaurant. The developed robot can follow line and avoid obstacles. The robot can take and serve orders to the customers. It reads RFID from tables to recognize particular orders from customers. The collected data will be saved in a cloud database. Taken orders by robots will automatically go to the chefs. Each order bill will also be generated on the robot. The robot will be able to take the bills also. The full system is made in very low cost than previously made systems. It will not increase unemployment problem too.
Machine Learning Approach to Predict SGPA and CGPA
(2021 International Conference on Artificial Intelligence and Computer Science Technology (ICAICST), IEEE, 2021-07-30) Saifuzzaman, Mohd.; Parvin, Masuma; Jahan, Israt; Moon, Nazmun Nessa; Nur, Fernaz Narin; Shetu, Syeda Farjana
The prediction of SGPA and CGPA is beneficial to university students. Students will easily get an estimate of their final outcome from this project. As a result, the students will be able to brace themselves for a successful outcome. Students pass the day by participating in a variety of events. Students use social media sites such as Facebook, Instagram, and Twitter. They engage in various hobbies such as playing mobile games, listening to music, among others. As a result, they were able to move several times with these tasks. As a result, if a student spends so much time doing any of those things, she will not be able to achieve a successful grade because of the experiment; students can develop a research routine or guideline that they can apply to their other tasks. Additionally, students' behaviors will forecast their outcomes. The Authors will now see machine learning in Python being used all over the place. After that, The Authors created a smart SGPA and CGPA prediction project, as well as the results on students. The findings are predicted using the Nave Byes algorithm. The Nave Byes algorithm is a simple but effective prediction algorithm. It is a machine learning algorithm as well. As a result, students will be given an estimate of their final exam scores. They can prepare them to make a good result by following the routine of the SGPA & CGPA prediction project.
Natural Language Processing Based Advanced Method of Unnecessary Video Detection
(International Journal of Electrical and Computer Engineering, 2021) Moon, Nazmun Nessa; Salehin, Imrus; Parvin, Masuma; Hasan, Md. Mehedi; Talha, Iftakhar Mohammad; Debnath, Susanta Chandra; Nur, Fernaz Narin; Saifuzzaman, Mohd.
In this study we have described the process of identifying unnecessary video using an advanced combined method of natural language processing and machine learning. The system also includes a framework that contains analytics databases and which helps to find statistical accuracy and can detect, accept or reject unnecessary and unethical video content. In our video detection system, we extract text data from video content in two steps, first from video to MPEG-1 audio layer 3 (MP3) and then from MP3 to WAV format. We have used the text part of natural language processing to analyze and prepare the data set. We use both Naive Bayes and logistic regression classification algorithms in this detection system to determine the best accuracy for our system. In our research, our video MP4 data has converted to plain text data using the python advance library function. This brief study discusses the identification of unauthorized, unsocial, unnecessary, unfinished, and malicious videos when using oral video record data. By analyzing our data sets through this advanced model, we can decide which videos should be accepted or rejected for the further actions.
Predicting Career Using Data Mining
(2nd International Conference on Electrical, Computer and Communication Engineering, ECCE 2019, IEEE, 2019-03-28) Arafath, Md. Yeasin; Saifuzzaman, Mohd.; Ahmed, Sumaiya; Hossain, Syed Akhter
Career goal specially choosing the appropriate career through monitoring of the scope and trends in computer science and engineering job dimension have been a prime need for all computer science undergraduate youngsters. It has always been essential for an early signal to help the developmental mindset. In this research work, we attempted exploring dynamic data set and apply data mining based methods to explore student's insights based on characteristics related to academic, technical and interpersonal factors. This research helped prediction of student's estimated career including student's strength and weakness. The accuracy of prediction actually lies with the set of relevant skill parameters, interpersonal and academic factors. The research also helped teachers identifying the students who need special attention and allowed the teacher to provide appropriate counselling as well as give them a proper guideline for selecting a specific job sector which leads a healthy collaboration between academia and industry. The model was tested and found performing well in constraint based learning environment.