Masters Thesis

Permanent URI for this collection

https://dspace.nstu.ac.bd/handle/123456789/95

Browse

Now showing 1 - 20 of 60

CLASSIFICATION OF EARLY AND LATE BLIGHT DISEASE OF POTATO USING CONVOLUTIONAL NEURAL NETWORK
(2020-12-08) Jesmin Akther
Crop diseases are a major threat to cultivate, and need to supervise growth and detrimental diseases in time. Potato early and late blight disease symptoms and detection both are vague to distinguish and isolate. The rising combination of smartphone penetration and recent advances in deep learning has paved the way for smart device assisted disease prognosis. Relying on pure naked-eye observation to detect and classify diseases can be very cumbersome. Absolute detection process proves to be effective and convenient for researchers. The technique of training deep learning models on increasingly vast and globally available image datasets presents a clear path toward smartphone aid crop disease experiment around the world. The color and analyze layer features are used to best match to recognize and classify different agriculture produce into early blight and late blight affected disease. Both features prove to be very effective in disease detection. This paper deployed a Sequential convolutional neural network (CNN) model to detect and identify diseases in real time survey potato leaves labeling early and late blight. In addition to normalization, divide and extract the images to prepare data prior CNN. This work adopts slight variation during CNN model finalization with the help of Tensorboard analysis. This analyzed effectively optimized model validation accuracy each layer by layer hierarchically. Best layers ensure to create the final model which assures 94% accuracy for this dataset and short timing classification. The experimental results indicate that the approach significantly can be modified model accuracy in automatic detection of both affected bight.
ANALYSIS ON IMPACT OF PRECEDING EDUCATIONAL PERFORMANCE ON THE RESULTS ACQUIRED IN HIGHER STUDY
(2020-12-08) MONIR HOSSAIN
Academic performance has been one of the most important goals of the educational process. Academic achievement is a key mechanism through which adolescents learn about their talents, abilities and competencies which are an important part of developing career aspiration. It is also a major goal, which every individual is expected to perform in all cultures. Many researches have been conducted to investigate factors affecting students’ performance in university and colleges. The aim of this research is that determine the impact of students academic result in school and college on student’s performance in university level. We determine the effect of SSC and HSC result in honor’s result. We find out the importance of various subject including Mathematics, Chemistry, Physics and Biology by determine individual impact on honors result in department of engineering and biology faculty. We also analysis the university honor’s result categorized by gender, department, SSC board and university admission merit. The research is based on student records based on the dataset collected through assessment from university databases. Data analysis technique- statistical analysis technique was used to extract useful information from the database using Rapid Miner software. The results obtained by using various charts like scatter, multiple scatter and bar charts. This analysis result helped to find out many useful information based on which proper guidance and suggestions are designed for students. Students will know more that which subject should be given more importance. Students will also see examples of good results in university without getting good results in the past and they will be more energetic to good results.
Automated Class Routine and Exam Schedule Management System(ACRESMS)
(2020-12-08) SHABBIR AHAMMED
Every educational institution needs class routine and exam schedule for its activities. If making this class routine and exam schedule will generate automatically, it will be very amazing. Automated Class Routine and Exam Schedule Management System(ACRESMS) is very important in any educational institutions. The authority can create class routine and exam schedule by clicking this system, generate class routine, update routine, generate exam schedule, update exam schedule and deleted it easily. This system saves time and reduce paper based work. We will divide the system into different segments such as teacher’s information, course information, classroom details, teacher details, time management, session, years, teacher summery etc. Every segments have contained different database for clear concept. We use here MySQL database to implement the system. The purpose of the project is to automated making ACRESMS which is user friendly, simple and fast. This system will be helpful for any institutions because there are few paper based task, student can get class schedules and exam schedule easily and admin can handle this system without any problem because it will be online based system. This system reduces complexity of class room, teacher availability problem, examination hall room, invigilator availability and paper based complexity. This system will be user friendly system.
AN EFFECTIVE APPROACH FOR EARLY LIVER DISEASE PREDICTION
(2020-12-08) FARIA AFRIN
Liver is one of the main organ of our body. It will be functioning normally even when it is partially damaged, therefore problems with liver patients cannot easily discovered in an early stage. Patient’s survival rate can be increased by an early identification of liver problems. Liver disease can be diagnosed by observing the levels of enzymes in the blood. Many researchers working on this issue and try to find the best algorithm with using Liver patient dataset which is suitable for predicting disease in early age. In this research liver patient dataset is investigated for building different classification models to get better result by comparing with the accuracy of the classifiers for disease prediction. Real data in this purpose is collected from the hospitals. This paper uses different classification methods including Bagged Trees, Support vector machine (SVM), K-Nearest Neighbor (KNN), Fine Tree classification methods. It can give a good impact on the liver disease diagnosis and it can be beneficial for physicians and can help to reduce the cost of diagnosis in the medical sector.
AN EFFECTIVE TECHNIQUE ON EARLY HEART DISEASE PREDICTION
(2020-12-10) TANZINA RAHMAN HERA
Heart disease is the most threatened issue in a human body. Most of the people in the world are affected by heart disease which increases the death rate of humans considerably. The detection of heart disease is the most trivial task for medical researchers which cannot be done more accurately. The early detection, manual prediction and prevention is a complex task and troublesome. So there is an urgent need for a well-designed method for the early detection of heart disease. Thus it is required to implement the automated system by considering the recent computer technologies which can help medical researchers to diagnosis heart disease firstly and accurately. Now a day’s artificial neural network has been widely used as a tool for solving many decision modelling problems. This research enlightened a number of structures in Artificial Neural Network by varying the configurations of neural network algorithms like Radial Basis Function Neural Network, Recurrent Neural Network, Decision tree classifier and Support Vector Machine Neural Network. This research also compared those Neural Network models on the early detection of heart disease and chose the best neural network model among them to detect the heart disease early. The Network Structure that showed more accuracy and efficiency is chosen among them.
Efficient Data Mining Techniques for Heart Disease Prediction and Comparative Analysis of Classification Algorithms
(2020-12-30) Masudur Rahman
Data mining techniques are used to extract interesting patterns and discover meaningful knowledge from huge amount of data. There has been increasing in usage of data mining techniques on medical data for determining useful trends and patterns that are used in analysis and decision making. About eighty percent of human deaths occurred in low and middle-income countries due to heart diseases. The healthcare industry generates large amount of heart disease data which are not organized. These data make the prediction process more complicated and voluminous. Data mining provides the techniques for fast and accurate transformation of data into useful information for heart diseases prediction. The main objectives of this research is to predict heart diseases more accurately using Naïve Bayes, Decision Tree, Neural Network, Random Forest classification algorithms and compare the performance of classifiers. The research uses raw dataset for performance analysis and the analysis is based on Jupyter. This research also shows better classification technique from them which is Random Forest on the basis of accuracy. Keywords: KDD, Jupyter, Naïve Bayes, Decision Tree, Multilayer Perceptron, CSV.
EFFICIENT COMBINED TECHNIQUES FOR PERSON RECOGNITION WITH COVERED FACE AND EYES
(2020-12-30) MD. MAHBUBUL ALAM
Face is the most common parameter which defines any person uniquely. Face recognition is a process of identifying or verifying the identity of an individual using their face. Principal component analysis is algorithm for face recognition. In facial recognition there are some complexities that degraded the efficiency of face recognition using Principal Component Analysis for covered face and covered eyes. Iris recognition is a process of detecting a person uniquely by reading the eyes. Iris recognition can remove the covered face complexities but when someone wears sunglasses which covered eyes then iris recognition will not work properly. Face recognition is not efficient for covered face like faces with mask, long beard and naqab. Iris recognition is not efficient for covered eyes like eyes with sunglasses. To overcome all these complexities which include covered face or eyes, our proposed efficient models are Combined PCA-Segmentation, Combined PCA-Daugman and Combined PCA-SVM Face Recognition. In this work, Principal Component Analysis process will take place combined with Segmentation, Daugman and Support Vector Machine. Segmentation will help for creating upper and lower face evaluation separately, Support Vector Machine will help to detect the covered faces to improve the recognition accuracy. To calculated the accuracy of the systems there are four image datasets used called ORL, Yale, Real and CASIA which is iris image dataset. This work has used also real image dataset. For all dataset each model has provided better accuracy than solo PCA. The motto of this work is to remove the complexities of beard, mustache, hijab and sunglasses at facial recognition to increase the overall accuracy for improving the face recognition.
DESIGN AND IMPLEMENTATION OF FOG ASSISTED IOT BASED HEALTH MONITORING SYSTEM
(2020-12-30) UMME AFIFA JINAN
With the proliferation of IoT devices in healthcare systems and the health informatics arena, IoT based health-monitoring systems have brought about a groundbreaking breakthrough in this 21st-century health information technology, and medical data processing. Meeting the challenges of distributed IoT based healthcare systems implementation, cloud computing alone cannot contribute to the scenario with IoT effectively. Huge medical sensors generated data to be stored in a centralized cloud server may generate problems like latency, network congestion, and increased data traffic due to the overflow of data in the system. Hence, fog computing can overcome these problems by working as a middle layer in between IoT and cloud. This decentralized cloud computing platform facilitates intermediate data processing, analysis, storage, real-time delivery. In this study, we enhanced such an IoT-enabled real-time patient health monitoring system by exploiting the fog computing concept for extracting sensor data, visualizing at a reduced cost and power, storing at local storage, monitoring, and interacting remotely in real-time. Using a couple of sensor devices that measure vital body parameters, we developed a new type of fog computing interface using Raspberry Pi and Arduino UNO. A dedicated local server was implemented as well for the storage and maintenance of the sensor extracted data and giving real-time notification. The implemented monitoring system portraits the efficacy of our proposed system architecture for monitoring patients simultaneously at low cost, low power with simpler system establishment and real-time remote monitoring. The comparison between medical data and biosignals and sensor generated data and signals showed the feasibility of the system. The technical feasibility of the developed fog computing node in terms of cost, power consumption, and latency was evaluated as well. The development and testing of the health monitoring system proves that this system is intended to give relief to medical caregivers while taking care of patients remotely irrespective of time and place.
DIGITAL ATTENDANCE CONTROL SYSTEM USING TECHNOLOGY OF BIOMETRIC FINGERPRINT
(2021-01-20) SELIM AHEMMED
Student's academic performance primarily depends on the attendance and participation of the class. The paper-dependent conventional attendance management for students in institutions is time-consuming and laborious work for the educators. Sometimes students get the opportunity for proxy attendance. Also, Students have no idea about the attendance percentage which is mandatory for attending the semester final examination. The world is turning towards automation for reducing human efforts and is striving to make the process smart and reliable. There are many smart systems to optimize attendance. Each system has some shortcomings and unable to achieve our requirements completely. In this project, a novel system is developed which used the technology of biometric fingerprint to control academic attendance. The device includes a fingerprint collection terminal and attendance control module in a computer website and database, designed as the transmitter and receiver node with the Arduino microcontroller, fingerprint sensor, display, and Wi-Fi unit. This method deals with the control of the student's attendance information. It generates attendance of students based on class presence. It publishes an attendance excel sheet and percentage for every course of the semester. The developed system monitors attendance without allowing students any chance of proxy attendance. The system can be installed at any spot. This system saves time, minimizes the volume of work that educators have to do, and replace the stationery material with a computer system by eliminating the boring old form. Apart from these, we strongly believe that this project makes us more competent for similar future tasks and enhance our technical abilities.
COMBINING CLOUD, FOG, ROOF AND DEW COMPUTING WITH SDN TO IMPROVE QoS OF IoT ECOSYSTEM
(2021-01-20) ISHTIAQ AHAMMAD
Recently, there's been a growing curiosity in the Internet of Things (IoT), due to the ubiquitous existence of the internet. Such curiosity leads the concept of IoT ecosystem. But contemporary fragmented ecosystem of regulations, technologies, and systems slows IoT deployments. Because they typically concentrate on a particular use case, or are confined to a specific standard. Therefore, an IoT ecosystem which encompasses all the elements (i.e. remote controls, dashboards, communications, access points, analytics, data management, security etc.) to enable companies, governments, and users to seamlessly connect their IoT devices to the existing ecosystem framework to receive services is a necessity. But some concerns in this ubiquitous IoT ecosystem infrastructure may end up making its development a really difficult task. Thus in this paper multi-tiered computational infrastructure is considered which would be feasible to provide services from the nearest possible location of end-user devices and thus fix most of the difficulty issues. However, bringing computational infrastructures to user surroundings doesn't really automatically address all technological challenges. It also generates complications of its own if it is not properly managed. Therefore, this paper takes into account Software-Defined Networking (SDN) as a solution. SDN has shown its utility in lessening the complications of management in today's networks. Now to understand the journey behind SDN-supported multi tier computational infrastructure; elaborate study on cloud, fog, roof, and dew computing and their interaction with SDN is performed in this paper. Then two novel methods are presented to improve QoS in an IoT ecosystem. In “Method I”, a novel architecture is proposed to combine independently researched areas of SDN and Fog Computing to improve QoS. In support of the architecture, there is also a proposed algorithm based on Virtual Partition for optimal access point and optimal place of operation selection. The “Method II” presents SD-DRFC framework architecture for today's IoT ecosystem which combines Cloud, Fog, Roof and Dew computing domains which are managed by SDN. The novelty of this SD-DRFC framework lies in its ability to deliver services from the nearest possible location, manage data routing pathways individually for various types of data, efficiently balance huge data traffic on the network, offer limited services without internet connection, and distribute network and computing resources appropriately. Next simulation setup is performed for both of these proposed methods. For simulation, a use case is defined for each method which is identical to the proposed methods architecture. These simulation setups are performed on iFogSim simulator. The result shows a significant improvement of several QoS parameters in the execution of proposed methods compared to the cloud-only execution. In specific, the simulation result of “Method I” offers much better results for energy consumption, network usage and latency compared with previous similar approaches. The result shows a 275.9% reduction in latency and a 212.21% reduction in network usage. For both “Method I” and “Method II”; the simulation results justify major improvement in some QoS parameter in favor of the proposed methods. Since these parameters are the most significant ones in an IoT ecosystem; hence their improvement indicates overall QoS improvement of IoT ecosystem.
LANGUAGE TRANSLATION USING NEURAL MACHINE TRANSLATION
(2021-01-20) NUSRAT JAHAN SUHA
Machine translation (MT) is an automatic translation from one language to another. The benefit of machine translation is that it is possible to translate large envelop of text in a very short time. Neural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the possibility of a sequence of words, typically modeling entire sentences in a single integrated model. In this paper, a recurrent neural network named long short term memory is used. Overall neural Machine translation is used for translating not only Bengali languages but also different western and Asian languages to English. Unlike the traditional phrase-based translation system which consists of many small sub-part that are tuned separately, neural machine translation attempts to build and train a single, large neural network that reads a sentence and outputs a correct translation. In this model, it gives a satisfied BLEU score which quality is better than human translation. Also, a comparison between Google translator and established neural machine translation has happened. These thesis paper have also worked with 4 uncommon languages to translate into English. These languages even do not add to the Google translator. The research has also shown that western languages have given better BLEU score than the Asian language. Especially the Latin script languages have given better translation quality than other script languages. The research has worked with 27 languages. Among 27 languages 14 languages have been widely analyzed. For the poor datasets, the BLEU score is not good but in the larger datasets, it gives satisfactory results than ever. Here, the neural machine translation model is established, trained. And by using these 27 languages datasets the model translation capacity have evaluated. Established neural machine translation gives pretty good translation quality. Although all the languages have not given a higher BLEU score or accuracy like Google translator, the translation quality is good according to the BLEU score matrix algorithm. For some languages the proposed and established model has given a better BLEU score than the Google Translator. Also, some sentences of every language have compared with the output of Google translator. In this comparison, a translation difference between the established translation system and Google translator is found. For some languages, the meaning of the languages is fully reversed in Google translator. But on the other hand, the established neural machine translation system has given a good translation in these aspects. So, in this research different languages are translated to English by the Neural Machine Translation model. This can make a good contribution to the field of machine translation.
UNIVERSITY HALL MANAGEMENT SYSTEM
(2021-01-30) JANNATUL FERDOUS
UNIVERSITY HALL MANAGEMENT SYSTEM is a web based application intended for the students of all places which could be beneficial for them on the long run. The main objective of this application is to make it interactive and its ease of use. From this application students will be facilitated by providing the accommodation information. They will be informed about the residential facilities in hall whether they will reside there or not and if they can, they will be more specific by knowing room number, quantity of seats and contact info. Through this website students will be able to apply for the hall seat to the Hall provost.. The main emphasis lies in providing mail service, Students application first sent to department chairman as an anonymous message, after confirmation it will be sent to the provost, the confirmation mail will be sent to the students after the provost confirm the application. Only the registered chairman and hall provost can view the details of students and confirm their application via mail. Students can also receive the confirmation mail. Hall provost can add student in the hall if hall seats are available otherwise student cannot be allowed to hall. It will be hassle-free and less time consuming for the students. “UNIVERSITY HALL MANAGEMENT SYSTEM” is designed and implemented using the HTML (Hypertext Mark-Up Language), CSS (Cascading Style Sheet), PHP (PHP Hypertext Pre Processor), and MySQL database at the front-end and back-end. The system was tested after the development and found that it was appropriate to meet all the prerequisites indicated.
SMART EXAMINATION ROUTINE MANAGEMENT SYSTEM
(2021-01-30) SHAMIA AHMED CHOWDHURY
Our education system is based on examination. This examination routine is done before starting any kind of test, because no work can be done properly without routine. So it is important to have an examination routine before the examination. The examination routine helps the students a lot in their studies. For example, if you know the day of the examination, the students have the opportunity to prepare for the subject. So if we can easily get the examination routine online then it is more convenient. Online examination routine is a very crucial activities for any education and training institutes to conduct end-of-term examination which helps to optimize use of time slot and total exam duration. Currently most of institutes are doing their exam routine manually which is time consuming. Exam course overlapping, which means a student has more than one exam schedule in a certain time period, is a frequent incident for a term exam routine which is very challenging to avoid in manual routine. It will be able to manage examination routine of the department by modern computer. It will help to provide all the information of the exam schedule of the department in a quicker process successfully. This system makes easy to use the manual system. Online examination routine system can lead to error free, secure, reliable and fast management system. It can be used from anywhere anytime as it is a web based application. The long lockdown for the COVID-19 pandemic has closed schools, college, university and other educational institutions. Now our education system is dependent on online. So the online examination routine for online exams is time consuming for this period. This proposed system will have two part. They are user part and the administrator part. User must register themselves before login into the system. The users were easily able to view the routine from the systems. The administrators control the whole exam routine management system. In this proposed system I used hypertext markup language (HTML), Object oriented hypertext preprocessor (OOP PHP), cascading style sheet (CSS), Bootstrap, JavaScript, JQUERY, asynchronous JavaScript and xml (AJAX) as the web programming language and my structured query language (MYSQL) as the database server . I also used sublime text software as a text editor and Mozilla Firefox as a web browser.
PREDICTING STUDENTS PERFORMANCE THROUGH INTERNET USAGE BY ARTIFICIAL NEURAL NETWORK
(2021-01-30) RABEYA KHATUN RINKY
Students academic performance primarily depends on their internet usage for various activity purpose. Predicting students academic success is critical for educational institutions. Because strategic programs can be planned in improving or maintaining students’ performance during the period of their studies. The estimation in this study is done by a multilayer perceptron neural network model. 18 parameters which contain students internet usage data captured by a questionnaire chosen as input layer parameters. Hidden nodes will be determined experimentally. The output level values which define success of the students. The Back-Propagation algorithm is used for training of ANN. The mean squares of the errors are used as a performance (error) function with its goal set to zero. In conclusion, the application done with comparison with other ML algorithms. It is recommended that a research with same parameters would be better results with higher participation. In this paper we perform our experiment for school, college and university students which helps us to indicate them separately.
ONLINE SYSTEM DEVELOPMENT FOR EDUCATION, MEDICATION, AGRICULTURE AND RELIEF WORK AT PANDEMIC TIME (COVID-19 PERIOD)
(2021-02-20) MD. KAWSAR RAHMAN
This project is about online system development for education, medication, agriculture and relief work at pandemic time (covid-19 period). Issues like education, people's health, food security, agriculture, economic development, child marriage, women empowerment, youth empowerment, poverty and social justice, natural disasters, relief, hunger crisis, refugee crisis, organize awareness camps on education, health, agriculture & sanitation etc. are on main focus among others. There are four fields in this project– Edu-Care (Neuron Educational Support Center), Medi-Care (Neuron Medical Support Center), Agri-Care (Neuron Agricultural Support Center) and Relief-Care (Neuron Relief Support Center). This project describes an organization named “Neuron Group” where students will receive the highest quality education. They will have the opportunity to study with the most talented doctors and engineers of the country. This project is to keep the students in their studies at pandemic time (covid-19 period) with the help of our website and social media such as facebook, twitter and instragram. In the district where the "Neuron Group" will have a branch, we will find the most meritorious students in the district through the "Talent Exploration Admission Test” and arrange scholarships for them. The "Neuron Group" will also contribute to the medical field through Medi-Care. In remote areas of the country where people are deprived of medical services, they will get completely free medical services. One day a week our team of specialist doctors will go to the remote areas of each upazilla of the district where the "Branch of Neuron Group" will be to provide medical services. The "Neuron Group" is also committed to contributing to Agriculture. If the farmer survives, the country will survive. "Neuron Group" has launched "Agri-Care" for farmers. The farmers of the country will get this service completely free of cost. One day a week, a team of our expert agriculturists (having completed Honors-Masters from Bangladesh Agricultural University) will go to the agriculture-dominated areas of each upazilla of the district where the "Neuron Group" will have a "branch to provide Agricultural Services". The "Neuron Group" will also work to alleviate hunger and poverty. In the district where the "Neuron Group will have a branch", a list of rational poor and destitute based on the wards of each upazilla of the district will be prepared and they will be given food aid from time to time. The future of Bangladesh belongs to the younger generation. All of us have to do our bit to get them involved in improving the lives of the rural poor. If we do not do so, there will be serious social conflicts. Unless we can provide basic amenities so that the rural poor can live a meaningful life, we will never become a great nation. This is a great challenge for all youngsters and it is my dream that they will take it up so as to make Bangladesh a better place to live and work. Keywords: Neuron group, Edu-Care, Medi-Care, Agri-Care, Relief-Care Development, Poverty, Justice, Disasters, Refugee.
PREDICTION OF DENGUE OUTBREAKS IN PERSPECT OF BANGLADESH USING ARTIFICIAL INTELLIGENCE
(2021-03-20) JONY AKTER
Dengue Fever is a disease that has grown worldwide in the last few years. The information about the patients can be maintained with clinical documents. By keeping huge volume of clinical documents we can easily predict the occurrence of dengue disease in the patients. Dengue is considered to be one of the vital diseases which are spreading in more than 110 countries. It is a vector borne disease caused by the mosquitoes of female Aedes Albopictus and Aedes Aegypti which are well suited human environment. With nearly 45,000 cases reported all over Bangladesh in the last year. Dengue fever has become a major health hazard in Bangladesh over the past few years. Several studies show that which variable is related to the disease, however, as far as we know there is no effective study in Bangladesh that reveals this relation. This research shows the accuracy of different algorithms of Artificial Neural Network (ANN) to predict Dengue outbreaks. Firstly, data is collected from different hospitals, and then data is normalized. Data is analyzed to see the infection rate of different parameters. Then data is splitted for training and testing and finally find the best accuracy for different Multi-layer perceptron algorithms such as Scaled Conjugate Gradient (SCG), Levenberg–Marquardt (LM) based on back propagation algorithm and Learning Vector Quantization (LVQ). In this work, an analysis of the influence of variables is performed and shows the efficiency of the neural networks is used to predict the number of disease cases. Accuracy of SCG, LM and LVQ algorithm is 87.1%, 95% and 90.3% with MSE 0.137, 0.0241 and 0.0967 respectively. And decision tree algorithm gives 98.92% in training stage but 90% accuracy gives in validation and testing. LM outperforms with minimum MSE than other algorithm. Thus, this work finds an efficient prediction model for dengue cases for districts of Bangladesh.
IOT BASED HOME MANAGEMENT SYSTEM
(2021-03-30) FARSIM MAHMUD
Internet of Things (IoT) is the network of interconnected devices, digital machines, home appliances and other objects embedded with sensors, software, switches and connectivity which enable these things to connect to a network and collect and exchange data. The system creates the scope of connecting the non-internet-enabled physical devices and machines to be connected over the internet and remotely monitored and controlled. Home automation system uses the portable devices as a user interface. They can communicate with home automation network through an Internet gateway. This project intends to create architecture for home automation using near field and mobile communication along with a mobile application. The basic architecture or framework consists of connecting devices which will use protocol (WiFi or ZigBee) to connect Edge gateway and cloud stores the data information using backend storage system. Along with smart control of the appliances in our project we are focusing to reduce excess energy consumption by remotely controlling the devices and to maintain appliances for consumer’s convenience. Keywords: IOT, HAN, EMS, HEMS.
ANALYSIS OF MOBILE PHONE RADIATION EFFECT ON HUMAN BODY USING SPECIFIC ABSORPTION RATE20
(2021-03-30) SAGAR MAHMUD
The use of mobile phones is rising everyday both in civic and rustic areas in Bangladesh. Every mobile phone disperses electromagnetic energy. This radiation or electromagnetic wave can penetrate into the human body. Specific absorption rate and change in temperature are the vital parameter to find the dominant effects on the human body. Many researchers have done a lot of work on the effects of radiation for his or her country. But in Bangladesh, no visible work has been done yet. The importance of the health hazards due to radiation from the mobile phone has not been understood among the common people. Because it cannot be seen, felt or smelt and it is very hard to realize the evil part. Importance of mobile phone cannot be ignored because it’s helps to keep in touch with family, friends and others to perform various tasks. This paper explores the radiation impact of mobile phones. Mathematical equations are used to evaluate the specific absorption rate and change in temperature at skin, fat, bone, brain, eye, muscle tissues at the frequency of 800MHz, 900 MHz, 1800 MHz, 2100 MHz, 2.5GHz, 2.6GHz, 3.4GHz, 3.5GHz, and 3.6GHz respectively. The calculations are performed at different distances and exposure times of mobile phone. A simple radio frequency detection circuit has been designed to find the radiated power of different frequency. The highest specific absorption rate is calculated for skin, brain, eye tissue. Child tissue absorption rate is higher than the adult. When the radiated power of mobile phone is high the specific absorption rate for different tissue crosses the safety limit. This paper also recommends the ways to diminish the effects of SAR. It is suggested that these methods will decrease the health risks. This work will be very helpful to understand the bad effect of using mobile phones and the way of reducing this effect.
PREDICTING STOCK MARKET PRICE BY USING ARTIFICIAL NEURAL NETWORK TRAINED WITH FOUR DIFFERENT ALGORITHM: A PILOT STUDY OF 15 BANGLADESHI COMPANY
(2021-03-30) MD FURKANUZZAMAN
Stock market price prediction is now a popular and important topic in financial and academic studies because stock market plays a vital rule in economy. Stock market price prediction is the act of trying to determine the future value of company stock. Stock market prices are actually time-series data and Artificial Neural Networks (ANNs) have the ability to find non-linear correlations between time-series data which makes it the best approach to predict stock market prices. Many researchers working on this topic and try to find the best algorithm with using stock market dataset which is suitable for predicting stock price. In this research historical data from Dhaka Stock Exchange is used to train and predict the price by using ANN. The Artificial Neural Network (ANN) is implemented by using multilayer Feedforward backpropagation model. In this paper fifteen companies six years data have been analyzed. To predict the specific result, the model has been trained in four different algorithm with change their parameter. Number of hidden layer, hidden neuron and percentage of training data have been change to get better output. After the training and testing process the predicted values are compared with the real data to find the accuracy. The trained network with the highest accuracy rate will able to predict the best possible price of the stock market.
CLASS ROUTINE DESIGN SYSTEM AND EXAM HALL INVIGILATION MANAGEMENT
(2021-03-30) RATUL PROSAD
This Project name is “Class Routine Design System and Exam Hall Invigilation Management”. This is a web based application. In Class Routine Design System mainly, focusses on creating automatic class routines with teacher’s requirements. Most universities handle this allocation process with a manual procedure. The manual procedure like this gives way to various challenges and is inclined to mistakes. A better approach to reliably schedule class routine is to utilize a computer assisted web-based system. This project has mainly two parts or two panel, Admin panel & User panel. In admin panel we get some information like courses information, teacher’s information, room’s information etc. We can Update, Delete & Add this information’s. There have teacher’s requirement for creating class routine and semester wise course offer distribution for teachers. We can update and view all this field in admin panel. After that we made a class routine using all of this field. In another panel is user panel. In this part we get all of information about course, teacher’s and rooms. In this panel we can see all this information & routine. Update, add and delete option in this panel also included. Both of this panel, we get routine separate by days, teacher’s and semester wise. We create this application for genetic algorithm, python. We create this application for reduce the complexity of routine creation manually, to reduce time to solve a problem and to reduce routine version. In Exam Hall Invigilation Management, proposes an improved algorithm to achieve automatic examination arrangement for invigilator based on greedy method, the algorithm can support the priorities better, set maximum frequency of invigilating and satisfy other personalization examination arrangement requirements, and also it can configure to allocate any numbers of invigilators in different examination halls in such a way that each invigilator will get equal amount of duties. This algorithm has written and implemented in java script language. Keywords: Routine Allocation System, Web Based Application, Invigilator, Examination.

Browse

Browsing Masters Thesis by Issue Date

Results Per Page

Sort Options