KUET Institutional Repository (Khulna University of Engineering & Technology)
Not a member yet
1045 research outputs found
Sort by
Development of Multiple Class Human-Computer Interaction System using Machine Learning Algorithm for Eyeball Movement
No full textThis thesis is submitted to the Department of Biomedical Engineering, Khulna University of Engineering & Technology in partial fulfillment of the requirements for the degree of Master of Science in Biomedical Engineering, August, 2019.Cataloged from PDF Version of Thesis.Includes bibliographical references (pages 97-104).Modern technologies in the field of Biomedical Engineering are flourishing astonishingly in recent times. Human-computer interaction (HCI) is one of the newest additions in this field. It is the study of the way people interact with computers and how the computers are or are not developed for interacting with human successfully. Electrooculography (EOG) machine can be used as HCI device. It is a technique for measuring the corneo-retinal standing potential which is present between the front and the back of the human eye. Pairs of electrodes are generally attached either above and below the eye or to the left and right of the eye to detect the eye movement. A potential difference occurs between the electrodes. Considering that the resting potential is constant, the recorded potential is a measure of the eye's position. EOG device can pick up these resting potentials while moving the eyeball in different directions. Data classification is important for HCI systems. It is to identify a new observation which belongs to a set of categories. Classification is done based on a training dataset having observations whose category membership is familiar. Various algorithms can be used to classify bio-signal data like ECG, EEG and EOG. These algorithms are called machine learning algorithm. It is a set of mathematical approaches to teaching computers to train based on large amount of data without step by step human instruction. In this research, EOG data are classified using machine learning algorithm to develop a multiple class HCI system.
EOG data for different directional eyeball movement is acquired with the help of Biopac MP3X Acquisition unit. By placing the disposable surface electrodes on the right position of the skull and connecting all the leads and wires to the proper channel, the setup is ready to pick up the EOG data. Subjects are instructed to follow the LED sequence in the navigational setup. The data of 7 subjects aged between 22 to 48 years are taken for this experiment. The data is then saved using Biopac Student Lab Software and then preprocessed to prepare an EOG dataset for classification. With Weka 3.9.2, the classification procedure is done on the prepared dataset. Six classification algorithms i.e. naïve bayes, support vector machine, logistic regression, k-nearest neighbor, random forest and bagging are applied on the dataset. Comparison is shown among the algorithms based on different parameters. In the EOG dataset, features are also added which can be correlated with the classes. This correlation method is performed in IBM SPSS Statistics 25 software to find the most significant features related to the class.
From the classification result, the accuracy of the different classifiers are obtained. The accuracy of Naïve Bayes is 30.7692%, SVM is 30.7692%, Logistic regression is 53.8462%, KNN is 7.6923%, Random forest is 84.61% and Bagging is 92.31% respectively. From the comparison among the classifiers based on different parameters, bagging has the highest and KNN has the lowest accuracy among them. The proposed method is then compared with other researches where it is seen that other methods applied only two or three algorithms but in the proposed method six machine learning algorithms are used. It is observed that bagging is more suiTable algorithm for EOG data than other algorithms used in the mentioned related works. As for the correlation, only the chi-square test is performed as Fisher’s exact test can be performed for 2x2 matrix whereas there are 9 classes in the dataset. From the chi-square test result, it is seen that the mean of channel 1 (horizontal channel) and channel 2 (vertical channel) used to acquire EOG data for eyeball movement are the most significant features. These two featuress are directly related to the classes.Mubtasim Rafid ChowdhuryMaster of Science in Biomedical Engineerin
Pyrolysis of Organic Waste: A Way to Solid Waste Management and Extraction of Fuel
No full textThis thesis is submitted to the Department of Energy Science and Engineering, Khulna University of Engineering & Technology in partial fulfillment of the requirements for the degree of Master of Science in Engineering in the Department of Energy Science and Engineering, June 2019.Cataloged from PDF Version of Thesis.Includes bibliographical references (pages 89-96).Bangladesh is a developing country and is one of the most densely populated countries in
the world. Her per capital energy consumption is also low compared to others. At present,
the energy demands are becoming more acute day by day. Environmental issues and
energy scarcity led the government of the developing countries to think about new and
alternative energy resources. Renewable energy resources may be one kind of alternative
energy. Various waste materials derived from agriculture or industrial sectors can
contribute to these issues. Tyre wastes, mixture of organic and inorganic materials, already
become potential source to derive liquid fuel as well as solid fuels by pyrolysis.
Shoe/sandal soles have similar compositions like tyres and also create environmental
pollution problems. Rubber containing wastes such as shoe/sandal soles are solid waste
which is non-biodegradable and with increased production of shoe/sandal, the volume of
waste soles will also be increased. Some typical problems are created to the environment
as well as to our surroundings by the disposal of such wastes. The dumping of waste
(shoe/sandal soles) in the drain is one of the main environmental issues in the
municipal/city areas of Bangladesh. Blockage of drain and generation of mosquitoes or
other bacteria are favored by the disposal of such wastes in unplanned manner. So,
deliberately this matters to the authority and researchers to manage these nonbiodegradable
waste materials (soles of shoe/sandal). So, a way to manage waste as well as
extraction of fuel may be a good solution to this problem.
Under the circumstances, extraction of fuel from shoe/sandal sole waste materials that
manages the environment, pyrolysis is the best way. It will indirectly help to manage such
non-biodegradable wastes, also low grade liquid fuels may be obtained. When waste
materials were pyrolyzed, they generate oil, char and gas, which are valuable. The oil has
sufficient calorific value and may be used to provide process energy and char may be used
as activated carbon or carbon black. So, they may be considered as a new raw material for
pyrolysis. In the present study, waste shoe/sandal soles were collected from the nearby local area of Jashore and Khulna city of Bangladesh were pyrolysed in a batch type
reactor.
Experiments on pyrolysis of shoe/sandal soles were conducted by varying the temperature
within the range of 200-250oC at every 25oC. The batch type fixed-bed pyrolysis system
was constructed and installed in the Heat Engine Laboratory of Department of Mechanical
Engineering, Khulna University of Engineering & Technology. The maximum yield of
pyrolytic oil and pyrolytic solid from waste shoe/sandal soles was 36.0 % (by weight) and
53.0 % (by weight) with the feed size of 0.75 × 0.50 cm and 1.25 × 1.0 cm respectively
with loading size of 1.7 kg.
The properties of pyrolytic oil obtained from waste soles of shoe/sandal such as density,
flash point, boiling point and pour point were measured and the respective values are in the
range of 0.877 – 0.934 g/cm3, 96 - 108oC, 153 – 158oC and -11 to -12.5oC respectively and
the gross calorific value (GCV) is around 35 - 38 MJ/kg. The gross calorific value (GCV)
of pyrolytic solid is around 11 - 16 MJ/kg which is comparable to same of peat (12 to 16
MJ/kg) and lignite coal (13 to 16 MJ/kg). The concentrations of elemental compositions of
pyrolytic liquid obtained from shoe/sandal sole pyrolysis were found to be almost 71.7%
for carbon, 10.9% for hydrogen, 1.12% for nitrogen, 0.50% for sulphur and 15.78% for
others at 200oC. The derived oil from pyrolysis of waste shoe/sandal soles were
investigated for FTIR four groups: alkane, alkenes, alkynes and aromatic compounds. The
results showed more aromatic hydrocarbons. The TGA analysis of the same shows that the
experimental curve is higher from 200 to 400ºC, when the rate of weight loss of
shoe/sandal sole pyrolysis is higher. The oil obtained from pyrolysis of shoe/sandal sole
wastes can be used as alternative fuel or chemical feedstock after some treatment. The
results show that these properties are similar to that of the low grade liquid fuels and thus
pyrolysis of such waste soles of shoe/sandal will reduce environmental pollution to some
extent as well as be an alternative source of energy.Farzana Yeasmin NipaMaster of Science in Engineering in the Department of Energy Science and Engineerin
A Study on the Effect of Seam, Color and Boundary Priors on Salient Region Detection
No full textThis thesis is submitted to the Department of Computer Science and Engineering, Khulna University of Engineering & Technology in partial fulfillment of the requirements for the degree of Master of Science in Computer Science and Engineering, December 2019.Cataloged from PDF Version of Thesis.Includes bibliographical references (pages 57-62).Being the best creation of almighty Allah, human beings have the ability to analyse a visual scenario. They not only see an image, but can judge the importance of different parts of a visual area. They can easily differentiate a running car from its background, can tell the color of different objects in an image and can focus attention to some important parts of a visible scene. The value of this visual power of human is easily understood if one thinks about these. Achieving this wonderful human quality using machine is one of the most precious goals of today’s scientific researches. With the continuous advancement of imaging technologies, more and more visual data are being collected all over the world. But, a major portion of these data are left unprocessed. Image processing is used to process these types of visual data. For all image processing techniques, the initial goal is to find some target region for extracting information from the image. Saliency detection is the technique of computationally finding important regions of an image. It is usually done using the contrast information present in an image. Seam map is the combination of cumulative summation of energy values from different directions. In this thesis, a combined method is proposed which uses seam importance map along with boundary aware color importance map. Color importance map is the weighted average of different color channels of Lab color space. Some intermediate combinations which are closer to the proposed optimized version but differ in the optimization technique are also presented in this thesis. Several standard benchmark datasets including the famous MSRA 10k and ECSSD datasets are used to evaluate performance of the suggested method. The proposed saliency model has been compared with several state of the art methods for each dataset. The qualitative and quantitative results from those omparisons make things easier to understand. Besides that, comparison with those state of the art techniques and precision recall curves and F-beta values found from the experiments on several datasets prove the superiority of the proposed method. This robust saliency model can
improve almost all types of vision related applications including object detection, robotics, medical image analysis, content aware image resizing etc. In this research, the proposed architecture of saliency detection technique has been applied into a simple implementation of pedestrian detection. Its application has significantly improved the result of pedestrian detection in terms of performance and accuracy.Aminul IslamMaster of Science in Computer Science and Engineerin
Development of an Optimal Inventory Management System in Khulna Shipyard Limited- A Case Study
No full textThis thesis is submitted to the Department of Industrial Engineering and Management, Khulna University of Engineering & Technology in partial fulfillment of the requirements for the degree of Master of Science in Engineering in Industrial Engineering and Management, December 2019.Cataloged from PDF Version of Thesis.Includes bibliographical references (pages 46-47).Inventory, the key component of any organization is the stock of any goods or asset that are required for manufacturing or assembly of the product to maintain the plant. The fundamental function of an inventory system is to keep track of and maintain the inventory levels, determine both the order size and replenishing period. Inventory is directly related with the manufacturing cost. As a result, Inventories influence the most essential portion of current resources of a greater numbers of companies. Thus, sufficient amount of capital is tied up due to maintaining the inventories in bulk by the organization. Poor inventory management may cause under-stocking or over-stocking including higher operating cost of the items. Thus, a firm ignoring the control and monitoring of inventories might be at risk of its ultimate profitability and may collapse in the long run. As a result, it is clearly necessary to manage inventories effectively and properly for the avoidance of unnecessary investment.
In the study it was found that Khulna Shipyard Limited frequently fails to maintain inventory level/ stock for the regular consumption of raw materials to meet the lead time of the demand. Demand for replenishment of inventory items are placed when it is required. The shipyard follows the traditional method of purchasing the raw materials and other items. As a result, the shipyard is unable to maintain delivery schedule of the project due to shortages of required materials and also due to the late delivery of proper materials from the suppliers. On the contrary, the plant also faces over stocking of materials in the warehouse. Both these situations act as a catalyst to increase the total inventory expenditure of the shipyard. Besides, the workers have to work in extra time (overtime) to finish the job quickly. Ultimately, the shipyard can not maintain the desire quality of the finished product and production cost also increases. As the ship cannot undock within the schedule time and the construction yard is engaged, the shipyard cannot dock the ship under pipeline within predetermined schedule. As a result, customer dissatisfaction may raise due to inferior quality, late delivery, failure to dock and high production cost of ships/ product. Moreover, this shipyard may lose their customer day by day. Thus the above discussion stated that, there is a room for improvement
to identify the procedure of managing and maintaining inventory at khulna shipyard limited. One of the most important goals in inventory management decision is how much inventory should be made and when to submit an order. If a firm procures higher quantities of inventory, carrying cost also increases. On the other hand, if the firm purchases less quantities, more orders to be placed which increases ordering cost. Therefore, the order quantity at a particular time should be controlled by balancing the ordering and carrying cost. Considering both the costs, EOQ model is applied to decide the optimal order quantity to be replenished at a specific order time for the optimization of carrying and ordering cost and also confirming the availability of material when required. In addition, ROP model provides information when to order the item. Safety stock policy can be adopted for providing protection against the variation and uncertainty in both lead time and demand.
It was observed that managing inventory at ship construction and repairs industry is more complicated due to the distinctive and uncertainty nature of demand. In this thesis, a sample for inventory items from a major workshop of khulna shipyard limited was identified and demand data for these items was collected. Accordingly, required data for cost calculation was gathered to implement EOQ, ROP and safety stock for the selected inventory items. Finally, the thesis work has been completed with several specific recommendations for the management of Khulna Shipyard Limited and suggestions for carrying out future research.Md. Safiq UzzamanMaster of Science in Engineering in Industrial Engineering and Managemen