http://rulrepository.ru.ac.bd/handle/123456789/65 2026-04-07T21:44:56Z 2026-04-07T21:44:56Z Islam, Md. Saiful http://rulrepository.ru.ac.bd/handle/123456789/1113 2023-08-30T07:32:22Z 2020-01-01T00:00:00Z

Construction of Statistical Visual Descriptors for CBIR Exploiting Time-inhomogeneous Markov Chain Model Islam, Md. Saiful Markov stationary features (MSF) based on homogeneous Markov chain model for content-based image retrieval (CBIR) is getting popularity nowadays. It not only considers the distribution of colors that the histogram method does, but also characterizes the spatial co-occurrence of histogram patterns. However, handling a large scale database of images with large degree of heterogeneity, a simple MSF method is not sufficient to discriminate the images. The method does not capture sufficient spatial co-occurrence information as required for large databases. To overcome the shortcoming in this research, two extended methods namely multichannel nonhomogencous MSF (MCN-MSF) and multi-resolution nonhomogeneous MSF (MRN-MSF) based on original MSF are proposed. In both cases, the concept of nonhomogeneous Markov chain model is exploited to construct the features. For the first method, we incorporate spatial co-occurrence structures of different color channels of an image by applying the time inhomogeneous (nonhomogeneous) Markov chain model. For the second method, by exploiting the similar nonhomogeneous model, we incorporate the spatial cooccu1Tence information more consistently by mapping the image with different resolution. Without compromising effectiveness and robustness, the methods proposed in this paper keeps the features level simplicity. Widely recognized WANGl000 and Corell0800 databases arc used to evaluate and compare the performances of the proposed algorithms with the existing methods. The experimental results show that both methods significantly improve the performances compare to the existing methods. The results also prove that second method is more effective for large databases. This Thesis is Submitted to the Department of Computer Science and Engineering , University of Rajshahi, Rajshahi, Bangladesh for The Degree of Doctor of Philosophy (PhD)

2020-01-01T00:00:00Z Rokanujjaman, Md. http://rulrepository.ru.ac.bd/handle/123456789/1048 2023-08-07T04:59:22Z 2021-01-01T00:00:00Z

Person Identification Using Gait Biometric with Challenging Clothing and Speed Cofactors Rokanujjaman, Md. Biometrics are the entire class of technologies and techniques utilized to identify the individual by using their physiological or behavioral attributes. The way of human walking, the most emergent and unique biometric signature allows automatic gait-based person identification. Gait identification task becomes more difficult due to the change of appearance by different cofactors (e.g., walking speed, shoe, surface, carrying, view, clothing and etc.). The main goal of this thesis is to develop novel methods to address the two most frequently happening covariate factors clothing and carrying condition and walking speed changes for gait recognition. These cofactors may affect some parts of gait while other parts remain unchanged and can be used for recognition. An algorithm is proposed to define which parts are more effective and which parts are less effective for cofactors like walking speed, clothing, carrying objects etc. It is found that, for clothing and carrying conditions the upper part of the body is more affected whereas for walking speed changes the lower body part is more affected. During the process of finding the effective body parts, the whole body is divided into small segments where each segment is a single row in this work. Based on positive and negative effect of each segment in terms of recognition rate, we define the whole gait into five unequal parts for clothing and carrying conditions. Usually, the dynamic areas (e.g., legs, arms swing) are comparatively less affected than static areas (e.g., head, torso) for different cofactors in appearance-based gait representation. To give more emphasis on dynamic areas and less on static areas, frequency-domain gait entropy termed as EnDFT representation is proposed and used as gait features. Experiments are conducted on two comprehensive benchmarking databases: The OU-ISIR Gait Database, the Treadmill dataset B with huge clothing variations and CASIA Gait Database, Dataset B with clothing and carrying conditions. The proposed method achieved the recognition rate 72.78% for OU-ISIR and 77.69% for CASIA gait database at rank-1 and presented better results in comparison with other existing gait recognition approaches. This Thesis is Submitted to the Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh for The Degree of Doctor of Philosophy (PhD)

2021-01-01T00:00:00Z Chowdhury, Utpala Nanda http://rulrepository.ru.ac.bd/handle/123456789/1035 2023-08-06T05:48:40Z 2021-01-01T00:00:00Z

Machine Learning and Bioinformatics Models to Identify the Genetic Link of Neurological Diseases Associated With the Causal Risk Factors Chowdhury, Utpala Nanda Neurological diseases (NDs) are causing burgeoning burden to the patients, healthcare sector and the entire society. Hundreds of millions of people are currently a ected by various NDs worldwide and the number is increasing very rapidly. The most frequent categories include Alzheimer's disease (AD), Parkinson's disease (PD), epilepsy, Multiple sclerosis (MS), stroke and other cerebrovascular disorders, migraine and other headache, malignant brain tumors such as Glioblastoma multiforme (GBM) etc. Despite numerous research initiatives, preventive and therapeutic options for most of these NDs still remain very limited. Taking AD as an example, fully e ective preventive strategies are unavailable till now. Preventive measures usually comprise primary prevention based on risk reducing by identifying in uential factors and secondary prevention through early detection and abatement of the disease at initial stage. But the inadequate epidemiological knowledge of AD risk factors and absence of early premortem accurate diagnosis has foiled AD prevention. However, better insight about the co-occurrence of other neurological complications with AD can yield preventive and therapeutic advancement. On the other hand, enhanced understanding about the factors that impacts the response to the treatment could prolong the survival period. For instance, GBM is such an ND with shorten survival period provided the rst line treatment include brain surgery followed by chemotherapy and radiotherapy. In this context, research initiatives to mitigate the information gap regarding how the causative factors a ect the cell pathways altered in NDs and their comorbidities can alleviate the disease burden. Availability of high throughput technologies including microarray and next-generation sequencing (NGS) of tissue mRNA to analyse large-scale transcriptomic data have excelled various bioinformatics methodologies as promising tools in biomedical research eld. These approaches include di erential gene expression analysis, protein-protein interactions (PPIs), gene ontology (GO), metabolic pathway and regulatory factor analysis. Genetic inspection into the transcriptomic data through these tools yields better insight into the molecular pathogenesis of any health condition in junction with its causative factors and related complications. In addition to this, the exponentially increasing amount of accessible biological data has made machine learning techniques as promising means of discovering hidden genetic knowledge. In this thesis, we presented bioinformatics and computational frameworks based on transcriptomic data and machine learning based survival prediction models. This Thesis is Submitted to the Department of Computer Science and Engineering , University of Rajshahi, Rajshahi, Bangladesh for The Degree of Master of Philosophy (MPhil)

2021-01-01T00:00:00Z Hossain, A.K.M. Akhtar http://rulrepository.ru.ac.bd/handle/123456789/546 2022-06-08T03:52:43Z 2006-01-01T00:00:00Z

Fingerprint Identification System Using Artificial Neural Computing Models Hossain, A.K.M. Akhtar This thesis presents the idea of features extraction technique of an off-line fingerprint. Traditionally, minutiae, core, delta, crossover, bifurcation, ridge ending, pore, island, enclosure, bridge, dot features of fingerprints are considered to identity a person. These features are available when the fingerprint images are good. The great demerit of those existing techniques is that, they fail to extract the features of poor fingerprint images. If the fingerprint image is blurred then it is difficult to extract those features from the fingerprint. In this research work is fully surveyed all the available methods and different problems related with poor fingerprint identification. Taking into consideration the merits and demerits of the available methods, a new method for feature extraction technique for the poor fingerprint images is proposed. This research is specially dealing with the problem of poorly input fingerprint identification. For these poor types of fingerprint images, features can be extracted by using proposed grid mapping feature extraction techniques. In this process, the fingerprint is processed through Grid Mapping Features (GMF) extraction with fixed square/rectangle cells, such as 16X16 square/rectangle areas. If one small square/rectangle cell of the grid map contains more than 45-55% black pixels, then its digital value is considered as I otherwise 0. These digital values are applied to the input of the neural network for training purpose using Minimum Distance Error Rate Back Propagation (MDER-BP) algorithm, which is proposed in this research work. During the training period, the values of the nodes are updated and stored in a relational knowledge base. The matching part of the system identifies the Fingerprint of a person with the help of the previous experiential values, which were stored in the relational knowledge-base of the system. The proposed Grid Mapping Feature-based fingerprint matching system gives an acceptable accuracy in off-line identification system for poor fingerprint images. It is also shown that the proposed MDER-BP Algorithm also possesses capability for training and matching the poor fingerprint images. Several factors are responsible for getting correct result through neural computing techniques. The convergence of the solution depends heavily on initialization with random numbers and accuracy of the results depends on (i) spread factors (ii) learning rates, (iii) iterations and (iv) hidden units. Finally, it has been concluded that for recognition of fingerprint using the MDER-BP Algorithm the system shows better efficiency with respect to Adaptive Resonance Theory-2 for the poor fingerprint images. This thesis is Submitted to the Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh for The Degree of Doctor of Philosophy (PhD)

2006-01-01T00:00:00Z