Botho University Library

Botho University Institutional Repository

Theses, dissertations, faculty research and archives from Botho University.

Quick Access

Everything you need, one tap away

Browse by Title Browse by Author Browse by Subject Submit an Item

Borrow · Botho University Library

The Library Catalogue

Books, journals and course reserves across all campuses. Check what is on the shelf, place a hold and manage your loans.

New Arrivals Most Borrowed Course Reserves My Account

Enter the catalogue

About the Botho University Library

The Botho University Library supports learning, teaching and research across the University’s campuses in Botswana, Lesotho, eSwatini and Ghana. Our collections span business, computing, engineering, health sciences, education and more, available to students, staff and researchers, on campus and online.

Explore the Collection University Website

Opening Hours

Mon – Fri8:00 – 20:00
Saturday9:00 – 13:00
SundayClosed

Ask a Librarian

Explore by Subject

Curated areas across Botho University

Now showing 1 - 5 of 9

Recent Submissions

Memetic Optimization with Cryptographic Encryption for Secure Medical Data Transmission in IoT-Based Distributed Systems
(2021) Srinath, Doss; Paranthaman, Jothi; Gopalakrishnan, Suseendran; Duraisamy, Akila; Pal, Souvik
In the healthcare system, the Internet of Things (IoT) based distributed systems play a vital role in transferring the medical-related documents and infor mation among the organizations to reduce the replication in medical tests. This datum is sensitive, and hence security is a must in transforming the sensational contents. In this paper, an Evolutionary Algorithm, namely the Memetic Algo rithm is used for encrypting the text messages. The encrypted information is then inserted into the medical images using Discrete Wavelet Transform 1 level and 2 levels. The reverse method of the Memetic Algorithm is implemented when extracting a hidden message from the encoded letter. To show its precision, equiva lent to five RGB images and five Grayscale images are used to test the proposed algorithm. The results of the proposed algorithm were analyzed using statistical methods, and the proposed algorithm showed the importance of data transfer in healthcare systems in a stable environment. In the future, to embed the privacy-pre serving of medical data, it can be extended with blockchain technology
A User-Intelligent Adaptive Learning Model for Learning Management System Using Data Mining And Artificial Intelligence
(International Journal for Innovative Research in Science and Technology, 2015-03) Sivakumar, Subitha; Venkataraman, Sivakumar; Gombiro, Cross
Entire world is revolving towards digital space as a result of the Internet and other emerging web technologies are helping the society to reach the universe. ICT and e-learning are growing radically fast and have captured a major role in higher educational systems. To develop the coast-to-coast purposes, institutions are changing the teaching style from chalk and talk to Learning Management System (LMS), called e-learning systems. Impact of e-learning introduces various delivery methods for teachers and different platforms to learn for learners. Teaching through LMS is most challenging because the difference in the learning styles and the nature of the course. Materials used for delivering the course are mostly static for all types of learners. Students are learning from the LMS tools, but not most effectively. To overcome this issues, the author(s) are recommending a new user intelligent adaptive learning model to be used in LMS. This allows the model to identify the learners learning style and endorses the appropriate learning materials for the learners. This method of delivering will be effective and efficient for different LMS learners.
A Model to Provide a Reliable Infrastructure for Cloud Computing
(World Congress on Engineering, 2012-07-04) Srinivasan R, Srivaramangai.P
The cloud computing offers dynamically scalable resources provided as a service over the Internet. It promises the drop in capital expenditure. But practically speaking if this is to become reality there are still some challenges which is to be still addressed. Amongst, the main issues are related to security and trust, since the user's data has to be released to the Cloud and thus leaves the secured area of the data owner. The users must trust the providers. There must be a strong trust relationship exist between the service providers and the users. This paper provides a model based on reputation which allows only reliable providers to provide the computing power and the resources which in turn can provide a reliable infrastructure for cloud computing.
Efficient Active Learning Constrains for Improved Semi-Supervised Clustering Performance
(International Journal of Computer Science and Electronics Engineering, 2015) Eswaraprasad, Ramkumar; Vengidusamy, Shanmugam
This paper presents a semi supervised clustering technique with incremental and decremented affinity propagation (ID-AP) that structures labeled exemplars into the AP algorithm and a new method for actively selecting informative constraints to make available of improved clustering performance. The clustering and active learning methods are both scalable to large data sets, and can hold very high dimensional data. In this paper, the active learning challenges are examined to choose the must-link and cannot-link constraints for semi-supervised clustering. The proposed active learning approach increases the neighborhoods based on selecting the informative points and querying their relationship between the neighborhoods. At this time, the classic uncertainty-based principle is designed and novel approach is presented for calculating the uncertainty associated with each data point. Further, a selection criterion is introduced that trades off the amount of uncertainty of each data point with the probable number of queries (the cost) essential to determine this uncertainty. This permits us to select queries that have the maximum information rate. Experimental results demonstrate that the proposed ID-AP technique adequately captures and takes full advantage of the intrinsic relationship between the labeled samples and unlabeled data, and produces better performance than the other considered methods Empirically evaluate the proposed method on the eight benchmark data sets against a number of competing methods. The evaluation results indicate that our method achieves consistent and substantial improvements over its competitors.
Face Recognition Using Dual Tree Complex Wavelet Transform
(Society of Digital Information and Wireless Communications, 2012) Shanmugasundaram, Suresh; Chidambaram, Divyapreya
We propose a novel face recognition using Dual Tree Complex Wavelet Transform (DTCWT), which is used to extract features from face images. The Complex Wavelet Transform is a tool that uses a dual tree of wavelet filters to find the real and imaginary parts of complex wavelet coefficients. The DT-CWT is, however, less redundant and computationally efficient. CWT is a relatively recent enhancement to the discrete wavelet transform (DWT). We show that it is a well-suited basis for this problem as it is directionally selective, smoothly shift invariant, optimally decimated at coarse scales and invertible (no loss of information). Our face recognition scheme is fast because of the decimated nature of the DTCWT. Dual Tree methods are based on image at different resolution. Normalization is done to reduce dimensionality which will reduce memory problem and computation time. Here Principal Component Analysis which is a linear dimensionality reduction technique, that attempt to represent data in lower dimensions, is used to perform the face recognition. PCA is applied that deals with the decomposition of the training set into the Eigenvectors called Eigen faces. Various discrimination analyzes such as, Euclidean, L1, L2 and Cosine similarity are used for the recognition of face images.