IJMSC Vol. 6, No. 4, Aug. 2020
Cover page and Table of Contents: PDF (size: 1040KB)
Today unauthorized access to sensitive information and cybercrimes is rising because of increasing access to the Internet. Improvement in software and hardware technologies have made it possible to detect some attacks and anomalies effectively. In recent years, many researchers have considered flow-based approaches through machine learning algorithms and techniques to reveal anomalies. But, they have some serious defects. By way of illustration, they require a tremendous amount of data across a network to train and model network’s behaviors. This problem has been caused these methods to suffer from desirable performance in the learning phase. In this paper, a technique to disclose intrusions by Support Vector Regression (SVR) is suggested and assessed over a standard dataset. The main intension of this technique is pruning the remarkable portion of the dataset through mathematics concepts. Firstly, the input dataset is modeled as a Directed Graph (DG), then some well-known features are extracted in which these ones represent the nature of the dataset. Afterward, they are utilized to feed our model in the learning phase. The results indicate the satisfactory performance of the proposed technique in the learning phase and accuracy over the other ones.[...] Read more.
When we are given a data set where in based upon the values and or characteristics of attributes each data point is assigned a class, it is known as classification. In machine learning a very simple and powerful tool to do this is the k-Nearest Neighbor (kNN) algorithm. It is based on the concept that the data points of a particular class are neighbors of each other. For a given test data or an unknown data, to find the class to which it is the neighbor one measures in kNN the Euclidean distances of the test data or the unknown data from all the data points of all the classes in the training data. Then out of the k nearest distances, where k is any number greater than or equal to 1, the class to which the test data or unknown data is the nearest most number of times is the class assigned to the test data or unknown data. In this paper, I propose a variation of kNN, which I call the ANN method (Alternative Nearest Neighbor) to distinguish it from kNN. The striking feature of ANN that makes it different from kNN is its definition of neighbor. In ANN the class from whose data points the maximum Euclidean distance of the unknown data is less than or equal to the maximum Euclidean distance between all the training data points of the class, is the class to which the unknown data is neighbor. It follows, henceforth, naturally that ANN gives a unique solution to each unknown data. Where as , in kNN the solution may vary depending on the value of the number of nearest neighbors k. So, in kNN, as k is varied the performance may vary too. But this is not the case in ANN, its performance for a particular training data is unique.
For the training data  considered in this paper, the ANN gives 100% accurate result.
[...] Read more.
This study presents trend analysis and forecasting of water level in Mtera dam. Data for water level were obtained from Rufiji Basin Development Authority (RUBADA). The study analyzed trend of water level using time series regression while forecasting of water level in Mtera dam was done using Exponential smoothing. Results revealed that both maximum and minimum water level trends were decreasing. Forecasted values show that daily water level will be below 690 (m.a.s.l) which is the minimum level required for electricity generation on 2023. It was recommended that proper strategies should be taken by responsible authorities to reduce effects that may arise. Strategies my include constructing small dams on upper side of Mtera dam to harvest rain water during rainy season as reserves to be used on dry season. In long run Tanzania Electric Supply Company (TANESCO) should invest into alternative sources of energy.[...] Read more.
The amount of data that is transmitted across the internet is continuously increasing. With the transmission of this huge volume of data, the need of an encryption algorithm that guarantees the data transmission speedily and in a secure manner is a must. Hence, to achieve security in wireless networks, cryptography plays a very important role. In this paper, several hybrid combinations, which combines both symmetric and asymmetric cryptographic techniques to offer high security with minimum key maintenance is presented. This hybrid combination offers several cryptographic primitives such as integrity, confidentiality and authentication, thereby enhancing the security. Various combinations of Advanced Encryption Standard (AES), Elliptical Curve Cryptography (ECC) and Rivest, Shamir and Adleman (RSA) algorithms are used to provide hybrid encryption. Secure Hash Algorithm (SHA-256) is also used to provide authentication and integrity. The experimental results show that the proposed hybrid combinations gives better performance in terms of computation time compared to individual cryptographic schemes.[...] Read more.
Organisations need information security to reduce the risk of unauthorized information disclosure, use, modification and destruction. To avoid this risk and ensure security diverse solutions are available such as Cryptography, Steganography and Watermarking. Encryption changes the form of information but latter two hide records or watermark in some medium. This paper is an effort to explore one of the solutions i.e. Steganography. It is a mechanism of hiding secret information in text, image, audio or video carriers. Broadly, these are classified in various categories such as Spatial domain, Transform domain and Distortion Technique. This work intends to give an overview of above mentioned techniques in detail by comparing algorithms based on performance metrics such as Bhattacharyya Coefficient, Correlation Coefficient, Intersection Coefficient, Jaccard Index, MAE, MSE, PSNR and UIQI. After analysing the MATLAB simulation and comparison based on different performance metrics, LSB Substitution and Pseudorandom technique are best suited for generating highly matched stego image with respect to their cover image.[...] Read more.