Tresor Lisungu Oteko

Mr. Tresor Lisungu Oteko

Electrical & Electronic Engineering Technology, University of Johannesburg, Johannesburg, Gauteng, South Africa
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 July 2019 in IEEE Access
Verified
Journal Article
Open access
TOTresor Lisungu Oteko
Tresor Lisungu Oteko
MSMbuyu Sumbwanyambe
Mbuyu Sumbwanyambe
In recent years hyperchaos has found applications in several fields such as medicine and engineering. It has been applied in image-based applications which require reliable, fast, and robust security systems to store or/and transfer images. Given the increased use of images, there is a fundamental requirement among security in ensuring protection, confidentiality, privacy, integrity, and authenticity of such images. This, in essence, has become a major concern. Many preventive and protective algorithms, including chaos-based schemes, have been developed over the past years in trying to prevent directed attacks. However, many existing chaos-based encryption schemes have been successfully decrypted. One of the main reasons for these chaos-based image encryption schemes being successfully attacked is that the degree of randomness of the chaotic system used is not high enough to guarantee robust encryption. The key space lengths of many of the existing cryptosystems are not long enough to guarantee the desired security properties of chaos-based ciphers. Thus, the security level is lowered. In this paper, a selective image encryption algorithm based on 2D Discrete Wavelet Transform, Henon's Map and 4D Qi Hyper Chaos is proposed. This paper is developed such that 2D DWT is used to decompose the image into details and approximations, Henon chaotic map is used to shuffle the decomposed image pixels' positions. The shuffled image is further encrypted with the bit streams generated by Qi hyperchaos using XOR operation. The experimental results demonstrate that the proposed algorithm provides a large key space, high security, and resistance to different types of attacks. When compared to some existing algorithms, the performance of the proposed method displays a better performance with respect to security and encryption making it suited for real-time applications.
1

1 January 2019
Verified
Conference Paper
Closed access
TOTresor Lisungu Oteko
Tresor Lisungu Oteko
MSMbuyu Sumbwanyambe
Mbuyu Sumbwanyambe
With an ever increase usage of multi-media content, such audio, image and video across networks, image compression and security of content has become almost a need to users who would want to transmit over such networks. Transmitting over such networks, especially with images, may result in some information in an image being lost. For that reason good and efficient encryption methods are needed to store and transmit images while preserving the best imaginable quality features enhanced with security. This paper suggests or develops an efficient image compression-encryption scheme based on Discrete wavelet decomposition, SPIHT and Qi hyperchaos. Pseudo-random numbers generated from Qi hyper chaos and which are in line with the Federal Information Processing Standards (FIPS) and National Institute of Standards and Technology (NIST) were used in this study. The random numbers were used to change the image characteristics and in essence to hide the visual information related to image. To achieve the selective Compression-encryption, the 2-D wavelet transform was used to decompose the image into details and approximation components, Set Partitioning in Hierarchical Tree compression method was used to compress the decomposed LL2 image before being encrypted with the bits stream key generated from the Qi hyper-chaos using exclusive or operation. The experimental results demonstrate that the proposed scheme is good for data compression and encryption.
1

1 January 2019
Verified
Conference Paper
Closed access
TOTresor Lisungu Oteko
Tresor Lisungu Oteko
MSMbuyu Sumbanyambe
Mbuyu Sumbanyambe
MMMinerve Maluambazila Mampaka
Minerve Maluambazila Mampaka
In mobile networks, there exists a relationship between the quality of service (QoS) and the quality of experience (QoE). This is often determined by the mean opinion score (MOS). There are several approaches that are used to determine the MOS in mobile networks and these may be subjective and objective. While the subjective approaches are standardized in their own essence, they are expensive and laborious to perform. Often, objective approaches have been used to determining the MOS by using network parameters such as delay, jitter and packet loss that are normally derived from network interfaces. The main aim of this study is to reduce the cost of the capital expenditure (CAPEX) and the operational expenditure (OPEX) linked to the drive testing method of obtaining the MOS. Thus, in this paper, a cost-effective objective MOS evaluation method based on the core network parameters from the Nb interface of a 2G and 3G mobile network are used. The training and verification of the proposed model was evaluated using machine learning techniques with regression analysis. The experimental results of the proposed model were compared with the subjective MOS evaluation from the drive test. Generally, the results showed that there was a high correlation between the predicted MOS and the values collected through the drive test, which is a subjective MOS evaluation approach.
1

4 August 2025 in Symmetry
Verified
Journal Article
Open access
PDF file
TOTresor Lisungu Oteko
Tresor Lisungu Oteko
Kingsley OgudoKingsley Ogudo
Kingsley Ogudo
The proliferation of biometric technology across various domains including user identification, financial services, healthcare, security, law enforcement, and border control introduces convenience in user identity verification while necessitating robust protection mechanisms for sensitive biometric data. While chaos-based encryption systems offer promising solutions, many existing chaos-based encryption schemes exhibit inherent shortcomings including deterministic randomness and constrained key spaces, often failing to balance security robustness with computational efficiency. To address this, we propose a novel dual-layer cryptographic framework leveraging a four-dimensional (4D) Qi hyperchaotic system for protecting biometric templates and facilitating secure feature matching operations. The framework implements a two-tier encryption mechanism where each layer independently utilizes a Qi hyperchaotic system to generate unique encryption parameters, ensuring template-specific encryption patterns that enhance resistance against chosen-plaintext attacks. The framework performs dimensional normalization of input biometric templates, followed by image pixel shuffling to permutate pixel positions before applying dual-key encryption using the Qi hyperchaotic system and XOR diffusion operations. Templates remain encrypted in storage, with decryption occurring only during authentication processes, ensuring continuous security while enabling biometric verification. The proposed system’s framework demonstrates exceptional randomness properties, validated through comprehensive NIST Statistical Test Suite analysis, achieving statistical significance across all 15 tests with p-values consistently above 0.01 threshold. Comprehensive security analysis reveals outstanding metrics: entropy values exceeding 7.99 bits, a key space of 10320, negligible correlation coefficients (<10−2), and robust differential attack resistance with an NPCR of 99.60% and a UACI of 33.45%. Empirical evaluation, on standard CASIA Face and Iris databases, demonstrates practical computational efficiency, achieving average encryption times of 0.50913s per user template for 256 × 256 images. Comparative analysis against other state-of-the-art encryption schemes verifies the effectiveness and reliability of the proposed scheme and demonstrates our framework’s superior performance in both security metrics and computational efficiency. Our findings contribute to the advancement of biometric template protection methodologies, offering a balanced performance between security robustness and operational efficiency required in real-world deployment scenarios.

9 November 2023
Verified
Journal Article
Closed access
TOTresor Lisungu Oteko
Tresor Lisungu Oteko
KOKingsley Ogudo
Kingsley Ogudo
Face recognition has become a crucial technology with diverse applications in various domains such as biometric security, healthcare, personal identification, and law enforcement. It stands out due to its high recognition rate, the richness of features, its universality, and its uniqueness. Having said that, challenges such as varying illumination, poses, facial expressions, face transformations, and backgrounds have hindered recognition accuracy, especially when using traditional techniques that rely on explicit feature extraction before the actual classification. The emergence of deep learning algorithms, such as Convolutional Neural Networks (CNNs), has exhibited prominent potential in image recognition capabilities, but building effective face recognition systems from scratch demands substantial labeled data and computational resources. To overcome these challenges, this paper proposes a novel approach that utilizes transfer learning and a pre-trained AlexNet CNN to improve face recognition capabilities. The model is trained with three different deep-learning optimizers, and the most suitable one is selected for the proposed system. For experiments, we created a custom database with images of five distinct individuals, generating over 1260 face images with each person having at least 250 samples. The dataset was further enriched using data augmentation technique. Using MATLAB with the Deep Learning Toolbox, the results demonstrate the model's recognition rate, peaking up to 100 per cent when the SGD optimizer is employed, 97.88 per cent when RMSProp is the optimizer, and 99.2 per cent for the Adam optimizer while using the same set of hyperparameters. These findings showcase the effectiveness of the approach and open doors for more efficient and accurate face recognition systems in real-world scenarios with large datasets.
1

7 September 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
TOTresor Lisungu Oteko
Tresor Lisungu Oteko
Kingsley OgudoKingsley Ogudo
Kingsley Ogudo
Accurate iris segmentation remains a fundamental challenge in iris biometric recognition and medical image analysis, particularly in challenging scenarios such as non-cooperative acquisition conditions involving variable illumination, partial occlusions, degraded image quality, and diverse unconstrained environments. Prevailing segmentation algorithms exhibit limited robustness when confronted with such challenges, and the disparity between near-infrared (NIR) and visible-light imaging modalities further compounds the complexity of achieving a robust segmentation outcome. To address these challenges, this paper introduces SwinIrisNet, a hybrid deep learning architecture that integrates Swin Transformer and convolutional neural network (CNN) branches within a U-Net framework for robust iris segmentation. The Swin Transformer branch leverages hierarchical window-based self-attention to capture global contextual dependencies, whereas the CNN branch extracts fine-grained local features essential for precise boundary delineation. A memory-efficient cross-attention fusion module combines these complementary feature representations, further enhanced by a Convolutional Block Attention Module (CBAM), Atrous Spatial Pyramid Pooling (ASPP), and attention-gated skip connections for multi-scale context aggregation. An extensive evaluation is conducted across four publicly available benchmark datasets, including UBIRIS.v2, IITD, CASIA-Thousand, and MMU.v1, encompassing both visible-light and NIR imaging environments. The proposed architecture yields F1 values of 0.9612–0.9672, Dice coefficients of 0.9489–0.9519, mIoU values of 0.9266–0.9450, precision values of 0.9565–0.9633, recall values of 0.9600–0.9672, and classification accuracies of 99.51–99.53%, with NICE1 error rates of 0.57–0.60% and NICE2 values of 1.82–2.24%, confirming pixel-level segmentation quality. Cross-database generalization experiments further demonstrate that SwinIrisNet learns transferable iris representations and generalizes effectively across heterogeneous imaging sources, with the strongest transfer occurring in the NIR-to-visible direction. A comparative analysis against existing algorithms demonstrates that the proposed architecture attains substantial performance improvements over several existing segmentation networks when evaluated on identical benchmark databases, surpassing them across the majority of qualitative and quantitative metrics while maintaining a marginally lower memory footprint.