Early and accurate diagnosis of heart conditions is pivotal for effective treatment. Phonocardiography (PCG) has become a standard diagnostic tool for evaluating and detecting cardiac abnormalities. While traditional cardiac auscultation remains widely used, its accuracy is highly dependent on the clinician’s experience and auditory skills. Consequently, there is a growing need for automated, objective methods of heart sound analysis. This study explores the efficacy of the Common Spatial Patterns (CSP) feature extraction algorithm paired with the Random Forest (RF) classifier to distinguish between normal and pathological heart sounds. The signal is denoised, transformed, and segmented into fixed-length segments. CSP is applied to extract discriminative features (a set of Spatial Patterns), which are then fed into the classifier for cardiac diagnosis. The proposed method was evaluated using PhysioNet/CinC Challenge 2016 and Yaseen2018 (Heart Sound Murmur) datasets. On the testing set of the PhysioNet dataset, the RF classifier achieved 100% precision, recall, accuracy, F1 score, and AUC. Similarly, on the testing set of the Yaseen2018 dataset, it achieved 96.30% precision, 1.00 recall, 98.08% accuracy, 98.11% F1 score, and 99.41% AUC.

The rapid pace of technological development in recent years necessitates the protection of smart cities’ infrastructure from various cyber threats. In the near future, cyber threats targeting smart cities are expected to increase in volume, number, nature, sophistication, and diversity. A literature review, on the other hand, indicates that smart cities do not have a comprehensive digital forensic readiness metamodel to address both predicted and unanticipated attacks. As a solution to this challenge, the present study developed a high abstract digital forensic readiness metamodel (HADFRM) for securing smart cities using a model-driven engineering approach. A major contribution of this study is to facilitate cybercrime investigation in such smart environments by integrating common processes and forensic readiness concepts embedded in HADFRM. The proposed HADFRM is bound to be an excellent source of practical assistance to forensic practitioners when a tool such as its structure can be used to help develop effective solutions to their problems. The HADFRM consists of five meta-processes: incident response process, data acquisition process, data preservation process, data analysis process, and reporting and presentation process. The HADFRM was evaluated with a realistic cybercrime scenario in a smart home. In this scenario, HADFRM was tested to determine its applicability and usefulness. By developing smart city security solutions, we have the opportunity to improve cybersecurity and stimulate sustainable economic growth, which ultimately contributes to improving citizens’ welfare.

Fetal hypoxia is a condition that is caused by insufficient oxygen supply to the fetus and poses serious risks, including abnormalities, birth defects, and potential mortality. Cardiotocography (CTG) monitoring is commonly used to identify fetal distress, including hypoxia, by categorizing cases as normal or hypoxia. However, traditional CTG interpretation, usually performed visually by experts, can be subjective and error-prone, resulting in observer variability and inconsistent outcomes. It highlights the need for an automated and objective diagnostic system to assist clinicians in interpreting CTG data more accurately and consistently. In this research, a fetal hypoxia diagnosis system is proposed based on CTG signals. The CTG dataset is first transformed into the time-frequency domain using instantaneous frequency and using common spatial pattern (CSP) for feature extraction. Finally, the extracted features are then used to train and evaluate four machine learning models for classification with a cross-validation 5-fold methodology. Objective criteria (pH values, BDecf, Apgar 1, and Apgar 5) and expert voting as a subjective criterion were used to classify the fetus as normal or hypoxia. The SVM model outperformed other models in detecting fetal hypoxia, achieving high accuracy across pH, BDecf, Apgar1, Apgar5, and expert voting in all steps. It achieved over 98% accuracy across all objective criteria and steps.

The Internet of Things (IoT) is expanding rapidly as more consumer devices become connected. This expansion presents significant security challenges for Software-Defined Networking (SDN), where static defense mechanisms are often insufficient. The proposed work presents a novel framework that enhances Intrusion Detection Systems (IDS) by combining dynamic resource allocation with game theory and Reinforcement Learning (RL). In this framework, the strategic interactions among the IDS, potential attackers, and the SDN controller are modeled to reflect the complex dynamics of consumer-centric IoT environments. The controller allocates resources in real time, adapting to network demands while maintaining security and performance. RL optimizes these decisions by enabling continuous adaptation to evolving attack patterns. Simulation results validate the effectiveness of the proposed approach, achieving a 98.2% attack detection rate with only 1.8% false positives, along with measurable improvements in throughput and latency compared to baseline methods. The proposed work resolves the key trade-off between security and efficiency, delivering a robust and efficient security framework for IoT-enabled SDN in consumer environments.

The Hassanat Distance (HasD) is a bounded, non-convex metric widely used in k-nearest-neighbor (KNN) classification for its robustness to noise, outliers, and heterogeneous feature scales. Its definition, however, breaks a natural symmetry: through a sign-dependent shift it assigns different distances to mirror-image pairs such as $(1,2)$ and $(-1,-2)$, distorting neighborhoods exactly in the value ranges that modern preprocessing (z-scoring, principal component analysis (PCA), learned embeddings) produces. We introduce the Sign-Symmetric Hassanat Distance (SHasD), a single branch-free formula $D(a,b)=|a-b|/(1+\max (\left|a\right|,\left|b\right|\left)\right)$ that is invariant under the reflection $x\mapsto -x$, coincides exactly with HasD on non-negative data, and removes the conditional shift entirely. We prove SHasD is a metric, and we derive a range-normalized companion, SHasD-R, that additionally restores ray monotonicity and the $[0,1)$ per-dimension bound. On 23 datasets across three normalization regimes and ten distance measures, SHasD improves significantly on HasD on data containing negative values (mean gain $+1.1$ percentage points, up to $+7.4$; Wilcoxon $p=0.0026$, Holm-corrected) and attains the best mean rank of the compared measures on signed, heavy-tailed, outlier-rich data, while preserving HasD’s robustness. An additive per-dimension decomposition yields a built-in interpretation of every prediction.

In todays landscape of increasing electronic crime, network forensics plays a pivotal role in digital investigations. It aids in understanding which systems to analyse and as a supplement to support evidence found through more traditional computer based investigations. However, the nature and functionality of the existing Network Forensic Analysis Tools (NFATs) fall short compared to File System Forensic Analysis Tools (FS FATs) in providing usable data. The analysis tends to focus upon IP addresses, which are not synonymous with user identities, a point of significant interest to investigators. This paper presents several experiments designed to create a novel NFAT approach that can identify users and understand how they are using network based applications whilst the traffic remains encrypted. The experiments build upon the prior art and investigate how effective this approach is in classifying users and their actions. Utilising an in-house dataset composed of 50 million packers, the experiments are formed of three incremental developments that assist in improving performance. Building upon the successful experiments, a proposed NFAT interface is presented to illustrate the ease at which investigators would be able to ask relevant questions of user interactions. The experiments profiled across 27 users, has yielded an average 93.3% True Positive Identification Rate (TPIR), with 41% of users experiencing 100% TPIR. Skype, Wikipedia and Hotmail services achieved a notably high level of recognition performance. The study has developed and evaluated an approach to analyse encrypted network traffic more effectively through the modelling of network traffic and to subsequently visualise these interactions through a novel network forensic analysis tool.