This paper proposes an LR-aided adaptive QRD-M detector for complexity reduction in MIMO-OFDM systems. The proposed approach integrates lattice-reduction preprocessing with an adaptive candidate selection strategy to control the search width of the QRD-M algorithm. Unlike the conventional QRD-M detector with a fixed candidate size, the proposed method dynamically adjusts the number of surviving paths to limit unnecessary computations while preserving detection reliability. Simulation results demonstrate that the proposed detector achieves near-optimal detection performance in frequency-selective MIMO-OFDM channels, reaching a symbol error rate (SER) of 10⁻⁵ for an 8×8 system using 16-QAM modulation at high SNR. For a 4×4 configuration, the proposed method reduces computational complexity by approximately 26% in terms of average squared Euclidean distance (SED) computations compared with the conventional QRD-M detector. Analytical FLOP evaluation further confirms consistent complexity savings as the antenna dimension increases. These results demonstrate an improved performance–complexity trade-off and strong scalability for practical large-scale MIMO deployments.
As developing cyber threats complexity and sophistication, traditional Network Intrusion Detection Systems (NIDS) face difficulties in detecting attacks within an acceptable time. For these challenges, this paper presents a new flow-based NIDS framework utilizing the benefits of Advanced Machine Learning methods, specifically the heterogeneous stacking ensemble. That leads to enhancing the detection performance in different attack scenarios. The proposed system merges three different base learner algorithms: Naïve Bayes (NB), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) with two different stackers(meta-learners): J48 decision tree and Logistic Regression (LR). The proposed system uses the comprehensive benchmark CSE-CIC-IDS-2018 dataset for testing and evaluation. In order to reduce the dimension of the feature space and to improve the model efficiency, feature selection is used with the aid of Mutual Information (MI). The experimental results showed that the LR-based meta-learner outperforms J48, achieving superior results of 97.98%, 98.90%, 93.92%, and 96.34% for accuracy, precision, recall, and f1-score, respectively. These results represent significant enhancements over the individual base classifiers and traditional ensemble methods. This can be used to build modern, effective cybersecurity applications that combine diverse machine learning algorithms with strategic feature engineering.
The rising quantities of the blowdown (carbon-sulfur) hydrocarbon waste generated in the production of sulfur posed challenges to the environment in Iraq. This research paper explored the application of blowdown as a sustainable filler in asphalt mix that had been modified with SBS polymer and synthetic zeolite (SZ) additives. Six asphalt mixtures were prepared with blowdown and traditional fillers of CaCO3 and were tested concerning mechanical and durability performances, using Marshall stability, indirect tensile strength, and deformation strength tests. Findings indicated that the SBS-modified blowdown mixtures had better strength, cracking, and rutting resistance than any other mixtures. These results proved that blowdown waste can be a good filler to be used in sustainable pavements to provide improved performance and environmental advantages
In recent years, network security has attracted significant research attention due to the growing frequency of attacks on computer networks. Among existing solutions, “Network Intrusion Detection Systems (NIDS)” play a central role. While binary NIDS effectively distinguish between normal and malicious traffic, they cannot accurately classify specific attack types. Multi-class intrusion detection systems address this limitation by enabling tailored responses for each attack category. This paper presents the development of a “multi-class Intrusion Detection System (IDS)” that integrates “Recursive Feature Addition (RFA)”, an embedded feature selection technique, with multi-level binary classifiers. The proposed system was evaluated using five machine learning algorithms: “Support Vector Machines (SVM)”, “Random Forests”, “J48”, “Random Tree”, and “J48Graft”. A hierarchical binary tree structure was employed to implement the multi-class detection, with performance assessed under two dataset distribution scenarios: “balanced” and “imbalanced”. To construct the overall “multi-class confusion matrix”, a novel estimation method that combines intermediate matrices from each binary sub-tree has been introduced.The ISCX 2012 intrusion detection benchmark dataset was used for evaluation, with results measured across five metrics: “Accuracy”, “F1-score”, “Detection Rate”, “False Alarm Rate (FAR)”, and “Precision”. Experimental findings show that “Random Tree” consistently achieved the best performance across both scenarios. For “balanced” datasets, it excelled in detecting DoS attacks, while for “imbalanced” datasets, it demonstrated superior efficiency in identifying Internal attacks. In addition, the proposed approach has demonstrated superiority over the baseline in terms of time required for (feature selection + classification hierarchy) and key metrics. These results highlight the effectiveness of the proposed multi-class IDS framework for enhancing intrusion detection in complex network environments
There is a goal to develop a fundamental deep learning system for histopathological image categorization, which operates in real-time while keeping a lightweight design to facilitate better cancer diagnostics in mobile health settings with limited resources. Accurate deep learning models are not well-suited for low-power edge devices, as they require high computational power and memory capacity and do not integrate well with user interfaces for real-time diagnostic applications. A CNN with optimization for inference latency reduction and power efficiency was achieved through a design approach that included quantization-aware network pruning to maintain performance and decrease model size. The proposed model implements grouped convolutional processing while decreasing its filter width, together with mixed-precision quantization, which enables INT8 convolutions combined with FP16 batch normalization and FP32 fully connected layer operation through a MATLAB graphical user interface that enables users to select images, along with automatic diagnostic report generation with label watermarking. The experimental results show that the system achieves 99.14% classification precision, with a model dimension of 263 KB and a runtime of 2.63 milliseconds, producing better or equivalent results compared to the lightweight ShuffleNet and MobileNetV2 architectures based on F1-score, throughput, and energy efficiency metrics. This work takes the concept of deep learning closer to practice by introducing an effective end-to-end prototype, but additional cross-dataset validation, on-edge device benchmarking, and interpretability to clinicians will be needed to make it clinically ready
