Search Results

This work discuss two different intelligent controllers: Online Neuro Fuzzy Controller (ONFC) and Proportional-Integral-Derivative Neural Network (PID-NN). They were applied to maintain the equilibrium and to control the position of a two-wheeled robot prototype. Experiments were carried out to investigate the equilibrium control and movement of the two-wheeled robot first on flat terrain, then in…

Mortar is used all over the world for construction purpose. It consists of cement paste and fine aggregates and admixtures if required are also incorporated to modify some of its properties. In this study coconut fibers and human hair were used as an additive materials in the mortar and its effects on compressive strength of…

This manuscript focuses on a hybrid power system combining a solar photovoltaic array and energy storage system based on hydrogen technology (fuel cell, hydrogen tank and electrolyzer) and battery. The complete architecture is connected to the national grid through power converters to increase the continuity of power. The proposed a hybrid power system is designed…

Methane found in coal seams is about 17% of total methane emissions by human activities and 8% of world’s greenhouse gases emissions. Mine methane can be generated through different streams of coal mines like degasification of underground coal mines, ventilation of air in coal seams, post mining processes and surface mining. Methane from ventilation air…

Security Operations Centers (SOCs) require intrusion detection systems that achieve high detection accuracy while maintaining a low false-positive rate and robustness to evolving attack patterns. However, most existing machine learning-based approaches primarily focus on detecting known threats and often overlook distribution shifts and the reliability of generated alerts. In this paper, we propose TL-SOC, a…

The rapid growth of Internet of things (IoT) devices have heightened the need for effective Intrusion Detection System (IDS) to combat evolving cyber threats. The IoT networks has the security challenges due to the heterogeneous and high-dimensional nature of network traffic data, redundant features, and class imbalance which hinder detection accuracy and efficiency. Effective IDS…

This paper introduces HLLSet (HyperLogLog Set), a probabilistic data structure that behaves like a set under all standard operations while containing no explicit elements. Unlike traditional HyperLogLog, which only estimates cardinality, HLLSets support full set operations (union, intersection, difference) through enhanced register structures and provide a principled framework for representing semantic relationships. We establish a…

Forecasting and assessing student performance are crucial for allowing educators to pinpoint deficiencies and promote grade improvement. A thorough comprehension of feature contributions is crucial for improving model interpretability and facilitating informed decision-making in academic institutions. Explainable artificial intelligence encompasses methodologies and strategies designed to deliver transparent and accessible rationales for the decisions rendered by…

This study investigated the influence of a biomass additive on the thermal performance of the inner liner of fired-clay cook-stoves. Fired-clay cook-stoves are essential cooking devices, particularly in areas with limited access to modern energy resources. The study aimed to enhance the thermal efficiency of the cook-stoves by incorporating rice husk into the inner liner…

The accumulation and analysis of large-scale patient data have led to breakthrough discoveries in potential flags for diseases based on pattern recognition, highlight medication efficacy, and local population health trends that would be impossible with traditional paper-based records. However, these benefits come with unique challenges posed by the application of data sharing for research and…

Neural Networks derives intelligent systems and modern autonomous applications. With the complexity introduced in today’s systems, designing architectures remains open research problem in all fields. Despite many efforts to generalize, the resources required by neural architectures remain challenge. Robots design, Smart cities, IoTs …etc. become the leading industry and driving the fourth industrial revolutions. All…

Heart rate (HR) is a critical indicator in fitness monitoring, athletic performance evaluation, and injury prevention. However, traditional motion-sensitive wearable devices are highly susceptible to movement artifacts, which degrade measurement accuracy during physical activity. Remote photoplethysmography (rPPG) offers a non-contact alternative for HR measurement, though it too remains sensitive to motion. This study proposes a…

This paper presents the design and fabrication of an electromagnetically actuated PCB-based resonating scanning micro-mirror for LiDAR applications, with optimization targeted towards low-cost fabrication and a high scanning angle. Traditional silicon MEMS-based micro-mirrors, while offering high precision and compatibility with CMOS processing, are limited by fragility at low scanning frequencies and costly fabrication processes. To…

The rapid proliferation of drones across various industries has introduced significant challenges related to privacy, security, and noise pollution. Current drone detection systems, primarily based on visual and radar technologies, face limitations under certain conditions, highlighting the need for effective acoustic-based detection methods. This paper presents a unique and comprehensive dataset of drone acoustic signatures,…

Complex networked systems provide a cornucopia of network statistics, many of which relate to the temporal behaviour of subsystems, devices, or even individual protocol layers. Different and flexible visualizations can play a crucial role in discovering and making patterns, relations, and trends tangible. We developed PerfVis, a tool that visualizes timestamp data to aid in…

Achieving targeted reliability for complex products in real-world field environments remains a persistent challenge, even when laboratory validation suggests high performance. A significant reliability gap often emerges during the initial deployment phase, typically within the first one to five years where field failure rates can be up to twice those predicted in controlled settings. Compounding…

This study establishes a method for determining whether learners have an understanding of data science. Data science requires knowledge in various fields, which makes many learners give up. To prevent learners from being discouraged, it is necessary to judge the comprehension of the principles in each specified skill. It is important to assess not only…

Deep neural networks (DNNs) have demonstrated remarkable success across a wide range of machine learning tasks. However, determining an effective network architecture, particularly the sizes of the hidden layers, remains a significant challenge and often relies on inefficient trial-and-error experimentation. In this paper, we propose an automated architecture design approach based on structurally adaptive DNNs,…

Zero Trust Architecture offers a transformative approach to network security by emphasizing ”never trust, always verify.” IoT devices, while increasingly integral to modern ecosystems, pose unique challenges for identity management and access control due to their constrained processing power, memory, and energy capabilities. In a Zero Trust framework, every IoT device is treated as a…

We address irregular polygon nesting on sheet materials with a lightweight evolutionary framework that operates directly in the layout space. The method formalizes multi-term fitness combining utilization, overlap penalties, spacing regularity, and local alignment, with all components normalized before aggregation. Feasibility is enforced by an AABB– SAT pipeline and validated via analytic ground-truth cases, degenerate…

In this work, we present CIRB-Edge, a novel integer compression method designed specifically to overcome the limitations of traditional techniques such as Huffman coding, Delta encoding, and dictionary-based algorithms. These legacy methods often fall short in meeting the stringent requirements of secure, energy-efficient, and real-time edge computing due to their high computational overhead, memory demands,…

Investment decision-making plays a pivotal role in shaping both individual and institutional economic outcomes. Given the increasing complexity and uncertainty in global markets, optimizing investment decisions has become essential for maximizing returns while managing risks. This work explores modern optimization approaches in investment decision-making, focusing on mathematical modeling techniques such as linear programming (LP), mixed-integer…

While prior research has focused on siloed approaches to equipment replacement, this study introduces an integrated decision-making framework that synergizes predictive maintenance (IoT/M), dynamic multi-criteria analysis (MCDM), and sustainability-driven material selection. By validating this model through cross-sector case studies and strategic operational planning across various industrial sectors. We demonstrate a 30% improvement in replacement timing…

As models based in artificial intelligence increase in sophistication, there is a higher demand for the integration of hardware components to heighten real-world implementations. Both facial feature tracking and shape-from-focus are known techniques in computer vision. However, the combination of these two elements, particularly in a cost-effective configuration, has not been extensively explored. In this…

Establishing an environment that allows for the quantitative evaluation of the ability of autonomous driving systems to respond to real-world adverse conditions is crucial to ensuring their safety and reliability. This study proposes a dynamic scenario-based simulation framework that simulates complex and sequential hazardous scenarios frequently encountered in actual road environments. The proposed scenarios are…