Search Results (40)

While Vision Transformers (ViTs) have achieved state-of-the-art (SOTA) results in visual recognition, their scalability remains fundamentally constrained by the quadratic complexity of global self-attention. To address this, we present a linear complexity attention design employing dual-stream information propagation to enhance representational efficiency and structured feature aggregation. Our proposed $D{S}^2$ attention acts as a versatile replacement for standard attention in various SOTA designs, such as Tokens-to-Token (T2T) and FasterViT. In our design, half of the attention heads perform left-to-right segmented information propagation in a Perceiver-style manner, while the remaining half of the heads perform right-to-left propagation. This bidirectional structured attention enables efficient long-range dependency modeling without the overhead of full global attention. To improve classification performance, we introduce a segment-level classification strategy in which each segment is associated with a summary token. The final prediction is produced via cross-attention between image tokens and these summary tokens, enabling hierarchical semantic comprehension. Extensive experiments demonstrate that the proposed attention design achieves on average 0.3% higher accuracy on the ImageNet-1K dataset, while offering improved information flow and higher efficiency across SOTA Vision Transformer designs. Full article

The fast-paced progress in quantum computing introduces significant new challenges for digital forensics by undermining classical cryptographic mechanisms that protect digital evidence. Algorithms such as Shor’s and Grover’s threaten the long-term reliability of traditional hash functions, digital signatures, and encryption schemes, thereby compromising the integrity, authenticity, and confidentiality of evidence. This paper investigates how quantum entanglement can be leveraged to enhance the security of digital forensic evidence in the post-quantum era. A hybrid quantum–classical forensic framework is proposed, integrating three entanglement-based components: an entanglement-assisted quantum hashing mechanism for integrity assurance, a CHSH nonlocality-based protocol for authenticity verification, and a BBM92 quantum key distribution scheme for confidentiality and secure chain-of-custody management. All components are implemented using IBM Qiskit and evaluated with the AerSimulator under realistic Noisy Intermediate-Scale Quantum conditions. Experimental results measured using Hamming distance, CHSH S-values, and Quantum Bit Error Rate demonstrate improved tamper detection, reliable authenticity validation, and strong overall confidentiality. Full article

Routine evaluation of insulator performance is important for maintaining the reliability and safety of power system operations. The use of unmanned aerial vehicles (UAVs) has been a significant advancement in transmission line monitoring, effectively replacing traditional manual inspection methods. With the rapid advancement of deep learning techniques, methods based on these models for detecting insulator defects have attracted increasing research interest and achieved notable advancements. Nevertheless, existing approaches primarily emphasize constructing sophisticated and intricate network architectures, which consequently lead to greater inference complexity when applied in practical scenarios. On the other hand, foggy scenarios pose challenges for learning algorithms due to difficulties in obtaining and labeling samples, as well as the poor performance of detectors trained on clear-weather samples. This study proposes adaptive enhancement based on YOLO, a framework that has robustness and domain generalization under fog-induced distribution shifts. It optimizes at multiple scales and enhances images as input to a detector in a single pipeline. Experimental results demonstrate improved performance on public UPID and SFID insulator defect datasets, improving insulator defect detection precision without increased computational complexity or inference resources, which is of great significance for advancing object detection in adverse weather. The proposed method achieves real-time performance, with an end-to-end inference speed exceeding 25 FPS and a model-only speed of approximately 38 FPS on 678 images from UPID, demonstrating both practical applicability and computational efficiency. Full article

The global issues of air pollution and the energy crisis present significant potential for the development of electric vehicles. However, modern power batteries fall short of conventional internal combustion engine vehicles in several categories, including factors such as cycle longevity, suitability for various environments, range of driving, and charging duration. Battery thermal management (BTM) must be performed well to solve these problems. Enhancing efficiency of electric vehicle batteries is one of the biggest challenges in lowering power usage during electric vehicle battery discharging while driving. Additionally, if the range of electric vehicles is extended, more individuals will acquire them. The cooling system for the battery is one of the main performance issues faced by electric vehicles. This literature review focuses on battery modules that use air and liquid cooling and discusses various cooling configuration arrangements. Liquid, straightforward liquid, and air-cooling strategies are also evaluated, as they can advance battery thermal management systems to a new generation. We aim to address and present various issues related to electric vehicle battery cooling systems, enabling researchers to design and improve current cooling systems for enhanced performance. Full article

As quantum computing advances, traditional digital forensic techniques face significant risks due to the vulnerability of classical cryptographic algorithms to quantum attacks. This review explores the emerging field of quantum digital forensics, with a particular focus on the role of quantum entanglement in enhancing the integrity, authenticity, and confidentiality of digital evidence. It compares classical and quantum forensic mechanisms, examines entanglement-based quantum key distribution (QKD), quantum hash functions, and quantum digital signatures (QDS), and discusses the challenges in practical implementation, such as scalability, hardware limitations, and legal admissibility. The paper also reviews various entanglement detection methods critical to the validation of quantum states used in forensic processes. Full article

The Transformer architecture has been the foundational cornerstone of the recent AI revolution, serving as the backbone of Large Language Models, which have demonstrated impressive language understanding and reasoning capabilities. When pretrained on large amounts of data, Transformers have also shown to be highly effective in image classification via the advent of the Vision Transformer. However, they still lag in vision application performance compared to Convolutional Neural Networks (CNNs), which offer translational invariance, whereas Transformers lack inductive bias. Further, the Transformer relies on the attention mechanism, which despite increasing the receptive field, makes it computationally inefficient due to its quadratic time complexity. In this paper, we enhance the Transformer architecture, focusing on its above two shortcomings. We propose two efficient Vision Transformer architectures that significantly reduce the computational complexity without sacrificing classification performance. Our first enhanced architecture is the EEViT-PAR, which combines features from two recently proposed designs of PerceiverAR and CaiT. This enhancement leads to our second architecture, EEViT-IP, which provides implicit windowing capabilities akin to the SWIN Transformer and implicitly improves the inductive bias, while being extremely memory and computationally efficient. We perform detailed experiments on multiple image datasets to show the effectiveness of our architectures. Our best performing EEViT outperforms existing SOTA ViT models in terms of execution efficiency and surpasses or provides competitive classification accuracy on different benchmarks. Full article

Despite deep learning-based object detection techniques showing promising results, identifying items from low-quality images under unfavorable weather settings remains challenging because of balancing demands and overlooking useful latent information. On the other hand, YOLO is being developed for real-time object detection, addressing limitations of current models, which struggle with low accuracy and high resource requirements. To address these issues, we provide an Adaptive Enhancement Algorithm YOLO (AEA-YOLO) framework that allows for an enhancement in each image for improved detection capabilities. A lightweight Parameter Prediction Network (PPN) containing only six thousand parameters predicts scene-adaptive coefficients for a differentiable Image Enhancement Module (IEM), and the enhanced image is then processed by a standard YOLO detector, called the Detection Network (DN). Adaptively processing images in both favorable and unfavorable weather conditions is possible with our suggested method. Extremely encouraging experimental results compared with existing models show that our suggested approach achieves 7% and more than 12% in mean average precision (mAP) on the PASCAL VOC Foggy artificially degraded and the Real-world Task-driven Testing Set (RTTS) datasets. Moreover, our approach achieves good results compared with other state-of-the-art and adaptive domain models of object detection in normal and challenging environments. Full article

Large Language Models (LLMs) have immensely advanced the field of Artificial Intelligence (AI), with recent models being able to perform chain-of-thought reasoning and solve complex mathematical problems, ranging from theorem proving to ones involving advanced calculus. The success of LLMs derives from a combination of the Transformer architecture with its attention mechanism, the autoregressive training methodology with masked attention, and the alignment fine-tuning via reinforcement learning algorithms. In this research, we attempt to explore a possible solution to the fundamental NP-hard problem of combinatorial optimization, in particular, the Traveling Salesman Problem (TSP), by following the LLM approach in terms of the architecture and training algorithms. Similar to the LLM design, which is trained in an autoregressive manner to predict the next token, our model is trained to predict the next node in a TSP graph. After the model is trained on random TSP graphs with known near-optimal solutions, we fine-tune the model using Direct Preference Optimization (DPO). The tour generation in a trained model is autoregressive one-step generation with no need for iterative refinement. Our results are very promising and indicate that, for TSP graphs up to 100 nodes, a relatively small amount of training data yield solutions within a few percent of the optimal. This optimization improves if more data are used to train the model. Full article

Quantum machine learning holds the potential to revolutionize cancer treatment and diagnostic imaging by uncovering complex patterns beyond the reach of classical methods. This study explores the effectiveness of quantum convolutional layers in classifying ultrasound breast images for cancer detection. By encoding classical data into quantum states through angle embedding and employing a robustly entangled 9-qubit circuit design with an SU(4) gate, we developed a Quantum Convolutional Neural Network (QCNN) and compared it to a classical CNN of similar architecture. Our QCNN model, leveraging two quantum circuits as convolutional layers, achieved an impressive peak training accuracy of 76.66% and a validation accuracy of 87.17% at a learning rate of 1 × 10⁻². In contrast, the classical CNN model attained a training accuracy of 77.52% and a validation accuracy of 83.33%. These compelling results highlight the potential of quantum circuits to serve as effective convolutional layers for feature extraction in image classification, especially with small datasets. Full article

Current AI detection systems often struggle to distinguish between Arabic human-written text (HWT) and AI-generated text (AIGT) due to the small marks present above and below the Arabic text called diacritics. This study introduces robust Arabic text detection models using Transformer-based pre-trained models, specifically AraELECTRA, AraBERT, XLM-R, and mBERT. Our primary goal is to detect AIGTs in essays and overcome the challenges posed by the diacritics that usually appear in Arabic religious texts. We created several novel datasets with diacritized and non-diacritized texts comprising up to 9666 HWT and AIGT training examples. We aimed to assess the robustness and effectiveness of the detection models on out-of-domain (OOD) datasets to assess their generalizability. Our detection models trained on diacritized examples achieved up to 98.4% accuracy compared to GPTZero’s 62.7% on the AIRABIC benchmark dataset. Our experiments reveal that, while including diacritics in training enhances the recognition of the diacritized HWTs, duplicating examples with and without diacritics is inefficient despite the high accuracy achieved. Applying a dediacritization filter during evaluation significantly improved model performance, achieving optimal performance compared to both GPTZero and the detection models trained on diacritized examples but evaluated without dediacritization. Although our focus was on Arabic due to its writing challenges, our detector architecture is adaptable to any language. Full article

The effectiveness of existing AI detectors is notably hampered when processing Arabic texts. This study introduces a novel AI text classifier designed specifically for Arabic, tackling the distinct challenges inherent in processing this language. A particular focus is placed on accurately recognizing human-written texts (HWTs), an area where existing AI detectors have demonstrated significant limitations. To achieve this goal, this paper utilized and fine-tuned two Transformer-based models, AraELECTRA and XLM-R, by training them on two distinct datasets: a large dataset comprising 43,958 examples and a custom dataset with 3078 examples that contain HWT and AI-generated texts (AIGTs) from various sources, including ChatGPT 3.5, ChatGPT-4, and BARD. The proposed architecture is adaptable to any language, but this work evaluates these models’ efficiency in recognizing HWTs versus AIGTs in Arabic as an example of Semitic languages. The performance of the proposed models has been compared against the two prominent existing AI detectors, GPTZero and OpenAI Text Classifier, particularly on the AIRABIC benchmark dataset. The results reveal that the proposed classifiers outperform both GPTZero and OpenAI Text Classifier with 81% accuracy compared to 63% and 50% for GPTZero and OpenAI Text Classifier, respectively. Furthermore, integrating a Dediacritization Layer prior to the classification model demonstrated a significant enhancement in the detection accuracy of both HWTs and AIGTs. This Dediacritization step markedly improved the classification accuracy, elevating it from 81% to as high as 99% and, in some instances, even achieving 100%. Full article

Quantum computing is a promising technology that may provide breakthrough solutions to today’s difficult problems such as breaking encryption and solving large-scale combinatorial optimization problems. An algorithm referred to as Quantum Approximate Optimization Algorithm (QAOA) has been recently proposed to approximately solve hard problems using a protocol know as bang–bang. The technique is based on unitary evolution using a Hamiltonian encoding of the objective function of the combinatorial optimization problem. The QAOA was explored in the context of several optimization problems such as the Max-Cut problem and the Traveling Salesman Problem (TSP). Due to the relatively small node-size solution capability of the available quantum computers and simulators, we developed a hybrid approach where sub-graphs of a TSP tour can be executed on a quantum computer, and the results from the quantum optimization are combined for a further optimization of the whole tour. Since the local optimization of a sub-graph is prone to becoming trapped in a local minimum, we overcame this problem by using a parallel Ant Colony Optimization (ACO) algorithm with periodic pheromone exchange between colonies. Our method exceeds existing approaches which have attempted partitioning a graph for small problems (less than 48 nodes) with sub-optimal results. We obtained optimum results for benchmarks with less than 150 nodes and results usually within 1% of the known optimal solution for benchmarks with around 2000 nodes. Full article

Epileptic seizure detection classification distinguishes between epileptic and non-epileptic signals and is an important step that can aid doctors in diagnosing and treating epileptic seizures. In this paper, we studied the existing epileptic seizure detection methods in terms of challenges and processes developed based on electroencephalograph (EEG) signals. To identify the research deficiencies and provide a feasible solution, we surveyed the existing techniques at each phase, including signal acquisition, pre-processing, feature extraction, and classification. Most previous and current research efforts have used traditional features and decomposing techniques. Therefore, in this paper, we introduced an enhanced and efficient epileptic seizure technique using EEG signals, for which we also developed a mobile application for monitoring the classification of EEG signals. The application triggers notifications to all associated users and sends a visual notification should an EEG signal be classified as epileptic. In this research, we have used publicly available EEG data from the University of Bonn. Our proposed method achieved an average accuracy of 98% by utilizing different machine-learning algorithms for classification, and it has outperformed recently published studies. Though there have been other mobile applications for epileptic seizure detection, they have been based on motion and falling detection, as opposed to ours, which was developed based on EEG classification. Our proposed method will have an impact in the medical field, particularly for epilepsy seizure monitoring as well as in the Human–Computer Interaction fields, majorly in the Brain–Computer Interaction (BCI) applications. Full article

This paper aims to design and implement a robust wireless charging system that utilizes affordable materials and the principle of piezoelectricity to generate clean energy to allow the user to store the energy for later use. A wireless charging system that utilizes the piezoelectricity generated as a power source and integrated with Qi-standard wireless transmission would substantially affect the environment and the users. The approach consists of a full-wave-rectified piezoelectric generation, battery storage, Qi-standard wireless transmission, and Bluetooth Low Energy (BLE) as the controller and application monitor. Three main functions are involved in the design of the proposed system: power generation, power storage, and power transmission. A client application is conceived to monitor the transmission and receipt of data. The piezoelectric elements generate the AC electricity from the mechanical movements, which converts the electricity to DC using the full-wave bridge rectifiers. The sensor transmits the data to the application via BLE protocols. The user receives continuous updates regarding the storage level, paired devices, and remaining time for a complete charge. A Qi-standard wireless transmitter transfers the stored electricity to charge the respective devices. The output generates pulses to 60 voltage on each compression of a transducer. The design is based on multiple parallel configurations to solve the issue of charging up to the triggering value VH = 5.2 V when tested with a single piezoelectric transducer. AA-type battery cells are charged in parallel in a series configuration. The system is tested for a number of scenarios. In addition, we simulate the design for 11.11 h for approximately 70,000 joules of input. The system can charge from 5% to 100% and draw from 98%. Using four piezos in the designed module results in an average output voltage of 1.16 V. Increasing the number of piezos results in 17.2 W of power. The system is able to wirelessly transmit and store power with a stable power status after less than 0.01 s. Full article

A high-efficiency crystalline silicon-based solar cell in the visible and near-infrared regions is introduced in this paper. A textured TiO₂ layer grown on top of the active silicon layer and a back reflector with gratings are used to enhance the solar cell performance. The given structure is simulated using the finite difference time domain (FDTD) method to determine the solar cell’s performance. The simulation toolbox calculates the short circuit current density by solving Maxwell’s equation, and the open-circuit voltage will be calculated numerically according to the material parameters. Hence, each simulation process calculates the fill factor and power conversion efficiency numerically. The optimization of the crystalline silicon active layer thickness and the dimensions of the back reflector grating are given in this work. The grating period structure of the Al back reflector is covered with a graphene layer to improve the absorption of the solar cell, where the periodicity, height, and width of the gratings are optimized. Furthermore, the optimum height of the textured TiO₂ layer is simulated to produce the maximum efficiency using light absorption and short circuit current density. In addition, plasmonic nanoparticles are distributed on the textured surface to enhance the light absorption, with different radii, with radius 50, 75, 100, and 125 nm. The absorbed light energy for different nanoparticle materials, Au, Ag, Al, and Cu, are simulated and compared to determine the best performance. The obtained short circuit current density is 61.9 ma/cm², open-circuit voltage is 0.6 V, fill factor is 0.83, and the power conversion efficiency is 30.6%. The proposed crystalline silicon solar cell improves the short circuit current density by almost 89% and the power conversion efficiency by almost 34%. Full article