Advanced Computer Research Articles

QuEst: Adversarial Attack Intensity Estimation via Query Response Analysis

Deep learning has dramatically advanced computer vision tasks, including person re-identification (re-ID), substantially improving matching individuals across diverse camera views. However, person re-ID systems remain vulnerable to adversarial attacks that introduce imperceptible perturbations, leading to misidentification and undermining system reliability. This paper addresses the challenge of robust person re-ID in the presence of adversarial examples by estimating attack intensity to enable effective detection and adaptive purification. The proposed approach leverages the observation that adversarial examples in retrieval tasks disrupt the relevance and internal consistency of retrieval results, degrading re-ID accuracy. This approach estimates the attack intensity and dynamically adjusts the purification strength by analyzing the query response data, addressing the limitations of fixed purification methods. This approach also preserves the performance of the model on clean data by avoiding unnecessary manipulation while improving the robustness of the system and its reliability in the presence of adversarial examples. The experimental results demonstrate that the proposed method effectively detects adversarial examples and estimates the attack intensity through query response analysis. This approach enhances purification performance when integrated with adversarial purification techniques in person re-ID systems.

Advanced Computational Pipeline for FAK Inhibitor Discovery: Combining Multiple Docking Methods with MD and QSAR for Cancer Therapy

Synthetic lethality, involving the simultaneous deactivation of two genes, disrupts cellular functions or induces cell death. This study examines its role in cancer, focusing on focal adhesion kinase and Neurofibromin 2. Inhibiting FAK, crucial for synthetic lethality with NF2/Merlin, offers significant cancer treatment potential. No FAK inhibitor has been clinically approved, underscoring the need for new, effective inhibitors. The small-molecule FAK inhibitors identified in this study show promise, with SP docking, IFD, QPLD, and MD simulations revealing intricate interactions. Based on the comprehensive analysis, the MM/GBSA scores from SP docking for amprenavir, bosutinib, ferric derisomaltose, flavin adenine dinucleotide, lactulose, and tafluprost were determined as −72.81, −71.84, −76.70, −69.09, −74.86, and −65.77 kcal/mol, respectively. The MMGBSA results following IFD docking MD identified the top-performing compounds with scores of −84.0518, −75.2591, −71.8943, −84.2638, −56.3019, and −75.3873 kcal/mol, respectively. The MMGBSA results from QPLD docking MD identified the leading compounds with scores of −77.8486, −69.5773, −71.9171, N/A, −62.5716, and −66.8067 kcal/mol, respectively. In conclusion, based on the MMGBSA scores obtained using the three docking methods and the 100 ns MD simulations, and considering the combined evaluation of these methods, amprenavir, ferric derisomaltose, and bosutinib are proposed as the most promising candidates.

A novel computer vision and point cloud-based approach for accurate structural analysis of a tall irregular timber structure

Wood material has been widely used in critical heritage structures such as pagodas, totem poles, and large-scale sculptures. Conducting rigorous structural analysis is crucial to protect these structures in high-seismic regions. Typically, these types of structures are modeled using an equivalent finite element (FE) model which used simple cylinder with a constant cross section equal to the average of the top and bottom cross section. However, simplified equivalent FE models may not accurately consider the irregularities and complexities of these structures. In this paper, advanced computer vision and point cloud techniques were adopted to accurately and rapidly construct a FE model of a 30-meter irregular timber sculpture. This was achieved using video scans, computer vision-aided 3D reconstruction, point cloud processing, and mesh to solid element conversion. The refined FE model was used to conduct capacity check, mesh sensitivity study, pushover analysis, and response spectrum analysis. The results of the refined FE model were compared to an equivalent FE model. The results show: 1) the proposed numerical modeling methodology for structural analysis can efficiently and accurately measure the dimension of the irregular sculpture up to 98.2 % accuracy; 2) the lateral stiffnesses of the 30-meter irregular sculpture vary significantly (up to 42.6 %) from one direction to the other; 3) the equivalent FE model overestimated the shear and moment capacities by 20.6 % and 13.2 %, respectively; 4) on average, the equivalent FE model overestimated the shear and moment demands by 8.9 % and 5.5 %, respectively. Overall, the proposed application has demonstrated a fast, economical and accurate method to conduct seismic evaluation and design for irregular structures.

Topology optimization designed twisted conformal cooling channel for additive-manufactured hot-stamping tool

Hot stamping is a manufacturing process that can be used to produce complex-shaped parts with high mechanical properties. In this process, the part quality and the production rate are strongly influenced by the efficiency of the cooling system within the tool. Improving the efficiency of the cooling system is therefore a key factor in reducing production time and costs. Traditional cooling systems for hot stamping tools often rely on simple drilled channels, limiting their potential for optimization. But recent improvements in additive manufacturing of steel have made it possible to design and produce cooling channels of more complex shapes and therefore allow the use of innovative design approaches such as topology optimization. This paper proposes a new rational method for optimum design of cooling system for additively manufactured hot stamping tools. The proposed new methodology is based on fluid-thermal topology optimization (TO). A low-fidelity model using the Stokes-Darcy equations is used to simulate fluid flow in the cooling channels. The objective function and constraints are designed to minimize the maximum temperature of the tool surface (cooling efficiency) with limited pressure drop of the cooling system. Advanced computations techniques including parallel computation, stabilization techniques, adaptive mesh and iterative solvers are used to ensure the computation performance. The procedure developed is first tested on a simple example to check the consistency of the results obtained. Then, to demonstrate the contribution of our work to the field under study, the procedure developed is used to optimize the design of the cooling system for an industrial hot stamping punch to be additively manufactured. The obtained optimum design is compared with standard drilled channels design and the deign with shell and core technology (with insert). These comparisons clearly shows that the optimal design combined with additive manufacturing can reduce quenching time by 37 % compared to conventional drilled straight channels, with very similar pressure drop and very similar load-bearing capacity. This research offers significant potential for improving efficiency and reducing costs in hot stamping and other manufacturing processes.

Advanced Computer Technologies in Enhancing New Energy Vehicles

Advanced Computer Technologies in Enhancing New Energy Vehicles

Visual Search Interactive Model for Artificial Intelligence Robotics Model forthe Agricultural Field Analysis

The Visual Search Interactive Model for Artificial Intelligence (AI) is designed to enhance the efficiency and effectiveness of visual data analysis across various applications. By leveraging advanced computer vision techniques and machine learning algorithms, this model enables AI systems to interpret and analyze visual information in real-time, facilitating tasks such as object recognition, image classification, and scene understanding. The interactive nature of the model allows users to engage with the AI, refining searches and improving outcomes through iterative feedback. This paper introduces the Auxiliary Clustering k-means Machine Learning (AC k-means ML) model, designed to enhance agricultural efficiency through advanced data analysis and robotic integration. The study evaluates the performance of the AC k-means ML model using a dataset comprising 1,950 samples, achieving an overall accuracy of 91.5% and a precision of 89.2%. Key performance metrics such as F1 scores averaged 88.6%, with the highest individual cluster accuracy reaching 96% for Cluster 10. In addition to data classification, the model facilitated the completion of 250 tasks with a remarkable success rate of 92%, while maintaining an average task completion time of 15.4 minutes and an energy consumption of just 0.5 kWh per task. The implementation of the AC k-means ML model resulted in a 15% increase in crop yield and substantial cost savings estimated at $2,000. With a user satisfaction score averaging 8.7 and an adaptability score of 9.0, the findings indicate that the integration of machine learning and robotics significantly optimizes agricultural processes, promoting sustainability and efficiency in farming practices.

Evaluating the Seismic Resilience of Newly Constructed Concrete Building in Zinda Jan District After the Devastating October 2023 Earthquake in Herat, Afghanistan

This study aims to evaluate the impact of the October 2023 earthquake on the Zinda Jan district, focusing on the structural integrity of more than 2000 newly constructed buildings situated near fault lines. The specific objective is to identify any vulnerabilities in the design of these structures. Advanced computer analyses, including Linear and Non-linear (Push-over analysis) assessments using Etabs software, were employed to investigate the structural performance of the buildings. The analysis revealed significant insights into the structural integrity of the new constructions. It was observed that certain central columns exhibited inadequate strength, thereby posing a considerable risk of failure during seismic events. This vulnerability primarily stems from a disparity in strength between columns and beams, with the latter being stronger. This research contributes to the field by emphasizing the critical role of meticulous design and analysis in safeguarding buildings located in earthquake-prone regions

Using advanced computing to improve outcome monitoring in substance use disorder treatment in Alaska

Abstract Issue In Alaska, crime associated with substance misuse is a massive public health and safety concern costing over $2.3 billion annually. Government officials make substantial investments to address this challenge but have little ability to monitor the long-term effectiveness of these interventions. Treatment providers are also stifled by minimal feedback regarding their lasting impact. While government databases exist that contain relevant information related to long-term treatment outcomes, low knowledge transfer continues to occur between these big data systems and treatment providers. Description To determine if emerging database technology can effectively monitor long-term recidivism outcomes, a prototype was implemented by Alaska’s leading treatment provider, Set Free Alaska. The Recidivism Tracking Interface is an innovative database system that strategically connects treatment records with the criminal justice system database. While maintaining high confidentiality and security standards, the first-of-its-kind interface assessed long-term recidivism outcomes of Set Free Alaska’s former clients from 2010 to 2023. Results Of those who successfully completed treatment (n = 970), only 12.06% were convicted of a new crime with an average of 1,167 days between discharge and new criminal charges. The current recidivism rate in Alaska is 66.3%. In addition to recidivism outcomes, the interface also revealed data incredibly useful for informing treatment services and relapse prevention practices. The Recidivism Tracking Interface effectively demonstrated that advanced computing systems can be utilized to monitor long-term outcomes in a manner that was previously unavailable to treatment providers. Lessons In the age of advanced cloud computing and generative AI, treatment providers around the world and their government partners can overcome current knowledge transfer barriers to monitor long-term outcomes in a manner that is automated, inexpensive, and easy to use. Key messages • Advanced computing offers new opportunities to improve long-term outcome monitoring. • Expanding secure access to relevant government databases can ultimately improve treatment outcomes and advance outcome-based funding models.

Analysis of etched drain based Cylindrical agate‐all‐around tunnel field effect transistor based static random access memory cell design

AbstractThis paper aims to propose a novel method for designing an static random access memory (SRAM) cell using an etched drain based Cyl GAA TFET with a hetero‐substrate material and an elevated density strip. The aim is to reduce power dissipation and improve stability, as demonstrated through analysis utilizing static noise margin (SNM) as well as N‐curve methods. With respect to the 16 nm MOSFET based SRAM cell, the proposed device‐based SRAM cell shows significant improvements with a 68.305% reduction in leakage power, a 15.58% increase in static voltage noise margin (SVNM), an 8.623% increase in static current noise margin (SINM), an 8.152% increase in write trip voltage (WTV), a 12.86% increase in write trip current (WTI), a 27.62% increase in static power noise margin (SPNM), and a 19.95% increase in write trip power (WTP). The design is implemented and analyzed using Cadence Virtuoso software, and a novel approach of look up tables and Verilog A is utilized for the device to circuit application. These results indicate promising advancements in the design of SRAM cells, which could have significant implications for the development of advanced computer systems.

Anisotropy of radiation-induced defects in Yb-implanted β-Ga2O3

RE-doped β-Ga2O3 seems attractive for future high-power LEDs operating in high irradiation environments. In this work, we pay special attention to the issue of radiation-induced defect anisotropy in β-Ga2O3, which is crucial for device manufacturing. Using the RBS/c technique, we have carefully studied the structural changes caused by implantation and post-implantation annealing in two of the most commonly used crystallographic orientations of β-Ga2O3, namely the (-201) and (010). The analysis was supported by advanced computer simulations using the McChasy code. Our studies reveal a strong dependence of the structural damage induced by Yb-ion implantation on the crystal orientation, with a significantly higher level of extended defects observed in the (-201) direction than for the (010). In contrast, the concentration and behavior of simple defects seem similar for both oriented crystals, although their evolution suggests the co-existence of two different types of defects in the implanted zone with their different sensitivity to both, radiation and annealing. It has also been found that Yb ions mostly occupy the interstitial positions in β-Ga2O3 crystals that remain unchanged after annealing. The location is independent of the crystal orientations. We believe that these studies noticeably extend the knowledge of the radiation-induced defect structure, because they dispel doubts about the differences in the damage level depending on crystal orientation, and are important for further practical applications.

Fine-art recognition using convolutional transformers

Digital image processing is a constantly evolving field encompassing a wide range of techniques and applications. Researchers worldwide are continually developing various algorithms across multiple fields to achieve accurate image classification. Advanced computer vision algorithms are crucial for architectural and artistic analysis. The digitalization of art has significantly enhanced the accessibility and conservation of fine-art paintings, yet the risk of art theft remains a significant challenge. Improving art security necessitates the precise identification of fine-art paintings. Although current recognition systems have shown potential, there is significant scope for enhancing their efficiency. We developed an improved recognition system for categorizing fine-art paintings using convolutional transformers, specified by an attention mechanism to enhance focused learning on the data. As part of the most advanced architectures in the deep learning family, transformers are empowered by a multi-head attention mechanism, thus improving learning efficiency. To assess the performance of our model, we compared it with those developed using four pre-trained networks: ResNet50, VGG16, AlexNet, and ViT. Each pre-trained network was integrated into a corresponding state-of-the-art model as the first processing blocks. These four state-of-the-art models were constructed under the transfer learning strategy, one of the most commonly used approaches in this field. The experimental results showed that our proposed system outperformed the other models. Our study also highlighted the effectiveness of using convolutional transformers for learning image features.

Novel method to assess anisotropy in formability using DIC

In this study, a novel technique was developed to identify localized neck of a tensile sample based on the curvature of the surface that is expected to work with any metal in which a localized neck forms prior to fracture. Moreover, a MATLAB-based computational tool has been developed to conduct advanced mathematical computations and numerical analysis on data generated from uniaxial tensile test of DP980 steel coupled with Digital Image Correlation (DIC) based on the novel curvature method. The presented curvature technique is a geometry-based approach that uses the specimen's surface profile and groove geometry to detect localized necking, avoiding the limitations of strain-based methods in distinguishing between localized and diffuse necking. A detailed analysis was conducted on the accuracy of the onset and anisotropy of localized neck. The results of the study revealed that specimens fabricated with 30-degree orientation with respect to the Rolling Direction (RD) of the sheet metal, exhibit a higher level of total strain at the onset of the localized necking, indicating the influence of anisotropy on the material's behavior for DP980. Moreover, consistent R-values were observed among specimens with the same orientation with respect to the RD, exhibiting a rising trend of R-value for orientations from zero to 60-degree, followed by a decrease from 60 to 90-degree. Furthermore, the results exhibited a negative linear relationship between R-values and the magnitude of thinning strain.

Unraveling the Anionic Redox Chemistry in Aqueous Zinc‐MnO2 Batteries

AbstractActivating anionic redox reaction (ARR) has attracted a great interest in Li/Na‐ion batteries owing to the fascinating extra‐capacity at high operating voltages. However, ARR has rarely been reported in aqueous zinc‐ion batteries (AZIBs) and its possibility in the popular MnO2‐based cathodes has not been explored. Herein, the novel manganese deficient MnO2 micro‐nano spheres with interlayer “Ca2+‐pillars” (CaMnO‐140) are prepared via a low‐temperature (140 °C) hydrothermal method, where the Mn vacancies can trigger ARR by creating non‐bonding O 2p states, the pre‐intercalated Ca2+ can reinforce the layered structure and suppress the lattice oxygen release by forming Ca−O configurations. The tailored CaMnO‐140 cathode demonstrates an unprecedentedly high rate capability (485.4 mAh g−1 at 0.1 A g−1 with 154.5 mAh g−1 at 10 A g−1) and a marvelous long‐term cycling durability (90.6 % capacity retention over 5000 cycles) in AZIBs. The reversible oxygen redox chemistry accompanied by CF3SO3− (from the electrolyte) uptake/release, and the manganese redox accompanied by H+/Zn2+ co‐insertion/extraction, are elucidated by advanced synchrotron characterizations and theoretical computations. Finally, pouch‐type CaMnO‐140//Zn batteries manifest bright application prospects with high energy, long life, wide‐temperature adaptability, and high operating safety. This study provides new perspectives for developing high‐energy cathodes for AZIBs by initiating anionic redox chemistry.

Unraveling the Anionic Redox Chemistry in Aqueous Zinc-MnO2 Batteries.

Activating anionic redox reaction (ARR) has attracted a great interest in Li/Na-ion batteries owing to the fascinating extra-capacity at high operating voltages. However, ARR has rarely been reported in aqueous zinc-ion batteries (AZIBs) and its possibility in the popular MnO2-based cathodes has not been explored. Herein, the novel manganese deficient MnO2 micro-nano spheres with interlayer "Ca2+-pillars" (CaMnO-140) are prepared via a low-temperature (140 °C) hydrothermal method, where the Mn vacancies can trigger ARR by creating non-bonding O 2p states, the pre-intercalated Ca2+ can reinforce the layered structure and suppress the lattice oxygen release by forming Ca-O configurations. The tailored CaMnO-140 cathode demonstrates an unprecedentedly high rate capability (485.4 mAh g-1 at 0.1 A g-1 with 154.5 mAh g-1 at 10 A g-1) and a marvelous long-term cycling durability (90.6 % capacity retention over 5000 cycles) in AZIBs. The reversible oxygen redox chemistry accompanied by CF3SO3 - (from the electrolyte) uptake/release, and the manganese redox accompanied by H+/Zn2+ co-insertion/extraction, are elucidated by advanced synchrotron characterizations and theoretical computations. Finally, pouch-type CaMnO-140//Zn batteries manifest bright application prospects with high energy, long life, wide-temperature adaptability, and high operating safety. This study provides new perspectives for developing high-energy cathodes for AZIBs by initiating anionic redox chemistry.

Deep Analogical Generative Design and Evaluation: Integration of Stable Diffusion and LoRA

Abstract The rapid evolution of generative design through artificial intelligence has opened new avenues for innovative product styling. Integrating this efficient generative technology with established professional theories presents a novel challenge in contemporary international design research. In response to this challenge, this paper introduces a pioneering and collaborative approach for the swift generation of automobile styling designs. The primary objective is to investigate an intelligent generation method that incorporates analogical reasoning and Stable Diffusion to support industrial designers in innovating product styling. This study scrutinizes traditional analogical reasoning design alongside the intelligent analogical reasoning design proposed herein, elucidating the distinctions through multidimensional comparisons using illustrative examples. The proposed methodological framework encompasses several key steps. Initially, a dataset comprising branded automobile images is meticulously constructed. Subsequently, an exclusive style model is trained leveraging Stable Diffusion techniques, coupled with advanced computer graphics and machine learning methodologies. Following this, design requirements are inputted, facilitating intelligent analogical reasoning design across multiple spatial dimensions to yield diverse and innovative automobile styling solutions. Finally, eye-tracking experiments are conducted to quantitatively compare the traditional analogical reasoning design approach with the Stable Diffusion-based analogical reasoning design method. The results substantiate that the latter effectively generates innovative and diversified automobile design solutions. This research contributes to enhancing the quality of automobile styling design, optimizing the design efficiency of enterprises, and catalyzing innovation in the automobile styling design process.

Investigating the impact of acetylenic linkage in C20 fullerene: Utilization in optoelectronic devices and as anode material

This study delves into the diverse characteristics of C80 fulleryne, derived from the incorporation of acetylenic linkages into each chain of the smallest fullerene, C20. Utilizing advanced theoretical computations, we confirm the stability of C80 fulleryne. Notably, its possession of a finite energy gap (0.743 eV) categorizes it as a semiconductor. Further enlightenment into its structural stability, bonding and reactivity stems from an exploration of different energy components, topological descriptors of electron density and chemical reactivity parameters. C80 fulleryne can act as radical scavenger owing to its higher electron affinity (5.5 eV). Spectral analysis revealed the C80 fulleryne’s absorption within the near-infrared region and its intriguing optical transparency with negligible loss in specific regions of the electromagnetic spectrum. Additionally, our investigation scrutinized the viability of C80 fulleryne as an anode material in Lithium-ion batteries. The presence of low adsorption energy (−1.693 eV) and significant amount of Bader charge transfer (0.917 e) between Li-ion and C atoms of C80 fulleryne confirms that Li-ion gets chemisorbed on the C80 fulleryne. Remarkably, this cage acts as a storehouse to host 12 Li ions, precisely one for each of its constituent pentagons within the C80 fulleryne structure, bearing a theoretical capacitance of 335 mAhg−1.

Non-invasive detection of hydraulic cylinder leakage using computer vision and time-frequency analysis

ABSTRACT This study presents a meticulous investigation facilitated by a bespoke high-pressure test rig. The rig stands as a cornerstone of the research endeavour, providing the capability to simulate diverse leakage scenarios under controlled conditions. With its capacity to replicate conditions akin to real-world hydraulic systems, including various levels of severity such as healthy operation, moderate leakage and severe leakage. The study delves into the intricate analysis of time-series discharge flow rate signals within this experimental framework. The study utilizes sophisticated signal processing techniques, particularly the Continuous Wavelet Transform (CWT), to observe frequency components and temporal occurrences. Despite prevalent challenges distinguishing between leakage severity levels, the CWT-based analysis provides crucial insights into the dominant low frequencies (2.3–3.3 hz) characterising all leakage conditions. An advanced computer vision-based methodology is devised to address the complexities inherent in leakage differentiation, integrating cutting-edge models such as You Only Look Once (YOLO-V7) and You Only Look Once-Neural Architecture Search (YOLO-NAS). These models are meticulously trained using annotated CWT images of flow rates corresponding to different leakage conditions. Notably, the superiority of YOLO-NAS in terms of both speed and accuracy underscores its efficacy in automated leakage detection. In summary, this comprehensive approach, underpinned by the innovative hydraulic test rig and advanced signal processing coupled with state-of-the-art computer vision techniques, presents a significant advancement in the realm of internal leakage detection in hydraulic systems.

Depression Detection through Integrative Multimodal Signals: Exploring Advanced Computational Techniques

Depression Detection through Integrative Multimodal Signals: Exploring Advanced Computational Techniques

All-Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons.

Artificial neurons and synapses are crucial for efficiently implementing spiking neural networks (SNNs) in hardware. The distinct functional requirements of artificial neurons and synapses present significant challenges in the implementation of area- and energy-efficient SNNs. This study reports an all-ferroelectric SNN system through co-optimization of material properties and device configurations using wafer-scale atomic layer deposition. For the first time, a double-gate (DG) morphotropic phase boundary-based thin-film transistor (MPBTFT) is utilized for a leaky integrate-and-fire (LIF) neuron. The DG MPBTFT-based LIF neuron eliminates the need for capacitors and reset circuits, thereby enhancing area and energy efficiency. The DG configuration demonstrates various neuronal functions with high reliability. Co-optimizing materials and devices significantly enhance the performance and functional versatility of artificial neurons and synapses. Meticulous material engineering facilitates the seamless co-integration of DG MPBTFT-based neurons, ferroelectric thin-film transistor (TFT)-based synapses, and normal TFTs on a single wafer. All-ferroelectric SNN systems achieved a high classification accuracy of 94.9%, thereby highlighting the potential of DG MPBTFT-based LIF neurons for advanced neuromorphic computing.

Dual Leap Motion Controller 2: A Robust Dataset for Multi-view Hand Pose Recognition

This paper presents Multi-view Leap2 Hand Pose Dataset (ML2HP Dataset), a new dataset for hand pose recognition, captured using a multi-view recording setup with two Leap Motion Controller 2 devices. This dataset encompasses a diverse range of hand poses, recorded from different angles to ensure comprehensive coverage. The dataset includes real images with the associated precise and automatic hand properties, such as landmark coordinates, velocities, orientations, and finger widths. This dataset has been meticulously designed and curated to maintain a balance in terms of subjects, hand poses, and the usage of right or left hand, ensuring fairness and parity. The content includes 714,000 instances from 21 subjects of 17 different hand poses (including real images and 247 associated hand properties). The multi-view setup is necessary to mitigate hand occlusion phenomena, ensuring continuous tracking and pose estimation required in real human-computer interaction applications. This dataset contributes to advancing the field of multimodal hand pose recognition by providing a valuable resource for developing advanced artificial intelligence human computer interfaces.