arXiv subjects

Ali Amini

Publications and source records attributed to Ali Amini.

8 recordsLinked to original sources

arXiv2026

From Full Boards to Tiny Defects: Scale-Aware Tile Inference with Topology-Aware Merging for High-Resolution PCB Defect Detection

High-resolution printed circuit board (PCB) inspection suffers from resolution collapse when full-board images are resized to standard detector inputs: micro-scale defects shrink to a few pixels and are missed. Tile-based inference preserves local detail but introduces boundary artefacts at tile edges, causing split detections and false negatives. We present a systematic comparison of five inference strategies evaluated on two high-resolution PCB defect datasets, PCB-Defect (230 images, 1704 annotations) and HRIPCB (693 images, 2 953 annotations), spanning six defect classes. We show that training-inference scale consistency is critical: a detector trained on full images collapses to mAP@50 = 0.01 under tile inference, while the same architecture trained on 640*640 tile crops achieves 0.72 and 0.94 on the two datasets respectively. We further exploited Topology-Aware Tile Merging (TA-TM), a training-free post-processing method that builds a tile-adjacency graph and adjusts boundary-sensitive detection scores using neighbour-tile agreement before global NMS. Across both datasets, adding 128 px tile overlap raises boundary-zone recall from ~26-63% to ~70-100%, TA-TM achieves the best mAP@50 on both benchmarks, and tile inference recovers 46-100% of small defects missed entirely by full-image methods. Results are consistent across datasets, confirming the generalizability of the proposed strategy. TA-TM requires no retraining and is architecture-agnostic, making it directly applicable to existing PCB inspection pipelines.

cs.CV↗

arXiv2025

ADHDeepNet From Raw EEG to Diagnosis: Improving ADHD Diagnosis through Temporal-Spatial Processing, Adaptive Attention Mechanisms, and Explainability in Raw EEG Signals

Attention Deficit Hyperactivity Disorder (ADHD) is a common brain disorder in children that can persist into adulthood, affecting social, academic, and career life. Early diagnosis is crucial for managing these impacts on patients and the healthcare system but is often labor-intensive and time-consuming. This paper presents a novel method to improve ADHD diagnosis precision and timeliness by leveraging Deep Learning (DL) approaches and electroencephalogram (EEG) signals. We introduce ADHDeepNet, a DL model that utilizes comprehensive temporal-spatial characterization, attention modules, and explainability techniques optimized for EEG signals. ADHDeepNet integrates feature extraction and refinement processes to enhance ADHD diagnosis. The model was trained and validated on a dataset of 121 participants (61 ADHD, 60 Healthy Controls), employing nested cross-validation for robust performance. The proposed two-stage methodology uses a 10-fold cross-subject validation strategy. Initially, each iteration optimizes the model's hyper-parameters with inner 2-fold cross-validation. Then, Additive Gaussian Noise (AGN) with various standard deviations and magnification levels is applied for data augmentation. ADHDeepNet achieved 100% sensitivity and 99.17% accuracy in classifying ADHD/HC subjects. To clarify model explainability and identify key brain regions and frequency bands for ADHD diagnosis, we analyzed the learned weights and activation patterns of the model's primary layers. Additionally, t-distributed Stochastic Neighbor Embedding (t-SNE) visualized high-dimensional data, aiding in interpreting the model's decisions. This study highlights the potential of DL and EEG in enhancing ADHD diagnosis accuracy and efficiency.

cs.LG↗

arXiv2025

Survey Transfer Learning: Recycling Data with Silicon Responses

As researchers increasingly turn to large language models (LLMs) to generate synthetic survey data, less attention has been paid to alternative AI paradigms given environmental costs of LLMs. This paper introduces Survey Transfer Learning (STL), which develops transfer learning paradigms from computer science for survey research to recycle existing survey data and generate empirically grounded silicon responses. Inspired by political behavior theory, STL leverages shared demographic variables with high predictive power in a polarized American context to transfer knowledge across surveys. Using a neural network pre-trained on the Cooperative Election Study (CES) 2020, freezing early layers to preserve learned structure, and fine-tuning top layers on the American National Election Studies (ANES) 2020, STL generates silicon responses CES 2022 and in held-out ANES 2020 data with accuracy rates of up to 93 percent. Results show that STL outperforms LLMs, especially on sensitive measures such as racial resentment. While LLMs silicon samples are costly and opaque, STL generates empirically grounded silicon responses with high individual-level accuracy, potentially helping to mitigate key challenges in social science and the polling industry.

cs.AI↗

arXiv2024

Model-Agnostic Meta-Learning for Fault Diagnosis of Induction Motors in Data-Scarce Environments with Varying Operating Conditions and Electric Drive Noise

Reliable mechanical fault detection with limited data is crucial for the effective operation of induction machines, particularly given the real-world challenges present in industrial datasets, such as significant imbalances between healthy and faulty samples and the scarcity of data representing faulty conditions. This research introduces an innovative meta-learning approach to address these issues, focusing on mechanical fault detection in induction motors across diverse operating conditions while mitigating the adverse effects of drive noise in scenarios with limited data. The process of identifying faults under varying operating conditions is framed as a few-shot classification challenge and approached through a model-agnostic meta-learning strategy. Specifically, this approach begins with training a meta-learner across multiple interconnected fault-diagnosis tasks conducted under different operating conditions. In this stage, cross-entropy is utilized to optimize parameters and develop a robust representation of the tasks. Subsequently, the parameters of the meta-learner are fine-tuned for new tasks, enabling rapid adaptation using only a small number of samples. This method achieves excellent accuracy in fault detection across various conditions, even when data availability is restricted. The findings indicate that the proposed model outperforms other sophisticated techniques, providing enhanced generalization and quicker adaptation. The accuracy of fault diagnosis reaches a minimum of 99%, underscoring the model's effectiveness for reliable fault identification.

eess.SY↗

arXiv2024

A Multiphysics Analysis and Investigation of Soft Magnetics Effect on IPMSM: Case Study Dynamometer

Nowadays, Interior Permanent Magnet Synchronous Motors (IPMSMs) are taken into attention in the industry owing to their advantages. Moreover, in many cases, performing static tests is not enough, and investigating electric machines under dynamic conditions is necessary. Accordingly, by employing a dynamometer system, the dynamic behavior of the electric machine under test is investigated. Among the dynamometers, the best is the Alternating (AC) dynamometer because the basic dynamometers cannot take loads with high complexity. So, in the following study, two IPMSM with V-type and Delta-type rotor configurations are designed and suggested to employ in AC dynamometer. Any non-ideality in the electric machines of AC dynamometers, electrically and mechanically, causes errors in the measurement of the motor under test. Electrically and mechanically, the behavior of a system significantly depends on the used soft magnetics besides its physical and magnetic configuration. Accordingly, by performing a Multiphysics analysis and using the FEM tool to change the soft magnetics in the rotor and stator core, comparing the electric motors' behavior in the AC dynamometer is investigated under the same operating conditions electrically and mechanically. Finally, which soft magnetics is more satisfactory for the AC dynamometer can be seen.

eess.SY↗

arXiv2024

Estimation Enhancing in Optoelectronic Property: A Novel Approach Using Orbital Interaction Parameters and Tight-Binding

This paper advocates for an innovative approach designed for estimating optoelectronic properties of quantum structures utilizing Tight-Binding (TB) theory. Predicated on the comparative analysis between estimated and actual properties, the study strives to validate the efficacy of this proposed technique; focusing notably on the computation of bandgap energy. It is observed that preceding methodologies offered a restricted accuracy when predicting complex structures like super-lattices and quantum wells. To address this gap, we propose a methodology involving three distinct phases using orbital interaction parameters (OIPs) and the TB theory. The research employed Aluminium Arsenide (AlAs) and Gallium Arsenide (GaAs) as the primary bulk materials. Our novel approach introduces a computation framework that first focuses on bulk computation, subsequently expanding to super-lattice structures. The findings of this research demonstrate promising results regarding the accuracy of predicated optoelectronic properties, particularly the cut-off wavelength. This study paves the way for future research, potentially enhancing the precision of the proposed methodology and its application scope within the field of quantum optoelectronics.

quant-ph↗

arXiv2022

HyperDbg: Reinventing Hardware-Assisted Debugging (Extended Version)

Software analysis, debugging, and reverse engineering have a crucial impact in today's software industry. Efficient and stealthy debuggers are especially relevant for malware analysis. However, existing debugging platforms fail to address a transparent, effective, and high-performance low-level debugger due to their detectable fingerprints, complexity, and implementation restrictions. In this paper, we present HyperDbg, a new hypervisor-assisted debugger for high-performance and stealthy debugging of user and kernel applications. To accomplish this, HyperDbg relies on state-of-the-art hardware features available in today's CPUs, such as VT-x and extended page tables. In contrast to other widely used existing debuggers, we design HyperDbg using a custom hypervisor, making it independent of OS functionality or API. We propose hardware-based instruction-level emulation and OS-level API hooking via extended page tables to increase the stealthiness. Our results of the dynamic analysis of 10,853 malware samples show that HyperDbg's stealthiness allows debugging on average 22% and 26% more samples than WinDbg and x64dbg, respectively. Moreover, in contrast to existing debuggers, HyperDbg is not detected by any of the 13 tested packers and protectors. We improve the performance over other debuggers by deploying a VMX-compatible script engine, eliminating unnecessary context switches. Our experiment on three concrete debugging scenarios shows that compared to WinDbg as the only kernel debugger, HyperDbg performs step-in, conditional breaks, and syscall recording, 2.98x, 1319x, and 2018x faster, respectively. We finally show real-world applications, such as a 0-day analysis, structure reconstruction for reverse engineering, software performance analysis, and code-coverage analysis.

cs.CR↗

arXiv2020

A bioinspired optically transparent tough glass composite

Glasses have numerous applications due to their exceptional transparency, however, poor fracture and impact resistance limit their applications as an engineering material. One relatively recent approach to improve the mechanical properties of materials is through bio-inspiration. Structural biological composites such as nacre, the protective inner layer of mollusk shells, offer far superior mechanical properties relative to their constituents. This has motivated researchers to mimic the design principles in natural composites to create tough transparent materials. However, current bio-inspired materials lack fabrication scalability or offer poor optical transmission. Here, an efficient, scalable bulk process is developed for creating optically transparent tough composites, resulting in a nacreous glass composite material with a four-fold increase in fracture toughness and a three-fold increase in flexural strength compared to conventional structural glasses, and with a 73% of average optical transmittance. The composite consists of glass flakes and poly (methyl methacrylate) (PMMA) assembled utilizing a centrifuge-based fabrication method that aligns and compacts the flakes into layers. To optimize the transparency of the structure, the refractive indices of the PMMA and glass are matched. Based on the results, this nacreous glass composite is proposed as a potential alternative in diverse architectural, vehicular, and electronics applications.

physics.app-ph↗