arXiv subjects

Gholamreza Anbarjafari

Publications and source records attributed to Gholamreza Anbarjafari.

At least 19 recordsLinked to original sources

arXiv2026

Moving Like a Human: Ego-Motion-Normalized Temporal Signatures for Real-Time Aerial Person Tracking on Milliwatt-Class Hardware

Follow-me person tracking must run on the drone itself, where affordable companion computers offer only a few effective int8 GFLOP/s. At typical follow distances a person spans 10-60 pixels, indistinguishable from clutter and beyond the reach of single-frame appearance detectors. The missing evidence is temporal and belongs in the input representation, computed analytically, rather than in learned temporal machinery. EMTS-Det is a five-stage system that estimates ego-motion, converts each frame into ego-motion-normalized residual-motion channels, detects person centers with a 22k-parameter, 7.6-MFLOP network, tracks a locked target with a Kalman filter in stabilized coordinates, and verifies tracks with a 1-D convolutional classifier of human motion (ROC AUC 0.941). Training uses a synthetic-motion curriculum with motion channels generated by the deployed ego-motion code. Multi-seed ablations locate the value in generalization: on held-out VisDrone-DET a luminance-only variant collapses to 0.051 AP25 versus 0.415, as does YOLOv8n fine-tuned identically despite 1,100 times the compute, while the deployed int8 detector reaches 0.694 AP25 in-domain and 0.444 on this split. Temporal-shift modules lower accuracy, so the deployed detector is stateless. Silent int8 calibration failures are documented; min-max calibration with propagated caches matches float within 0.008 AP. On a Raspberry Pi Zero 2W the pipeline runs at 31.85 FPS with 0.462 AP25 and 0.714 recall over 1,000 real-world UAV videos, versus 1.95 FPS and 0.172 AP25 for YOLOv8n. A 57-second field sequence shows auto-lock at 1.3 s, 97.9% lock recall, and recovery from all nine occlusions with zero false re-locks.

cs.CV↗

arXiv2026

Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks

Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the true probability of correctness. We propose a quantum-inspired classification head architecture that projects backbone features into a complex-valued Hilbert space and evolves them under a learned unitary transformation parameterised via the Cayley map. Through a controlled hybrid experimental design - training a single shared backbone and comparing lightweight interchangeable heads - we isolate the effect of complex-valued unitary representations on calibration. Our ablation study on CIFAR-10 reveals that the unitary magnitude head (complex features evolved under a Cayley unitary, read out via magnitude and softmax) achieves an Expected Calibration Error (ECE) of 0.0146, representing a 2.4x improvement over a standard softmax head (0.0355) and a 3.5x improvement over temperature scaling (0.0510). Surprisingly, replacing the softmax readout with a Born rule measurement layer - the quantum-mechanically motivated approach - degrades calibration to an ECE of 0.0819. On the CIFAR-10H human-uncertainty benchmark, the wave function head achieves the lowest KL-divergence (0.336) to human soft labels among all compared methods, indicating that complex-valued representations better capture the structure of human perceptual ambiguity. We provide theoretical analysis connecting norm-preserving unitary dynamics to calibration through feature-space geometry, report negative results on out-of-distribution detection and sentiment analysis to delineate the method's scope, and discuss practical implications for safety-critical applications. Code is publicly available.

cs.LG↗

arXiv2026

A Multi-physics Simulation Framework for High-power Microwave Counter-unmanned Aerial System Design and Performance Evaluation

The proliferation of small unmanned aerial systems (sUAS) operating under autonomous guidance has created an urgent need for non-kinetic neutralization methods that are immune to conventional radio-frequency jamming. This paper presents a comprehensive multi-physics simulation framework for the design and performance evaluation of a high-power microwave (HPM) counter-UAS system operating at 2.45\,GHz. The framework integrates electromagnetic propagation modelling, antenna pattern analysis, electromagnetic coupling to unshielded drone wiring harnesses, and a sigmoid-based semiconductor damage probability model calibrated to published CMOS latchup thresholds. A 10{,}000-trial Monte Carlo analysis incorporating stochastic variations in transmitter power, antenna pointing error, target wire orientation, polarization mismatch, and component damage thresholds yields system-level kill probabilities with 95\% confidence intervals. For a baseline configuration of 25\,kW continuous-wave power and a 60\,cm parabolic reflector (21.2\,dBi gain), the Monte Carlo simulation predicts a kill probability of $51.4\pm1.0$\% at 20\,m, decreasing to $13.1\pm0.7$\% at 40\,m. Pulsed operation at 500\,kW peak power (1\% duty cycle) extends the 90\% kill range from approximately 18\,m to 88\,m. The framework further provides parametric design maps, safety exclusion zone calculations compliant with ICNIRP 2020 guidelines, thermal management requirements, and waveguide mode analysis. All simulation codes and results are provided for full reproducibility.

eess.SY↗

arXiv2026

Responsible AI: The Good, The Bad, The AI

The rapid proliferation of artificial intelligence across organizational contexts has generated profound strategic opportunities while introducing significant ethical and operational risks. Despite growing scholarly attention to responsible AI, extant literature remains fragmented and is often adopting either an optimistic stance emphasizing value creation or an excessively cautious perspective fixated on potential harms. This paper addresses this gap by presenting a comprehensive examination of AI's dual nature through the lens of strategic information systems. Drawing upon a systematic synthesis of the responsible AI literature and grounded in paradox theory, we develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions. Our framework advances theoretical understanding by conceptualizing responsible AI governance as the dynamic management of paradoxical tensions between value creation and risk mitigation. We provide formal propositions demonstrating that trade-off approaches amplify rather than resolve these tensions, and we develop a taxonomy of paradox management strategies with specified contingency conditions. For practitioners, we offer actionable guidance for developing governance structures that neither stifle innovation nor expose organizations to unacceptable risks. The paper concludes with a research agenda for advancing responsible AI governance scholarship.

cs.AI↗

arXiv2026

A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge

The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. However, existing agent frameworks often suffer from architectural rigidity, vendor lock-in, and prohibitive complexity that impedes rapid prototyping and deployment. This paper presents AgentForge, a lightweight, open-source Python framework designed to democratize the construction of LLM-driven autonomous agents through a principled modular architecture. AgentForge introduces three key innovations: (1) a composable skill abstraction that enables fine-grained task decomposition with formally defined input-output contracts, (2) a unified LLM backend interface supporting seamless switching between cloud-based APIs and local inference engines, and (3) a declarative YAML-based configuration system that separates agent logic from implementation details. We formalize the skill composition mechanism as a directed acyclic graph (DAG) and prove its expressiveness for representing arbitrary sequential and parallel task workflows. Comprehensive experimental evaluation across four benchmark scenarios demonstrates that AgentForge achieves competitive task completion rates while reducing development time by 62% compared to LangChain and 78% compared to direct API integration. Latency measurements confirm sub-100ms orchestration overhead, rendering the framework suitable for real-time applications. The modular design facilitates extension: we demonstrate the integration of six built-in skills and provide comprehensive documentation for custom skill development. AgentForge addresses a critical gap in the LLM agent ecosystem by providing researchers and practitioners with a production-ready foundation for constructing, evaluating, and deploying autonomous agents without sacrificing flexibility or performance.

cs.AI↗

arXiv2025

Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium

Contemporary autoregressive transformers operate in open loop: each hidden state is computed in a single forward pass and never revised, causing errors to propagate uncorrected through the sequence. We identify this open-loop bottleneck as a fundamental architectural limitation underlying well-documented failures in long-range reasoning, factual consistency, and multi-step planning. To address this limitation, we introduce the closed-loop prediction principle, which requires that models iteratively refine latent representations until reaching a self-consistent equilibrium before committing to each token. We instantiate this principle as Equilibrium Transformers (EqT), which augment standard transformer layers with an Equilibrium Refinement Module that minimizes a learned energy function via gradient descent in latent space. The energy function enforces bidirectional prediction consistency, episodic memory coherence, and output confidence, all computed without external supervision. Theoretically, we prove that EqT performs approximate MAP inference in a latent energy-based model, establish linear convergence guarantees, and show that refinement improves predictions precisely on hard instances where one-shot inference is suboptimal. The framework unifies deep equilibrium models, diffusion language models, and test-time training as special cases. Preliminary experiments on the binary parity task demonstrate +3.28% average improvement on challenging sequences, with gains reaching +8.07% where standard transformers approach random performance, validating that the benefit of deliberation scales with task difficulty. Just as attention mechanisms resolved the sequential bottleneck of recurrent networks, we propose that closed-loop equilibrium may resolve the commitment bottleneck of open-loop autoregression, representing a foundational step toward language models.

cs.LG↗

arXiv2025

Dynamic Nested Hierarchies: Pioneering Self-Evolution in Machine Learning Architectures for Lifelong Intelligence

Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures that hinder continual adaptation and lifelong learning. Building upon the nested learning paradigm, which decomposes models into multi-level optimization problems with fixed update frequencies, this work proposes dynamic nested hierarchies as the next evolutionary step in advancing artificial intelligence and machine learning. Dynamic nested hierarchies empower models to autonomously adjust the number of optimization levels, their nesting structures, and update frequencies during training or inference, inspired by neuroplasticity to enable self-evolution without predefined constraints. This innovation addresses the anterograde amnesia in existing models, facilitating true lifelong learning by dynamically compressing context flows and adapting to distribution shifts. Through rigorous mathematical formulations, theoretical proofs of convergence, expressivity bounds, and sublinear regret in varying regimes, alongside empirical demonstrations of superior performance in language modeling, continual learning, and long-context reasoning, dynamic nested hierarchies establish a foundational advancement toward adaptive, general-purpose intelligence.

cs.LG↗

arXiv2025

A Mathematical Framework for AI Singularity: Conditions, Bounds, and Control of Recursive Improvement

AI systems improve by drawing on more compute, data, energy, and better training methods. This paper asks a precise, testable version of the "runaway growth" question: under what measurable conditions could capability escalate without bound in finite time, and under what conditions can that be ruled out? We develop an analytic framework for recursive self-improvement that links capability growth to resource build-out and deployment policies. Physical and information-theoretic limits from power, bandwidth, and memory define a service envelope that caps instantaneous improvement. An endogenous growth model couples capital to compute, data, and energy and defines a critical boundary separating superlinear from subcritical regimes. We derive decision rules that map observable series (facility power, IO bandwidth, training throughput, benchmark losses, and spending) into yes/no certificates for runaway versus nonsingular behavior. The framework yields falsifiable tests based on how fast improvement accelerates relative to its current level, and it provides safety controls that are directly implementable in practice, such as power caps, throughput throttling, and evaluation gates. Analytical case studies cover capped-power, saturating-data, and investment-amplified settings, illustrating when the envelope binds and when it does not. The approach is simulation-free and grounded in measurements engineers already collect. Limitations include dependence on the chosen capability metric and on regularity diagnostics; future work will address stochastic dynamics, multi-agent competition, and abrupt architectural shifts. Overall, the results replace speculation with testable conditions and deployable controls for certifying or precluding an AI singularity.

cs.CV↗

arXiv2025

Mapping Emotions in the Brain: A Bi-Hemispheric Neural Model with Explainable Deep Learning

Recent advances have shown promise in emotion recognition from electroencephalogram (EEG) signals by employing bi-hemispheric neural architectures that incorporate neuroscientific priors into deep learning models. However, interpretability remains a significant limitation for their application in sensitive fields such as affective computing and cognitive modeling. In this work, we introduce a post-hoc interpretability framework tailored to dual-stream EEG classifiers, extending the Local Interpretable Model-Agnostic Explanations (LIME) approach to accommodate structured, bi-hemispheric inputs. Our method adapts LIME to handle structured two-branch inputs corresponding to left and right-hemisphere EEG channel groups. It decomposes prediction relevance into per-channel contributions across hemispheres and emotional classes. We apply this framework to a previously validated dual-branch recurrent neural network trained on EmoNeuroDB, a dataset of EEG recordings captured during a VR-based emotion elicitation task. The resulting explanations reveal emotion-specific hemispheric activation patterns consistent with known neurophysiological phenomena, such as frontal lateralization in joy and posterior asymmetry in sadness. Furthermore, we aggregate local explanations across samples to derive global channel importance profiles, enabling a neurophysiologically grounded interpretation of the model's decisions. Correlation analysis between symmetric electrodes further highlights the model's emotion-dependent lateralization behavior, supporting the functional asymmetries reported in affective neuroscience.

q-bio.NC↗

arXiv2021

Responsible AI: Gender bias assessment in emotion recognition

Rapid development of artificial intelligence (AI) systems amplify many concerns in society. These AI algorithms inherit different biases from humans due to mysterious operational flow and because of that it is becoming adverse in usage. As a result, researchers have started to address the issue by investigating deeper in the direction towards Responsible and Explainable AI. Among variety of applications of AI, facial expression recognition might not be the most important one, yet is considered as a valuable part of human-AI interaction. Evolution of facial expression recognition from the feature based methods to deep learning drastically improve quality of such algorithms. This research work aims to study a gender bias in deep learning methods for facial expression recognition by investigating six distinct neural networks, training them, and further analysed on the presence of bias, according to the three definition of fairness. The main outcomes show which models are gender biased, which are not and how gender of subject affects its emotion recognition. More biased neural networks show bigger accuracy gap in emotion recognition between male and female test sets. Furthermore, this trend keeps for true positive and false positive rates. In addition, due to the nature of the research, we can observe which types of emotions are better classified for men and which for women. Since the topic of biases in facial expression recognition is not well studied, a spectrum of continuation of this research is truly extensive, and may comprise detail analysis of state-of-the-art methods, as well as targeting other biases.

cs.CV↗

arXiv2021

Ensemble approach for detection of depression using EEG features

Depression is a public health issue which severely affects one's well being and cause negative social and economic effect for society. To rise awareness of these problems, this publication aims to determine if long lasting effects of depression can be determined from electoencephalographic (EEG) signals. The article contains accuracy comparison for SVM, LDA, NB, kNN and D3 binary classifiers which were trained using linear (relative band powers, APV, SASI) and non-linear (HFD, LZC, DFA) EEG features. The age and gender matched dataset consisted of 10 healthy subjects and 10 subjects with depression diagnosis at some point in their lifetime. Several of the proposed feature selection and classifier combinations reached accuracy of 90% where all models where evaluated using 10-fold cross validation and averaged over 100 repetitions with random sample permutations.

cs.LG↗

arXiv2021

Atmospheric ray tomography for low-Z materials: implementing new methods on a proof-of-concept tomograph

Cosmic rays interacting with the atmosphere result in a flux of secondary particles including muons and electrons. Atmospheric ray tomography (ART) uses the muons and electrons for detecting objects and their composition. This paper presents new methods and a proof-of-concept tomography system developed for the ART of low-Z materials. We introduce the Particle Track Filtering (PTF) and Multi-Modality Tomographic Reconstruction (MMTR) methods. Based on Geant4 models we optimized the tomography system, the parameters of PTF and MMTR. Based on plastic scintillating fiber arrays we achieved the spatial resolution 120 $μ$m and 1 mrad angular resolution in the track reconstruction. We developed a novel edge detection method to separate the logical volumes of scanned object. We show its effectiveness on single (e.g. water, aluminum) and double material (e.g. explosive RDX in flesh) objects. The tabletop tomograph we built showed excellent agreement between simulations and measurements. We are able to increase the discriminating power of ART on low-Z materials significantly. This work opens up new routes for the commercialization of ART tomography.

physics.ins-det↗

arXiv2020

Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-based Recommendation in E-Commerce

Boosting sales of e-commerce services is guaranteed once users find more matching items to their interests in a short time. Consequently, recommendation systems have become a crucial part of any successful e-commerce services. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems during the recent few years. This growing interest is due to the security concerns in collecting personalized user behavior data, especially after the recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with his/her preferences. Our extensive experiments investigate baseline techniques (\textit{e.g.,} nearest neighbors and pattern mining algorithms) and deep learning approaches (\textit{e.g.,} recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most of the scenarios. However, we found that these models suffer more in case of long sessions when there exists drift in user interests, and when there is no enough data to model different items correctly during training. Our study suggests that using hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field.

cs.IR↗

arXiv2019

ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than $200$ teams round the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of $8.1\%$ (from $0.8917$ to $0.9639$) of CSR.

cs.CV↗

arXiv2019

On the effect of age perception biases for real age regression

Automatic age estimation from facial images represents an important task in computer vision. This paper analyses the effect of gender, age, ethnic, makeup and expression attributes of faces as sources of bias to improve deep apparent age prediction. Following recent works where it is shown that apparent age labels benefit real age estimation, rather than direct real to real age regression, our main contribution is the integration, in an end-to-end architecture, of face attributes for apparent age prediction with an additional loss for real age regression. Experimental results on the APPA-REAL dataset indicate the proposed network successfully take advantage of the adopted attributes to improve both apparent and real age estimation. Our model outperformed a state-of-the-art architecture proposed to separately address apparent and real age regression. Finally, we present preliminary results and discussion of a proof of concept application using the proposed model to regress the apparent age of an individual based on the gender of an external observer.

cs.CV↗

arXiv2018

A Study of Language and Classifier-independent Feature Analysis for Vocal Emotion Recognition

Every speech signal carries implicit information about the emotions, which can be extracted by speech processing methods. In this paper, we propose an algorithm for extracting features that are independent from the spoken language and the classification method to have comparatively good recognition performance on different languages independent from the employed classification methods. The proposed algorithm is composed of three stages. In the first stage, we propose a feature ranking method analyzing the state-of-the-art voice quality features. In the second stage, we propose a method for finding the subset of the common features for each language and classifier. In the third stage, we compare our approach with the recognition rate of the state-of-the-art filter methods. We use three databases with different languages, namely, Polish, Serbian and English. Also three different classifiers, namely, nearest neighbour, support vector machine and gradient descent neural network, are employed. It is shown that our method for selecting the most significant language-independent and method-independent features in many cases outperforms state-of-the-art filter methods.

eess.AS↗

arXiv2018

From 2D to 3D Geodesic-based Garment Matching

A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is matched to a new source garment and rendered, resulting in augmented images in which the target garment has been retextured by using the texture of the source garment. We divide the problem into garment boundary matching based on Gaussian mixture models and then interpolate inner points using surface topology extracted through geodesic paths, which leads to a more realistic result than standard approaches. We evaluated and compared our system quantitatively by mean square error (MSE) and qualitatively using the mean opinion score (MOS), showing the benefits of the proposed methodology on our gathered dataset.

cs.CV↗

arXiv2018

Doubly Attentive Transformer Machine Translation

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks, conquering any gap between image captioning and translation. In this framework, the transformer decoder figures out how to take care of source-language words and parts of an image freely by methods for two separate attention components in an Enhanced Multi-Head Attention Layer of doubly attentive transformer, as it generates words in the target language. We find that the proposed model can effectively exploit not just the scarce multimodal machine translation data, but also large general-domain text-only machine translation corpora, or image-text image captioning corpora. The experimental results show that the proposed doubly-attentive transformer-decoder performs better than a single-decoder transformer model, and gives the state-of-the-art results in the English-German multimodal machine translation task.

cs.CL↗