arXiv subjects

Ismail Uysal

Publications and source records attributed to Ismail Uysal.

9 recordsLinked to original sources

arXiv2026

ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise

Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers. Although correntropy-based objectives improve robustness, existing formulations rely on fixed kernel parameters that must be empirically tuned and remain static during training. To address these limitations, we propose an Adaptive Log-Correntropy Loss (ALCL), a heavy-tailed loss formulation that adaptively learns its robustness geometry during optimization. ALCL introduces a logarithmic residual model whose shape and scale parameters are learned jointly with network weights through differentiable reparameterization. This yields a principled maximum likelihood formulation whose influence function is formally bounded and redescending, allowing the loss geometry to adapt dynamically to evolving residual statistics while suppressing extreme outliers. Comparative experiments on four widely used benchmark datasets spanning grayscale and red-green-blue (RGB) image data under mixed heavy-tailed and impulsive noise demonstrate that ALCL consistently outperforms MSE and optimally tuned generalized correntropy losses in both reconstruction fidelity and downstream classification accuracy. While performance differences remain small under low-noise conditions, under high-noise regimes ALCL improves median accuracy by up to 4.75% on grayscale benchmarks and 4.51% on RGB datasets, with reduced variance across runs. These results demonstrate that adaptive robustness through joint learning of loss parameters provides a computationally efficient alternative to static correntropy-based losses for deep learning in non-Gaussian environments.

cs.LG↗

arXiv2026

Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms

Human activity recognition (HAR) has become a key component of intelligent systems for healthcare monitoring, assistive living, smart environments, and human-computer interaction. Although deep learning has substantially improved HAR performance on multivariate sensor data, the resulting models often remain opaque, limiting trust, reliability, and real-world deployment. Explainable artificial intelligence (XAI) has therefore emerged as a critical direction for making HAR systems more transparent and human-centered. This paper presents a comprehensive review of explainable HAR methods across wearable, ambient, physiological, and multimodal sensing settings. We introduce a unified perspective that separates conceptual dimensions of explainability from algorithmic explanation mechanisms, reducing ambiguities in prior surveys. Building on this distinction, we present a mechanism-centric taxonomy of XAI-HAR methods covering major explanation paradigms. The review examines how these methods address the temporal, multimodal, and semantic complexities of HAR, and summarize their interpretability objectives, explanation targets, and limitations. In addition, we discuss current evaluation practices, highlight key challenges in achieving reliable and deployable XAI-HAR, and outline directions toward trustworthy activity recognition systems that better support human understanding and decision-making.

cs.LG↗

arXiv2021

A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations

This article describes location aware temperature profiles from six strawberry shipments across the continental United States. Three pallets were instrumented in each shipment with three vertically placed loggers to take a longitudinal and latitudinal snapshot of 9 strategically different locations (including the top, middle and bottom layers of the pallets placed in the back, middle and the front of the shipping container) for a combined 54 measurement points across shipments of varying lengths. The sensors were instrumented in the field, right at the point of harvest, recorded temperatures every every 5 to 10 minutes depending on the shipment, and uploaded their data periodically via cellular radios on each device. The data is a result of significant collaboration between stakeholders from farmers to distributors to retailers to academics, which can play an important role for researchers and educators in food engineering, cold-chain, machine learning, and data mining, as well as in other disciplines related to food and transportation.

eess.SP↗

arXiv2020

GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning

In this paper, we propose a novel graph-based approach for semi-supervised learning problems, which considers an adaptive adjacency of the examples throughout the unsupervised portion of the training. Adjacency of the examples is inferred using the predictions of a neural network model which is first initialized by a supervised pretraining. These predictions are then updated according to a novel unsupervised objective which regularizes another adjacency, now linking the output nodes. Regularizing the adjacency of the output nodes, inferred from the predictions of the network, creates an easier optimization problem and ultimately provides that the predictions of the network turn into the optimal embedding. Ultimately, the proposed framework provides an effective and scalable graph-based solution which is natural to the operational mechanism of deep neural networks. Our results show comparable performance with state-of-the-art generative approaches for semi-supervised learning on an easier-to-train, low-cost framework.

cs.LG↗

arXiv2019

Bio-inspired Filter Banks for Frequency Recognition of SSVEP-based Brain-computer Interfaces

Brain-computer interfaces (BCIs) and their associated technologies have the potential to shape future forms of communication, control, and security. Specifically, the steady-state visual evoked potential (SSVEP) based BCIs have the advantages of better recognition accuracy, and higher information transfer rate (ITR) compared to other BCI modalities. To fully exploit the capabilities of such devices, it is necessary to understand the underlying biological features of SSVEPs and design the system considering their inherent characteristics. This paper introduces bio-inspired filter banks (BIFBs) for improved SSVEP frequency recognition. SSVEPs are frequency selective, subject-specific, and their power gets weaker as the frequency of the visual stimuli increases. Therefore, the gain and bandwidth of the filters are designed and tuned based on these characteristics while also incorporating harmonic SSVEP responses. The BIFBs are utilized in the feature extraction stage to increase the separability of classes. This method not only improves the recognition accuracy but also increases the total number of available commands in a BCI system by allowing the use of stimuli frequencies that elicit weak SSVEP responses. The BIFBs are promising particularly in the high-frequency band, which causes less visual fatigue. Hence, the proposed approach might enhance user comfort as well. The BIFB method is tested on two online benchmark datasets and outperforms the compared methods. The results show the potential of bio-inspired design, and the findings will be extended by including further SSVEP characteristics for future SSVEP based BCIs.

eess.SP↗

arXiv2018

Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization

In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to each observation which is then modified by applying the domain specific transformation associated with the assigned label. Generated pseudo observation-label pairs are subsequently used to train a neural network with Auto-clustering Output Layer (ACOL) that introduces multiple softmax nodes for each pseudo parent-class. Due to the unsupervised objective based on Graph-based Activity Regularization (GAR) terms, softmax duplicates of each parent-class are specialized as the hidden information captured through the help of domain specific transformations is propagated during training. Ultimately we obtain a k-means friendly latent representation. Furthermore, we demonstrate how the chosen transformation type impacts performance and helps propagate the latent information that is useful in revealing unknown clusters. Our results show state-of-the-art performance for unsupervised clustering tasks on MNIST, SVHN and USPS datasets, with the highest accuracies reported to date in the literature.

cs.LG↗

arXiv2017

Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks

In this paper, we discuss a different type of semi-supervised setting: a coarse level of labeling is available for all observations but the model has to learn a fine level of latent annotation for each one of them. Problems in this setting are likely to be encountered in many domains such as text categorization, protein function prediction, image classification as well as in exploratory scientific studies such as medical and genomics research. We consider this setting as simultaneously performed supervised classification (per the available coarse labels) and unsupervised clustering (within each one of the coarse labels) and propose a novel output layer modification called auto-clustering output layer (ACOL) that allows concurrent classification and clustering based on Graph-based Activity Regularization (GAR) technique. As the proposed output layer modification duplicates the softmax nodes at the output layer for each class, GAR allows for competitive learning between these duplicates on a traditional error-correction learning framework to ultimately enable a neural network to learn the latent annotations in this partially supervised setup. We demonstrate how the coarse label supervision impacts performance and helps propagate useful clustering information between sub-classes. Comparative tests on three of the most popular image datasets MNIST, SVHN and CIFAR-100 rigorously demonstrate the effectiveness and competitiveness of the proposed approach.

cs.LG↗

arXiv2017

Clustering-based Source-aware Assessment of True Robustness for Learning Models

We introduce a novel validation framework to measure the true robustness of learning models for real-world applications by creating source-inclusive and source-exclusive partitions in a dataset via clustering. We develop a robustness metric derived from source-aware lower and upper bounds of model accuracy even when data source labels are not readily available. We clearly demonstrate that even on a well-explored dataset like MNIST, challenging training scenarios can be constructed under the proposed assessment framework for two separate yet equally important applications: i) more rigorous learning model comparison and ii) dataset adequacy evaluation. In addition, our findings not only promise a more complete identification of trade-offs between model complexity, accuracy and robustness but can also help researchers optimize their efforts in data collection by identifying the less robust and more challenging class labels.

cs.LG↗

arXiv2016

Bio-Inspired Filter Banks for SSVEP-based Brain-Computer Interfaces

Brain-computer interfaces (BCI) have the potential to play a vital role in future healthcare technologies by providing an alternative way of communication and control. More specifically, steady-state visual evoked potential (SSVEP) based BCIs have the advantage of higher accuracy and higher information transfer rate (ITR). In order to fully exploit the capabilities of such devices, it is necessary to understand the features of SSVEP and design the system considering its biological characteristics. This paper introduces bio-inspired filter banks (BIFB) for a novel SSVEP frequency detection method. It is known that SSVEP response to a flickering visual stimulus is frequency selective and gets weaker as the frequency of the stimuli increases. In the proposed approach, the gain and bandwidth of the filters are designed and tuned based on these characteristics while also incorporating harmonic SSVEP responses. This method not only improves the accuracy but also increases the available number of commands by allowing the use of stimuli frequencies elicit weak SSVEP responses. The BIFB method achieved reliable performance when tested on datasets available online and compared with two well-known SSVEP frequency detection methods, power spectral density analysis (PSDA) and canonical correlation analysis (CCA). The results show the potential of bio-inspired design which will be extended to include further SSVEP characteristic (e.g. time-domain waveform) for future SSVEP based BCIs.

cs.HC↗