We develop an energy-efficient indoor positioning system based on Artificial Intelligence (AI). In our system, first, at the positioning layer, a Multi-Layer Perceptron (MLP) estimates the current indoor position of an IoT device based on positioning indicators obtained from the anchors. Second, at the forecasting layer, a pair of MLPs estimate the future positions of the device based on the past position estimates obtained when the device woke up as well as the forecast positions of the device during the sleep periods. Third, the device is awakened to send a positioning beacon at intervals over which a significant displacement is predicted to occur by the forecasting layer. Our results demonstrate that our indoor positioning system saves significant energy via adaptive sleep cycles whose duration is determined by the prediction of a significant displacement. This work establishes a foundation for indoor positioning that utilizes AI-based positioning and trajectory forecasting.
01615nas a2200157 4500000000100000000000100001008004100002260002700043100001700070700001800087700001900105700001500124700001900139245014200158520115700300 2021 d bIEEE aIstanbul, Turkey 1 aAlper Saylam 1 aNur Kelesoglu 1 aRifat Cikmazel 1 aMert Nakip 1 aVolkan Rodoplu 00 aDynamic Positioning Interval Based On Reciprocal Forecasting Error (DPI-RFE) Algorithm for Energy-Efficient Mobile IoT Indoor Positioning 3 aWe develop an algorithm called “Dynamic Positioning Interval based on Reciprocal Forecasting Error (DPIRFE)” for energy-efficient mobile Internet of Things (IoT) Indoor Positioning (IP). In contrast with existing IP algorithms, DPIRFE forecasts the future trajectory of a mobile IoT device by using machine learning and dynamically adjusts the positioning interval based on the reciprocal instantaneous forecasting error, thereby dynamically trading off transmit energy consumption against forecasting error. We compare the performance of DPIRFE with respect to the total transmit energy consumption and the average forecasting error against Constant Positioning Interval (CPI) and Positioning Interval based on Displacement (PID) algorithms. Our results show that DPI-RFE significantly outperforms both of these benchmark algorithms with respect to transmit energy consumption while achieving a competitive average forecasting error performance. These results open the way to the design of machine learning based trajectory forecasting algorithms that can be utilized for energy-efficient positioning in next-generation wireless networks.
01730nas a2200145 4500000000100000000000100001008004100002260003600043100001800079700002000097700002100117245010300138856005000241520129300291 2023 d c01/2024 bIEEE aSorrento, Italy 1 aNur Kelesoglu 1 aKatarzyna Filus 1 aJoanna Domańska 00 aHierAct: a Hierarchical Model for Human Activity Recognition in Game-Like Educational Applications uhttps://ieeexplore.ieee.org/document/10386919 3 aConstantly evolving landscape of modern education makes the integration of technology crucial to enable more interactive and immersive learning experiences. One of the key problems in this domain is Human Activity Recognition (HAR), which uses standard smartphone sensors to understand and recognize user movements. While HAR exhibits high potential in this area, its persistent challenge is to differentiating between similar activities, whose occurrences can often lead to misclassification and reduced quality of applications. To tackle this problem, we employ specialized classifiers and use them in a hierarchical manner instead of using monolith multi-class models. We propose HierAct - a Hierarchical model that solves the multi-class human activity recognition problem. We also release a new HAR dataset - EduAct - (https://github.com/iitis/HierAct-Dataset) focused on activities that could be used to create game-like educational applications.Our results show that the performance of the proposed model is substantially better than other state-of-the-art machine learning models. Our work shows the potential of hierarchical classifiers in HAR applications for education, by offering educators and students a more accurate, reliable, and engaging interactive experience.
02003nas a2200145 4500000000100000000000100001008004100002260001200043100001500055700001800070700002200088245012400110490000800234520161500242 2024 d c10/2024 1 aMert Nakip 1 aNur Kelesoglu 1 aCüneyt Güzeliş 00 aFire Detection and Risk Assessment via Support Vector Regression with Flattening-Samples Based Augmented Regularization 0 v164 3 aWe propose a Hybrid Support Vector Regression (SVR) with Flattening-Samples Based Augmented Regularization (Hybrid FSR-SVR) architecture for multi-sensor fire detection and forest fire risk assessment. The Hybrid FSR-SVR is a lightweight architecture built upon the novel Flattening-Samples Based Augmented Regularization (FSR) approach and temporal trends of environmental variables. The FSR approach augments l2 norm based smoothing term into an l1-l2 combination, facilitating the integration of l1 regularization into the SVR method, thereby enhancing generalization with minimal computational load. We evaluate the performance of Hybrid FSR-SVR using two distinct datasets covering indoor and forest fires, benchmarking against 15 machine learning models, including state-of-the-art techniques, such as Recurrent Trend Predictive Neural Network (rTPNN), Long-Short Term Memory (LSTM), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU), and Gradient Boosting. Our findings demonstrate that Hybrid FSR-SVR effectively assesses the risk of forest fire, enabling early preventive measures. Notably, it achieves a remarkable accuracy of 0.95 for forest fire detection and ranks third with 0.88 accuracy for indoor fire detection. Importantly, it exhibits computation times significantly lower – by 1 to 2 orders of magnitude – than the majority of compared techniques. The superior generalization ability of Hybrid FSR-SVR, facilitated by flattening-samples based augmented regularization, allows for high detection performance even with smaller training sets.
00367nas a2200133 4500000000100000000000100001008004100002260001200043100001800055700002000073245008600093856004700179490000700226 2024 d c11/2024 1 aNur Kelesoglu 1 aŁukasz Sobczak 00 aZigBeeNet: Decrypted ZigBee IoT Network Traffic Dataset in Smart Home Environment uhttps://www.mdpi.com/2076-3417/14/23/10844 0 v14 00597nas a2200181 4500000000100000000000100001008004100002260001200043100001800055700002000073700002000093700002100113700002200134700001800156700003000174245008000204856013100284 2025 d c02/2025 1 aNur Kelesoglu 1 aŁukasz Sobczak 1 aPiotr Biernacki 1 aJoanna Domańska 1 aFrancisco Ferrão 1 aShahid Mumtaz 1 aFideline Tchuenbou-Magaia 00 aArtificial Intelligence for Electronic-based Systems in Safety Applications uhttps://www.researchgate.net/publication/389204536_Artificial_Intelligence_for_Electronic-based_Systems_in_Safety_Applications 02261nas a2200169 4500000000100000000000100001008004100002260001200043100001800055700001900073700001700092245007800109856005000187490000700237520183300244022001402077 2025 d c07/2025 1 aNur Kelesoglu 1 aMarzena Halama 1 aAnna Strzoda 00 aEnhancing LoRa-based Outdoor Localization Accuracy Using Machine Learning uhttps://ieeexplore.ieee.org/document/11080010 0 v13 3 aThe Internet of Things is gaining significant relevance, driving increasing interest in location-
based services using wireless signals, particularly Low Power Wide Area Network (LPWAN) technology.
LoRa (Long Range), together with LoRaWAN, is a prominent LPWAN standard that provides long-range
connectivity and low energy consumption, making it viable for IoT-based positioning systems in smart
cities. For localization systems leveraging LoRa signals, Machine Learning (ML) approaches are being
increasingly explored, as ML-based solutions offer a powerful way to enhance the accuracy of positioning.
In this study, we propose various ML approaches for LoRa-based positioning in outdoor environments. We
evaluate six different ML models: k-NN, CNN, SVR, ANN, XG-Boost, and LightGBM-using an open-
source urban LoRaWAN dataset. We further propose a Hybrid Model that combines convolutional feature
extraction with gradient-boosted regression. This architecture integrates the strengths of deep learning and
tree-based models, aiming to capture both temporal signal patterns and structured input correlations for
improved localization accuracy. The models are trained offline and tested for performance in terms of
localization accuracy, mean square error, and computational efficiency. Additionally, we investigate the
impact of different Feature Vector (FV) subsets on localization performance by analyzing the significance of
LoRaWAN signal attributes. Our results highlight the effectiveness of ML models in enhancing localization
accuracy for LoRa-based outdoor positioning systems, demonstrating performance improvements ranging
from 10% to 73% compared to previous ML studies in outdoor localization.
The generation of realistic network traffic is a critical requirement for testing, simulation, and security evaluation in ZigBee-based IoT systems. In this study, we propose a novel framework that extracts sample ZigBee traffic packets and generates semantically meaningful and protocol-compliant synthetic traffic by using Large Language Models (LLMs) such as GPT-4.1 and GPT-5. Unlike traditional rule-based or statistical generators, our approach is data-driven and incorporates sample-based few-shot learning, prompt engineering, and a human-in-the-loop feedback mechanism. To evaluate the effectiveness of the proposed framework, we conduct two sets of experiments. The first focuses on generating unidirectional traffic to emulate typical device-to-hub communication, while the second extends this setup to bidirectional exchanges, capturing realistic request--response dynamics and interaction patterns. The realism of the generated traffic is assessed using a multi-dimensional evaluation framework that includes statistical similarity measures, such as Jensen--Shannon Divergence, as well as protocol compliance, semantic correctness, temporal consistency, and diversity metrics. In addition, we compare the performance of LLM-based generators with classical deep learning baselines, including recurrent neural networks (RNNs) and generative adversarial networks (GANs). We further analyze the computational cost and the impact of internal reasoning effort on traffic generation by systematically evaluating different GPT-5 reasoning configurations. Experimental results show that both GPT-4.1 and GPT-5 successfully learn the temporal and structural dependencies of ZigBee traffic and significantly outperform RNN and GAN baselines in terms of semantic correctness and long-duration generation. Across all experiments, GPT-4.1 consistently generates traffic that more closely resembles real ZigBee traffic while requiring substantially lower computational resources. These findings highlight that low-latency, non-reasoning LLMs can be particularly well suited for highly structured, protocol-constrained network traffic generation tasks, and demonstrate the potential of LLM-based approaches for realistic IoT traffic generation in research and security evaluation.
00560nas a2200109 4500000000100000008004100001260026300042100001800305700002000323700002100343245008600364 2026 d b(This work was partly supported by the National Centre for Research and Development (NCBR) and co-funded by the European Union under the European Funds for ModernEconomy(FENG)Programme(SMARTKonsorcja),projectno.FENG.01.01-IP.01-A0GV/24-00,) aKraków, Poland 1 aNur Kelesoglu 1 aŁukasz Sobczak 1 aJoanna Domańska 00 aCPU Utilization Forecasting in Large-Scale Cloud Clusters Using Gradient Boosting 01600nas a2200133 4500000000100000008004100001260004000042100002000082700001800102700002100120245007800141856005000219520119700269 2026 d c10.08.2026 bIEEE aKitakyushu, Japan 1 aŁukasz Sobczak 1 aNur Kelesoglu 1 aJoanna Domańska 00 aReliability-Aware LLM Reasoning: Handling Uncertainty in Robot Perception uhttps://ieeexplore.ieee.org/document/11714851 3 aRobots operating in human environments must often make decisions based on perceptual information that
is uncertain, incomplete, or ambiguous. This paper proposes a reliability-aware reasoning framework that enables large
language models (LLMs) to account for perceptual uncertainty when selecting actions in human-robot interaction scenarios.
The environment is represented as a structured scene composed of detected objects enriched with confidence estimates, attribute reliability, and spatial uncertainty information. Using this representation, the LLM evaluates candidate objects through a reliability scoring mechanism that integrates multiple sources of perceptual evidence and supports uncertainty-aware decision making.The proposed approach is evaluated using perception episodes with controlled levels of uncertainty and compared with a baseline LLM-based matching strategy that ignores perceptual
reliability. Experimental results show that incorporating uncertainty-aware reasoning substantially improves decision
robustness under medium and high uncertainty conditions while reducing safety-critical behaviors caused by overconfident
autonomous decisions.
Safe and reliable human–robot interaction remains a challenge, especially for Large Language Model (LLM)-powered socially assistive robots in elderly care. This paper proposes a risk-aware response framework that explicitly models the safety implications of user queries. We introduce a Query Risk Assessment Module (QRAM), which computes a Query Risk Score (QRS) using structured semantic indicators to classify user inputs into different risk levels. Based on this, we develop two strategies: risk-aware response refinement and risk-aware response generation. To assess safety, we introduce the Risk-Aware Response Safety Score (RRSS), a metric that captures both the presence of risk-bearing language and the absence of necessary safety-critical guidance. Experimental results across multiple LLMs demonstrate that incorporating query-level risk awareness reduces response-level risk, with both strategies outperforming raw responses.
00541nas a2200205 4500000000100000008004100001260001200042653001900054653002000073653002000093653002200113653001700135100001500152700001800167700001600185700002200201245009700223300000700320490000800327 2026 d c07/2026 10 aFire detection 10 aSelf-Supervised 10 aonline learning 10 ahuman-in-the-loop 10 amulti-sensor 1 aMert Nakip 1 aNur Kelesoglu 1 aTaylan Mert 1 aCüneyt Güzeliş 00 aSelf-Supervised Online Learning Algorithm for rTPNN to Reduce False Alarms in Fire Detection a14 0 v350 00303nas a2200109 4500000000100000008004100001260001800042100002000060700001800080700002000098245007500118 2026 d aNaples, Italy 1 aŁukasz Sobczak 1 aNur Kelesoglu 1 aSławomir Nowak 00 aRisk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning 00420nas a2200121 4500000000100000008004100001260003000042100001800072700002000090700002100110245011600131856005100247 2026 d c10/05/2026 aNaples, Italy 1 aNur Kelesoglu 1 aŁukasz Sobczak 1 aJoanna Domańska 00 aFrom Plots to Words: Model-Aware Multimodal Explanations as a Foundation for Accessible, Non-Visual Interaction uhttps://dl.acm.org/doi/10.1145/3776591.3833865 00341nas a2200097 4500000000100000008004100001260003000042100001800072245010200090856005100192 2026 d c10/05/2026 aNaples, Italy 1 aNur Kelesoglu 00 aJudging Turn-Taking Through a Monocultural Lens: A Parallel-Corpus Probe of Cultural Bias in LLMs uhttps://dl.acm.org/doi/10.1145/3776591.3836647 00338nas a2200109 4500000000100000008004100001260001600042100002000058700001800078700002100096245011100117 2026 d aBari, Italy 1 aŁukasz Sobczak 1 aNur Kelesoglu 1 aJoanna Domańska 00 aKnowledge-Graph-Grounded Multimodal Explanations for Trustworthy Time-Series Forecasting in DevOps Systems 00288nas a2200097 4500000000100000008004100001260001600042100001800058700002000076245009400096 2026 d aBari, Italy 1 aNur Kelesoglu 1 aŁukasz Sobczak 00 aWhy the Robot Said No: Knowledge-Graph-Grounded Explanations for LLM-Based Robot Planning 00338nas a2200097 4500000000100000008004100001100001800042700002000060700002100080245013900101 2026 d 1 aNur Kelesoglu 1 aŁukasz Sobczak 1 aJoanna Domańska 00 aGrounding LLM-Generated Network Traffic in Semantics: A Knowledge-Graph Framework for Detecting and Explaining Protocol Hallucinations