Nicholas Kania
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nicholas Kania has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chiara Contoli
Department of Pure and Applied Sciences, University of Urbino, Urbino, Italy
5 shared publications - Emanuele Lattanzi
Department of Pure and Applied Sciences, University of Urbino, Urbino, Italy
5 shared publications - Lorenzo Calisti
Department of Pure and Applied Sciences, University of Urbino, Urbino, Italy
4 shared publications - Giacomo Di Fabrizio
University of Urbino
3 shared publications - Alessandro Bogliolo
University of Urbino
1 shared publication - Deborah Busonero
INAF - Osservatorio Astrofisico di Torino, via Osservatorio 20, 10025 Pino Torinese, Italy
1 shared publication
Latest Publications
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 167-172
Enhancing Stellar Distance Estimation with Uncertainty-Weighted Loss Functions in Deep Learning Models
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 167-172
Open AccessEnhancing Stellar Distance Estimation with Uncertainty-Weighted Loss Functions in Deep Learning Models
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 155-160
Teaching LLMs to Move: Generation of Human Activity Sensor Traces with BERT
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 155-160
Open AccessTeaching LLMs to Move: Generation of Human Activity Sensor Traces with BERT
- Open Access
- 31 July 2024
- Published by Elsevier in SSRN Electronic Journal
Semantic Template Recognition of Human Activities in Wearable Sensor Data Using Siamese Network
Human activity recognition plays a pivotal role in various fields, such as healthcare monitoring, smart environments, and human-computer interaction. In this study, we propose a novel approach for sensor-based human activity recognition leveraging template matching through a deep-learning Siamese network. Our method focuses on defining activity representations we call “semantic templates” which represent prototypical activity patterns and serve as reference points for matching and comparing observed activities. Through a series of rigorous experiments conducted on three distinct public datasets, we have demonstrated that the proposed approach yields enhanced performance in the recognition of human activities when compared to a traditional deep multi-class classifier for resource-constrained devices. Furthermore, we have showcased how our approach outperforms previous works by up to 20% in the classification of previously unseen activities, paving the way for the development of class-incremental continuous learning techniques.
- 31 July 2024
- Published by Elsevier in SSRN Electronic Journal
Open AccessSemantic Template Recognition of Human Activities in Wearable Sensor Data Using Siamese Network
Human activity recognition plays a pivotal role in various fields, such as healthcare monitoring, smart environments, and human-computer interaction. In this study, we propose a novel approach for sensor-based human activity recognition leveraging template matching through a deep-learning Siamese network. Our method focuses on defining activity representations we call “semantic templates” which represent prototypical activity patterns and serve as reference points for matching and comparing observed activities. Through a series of rigorous experiments conducted on three distinct public datasets, we have demonstrated that the proposed approach yields enhanced performance in the recognition of human activities when compared to a traditional deep multi-class classifier for resource-constrained devices. Furthermore, we have showcased how our approach outperforms previous works by up to 20% in the classification of previously unseen activities, paving the way for the development of class-incremental continuous learning techniques.
- Open Access
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 279-286
EESiamese: Energy-efficient Siamese Neural Network for Constrained Devices
As the deployment of artificial intelligence applications continues to expand, the demand for energy-efficient models tailored for resource-constrained devices has become increasingly critical. This paper introduces a novel approach to address this challenge by proposing an Energy-Efficient Siamese Neural Network (EESiamese) specifically designed for constrained devices such as edge computing platforms, IoT devices, and other low-power computing environments deployment. The EESiamese architecture is carefully crafted to optimize both accuracy and energy consumption. Through systematically exploring model architectures and hyperparameters, we present a fine-tuned EESiamese model that achieves competitive performance compared to traditional Siamese networks while significantly mitigating the energy overhead. Extensive experiments are conducted across a variety of constrained devices to validate the efficacy of the proposed EESiamese model in real-world scenarios. The findings demonstrate the high energy efficiency of the EESiamese, which is executed in a fraction of a millisecond and maintains an accuracy greater than 96%.
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 279-286
Open AccessEESiamese: Energy-efficient Siamese Neural Network for Constrained Devices
As the deployment of artificial intelligence applications continues to expand, the demand for energy-efficient models tailored for resource-constrained devices has become increasingly critical. This paper introduces a novel approach to address this challenge by proposing an Energy-Efficient Siamese Neural Network (EESiamese) specifically designed for constrained devices such as edge computing platforms, IoT devices, and other low-power computing environments deployment. The EESiamese architecture is carefully crafted to optimize both accuracy and energy consumption. Through systematically exploring model architectures and hyperparameters, we present a fine-tuned EESiamese model that achieves competitive performance compared to traditional Siamese networks while significantly mitigating the energy overhead. Extensive experiments are conducted across a variety of constrained devices to validate the efficacy of the proposed EESiamese model in real-world scenarios. The findings demonstrate the high energy efficiency of the EESiamese, which is executed in a fraction of a millisecond and maintains an accuracy greater than 96%.
- Open Access
- 4 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
A Study on the energy-efficiency of the Object Tracking Algorithms in Edge Devices
- 4 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessA Study on the energy-efficiency of the Object Tracking Algorithms in Edge Devices