Machine Learning is a branch of artificial intelligence widely used in the medical field to analyze high-dimensional medical data and the early detection of certain dangerous diseases. Lung diseases continue to increa...
详细信息
Humans use log-compressed number lines to represent different quantities, including elapsed time, traveled distance, numerosity, sound frequency, etc. Inspired by recent cognitive science and computational neuroscienc...
Humans use log-compressed number lines to represent different quantities, including elapsed time, traveled distance, numerosity, sound frequency, etc. Inspired by recent cognitive science and computational neuroscience work, we developed a neural network that learns to construct log-compressed number lines. The network computes a discrete approximation of a real-domain Laplace transform using an RNN with analytically derived weights giving rise to a log-compressed timeline of the past. The network learns to extract latent variables from the input and uses them for global modulation of the recurrent weights turning a timeline into a number line over relevant dimensions. The number line representation greatly simplifies learning on a set of problems that require learning associations in different spaces - problems that humans can typically solve easily. This approach illustrates how combining deep learning with cognitive models can result in systems that learn to represent latent variables in a brain-like manner and exhibit human-like behavior manifested through Weber-Fechner law.
Robot-Assisted Minimally Invasive Surgery (RAMIS) is an innovation that has benefited hundreds of thousands of patients to date. However, despite their many advantages, those robots are not as popular as expected. Man...
详细信息
The exponential growth of the number and variety of monitoring devices for patients in the hospital, as well as the improvement of medical equipment and hygiene conditions constitute the core of eHealth projects nowad...
详细信息
Taxonomies are vehicles for thinking about what’s possible, for identifying unconsidered options, as well as for establishing formal relations between entities. We identify several shortcomings in 10 existing taxonom...
详细信息
One of the musical activities that can be positively impacted by the Internet of Musical Things (IoMusT) is music education. However, although the IoMusT's properties hold a promising potential to enrich music lea...
详细信息
ISBN:
(数字)9798350366525
ISBN:
(纸本)9798350366532
One of the musical activities that can be positively impacted by the Internet of Musical Things (IoMusT) is music education. However, although the IoMusT's properties hold a promising potential to enrich music learning processes, the extent to which early childhood music educators and scholars have embraced this emerging type of technology and explored their potential is still very limited. To bridge this gap, we first survey the relevant literature at the confluence of the Internet of Things, music technology, and education. Then, we propose a pedagogical framework to support designing IoMusT applications for early childhood music education. The framework is based on five dimensions: embodied sense-making, nonlinearity, participatory sense-making, privacy and security, as well as accessibility and inclusiveness. Furthermore, we corroborate the framework with a set of pedagogical scenarios showing its usage. Our study aims to foster interdisciplinary research at the confluence of pedagogy and music technology in an application domain, that of early childhood music education, hitherto unexplored.
This paper presents federated learning with over-the-air (OTA) aggregation over a noisy communication channel for human activity recognition (HAR) problem. OTA aggregation permits simultaneous transmission of model we...
详细信息
ISBN:
(数字)9798350374513
ISBN:
(纸本)9798350374520
This paper presents federated learning with over-the-air (OTA) aggregation over a noisy communication channel for human activity recognition (HAR) problem. OTA aggregation permits simultaneous transmission of model weights through waveform superposition, enabling federated computation over the air. However, noise susceptibility in the channel can degrade weight signal aggregation quality. To this end, we propose a novel PerSonalized OTA FL (PerSOTA FL), which employs QR decomposition to estimate model weight. Our PerSOTA FL leverages multiple antennas for robust OTA-based aggregation, particularly in environments with low signal-to-noise ratio (SNR). Our experiments, with two real-world HAR datasets exhibiting practical data and label heterogeneity, indicate that our PerSOTA FL approach achieves comparable performance to vanilla FL while outperforms the conventional OTA FL. Our experimental results verify the efficiency of our PerSOTA FL, demonstrating its capacity for on-device personalized training while delivering a generalized HAR model through OTA FL. The GitHub code is available at https://***/FL-HAR/PerSOTA-FL-A-ROBUST-TO-NOISE-PERSONALIZED-OTA-FL-FOR-HAR.
Authoritative thesauri in the form of web ontologies offer a sound representation of domain knowledge and can act as a reference point for automated semantic tagging. On the other hand, current language models achieve...
详细信息
The integration of Industry 4.0 technologies in agriculture will reduce the increasing challenges of agricultural process around the globe. The real-time farm management with high degree of automation will greatly imp...
详细信息
The integration of Industry 4.0 technologies in agriculture will reduce the increasing challenges of agricultural process around the globe. The real-time farm management with high degree of automation will greatly improve productivity, agri-food supply chain efficiency and food safety. This paper describes a fully customized LoRa-based IoT system that aims for a low-cost, low power and wide range wireless sensor network targeted for smart farms. The presented system integrates already existing Programmable Logic Controllers (PLC) typically used to control multiple processes and devices such as water pumps, certain machinery, etc. along with a newly developed network of wireless LoRA sensors distributed over the farm. A Telegram bot is also included as novelty for automated user communication via this mobile phone messaging application. The network structure was deployed and tested. The developed integrated system also includes a cloud-based monitoring application to provide remote visualization and control for all the farming environment.
During the COVID-19 pandemic, the use of a people tracking system could have been crucial, particularly in sensitive environments, such as hospitals. DPPL Hallway Tracker is a framework that uses security camera foota...
详细信息
暂无评论