In this paper, we present an electronic nose application case study based on an affordable Bosch BME688 AI (artificial intelligence) capable sensor module set (and development kit) to distinguish and identify differen...
详细信息
ISBN:
(数字)9798350385472
ISBN:
(纸本)9798350385489
In this paper, we present an electronic nose application case study based on an affordable Bosch BME688 AI (artificial intelligence) capable sensor module set (and development kit) to distinguish and identify different soft drinks and beverages. During the work, the device was prepared for TinyML and AI-based identification. The module contains eight pieces of BME688 sensors, and it is compatible with the Bosch BME AI Studio software. Based on their unique odor profiles, we created and tested various ML (machine learning) algorithms to distinguish between fruit palinka (fruit spirit) types, different beers, and ethanol. The case study aims to determine whether the module can distinguish between beverages. For this, we applied passive delivery. It was found that the differentiation between air and different samples (cola, lager beer) is possible. Still, ethanol and spirits with high alcohol content saturate the device, pointing to future dynamic sampling (active delivery).
FC Portugal, a simulated humanoid soccer team from the universities of Porto and Aveiro, achieved the third consecutive victory in the main competition of the 2024 RoboCup 3D Simulation League. The team registered 16 ...
详细信息
In this paper a selection of designs of directional lens antennas for V2X communication is presented and investigated. We have compared five different types of all-dielectric 3D-printed lenses - extended hemispherical...
详细信息
Grammatical error detection in low-resource languages like Slovak is challenging due to the scarcity of annotated data and language-specific models. This paper investigates the performance of state-of-the-art multilin...
详细信息
ISBN:
(数字)9798350379365
ISBN:
(纸本)9798350379372
Grammatical error detection in low-resource languages like Slovak is challenging due to the scarcity of annotated data and language-specific models. This paper investigates the performance of state-of-the-art multilingual models, including ByT5, mT5, uMT5, and Flan-T5, on the task of grammatical error detection in Slovak sentences. The study explores model efficiency across various dataset sizes and error types, focusing on single-word, multi-word, and random-word corruption scenarios. Our experiments reveal that ByT5 outperforms other models in terms of precision and recall, especially when handling large datasets. The results provide insights into how different multilingual architectures can be applied to improve grammatical error detection in low-resource language contexts.
One of the possible approaches to the three-dimensional (3D) localization based on a multistatic ultra-wideband (UWB) radar system, which works with more than three channels, is the application of the so-called direct...
详细信息
This study focuses on reformulating the shortest path problem in undirected weighted graphs into a QUBO problem, leveraging the D-Wave quantum annealing hybrid solver for execution. While A * search with heuristics, a...
详细信息
ISBN:
(数字)9798350379365
ISBN:
(纸本)9798350379372
This study focuses on reformulating the shortest path problem in undirected weighted graphs into a QUBO problem, leveraging the D-Wave quantum annealing hybrid solver for execution. While A * search with heuristics, a widely used algorithm for solving shortest path problem, serves as a baseline for comparison, our primary contribution lies in analyzing the accuracy and benefits of the proposed QUBO formulation. Our analysis reveals that the proposed QUBO formulation together with selected quantum annealing hybrid solver is loosing its efficiency with increasing number of nodes. This is caused by the size of the problem and related penalty calculation but also by the architecture of the D-Wave QPU and design of the hybrid solver. We are proposing techniques to improve the results, such as graph pruning during preprocessing or penalty parameter tuning to achieve better, more accurate, results. This study provides valuable insights into the limitations of current approaches and explores the future applications of quantum computing in solving real-world challenges.
This work is devoted to investigating the effect of flux residues on the underfill. Prepared samples were made of copper sheets to eliminate the influence of multi-layered, inhomogeneous materials. Two sets of these s...
详细信息
We consider a generalization of binary search in linear orders to the domain of weighted trees. The goal is to design an adaptive search strategy whose aim is to locate an unknown target vertex of a given tree. Each q...
详细信息
This work aimed to investigate the susceptibility of novel nanocomposite solder paste to electrochemical migration (ECM). Bismuth-tin solder paste was filled with 0.1 wt.% of TiO2 nanoparticles. The electrochemical mi...
详细信息
The security of IoT that is based on layered approaches has shortcomings such as the redundancy, inflexibility, and inefficiently of security solutions. There are many harmful attacks in IoT networks such as DoS and D...
详细信息
暂无评论