Received signal strength (RSS)-based Visible Light Positioning (VLP) has gained attention due to its relatively easy infrastructure deployment and high localization accuracy. Different low-complexity geometrical and m...
详细信息
ISBN:
(数字)9783903176713
ISBN:
(纸本)9798331522025
Received signal strength (RSS)-based Visible Light Positioning (VLP) has gained attention due to its relatively easy infrastructure deployment and high localization accuracy. Different low-complexity geometrical and machine learning (ML)-based models have been proposed for localization because of their robustness against the uncertainty produced by tilted devices, non-Lambertian sources, and the low dimensionality of RSS-vector. Inspired by the Kolmogorov-Arnold representation theorem, Kolmogorov-Arnold Networks (KANs) have been proposed as a promising alternative to Multi-Layer Perceptrons (MLPs). This paper evaluates the use and performance of KANs in VLP systems for the first time. Results show that in the proposed scenario, KANs achieve below cm-level accuracy. Moreover, symbolic regression (SR) can be implemented straightforwardly to find a function that relates RSS with distance. It is shown in this paper that both KANs and SR-KAN models outperform MLP and Weighted K-nearest neighbors based approaches.
Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network ...
详细信息
Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network (SNN) stands out for its potential in efficient neural computation. However, achieving high inference accuracy through precise multiply-accumulate (MAC) operations necessitates a large membrane capacitor—224 to 547 times larger than the synapse array at the 14nm technology node—resulting in prohibitive area costs. Additionally, the large capacitor size introduces higher energy consumption and longer access times. Thus, a key research challenge is maintaining accuracy while mitigating the costs associated with the large membrane capacitor. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14 $\times$ reduction in capacitor size along with a 34% reduction in energy consumption over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.
For the development of new types of hip implants for acetabulum revision, it is beneficial to analyse the acetabular defects of the indication group in advance. In order to be able to specially compare the bone defect...
详细信息
Cerebellar neural networks can be applied to robotic arm control, unmanned aircraft system localization, and humanoid robots. Despite many applications of brain-inspired intelligence, the firing mechanism of granular ...
详细信息
ISBN:
(数字)9798331544706
ISBN:
(纸本)9798331544713
Cerebellar neural networks can be applied to robotic arm control, unmanned aircraft system localization, and humanoid robots. Despite many applications of brain-inspired intelligence, the firing mechanism of granular cells in the cerebellum has not been studied. In brain-inspired intelligence, it is significant to study the firing mechanism of granular cells (GR), which are the only excitatory neurons and the most numerous neurons in the cerebellum. In this paper, the Shannon information entropy was put forward to measure the degree of disorder in the firing activities of granular cells. The effects of critical neuronal properties on granular cells' firing activities were studied. Given inhibitory synapses between granular cells and Golgi cells (GO), we examined the effects of membrane capacitance and firing time constant of granular cells and Golgi cells on the firing activities of granular cells. Then, we discussed the impact of the strength of the connection between GR and GO on the Shannon information entropy of GR. Through the above research, we concluded the effects of critical neuronal properties’ impact trends on the Shannon information entropy of GR. Appropriate adjustments of the above parameters can change the firing activities of granular cells and meet the specific needs of different neuronal networks. Then, the designed neuronal networks can be used in adaptive motor control systems, such as in robotic coordination and autonomous driving under complex environments.
Human robot interaction often requires many sub-systems to work together in order to facilitate more natural and intelligent interactions with multiple humans. For this work, the relevant systems include audio and vis...
Human robot interaction often requires many sub-systems to work together in order to facilitate more natural and intelligent interactions with multiple humans. For this work, the relevant systems include audio and visual direction of arrival estimation that are used in an encompassing sensor fusion framework. The presented sub-systems are used concurrently online to allow for humanoid robots to identify active speakers in a scene, track human subjects, and identify when other subjects may require attention. We present evaluations of performance, while also implementing relevant humanlike behaviours on the REEM-C Humanoid Robot. A conducted user study delivers valuable feedback on these systems, which provide a strong foundation for improved humanoid intelligence and more innovative human-robot interaction.
This study proposes a novel approach for real-time facial expression recognition utilizing short-range Frequency-Modulated Continuous-Wave (FMCW) radar equipped with one transmit (Tx), and three receive (Rx) antennas....
详细信息
ISBN:
(数字)9798350363517
ISBN:
(纸本)9798350363524
This study proposes a novel approach for real-time facial expression recognition utilizing short-range Frequency-Modulated Continuous-Wave (FMCW) radar equipped with one transmit (Tx), and three receive (Rx) antennas. The system leverages four distinct modalities simultaneously: Range-Doppler images (RDIs), micro range-Doppler Images (micro-RDIs), range azimuth images (RAIs), and range elevation images (REIs). Our innovative architecture integrates feature extractor blocks, intermediate feature extractor blocks, and a ResNet block to accurately classify facial expressions into smile, anger, neutral, and no-face classes. Our model achieves an average classification accuracy of 98.91% on the dataset collected using a 60 GHz short-range FMCW radar. The proposed solution operates in real-time in a person-independent manner, which shows the potential use of low-cost FMCW radars for effective facial expression recognition in various applications.
In recency, neural signed distance fields have become more popular for reconstructing 3D indoor environments. While great improvements have been made due to missing incident radiance and materials in the surface estim...
In recency, neural signed distance fields have become more popular for reconstructing 3D indoor environments. While great improvements have been made due to missing incident radiance and materials in the surface estimation, current methods cannot reconstruct high-quality surfaces. To address this issue, we propose Neural Painted Radiosity Fields (NPRF), consisting of Neural Radiosity Fields for volumetric surface representation and Neural Painted Scenes for novel view synthesis. Neural Radiosity Fields combine the radiative transfer equation with neural radiosity to estimate 3D surfaces, thus leveraging raytracing to improve the volumetric representation. Neural Painted Scenes employs sparsification and projection of 3D points into 2D images in conjunction with a generative, context-aware inpainting network to produce high-quality novel views. We show that NPRF leads to overall improvements in F-score on the popular ScanNet dataset. Finally, we show that NPRF improves novel view synthesis by a significant margin, giving improvements of up to 25% on PSNR, 53% on LPIPS, and 3% on SSIM.
Human reasoning comprises the ability to understand and reason about the current action solely based on past information. To provide effective assistance in an eldercare or household environment an assistive robot or ...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Human reasoning comprises the ability to understand and reason about the current action solely based on past information. To provide effective assistance in an eldercare or household environment an assistive robot or intelligent assistive system has to assess human actions correctly. Based on this presumption, the task of online action detection determines the current action solely based on the past without access to future information. During inference, the performance of the model is largely impacted by the attributes of the underlying training dataset. However, as high costs and ethical concerns are associated with the real-world data collection process, synthetically created data provides a way to mitigate these problems while providing additional data for the training process of the underlying action detection model to improve performanceDue to the inherent domain shift between the synthetic and real data, we introduce a new egocentric dataset called Human Kitchen Interactions (HKI) to investigate the sim-to-real gap. Our dataset contains in total 100 synthetic and real videos in which 21 different actions are executed in a kitchen environment. The synthetic data is acquired in an egocentric virtual reality (VR) setup while capturing the virtual environment in a game engine. We evaluate state-of-the-art online action detection models on our dataset and provide insights into sim-to-real domain shift. Upon acceptance, we will release our dataset and the corresponding features at https://***/HKI/.
Quantum computing offers the potential to solve problems that are intractable for classical computers. A major challenge in scaling quantum computers lies in bridging the gap between cryogenic qubits, operating at mil...
详细信息
ISBN:
(数字)9798350356830
ISBN:
(纸本)9798350356847
Quantum computing offers the potential to solve problems that are intractable for classical computers. A major challenge in scaling quantum computers lies in bridging the gap between cryogenic qubits, operating at millikelvin to few kelvin temperatures, and the classical CMOS-based system-on-chip (SoC) typically located at room temperature (300K). This connection introduces heat leakage, which can destabilize the qubit states. A promising solution is to relocate the control circuits and processors to the cryogenic environment, but this imposes strict constraints on power consumption due to limited cooling capacity. Additionally, the SoC must meet stringent timing requirements for qubit measurement classification. In this work, we investigate the performance of CMOS-based circuits for cryogenic operations using 5 nm FinFET technology. We begin by measuring the electrical characteristics of advanced 5 nm FinFETs at both 10K and 300K. Using these measured data, we calibrate the industry-standard compact model (BSIM-CMG) and develop two standard cell libraries for each temperature. Through the logic synthesis of six circuits from the EPFL benchmark suite, we analyze their behavior at cryogenic temperatures. Our results show that circuits at 10K achieve a 41% increase in speed compared to 300K. Further, they operate efficiently at lower supply voltages, which enables reduced power consumption while maintaining high-speed performance in cryogenic environments.
Moving object segmentation (MOS) using a 3D light detection and ranging (LiDAR) sensor is crucial for scene understanding and identification of moving objects. Despite the availability of various types of 3D LiDAR sen...
详细信息
暂无评论