Kidney cancer is one of the most common cancers worldwide. The major types of malignant renal tumors are renal cell carcinoma and urothelial carcinoma. Although the majority of renal tumors are malignant, up to 20% ar...
详细信息
The article introduces a two-dimensional polynomial regression model for the predictive analysis of glucose concentration in a fractal microwave sensor NP model, utilizing frequency and transmission coefficient differ...
详细信息
This study introduced a capacitive sensing interactive game platform aimed at promoting emotional stability, which we have named the 'Sunrise and Sunset' game. This game primarily consists of two pieces of reg...
详细信息
The swift progression of industrial technology underscores the need for adept professionals capable of skillfully implementing and managing intricate systems. Vocational education assumes a pivotal role in cultivating...
详细信息
In this work, we demonstrated upconversion imagers integrated with shortwave infrared photodetectors paired with an electron blocking layer. The use of electron blocking layer screened charge injection to prevent reco...
详细信息
This paper describes the automation of a forearm prosthesis using the signal collected by a Fiber Bragg Grating (FBG) sensor. The FBG sensor is applied to one subject's forearm to measure the deformation as a resu...
详细信息
Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood agg...
详细信息
ISBN:
(纸本)9798350324457
Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph's topology, particularly for large-scale or complex *** propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph's topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current *** results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. These results hold across diverse datasets and edge features, underscoring the robustness and generalizability of our methods. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning. A significantly lower number of tunable parameters for a given evaluation metric makes TCNN and DVCNN especiall
In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visi...
详细信息
Stroke is a neurological syndrome that may cause severe cognitive and motor impairments for survival. Alternative rehabilitation techniques have been developed to recover lower-limb movements and gait of post-stroke p...
详细信息
Antenna-on-Chip (AoC) is one of the most promising solutions in upcoming 6G era. However, AoC suffers from low gain usually due to the highly conductive silicon substrate in mainstream complementary-metal-oxide-semico...
详细信息
ISBN:
(数字)9798331518424
ISBN:
(纸本)9798331518431
Antenna-on-Chip (AoC) is one of the most promising solutions in upcoming 6G era. However, AoC suffers from low gain usually due to the highly conductive silicon substrate in mainstream complementary-metal-oxide-semiconductor (CMOS) processes. Artificial magnetic conductors (AMC) embedded within the stack-up of standard CMOS processes have been widely used to enhance the gain by isolating the AoC from the Si substrate and providing constructive reflection. Nonetheless, the ultra-thin stack-up of standard CMOS processes causes that only the AMC unit cells nearby the AoC can be illuminated well while the outermost part is illuminated poorly, which prevents the AMC from its optimal reflection performance. To mitigate the issue, this paper proposes a novel via-based magnetic coupling enhancement structures (H-CES- V) to improve the AMC illumination by coupling the energy from well-illuminated unit cells to outermost unit cells magnetically. Compared to conventional AMC, the gain can be improved by 1.5 dBi with the proposed structure. Finally, the proposed AMC-backed AoC with H-CES- V shows a boresight gain of 7 dBi (12 dBi better than a standalone AoC without AMC), and a radiation efficiency of 59 % at 94 GHz.
暂无评论