检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Rocha, Karoline da Bermudez, José C.M. Rivero, Elena Riet Correa Costa, Márcio Holsbach Graduate Program in Electrical Engineering Federal University of Santa Catarina Florianópolis Brazil Department of Pathology Federal University of Santa Catarina Florianópolis Brazil

Background and Objectives: Oral squamous cell carcinoma (OSCC) is the most common oral cancer, with high mortality rates, making early detection crucial. Malignant transformation is preceded by oral potentially malignant disorders (OPMDs), with leukoplakia being the most frequent. Epithelial dysplasia (ED) is a key histological feature for predicting the risk of progression to OSCC. However, its diagnosis relies on subjective visual assessment by pathologists, which is influenced by experience and emotional state. This study aims to develop a Machine Learning (ML), based methodology to assist in ED detection in leukoplakia lesions. Methods: The proposed methodology integrates histopathological image analysis with complementary patient data. Epithelial regions were selected for cutout extraction based on pathologist knowledge and combined with risk factors from patient data. A multilayer perceptron artificial neural network (MLP-ANN) was trained and evaluated. Performance was compared with a pre-trained convolutional neural network (ResNet-50V2) using the McNemar test. Results: The MLP-ANN achieved an area under the curve (AUC) of 0.9484. No statistically significant difference was found between the proposed method and the pre-trained CNN. However, the proposed approach was approximately 9.7 times faster in computational time. Conclusions: The ML-based methodology demonstrated high classification performance and computational efficiency. Refining the confidence criterion for intermediate classification results may further enhance its diagnostic accuracy, supporting pathologists in ED detection. © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ring Oscillators with identical Circuit Structure to Measure Bias Temperature Instability

Ring Oscillators with identical Circuit Structure to Measure...

引用

International Conference on ASIC

作者： Daisuke Kikuta Ryo Kishida Kazutoshi Kobayashi Department of Electronics Graduate School of Science and Technology Kyoto Institute of Technology Japan Department of Electrical and Electronic Engineering Faculty of Engineering Toyama Prefectural University Japan

Ring oscillators (ROs) are frequently used to measure bias temperature instability (BTI). However, it is difficult to accurately compare the degradation rates of different BTI phenomenon because the parasitic components depend on circuit structures. The identical circuit structure with control signals is implemented to measure different BTI phenomenon. Test chips equipped with these ROs were fabricated in a 65 nm process. From the measurement results, well-known power-law models of BTI with time exponent n = 1/6 were extracted. The identical circuit structure can compare the BTI degradation rates of different BTI phenomenon based on the identical oscillation frequency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FDAM: Filter-Dedicated Approximate Multiplier Design for Real-Time CNN Acceleration

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Nguyen, Kihwan Kim Xuan Truong Jeon, Dongsuk Lee, Hyuk-Jae Korea Republic of program Department of Electrical Engineering Seoul08826 Korea Republic of Inter-University Semiconductor Research Center Seoul National University Graduate School of Convergence Science and Technology Research Institute for Convergence Science Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Video super-resolution (VSR) is widely used in various high-definition applications, such as HDTVs and smartphones, requiring a dedicated upscaling technique for realtime full-HD generation. To reduce on-chip buffers for largesize output feature maps, a streaming VSR accelerator may employ an output stationary dataflow, leading to a large energy consumption caused by frequent filter switching. To mitigate this, we introduce a new filter-dedicated multiplier design for realtime VSR acceleration. We replace costly multipliers with adders, shifters, and multiplexers (MUXes), referred to as unified multiple constant multiplications (UMCM). The conventional UMCM, however, may incur considerable area/power overhead due to the unified topology constraint among different filter sets. To address this problem, we propose a new approximated MCM (AMCM) problem to relax the constraint and an approximate compatible graph synthesis (A-CGS) framework to efficiently solve AMCM by jointly searching for approximated filters and constructing a unified graph. Additionally, we suggest a lightweight finetuning method by freezing approximated filters and only finetuning biases, which can recover the original model’s accuracy within a few epochs. Experimental results with synthetic data demonstrate that AMCM reduces the area by up to 49.8%, 44.8%, and 40.3% when considering constant sets of 2, 4, and 8, respectively. Our designs with SR application achieve up to a 73.3% reduction in energy consumption. Experiments with the Set5 and Set14 datasets show that our model with bias correction achieves similar restoration performance compared to the eightbit models. © 1982-2012 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Electrostatic Shielding for Bearing Current Mitigation - An Analysis of its Thermal Impact on the Motor

Electrostatic Shielding for Bearing Current Mitigation - An ...

引用

2022 IEEE IAS Petroleum and Chemical Industry Technical Conference, PCIC 2022

作者： Evo, Marco T.A. Junior, Arismar M.G. Silva, Caio Eduardo De Paula, Helder Federal University of São João Del Rei Electrical Engineering Department MG São João del Rei36307-352 Brazil Federal University of Uberlândia Graduate Program in Electrical Engineering MG Uberlândia Brazil Federal University of Uberlândia Faculty of Electrical Engineering MG Uberlândia Brazil

ISBN: (纸本)9781665497169

This work presents a study on the use of electrostatic shields to reduce bearing currents (both Electrostatic discharge machining and circulating currents), focusing on its thermal impact on the motor operation. 2-D finite element models are utilized to analyze the temperature distribution inside the coil winding slot of motors both with and without shielding. The results show that the shielding device can be used with a negligible influence on the temperature rise inside the slot. In addition, it is demonstrated that for some shield configurations, the stator winding eddy current loss can be attenuated. In such cases, the shield presence can also lead to a temperature reduction in the stator conductors. Furthermore, the developed models can be expanded to be used in the analysis of any other motor equipped with this type of solution, aiding the design and implementation of the shielding device. Keeping in mind that the majority of the motor failures are due to bearing problems, this paper contributes to the industry by addressing issues closely related to the reliability topic, such as solutions to increase the motor availability, which is the very case of the shielding device. © 2022 IEEE.

关键词： Induction motors

来源：评论

学校读者我要写书评

暂无评论

A 28nm Fully Integrated End-to-End Genome Analysis Accelerator for Next-Generation Sequencing

引用

IEEE Transactions on Biomedical Circuits and Systems 2025年 PP卷 PP页

作者： Wu, Yi-Chung Chen, Yen-Lung Yang, Chung-Hsuan Lee, Chao-Hsi Chen, Wen-Ching Lin, Liang-Yi Chang, Nian-Shyang Lin, Chun-Pin Chen, Chi-Shi Hung, Jui-Hung National Taiwan University Graduate Institute of Electronics Engineering Taipei Taiwan National Yang Ming Chiao Tung University Institute of Electronics Taiwan GeneASIC Technologies Corporation Hsinchu30288 Taiwan Taiwan Semiconductor Research Institute Hsinchu300091 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu30010 Taiwan National Taiwan University Department of Electrical Engineering Graduate Institute of Electronics Engineering Taipei10617 Taiwan

This paper presents the first end-to-end next-generation sequencing (NGS) data analysis accelerator for short-read mapping, haplotype calling, variant calling, and genotyping. It supports both single-end and paired-end short-reads (or reads) and uses the FM-index, a compact index data structure, for exact-match in short-read mapping. For inexact match part of short-read mapping, a dynamic programming array is proposed to determine the mapping results. To reduce the workload of short-read mapping, a rapid similarity calculation is designed. A rescue technique is also adopted to increase the overall sensitivity. In haplotype calling, a parallel k-mer processing engine can construct the de Bruijn graph and assemble the haplotypes. The variant calling step determines variants between a subject and a reference genome sequence with a variant discovery engine. Lastly, genotype likelihood is computed in parallel by a genotype likelihood computing engine, which outputs genotypes of all discovered variants and corresponding Phred-scaled likelihood (PL) values. This work completes end-to-end data analysis for the 50× PrecisionFDA dataset in an average of 28.2 minutes. It achieves a 3-to-59× higher throughput than the existing solutions with higher precision (99.79%) and sensitivity (99.03%). The chip also achieves a 935× higher energy efficiency than the Illumina DRAGEN FPGA acceleration system. © 2007-2012 IEEE.

关键词： Application specific integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Beamforming and Anti -Jamming with Intelligent Omni-Surfaces

Simultaneous Beamforming and Anti -Jamming with Intelligent ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yuhan Wang Shuhao Zeng Qingyu Liu Boya Di Hongliang Zhang School of Electronic and Computer Engineering Peking University Shenzhen Graduate School China Pengcheng Laboratory China Department of Electrical and Computer Engineering Princeton University USA School of Electronics Peking University China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Wireless transmission is vulnerable to malicious jamming attacks due to the openness of wireless channels, posing a severe threat to wireless communications. Current anti-jamming studies primarily focus on either enhancing desired signals or mitigating jamming, resulting in limited performance. To address this issue, intelligent omni-surface (lOS) is a promising solution. By jointly designing its reflective and refractive properties, the lOS can simultaneously nullify jamming and enhance desired signals. In this paper, we consider an lOS-aided multi-user anti-jamming communication system, aiming to improve desired signals and nullify jamming by optimizing lOS phase shifts and transmit beamforming. However, this is challenging due to the coupled and discrete lOS reflection and refraction phase shifts, the unknown jammer's beamformer, and imperfect jammer-related channel state information. To tackle this, we relax lOS phase shifts to continuous states and optimize with a coupling-aware algorithm using the Cauchy-Schwarz inequality and S-procedure, followed by a local search to recover discrete states. Simulation results show that the proposed scheme significantly improves the sum rate amid jamming attacks.

关键词： Wireless communication Array signal processing Simulation Reflection Jamming Channel state information

来源：评论

学校读者我要写书评

暂无评论

Optimizing 3D Clothing Models for VR: A Deep Learning Approach to Triangle Count Reduction

Optimizing 3D Clothing Models for VR: A Deep Learning Approa...

引用

IEEE International Conference on Consumer electronics-Taiwan (ICCE-TW)

作者： Surasachai Doungtap Varinya Phanichraksaphong Jenq-Haur Wang International Graduate Program of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

This study presents a deep learning framework optimizing 3D clothing models for VR, using a CNN to significantly reduce the triangle count of models from DeepFashion3D and CAP-UDF datasets. Achieving a balance between efficiency and detail, it cuts triangle count from over 160,000 to below 4,000, maintaining high DPI. The approach automates optimization, promising scalability and efficiency in VR fashion, setting a foundation for future 3D content development, enhancing virtual garment realism and interactivity.

关键词： Deep learning Solid modeling Three-dimensional displays Scalability Clothing Optimization Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Design of a Compact GaN-Based Four-Switch Buck-Boost Converter for Supercapacitor Integration in Missile Applications

Design of a Compact GaN-Based Four-Switch Buck-Boost Convert...

引用

Compatibility in Power electronics (CPE)

作者： Huzeyfe Hintoğlu Bünyamin Tamyürek Graduate School of Natural and Applied Sciences Gazi University Roketsan Missiles Inc. Ankara Türkiye Department of Electrical and Electronics Engineering Faculty of Engineering Gazi University Ankara Türkiye

ISBN: (数字)9798331515171

ISBN: (纸本)9798331515188

This paper presents the design and implementation of a compact GaN-based four-switch buck-boost converter tailored for supercapacitor integration in missile applications. The study's objective is to develop an alternative solution for using thermal batteries as a power source in missile systems because of their single-use nature, higher cost, and inability to adapt to varying operational concepts. The study starts by specifying missile system requirements and providing information about supercapacitors as a power source. Then, energy calculations are made in detail, and suitable supercapacitors are selected. To utilize the energy in the supercapacitors, the use of a four-switch buck-boost converter is determined, and its operation is explained. Firstly, a solution based on an integrated FET four-switch buck-boost converter has been evaluated. However, limitations in this solution, like handling higher current loads, low efficiency, and lower thermal management, have emerged. To overcome these limitations, a GaN-based four-switch buck-boost converter solution is proposed. The GaN-based architecture offers flexible solutions for higher voltage and current needs, lowers thermal stress, and increases efficiency. The design is validated through simulations and hardware implementations. Finally, the experimental setup and results are presented. The study concludes that using a GaN-based four-switch buck-boost converter for supercapacitor integration offers a compact, rechargeable, low-cost, and reliable solution in missile applications.

关键词： Missiles Voltage Supercapacitors Thermal management Hardware Power system reliability Batteries Thermal loading Stress Load modeling

来源：评论

学校读者我要写书评

暂无评论

Hot-Carrier Effect and Nanometer Metal Enabling Si-Based Mid-Infrared Detection Beyond 5μm of Wavelength

IEEE Photonics Journal

引用

IEEE Photonics Journal 2024年第3期16卷 1-10页

作者： Su, Zih-Chun Dong, Yao-Han Lin, Ching-Fuh Graduate Institute of Photonics and Optoelectronics National Taiwan University Taipei106319 Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taipei106319 Taiwan Department of Electrical Engineering National Taiwan University Taipei106319 Taiwan Center for Electronics Technology Integration National Taiwan University Taipei106319 Taiwan

Detection of photons with energy below the bandgap or Schottky barrier height of silicon has been limited in the past. Here, we reveal an approach that harnesses hot carriers through diffusion over a very thin metal to achieve silicon-based mid-infrared detection. With strong localized surface plasmon resonance (LSPR) effect to enhance infrared absorption and diffusion across 10 nm metal in Schottky structure, the hot carriers can be effectively collected. Such mechanism leads to responsivity from 0.098 mA/W to 0.237 mA/W for the wavelengths between 2700 nm and 5300 nm, all corresponding to photon energy below Schottky barrier height. Our investigation further shows that inverted pyramidal structures could enhance LSPR and so the responsivity. In addition, this approach enables us to monitor high frequency optical signals up to 2.1 MHz. By harnessing hot carriers and enhancing LSPR, we have not only overcome previous limitations in silicon-based mid-infrared detection but also opened up new possibilities for advanced photonics and optoelectronics applications. © 2009-2012 IEEE.

关键词： Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Dynamic Volumetric Video Coding with Tensor Decomposition

Dynamic Volumetric Video Coding with Tensor Decomposition

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Ju-Yeon Shin Yeoneui Kim Je-Won Kang Gun Bang Dept. of Electronic and Electrical Engineering and Graduate Program in Smart Factory Ewha Womans University Seoul South Korea Electronics and Telecommunications Research Institute Daejeon South Korea

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

Recently, volumetric video coding based on neural radiance fields has gained significant attention for storing and transmitting three-dimensional (3D) scenes captured from multi-view video. Because the neural networks are trained to produce novel view synthesis of surrounding 3D scenes, compressing the model and then rendering the colors and geometry through the decompressed model can be utilized as a 3D video coding system. However, although this approach provides superior performance compared to conventional 3D video coding standards using depth video, challenges remain in reducing overall model sizes to improve coding efficiency. In this paper, we propose a novel dynamic volumetric video coding technique that employs a Group of Volume (GoV) to divide multi-view video sequences into smaller chunks, addressing complex temporal dynamics. Our method uses volumetric video features represented with 3D spatial and temporal tensor matrices and vectors and encodes them with the GoVs. The tensors are compressed by existing 2D video codec, allowing for fast rendering and easing deployment. Experimental results validate that our method not only reduces memory footprint but also maintains high-quality rendering as compared to state-of-the-art studies.

关键词： Video coding Solid modeling Three-dimensional displays Image coding Tensors Visual communication Video sequences Rendering (computer graphics) Video codecs Standards

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：