检索结果-内蒙古大学图书馆

Proceedings of the 2025 ACM/SIGDA International Symposium on Field programmable Gate Arrays

作者： Ling-Chi Yang Chi-Jui Chen Trung Le Bo-Cheng Lai Scott Hauck Shih-Chieh Hsu Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of College of Electrical and Computer Engineering in National Yang Ming Chiao Tung University Hsinchu Taiwan Electrical and Computer Engineering in University of Washington Seattle USA Electrical and Computer Engineering University of Washington Seattle USA Physics University of Washington Seattle USA

ISBN: (纸本)9798400713965

FPGAs are a compelling substrate for supporting machine learning inference. Tools such as High-Level Synthesis and hls4ml can shorten the development cycle for deploying ML algorithms on FPGAs, but can struggle to handle the large on-chip storage needed for many of these models. In particular the high BRAM usage found in many of these flows can cause Place & Route failures during synthesis. In this paper we propose using a Simulated-Annealing based flow to perform BRAM-aware quantization. This approach trades off inference accuracy with BRAM usage, to provide a high-quality inference engine that still meets on-chip resource constraints. We demonstrate this flow for Transformer-based machine learning algorithms, which include Flash Attention in a Stream-based Dataflow architecture. Our system imposes minimal accuracy drops, yet can reduce BRAM usage by 20%-50%, and improve power efficiency by 264%-812% compared to existing Transformer-based accelerators on FPGAs

关键词： efficient transformer

来源：评论

学校读者我要写书评

暂无评论

Light extraction improvement via ITO p-electrodes for InGaN red micro-LEDs emitting at 640 nm

Optics Continuum

引用

Optics Continuum 2025年第5期4卷 1040-1050页

作者： Cesur Altinkaya Mohammed A Najmi Daisuke Iida Kazuhiro Ohkawa Material Science and Engineering Program Physical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia cesur.altinkaya@kaust.edu.sa Electrical and Computer Engineering Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia daisuke.iida@kaust.edu.sa kazuhiro.ohkawa@kaust.edu.sa

We present light extraction efficiency (LEE) improvement for InGaN red micro-light emitting diodes (micro-LEDs) of various sizes operating at low current densities. We compared the characteristics of micro-LEDs with indium tin oxide (ITO) transparent p-electrodes with conventional opaque metal p-electrodes. 50 µm × 50 µm micro-LEDs with ITO p-electrodes achieved a peak on-wafer external quantum efficiency (EQE) of 2.54% with an emission wavelength of 640 nm at a current density as low as 0.4 A/cm 2 . This represents a 1.18-fold improvement in peak EQE compared to devices with metal p-electrodes. Light ray tracing simulation confirmed that the ITO p-electrodes exhibit 1.18 times higher light escape than metal-based micro-LEDs, validating the role of enhanced light extraction. These findings provide valuable insights for advancing high-definition display and VR applications.

关键词： Atomic layer deposition Indium tin oxide Light extraction Opacity Quantum efficiency Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Using Random Forest and Linear SVM for Dyslexia Classification on Hebb-Williams Mazes

Using Random Forest and Linear SVM for Dyslexia Classificati...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Padmanabh Kaushik Yih-Choung Yu Lisa Gabel Department of Electrical and Computer Engineering Lafayette College Easton PA USA Department of Psychology and Neuroscience Program Lafayette College Easton PA USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

Dyslexia is a learning disability that negatively impacts an individual's ability to read, write, spell, and sometimes speak. It results in difficulties in recognizing and decoding words and patterns, despite normal level of education and intelligence. Studies have shown that early detection of dyslexia is vital for improving learning abilities in young children. Many virtual platforms exist for diagnosing and rehabilitating dyslexia; however, most require tests that measure reading skills. Since developing reading capabilities can delay the detection of dyslexia, a gaming platform based on Hebb-Williams mazes has been developed. This platform does not rely on reading skills and can diagnose dyslexia in young children. This paper presents a machine learning driven approach using two algorithms - Random Forest and Linear SVM - to classify reading abilities based on data from participants performing virtual maze tasks, which are indicative of symptoms of dyslexia. Results from this study indicate that it is possible to predict dyslexia with up to 95% accuracy based on a participant's performance in virtual gaming environments.

关键词： Support vector machines Radio frequency Accuracy Dyslexia Prediction algorithms Boosting Classification algorithms Pattern recognition Random forests Synthetic data

来源：评论

学校读者我要写书评

暂无评论

7-Level Soft Charging Switched Capacitor Multilevel Inverter

引用

IEEE Access 2025年

作者： Memis, Mehmet Karakilic, Murat Van Yüzüncü Yıl University Başkale Vocational School Electrical and Energy Program Van Turkey Igdir University Department of Computer Engineering Igdir Turkey

This paper proposes a novel 7-level switched capacitor multilevel inverter (SC-MLI) topology with soft charging capability and analyzes the performance in terms of efficiency and component optimization. The proposed structure achieves high efficiency up to 97.32% while producing the same output level with fewer components compared to existing SC-MLI designs in the literature. Moreover, the total cost function (CF) value of 3.26 is among the lowest values, indicating that the system offers an economically advantageous solution. Simulation and experimental studies confirm that the system generates stable output waveforms under resistive and inductive loads and operates stably over a wide frequency and modulation index (MI) range. In particular, the effect of the soft charging technique on capacitor currents has been investigated and it has been found that this technique minimizes switching losses by reducing inrush current transients. The SPWM method using high switching frequency produces a natural soft charging effect on the capacitor currents, producing lower peak currents compared to NLC control and improving the overall efficiency of the system. The study shows that SC-MLI is optimized as a function of low component count, high efficiency and low cost. The results reveal that this structure is suitable for high-performance applications such as renewable energy systems, electric vehicle power conversion systems, uninterruptible power supplies (UPS), microgrids, and motor drives. These findings provide an important reference for the future development of SC-MLI designs. © 2013 IEEE.

关键词： Uninterruptible power systems

来源：评论

学校读者我要写书评

暂无评论

Cascaded multiparameter quantum metrology

引用

Physical Review A 2025年第1期111卷 012618-012618页

作者： Gregory Krueper Lior Cohen Juliet T. Gopinath Department of Physics University of Colorado Boulder Boulder Colorado 80309 USA Department of Electrical Computer and Energy Engineering University of Colorado Boulder Boulder Colorado 80309 USA Materials Science and Engineering Program University of Colorado Boulder Boulder Colorado 80309 USA

We present an innovative, platform-independent concept for multiparameter sensing where the measurable parameters are in series, or cascaded, enabling measurements as a function of position. With temporally resolved detection, we show that squeezing can give a quantum enhancement in sensitivity over that of classical states by a factor of e2r, where r≈1 is the squeezing parameter. As an example, we have modeled an interferometer that senses multiple phase shifts along the same path, demonstrating a maximal quantum advantage by combining a coherent state with squeezed vacuum. Further classical modeling with up to 100 phases shows linear scaling potential for adding nodes to the sensor. The approach can be applied to remote sensing, geophysical surveying, and infrastructure monitoring.

关键词： Interferometers

来源：评论

学校读者我要写书评

暂无评论

An Improved Vision Transformer Architecture-Based computer Recognition Platform for Lilium Classification

An Improved Vision Transformer Architecture-Based Computer R...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Xiang-Rui Huang Huai-Jhan Ke Szu-Yu Kuo Liang-Bi Chen Department of Electrical Engineering Master Program in Electrical Engineering and Computer Science National Penghu University of Science and Technology Penghu Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Shipping and Transportation Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Lilies are popular in the global flower market, but consumers often lack information about specific varieties. To address this issue, this paper proposes a computer recognition platform based on the Vision Transformer (ViT) architecture. The proposed platform uses an improved vision transformer (ViT) architecture to classify different types of lilies, allowing consumers to access information and names of various Lilium species. The experimental results show that the proposed lily classification model achieved a 96.4% accuracy rate in classifying six lily species.

关键词： computer vision Electric potential Accuracy Computational modeling computer architecture computer applications Flowering plants Network architecture Transformers Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Convergent effects of peptides on the initiation of feeding motor programs in the mollusk Aplysia

引用

Journal of Neurophysiology 2025年第5期133卷 1368-1379页

作者： Evans, Colin G. Barry, Michael A. Reaver, Carrie N. Patel, Paras R. Chestek, Cynthia A. Perkins, Matthew H. Jing, Jian Cropper, Elizabeth C. Department of Neuroscience Friedman Brain Institute Icahn School of Medicine at Mount Sinai New York NY United States Department of Biomedical Engineering Biointerfaces Institute University of Michigan Ann Arbor MI United States Department of Electrical Engineering and Computer Science Neurosciences Program Robotics Program University of Michigan Ann Arbor MI United States State Key Laboratory of Pharmaceutical Biotechnology Institute for Brain Sciences Chemistry and Biomedicine Innovation Center Jiangsu Engineering Research Center for MicroRNA Biology and Biotechnology Advanced Institute for Life Sciences School of Life Sciences Nanjing University Nanjing China

Neuropeptides configure the feeding network of Aplysia. For example, egestive activity is promoted by small cardioactive peptide (SCP), and ingestive activity is promoted by a combination of feeding circuit activating peptide (FCAP) and cerebral peptide 2 (CP-2). In addition, SCP and FCAP/CP-2 have a common network effect that does not contribute to motor program specification. They increase the excitability of an interneuron, B63. In this report, we further characterized the effects of peptides on B63. We performed voltage-clamp experiments and used a step protocol to look at steady-state currents. We found that SCP and FCAP/CP-2 both induced an inward current that was virtually absent in low-sodium saline. Previous work has established that B63 is unusual in the feeding circuit in that subthreshold depolarizations are autonomously generated that can trigger motor programs. Here, we show that this autonomous activity is more frequent in the presence of peptides. Previous studies have also shown that activity of the feeding central pattern generator (CPG) can be initiated by neurons that excite B63, e.g., by cerebral buccal interneuron 2 (CBI-2), a projection neuron that triggers biting-like motor programs. Here, we show that the latency of CBI-2-induced activity is decreased by stimulation of the esophageal nerve (EN) (which releases endogenous SCP). These results, taken together with previous results, indicate that peptides that act divergently to configure network activity additionally act convergently to promote motor program induction. We present data that suggest that this arrangement facilitates brief switches between ingestive and egestive motor activity. © 2025 The Authors.

关键词： central pattern generator invertebrate modulation motor program neuropeptide

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Analysis Using Maximum Abundance Classification

Hyperspectral Image Analysis Using Maximum Abundance Classif...

引用

International Conference on Intelligent Control and Information Processing (ICICIP)

作者： Nian Zhang Sougre-Nonma Stephanie Rouamba Wagdy H. Mahmoud Lara A. Thompson Department of Electrical and Computer Engineering University of the District of Columbia Washington D.C. USA Department of Mechanical Engineering Biomedical Engineering Program University of the District of Columbia Washington D.C. USA

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

This paper presents a satellite hyperspectral image processing method that utilizes a maximum abundance classifier to categorize different regions of hyperspectral images into ground truth classes. First, the class names for each endmember and their corresponding columns in the signature matrix are identified, followed by the visualization of their spectral profiles. Abundance maps for the endmembers are then generated using the fully constrained least squares (FCLS) method. Afterward, the maximum abundance classifier is applied, and the resulting classified image is displayed with color-coded pixels. The abundance maps illustrate the spatial distribution of endmembers across the hyperspectral image, where the abundance values of each pixel represent the proportion of each endmember present. By determining the highest abundance value for each pixel and assigning it to the corresponding endmember class, the pixels within the hyperspectral images are classified. Experimental results demonstrate that the proposed MAC method effectively handles mixed pixels. In addition, it can effectively deal with the mixed pixel problem in hyperspectral images because it identifies components by calculating the abundance values for each pixel rather than relying solely on single spectral features.

关键词： Visualization Image segmentation Satellites Graphical models Information processing Hyperspectral imaging Intelligent control Image classification Distribution functions

来源：评论

学校读者我要写书评

暂无评论

MathReader : Text-to-Speech for Mathematical Documents

MathReader : Text-to-Speech for Mathematical Documents

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sieun Hyeon Kyudan Jung Nam-Joon Kim Hyun Gon Ryu Jaeyoung Do Department of Electrical and Computer Engineering Seoul National University Department of Mathematics Chung-Ang University NVIDIA Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions. This is because most modern academic papers are written in LaTeX, and when LaTeX formulas are compiled, they are rendered as distinctive text forms within the document. However, traditional TTS document readers output only the text as it is recognized, without considering the mathematical meaning of the formulas. To address this issue, we propose MathReader, which effectively integrates OCR, a fine-tuned T5 model, and TTS. MathReader demonstrated a lower Word Error Rate (WER) than existing TTS document readers, such as Microsoft Edge and Adobe Acrobat, when processing documents containing mathematical formulas. MathReader reduced the WER from 0.510 to 0.281 compared to Microsoft Edge, and from 0.617 to 0.281 compared to Adobe Acrobat. This will significantly contribute to alleviating the inconvenience faced by users who want to listen to documents, especially those who are visually impaired. The code is available at https://***/hyeonsieun/MathReader.

关键词： Text recognition Error analysis Pipelines Optical character recognition Graphics processing units Signal processing Real-time systems Mathematical models Text to speech Speech processing

来源：评论

学校读者我要写书评

暂无评论

Learning 3D Scene Analogies with Neural Contextual Scene Maps

arXiv

引用

arXiv 2025年

作者： Kim, Junho Bae, Gwangtak Lee, Eun Sun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open spaces, we propose teaching machines to identify relational commonalities in 3D spaces. Instead of focusing on point-wise or object-wise representations, we introduce 3D scene analogies, which are smooth maps between 3D scene regions that align spatial relationships. Unlike well-studied single instance-level maps, these scene-level maps smoothly link large scene regions, potentially enabling unique applications in trajectory transfer in AR/VR, long demonstration transfer for imitation learning, and context-aware object rearrangement. To find 3D scene analogies, we propose neural contextual scene maps, which extract descriptor fields summarizing semantic and geometric contexts, and holistically align them in a coarse-to-fine manner for map estimation. This approach reduces reliance on individual feature points, making it robust to input noise or shape variations. Experiments demonstrate the effectiveness of our approach in identifying scene analogies and transferring trajectories or object placements in diverse indoor scenes, indicating its potential for robotics and AR/VR applications. © 2025, CC BY.

关键词： Adversarial machine learning

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：