检索结果-内蒙古大学图书馆

2009 International conference on optical Instruments and Technology, OIT 2009

ISBN: (纸本)9780819478924

The proceedings contain 97 papers. The topics discussed include: diffractive optics with plasmonics and metamaterials;brightness field and luminance distribution of light guiding plate using micro molding;activity at Instrument Technology Research Center (ITRC);analog mean delay method (AMD) for real-time fluorescence lifetime microscopy (FLIM);principle and application of portable NIR tea drinks analyzer;the design and application of laser triangulation ranging system based on virtual instruments;research and hardware implementation of image enhancement algorithm in OLED system;analysis and optimization of the stereo system with a biprism adapter;determination of zero incident angle by optical feedback effect and its applications in the measurement of refractive indices;and double-threshold image segmentation method based on gray gradient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

design and computational Study of a Two Dimensional Photonic Crystal Based Ethanol Sensor

Design and Computational Study of a Two Dimensional Photonic...

引用

Integrated Circuits and Communication systems (ICICACS), IEEE International conference on

作者： D Sreekanth Savita Soma Mahesh V Sonth Guru Nanak Dev Engineering College Bidar Visvesvaraya Technological University Belagavi Karnataka India CMR Technical Campus Hyderabad Department of ECE Guru Nanak Dev Engineering College Bidar Department of E&TC SECS JSPM University Pune

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

This research article provides a computational study of light interaction with two dimensional photonic crystal (PhC) structure. This PhC structure is used to measure ethanol percentage in liquid water by identifying and computing mid gap wavelength shift. Analysis of the Maxwell's equations that govern the photon behaviour in the periodic structure is discussed in detail for PhC structures. The photonic band gap (PBG) which prohibits the photon momentum in certain directions in the crystal is computed using plane wave expansion (PWE) method by deriving solutions to the eigenvalue equation. A two dimensional (2D) PhC structure is designed by taking 18 × 17 number of holes on a dielectric slab. This holes on the dielectric configuration is used to sense the ethanol level in liquid water. The PBG width for the design in transverse electric mode is [ωa/2πc] ranging from 0.3841 to 0.4428. The band gap size Δλ 480 nm and mid gap wavelength λ c = 2391.2 nm is achieved from the structure. The sensor achieves a sensitivity of 10645.24 nm/RIU and a transmission ratio more than 94%. This structure is a suitable candidate for ethanol sensing applications as it offers a wide bandgap for light propagation.

关键词： Sensitivity Liquids Photonic band gap Ethanol Wavelength measurement Lattices Dielectrics optical sensors Maxwell equations Photonics

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Multi-Class Classification of GUI/UI Textual and Non-Textual Elements Through Enhanced AI Framework

Segmentation and Multi-Class Classification of GUI/UI Textua...

引用

Intelligent systems and computational Networks (ICISCN), International conference on

作者： Kalyanaraman P Padma Priya R Rahul Kumar Smita Basavaraj Kambi Sandeep B S Aravind Nandanasabapathy Jhananithaa B Abhirami A Shubh Gupta Ramachandra Aditya Stuti Stuti VIT University Vellore India Samsung R&D India Bangalore India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

The process of building and testing Graphical User Interface (GUI) elements in Android apps is labor-intensive, requiring meticulous validation by human testers. This work proposes an automated framework for extracting, preprocessing, and classifying GUI elements from mobile app screenshots. Using OpenCV, the system preprocesses images by removing device-specific artifacts, and a Convolutional Neural Network (CNN) classifies non-textual elements. optical Character Recognition (OCR) integration enhances text analysis by addressing variations in font size and orientation. The framework generates a JSON file with the semantic properties of each element. Extensive experimentation on a large-scale mobile app dataset demonstrates the framework’s effectiveness, achieving a training accuracy of 97.61%. Compared to traditional GUI analysis tools, the proposed method significantly improves accuracy, scalability, and automation. Key results include enhanced cross-platform compatibility, precise element recognition, and streamlined mobile app testing workflows. This hybrid framework, combining CNN and OCR, provides developers and QA teams with a robust tool to automate UI analysis, offering significant improvements in efficiency, reliability, and user-focused design.

关键词： Training Accuracy Automation Text analysis optical character recognition Semantics Mobile applications Convolutional neural networks Graphical user interfaces Testing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Parallel Control for Wideband Multi-Frequency Vibration Rejection: design and Application to A Piezoelectric Tip-tilt Stage

Adaptive Parallel Control for Wideband Multi-Frequency Vibra...

引用

International conference on Mechatronics (ICM)

作者： Li Wen Tao Tang Kaoru Yamamoto National Key Laboratory of Optical Field Manipulation Science and Technology Key Laboratory of Optical Engineering Institute of Optics and Electronics Chinese Academy of Sciences Chengdu China University of Chinese Academy of Sciences Beijing China Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Fukuoka Japan

ISBN: (数字)9798331533892

ISBN: (纸本)9798331533908

Image-stabilized piezoelectric tip-tilt stages are subjected to various external disturbances. Traditional disturbance rejection methods primarily focus on narrow-band disturbances, neglecting the impact of wideband disturbances characterized by energy concentration across multiple frequency bands, which can significantly degrade stabilization accuracy. These wideband disturbances are typically time-varying, with wide spectral peaks appearing at frequencies above the servo bandwidth. To address the challenge of mitigating such disturbances, this paper proposes an adaptive parallel control method. The adaptive strategy enables two-degree-of-freedom estimation of the disturbance's central frequency and spectral peak width, allowing for automatic adjustment of control efforts based on real-time disturbance characteristics. Based on the estimated disturbance features, a reduced-order parallel control strategy is designed to accommodate the presence of multiple wideband disturbances. The proposed control strategy was evaluated on a piezoelectric tip-tilt imaging system. Results demonstrate that the method effectively suppresses multiple wideband disturbances.

关键词： Vibrations Time-frequency analysis Adaptive systems Precision engineering Transforms Robustness Real-time systems Servomotors Wideband Tuning

来源：评论

学校读者我要写书评

暂无评论

Automated Optic Disc and Cup Segmentation Using Mask R-CNN for Glaucoma Assessment

Automated Optic Disc and Cup Segmentation Using Mask R-CNN f...

引用

Cybernetics and Innovations (ICCI), International conference on

作者： Siwakorn Inkong-Ngam Kreangsak Tamee Rabian Wangkeeree Department of Computer Science and Information Technology Naresuan University Phitsanulok Thailand Department of Mathematics Naresuan University Phitsanulok Thailand

ISBN: (数字)9798331533267

ISBN: (纸本)9798331533274

Glaucoma, a leading cause of irreversible blindness, requires precise segmentation of the optic disc and optic cup in fundus images for early diagnosis and progression monitoring. This study presents an automated deep-learning-based segmentation approach using Mask R-CNN, trained on the G1020 dataset, which consists of 1,020 fundus images with corresponding labeled masks. The dataset was split into an 80% training set (816 images) and a 20% test set (204 images). The model was finetuned with a customized predictor for multiclass segmentation to effectively detect the optic disc and cup regions. Training was conducted using a stochastic gradient descent optimizer with a learning rate scheduler to enhance convergence. The proposed model achieved an average Dice coefficient of 0.9381 for the optic disc and 0.8372 for the optic cup, with corresponding Intersection over Union (IoU) scores of 0.8887 and 0.7319, demonstrating robustness in identifying these critical anatomical structures. The segmentation results show significant potential for clinical applications, aiding ophthalmologists in automated glaucoma assessment. Future work will focus on improving the model's generalizability to diverse datasets and integrating it into real-time clinical decision-making systems.

关键词： Glaucoma Integrated optics Training Image segmentation Technological innovation Accuracy computational modeling optical imaging Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous CNN Compilation Framework for RISC-V CPU and NPU Integration Based on ONNX-MLIR

引用

IEEE Transactions on Computer-Aided design of Integrated Circuits and systems 2025年

作者： Cao, Shan Yang, Meiling Liu, Yintao Li, Yu Zhao, Beining Chen, Xinyu Jiang, Zhiyuan Shanghai University Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science Shanghai200444 China

With the continuous advancement of convolutional neural networks (CNNs), many neural network processing units (NPU) have emerged in recent years. NPUs offer advantages such as improved energy efficiency and low latency compared to traditional processors. However, NPUs often struggle to keep pace with the growing complexity of algorithmic models, which limits the implementation of certain AI applications. Central processing units (CPU) are known for their versatility, but are computationally inefficient. Combining the strengths of both architectures could present a viable solution to these challenges. Despite this potential, there is currently insufficient academic focus on CPU/NPU co-computing, and few architectures or toolchains have been developed to support such integration. In this paper, we propose a RISC-V CPU/NPU co-computing-based compilation framework to solve the problem of mapping from algorithms to heterogeneous architectures. To bridge the computational gap between heterogeneous platforms, within ONNX-MLIR, we developed three phases to support operator packing, algorithm adaption, and data coordination. To integrate heterogeneous compilation platforms, we introduce four additional functions to handle task scheduling, weight quantization, weight rearrangement, and memory management. In particular: (1) to optimize the transition overhead, an operator packing technique is introduced by extending the ONNX-MLIR framework with custom operators, which enhances NPU efficiency by reducing the number of transitions between operations. (2) At the aspect of task scheduling, a three-mode task scheduler is developed to allow users to customize task distribution for correctness verification, performance optimization, or detailed analysis on heterogeneous platforms, which demonstrates the versatility of our framework. (3) In terms of memory management, an optimized scheme for CPU/NPU architectures is proposed to ensure accurate data access. This memory management emplo

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

On the Fault-Tolerant Capability of Optimal Constructions of optical Priority Queues

On the Fault-Tolerant Capability of Optimal Constructions of...

引用

International conference on Computing, Networking and Communications (ICNC)

作者： Jay Cheng Shin-Shiang Huang Department of Electrical Engineering National Tsing Hua University Hsinchu R.O.C.

ISBN: (数字)9798331520960

ISBN: (纸本)9798331520977

Construction of optical buffers for packet conflict resolution is one of the most important and challenging issues in all-optical packet switching. Priority queues (PQs) is one of the most general and versatile buffering schemes, and includes the most commonly used first-in first-out (FIFO) queues and last-in first-out (LIFO) queues as special cases. The best constructions of optical PQs currently available was obtained by Cheng et al. by using a feedback architecture consisting of an optical crossbar switch and k groups of optical FIFO multiplexers with delay one (FM1’s), where the i th group has m i parallel optical n i - to-1 FM1’s (n i FM1’s) with the same buffer size B i (B i ≥ 1) for i = 1,2,…,k (see Figure 2 in Section I). In this paper, we consider an important practical issue in the constructions of optical PQs: the fault-tolerant capability. We consider the scenario that each group of FM1’s has the same number of FM1’s, say, m i = m for 1 ≤ i ≤ k, and show that the optimal constructions obtained by Cheng et al. possess fault-tolerant capability: the feedback architecture can still be operated as an optical PQ but with a smaller buffer size after up to f FM1’s fail to function properly, where the fault-tolerant capability f can be expressed in terms of the number m of FM1’s in each group and the numbers n 1 ,n 2 ,…,n k of arrival links of the FM1’s in the k groups as f = min 1≤i≤k ⌊(m − 1)/(n i − 1)⌋. Such a result can be used in the design of the parameters m and n 1 ,n 2 ,…,n k to provide quality of service (QoS) that guarantees a certain level of fault-tolerant capability.

关键词： Integrated optics Multiplexing Fault tolerance optical feedback optical switches optical buffering Fault tolerant systems Quality of service Computer architecture optical packet switching

来源：评论

学校读者我要写书评

暂无评论

ELECTRO-optical systems design conference-1971 WEST.

引用

1971年

作者： Conf

Collection of 59 papers by various authors. The topics discussed in different sessions are - laser technology, atmospheric optics and aerosol scattering, coherent optics, IR detectors and systems, laser applications, imaging, computer output microfilm, underwater electro-optics, solid state detectors and applications, and information display. Selected papers are indexed separately.

关键词： Laser beams

来源：评论

学校读者我要写书评

暂无评论

Simulative Analysis of DSP-PDM-256-QAM-Enabled Free Space optics Transmission: Impact of Rain and Fog Weather conditions

Simulative Analysis of DSP-PDM-256-QAM-Enabled Free Space Op...

引用

Device Intelligence, Computing and Communication Technologies, (DICCT), International conference on

作者： Ritu Sharma Neetu Harmanpreet Kaur ECE Department Chandigarh University Mohali India Department of Physics Chandigarh University Mohali India

ISBN: (数字)9798331543358

ISBN: (纸本)9798331543365

This research work presents a complete simulation-based analysis of a free-space optics (FSO) communication system that combines digital signal processing (DSP) with polarization-division multiplexing (PDM) and 256-QAM modulation. The performance of the system is assessed under different weather conditions, such as rain and fog. The design and evaluation are done using a simulation framework, with bit error rate (BER) and error vector magnitude (EVM) acting as the main performance parameters. Significant findings indicate that the system is able to transmit the data over a maximum distance of 1200 m in light fog, 700 m in moderate fog, and 550 m in heavy fog. Similarly, in rainfall conditions, the system provides data transmission over distances of 1600 m during light rain, 1250 m in moderate rain, and 750 m during heavy rain, all considering the EVM value below 3% and the BER value at or below 10– 4 . These results explain the reliability and adaptability of the DSP-PDM-256-QAM-enabled FSO system throughout the challenging weather conditions, highlighting its suitability for implementation in difficult environments. The study gives a key understanding of optimizing FSO systems to combat harsh weather, laying the foundation for robust, high-performance communication networks.

关键词： Multiplexing Rain Free-space optical communication Atmospheric modeling Bit error rate Weather forecasting Digital signal processing Attenuation Data communication Meteorology

来源：评论

学校读者我要写书评

暂无评论

Lightweight Edge AI Model for Real-Time Vessel Detection in Maritime Surveillance Using Multi-Modal Data

Lightweight Edge AI Model for Real-Time Vessel Detection in ...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International conference on

作者： S.Devika Priyadharshini K. Vadivazhagan Department of Computer and Information Science Annamalai University Tamilnadu India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

For the purpose of monitoring, it is necessary to design vessel detecting system that are not only accurate but also lightweight, efficient and capable of functioning on edge devices. Even if they are achieved, traditional deep learning methods require a significant amount of computational power, which makes it difficult to implement them in situations with limited resources, such as unmanned aerial vehicles (UAV) or remote marine monitoring stations as examples. A revolutionary lightweight Edge artificial intelligence method was created for real time vessel detection is presented in this work. Utilizing method architecture such as Mobile Net and Tiny YOLO, the advanced method compression technique such as pruning and quantization is applied to reduce the amount of computational complexity and memory footprint without affecting the accuracy of detection. Synthetic Aperture Rader (SAR) imaging and multi modal data sources such as optical and infrared images are employed into the proposed system to improve its robustness in a variety of maritime circumstances. It is further optimized for low latency operation which guarantees high speed inference which is essential for time sensitive applications such as identification of illicit fishing, the prevention or piracy and the search and rescue operations. It has been demonstrated through experimental evaluations on high resolution SAR dataset that the method is capable of delivering improved detection performance while simultaneously reducing the number of computational resources required. This result in a significant enhancement in both the speed of processing and energy efficiency. This finding provides the possibility of deploying this lightweight method on edge devices, which would revolutionize maritime surveillance by providing solution that are real time, dependable and scalable.

关键词： Adaptation models Accuracy computational modeling Surveillance Image edge detection Soft sensors Autonomous aerial vehicles Real-time systems Robustness Synthetic aperture radar

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：