检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Wang, Hongyu Zhang, Xiangyu Lou, Xin ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China Minist Educ Key Lab Intelligent Percept & Human Machine Colla Shanghai Peoples R China

ISBN: (纸本)9798350330991;9798350331004

6-D vision, which combines stereo and flow estimation to derive 3-D location and motion information, is crucial for comprehensive real-world perception. This paper presents a multi-scale block PatchMatch (MBPM)-based efficient 6-D vision algorithm with a balance tradeoff between computational complexity and accuracy, making it suitable for embedded application scenarios. By adopting a random search strategy, the proposed algorithm effectively reduces the computational burden without compromising accuracy. Additionally, the block-level processing approach further enhances efficiency by processing data in smaller, manageable chunks. Due to the significantly larger search range in flow estimation compared to stereo, we further incorporate direction initialization and multi-scale PatchMatch propagation techniques. These enhancements are crucial for ensuring reliable accuracy while expediting algorithm convergence. Compared with existing 6-D vision algorithms, the proposed method achieves 16.7% higher accuracy in stereo and 11.1% in flow estimation with much lower complexity. Even when faced with larger searching ranges, the proposed method exhibits consistent accuracy, allowing it to effectively handle fast motion scenarios.

关键词： 6-D vision optical flow stereo matching low complexity hardware-algorithm co-design

来源：评论

学校读者我要写书评

暂无评论

Numerical Performance Evaluation of 1 − 2 Sparse Reconstruction Using optical Analog Circuit

Numerical Performance Evaluation of 1 − 2 Sparse Reconstruc...

引用

2023 Asia Pacific Signal and information processing Association Annual Summit and Conference, APSIPA ASC 2023

作者： Furusawa, Soma Hayashi, Kazunori Kameda, Kaito Hayakawa, Ryo Graduate School of Informatics Kyoto University Kyoto Japan Graduate School of Engineering Science Osaka University Osaka Japan

ISBN: (纸本)9798350300673

Iterative shrinkage thresholding algorithm (ISTA), fast ISTA (FISTA) and alternating direction method of multipliers (ADMM) based algorithm are well known convex optimization algorithms based on proximal splitting for 1 − 2 optimization problem in compressed sensing. In our previous study, aiming at the implementation with optical analog devices, we have proposed constant inertial FISTA (CIFISTA) and an approximated ADMM based algorithm, which do not require the operation of division. In this paper, we consider to realize those algorithms with optical analog devices and show concrete configurations of analog circuits using optical devices. We have conducted computer experiments to evaluate the performance of each algorithm, taking into account the effects of the additive noise introduced by optical amplifiers assuming the implementation using optical devices for common optical fiber communications systems. From the numerical results, it has been confirmed that both the proposed CIFISTA and the approximated ADMM based algorithm can achieve faster convergence than ISTA, while the degradation of the steady state mean squared error (MSE) due to the circuit noise is much smaller than that of the conventional ADMM algorithm. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Battlefield information and tactics engine (BITE): a multimodal, large language model approach for battlespace management 6

Battlefield information and tactics engine (BITE): a multimo...

引用

Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications vi

作者： Connolly, Brian J. Southwest Res Inst 6220 Culebra Rd San Antonio TX 78238 USA

ISBN: (纸本)9781510674219;9781510674202

Battlespace management requires rapid processing of large amounts of data to facilitate informed decision-making. Large Language Models (LLMs) have demonstrated near or above human performance on a wide range of cognitive tasks. Current LLMs are unreliable, have poor explainability, and are prone to bias and hallucinations. As such they are unsuitable for many defense applications, but their abilities can be studied with future, improved LLMs in mind. Specifically, LLM capabilities to synthesize defense-relevant data and make decisions in a combat environment have been largely unexplored. The battlefield information and tactics engine (BITE) uses LLMs as observers and decision-makers in a military environment. A multiplayer video game focusing on modern mechanized combat, Squad by Offworld Industries Ltd., is used as an operating environment due to its moderate realism levels and focus on audio communication between players. BITE is tasked with ingesting tactical data, providing summaries of the current situation, and giving order to a squad of human players. The present work aims to qualitatively assess the suitability of BITE, and LLMs in general, for use in battlespace management systems. Shortcomings are identified in the areas of spatial awareness, decision-making time, and reliability. However, BITE exhibits instances of competent leadership and demonstrates a generalized understanding of modern mechanized combat. While current LLMs are currently deeply unsuitable for combat environments, BITE and similar approaches show promise in wargaming and training applications.

关键词： Image segmentation Object detection optical character recognition Decision making

来源：评论

学校读者我要写书评

暂无评论

Widely Linear Filtering for Multiimpairment Compensation in Dispersion Managed mQAM Modulated optical systems

引用

IEEE ACCESS 2022年 10卷 73278-73293页

作者： Yadav, Rekha Venkatasubramani, Lakshmi Narayanan Koilpillai, R. David Venkitesh, Deepa Indian Inst Technol Madras Dept Elect Engn Chennai 600036 Tamil Nadu India Dublin City Univ Sch Elect Engn Radio & Opt Commun Lab Dublin D09 E432 9 Ireland

We propose a blind joint equalization algorithm for M-QAM signals based on a widely linear filtering approach. The proposed scheme jointly compensates for receiver IQ imbalance, receiver IQ skew, polarization mixing, carrier recovery, followed by transmitter IQ imbalance and skew. We first investigate the proposed scheme's tolerance to each of these impairments through numerical simulations for 32 GBd PM-16QAM and PM-64QAM signals and compare its performance with the conventional digital processing algorithms with and without IQ imbalance compensation. The proposed joint transceiver equalizer outperforms the conventional algorithms with a Q(2) improvement of greater than 1 dB, and with improved tolerance to IQ imbalance. Further, with the proposed algorithm, we experimentally demonstrate the improvement in Q(2) value with respect to conventional DSP for both PM-16QAM and PM-64QAM signals. We also show that the MSE convergence of the proposed joint equalizer is much faster than conventional DSP algorithms.

关键词： Augmented signal processing IQ imbalance joint equalization modified widely linear CMA filter polarization multiplexing widely linear processing

来源：评论

学校读者我要写书评

暂无评论

A Word Structure Similarity Framework for Wordle Game 15

A Word Structure Similarity Framework for Wordle Game

引用

15th International Conference on Signal processing systems, ICSPS 2023

作者： Huang, Yi Rao, Wenjun Lao, Bin Lu, Wei Han, Ling Bo School of Information Science and Technology Guangdong University of Foreign Studies China School of Foreign Languages Sun Yat-sen University China School of Electronics and Information Engineering Guangdong Ocean University China

ISBN: (纸本)9781510675056

In 2022, lots of tweets consisting of emoji squares and a few words describing moods emerge on Twitter. In fact, it is the result of a word guessing game called Wordle. In order to figure out the relationship among words in Wordle, this paper tries to study the feedback data of its players and extract useful information to further improve the design of Wordle as well as other games of its kind. Specifically, from the perspective of word structure, strict and fuzzy matching algorithms were designed to simulate the data distribution of target word, while some common structure features of words were extracted and weighted by word frequency. On one hand, the data distribution of the target word is simulated with reference to the words with the most similar structures. On the other hand, the difficulty of a word in the Wordle game was quantified by analyzing the number of player’s tries, and then the difficulty coefficient of each word was calculated. Combined with the above numerical algorithms, the difficulty of the target word was evaluated objectively by the difficulty of its similar word sequences. Experiments showed that the proposed framework achieved good performance on the Wordle dataset. Our work was awarded Honorable Mention in 2023 Mathematical Contest in Modeling (MCM). © 2024 SPIE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

MAC-Leonets-A novel optimized hybrid convolutional neural networks for the segmentation and diagnosis of Edema diseases using retinal OCT images

引用

JOURNAL OF INTELLIGENT & FUZZY systems 2023年第6期44卷 10605-10620页

作者： Sudha, V. Shanmugam, Sathiya Priya Anitha, D. Raja, R. Sona Coll Technol Salem Dept ECE Tamil Nadu India Panimalar Engn Coll Dept ECE Chennai Tamil Nadu India SRM Inst Sci & Technol Sch Comp Dept Computat Intelligence Kattankulathur Tamilnadu India Muthayammal Engn Coll Autonomous Dept EEE Rasipuram Tamilnadu India

An intelligent segmentation and identification of edemas diseases constitutes a most important crucial ophthalmological issues since they provide important information for the diagnosis process in accordance to the disease severity. But diagnosing the different edema diseases using the OCT-images are considered to be daunting challenge among the researchers. The implementation of computational intelligence techniques such as machine learning, deep learning, bio inspired algorithms and image processing techniques may help the doctors for some extent in improving the automatic extraction and diagnosis process consequently improving patients' life quality. But, these are liable to more errors and less performance, which requires further improvisation in designing the intelligent systems for an effective classification of edema diseases. In this context, this paper proposes the hybrid intelligent framework for the identification, segmentation and classification of three types of edemas such as using the retinal optical coherence tomography (OCT) Images. In this process, Single Feed Forward Training networks (SLFTN) are integrated with Convolutional Layers whose hyperparameters are tuned by using Lion Optimization algorithm. An intensive experimentation is carried out using the Kaggle Retinal OCT Image datasets-2020 with Tensor flow and the proposed framework is trained with the different set of 84,494 images in which performance metrics such as accuracy, sensitivity, specificity, recall and f1score are calculated. Results shows the proposed system has provided satisfactory performance, reaching the average highest accuracy of 99.9% in identifying and classifying the respectively.

关键词： Machine learning deep learning retinal optical coherance tomography images convolutional layers lion optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Improving optical Character Recognition(OCR) Accuracy using Multi-Layer Perceptron(MLP) 7

Improving Optical Character Recognition(OCR) Accuracy using ...

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Krishnamoorthi, M. Ram, Karthi P Sri Sathyan, M. Vasanth, T. Dr.N.G.P Institute of Technology Professor of the Department Coimbatore India Dr.N.G.P Institute of Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350397284

optical Character Recognition (OCR) is a cutting-edge application that has been made possible due to advances in technology. optical Character Recognition involves using deep learning algorithms such as Multi-Layer Perceptron and Support Vector Machine to create a system that can recognize characters in an image. The optical Character Recognition system first segments each character individually as part of the pre-processing step, after which it post-processes the image to compare each character to the pre-processed data. In the modern world, optical Character Recognition is a crucial technology used in many industries to shorten turnaround times while increasing accuracy. However, one of the challenges faced with optical Character Recognition is that it takes longer to match exact results and produces results with lower precision and character misreadings. To address this challenge, the pre-processed data used by optical Character Recognition systems now includes practically all fonts. This means that the optical Character Recognition system has to match the characters with a much larger dataset, making the process more time-consuming and less accurate. To improve the accuracy and speed of optical Character Recognition systems, several methods have been employed. For instance, post-processing techniques such as error correction algorithms can be used to detect and correct errors in the optical Character Recognition output. Additionally, the use of deep learning techniques such as Conventional Neural Networks has been shown to improve the accuracy of optical Character Recognition systems. By employing these methods, optical Character Recognition can become an even more powerful tool that can shorten turnaround times while increasing accuracy. © 2023 IEEE.

关键词： optical character recognition

来源：评论

学校读者我要写书评

暂无评论

3rd International Conference on information Technologies and Intelligent Decision Making systems, ITIDMS 2023

3rd International Conference on Information Technologies and...

引用

3rd International Conference on information Technologies and Intelligent Decision Making systems, ITIDMS 2023

ISBN: (纸本)9783031603174

The proceedings contain 18 papers. The special focus in this conference is on information Technologies and Intelligent Decision Making systems. The topics include: Comparative Analysis of Traditional Machine Learning Approaches for Time Series Clustering Under Colored Noise;on the Open Transport Data Analysis Platform;investigation of the Characteristics of a Frequency Diversity Array Antenna;comparative Analysis of Fuzzy Controllers in a Truck Cruise Control System;implementation of a Blockchain-Based Software Tool to Verify the Authenticity of Paper Documents;development of Methods and algorithms for Dimension Reduction of Space Description for Pattern Recognition Problem;service for Checking Students’ Written Work Using a Neural Network;implementing a Jenkins Plugin to visualize Continuous Integration Pipelines;elimination of optical Distortions Arising from In vivo Investigation of the Mouse Brain;quantum Fourier Transform in Image processing;choosing an information Protection Mechanism Based on the Discrete Programming Method;application of Machine Learning Methods for Annotating Boundaries of Meshes of Perineuronal Nets;diagnostics of Animals Diseases Based on the Principles of Neutrosophic Sets and Sugeno Fuzzy Inference;the Technique of processing Non-Gaussian Data Based on Artificial Intelligence;development of Automation and Control System of Waste Gas Production Process Based on information Technology;machine Learning and Data Mining.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Infrared small target detection method based on full-direction dilation Gaussian filtering and local background estimation

Infrared small target detection method based on full-directi...

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2023

作者： Sun, Xiyu Pan, Shengda College of Information Engineering Shanghai Maritime University Shanghai China

ISBN: (纸本)9781510677685

Addressing the limitations of currently rare small target detection algorithms based on Human visual systems (HVS) that struggle with achieving satisfactory performance in complex backgrounds and lack high real-time capabilities, this paper introduces an innovative small target detection algorithm. This approach is founded on the integration of the Full-Direction Dilation Difference of Gaussians (FDD-DOG) and background estimation based on local contrast (LCBE). First, the high-frequency signal in the target area is enhanced by using the FDD-DOG operation, based on the difference between the real target and the background. Then, the background noise is further suppressed by assigning appropriate weights to the enhanced image by using local contrast-based background estimation. After that, the target to be detected is extracted by the adaptive threshold segmentation method. Experiments comparing the algorithm proposed in this paper with other HVS-based detection algorithms show that the method in this paper exhibits better detection performance in different infrared image sequences, where the background suppression factor is improved by an average of about 25 times and the signal-to-clutter ratio gain is improved by an average of about 15 times. © 2024 SPIE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Cloud and cloud shadow detection for optical satellite imagery: Features, algorithms, validation, and prospects

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2022年 188卷 89-108页

作者： Li, Zhiwei Shen, Huanfeng Weng, Qihao Zhang, Yuzhuo Dou, Peng Zhang, Liangpei Wuhan Univ Sch Resource & Environm Sci Wuhan Peoples R China Hong Kong Polytech Univ Dept Land Surveying & Geo Informat Hung Hom Kowloon Hong Kong Peoples R China Chinese Acad Sci Northwest Inst Eco Environm & Resources Lanzhou Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan Peoples R China

The presence of clouds prevents optical satellite imaging systems from obtaining useful Earth observation information and negatively affects the processing and application of optical satellite images. Therefore, the detection of clouds and their accompanying shadows is an essential step in preprocessing optical satellite images and has emerged as a popular research topic in recent decades due to the interest in image time series analysis and remote sensing data mining. This review first analyzes the trends of the field, summarizes the progress and achievements in the cloud and cloud shadow detection methods in terms of features, algorithms, and validation of results, and then discusses existing problems, and provides our prospects at the end. We aim at identifying the emerging research trends and opportunities, while providing guidance for selecting the most suitable methods for coping with cloud contaminated problems faced by optical satellite images, an extremely important issue for remote sensing of cloudy and rainy areas. In the future, expected improvements in accuracy and generalizability, the combination of physical models and deep learning, as well as artificial intelligence and online big data processing platforms will be able to further promote processing efficiency and facilitate applications of image time series. In addition, this review collects the latest open-source tools and datasets for cloud and cloud shadow detection and launches an online project (Open Satellite Image Cloud Detection Resources, i.e., OpenSICDR) to share the latest research outputs (https://***/dr-lizhiwei/OpenSICDR).

关键词： Cloud detection Cloud shadow detection optical remote sensing Satellite imagery Cloudy and rainy regions

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：