检索结果-内蒙古大学图书馆

Enhancing Security in Distributed Drone-Based Litchi Fruit Recognition and Localization Systems

computers, Materials & Continua 2025年第2期82卷 1985-1999页

作者： Liang Mao Yue Li Linlin Wang Jie Li Jiajun Tan Yang Meng Cheng Xiong Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute Shenzhen Polytechnic UniversityShenzhen518055China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China

This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate Selective Kernel Attention (SKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable lighting and obstructive foliage. To reinforce security, the tasks of recognition and localization are distributed among multiple drones, enhancing resilience against tampering and data manipulation. This distribution also optimizes resource allocation through collaborative processing. The model remains lightweight and is optimized for rapid and accurate detection, which is essential for real-time applications. Our proposed system, validated with a D435 depth camera, achieves a mean Average Precision (mAP) of 0.943 and a frame rate of 169 FPS, which represents a significant improvement over the baseline by 0.039 percentage points and 25 FPS, respectively. Additionally, the average localization error is reduced to 0.82 cm, highlighting the model’s high precision. These enhancements render our system highly effective for secure, autonomous fruit-picking operations, effectively addressing significant performance and cybersecurity challenges in agriculture. This approach establishes a foundation for reliable, efficient, and secure distributed fruit-picking applications, facilitating the advancement of autonomous systems in contemporary agricultural practices.

关键词： Objective detection deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Visible-Infrared Person Re-Identification with Large Foundation Models 38

Empowering Visible-Infrared Person Re-Identification with La...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Zhangyi Yang, Bin Ye, Mang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China

Visible-Infrared Person Re-identification (VI-ReID) is a challenging cross-modal retrieval task due to significant modality differences, primarily resulting from the absence of color information in the infrared modality. The development of large foundation models like Large Language Models (LLMs) and Vision Language Models (VLMs) motivates us to explore a feasible solution to empower VI-ReID with off-the-shelf large foundation models. To this end, we propose a novel Text-enhanced VI-ReID framework driven by Large Foundation Models (TVI-LFM). The core idea is to enrich the representation of the infrared modality with textual descriptions automatically generated by VLMs. Specifically, we incorporate a pre-trained VLM to extract textual features from texts generated by VLM and augmented by LLM, and incrementally fine-tune the text encoder to minimize the domain gap between generated texts and original visual modalities. Meanwhile, to enhance the infrared modality with extracted textual representations, we leverage modality alignment capabilities of VLMs and VLM-generated feature-level filters. This enables the text model to learn complementary features from the infrared modality, ensuring the semantic structural consistency between the fusion modality and the visible modality. Furthermore, we introduce modality joint learning to align features across all modalities, ensuring that textual features maintain stable semantic representation of overall pedestrian appearance during complementary information learning. Additionally, a modality ensemble retrieval strategy is proposed to leverage complementary strengths of each query modality to improve retrieval effectiveness and robustness. Extensive experiments on three expanded VI-ReID datasets demonstrate that our method significantly improves the retrieval performance, paving the way for the utilization of large foundation models in downstream multi-modal retrieval tasks. © 2024 Neural information processing systems foundat

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leadership Succession in the National science Foundation Revolutionizing engineering Departments Projects 129

Leadership Succession in the National Science Foundation Rev...

引用

129th ASEE Annual Conference and Exposition: Excellence Through Diversity, ASEE 2022

作者： Williams, Julia M. Andrijcic, Eva Margherio, Cara Litzler, Elizabeth Mohan, Sriram Güler, Selen Engineering Management Computer Science & Software Engineering

来源：评论

学校读者我要写书评

暂无评论

Smart Glove with Mobile Application to Detect Static Arabic Hijaiyah Hand Code for Quran Recitation 21

Smart Glove with Mobile Application to Detect Static Arabic ...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Elshareif, Mohamed Elgilani Eltahir Ahmad Alias, Nurul Aswani Jomhari, Nazean Sofian, Hazrina University of Malaya Faculty of Computer Science and Information Technology Department of Software Engineering Kuala Lumpur Malaysia

ISBN: (纸本)9798350393569

The use of assistive technology in the field of education is now a common practice in today's tech-driven era. The implementation is quite rampant in all levels and sections of education, including by special needs students with hearing impairments. With the help of technology or Internet of Things (IoT), they are offered with better opportunities to improve their communication and the teaching and learning process especially when it comes to sign language. However, the situation is quite different for Muslim deaf individuals. Sign language is not only used for communication but also as a form for reciting the Quran. Yet, the utilization of technology in the area of sign language for Quranic recitation is still limited. Hence, the goal of this study was to design and develop a sensor-based sign language recognition device consisting of a sensory smart glove and mobile application to detect Arabic sign language alphabets used in Quran recitation. The experimental result shows that the gesture recognition rate of 28 different Arabic alphabet signs, performed by 7 different signers, is 79.08%. The significance of the system lies in its mobility and capability to recognize the hand gestures regardless of the background noise. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models 38

Reference Trustable Decoding: A Training-Free Augmentation P...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shi, Luohe Yao, Yao Li, Zuchao Zhang, Lefei Zhao, Hai National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage. Our code can be found at https://***/ShiLuohe/ReferenceTrustableDecoding. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study on Identifying, Categorizing and Reporting Usability Bugs and Challenges 4

A Study on Identifying, Categorizing and Reporting Usability...

引用

4th International Conference on Communication Technologies, ComTech 2023

作者： Ain, Qurat Ul Rana, Tauseef Aamana Department of Computer Science Islamabad Pakistan NUST Military College of Signals Department of Computer Software Engineering Islamabad Pakistan Department of Software Engineering Rawalpindi Pakistan

ISBN: (纸本)9798350337211

To assess the quality, acceptability and user experience of interactive applications, usability is one of the most integral quality attributes. However, significant number of usability bugs are being experienced by the end users of interactive applications thus creating a gap between users and technology. To bridge this gap and to overcome those usability bugs and challenges, it is significantly important to clearly identify the those usability bugs along with the gaps and challenges causing them. This research study aims to identify the usability bugs being experienced by users of interactive applications and proposes a categorization taxonomy for the identified bugs. Moreover, to reach the cause of emergence of usability bugs, the study attempts to identify and report the usability gaps and challenges in existing usability practices. Furthermore, this study performs a mapping between the identified gaps and challenges in existing practices to that of the recommendations to address the identified gaps. Index Terms - Usability, interactive applications, usability bugs, user experience, user satisfaction, usability testing, user interface. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Recently emerging trends in big data analytic methods for modeling and combating climate change effects

引用

Energy Informatics 2024年第1期7卷 6页

作者： Ikegwu, Anayo Chukwu Nweke, Henry Friday Mkpojiogu, Emmanuel Anikwe, Chioma Virginia Igwe, Sylvester Agbo Alo, Uzoma Rita Software Engineering Department Veritas University Abuja Nigeria Computer Science Department David Umahi Federal University of Health Sciences Ebonyi State Uburu Nigeria Computer Science Department Alex Ekwueme Federal University Ebonyi Ndufu-Alike Nigeria Computer Science Department Ebonyi State University Ebonyi State Abakaliki Nigeria

Big climate change data have become a pressing issue that organizations face with methods to analyze data generated from various data types. Moreover, storage, processing, and analysis of data generated from climate change activities are becoming very massive, and are challenging for the current algorithms to handle. Therefore, big data analytics methods are designed for significantly large amounts of data required to enhance seasonal change monitoring and understand and ascertain the health risks of climate change. In addition, analysis of climate change data would improve the allocation, and utilisation of natural resources. This paper provides an extensive discussion of big data analytic methods for climate data analysis and investigates how climate change and sustainability issues can be analyzed through these approaches. We further present the big data analytic methods, strengths, and weaknesses, and the essence of analyzing big climate change using these methods. The common datasets, implementation frameworks for climate change modeling, and future research directions were also presented to enhance the clarity of these compelling climate change analysis challenges. This big data analytics method is well-timed to solve the inherent issues of data analysis and easy realization of sustainable development goals. © The Author(s) 2024.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Developing Accurate Sri Lankan Sign Language to Tamil Vocal And American Sign Language Translation 10

Developing Accurate Sri Lankan Sign Language to Tamil Vocal ...

引用

10th International Conference on engineering and Emerging Technologies, ICEET 2024

作者： Ratnasingam, Sabaskaran Sakajarasa, Dilaxshan Chamara, Didula Gamage, Aruna Ishara Sri Lanka Institue of Information Technology Department of Computer Science & Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798331532895

This research presents a web-based real-time Sri Lankan Sign Language (SLSL) translation system aimed at bridging communication gaps for individuals with speech and hearing disabilities. Leveraging advanced machine learning, the system translates SLSL gestures into Tamil vocal language and American Sign Language (ASL), supported by video-to-text conversion with Yolo-NAS, voice model and clips of animated 3D characters. Key objectives included accurate vocabulary mapping for selected vocabularies, real-time translation with minimal latency, an audio player to display Tamil voice and animated 3D characters to convey nuanced ASL gestures. The system is integrated as one website, but each translation part has separate pages where users can navigate and fulfill their needs. User feedback highlighted the simple and direct user interface design and fluidity of interactions, particularly the animated 3D characters in SLSL to ASL translation. Challenges included optimizing gesture rendering and expanding vocabulary coverage, which will be addressed in future work. This research underscores the potential of AI-driven solutions for enhancing accessibility and inclusivity in communication with cross-lingual and cross-model communication features. © 2024 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Optimisation of sparse deep autoencoders for dynamic network embedding

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1361-1376页

作者： Huimei Tang Yutao Zhang Lijia Ma Qiuzhen Lin Liping Huang Jianqiang Li Maoguo Gong College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Institute for Infocomm Research Agency for Science Technology and ResearchSingaporeSingapore Key Laboratory of Collaborative Intelligence Systems Ministry of EducationXidian UniversityXi'anChina

Network embedding(NE)tries to learn the potential properties of complex networks represented in a low-dimensional feature ***,the existing deep learningbased NE methods are time-consuming as they need to train a dense architecture for deep neural networks with extensive unknown weight parameters.A sparse deep autoencoder(called SPDNE)for dynamic NE is proposed,aiming to learn the network structures while preserving the node evolution with a low computational *** tries to use an optimal sparse architecture to replace the fully connected architecture in the deep autoencoder while maintaining the performance of these models in the dynamic ***,an adaptive simulated algorithm to find the optimal sparse architecture for the deep autoencoder is *** performance of SPDNE over three dynamical NE models(*** architecture-based deep autoencoder method,DynGEM,and ElvDNE)is evaluated on three well-known benchmark networks and five real-world *** experimental results demonstrate that SPDNE can reduce about 70%of weight parameters of the architecture for the deep autoencoder during the training process while preserving the performance of these dynamical NE *** results also show that SPDNE achieves the highest accuracy on 72 out of 96 edge prediction and network reconstruction tasks compared with the state-of-the-art dynamical NE algorithms.

关键词： deep autoencoder dynamic networks low-dimensional feature space network embedding sparse structure

来源：评论

学校读者我要写书评

暂无评论

Ubiquitous WiFi and Acoustic Sensing:Principles,Technologies,and Applications

引用

Journal of computer science & Technology 2023年第1期38卷 25-63页

作者：黄佳玲王云舒邹永攀伍楷舜倪明选 The IoT Research Center College of Computer Science and Software EngineeringShenzhen UniversityShenzhen 518060 China The Hong Kong University of Science and Technology(Guangzhou) Guangzhou 511455China The Hong Kong University of Science and Technology Hong KongChina

With the increasing pervasiveness of mobile devices such as smartphones,smart TVs,and wearables,smart sensing,transforming the physical world into digital information based on various sensing medias,has drawn researchers’great *** different sensing medias,WiFi and acoustic signals stand out due to their ubiquity and zero hardware *** on different basic principles,researchers have proposed different technologies for sensing applications with WiFi and acoustic signals covering human activity recognition,motion tracking,indoor localization,health monitoring,and the *** enable readers to get a comprehensive understanding of ubiquitous wireless sensing,we conduct a survey of existing work to introduce their underlying principles,proposed technologies,and practical *** we also discuss some open issues of this research *** survey reals that as a promising research direction,WiFi and acoustic sensing technologies can bring about fancy applications,but still have limitations in hardware restriction,robustness,and applicability.

关键词： WiFi sensing acoustic sensing human-computer interaction human activity recognition

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：