检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Ye, Yuanxin Zhang, Jiacheng Zhou, Liang Li, Jinjin Ren, Xiaoyue Fan, Jianwei Faculty of Geosciences and Environmental Engineering Southwest Jiaotong University Chengdu611756 China School of Computer and Information Technology Xinyang Normal University Xinyang464000 China

With the expansion of optical and SAR image fusion application scenarios, it is necessary to integrate their information in land classification, feature recognition, and target tracking. Current methods focus excessively on integrating multimodal feature information to enhance the information richness of the fused images, whereas neglecting the highly corrupted visual perception of the fused results by modal differences and SAR speckle noise. To address that, this paper proposes a novel optical and SAR image fusion framework named Visual Saliency Features Fusion (VSFF), which is based on the extraction and balancing of significant complementary features of optical and SAR images. Firstly, we propose a decomposition algorithm of complementary features to reduce most of the speckle noise in the initial image, and divide the image into main structure features and detail texture features. Then, for the fusion of main structure features, we reconstruct the visual saliency features maps of the pixel and structure that contain significant information from optical and SAR images, and input them into a total variation constraint model to compute the fusion result and achieve the optimal information transfer. Meanwhile, we construct a new feature descriptor based on the Gabor wavelet, that separates meaningful detail texture features from residual noise and selectively preserves features that can improve the interpretability of fusion result. Finally, a fast IHS transform fusion is used to supplement the fused image with realistic color information. In a comparative analysis with seven state-of-the-art fusion algorithms, VSFF achieved better results in qualitative and quantitative evaluations, and our fused images have a clear and appropriate visual perception. © 2023, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Learning Fine-Grained information Alignment for Calibrated Cross-Modal Retrieval

Learning Fine-Grained Information Alignment for Calibrated C...

引用

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

作者： Jianhua Dong Shengrong Zhao Hu Liang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China

Masked Language Modeling (MLM) and Image-Text Matching (ITM) are always used in fusion encoder to learn the joint representation of images and text. In existing methods, the masking strategy of MLM leads to the neglect of image details during the modeling process. Meanwhile, the sampling strategy of ITM struggles to consistently select high-difficulty hard negative instances, reducing the effectiveness of constraints. This leads to challenges in aligning fine-grained information in cross-modal retrieval. In response to this challenge, a fine-grained information alignment-based visual language model (FAM) is proposed in this paper. On one hand, the attribute-based masking strategy is employed in MLM, helping the model focus on the details of objects in images during modeling. On the other hand, the robust hard negative sample generation strategy provides challenging negative samples for ITM by altering the relationships between objects. This enables the model to align relationships between objects in different modalities and thus calibrates cross-modal retrieval. Extensive experiments demonstrate the effectiveness of the model in cross-modal retrieval tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EVALUATING EXPLAINABLE AI METHODS IN DEEP LEARNING MODELS FOR EARLY DETECTION OF CEREBRAL PALSY

arXiv

引用

arXiv 2024年

作者： Pellano, Kimji N. Strümke, Inga Groos, Daniel Adde, Lars Ihlen, Espen Alexander F. Department of Neuromedicine and Movement Science Faculty of Medicine and Health Sciences Norwegian University of Science and Technology Trondheim7034 Norway Department of Computer Science Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim7034 Norway Department of Clinical and Molecular Medicine Faculty of Medicine and Health Sciences Norwegian University of Science and Technology Trondheim7034 Norway

Early detection of Cerebral Palsy (CP) is crucial for effective intervention and monitoring. This paper tests the reliability and applicability of Explainable AI (XAI) methods using a deep learning method that predicts CP by analyzing skeletal data extracted from video recordings of infant movements. Specifically, we use XAI evaluation metrics — namely faithfulness and stability — to quantitatively assess the reliability of Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) in this specific medical application. We utilize a unique dataset of infant movements and apply skeleton data perturbations without distorting the original dynamics of the infant movements. Our CP prediction model utilizes an ensemble approach, so we evaluate the XAI metrics performances for both the overall ensemble and the individual models. Our findings indicate that both XAI methods effectively identify key body points influencing CP predictions and that the explanations are robust against minor data perturbations. Grad-CAM significantly outperforms CAM in the RISv metric, which measures stability in terms of velocity. In contrast, CAM performs better in the RISb metric, which relates to bone stability, and the RRS metric, which assesses internal representation robustness. Individual models within the ensemble show varied results, and neither CAM nor Grad-CAM consistently outperform the other, with the ensemble approach providing a representation of outcomes from its constituent models. Both CAM and Grad-CAM also perform significantly better than random attribution, supporting the robustness of these XAI methods. Our work demonstrates that XAI methods can offer reliable and stable explanations for CP prediction models. Future studies should further investigate how the explanations can enhance our understanding of specific movement patterns characterizing healthy and pathological development. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

RFID-Based Student Identification Card Attendance Monitoring System 1

引用

6th International Conference on Communication, Devices and Networking, ICCDN 2022

作者： Awotunde, Joseph Bamidele Sur, Samarendra Nath Aderinto, Muqeetat Tolulope Gaber, Tarek Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electronics and Communication Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University East Sikkim Rangpo Majitar737136 India Faculty of Computers and Informatics Suez Canal University Ismailia41522 Egypt School of Science Engineering and Environment University of Salford ManchesterM5 4WT United Kingdom

ISBN: (数字)9789819919833

ISBN: (纸本)9789819919826

Passive (low-frequency) radio-frequency identification (RFID) technology is being used in an increasing number of contactless systems. This project presents contactless attendance system passive radio-frequency identification (RFID)-based approach. RFID is a technology that uses radio waves to send information from an RFID tag attached to an object to a reader for the purpose of monitoring and identifying the object. This technology is one of the most widely used in the world;almost every organization uses RFID-based tracking, identification, and other functions on some level. A contactless RFID-based attendance monitoring system is a less cost-effective and efficient automated solution. The proposed system focuses on an RFID-based attendance monitoring system that uses RFID technology in connection with a programmable logic circuit (such as an Arduino) to address the problems that traditional paper and contact-based attendance systems experience. Each user (student or lecturer) will be given an RFID card. When the user puts the RFID card near the RFID reader, the RFID reader scans the user's data stored on the card, recording the current time using the real-time clock (RTC) module and the RFID tag number (UID) on the SD card. The Arduino uses the SD card module to communicate with the SD card. The buzzer beeps when a tag is scanned, and the system employs a 16 × 2 LCD module for display purposes. This system will take attendance automatically, and the attendance records will be stored in the database. The SD card serves as backup and can help to generate accurate reports when required. Therefore, the system rectifies human errors, saves time, and gives clear attendance. The system has been implemented using C# programming language. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Radio waves

来源：评论

学校读者我要写书评

暂无评论

Dealing with noise in crowdsourced GPS human trajectory logging data

Dealing with noise in crowdsourced GPS human trajectory logg...

引用

作者： Adhinugraha, Kiki Rahayu, Wenny Hara, Takahiro Taniar, David Department of Computer Science and Information Technology School of Engineering and Mathematical Sciences La Trobe University MelbourneVIC Australia Department of Multimedia Engineering Osaka University Osaka Japan Faculty of Information Technology Monash University MelbourneVIC Australia

As a crowdsourcing map platform, OpenStreetMap (OSM) relies on public contributions to enhance its dataset where the contributors can create, modify or remove features from the maps or share their trajectory trips in the repository. The majority of the data provided in a crowdsourcing platform are manually created and reviewed to suit real-world conditions, hence human perception is the key indicator to consider the correctness of the data. One of the data that is provided by crowdsourcing platform is public trajectory. Public trajectory data contains details of historical trips obtained from contributors' GPS logger devices that are embedded in mobile devices, wearable devices, satnavs, or vehicle GPS trackers to record the user's trajectory path. While public trajectory data can be used as an alternate data source for human movement analysis, this crowdsourced dataset is also prone to noise and inaccuracy which makes the preprocessing step an important phase prior of any processing step. In this article, we discuss the characteristics and the most common noise from crowdsourcing GPS trajectories and utilize a non-map-matching approach convex hull-based reduction method to minimize spike noise, followed by granularity reduction to reduce the number of trajectory points while maintaining the nature of the trajectories. © 2020 John Wiley & Sons, Ltd.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Delay-Beat Differential Phase Demodulation for Laser Phase Noise Immunity in Phase-Sensitive OTDR

Delay-Beat Differential Phase Demodulation for Laser Phase N...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Heng Qian Chuan Li Chengli Li Yunnan Key Laboratory of Computer Technologies Application Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Opo-electronic Information Technology School of Physics and Electronic Information Yunnan Normal University Kunming China

A phase demodulation method immune to laser phase noise based on time-delay beat-frequency coherent Φ-OTDR is proposed. In this method, the two Rayleigh backscattered light beams with time delay are beat with local light beams respectively, and the phase difference of the two beat signals is used instead of the traditional distance-difference phase to obtain the local disturbance information. In this way, the impact of laser phase noise introduce by the distance-difference phase is avoid, and the constraint of laser linewidth on phase demodulation performance is weakened. In the experiment, a demodulation accuracy of -63.5dB rad 2 /Hz is achieved under the condition of a laser with a linewidth of 100kHz, which is improve by 11dB compared to traditional phase demodulation method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Image Diagnosis with Convolutional Neural Networks

Enhancing Medical Image Diagnosis with Convolutional Neural ...

引用

International Conference on Advances in information technology (ICAIT)

作者： K. Mahadevan S. Pushparani K. SashiRekha V.M. Sivagami R. Usharani Department of Computer Science and Engineering CARE College of Engineering Trichy Tamil Nadu India Department of Computer Science and Engineering Meenakshi College of Engineering Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Information Technology Sri Venkateswara College of Engineering Chennai Tamil Nadu India Department of Computational Intelligence Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

This paper is a comparative analysis of medical image diagnosis algorithms with Convolutional Neural Networks (CNNs) and other methods; such as Support Vector Machine (SVM), Random Forest, and k-nearest Neighbors (k-NN) The study performs evaluations on datasets with multi-modalities like medical images and diagnostic and various imaging modalities. Results shows that CNNs have the upper hand over traditional, static algorithms across several metrics that assesses the performance of the system such as accuracy, precision, recall, and F1. In particular, CNN precision was 90.5% while the recall was 93.7%, and the accuracy was 92.1% as well as F1-score 92.0%. In addition, the high area under the Receiver Operating Characteristic curve (AUC-ROC) of over 0.95 for the CNN also signed for its excellent discriminatory power. These outcomes only exemplify CNN usefulness in the diagnostic area because it is an exact and accurate method for analyzing medical images. Although the nets CNNs are deployed in clinical cases may help address concerns regarding interpretability, compliance with regulations, and ethical opinions, such issues still exist and require further exploration. Overall, this research takes the first steps in directing algorithmic approach towards medical diagnosis and show the feasibility in deployment of CNNs as inseparable pieces of equipment in modern healthcare.

关键词： Support vector machines Ethics Accuracy Recurrent neural networks Machine learning algorithms Nearest neighbor methods Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Captioning with Reinforcement Learning

Image Captioning with Reinforcement Learning

引用

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Anand Verma Saurabh Agarwal K.V. Arya Ivan Petrlik Roberto Esparza Ciro Rodriguez Department of Information Technology ABV-IIITM Gwalior Madhya Pradesh India Department of Computer Science and Engineering Multimedia and Information Security Research Group ABV-Indian Institute of Information Technology and Management Gwalior India Faculty of Industrial and Systems Engineering National University Federico Villarreal Lima Peru Faculty of Systems Engineering and Informatics National University Mayor de San Marcos

Image captioning involves generating a natural language description that accurately represents the content and context of an image. To achieve this, image captioning utilises various machine learning techniques and fields, such as computer vision and natural language processing. In the field of image captioning, a lot of advances have been made with encoder-decoder models and reinforcement learning algorithms. However, there are still problems of imbalance between testing and training, as reinforcement learning only handles single comparator metrics such as CIDEr, SPICE, and BLEU and could not perform better in multiple metrics at once. Which is why a lack of diversity can be seen in generated captions. This idea proposes a general technique for collaborative updating that can bridge the gap between evaluation measures and test metrics to produce captions that are more human-like. To increase the precision of image captions, the approach involves using a compiled reward system that considers multiple evaluation metrics to compare the generated sentence with the provided sentences. We will evaluate the model's performance and the reward updating process on standard datasets like MS COCO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of LoRa 923 MHz for the Internet of Things

Performance Evaluation of LoRa 923 MHz for the Internet of T...

引用

information technology International Seminar (ITIS)

作者： Angga Putra Juledi Moh. Khoridatul Huda Muhammad Taufik Dwi Putra Lalu Delsi Samsumar Puput Dani Prasetyo Adi Yanuar Nurdiansyah Department of Information Technology Faculty of Science and Technology Universitas Labuhanbatu Labuhanbatu City Indonesia Universitas Islam Raden Rahmat (UNIRA) Malang Malang East Java Indonesia Department of Computer Engineering Universitas Pendidikan Indonesia Bandung Indonesia Department of Information Technology Universitas Teknologi Mataram Mataram City Indonesia Research Center for Telecommunication National Research and Innovation Agency (BRIN) Bandung Indonesia Faculty of Computer Science University of Jember

ISBN: (数字)9798331521295

ISBN: (纸本)9798331521301

This research focuses on enhancing the performance of data transmission in the Internet of Things (IoT) by leveraging LoRa technology. Specifically, it utilizes the LILYGO 923 MHz LoRa32 board, which integrates the ESP32 microcontroller with a LoRa module and additional devices like a 0.96-inch OLED display. This board also features a serial converter interface, simplifying the programming process, and uses a micro USB connection for both power and uploading code. One of the goals of this research is to enable the transmission of images using LoRa, though currently, only image conversion during transmission is implemented. The study includes reliability testing of the LoRa module over a distance of 10 km. The results show that the Packet Delivery Ratio (PDR) for Spreading Factor (SF) 7 is 50%, while for SF 12, it improves to 85%. Additionally, the Received Signal Strength Indicator (RSSI) measurements at a distance of 1000 meters with 3 Non-Line-of-Sight (NLoS) conditions yielded values of -120 dBm, -90 dBm, and -78 dBm. These results highlight the potential of LoRa technology in improving IoT data transmission, especially for long-range applications.

关键词： Performance evaluation Seminars LoRa Universal Serial Bus Internet of Things Servers Received signal strength indicator Arrays Reliability Testing

来源：评论

学校读者我要写书评

暂无评论

Integrating Vehicular Clouds For Supporting Smart Transportation Infrastructure

Integrating Vehicular Clouds For Supporting Smart Transporta...

引用

International Colloquium on Smart Grid Metrology (SmaGriMet)

作者： Josip Balen Marin Matijašević Lovro Pejčić Josip Kundid Muhammad Moazam Azeem Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University of Osijek Osijek Croatia TTTech Auto Osijek Osijek Croatia Department of Computer Science and Engineering Qatar University Doha Qatar

An emerging vehicular ad hoc network (VANET) is a network of connected vehicles which are communicating with each other and with roadside units (RSUs) exchanging useful information. As a result, road safety is increased, and complex traffic management is enabled. However, we are moving one step further and proposing the usage of vehicle resources, such as computing capabilities and data storage, for enabling vehicular clouds which can efficiently support smart transportation infrastructure. The main goal for establishing vehicular clouds is utilization of vast amounts of unused hardware resources available at vehicles for enabling and supporting smart transportation infrastructure. Vehicular clouds can enable additional distributed computing and storage resources to various groups of users, as well as introduce new use cases and applications. Recent vehicular cloud computing methods and models, as well as vehicular cloud computing architecture and services are explored in this paper. Based on the research and our work a new vehicular cloud computing architecture VANET-CC is proposed and elaborated. Furthermore, possible services for cloud computing are pointed out together with vehicle management in such clouds.

关键词： Cloud computing Smart cities Vehicular ad hoc networks Memory computer architecture Metrology Hardware

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：