检索结果-内蒙古大学图书馆

Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-Based Recruitment

SN Computer Science 2023年第5期4卷 434页

作者： Peña, Alejandro Serna, Ignacio Morales, Aythami Fierrez, Julian Ortega, Alfonso Herrarte, Ainhoa Alcantara, Manuel Ortega-Garcia, Javier Universidad Autónoma de Madrid Madrid 28049 Spain

The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good;(ii) privacy and data ownership;(iii) transparency and accountability;and (iv) fairness in AI-driven decision-making processes. All these four Human-Centric requirements are closely related to each other. With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious case study focused on automated recruitment: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles including image, text, and structured data, which are consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind automatic recruitment tools built this way (a common practice in many other application scenarios beyond recruitment) to extract sensitive information from unstructured data and exploit it in combination to data biases in undesirable (unfair) ways. We present an overview of recent works developing techniques capable of removing sensitive information and biases from the decision-making process of deep learning architectures, as well as commonly used databases for fairness research in AI. We demonstrate how learning approaches developed to guarantee privacy in latent spaces can lead to unbiased and fair automatic decision-making process. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems. © 2023, The Author(s).

关键词： Automated recruitment Bias Biometrics Computer vision Deep learning FairCV Fairness Multimodal Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Contrast Enhancement and ROI detection in satellite images Application to the environment and sustainable development

Contrast Enhancement and ROI detection in satellite images A...

引用

International conference on image and Signal processing and their Applications (ISPA)

作者： Aicha Mehidi Malika Mimi Abdallah Mehidi Soraya Zehani Electrical Engineering Department Laboratory of Signals and Systems Faculty of Sciences and Technology University of Abdelhamid Ibn Badis Mostaganem Algeria Laboratory of Signals and Systems Faculty of Sciences and Technology University of Abdelhamid Ibn Badis Mostaganem Algeria Electrical Engineering Department Laboratory of Vision and Communication Systems Faculty of Sciences and Technology University of Biskra

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

During the last few years, remote sensing is considerably used for Earth observation for the environment and sustainable development. The temporal classes of satellite images provide better information for monitoring the earth's surface at different scales; therefore these images are becoming a very relevant opportunity of investigating. The numerical analyses of image processing are based on the artificial intelligence (AI) tool rather than the traditional methods. The environmental indicators from these images offer very important statistics, the carried out work of dynamic phenomena, the observation event and interpretation of evolving circumstances like: atmospheric conditions, crises and natural disasters taking the opportunity to be studied, several problems come out of deforestation and monitoring of water resources (water bodies). The purpose of this study is focused on drawing out details from the database used and then to give an offer for a texture analysis strategy. Firstly, using specific development and then developing the existing software in the second hand. This work is to establish an algorithm for the detection of region of interest (water body) which is based on the theory of fuzzy logic and the hypothesis of Fuzzy C-Means.

关键词： Earth image segmentation Software algorithms Signal processing algorithms Satellite images Sustainable development Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Based on Edge Computing of Wireless Sensor Networks

Application of Deep Learning Based on Edge Computing of Wire...

引用

Advanced algorithms and Control Engineering (ICAACE), International conference on

作者： Huaqiao Duan Qijing Wang Nanjing University Suzhou China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

With the rapid advancement of the Internet of Things (IoT) technology, Wireless Sensor Networks (WSN) have become a fundamental component of contemporary society. Nevertheless, the surge in complex application scenarios coupled with an exponential increase in data volumes has rendered the traditional cloud computing processing model insufficient. The edge computing-based deep learning framework can effectively handle these large-scale image datasets without compromising privacy and security, facilitating intelligent analysis and decision-making. This study,through experimental design, we developed a deep learning model grounded in edge computing, tailored for addressing specific challenges in image data processing within wireless sensor networks, such as image recognition, classification, and analysis. For concrete metrics, consider a scenario where edge computing-based deep learning models were deployed for real-time traffic flow analysis. These models, by processing data locally, can reduce data transmission times by up to 70%, enhancing response times from seconds to milliseconds. Furthermore, in privacy-sensitive applications such as wildlife monitoring, edge computing ensures data is processed on-site, reducing the risk of sensitive data exposure by over 80%. Lastly, in terms of energy consumption, edge devices operating on optimized deep learning algorithms can achieve a reduction of up to 40% compared to traditional cloud-based processing methods, underlining the significant efficiency and performance gains achievable with this technology integration.

关键词： Deep learning Wireless sensor networks Cloud computing Computational modeling image edge detection Data processing Data models Real-time systems Time factors Edge computing

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign and Obstacle Detection for Autonomous Vehicle Navigation using Edge Computing

Traffic Sign and Obstacle Detection for Autonomous Vehicle N...

引用

International conference on Wireless Communications, Signal processing and Networking (WiSPNET)

作者： M. Vijayalakshmi M. Bharathwaj D. Anjelin Deva Dharshini Department of IST CEG Anna University Chennai India

ISBN: (数字)9798331524227

ISBN: (纸本)9798331524234

The advancement of autonomous vehicle technology necessitates robust systems for real-time traffic sign recognition and obstacle detection to ensure safe navigation. This paper proposes a comprehensive autonomous vehicle (AV) simulation framework utilizing the Carla simulator, advanced image processing, and state-of-the-art machine learning models to enhance autonomous navigation capabilities. The system initiates by loading a specified virtual map within the Carla simulator and deploying an ego vehicle equipped with a camera sensor to capture environmental images. These images undergo preprocessing techniques, to ensure suitability for analysis. Traffic sign recognition system uses a pre-trained YOLOv7 model, enabling the AV to identify and respond to various traffic signals amidst occlusion, adverse weather, and variations in placement and size. Concurrently, a pre-trained Faster R-CNN model detects obstacles such as vehicles and pedestrians along the vehicle’s path. A dedicated distance estimation module further analyzes these preprocessed images to calculate the relative distances of detected obstacles using depth estimation techniques, providing crucial spatial information. The decision-making algorithm resolves conflicts between recommended actions from traffic sign recognition and obstacle detection modules, prioritizing safety-critical commands to ensure operational safety and efficiency. The models are stored on the network edge, facilitating efficient deployment and real-time processing. This framework demonstrates an effective integration of simulation, image analysis, and decision-making, advancing the reliability and performance of autonomous navigation systems.

关键词： Navigation Heuristic algorithms Decision making Signal processing algorithms Cameras Real-time systems Road safety Classification algorithms Autonomous vehicles Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Comparative Review on Design and Development of Automation System for Grading of Onion

A Comparative Review on Design and Development of Automation...

引用

AIML-Applications for Engineering & Technology (ICAET), International conference on

作者： Rahul Suryawanshi Jayesh Jagtap Dnyaneshwari Shegokar Siddhesh Jaju Chandan M. N Avinash M. Badadhe Department of Automation and Robotics JSPM's Rajarshi Shahu College of Engineering Pune India

ISBN: (数字)9798350355611

ISBN: (纸本)9798350355628

Grading of onion is important for the purpose of quality as well as market value, and it has, in the past, used traditional methods. Onion grading has thus been automated, which has been a focus of numerous researchers because of the rising need for quality produce. Thus, the findings highlighted in this work show the progress and current approaches and methodologies designed for the design and implementation of automation systems for grading onions. This work outlines various methods such as image processing, gas sensor technology, Near Infra-Red (NIR) spectroscopy, X-ray imaging, Laser Doppler Vibrometry (LDV), and some artificial intelligence approaches that have been used in improving onion sorting systems. In addition, it reveals the drawbacks of these technologies, such as the realization of high image processing, the availability of small data sets, and the stability of the sortation systems. Based on the findings of this review, some recommendations for future research are suggested, such as the integration of multi-sensor systems and the enhancement of the efficiency of the automated onion grading systems using different types of algorithms.

关键词： Automation Reviews image processing X-ray lasers Laser stability Doppler effect Gas lasers Artificial intelligence X-ray imaging Sorting

来源：评论

学校读者我要写书评

暂无评论

An Accurate and Time-Efficient Subtractor by Cross Format Coding in Stochastic Computing

An Accurate and Time-Efficient Subtractor by Cross Format Co...

引用

IEEE Asia Pacific conference on Circuits and systems (APCCAS)

作者： Zhang, Zhihuai Zhang, Weiqian Xiong, Shisheng Zhao, Yudi Fudan Univ Sch Informat Sci & Technol Micronano Syst Ctr Shanghai Peoples R China Beijing Informat Sci & Technol Univ Minist Informat Ind Key Lab Informat & Commun Syst Beijing Peoples R China

ISBN: (纸本)9781665450737

Different from binary computation, stochastic computation (SC), as a new paradigm, uses stochastic bit stream (SBS) to encode data. By simplifying computing elements, the circuit area can be greatly reduced. SBS can be generated by a stochastic number generator (SNG) with a variety of formats. In this work, we use unipolar (UP) and bipolar (BP) formats to optimize the traditional SC subtractor, which is named the UP-to-BP Subtractor (UBS). A new cross format coding (CFC) method is proposed for stochastic computing, which combines the UP and BP format, and is applied to Sobel edge detection in image processing algorithms. The fault tolerance and detection efficacy of the proposed CFC method and conventional binary computing are compared in this paper. By using the CFC method, the detected F-Score is improved by 0.15(23%). If the F-score remains unchanged, the processing speed can be about 10 times faster.

关键词： stochastic computing stochastic subtractor image processing edge detection

来源：评论

学校读者我要写书评

暂无评论

Overview of image Detection algorithms: Performance Analysis and Technology Trends

Overview of Image Detection Algorithms: Performance Analysis...

引用

International conference on Informatics and Computing (ICIC)

作者： Nurul Hidayat R. Rizal Isnanto Department of Informatics Jenderal Soedirman University Purwokerto Indonesia Department of Computer Engineering Diponegoro University Semarang Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

image detection plays a vital role in digital image processing and artificial intelligence, with applications ranging from security surveillance to autonomous vehicles and medical image analysis. This study employs a qualitative approach to review the performance of image detection algorithms, focusing on deep learning methods such as YOLO, SSD, and CNN. Through computational experiments using quantitative data, this research provides performance comparisons based on accuracy, precision, recall, and computational efficiency. The results highlight YOLO’s superior performance in terms of both accuracy ($\mathbf{9 2} .5 \%$) and inference speed (75.2 fps), making it suitable for real-time applications. This study contributes by addressing the gap in balancing computational efficiency and adaptability for real-world applications.

关键词： YOLO Deep learning Machine learning algorithms Accuracy Computational modeling Real-time systems Inference algorithms Computational efficiency Detection algorithms Edge computing

来源：评论

学校读者我要写书评

暂无评论

Research on the Detection Algorithm of Rural Road Surface Damage Based on image processing 2nd

Research on the Detection Algorithm of Rural Road Surface Da...

引用

2nd International conference on image, Vision and Intelligent systems, ICIVIS 2022

作者： Ye, Pei Jiang, Tao Zhan, Hui Wuchang Institute of Technology HB WuHan China Wuhan University of Technology HB WuHan China

ISBN: (纸本)9789819909223

China's new rural construction project has developed rapidly. The rural landscape has changed a lot. The scale of the rural roads is getting larger and larger. The maintenance cost of rural road diseases is also very large. People use computer technology and artificial intelligence technology to improve the detection effect of road viruses in rural areas. This paper has collected a large number of pictures of rural road surface diseases. The types of disease include: heet damage, potholes, cracks and peeling. We use the SSD algorithm to process and identify these images. with some results, We have achieved some results, but the overall identification rate is not particularly high. To further improve the identification effect, we propose an improved SSD algorithm. We found that the improved SSD algorithm also had some results in the identification of rural road surface diseases. We compare the two algorithms, and we find that improving the SSD algorithm has more advantages. The improved SSD algorithm has a higher recognition rate and a faster recognition speed. We believe that this algorithm can provide a new idea for rural pavement disease identification. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Hardware Accelerator For Lossless Data Compression 5

An Efficient Hardware Accelerator For Lossless Data Compress...

引用

5th International conference on Communications, Signal processing, and their Applications (ICCSPA)

作者： Mahmoud, Adel Farid, Samuel Maged, Mark Mohamed, Othman Karam, Reham Salah, Khaled El-Kharashi, M. Watheq Ain Shams Univ Dept Comp & Syst Fac Engn Cairo Egypt Siemens Digital Ind Software Fremont CA 94538 USA

ISBN: (纸本)9781665482370

Data compression is a trending field that is used in data storage and data transmission systems. Lossy compression means that data cannot be completely retrieved while in lossless compression the compressed data must be reconstructed exactly. Lossless data compression is used in compressing binary files, telemetry data and high-fidelity medical and scientific images where details are crucial. There is no generic compression algorithm that gives best compression ratio on all data pattern. In this paper, we propose a hybrid lossless hardware architecture that compresses most of data patterns such as repeated data, Gaussian distribution data and images. A profiling-before-compressing and then choosing the right compression hardware is proposed. The proposed design is a highly parallelized architecture that can compress/decompress 64 bytes/cycle with minor overhead. Moreover, it provides high compression ratio on small block sizes as well as large ones.

关键词： Lossless Data Compression Lossless image Compression Hardware Accelerator Compression algorithms Rice-Golomb Predictive Coding XORing

来源：评论

学校读者我要写书评

暂无评论

Block-based Multi-scale Haze image Enhancement Method for Surveillance Application 6

Block-based Multi-scale Haze Image Enhancement Method for Su...

引用

conference on Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies VI

作者： Voronin, V. Zhdanova, M. Khamidullin, I Tokareva, O. Zelensky, A. Semenishchev, E. Moscow State Univ Technol STANKIN Ctr Cognit Technol & Machine Vis Moscow Russia

ISBN: (纸本)9781510655546

images captured in surveillance systems suffer from low contrast and faint color. Recently, plenty of dehazing algorithms have been proposed to enhance visibility and restore color. We present a new image enhancement algorithm based on multi-scale block-rooting processing. The basic idea is to apply the frequency domain image enhancement approach for different image block scales. The parameter of transform coefficient enhancement for every block is driven through optimization of measure of enhancement. The main idea is that enhancing the contrast of an image would create more high-frequency content in the enhanced image than the original image. To test the performance of the proposed algorithm, the public database O-HAZE is used.

关键词： dehazing surveillance image enhancement block-rooting frequency domain

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：