检索结果-内蒙古大学图书馆

2nd Advanced Imaging and Information Processing Conference, AIIP 2024

作者： Jin, Nanxi Xin, Yuelan Deng, Shenghui Chen, Kuan Yang, Lan Huo, Haoyi Zhao, Jia Fang, Huiting Dept. of Physics and Electronic Information Engineering Qinghai Normal University 38 Wusi West Road. Qinghai Xining810001 China State Key Laboratory of Tibetan Language Information Processing and Applications Qinghai Normal University 38 Wusi West Road. Qinghai Xining810001 China Dept. of Computer Science Qinghai Normal University 38 Wusi West Road. Qinghai Xining810001 China

ISBN: (纸本)9781510683068

To enhance the accuracy of existing algorithms in the task of retinal vessel image segmentation, this paper proposes the incorporation of two modified convolutional blocks, in lieu of traditional ones, within the framework of the U-Net neural network, aiming to strengthen the extraction of detailed features. Firstly, a convolutional block equipped with local channel attention is devised for feature extraction in the shallow layers of the network. Secondly, a convolutional block incorporating global channel attention is introduced for feature extraction in the deeper layers. Lastly, skip connections are employed to feed the features extracted from the shallow layers into the deeper layers. Experimental results demonstrate that the proposed retinal vessel segmentation algorithm achieves a Dice coefficient of 88.21% and a sensitivity of 87.16%, marking improvements of 2.25% and 1.64% respectively over the original UNet network. © 2024 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Design and Implement Driveway Door Access Control by Using VLC and RFID Technology 12

Design and Implement Driveway Door Access Control by Using V...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Hung, Chi-Huang Fanjiang, Yong-Yi Li, Cheng-Yen Chiu, Sheng-Wei Hung, Tzu-Chieh Chiang, Meng-Huan Fu Jen Catholic University Lee-Ming Institute of Technology Graduate Institute of Applied Science and Engineering Dept. of Information Technology New Taipei City Taiwan Fu Jen Catholic University Graduate Institute of Applied Science and Engineering Dept. of Computer Science and Information Engineering New Taipei City Taiwan Fu Jen Catholic University Graduate Institute of Applied Science and Engineering New Taipei City Taiwan Lee-Ming Institute of Technology Dept. of Vehicle Engineering New Taipei City Taiwan Kang Chiao International School Dept. of International High School New Taipei City Taiwan

ISBN: (纸本)9798350340181

In recent years, the application of radiofrequency identification technology in smart access control systems has become a trend. Users only need to take out the RFID electronic key and approach the sensor of the gate to open the gate through signal induction. For housewives who always have a lot of bags and bags in their hands, there is no need to free up one hand to find the key to open the door and avoid being in a hurry. However, it is relatively inconvenient for drivers. Instead, it is much more convenient to use wireless controllers or license plate recognition. This study proposes a system that combines RFID with optical communication technology and vehicle headlights to open the garage door with a light code. © 2023 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

A Field Practical Approach to Memory Bandwidth Allocation for Consolidating Multi-Domain Automotive applications on a Single SoC

A Field Practical Approach to Memory Bandwidth Allocation fo...

引用

IEEE Symposium on Real-Time and Embedded Technology and applications

作者： Hayeon Park Jiwoong Lee Hoyong Lee Taekyoung Kwon Wan Choi Sangmi Moon Chang-Gun Lee Dept. of Computer Science and Engineering Seoul National University Republic of Korea Dept. of Electrical and Computer Engineering Seoul National University Republic of Korea Dept. of IT Artificial Intelligence Korea Nazarene University Republic of Korea

ISBN: (数字)9798331543402

ISBN: (纸本)9798331543419

Along with the advent of a high-end SoC with multiple CPU clusters and many GPUs, the automotive industry has a strong motivation to consolidate multi-domain applications on such a single SoC for wiring harness reduction and space/weight saving. For this, it is essential to bound their mutual interferences among CPU+GPU clusters on the system memory since advanced automotive applications use huge size code/data like autonomous driving and multi-screen infotainment. In order to guarantee memory bandwidth to each cluster, this paper proposes a cluster-level memory access regulation that aggregates the total memory access amount by each cluster (by all CPU cores and GPUs within the cluster) and throttles the cluster if it exceeds the given threshold. Then, we propose a few-shot measurement based optimal memory bandwidth allocation that can find a near optimal solution with only a few measurements, which is practically essential to save the system development cost. Our extensive experiments on a real SoC board say that our proposed techniques successfully regulate each cluster's memory bandwidth usage within ± 10 % margin of the allocated bandwidth. Also, our optimization can achieve a near-optimal utility with less than 0.6 % loss on average compared to the real optimal, with only a few measurements (mostly three measurements) instead of 25 measurements needed for the real optimal.

关键词： Wiring Costs Memory management Automotive applications Bandwidth Channel allocation Regulation Loss measurement Timing Optimization

来源：评论

学校读者我要写书评

暂无评论

Development of IoT-based Scale Sensor to Measure AWD System Water Level in Crop Field

Development of IoT-based Scale Sensor to Measure AWD System ...

引用

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Md Shahriar Kabir Khalid Mahmud Niloy Md Imon Hossen Sumaiya Afrose Md. Ismail Hossain Mofazzol Dept. of Electrical & Electronics Engineering American International University-Bangladesh Dept. of Computer Science Engineering Uttara University Dhaka Bangladesh

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

The paper introduces an innovative Internet of Things (IoT)-based scale sensor that measures the water level in the alternate wetting and drying (AWD) system and displays data in the mobile app to enable remote monitoring. The AWD system mainly consists of 30 cm of PVC pipe or bamboo with a diameter of 10-15 cm inserted into the paddy field, with a lower 20 cm buried in the soil and tiny holes at the bottom to allow field water to enter. The water level within the pipe indicates the field's water level, especially the underground water level. The AWD method optimizes water usage and reduces methane emissions by watering periodically and drying rice fields instead of maintaining continuous flooding. The current manual measurement process for water level needs to go to crop fields daily with a scale, which is difficult for continuous and remote monitoring. The developed scale sensor has IoT connectivity that removes the difficulties. The scale sensor works based on conductive rain sensors to precisely detect each centimeter rise or fall of water. The sensor consists of two open conductive layers that create a short circuit when the water level touches them by raising, triggering the microcontroller to register a voltage drop. The scale can measure up to 20 cm as it has 20 conductive layers, which fulfill the requirements. It has a 1 cm resolution, and in the test, it shows 95-99% accuracy. So, the sensor can effectively measure the water level in the AWD system, and further research is required to add an automatic irrigation system with the sensor so that the whole process can be controlled remotely.

关键词： Irrigation Accuracy Microcontrollers Crops Soil Robot sensing systems Mobile applications Timing Internet of Things Remote monitoring

来源：评论

学校读者我要写书评

暂无评论

PhishGuard: A Convolutional Neural Network-Based Model for Detecting Phishing URLs with Explainability Analysis

PhishGuard: A Convolutional Neural Network-Based Model for D...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Md Robiul Islam Md Mahamodul Islam Mst. Suraiya Afrin Anika Antara Nujhat Tabassum Al Amin Dept. of Computer Science and Engineering Uttara University Dhaka Bangladesh Dept. of Informatics University of Oslo Oslo Norway Dept. of Building Engineering and Construction Management Khulna University of Engineering and Technology (KUET) Khulna Bangladesh Dept. of Electrical and Electronics Engineering BRAC University Dhaka Bangladesh Dept. of Electrical and Computer Engineering North South University Dhaka Bangladesh Dept. of Computer Science American International University Bangladesh (AIUB) Dhaka Bangladesh

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Abstract-Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models’ decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a $1 D$ Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85 %. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL.

关键词： Uniform resource locators Deep learning Analytical models Accuracy Phishing Organizations Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Defense: A Hybrid LSTM-ANN Architecture for Intelligent Intrusion Detection System

Deep Defense: A Hybrid LSTM-ANN Architecture for Intelligent...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Mohit Shadeja Shashwat Singh Ayushi Prakash Dept. of Computer Science and Engineering Ajay Kumar Garg Engineering College Ghaziabad Uttar Pradesh India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

The rapidly evolving cyber threat landscape requires innovative and adaptive intrusion detection solutions. Traditional signature-based intrusion detection systems, despite their high accuracy, are inherently inflexible and susceptible to evasion tactics, making them ineffective against novel and sophisticated attacks. In contrast, machine learning-powered anomaly-based intrusion detection systems demonstrate improved detection capabilities, but their advantages are often outweighed by substantial drawbacks, including significant computational resource requirements when the dataset and its features for behavior analysis increase. Also, there are high power consumption and latency issues in communication that compromise network performance. This study proposes a hybrid ANN-LSTM approach for performing deep packet inspection and efficiently detecting malicious network packets. By analyzing binary container data, our model reduces time and space complexity, thereby mitigating the computational resources and power consumption challenges but also increasing the efficiency of intrusion detection by 3%, making it more intelligent than various established IDS.

关键词： Power demand Computational modeling Intrusion detection Machine learning computer architecture Inspection Containers Feature extraction Data models Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning to Improve the Accuracy of Soil Nutrient Classification 2

Application of Deep Learning to Improve the Accuracy of Soil...

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Rathore, Manpreet Nath Singh, Paras CMR Institute of Technology Dept. of Computer Science and Engineering Bengaluru560037 India CMR Institute of Technology Dept. of Cse Bengaluru560037 India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

Soil characteristics are required to calculate of computer soil nutrients for specific crops productivity. Soil testing is necessary for determining the soil's nutritional level determining the treatment of the soil for its fertilities and crop requirements. Soil test reports are used to classify the significant soil features by indices of Phosphorus, Potassium, Organic carbon, and Boron for parameter soil reaction (pH). Improved accuracy in prediction of the soil parameter will aid to reduce expenditure on fertilizers will increase farmer's profit. Machine learning comes under AI (Artificial Intelligence), and a superset of Deep Learning. Deep Learning mostly uses CNN (Convolutional Neural Network) which is an extended and inspired architecture to make classification and predictions with more percentage of accuracy. In this paper accuracy of classification for soil nutrients are analyzed and improved using deep learning methods such as CNN, which gives better accuracy results. Image classification can be done using regression and SVM (support Vector Machine) also but CNN from Deep Learning model is more effective in learning patterns in 3-dimensional data of colour images and by automatic feature learning capability in the proposed CNN model. Images of soils are used to train a classifier to identify common soil types and fractions of soil type. OpenCV and TensorFlow tools of Python are used for image processing, testing and training soil image data. Using these tools images of 3 soils (gravel, sand and silt) of Karnataka region of India have been taken for training and testing model and classification accuracy is improved. © 2022 IEEE.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Information Flow in Multimodal Large Language Models

arXiv

引用

arXiv 2024年

作者： Zhang, Zhi Yadav, Srishti Han, Fengze Shutova, Ekaterina ILLC University of Amsterdam Netherlands Dept. of Computer Science University of Copenhagen Denmark Dept. of Computer Engineering Technical University of Munich Germany

The recent advancements in auto-regressive multimodal large language models (MLLMs) have demonstrated promising progress for vision-language tasks. While there exists a variety of studies investigating the processing of linguistic information within large language models, little is currently known about the inner working mechanism of MLLMs and how linguistic and visual information interact within these models. In this study, we aim to fill this gap by examining the information flow between different modalities—language and vision—in MLLMs, focusing on visual question answering. Specifically, given an image-question pair as input, we investigate where in the model and how the visual and linguistic information are combined to generate the final prediction. Conducting experiments with a series of models from the LLaVA series, we find that there are two distinct stages in the process of integration of the two modalities. In the lower layers, the model first transfers the more general visual features of the whole image into the representations of (linguistic) question tokens. In the middle layers, it once again transfers visual information about specific objects relevant to the question to the respective token positions of the question. Finally, in the higher layers, the resulting multimodal representation is propagated to the last position of the input sequence for the final prediction. Overall, our findings provide a new and comprehensive perspective on the spatial and functional aspects of image and language processing in the MLLMs, thereby facilitating future research into multimodal information localization and editing. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Forecasting Using Machine Learning with Temporal Fusion Transformer and Graph Neural Networks

Air Pollution Forecasting Using Machine Learning with Tempor...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Subhashree Rath Maneesha P dept. of Computer Science and Engineering New Horizon College Of Engineering Autonomous College Affiliated to VTU Bengaluru

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Air pollution is a significant obstacle to achieving urban sustainability and public health, particularly in rapidly developing regions. Accurate air quality prediction is essential for proactive pollution management and policy formulation. In this study, we employ sophisticated machine learning frameworks, such as Temporal Fusion Transformer (TFT) and Graph Neural Networks (GNNs), to predict air quality levels. TFT is designed to capture temporal dependencies, making it ideal for time-series forecasting, while GNNs model spatial relationships, enabling the analysis of pollutant dispersion across monitoring stations. A synthetic dataset comprising 50 rows was generated, simulating pollutant concentrations (PM2.5, PM10, CO, NO2, SO2) and meteorological variables (temperature, humidity, wind speed). The models were assessed using criteria like $R^{2}$ , RMSE, and MAE. TFT achieved an $R^{2}$ of 0.97 and an RMSE of $4.2 \mu ~\mathrm{g} / \mathrm{m}^3$ , significantly outperforming traditional models like Random Forest and XGBoost. GNN provided spatial insights, identifying pollutant hotspots and their dispersion patterns. This research highlights the superior accuracy and scalability of TFT and GNN for air quality prediction. The results underline their potential for real-time monitoring, smart city integration, and proactive environmental management, offering a robust solution for addressing urban air pollution challenges.

关键词： Accuracy Atmospheric modeling Predictive models Transformers Air pollution Graph neural networks Real-time systems Thin film transistors Forecasting Dispersion

来源：评论

学校读者我要写书评

暂无评论

Real-World Atmospheric Turbulence Correction Via Domain Adaptation

Real-World Atmospheric Turbulence Correction Via Domain Adap...

引用

IEEE International Conference on Image Processing

作者： Xijun Wang Santiago López-Tapia Aggelos K. Katsaggelos Dept. of Computer Science Northwestern University Evanston IL USA Dept. of Electrical and Computer Engineering Northwestern University Evanston IL USA

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth’s surface. This phenomenon results in distorted and blurred acquired images or videos and can significantly impact downstream vision tasks, particularly those that rely on capturing clear, stable images or videos from outdoor environments, such as accurately detecting or recognizing objects. Therefore, people have proposed ways to simulate atmospheric turbulence and designed effective deep learning-based methods to remove the atmospheric turbulence effect. However, these synthesized turbulent images can not cover all the range of real-world turbulence effects. Though the models have achieved great performance for synthetic scenarios, there always exists a performance drop when applied to real-world cases. Moreover, reducing real-world turbulence is a more challenging task as there are no clean ground truth counter-parts provided to the models during training. In this paper, we propose a real-world atmospheric turbulence mitigation model under a domain adaptation framework, which links the supervised simulated atmospheric turbulence correction with the unsupervised real-world atmospheric turbulence correction. We will show our proposed method enhances performance in real-world atmospheric turbulence scenarios, improving both image quality and downstream vision tasks.

关键词： Image quality Training Learning systems Adaptation models Atmospheric modeling Prevention and mitigation Image restoration

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：