检索结果-内蒙古大学图书馆

4th International Academic Exchange Conference on science and technology Innovation, IAECST 2022

作者： Fan, Jihui Yuan, Fengshan St. Paul University Philippines Department of Graduate School Cagayan Tuguegarao Philippines Guangzhou Institute of Science and Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350320008

Research shows that in 2018, there are about 8.4 billion spam messages in China (360 Internet Security Center), which focuses on bank fraud, false online shopping on the Internet, telecommunications fraud, etc. China's current status of spam messages, the black interest chain of spam messages, the lack of legal protection, the increasingly changeable types of SMS, the continuous improvement of delivery methods, the changeable contents of spam messages and the various types of spam messages. Some bad organizations even collect spam messages through various channels Collect personal mobile phone information and sell mobile phone information to businesses and business personnel to obtain illegal benefits. At the same time, businesses seek benefits by sending spam short interest such as fraud and advertising, these methods endangers the information security and broke the daily life of the users. Based on the text content of SMS, this paper establishes a recognition model to accurately identify spam SMS, so as to solve the problem of spam SMS filtering. Using python programming, Gaussian naive Bayes is used to realize text classification, and a high classification accuracy is achieved. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

An Explainable Machine Learning-Based Phishing Website Detection using Gradient Boosting

An Explainable Machine Learning-Based Phishing Website Detec...

引用

2024 International Conference on Information technology Research and Innovation, ICITRI 2024

作者： Prayogo, Rizal Dwi Alfisyahrin, Alvin Rizqi Gambetta, Windy Karimah, Siti Amatullah Nambo, Hidetaka Kanazawa University Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa Japan Telkom University School of Computing Bandung Indonesia Kanazawa University Faculty of Transdisciplinary Sciences Institute of Philosophy in Interdisciplinary Sciences Kanazawa Japan Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350376210

As the need for achieving optimal performance in prediction models, several recent and complex models have been developed. However, many of these models operate as black boxes, providing little insight into their predictive results. In recent years, three gradient-boosting methods based on Decision Trees have been recommended, i.e., XGBoost, CatBoost, and LightGBM. These methods have proven to deliver competitive performance with fast training times. Nevertheless, in critical domains like security, there is a growing need for increased transparency among stakeholders. One pressing concern in the security field is the proliferation of phishing websites. To address this issue, we propose an explainable machine learning-based approach using gradient-boosting methods with hyperparameter optimization on three phishing website datasets. Our best methods surpass the state-of-the-art phishing website detection methods, achieving accuracy rates of 97.45%, 99.16%, and 97.85% for the UCI (2015), Mendeley (2018), and Mendeley (2020) datasets, respectively. Subsequently, we implement posthoc explainability using SHAP and LIME for the selected dataset. The experimental results indicate that three features, i.e., length_url, directory_length, and time_domain_activation, are consistently identified as the most influential features in the dataset. Moreover, our proposed approach demonstrates promising results for detecting phishing websites with both high accuracy and explainability. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Ancestral-Path Descendant-Labels Histogram Distance for Rooted Labeled Trees 16

Ancestral-Path Descendant-Labels Histogram Distance for Root...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Abe, Daisuke Hirata, Kouichi Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Kawazu 680-4 Iizuka820-8502 Japan Kyushu Institute of Technology Department of Artificial Intelligence Kawazu 680-4 Iizuka820-8502 Japan

ISBN: (纸本)9798350377903

In order to compare rooted labeled trees (trees, for short), in this paper, we introduce an ancestral-path descendant-labels (APDL, for short) histogram distance as the L1 distance between histograms of triples consisting of the path from the root to v, the label of v and the multiset of labels in the descendant of v for every vertex v. Then, we show that the APDL histogram distance can be computed in linear time with respect to the number of vertices in trees and it is a metric. Furthermore, we compare APDL histogram distance with the isolated-subtree distance for real data. © 2024 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Organic X-Ray Image Sensors Using a Medium Bandgap Polymer Donor with Low Dark Current

引用

Energy & Environmental Materials 2024年第6期7卷 230-237页

作者： Jong-Woon Ha Seung Hun Eom Bo Kyung Cha Seyeong Song Hyeong Ju Eun Jong H.Kim Jong Mok Park BongSoo Kim Byoungwook Park Seo-Jin Ko Sung Cheol Yoon Changjin Lee In Hwan Jung Do-Hoon Hwang Department of Chemistry Chemistry Institute for Functional MaterialsPusan National UniversityBusan 46241Korea Division of Advanced Energy Materials Research Center Korea Research Institute of Chemical Technology(KRICT)Daejeon 34114Korea Electro-Medical Device Research Center Korea Electrotechnology Research Institute(KERI)Ansan 15588Korea Graduate School of Carbon Neutrality School of Energy and Chemical EngineeringUlsan National Institute of Science and Technology(UNIST)Ulsan 44919Korea Department of Molecular Science and Technology Ajou UniversitySuwon 16449Korea Research Center for Advanced Specialty Chemicals Korea Research Institute of Chemical TechnologyUlsan 44412Korea Department of Chemistry Ulsan National Institute of Science and Technology(UNIST)Ulsan 44919Korea Department of Organic and Nano Engineering Human-Tech Convergence ProgramHanyang University222 Wangsimni-roSeongdong-guSeoul 04763Korea

The development of portable X-ray detectors is necessary for diagnosing fractures in unconscious patients in emergency ***,this is quite challenging because of the heavy weight of the scintillator and silicon *** weight and thickness of X-ray detectors can be reduced by replacing the silicon layer with an organic *** study presents a novel bithienopyrroledione-based polymer donor that exhibits excellent photodetection properties even in a thick photoactive layer(~700 nm),owing to the symmetric backbone and highly soluble molecular structure of *** ability of bithienopyrroledione-based polymer donor to strongly suppress the dark current density(Jd~10−10 A cm^(−2))at a negative bias(−2.0 V)while maintaining high responsivity(R=0.29 A W−1)even at a thickness of 700 nm results in a maximum shot-noise-limited specific detectivity of D_(sh)^(*)=2.18×10^(13)Jones in the organic *** organic photodetectors are developed by slot-die coating for use in X-ray detectors,which exhibit D_(sh)^(*)=2.73×10^(12)Jones with clear rising(0.26 s)and falling(0.29 s)response times upon X-ray *** reliability is also proven by linear response of the X-ray detector,and the X-ray detection limit is 3 mA.

关键词： low dark current low detection limit organic photodetector printable X-ray

来源：评论

学校读者我要写书评

暂无评论

The Effect of Viewpoint Change Strategies on Multi-View Video and Audio Transmission QoE Over ICN/CCN

The Effect of Viewpoint Change Strategies on Multi-View Vide...

引用

IEEE Region 10 International Conference TENCON

作者： Toshiro Nunome Yoshiyuki Takada Department of En-gineering Computer Science Program Graduate School of Engineering Nagoya Institute of Technology Nagoya Japan Department of Engineering Computer Science Program Graduate School of Engineering Nagoya Institute of Technol-ogy Nagoya Japan

In this paper, we exploit caches on intermediate nodes for QoE enhancement of multi-view video and audio transmission over ICN/CCN by controlling the content request start timing of consumers. We assume the selected single viewpoint transmission method; a consumer receives video and audio streams of a requested viewpoint. We perform a simple experiment with two consumers. When the consumers play video and audio with the time difference, we assess the effect of cached content by the former consumer's request on the output quality of the latter consumer. We deal with two types of viewpoint change strategies for the former consumer, which affect the efficiency of cache utilization. From the assessment results, we see that cache utilization has an important factor in enhancing QoE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learnable upsampling bilateral grid refinement for stereo matching network 4

Learnable upsampling bilateral grid refinement for stereo ma...

引用

4th International Conference on Advanced Algorithms and Neural Networks, AANN 2024

作者： Qiu, Wenfeng Ma, Chihao Li, Jianhua Qian, Ren Zhao, Yong College of Computer Science and Technology Guizhou University Guiyang550025 China School of Electronic and Computer Engineering Shenzhen Graduate School of Peking University Shenzhen518055 China College of Artificial Intelligence and Big data Luzhou Vocational and Technical College Sichuan Luzhou646000 China

ISBN: (纸本)9781510686106

Most existing binocular stereo matching algorithms require a trade-off between accuracy and speed, unable to achieve both simultaneously. One reason lies in the complexity and variability of scenes that stereo matching tasks must handle, where disparities in heavily textured, weakly textured, and occluded areas are often difficult to infer correctly. Therefore, this paper proposes the Learnable Upsampling Bilateral Grid Refinement for Stereo Matching Network (LUGNet). Through learnable bilateral grid upsampling guided by the left image, LUGNet calculates offsets for cost volume upsampling, while simultaneously leveraging the network to automatically learn interpolation weights to accommodate features of different datasets. Ultimately, LUGNet achieves error rates comparable to high-precision networks with a parameter count of 2.6M and an inference time of 58ms. © 2024 SPIE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Emotion Recognition in Facial Image Using Attentive Deep Convolutional Neural Network 2

Evaluation of Emotion Recognition in Facial Image Using Atte...

引用

2nd International Conference on Information technology Research and Innovation, ICITRI 2023

作者： Aini, Nur Pardede, Hilman Ferdinandus Graduate School of Computer Science Universitas Nusa Mandiri Faculty of Technology Information Depok Indonesia Research Center for AI and Cybersecurity National Research and Innovation Agency Indonesia

ISBN: (纸本)9798350324945

Emotion recognition in facial images is a topic that has attracted many interests. Research on emotion recognition in facial images continues to face challenges such as variations of human faces due to environments or situations. Of all the techniques that have been used, the Deep Convolution Neural Network (DCNN) method reports a significant improvement compared to traditional machine learning methods. In recent years, self-attachment mechanisms have increased in popularity in DCNN, especially in Natural Language Processing. In this study, we propose to add attention networks to DCNN method to improve the performance of emotion recognition. By incorporating self-attention mechanisms into the model architecture, the network is able to recognize which facial features are most relevant for each emotion, increasing the accuracy and interpretation of the model. This study reports an accuracy of 69.55% which is 11.15% higher than using the traditional DCNN model. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Numerical simulations on self-referential holographic data storage with built-in denoising function by self-referential holographic deep neural network

引用

Optical Review 2025年 1-12页

作者： Eto, Yuta Tomioka, Rio Takatsu, Taichi Takabayashi, Masanori Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Research Center for Neuromorphic AI Hardware Kyushu Institute of Technology Wakamatsu Japan

Self-referential holography (SRH), a holographic technique that enables the recording, reading, and control of two-dimensional (2D) patterns using a one-beam geometry, can be applied to holographic data storage (HDS) and optoelectronic deep neural network (OE-DNN). Since both applications are implemented using the same optical system, they can be integrated into a single system. We propose a self-referential HDS (SR-HDS) with a built-in denoising function using a self-referential holographic deep neural network (SR-HDNN), where the quality of reconstructed datapages in HDS can be enhanced using deep neural networks (DNNs) without requiring costly electronic computers for implementation. Numerical simulations are performed to demonstrate the feasibility of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mixed Deep Reinforcement Learning Considering Discrete-continuous Hybrid Action Space for Smart Home Energy Management

引用

Journal of Modern Power Systems and Clean Energy 2022年第3期10卷 743-754页

作者： Chao Huang Hongcai Zhang Long Wang Xiong Luo Yonghua Song IEEE State Key Laboratory of Internet of Things for Smart City University of MacaoMacao S.A.R.China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Shunde Graduate School University of Science and Technology BeijingFoshan 528399China State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering University of MacaoMacao S.A.R.China

This paper develops deep reinforcement learning(DRL)algorithms for optimizing the operation of home energy system which consists of photovoltaic(PV)panels,battery energy storage system,and household ***-free DRL algorithms can efficiently handle the difficulty of energy system modeling and uncertainty of PV ***,discretecontinuous hybrid action space of the considered home energy system challenges existing DRL algorithms for either discrete actions or continuous ***,a mixed deep reinforcement learning(MDRL)algorithm is proposed,which integrates deep Q-learning(DQL)algorithm and deep deterministic policy gradient(DDPG)*** DQL algorithm deals with discrete actions,while the DDPG algorithm handles continuous *** MDRL algorithm learns optimal strategy by trialand-error interactions with the ***,unsafe actions,which violate system constraints,can give rise to great *** handle such problem,a safe-MDRL algorithm is further *** studies demonstrate that the proposed MDRL algorithm can efficiently handle the challenge from discrete-continuous hybrid action space for home energy *** proposed MDRL algorithm reduces the operation cost while maintaining the human thermal comfort by comparing with benchmark algorithms on the test ***,the safe-MDRL algorithm greatly reduces the loss of thermal comfort in the learning stage by the proposed MDRL algorithm.

关键词： Demand response deep reinforcement learning discrete-continuous action space home energy management safe reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Deep Learning Approaches on Real-Time Data Analysis in Machine Learning

Analyzing the Impact of Deep Learning Approaches on Real-Tim...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Deepti Nalluri, Mounika Mupparaju, Chinna Babu Rongali, Aruna Sri Dhar, Sohong Ajitha, P. Sloan School of Management Mit United States Computer Information Systems Murray State University United States University of Central Missouri Computer Science warrensburg United States University of the Cumberlands Graduate Doctoral Information Technology Information Technology Emphasis/Information Technology United States Azure Microsoft United States Library & Information Science Jadavpur University India School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798350357769

Deep learning is a powerful subset of synthetic intelligence, and it has the potential to significantly enhance the skills of machine getting to know. it's miles primarily based on the idea of artificial neural networks, which might be laptop fashions that are capable of gaining knowledge of from records and making decisions, just like the manner a human mind works. Deep mastering isn't the same as traditional system mastering algorithms in that it can technique complex inputs with multiple layers of abstraction, main to greater accurate evaluation. Deep studying algorithms are capable of unexpectedly examine raw facts and generate styles, making them perfect for actual-time statistics analysis. Deep studying is capable of as it should be predicting behaviors and trends, which may be used to optimize procedures and enhance operational efficiencies. Deep studying models can also be used for automated fault detection and predictive renovation, permitting businesses to count on and prevent capacity troubles. Additionally, deep mastering models frequently offer quicker consequences than other device studying or conventional techniques, as well as permitting an extra diploma of control over the resolution of the data being analyzed. This has widespread implications for real-time programs, such as medical diagnostics, independent automobiles, and manufacturing monitoring. © 2023 IEEE.

关键词： Diagnosis

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：