检索结果-内蒙古大学图书馆

Classification Model for IDS Using Auto Cryptographic Denoising Technique

computer Systems science & engineering 2023年第4期45卷 671-685页

作者： N.Karthikeyan P.Sivaprakash S.Karthik Department of Computer Science&Engineering PPG Institute of TechnologyCoimbatoreTamilnaduIndia Department of Computer Science&Engineering SNS College of TechnologyCoimbatoreTamilnaduIndia

Intrusion detection systems(IDS)are one of the most promising ways for securing data and networks;In recent decades,IDS has used a variety of categorization *** classifiers,on the other hand,do not work effectively unless they are combined with additional algorithms that can alter the classifier’s parameters or select the optimal sub-set of features for the *** are used in tandem with classifiers to increase the stability and with efficiency of the classifiers in detecting *** algorithms,on the other hand,have a number of limitations,particularly when used to detect new types of *** this paper,the NSL KDD dataset and KDD Cup 99 is used to find the performance of the proposed classifier model and compared;These two IDS dataset is preprocessed,then Auto Cryptographic Denoising(ACD)adopted to remove noise in the feature of the IDS dataset;the classifier algorithms,K-Means and Neural network classifies the dataset with adam *** classifier is evaluated by measuring performance measures like f-measure,recall,precision,detection rate and *** neural network obtained the highest classifying accuracy as 91.12%with drop-out function that shows the efficiency of the classifier model with drop-out function for KDD Cup99 *** their power and limitations in the proposed methodology that could be used in future works in the IDS area.

关键词： Auto cryptographic denoising(ACD) classifier intrusion detection system(IDS) optimizer performance measures

来源：评论

学校读者我要写书评

暂无评论

SEOE:an option graph based semantically embedding method for prenatal depression detection

引用

Frontiers of computer science 2024年第6期18卷 245-258页

作者： Xiaosong HAN Mengchen CAO Dong XU Xiaoyue FENG Yanchun LIANG Xiaoduo LANG Renchu GUAN College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun 130012China Department of Electrical Engineering and Computer Science and Christopher S.Bond Life Sciences Center University of MissouriColumbiaMO 65211USA Department of Computer Science and Technology Zhuhai Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationZhuhai College of Science and TechnologyZhuhai 519041China Jilin Provincial Institute of Population Science and Technology Changchun 130000China

Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing ***,it is essential to detect prenatal depression early and conduct an attribution *** studies have used questionnaires to screen for prenatal depression,but the existing methods lack *** diagnose the early signs of prenatal depression and identify the key factors that may lead to prenatal depression from questionnaires,we present the semantically enhanced option embedding(SEOE)model to represent questionnaire *** can quantitatively determine the relationship and patterns between options and *** first quantifies options and resorts them,gathering options with little difference,since Word2Vec is highly dependent on *** resort task is transformed into an optimization problem involving the traveling salesman ***,all questionnaire samples are used to train the options’vector using ***,an LSTM and GRU fused model incorporating the cycle learning rate is constructed to detect whether a pregnant woman is suffering from *** verify the model,we compare it with other deep learning and traditional machine learning *** experiment results show that our proposed model can accurately identify pregnant women with depression and reach an F1 score of *** most relevant factors of depression found by SEOE are also verified in the *** addition,our model is of low computational complexity and strong generalization,which can be widely applied to other questionnaire analyses of psychiatric disorders.

关键词： questionnaire analyses text classification graph representation learning traveling salesman problem prenatal depression

来源：评论

学校读者我要写书评

暂无评论

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection 39

View Transformation Robustness for Multi-View 3D Object Reco...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Qi Luo, Zhouhang Yu, Tao Huang, Hui College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen China

ISBN: (纸本)157735897X

View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods' stability under inputs with various view transformations. However, existing research seldom focuses on view transformation robustness in multi-view 3D object reconstruction. One direct way to improve the models' VTR is to produce data with more view transformations and add them to model training. Recent progress on large vision models, particularly Stable Diffusion models, has provided great potential for generating 3D models or synthesizing novel view images with only a single image input. To fully utilize the power of Stable Diffusion models without causing extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness. Instead of synthesizing random views, we propose a reconstruction error-guided view selection method, which considers the reconstruction errors' spatial distribution of the 3D predictions and chooses the views that could cover the reconstruction errors as much as possible. The methods are trained and tested on sets with large view transformations to validate the 3D reconstruction models' robustness to view transformations. Extensive experiments demonstrate that the proposed method can outperform state-of-the-art 3D reconstruction methods and other view transformation robustness comparison methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Edge Artificial Intelligence for Real-Time Decision Making using NVIDIA Jetson Orin, Google Coral Edge TPU and 6G for Privacy and Scalability

Edge Artificial Intelligence for Real-Time Decision Making u...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Anchitaalagammai, J.V. Kavitha, S. Buurvidha, R. Santhiya, T.S. Roopa, M. Devi Sankari, S. Sri Computer Science and Engineering Velammal College of Engineering and Technology Madurai India

ISBN: (纸本)9798331521394

Edge AI or Edge Artificial Intelligence is the provision of AI within edge devices itself without needing a connection to the cloud. AI gets better with more information and time, and so a lot of AI models 'live in the cloud.' However, AI made Edge devices is more smarter by deploying models onboard. There are several factors like NVIDIA's Jetson Orin, Google's Coral Edge TPU, and Qualcomm's AI optimized Snapdragon platforms, which has accelerated the adoption of Edge AI and made these onboard Edge devices with modests resources, robust processing capabilities. Experts anticipate that the advent of 6G technology will further expand speeds, making it possible to utilize augmented (AR) and virtual (VR) reality as well as the Internet of Things (IoT). Privacy of the end user is still safeguarded through federated and differential learning which enables intelligent distribution while data is kept close to the source. The concept of optimization techniques such as quantization, pruning, and NAS are resources that help in considerations for deploying AI models at the Edge as highlighted in the literature. Containerization and microservices also provide a great ecosystem for Edge AI deployments supported by Docker, Kubernetes and KubeEdge which provide scalable infrastructure. Evaluations conducted on various use cases rangingfrom predictive maintenance of industrial IoT[l], real- time health monitoring as well as autonomous systems, show the performance of these models to improve in terms of model accuracy, inference computation as well as energy efficiency through the enhanced methodologies. The recent advancements in hardware and software capabilities have placed Edge AI as a preferred option for many applications that have strict latency requirements in addition to needing to make real time decisions. Edge AI is set to revolutionize industries likehealth care, smart cities, industrial automation despite hitches like data unification and barrier from privacylaws. Furthe

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Navigating the Future:Lane Line Detection for Autonomous and Non-Autonmous Vehicles

Navigating the Future:Lane Line Detection for Autonomous and...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Kamali Kanmani, K. Vanitha, S. Rajeswari, A.M. Velammal College of Engineering and Technology Computer Science and Engineering Madurai India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521394

The lane line detection helps in reducing the accidents. Current systems, integrated into advanced driver assistance systems (ADAS), often fail to provide accurate detection under challenging conditions such as poor weather, low visibility, and dynamic road environments, leading to inconsistent performance and delayed corrective actions. The proposed lane line detection system addresses key issues in road safety, particularly the challenge of maintaining lane adherence for both autonomous and non-autonomous vehicles. Many existing systems also lack effective real-time feedback mechanisms, particularly for non-autonomous vehicles, reducing driver situational awareness and increasing accident risks. To overcome these limitations, our solution integrates infrared (IR) sensors, a micro controller, and an LCD display to continuously monitor lane lines and detect nearby obstacles, ensuring timely corrective actions in case of lane deviations. The system operates efficiently across various environments, including extreme weather, and offers real-time communication capabilities for road condition updates. Designed for high-speed processing, it enhances both vehicle and driver safety by improving lane detection accuracy, promoting smarter navigation, and reducing the likelihood of accidents, ultimately contributing to the advancement of smart transportation systems. © 2025 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning for Deep Neural Networks Based Optimization Algorithm

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 2559-2573页

作者： D.Vidyabharathi V.Mohanraj Sona College of Technology Computer Science and EngineeringSalem636005India Sona College of Technology Information TechnologySalem636005India

For training the present Neural Network(NN)models,the standard technique is to utilize decaying Learning Rates(LR).While the majority of these techniques commence with a large LR,they will decay multiple times over *** has been proved to enhance generalization as well as *** parameters,such as the network’s size,the number of hidden layers,drop-outs to avoid overfitting,batch size,and so on,are solely based on *** work has proposed Adaptive Teaching Learning Based(ATLB)Heuristic to identify the optimal hyperparameters for diverse *** we consider three architec-tures Recurrent Neural Networks(RNN),Long Short Term Memory(LSTM),Bidirectional Long Short Term Memory(BiLSTM)of Deep Neural Networks for *** evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate(CLR),Hyperbolic Tangent Decay(HTD),and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts(T-HTR)*** results have shown the performance improvement on the 20Newsgroup,Reuters Newswire and IMDB dataset.

关键词： Deep learning deep neural network(DNN) learning rates(LR) recurrent neural network(RNN) cyclical learning rate(CLR) hyperbolic tangent decay(HTD) toggle between hyperbolic tangent decay and triangular mode with restarts(T-HTR) teaching learning based optimization(TLBO)

来源：评论

学校读者我要写书评

暂无评论

LogCSS: Log anomaly detection based on BERT-CNN with context-semantics-statistics features

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 7659-7676页

作者： Li, Zhongliang Tu, Xuezhen Gao, Hong Huang, Shiyue Ma, Zongmin College of Computer Science & Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Computer Science Peking University Beijing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

With the development of artificial intelligence, deep-learning-based log anomaly detection proves to be an important research topic. In this paper, we propose LogCSS, a novel log anomaly detection framework based on the Context-Semantics-Statistics Convolutional Neural Network (CSSCNN). It is the first model that uses BERT (Bidirectional Encoder Representation from Transformers) and CNN (Convolutional Neural Network) to extract the semantic, temporal, and correlational features of the logs. We combine the features with the statistic information of log templates for the classification model to improve the accuracy. We also propose a technique, DOOT (Deals with the Out-Of-Templates), for online template matching. The experimental research shows that our framework improves the average F1 score of the six best algorithms in the industry by more than 5% on the open-source dataset HDFS, and improves the average F1 score of the six best algorithms in the industry by more than 8% on the BGL dataset, LogCSS also performs better than other similar methods on our own constructed dataset. © 2024 – IOS Press.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

VisionAid Smart Cane: A Guardian in Mobility for the Visually Impaired

VisionAid Smart Cane: A Guardian in Mobility for the Visuall...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Sarala, R. Shobika, R.J. Keerthiga, J.S. Velammal College of Engineering and Technology Computer Science and Engineering Madurai India

ISBN: (纸本)9798331521394

The Smart Cane helps to overcome the mobility-related problem faced by visually impaired people, with an innovative approach that will help in improving safety, independence, and accessibility. Traditional canes lack modern functionalities, making them inefficient in operating complicated scenarios. The proposed Smart Cane packs advanced sensors: IR sensor for obstacle detection, ADLX sensor for surface irregularities, GPS for navigating around places in real time with vocal directions. The device hosts audio and vibration alerts to improve situational awareness in noisy or crowded areas, Bluetooth connectivity to pair the device with a smartphone and allow location tracking, emergency alerts, and usage logs, and is equipped with AI-driven features such as environment recognition, fall detection, heart rate and SpO2 health monitoring. The device employs a BeagleBone Black Rev C3 for real-time processing. The device also charges through a solar cell, has multi-language capabilities, and customized user profiles. This solution is designed in order to transform assistive technology and empower users with greater mobility and confidence in a variety of different scenarios. © 2025 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Intent and URL based ML Classification for Phishing Detection

Intent and URL based ML Classification for Phishing Detectio...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Uloli, Thiruvaazhi Sadasivam, Sudha Kumaraguru College of Technology Department of Computer Science & Engineering Coimbatore India PSG College of Technology Department of Computer Science & Engineering Coimbatore India

ISBN: (纸本)9798350378177

Reports show that the number of phishing web sites is exponentially increasing and it is estimated that between 80% to 93 % of the data breaches are involving phishing attacks. With both probability of occurrence as well as impact high, it is a high risk calling for an effective solution. Linear approaches like multi-factor authentication currently practiced addressing an exponentially growing problem is inadequate. In this work, we present a solution using domain-based understanding of the attacker intent based on the attributes of information that the attacker ultimately seeks to know from the user and make it more effective by combining it with machine learning based solutions of phishing detection based on URL features. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional information-driven many-objective software remodularization approach

引用

Frontiers of computer science 2023年第3期17卷 45-62页

作者： Amarjeet PRAJAPATI Anshu PARASHAR Amit RATHEE Department of Computer Science Engineering&Information Technology Jaypee Istitute of Information TechnologyNoida 201307India Department of Computer Science&Engineering Thapar Institute of Engineering&TechnologyPunjab 147004India Department of Computer Science Government College BarotaHaryana 131301India

Most of the search-based software remodularization(SBSR)approaches designed to address the software remodularization problem(SRP)areutilizing only structural information-based coupling and cohesion quality ***,in practice apart from these quality criteria,there require other aspects of coupling and cohesion quality criteria such as lexical and changed-history in designing the modules of the software ***,consideration of limited aspects of software information in the SBSR may generate a sub-optimal modularization ***,such modularization can be good from the quality metrics perspective but may not be acceptable to the *** produce a remodularization solution acceptable from both quality metrics and developers’perspectives,this paper exploited more dimensions of software information to define the quality criteria as modularization ***,these objectives are simultaneously optimized using a tailored manyobjective artificial bee colony(MaABC)to produce a remodularization *** assess the effectiveness of the proposed approach,we applied it over five software *** obtained remodularization solutions are evaluated with the software quality metrics and developers view of *** demonstrate that the proposed software remodularization is an effective approach for generating good quality modularization solutions.

关键词： software restructuring remodularization multiobjective optimization software coupling and cohesion

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：