检索结果-内蒙古大学图书馆

Detecting Android Malware with Convolutional Neural Networks and Hilbert Space-Filling Curves

SN computer science 2024年第7期5卷 810页

作者： Mbungang, Benedict Ngaibe Ali Wacka, Joan Beri Tchakounte, Franklin Polatidis, Nikolaos Nlong II, Jean Michel Tieudjo, Daniel Department of Mathematics and Computer Science University of Ngaoundere Ngaoundere Cameroon Cybersecurity with Computational and Artificial Intelligence Research Group University of Ngaoundere Ngaoundere Cameroon Department of Computer Science University of Buea Buea Cameroon School of Architecture Technology and Engineering University of Brighton Brighton United Kingdom

computer vision techniques have advanced greatly in recent years through deep learning, achieving unprecedented performance. This has motivated applying deep learning to malware detection through image-based approaches to circumvent extensive feature engineering for diverse threats. However, existing work converting Android binaries to rectangular images neglects the intrinsic byte sequence structure, introducing spurious spatial relationships that weaken detection accuracy. To address this, space-filling curves have mapped binaries to images while preserving ordering. This paper proposes a novel method using Hilbert space-filling curves to visualize and classify Android apps. Bytecode is extracted from Dalvik Executable (DEX) files and transformed to grayscale images via Hilbert coding for model training. Additionally, a novel and balanced image dataset is proposed consisting of Hilbert transformations for 4995 benign and 4995 malicious Android apps randomly sampled from the AndroZoo repository. Experiments using this dataset evaluated pre-trained InceptionV3, VGG16, ResNet50 and EfficientNetB0 via transfer learning. A custom Convolutional Neural Network (CNN) was also trained from scratch. InceptionV3 achieved the highest performance at 97.99% accuracy, 98.50% precision, 97.50% recall and 97.99% F1-score. Comparative assessment with previous image-based malware detection research indicates our approach outperforms state-of-the-art approaches. By leveraging Hilbert space-filling curves to map binaries to images while preserving sequential relationships, detection accuracy is improved over methods introducing extraneous spatial representations. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Android Hilbert space-filling curve Image Malware detection

来源：评论

学校读者我要写书评

暂无评论

Symmetric Matrix Completion with ReLU Sampling 41

Symmetric Matrix Completion with ReLU Sampling

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Huikang Wang, Peng Huang, Longxiu Qu, Qing Balzano, Laura Antai College of Economics and Management Shanghai Jiao Tong University China Department of Electrical Engineering and Computer Science University of Michigan United States Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University United States

We study the problem of symmetric positive semidefinite low-rank matrix completion (MC) with deterministic entry-dependent sampling. In particular, we consider rectified linear unit (ReLU) sampling, where only positive entries are observed, as well as a generalization to threshold-based sampling. We first empirically demonstrate that the landscape of this MC problem is not globally benign: Gradient descent (GD) with random initialization will generally converge to stationary points that are not globally optimal. Nevertheless, we prove that when the matrix factor with a small rank satisfies mild assumptions, the nonconvex objective function is geodesically strongly convex on the quotient manifold in a neighborhood of a planted low-rank matrix. Moreover, we show that our assumptions are satisfied by a matrix factor with i.i.d. Gaussian entries. Finally, we develop a tailor-designed initialization for GD to solve our studied formulation, which empirically always achieves convergence to the global minima. We also conduct extensive experiments and compare MC methods, investigating convergence and completion performance with respect to initialization, noise level, dimension, and rank. © 2024 Proceedings of Machine Learning Research. All rights reserved.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Methodical Tamil Character Recognition Using Fabricated CNN Model

Methodical Tamil Character Recognition Using Fabricated CNN ...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Bhavani, M. Ravikumar, S. Prithi, S. Arockia Raj, Y. Rajendiran, Babu Rajalakshmi Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India School of Computing Department of Computational Intelligence SRM Institute of Science and Technology Chennai India PSNA College of Engineering and Technology Department of Computer Science and Engineering Dindigul India

ISBN: (纸本)9798350348217

Recognizing text is one of the most challenging problems in computer vision. To put it simply, handwritten character recognition is the process of recognising text in photographs, papers, and other media and converting it into a form that a computer can read. You can solve this issue by employing the image classification method. We will be able to recognise the user's typed Tamil characters in this paper. We designed a brand new model, MVGG16, to handle character recognition and classification. Its basic structure is analogous to that of VGG16, but we added a few more layers to improve accuracy. So far, 156 Tamil characters have been learnt, with 350 images each class. In experimental settings, this model achieves an accuracy of 91.8%. As an input method, this work makes use of a whiteboard where the user can scribble the Tamil character to be recognised. The character will be sent for verification after the user has written it and the image has been exported. Once the model identifies the character, it will show it to the user. © 2023 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Optimized Load Balancing Technique for Software Defined Network

引用

computers, Materials & Continua 2022年第7期72卷 1409-1426页

作者： Aashish Kumar Darpan Anand Sudan Jha Gyanendra Prasad Joshi Woong Cho Department of Computer Science and Engineering Chandigarh UniversityMohaliPunjab140413India School of Computational Sciences CHRIST(Deemed to be University)Ghaziabad201003India Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Automotive ICT Convergence Engineering Daegu Catholic UniversityGyeongsan38430Korea

Software-defined networking is one of the progressive and prominent innovations in Information and Communications *** mitigates the issues that our conventional network was ***,traffic data generated by various applications is increasing day by *** addition,as an organization’s digital transformation is accelerated,the amount of information to be processed inside the organization has increased *** might be possible that a Software-Defined Network becomes a bottleneck and *** models have been proposed in the literature to balance the ***,most of the works consider only limited parameters and do not consider controller and transmission media *** loads also contribute to decreasing the performance of Software-Defined *** work illustrates how a software-defined network can tackle the load at its software layer and give excellent results to distribute the *** proposed a deep learning-dependent convolutional neural networkbased load balancing technique to handle a software-defined network *** simulation results show that the proposed model requires fewer resources as compared to existing machine learning-based load balancing techniques.

关键词： SDN software-defined networks load balancing performance enhancement

来源：评论

学校读者我要写书评

暂无评论

Butterfly Optimized Feature Selection with Fuzzy C-Means Classifier for Thyroid Prediction

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 2909-2924页

作者： S.J.K.Jagadeesh Kumar P.Parthasarathi Mehedi Masud Jehad F.Al-Amri Mohamed Abouhawwash Department of Computer Science and Engineering Kathir College of EngineeringCoimbatore641062India Department of Computer science and Engineering Bannari Amman Institute of TechnologySathyamangalam638401TamilnaduIndia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.BOX 11099Taif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura 35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

The main task of thyroid hormones is controlling the metabolism rate of humans,the development of neurons,and the signiﬁcant growth of reproductive *** medical science,thyroid disorder will lead to creating thyroiditis and thyroid *** two main thyroid disorders are hyperthyroidism and *** research works focus on the prediction of thyroid *** improve the accuracy in the classiﬁcation of thyroid disorder this paper pro-poses optimization-based feature selection by using differential evolution with the Butterﬂy optimization algorithm(DE-BOA).For the classiﬁer fuzzy C-means algorithm(FCM)is *** proposed DEBOA-FCM is evaluated with para-metric metric measures of sensitivity,speciﬁcity,and *** this work,the thyroid disease dataset collected from the machine learning University of Cali-fornia Irvine(UCI)database was *** accuracy rate for the Differential Evo-lutionary algorithm got 0.884,the Butterﬂy optimization algorithm got 0.906,Fuzzy C-Means algorithm got 0.899 and DEBOA+Focused Concept Miner(FCM)proposed work 0.943.

关键词： Fuzzy butterﬂy differential evolution thyroid hyperthyroid

来源：评论

学校读者我要写书评

暂无评论

Dynamic Bidirectional Translation for Sign Language by Using Machine Learning-Infused Approach with Integrated computer Vision 2

Dynamic Bidirectional Translation for Sign Language by Using...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Jain, Somya Diwakar, Shikha Yadav, Neha G.L. Bajaj Institute of Technology and Management Engineering/ Computer Science Artificial Intelligence Department of Applied Computational Science India School of Information & Communication Technology Gautam Buddha University Engineering/Artificial Intelligence India G.L. Bajaj Institute of Technology and Management Department of Applied Computational Science India

ISBN: (纸本)9798350371055

This research aims to break communication barriers for the deaf and hard-of-hearing by pioneering a real-time, dynamic sign language translator. Unlike existing apps, it uses a CNN to translate simultaneously between English and American Sign Language (ASL). It features an animated avatar for interactive communication, and goes beyond translation with chat, video calls, and precise hand motion capture. This innovative approach paves the way for inclusive and secure communication within the deaf community. © 2024 IEEE.

关键词： ASL avatar CNN communication barriers deaf inclusive real-time Sign language translation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Healthcare Accessibility and Effectiveness through the Implementation of AI Solutions for Remote Patient Monitoring 3

Optimizing Healthcare Accessibility and Effectiveness throug...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Singh, Jagendra Sahu, Dinesh Prasad Kumar, Ashwini Ahmad, Salman Khursheed Majumder, Jayeeta Gangopadhyay, Sourav Bennett University School of Computer Science Engineering & Technology Greater Noida India Camellia Institute of Technology & Management Department of Computer Science & Engineering Jaipur India Gl Bajaj Institute of Technology & Management Dept. of Applied Computational Science and Engineering Greater Noida India Brainware University Department of Hospital Management Kolkata India

ISBN: (纸本)9798350384598

This study investigates the optimization of healthcare accessibility and effectiveness by integrating artificial intelligence (AI) solutions within Internet of Things (IoT) systems for remote patient monitoring. Embracing a holistic approach, we deploy medical sensors, including temperature, pressure, heart rate, and oxygen sensors, to collect patients' continuous health metrics (vital signs). These sensed data are then transmitted to an Arduino controller, responsible for managing data communication with the cloud infrastructure using a Wi-Fi module that facilitates data storage and analysis. Stored data are accessed by authorized healthcare professionals, who exploit machine learning models, including Artificial Neural Networks (ANN), Logistic Regression (LR) and Decision Tree (DT), to forecast patients' health outcome in advance using the sensed data. A rigorous evaluation demonstrated the IoT system's effectiveness, based on testing with sensed data from ten patients over a month, where 70% of the data were used for training the models, and the rest for testing. The proposed IoT system demonstrates the success;ANN exhibited the highest accuracy at 97.88%, followed by LR at 93.43%, and DT at 91.20%. Precision, recall, and F1 scores further validated the models' ability to predict health outcome accurately. Evaluation of the accuracy and loss curves showed the convergence of the models towards optimal performance. This study contributes to remote healthcare monitoring and provides a promising IoT paradigm for realizing ubiquitous remote monitoring, optimized healthcare effectiveness, and patient outcome through AI-enabled IoT systems. © 2024 IEEE.

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramya, R.S. Daniel, Keren Lois Rajkumar, S. Madhavan, Sruthi S. Akshya, J. Choudhry, Mani Deepak Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Computer Science and Business Systems Coimbatore India Sona College of Technology Department of Information Technology Salem India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Detection analysis of malicious cyber attacks using machine learning algorithms

引用

Materials Today: Proceedings 2022年 68卷 26-34页

作者： Karthika, R.A. Maheswari, M. Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai India Department of Computational Intelligence SRM Institute of Science and Technology KTR Chennai 603203 India

Cybersecurity is the practice of safeguarding information and the systems that store or process information. Cybersecurity violations are the foremost persecution instigated by cyber attackers through one or more systems on single or several networks or systems. This kind of cyber threats can ruthlessly trigger data loss or theft besides halting the network systems partially or fully. Among various cybersecurity attacks, the Denial of Service (DoS) attack is one of the most dominant hacking modus operandi over the internet. The hackers use the weapons at their disposal to disrupt traffic in and around the network surroundings or the target system by bombarding it with a lot of malicious requests. This paper introduced machine learning algorithms such as Gaussian Naïve Bayes and Nearest Centroid to identify the attacks via classifying the given dataset into normal and malicious traffic. Furthermore, metrics such as accuracy, f-score, FNR, precision, and prediction time etc., were calculated to identify the best performing model. © 2022

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Removing Gaussian Image Noise Using Advanced Non-Local Means Filtering Techniques

Removing Gaussian Image Noise Using Advanced Non-Local Means...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Suresh, A. Waris, Saiyed Faiayaz Mohankumar, B. Arumuga Arun, R. Saravanan, G. Vellore Institute of Technology School of Computer Science and Engineering Department of Computational Intelligence Vellore India Vignan's Foundation for Science Technology & Research Vadlamudi Department of Computer Science and Engineering Andhrapradesh Guntur India Vellore Institute of Technology School of Computer Science and Engineering Vellore India Veltech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350317060

Our system is aimed at improving the application of image de-noising processes, even though the presence of noise has a negative impact on image quality. End-user applications suffer as a result of the focusing Gaussian noise. Introduce the Non-local means (NLM) filter to take advantage image similarities and analyse data preservation in de-noising. Even though the NLM approach eliminates some noises, like salt and pepper, an estimate weighted between the input images and edge preservation is still calculated. It could experience loss of visual structure, noise reduction, and blurring. This research shows the enhancement of the threshold level by combining stationary wavelet transform with NLM. This type of Advanced NLM method is effective at removing high noisy regions like Gaussian noise levels. The proposed ANLM method improves edge preservation and image structure similarities. This article uses some noisy images as input, then employs quantitative parameters to perform the measurement. Finally, this method demonstrates the effective removal noise and edge preservation of weighted refined structures. PSNR, COC, and MSE are the measuring parameters. © 2023 IEEE.

关键词： Mean square error

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：