检索结果-内蒙古大学图书馆

7th International Conference on Soft Computing and Signal Processing, ICSCSP 2024

作者： Banu, Mohammed Razia Alangir Gupta, Arpita Banu, Athur Shaik Ali Gousia Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad500075 India Department of Computer Science and Engineering Muffakham Jah College of Engineering & Technology Hyderabad India Department of Computer Science and and Information Technology Muffakham Jah College of Engineering & Technology Hyderabad India

ISBN: (纸本)9789819609239

MRI is important for diagnosing brain tumors due to its clear imaging. Manual brain tissue segmentation in MRI images is time- consuming and prone to errors. Deep learning can now automate this task effectively. Left4Dead team uses deep learning to segment brain tissues and identify tumor locations in MRI scans accurately. CNNs, RNNs, and other deep learning structures combined with traditional techniques enhance segmentation performance. Applying hybrid deep learning methods in medical imaging may improve brain tumor detection. Techniques like merging features on different scales and transfer learning can tackle obstacles in brain tissue segmentation and tumor detection. Integration of GANs and reinforcement learning can enhance data augmentation in this field. This review analyzes advanced techniques and challenges in previous research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A novel approach to detect, analyze and block adversarial web pages

引用

International Journal of Information Technology (Singapore) 2024年第6期16卷 3617-3622页

作者： Kumar, M. Ranjith Naik, Darshana A. Kapila, Neha Mohan, Chinnem Rama Prasad, Ch Raghava Shelke, Chetan Rao, C. V. Guru School of Computer Science and Engineering Vellore Institute of Technology Department of Computer Science and Engineering M S Ramaiah Institute of Technology Department of Electronics and Electrical Engineering Lovely Professional University Department of Computer Science and Engineering Narayana Engineering College Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation Alliance College of Engineering and Design Alliance University School of CS & amp AI SR Universtity

The phenomenon of distraction is very common, and its adverse effects are seen among people. The major cause underlying this issue is the ease with which adversarial web sites and web pages can be accessed. It is of utmost importance to locate, evaluate, and actively block such web pages in an effort to comprehensively and globally solve this societal issue. Thus, the given paper proposes an extension or plug-in to detect, analyze, and block websites smartly. The proposed approach takes keywords entered by the user as input into consideration, which eventually leads to the generation of web pages and web links. The filtering of web links is done by the proposed extension, followed by the extraction of features, the utilization of support vector machines (SVM) for binary classification, and the summarization of textual data using natural language processing (NLP). Lastly, the precise results corresponding to relevant web links are presented to the users, which will increase their productivity, thereby reducing their distraction levels under all working circumstances. The performance of the proposed approach is validated against existing recent studies based on evaluation metrics such as adversarial website detection time (ms) and accuracy (%). © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Adversarial web pages Distraction Natural language processing (NLP) Support vector machine (SVM) Text summarization

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of 6 Degree of Freedom Robotic Whiteboard Cleaner 6th

Design and Analysis of 6 Degree of Freedom Robotic Whiteboar...

引用

6th International Conference on Mechanical engineering Research, ICMER 2021

作者： Estrera, Mark Ryan M. Genobiagon, Cresencio P. Mechanical Engineering Program College of Engineering Education University of Mindanao Matina Davao City Philippines

ISBN: (纸本)9789811915765

The design and analysis of a six DOF robotic white board cleaner is the focus of this project. A kinematic model for a six-degree-of-freedom (DOF) white board cleaner is presented in this study. Moreover, forward kinematics and inversed kinematics model is developed, and Denavit-Hartenberg (D-H) parameters are used to find solutions. The forward model is used to determine the position and orientation of the end-effector whereas inversed kinematics is used analyze its results associated with solidworks. The experiment is then repeated to confirm the simulation results. Results exhibit that the analytical data are consistent with the measured points and orientation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Attention Guided Enhancement Network for Weakly Supervised Semantic Segmentation

引用

Chinese Journal of Electronics 2023年第4期32卷 896-907页

作者： ZHANG Zhe WANG Bilin YU Zhezhou ZHAO Fengzhi College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

Weakly supervised semantic segmentation using only image-level labels is critical since it alleviates the need for expensive pixel-level labels. Most cuttingedge methods adopt two-step solutions that learn to produce pseudo-ground-truth using only image-level labels and then train off-the-shelf fully supervised semantic segmentation network with these pseudo labels. Although these methods have made significant progress, they also increase the complexity of the model and training. In this paper, we propose a one-step approach for weakly supervised image semantic segmentation—attention guided enhancement network(AGEN), which produces pseudopixel-level labels under the supervision of image-level labels and trains the network to generate segmentation masks in an end-to-end manner. Particularly, we employ class activation maps(CAM) produced by different layers of the classification branch to guide the segmentation branch to learn spatial and semantic ***, the CAM produced by the lower layer can capture the complete object region but with many ***, the self-attention module is proposed to enhance object regions adaptively and suppress irrelevant object regions, further boosting the segmentation *** on the Pascal VOC 2012 dataset demonstrate that AGEN outperforms alternative state-of-the-art weakly supervised semantic segmentation methods exclusively relying on image-level labels.

关键词： Training Annotations Semantic segmentation Scalability Semantics Benchmark testing Boosting

来源：评论

学校读者我要写书评

暂无评论

An optimal deep learning-based framework for the detection and classification of android malware

引用

Journal of Intelligent and Fuzzy Systems 2023年第6期44卷 9297-9310页

作者： Jebin Bose, S. Kalaiselvi, R. Department of Computer Science and Engineering Noorul Islam Centre for Higher Education Tamil Nadu Kumaracoil India Department of Computer Science and Engineering R.M.K. College of Engineering and Technology Gummidipoondi Tamil Nadu Puduvoyal India

The use of smartphones is increasing rapidly and the malicious intrusions associated with it have become a challenging task that needs to be resolved. A secure and effective technique is needed to prevent breaches and detect malicious applications. Through deep learning methods and neural networks, the earliest detection and classification of malware can be performed. Detection of Android malware is the process to identify malicious attackers and through the classification method of malware, the type is categorized as adware, ransomware, SMS malware, and scareware. Since there were several techniques employed so far for malware detection and classification, there were some limitations like a reduced rate of accuracy and so on. To overcome these limitations, a deep learning-based automated process is employed to identify the malware. In this paper, initially, the datasets are collected, and through the preprocessing method, the duplicate and noisy data are removed to improve accuracy. Then the separated malware and benign dataset from the preprocessing phase is dealt with in feature selection. The reliable features are extracted in this process by Meta-Heuristic Artificial Jellyfish Search Optimizer (MH-AJSO). Further by the process of classification, the type of malware is categorized. The classification method is performed by the proposed Dense Dilated ResNet101 (DDResNet101) classifier. According to the type of malware the breach is prevented and secured on the android device. Although several methods of malware detection are found in the android platform the accuracy is effectively derived in our proposed system. Various performance analysis is performed to compare the robustness of detection. The results show that better accuracy of 98% is achieved in the proposed model with effectiveness for identifying the malware and thereby breaches and intrusion can be prevented. © 2023-IOS Press. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Implementing a Robust Method for Detecting Human Actions in Health Monitoring by Employing Sensors on Mobile Internet of Things Devices and Utilizing a One-Dimensional Convolutional Neural Network

引用

Journal of Technology in Behavioral Science 2025年第1期10卷 79-91页

作者： Vignesh, T. Thyagharajan, K.K. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Electronics and Communication Engineering R.M.D Engineering College Chennai India

This research is focused on developing a precise human action recognition system by utilizing accelerometer and gyroscope sensor data. The aim is to analyze various human actions like jogging, sitting, standing, walking, going upstairs, going downstairs, and falling, using multiple sensors found in modern smartphones. Previous studies have explored human action recognition using different sensors, cameras, and machine learning and deep learning techniques. However, some existing approaches, particularly those based on channel state information (CSI), have shown less satisfactory outcomes. In contrast, this paper employs deep learning techniques, specifically one-dimensional convolutional neural networks (1D-CNN), for more accurate human action analysis. One significant advantage of the proposed system is its potential as a wearable device. The paper will introduce a one-dimensional convolutional neural network tailored for human action recognition and an optimized approach for determining the magnitude of accelerometer's X, Y, and Z coordinates, as well as gyroscope sensor values. By utilizing these coordinates, the One-Dimensional Convolutional Neural Networks can effectively classify various human actions like jogging, sitting, standing, walking, going upstairs, going downstairs, and falling. To evaluate the performance of the 1D-CNN approach, a comparison is made with other methods, including SOM, SVM, and FCM. The results demonstrate that the proposed method (1D-CNN) outperforms other classification techniques with an impressive accuracy of 92.42 per cent. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Acceleration Gyroscope Human action recognition One-dimensional convolutional neural network Sensors

来源：评论

学校读者我要写书评

暂无评论

Temperature Profile of Mixed Mode Solar Cabinet Coconut Dryer 6th

Temperature Profile of Mixed Mode Solar Cabinet Coconut Drye...

引用

6th International Conference on Mechanical engineering Research, ICMER 2021

作者： Diez, Keith Yvonne B. Yap, Jao Philip A. Genobiagon Jr, Cresencio P. Mechanical Engineering Program College of Engineering Education University of Mindanao Matina Davao City Philippines

ISBN: (纸本)9789811915765

A low-cost mixed-mode natural convection dryer was designed to dry coconut kernels. The dryer was made of low-cost materials readily available in local areas. The dryer consists of two major parts, the heat collector and the chamber. The study aim to compare the performance of solar dryer with sun drying. The experiment was conducted in the open field at the University of Mindanao, Davao City, Davao del Sur, Philippines. Coconut cups were placed in the drying chamber and dried until the ideal moisture content is achieved. The temperature, and moisture content were observed during the experiment, as well as the weight of coconut. The drying chamber has a maximum temperature of 78.4 °C and a minimum temperature of 64.6 °C under a clear sky sunny weather. The dryer has reduced the initial moisture content of 54.86 to 6.82% in 21 h of drying. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Natural convection

来源：评论

学校读者我要写书评

暂无评论

Environmental water quality prediction based on COOT-CSO-LSTM deep learning

引用

Environmental Science and Pollution Research 2024年第42期31卷 54525-54533页

作者： Rajagopal, Sankarasubbu Ganesh, Sundaram Sankar Karthick, Alagar Sampradeepraj, Thangavel Department of Information Technology National Engineering College Tamilnadu Kovilpatti628503 India Department of Computer Science and Engineering R.M.K. College of Engineering and Technology Puduvoyal Tamilnadu Thiruvallur601206 India Renewable Energy Lab Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Tamilnadu Coimbatore641407 India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu Virudhunagar626126 India

Water resource management relies heavily on reliable water quality predictions. Predicting water quality metrics in the watershed system, including dissolved oxygen (DO), is the main emphasis of this work. The enhanced long short-term memory (LSTM) model was suggested to improve the model’s performance. Additionally, a hybrid model was employed to calculate the ideal parameter values for the LSTM model, which helped overcome the nonstationarity, unpredictability, and nonlinearity of the data about the water quality parameters. This model recruited the COOT method. The original weekly water quality values at the Vaigai River, Madurai, Tamil Nadu, India, were tested using the suggested hybrid model. An independent LSTM, the hybrid optimisation method takes its cues from the cuckoo bird’s reproductive strategy and a novel meta-heuristic optimisation technique dubbed COOT, which is based on the behaviour of a flock of coot birds. If implemented, the suggested hybrid model might serve as an alternate framework for water quality prediction, laying the groundwork for basin-wide efforts to manage water quality and control pollutants. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Macroinvertebrates

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Reversible Data Hiding Scheme using Image Processing and Deep Learning Techniques 5

An Adaptive Reversible Data Hiding Scheme using Image Proces...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Allwyn, Philip Hemalatha, J. Sampathkumar, Nithyanantham Ramaraj, Kottaimalai Swain, Gandharba Sekar, M. AAA College of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Sivakasi India AAA College of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Sivakasi India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Krishnankoil India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhrapradesh Vaddeswaram India AAA College of Engineering and Technology Department of Mechanical Engineering Tamilnadu Sivakasi India

ISBN: (纸本)9798331530013

Image steganography is the process of hiding data from digital photos without changing how they look on the outside. It functions as a covert mode of communication, giving access to confidential data without raising the suspicions of opponents or unauthorized parties. It provides an extra degree of secrecy and security for digital communications. Prediction-error expansion (PEE) is an extensively used method in the type of reversible data hiding (RDH) that hiding data with intact image quality in the prediction errors. High-accuracy prediction algorithms are typically essential for a PEE-based RDH implementation to be successful. Current PEE-based Reversible Data Hiding (RDH) systems frequently use a single forecasting approach, typically with worldwide optimization, but pay little attention to the local neighborhoods' pixel distribution features. This study aims to analyze the most recent RDH techniques and investigate image processing and deep learning (DL) techniques for reversible data hiding (DH) schemes. RDH is a difficult topic in general which has potential uses in today's digital world. Reversible data hiding techniques properly restore the cover medium while safely transferring secret data (SD). The goal of RDH techniques is to achieve both large capacity and tunable quality. Even though reversible data hiding has been the subject of indepth research recently, there hasn't yet been a thorough literature analysis to identify research gaps and potential future approaches. © 2024 IEEE.

关键词： Data Hiding Data Security Image Processing Pixel Sorting Reversible Data Hiding Steganography

来源：评论

学校读者我要写书评

暂无评论

Individuation and Interaction Enhancement of Landscape Design Based on computer-Aided Design and Reinforcement Learning

引用

computer-Aided Design and Applications 2024年第S23期21卷 224-238页

作者： Feng, Zhen Wu, Jianghong Bai, Jiabao Department of Art and Design Shaanxi Fashion Engineering University Shaanxi Xi'an712046 China Preschool Education Program of the Art Education College Xi'an Academy of Fine Arts Shaanxi Xi'an712046 China

The traditional approach to landscape design primarily hinges on the designer's expertise and gut feeling, greatly constraining the design's adaptability to diverse and personalized user needs. Current research, therefore, focuses on integrating cutting-edge technology into landscape design to enhance its individuality and user engagement. This article aims to pioneer innovative methods that enhance the uniqueness and interactivity of landscape designs, thus catering to the escalating demands of users. To this end, we introduce a novel approach that seamlessly merges computer-Aided Design (CAD) with Reinforcement Learning (RL) algorithms. This approach allows us to capture users' preferences in real-time and leverages RL technology to continuously refine the design proposal, fostering a profound interaction between users and the design process. Rigorous experimental validations and user evaluations reveal that this approach significantly outperforms traditional design methodologies in terms of user satisfaction, design efficacy, and an overall superior score. The findings underscore that this method not only elevates the individuality and interactivity of designs but also propels the automation and intelligence of the design process. © 2024 U-turn Press LLC.

关键词： computer aided design

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：