检索结果-内蒙古大学图书馆

Hybrid RNN Based Text Classification Model for Unstructured Data

SN computer Science 2024年第6期5卷 726页

作者： Sunagar, Pramod Sowmya, B.J. Pruthviraja, Dayananda Supreeth, S. Mathew, Jimpson Rohith, S. Shruthi, G. Cloudthat Technologies Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education School of Computer Science and Engineering REVA University Department of Computer Science and Engineering Indian Institute of Technology Patna Department of ECE Nagarjuna College of Engineering and Technology

The volume of social media posts is on the rise as the number of social media users expands. It is imperative that these data be analyzed using cutting-edge algorithms. This goal is handled by the many techniques used in text categorization. There are a variety of text categorization techniques available, ranging from machine learning to deep learning. Numerical crunching has become easier with less processing time since the emergence of high-end computer facilities. This has led to the development of sophisticated network architectures that can be trained to achieve higher precision and recall. The performance of neural network models which was evaluated by the F1 score is affected by cumulative performance in precision and recall. The current study intends to analyze and compare the performance of the neural network proposed, A Hybrid RNN model that has two layers of BiLSTM and two layers of GRU to that of previous hybrid models. GloVE dataset is used to train the models and their accuracy, precision, recall, and F1 score are used to assess performance. Except for the RNN + GRU model, the RNN + BILSTM + GRU model has a precision of 0.767, a recall of 0.759, and an F1-score of 0.7585. This hybrid model outperforms the others. © The Author(s) 2024.

关键词： Bidirectional long-short-term memory (BiLSTM) Gated recurrent units (GRU) Recurrent neural networks (RNN) Region-based convolutional neural networks (RCNN) Text classification

来源：评论

学校读者我要写书评

暂无评论

Exploring Transfer Learning in Brain Tumor Classification with Deep Neural Networks 11

Exploring Transfer Learning in Brain Tumor Classification wi...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Rawat, Vikas Singh Johar, Sakshi Kumar, Amit Singh, Ninni University Department of Computer Science and Engineering Dehradun India Cmr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350357

In today's era, medical advancements have reached their peak but still, some bugs led to the emergence and involvement of advanced techniques like Machine learning, Artificial Intelligence, and Deep Learning. These three are interconnected and have strong relationships that work as such, to increase the growth of work in any domain with rapid accuracy and without any error. This paper deals with the identification and categorization of tumors. Brain tumors are a result of abnormal behavior of cell division which leads to uncontrolled growth of cells and results in the formation of masses and lumps in the brain. The detection of tumors is done using radiology with the help of MRI techniques or MRI scans. Traditional scans sometimes lead to errors causing misdiagnoses. This process is also timeconsuming and as such requires high expertise. To elevate this process, in this paper, we used a multi-layered CNN model which takes the MRI images as input and classifies it into one of the four major categories i.e., 'Glioma', 'Meningioma', 'Pituitary' or 'No Tumor'. The publicly available dataset used to train this model contains over 7000 images which have been segregated into testing and training where both classes contain 4 different segmentations depicting the different brain tumors. The training folder contains nearly 5200 images, and the testing folder has over 1500 images. The accuracy of the model has been tested to over 96 percent. Then we converted the above model to the VGG16 model by using the study of Transfer Learning and the model gave up to 98.04% accuracy and validation accuracy was approximately 94.73%. © 2024 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Demographic and Operational Variables on 1-to-Many Face ID Search

IEEE Transactions on Technology and Society

引用

IEEE Transactions on technology and Society 2024年第2期5卷 217-230页

作者： Pangelinan, Gabriella Bhatta, Aman Wu, Haiyu King, Michael C. Bowyer, Kevin W. Florida Institute of Technology Department of Electrical Engineering and Computer Science MelbourneFL32901 United States University of Notre Dame Department of Computer Science and Engineering Notre DameIN46556 United States

Concerns related to the proliferation of automated face recognition technology with the intent of solving or preventing crimes continue to mount. The technology being implicated in wrongful arrest following 1-to-many face identification has heightened scrutiny in the media and spawned lawsuits. We analyze the accuracy of 1-to-many face identification across African-American and Caucasian demographic groups and in the presence of blur and reduced resolution in the probe image, as might occur in "surveillance camera quality"images. Because of the high accuracy of modern face recognition algorithms with "government ID quality"images and the size of available datasets, we use the following indirect metrics to assess the relative propensity for false positive identifications: (1) the traditional d-prime statistic between mated and non-mated score distributions, (2) absolute score difference between thresholds in the high-similarity tail of the non-mated distribution and the low-similarity tail of the mated distribution, and (3) distribution of (mated - non-mated rank-one scores) across the set of probe images. We find that demographic variation patterns in 1-to-many accuracy largely, but not perfectly, follow that observed in 1-to-1 accuracy. We show that, different from the case with 1-to-1 matching accuracy, demographic comparison of 1-to-many accuracy can be affected by different numbers of identities and images across demographics. We also show that increased blur or reduced resolution of the face in the probe image can significantly increase the false positive identification rate. This point is important because the reputation of modern face recognition algorithms for high accuracy in 1-to-many face identification comes from statistics based on analyzing "government ID quality"rather than "surveillance camera quality"images. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Automated Immune Cell Classification using Image Processing Techniques 6

Automated Immune Cell Classification using Image Processing ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Sathiyaprasad, B. Reddy, Arva Hari Vardhan Abdurrahman, Usama Micheal, A. Annie Department of Computer Science and Engineering Sathyabama institute of science and technology Chennai India

ISBN: (纸本)9798331522667

Advances in immunological research are essential for elucidating immune responses and developing targeted therapeutic approaches. This study proposes an automated method for immune cell classification leveraging machine learning and image processing techniques. A novel framework is introduced, combining high-resolution imaging with computational algorithms to accurately classify various immune cell types from biological samples. The methodology incorporated preprocessing steps, like normalization and noise reduction. Then, deep learning models, such as CNNs and SVMs, will be applied for feature extraction and classification. These models were trained on annotated datasets derived from flow cytometry and microscopy, demonstrating better accuracy and reliability. Results demonstrate an improvement in processing speed and accuracy of classification over traditional approaches, which underlines the importance of automation in immunological diagnostics. The data obtained can be used in high-throughput immunotherapy and disease diagnostic screening;it allows for the identification of immune cell populations within a short period and therefore improves research efficiency. The work provides a basis for real-time analysis and incorporation of multiscale datasets that will help to better understand immunity and its associated disorders. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Kernel-based Actor-Critic Learning Framework for Autonomous Brain Control on Trajectory

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期17卷 554-563页

作者： Song, Zhiwei Zhang, Xiang Chen, Shuhang Tan, Jieyuan Wang, Yiwen Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong University of Science and Technology Department of Chemical and Biological Engineering Hong Kong Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Department of Chemical and Biological Engineering Hong Kong

Reinforcement learning (RL)-based Brain-Machine Interfaces (BMIs) hold promise for restoring motor functions in paralyzed individuals. These interfaces interpret neural activity to control external devices through trial-and-error. In brain control (BC) tasks, subjects control the device continuously moving in space by imagining their own limb movement, in which the subject can change direction at any position before reaching the target. Such multi-step BC tasks span a large space both in neural state and over a sequence of movements. However, conventional RL decoders face challenges in efficient exploration and limited guidance from delayed rewards. In this paper, we propose a kernel-based actor-critic learning framework for multi-step BC tasks. Our framework integrates continuous trajectory control (actor) and internal continuous state value estimation (critic) from medial Prefrontal Cortex (mPFC) activity. We evaluate our algorithm's performance in a BC three-lever discrimination task using data from two rats, comparing it to a kernel RL decoder with internal binary rewards and delayed external rewards. Experimental results show that our approach achieves faster convergence, shorter target-acquisition time, and shorter distances to targets. These findings highlight the potential of our algorithm for clinical applications in multi-step brain control tasks. © 2016 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Neuro-Cybernetics: Enabling Human–Machine Interaction Through Brain Signals

Neuro-Cybernetics: Enabling Human–Machine Interaction Throu...

引用

Congress on Smart Computing Technologies, CSCT 2023

作者： Kulkarni, Mukund Lautawar, Tanmay Bhalgat, Kunal Nandankar, Kuntesh Lad, Yogita Langade, Niranjan Department of Computer Engineering BRACT’s Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9789819780952

In an era where human–machine interaction is at the forefront of technological advancement, the search for a seamless and responsive interface between human cognition and robotic control is supreme. This paper delves into the creation of an IoT-enabled mind-controlled robot, an innovation poised to redefine the boundaries of human–robot collaboration. The challenge addressed here is the establishment of Brain-computer Interface (BCI) which is real-time, having precise control over a robotic platform using EEG-based brain signals. Leveraging NodeMcu devices and wireless communication, this study pioneers a Server-Client Model for facilitating uninterrupted communication between the user and the robot. Within this framework, the user interface NodeMcu captures EEG signals via specialized sensors, while signal processing algorithms extract meaningful patterns. These patterns are mapped to predefined commands, which, when transmitted to the robotic platform NodeMcu, are transformed into motor control signals, driving the robot's movements. This dynamic interaction not only showcases the potential of mind-controlled robotics but also opens new horizons for intuitive and efficient human–robot collaboration. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Synergistic Fusion of Steganography and Cryptography in Medical Imaging: A Comparative Analysis to Enhance Image Security 4th

Synergistic Fusion of Steganography and Cryptography in M...

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Ghosh, Sharmila Saha, Ashim Pal, Tannistha Department of Computer Science and Engineering National Institute of Technology Agartala Agartala India

ISBN: (纸本)9789819751990

Image steganography is a technique for encrypting data, allowing covert communication, and enhancing data security inside image files. This study provides an in-depth analysis of image steganography, covering its core ideas, methods, uses, difficulties, and developments. Numerous embedding algorithms and methodologies, including transform domain methods and LSB-based strategies, are examined in this study. The paper highlights the need for effective defenses against steganalysis attacks, while also discussing the challenges and potential weaknesses in steganography. It examines common steganography techniques and discusses countermeasures such as adaptive embedding, key-based embedding, and algorithmic resistance. Additionally, the paper also highlights the significance of assessing the efficacy and caliber of image steganography techniques. Objective metrics such as PSNR and MSE are discussed, providing insights into the trade-offs between security and image fidelity. For those interested in understanding image steganography, its applications, and its challenges, this study offers a complete resource. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

An empirical evaluation of teaching–learning-based optimization, genetic algorithm and particle swarm optimization

引用

International Journal of computers and Applications 2023年第1期45卷 36-50页

作者： Shukla, Alok Kumar Pippal, Sanjeev Kumar Chauhan, Sansar Singh Department of Computer Science and Engineering G.L. Bajaj Institute of Technology & Management Greater Noida India Department of Computer Science & Engineering Galgotias University Greater Noida India

Metaheuristic algorithms have probable to solve global optimization problems in various fields of engineering and industry. To find a global solution by exploring irregular or non-linear surfaces, classical optimization techniques are not able. To overcome the limitation of the classical approach, in the recent study, a large number of metaheuristic methods have been investigated to improve the solution quality concerning convergence and accuracy on the complex problems. Nowadays, a popular metaheuristic algorithm is introduced called teaching–learning-based optimization (TLBO). It is recently being used as an innovative, and robust method to solve the global optimization problem, inspired by the teaching–learning phenomenon. On the other hand, particle swarm optimization (PSO) algorithm is one of the most utilized algorithms in the current scenario, which has indicated acceptable efficiency. Genetic algorithm (GA) is a valuable component of metaheuristic which has been applied in various research applications. In this article, the performance of TLBO algorithm is estimated on 25 numerical test suites against other metaheuristic algorithms such as PSO and GA. The results of our experimental study show that TLBO outperforms the PSO and GA algorithm regarding convergence solution. © 2019 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Detecting Inattentive and Aggressive Driver Behavior Using Deep Learning: Recent Advances, Challenges with Performance Evaluation 4th

Detecting Inattentive and Aggressive Driver Behavior Using D...

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Debbarma, Tina Pal, Tannistha Debbarma, Nikhil Department of Computer Science and Engineering National Institute of Technology Agartala Agartala India

ISBN: (纸本)9789819751990

Road safety faces a grave threat from the prevalence of aggressive and inattentive driving behaviors, contributing significantly to the global rise in traffic accidents and fatalities. Identifying, tracking, and proactively addressing instances of aggressive and inattentive driving are pivotal steps toward mitigating accidents and enhancing road safety. This research project seeks to explore the potential of deep learning methods for analyzing human driving behavior, with a specific focus on identifying inattentive and aggressive driving behaviors. The ultimate goal is to develop a robust and reliable system capable of accurately recognizing and categorizing such behaviors. To achieve this objective, we harness the power of deep learning algorithm. This paper also discusses the identification and categorization of aggressive and distracted driving behaviors among human drivers, using deep learning methodologies which offer substantial promise for elevating traffic safety. The literature review uncovered several noteworthy techniques, including CNN, MTCNN, transformer-based action detection systems, and fusion models inspired by densely connected convolution networks. Comparative analysis revealed improvements in accuracy and precision through the utilization of these techniques. However, the pursuit of larger and more diverse datasets, real-time implementation capabilities, and robustness in various environmental conditions remain essential requirements. Despite these challenges, deep learning-based systems offer the potential for automatic and precise analysis of intricate driving patterns, pivotal in accident prevention and overall road safety enhancement. Future research should focus on surmounting current limitations and advancing the development of more intricate deep learning models for accurate recognition and categorization of human driving behaviors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Early Heart Failure Recognition for Infants using Machine Learning 5

Early Heart Failure Recognition for Infants using Machine Le...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Indumathi, N. Meera, J. Palani Upadhyay, Shrikant Pithamber, Khobragade Kumar, Manoj Gupta, Jaina Sumith Rajalakshmi Institute of Technology Department of Computer Science and Engineering Chennai India Sathyabama Instittue of Science and Technology Department of Computer Science and Engineering Chennai India Mlr Institue of Technology Department of Electronics and Communiction Engineering Hyderabad India Mlr Institute of Technology Department of Computer Electronics and Communication Engineering Hyderabad India

ISBN: (纸本)9798331504403

Caring of newborn babies is one of major concern for the doctors and to take care of his/her life is very challenging and sometime critical. Cardiac attack is one the severe issue that require immediate medical support to the new born baby. Providing some shocks using some device is one the immediate treatment to save the life of babies. The computation and prediction of cardiovascular status is one of the challenging tasks. In this paper we try to analyze the cardia prior heart failure chances with the different levels using machine learning methodology. The target rate of cardiac arrest detected is 58.78% and level of no cardiac found is 46.67% is achieved and this prediction level which help to recognize the level of cardiac attack for new born child. Here, we also analyze the different parameters like false rate, false observation, stability rate etc., that will help for the proper analysis of the collected data with a stability rate of 1.67% and precision rate of 60.039%. This result may provide the healthcare professional to handle the different level of heart failure for new born child. © 2024 IEEE.

关键词： Machine learning

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：