检索结果-内蒙古大学图书馆

Massive data clustering by multi-scale psychological observations

National Science Review 2022年第2期9卷 43-51页

作者： Shusen Yang Liwen Zhang Chen Xu Hanqiao Yu Jianqing Fan Zongben Xu National Engineering Laboratory of Big Data Analytics Xi'an Jiaotong University Industrial Artificial Intelligent Center Pazhou Laboratory Department of Mathematics and Statistics University of Ottawa Center for Statistics and Machine Learning Princeton University

Clustering is the discovery of latent group structure in data and is a fundamental problem in artificial intelligence,and a vital procedure in data-driven scientific research over all ***,existing methods have various limitations,especially we ak cognitive interpretability and poor computational scalability,when it comes to clustering massive datasets that are increasingly available in all ***,by simulating the multi-scale cognitive observation process of humans,we design a scalable algorithm to detect clusters hierarchically hidden in massive *** observation scale changes,following the Weber-Fechner law to capture the gradually emerging meaningful grouping *** validated our approach in real datasets with up to a billion records and 2000 dimensions,including taxi trajectories,single-cell gene expressions,face images,computer logs and *** approach outperformed popular methods in usability,efficiency,effectiveness and robustness across different domains.

关键词： massive data clustering psychological observation Weber–Fechner law cognitive interpretability computational scalability

来源：评论

学校读者我要写书评

暂无评论

Development of Punjabi Automatic Speech Recognition Application for Mobile Devices 7

Development of Punjabi Automatic Speech Recognition Applicat...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Mittal, Puneet Sharma, Sukhwinder Manipal University Jaipur Department of Artificial Intelligence & Machine Learning Jaipur India Manipal University Jaipur Department of Data Science & Engineering Jaipur India

ISBN: (纸本)9798350304268

Speech recognition based mobile device applications are gaining popularity due to their ease of use, flexibility as well as ability to provide hands-free access to device features and functions for persons without hands or with disabilities like blindness. The increased accuracy of Automatic Speech Recognition (ASR) systems and support to multiple languages is further motivating the researchers to develop such applications. The development of an application for mobile device helps to validate the applicability of an ASR system in real world environment. An android based speech recognition application for calling and messaging features has been designed and developed in this paper. User can send message or call to any phone number or contact stored in the mobile phone using Punjabi speech. Punjabi based ASR system having pronunciation dictionary, acoustic model and language model is used to implement the underlying speech recognition for Punjabi speakers. Speech user interface has been designed using Android, while AndroidPocketSphinx has been used as speech decoder. The successfully running application has been tested for multiple male and female native Punjabi speakers, followed by thorough performance analysis. The results shown are quite optimistic with a very low combined error of 1.6% for all female speakers and 2.1% for all male speakers. The application gives 98.4% success rate or recognition accuracy for female speakers and 97.9% for male speakers for the underlying Punjabi based ASR system. © 2023 IEEE.

关键词： Acoustic model AndroidPocketSphinx ASR Language Model Pronunciation Dictionary Speech Recognition

来源：评论

学校读者我要写书评

暂无评论

A recurrent neural network architecture for android mobile data analysis for detecting malware infected data

引用

Soft Computing 2024年第21期28卷 12917-12928页

作者： Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Garg, Shruti Department of ECE Saveetha School of Engineering Simats Chennai602105 India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Simats Chennai602105 India Department of Netwoking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business System School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Applied Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technological Sciences Tamilnadu Chennai India Birla Institute of Technology Mesra Ranchi India

One of the latest modern communication devices is a mobile device seriously affected by multiple malware. Malware is a virus software installed automatically by hackers on various computing devices. Malware corrupts the system software, kills *.exe files, and tries to access user-sensitive data from the device. Around the world, 80% of people use smartphones, and 70% use Android phones. All Android phones are installed with anti-virus software but not used properly. Thus, it creates a pathway for malware to enter Android mobile devices and deploy vulnerabilities. Several earlier methods have focused on using the malware detection method by analyzing static data, which cannot identify the dynamic behavior of the malware. Thus, this paper implemented one of the deep learning algorithms, RNN, for identifying and detecting malware activities in Android mobile devices statically and dynamically. An IoT network architecture is proposed for experimenting with the RNN algorithms verifying the performance. The results of the RNN method show that it is better than other models in malware detection in mobile devices. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

A human-in-the-loop method for pulmonary nodule detection in CT scans

引用

Visual Intelligence 2024年第1期2卷 1-13页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an 710072 China Australian Institute for Machine Learning The University of Adelaide Adelaide 5000 SA Australia

Automated pulmonary nodule detection using computed tomography scans is vital in the early diagnosis of lung cancer. Although extensive well-performed methods have been proposed for this task, they suffer from the domain shift issue between training and test images. Unsupervised domain adaptation (UDA) methods provide a promising means to mitigate the domain variance;however, their performance is still limited since no target domain supervision is introduced. To make the pulmonary nodule detection algorithm more applicable in clinical practice and further boost the performance across domains, we propose a human-in-the-loop method in a semi-supervised fashion to enhance the model generalization ability when transferred from source domain to target domain. Specifically, we first train a detector model on source domain, and then the pre-trained detector is utilized with our proposed uncertainty-guided sample selection scheme (USSS) to find a few target domain samples worth annotating most and obtain their human annotations. Finally, the annotated and the rest unlabeled target domain samples are used together to refine the pre-trained model via our proposed zoom-in and zoom-out constraint (ZZC) strategy. We evaluate our method on the Nodule Analysis 2016 (LUNA16) and TianChi datasets. Experimental results show that our method surpasses recent competitive methods on source domain and also achieves surprising performance on target domain. © The Author(s) 2024.

关键词： Domain adaptation Human-in-the-loop Pulmonary nodule detection Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multilingual Facial Emotion Decoding and Posture Recognition using Random Forest Classifier

Multilingual Facial Emotion Decoding and Posture Recognition...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Sangeetha, K. Balaji, V.S. Manju, M. Renuka Devi, S. Velayutham, P. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Chennai India

ISBN: (纸本)9798350374933

Effective communication is crucial for success in various interactions, including personal and online interviews. The work proposed is to refine the communication effectiveness and extend the understanding of interactions by incorporating new system functions of real-time emotion and body language capture. Facial and body landmarks are analyzed using Google’s Mediapipe to ensure accurate identification of the frequently performed emotions and frequently posed postures. The proposed system uses three classifiers, namely Random Forest, Gradient Boosting, and Ridge Classifier, all integrated in one pipeline;this makes our work distinct. In the testing phase the classifiers are checked to avoid misidentification of emotions or incorrect posture in different situations. One of the major novelties of this work is its ability to address users of different languages, thus it is relevant anywhere in the world. This dynamic and robust system provides accurate emotion analysis achieving the accuracy of 92%, enhancing understanding in various communication contexts and setting a new standard for interview and interaction analysis. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Review on the Role of Artificial Intelligence in Personalized learning

A Review on the Role of Artificial Intelligence in Personali...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Qureshi, Rukaiyya Hajare, Shital Verma, Prateek Sawangi Meghe Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Sawangi Meghe Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798350361537

This article explores the revolutionary role of Artificial Intelligence (AI) in personalized learning, focusing on its potential to revolutionize educational processes and improve learning outcomes. This paper provides insights into how AI technologies can be used to tailor instruction, identify learning needs, and provide specific strategies that cater to different students' psychological, cognitive, and motivational preferences. The article examines case studies and examples to demonstrate different uses of AI in personalized learning settings, such as autonomous tutoring systems, personalized education channels, and analysis based on data. However, the use of AI in education raises ethical, technological, and policy concerns that require careful study and proactive actions to assure fair access, preserve learner privacy, and eliminate algorithmic biases. Ultimately, finally, the article emphasizes AI's transformative potential in personalized learning and advocates for coordinated efforts among educators, academics, and policymakers to leverage its benefits while tackling accompanying obstacles. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach of CNN & RNN for Breast Cancer Detection and Segmentation 3

Hybrid Approach of CNN & RNN for Breast Cancer Detection and...

引用

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Manju Bala, P. Priyadharshini, S. Usharani, S. Balachandar, A. IFET College of Engineering An Autonomous Institution Department of Artificial Intelligence and Data Science India IFET College of Engineering An Autonomous Institution Department of Computer Science and Engineering India IFET College of Engineering An Autonomous Institution Department of Artificial Intelligence and Machine Learning India

ISBN: (纸本)9798350391565

Breast cancer is a serious worldwide health concern, and advanced diagnostic tools are needed for an accurate and timely identification of the illness. In order to classify breast cancer through ultrasound pictures, this method suggests a hybrid strategy that combines Convolutional Neural Networks (CNNs) with Recurrent Neural Networks (RNNs). CNN integration makes it possible to extract spatial data from ultrasound pictures and identify complex patterns that may be signs of cancer. Concurrently, RNNs are used to record temporal relationships between successive ultrasound frames, which enables the model to identify changing features of possible anomalies. By combining the advantages of both CNNs & RNNs, the suggested hybrid architecture improves the model's capacity to identify minute, dynamic patterns that are essential for precise diagnosis. In comparison to standalone CNN or RNN models, the hybrid model performs better in classification, as evidenced by experimental assessments carried out on a variety of ultrasound picture datasets. The findings highlight the hybrid approach's potential to improve breast cancer diagnostic skills and present a viable path for raising the precision and dependability of ultrasound-based tumour classification techniques. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Agricultural Yield Predictions with Real-Time IoT Sensor data and machine learning Integration 5

Enhancing Agricultural Yield Predictions with Real-Time IoT ...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Chandiraprakash, N. Chinnasamy, A. Ashok, M. Malla Reddy College of Engineering Department of Artificial Intelligence and Machine Learning Hyderabad India School of Computing Department of Data Science and Business Systems SRMIST kattankulathur campus Chennai India Malla Reddy College of Engineering Hyderabad India

ISBN: (纸本)9798331518097

This research extends previous studies on the effects of climate change on agricultural yield predictions by integrating advanced machine learning (ML) methods with real time environmental sensing data. It builds on the basic usage of Long Short-Term Memory (LSTM) and Random Forest (RF) methods by employing real time data streams from IoT based field sensors that measure soil moisture, nutrient levels and pest activity. The aim is to enhance the prediction model's adaption to changing climatic circumstances, therefore increasing their utility in agricultural management. This study proposes a dynamic adaptation feature that uses real time data to make timely adjustments to crop management predictions. Moreover, the integration of Convolutional Neural Network (CNN) with LSTM is being investigated to increase the spatial and temporal accuracy of these predictions. By integrating conventional climatic data with detailed micro environmental elements from IoT sensors, this method obtains a aspects which affects the crop growth. This study also focuses on developing a userfriendly interface that allows farmers to easily access predictive developments and recommendations, allowing for more informed decision making. This technique is predicted to make substantial advances in precision agriculture, giving more effective methods for regulating agricultural productivity in dynamic climatic variability. These results may improve food security and sustainability by optimizing resource utilization and reducing the environmental impact of farming operations. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A Dual-Port, and Single-Element Planar Inverted-F Antenna for Current 4G/5G Portable Applications 21

A Dual-Port, and Single-Element Planar Inverted-F Antenna fo...

引用

21st International Multi-Conference on Systems, Signals and Devices, SSD 2024

作者： Alja'Afreh, Saqer S. Altakhaineh, Amjaad T. Al-Shamaileh, Mallak H. Matarneh, Aser M Daoud, Omar R. Al-Khawaldah I, Mohammad School of Engineering and Computing American International University Electrical and Computing Engineering Al-Jahra Kuwait Pioneers International Academy Data Science and Machine Learning Dept. Amman Jordan Al-Ahliyya Amman University Communications and Computer Engineering Amman Jordan

ISBN: (纸本)9798350374131

A first-hand, low-profile, two-port planar inverted-F antenna is proposed for current 4G/5G sub-3 GHz hand-portable multiple-input and multiple-output (MIMO) applications. The design features a profile of about 5 mm and dual-coplanar feeds, which are isolated using only a modified top plate, while the shared ground plane is not perturbed as in previous designs. An open-edge slot on the top of the PIFA provides a 3λ/4 current path. The proposed antenna covers approximately a 15% impedance bandwidth fraction in the range of 2.45-2.85 GHz. The simulated results, including scattering parameters, far-field radiation patterns, and the envelope correlation coefficient, all exhibit excellent features. © 2024 IEEE.

关键词： Antenna feeders

来源：评论

学校读者我要写书评

暂无评论

Addressing data Imbalance in machine learning: Challenges and Approaches 6

Addressing Data Imbalance in Machine Learning: Challenges an...

引用

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

作者： Langote, Meher Zade, Nikita Gundewar, Swapnil Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India

ISBN: (纸本)9798331522667

A key difficulty of dealing with imbalanced datasets is that machine learning models are trained to favor the majority class and therefore perform poorly when it comes to a minority class classification. In this paper, we consider the following methods of tackling the issue of the over-representation of a class;random oversampling, undersampling, SMOTE, cost-sensitive learning, and ensemble methods. Comparing them, we assess the performance of each of these techniques within different classifiers. Techniques including SMOTE together with combined methods including Random Forests also show higher capacity in minority class predictions. However, problems such as overfitting and the increase in the computational load are not escapable yet. We briefly recap the strengths and weaknesses of each approach and propose potential refinements including a combination of both methods and dynamic resampling methods to serve as the next steps toward improving the model. Thereby, our results draw attention to the necessity of accurate methods for handling the class imbalance, which will further yield more accurate and fair machine learning solutions across a variety of applications. © 2025 IEEE.

关键词： Adversarial 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：