检索结果-内蒙古大学图书馆

Comprehensive analysis of multiple machine learning techniques for rock slope failure prediction

Journal of Rock Mechanics and Geotechnical engineering 2024年第11期16卷 4386-4398页

作者： Arsalan Mahmoodzadeh Abed Alanazi Adil Hussein Mohammed Hawkar Hashim Ibrahim Abdullah Alqahtani Shtwai Alsubai Ahmed Babeker Elhag Department of Civil Engineering University of HalabjaHalabjaKurdistan Region46018Iraq Department of Computer Science College of Computer Engineering and Sciences in Al-KharjPrince Sattam bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Department of Communication and Computer Engineering Faculty of EngineeringCihan University-ErbilKurdistan RegionIraq Department of Civil Engineering College of EngineeringSalahaddin University-Erbil44002ErbilKurdistan RegionIraq Software Engineering Department College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Department of Civil Engineering College of EngineeringKing Khalid UniversityAbha61413Saudi Arabia

In this study,twelve machine learning(ML)techniques are used to accurately estimate the safety factor of rock slopes(SFRS).The dataset used for developing these models consists of 344 rock slopes from various open-pit mines around Iran,evenly distributed between the training(80%)and testing(20%)*** models are evaluated for accuracy using Janbu's limit equilibrium method(LEM)and commercial tool GeoStudio *** assessment metrics show that the random forest model is the most accurate in estimating the SFRS(MSE=0.0182,R2=0.8319)and shows high agreement with the results from the LEM *** results from the long-short-term memory(LSTM)model are the least accurate(MSE=0.037,R2=0.6618)of all the models ***,only the null space support vector regression(NuSVR)model performs accurately compared to the practice mode by altering the value of one parameter while maintaining the other parameters *** is suggested that this model would be the best one to use to calculate the SFRS.A graphical user interface for the proposed models is developed to further assist in the calculation of the SFRS for engineering *** this study,we attempt to bridge the gap between modern slope stability evaluation techniques and more conventional analysis methods.

关键词： Rock slope stability Open-pit mines Machine learning(ML) Limit equilibrium method(LEM)

来源：评论

学校读者我要写书评

暂无评论

SentiSense: Pioneering Emotional Intelligence through Advanced Detection Technology

SentiSense: Pioneering Emotional Intelligence through Advanc...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Bhatt, Chandradeep Tasleem, Albeena Rawat, Nishant Singh, Sachin Bahuguna, Tanisha Singh, Teekam Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350361537

Human emotion detection from images poses a significant challenge in social communication research. This paper introduces an artificial intelligence (AI) system designed for emotion detection through facial expressions, utilizing deep learning (DL) techniques. The proposed method surpasses traditional image processing approaches, showcasing improved performance. The emotion detection process consists of three key steps: face detection, feature extraction, and emotion classification. The paper presents a convolutional neural networks (CNN) based architecture tailored for deep learning in emotion detection from *** have a observe delves in addition into the version's conduct with the aid of analyzing a Confusion Matrix, providing valuable insights into times of misclassifications across exceptional emotional states. The studies underscore the significance of emotion reputation in numerous programs, together with human-pc interaction, intellectual health assessment, and sentiment assessment. Leveraging current-day deep studying techniques, in particular CNNs, proves promising in automatically extracting complex functions from facial expressions for proper emotion categorization. The technique includes acquiring and preprocessing a whole dataset to facilitate strong education and assessment of the CNN *** effects exhibit the efficacy of the proposed method in adeptly figuring out and categorizing emotional states. Rigorous assessment metrics, inclusive of precision, bear in thoughts, F1 rating, and accuracy, display off the version's capability to generalize well to severa emotional expressions. In stop, this study contributes to advancing emotion detection via cutting-edge CNNs, highlighting their capability effect on various actual-worldwide packages. © 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

Machine Learning for Real-Time Language Translation: A Server-Side Approach to Overcome Cross-Cultural Communication Challenges 4

Machine Learning for Real-Time Language Translation: A Serve...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Elango, S. Mohanaprakash, T.A. Siva, D. Gowtham, A. Sasikumar, A.N. Sunitha, T. Department of Computer Science and Engineering SOET CMR University Bengaluru India Department of Computer Science and Applications SRM Institute of Science and Technology Chennai India Madanapalle Institute of Technology & Science AP India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Artificial Intelligence & Data Science Saveetha Engineering College Chennai India

ISBN: (纸本)9798331515720

The evolution of human civilization has been intrinsically linked to advancements in technology, leading to the development of multiple languages as mediums of communication. However, this linguistic diversity poses significant challenges in cross-cultural communication. Despite numerous efforts and achieving near state-of-The-Art results in language translation, a universal solution remains elusive. This research study proposes an advanced approach to machine translation by utilizing server-side machine learning to enable seamless communication across various languages. By sending GET or POST requests through JQuery, users can efficiently translate text. The process is structured into three key steps: speech recognition (conversion of spoken words to text), translation using machine learning algorithms, and speech synthesis (conversion of translated text to audio). This approach aims to enhance real-Time translation capabilities, offering a more effective and user-friendly solution for overcoming language barriers. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Double Auction Strategies for Peer-to-Peer Energy Trading in Smart Grids: A Game Theoretic and Blockchain Approach 6

Double Auction Strategies for Peer-to-Peer Energy Trading in...

引用

6th International Conference on Energy, Power and Environment, ICEPE 2024

作者： Naik, Madhusudan Pradhan, Nihar Ranjan Pratap Singh, Akhilendra National Institute of Technology Meghalaya Department of Computer Science and Engineering Shillong India VIT-AP University School of Computer Science and Engineering Amaravati India

ISBN: (纸本)9798350379297

The concept of using blockchain technology for peer-to-peer energy trading (P2PET) in smart grids, particularly employing a double auction-based game theoretic method, is a fascinating application of both blockchain and economic principles. This paper deals with a blockchain-enabled framework for P2PET in a smart grid by using a double auction-based game theory approach. The proposed permissioned blockchain network was developed using Hyperledger Fabric, Minifab and designed by configuring the *** file. Three smart contracts, or Chaincode namely Double Auction Order, CreateP2PEnergy, and Matching, have been written using Golang and deployed into the blockchain network, thereby creating automatic energy trading transactions between energy producers and consumers. The client communication, such as consumer queries, user input, and producer trading concepts, was designed using the Postman API. Additionally, the double auction framework's performance has been measured by Hyperledger Caliper. Analysis shows that when 1000 transactions were initiated in each round by clients using Hyperledger Caliper and REST API services, the Proof of Elapsed Time (PoET) mechanism successfully processed 946 transactions, in contrast to the 627 transactions managed by Proof of Work (PoW). The outcomes from multiple rounds of testing underscore the enhanced performance of this framework. In summary, the combination of blockchain technology, P2P energy trading, smart grids, and game theory offers a promising approach to revolutionizing the energy sector. By decentralizing energy trading, empowering consumers, and leveraging market mechanisms, this approach has the potential to enhance efficiency, promote renewable energy adoption, and foster a more sustainable energy ecosystem. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Integrating Brainwave Analysis and Facial Detection for Enhanced Security in Transactional Systems 8

Integrating Brainwave Analysis and Facial Detection for Enha...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Talasila, Smeeth Vadlamudi, Gnana Abhinay Vadlamudi, Anvitha School of Computer Science and Engineering Plano West Senior High School TX United States Department of Computer Science and Engineering New York United States School of Computer Science and Engineering Vit Ap University Amaravati India

ISBN: (纸本)9798331505462

This paper proposes an innovative user authentication system tailored for high-value asset transactions, leveraging advancements in brainwave analysis and emotional state detection. Traditional authentication methods are increasingly vulnerable to sophisticated attacks, necessitating novel approaches to bolster security in transactional systems. Our research explores the untapped potential of Electroencephalography (EEG) data to establish a unique user identifier based on distinctive brainwave patterns, including alpha, beta, gamma, delta, and theta waves. We identify specific patterns associated with the user's relaxed state through rigorous analysis, presenting a robust and bypass-resistant authentication factor. Furthermore, our system integrates facial expression recognition technology to detect negative emotional states, such as stress or panic, during transactional interactions. By combining brainwave analysis with facial recognition, our multi-layered approach enhances security by considering both physiological and emotional indicators. If the brainwave analysis identifies a relaxed state while facial recognition detects negative emotions, the system identifies potential coercion attempts and restricts transaction completion, thus safeguarding against fraudulent activities. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Identification from CT Scans using a Soft-attention enabled Deep Transfer Learning Model 3

Lung Cancer Identification from CT Scans using a Soft-attent...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Dev, Shubhro Roy, Pragyadipta Sinha Chakraborty, Neelotpal Chakraborty, cNeelotpal Sarkar, Ram Rajiv Gandhi Institute of Petroleum Technology Department of Computer Science & Engineering Uttar Pradesh 229305 India KIIT University Department of Computer Science & Engineering Bhubaneswar751024 India RCC Institute of Information Technology Department of Computer Science & Engineering Kolkata700015 India Jadavpur University Department of Computer Science & Engineering Kolkata700032 India

ISBN: (纸本)9798331523893

Being a major contributor to the global mortality, lung cancer, owing to its fatality, calls for early and efficient diagnosis. This requires the employment of efficient computer aided diagnostics for determining the computed tomography (CT) scans as indicating lung cancer or not. Most such systems leverage the high efficiency of deep learning models to identify the lung cancer type from an input CT scan. In this work, a deep transfer learning model equipped with a soft attention block is framed to classify CT scans as either lung cancer affected or normal. Public datasets such as IQ-OTH/NCCD along with LIDC-IDRI are adopted for evaluation of the proposed technique which scored accuracies of 99.55% and 95.41% respectively, that are comparable with those of some recent standard techniques. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Drift Detection and Analysis in Real Time Twitter Data Streams

引用

computer Systems science & engineering 2023年第6期45卷 3231-3246页

作者： E.Susi A.P.Shanthi Department of Computer Science&Engineering Anna UniversityChennai600025Tamil NaduIndia

Handling sentiment drifts in real time twitter data streams are a challen-ging task while performing sentiment classifications,because of the changes that occur in the sentiments of twitter users,with respect to *** growing volume of tweets with sentiment drifts has led to the need for devising an adaptive approach to detect and handle this drift in real *** work proposes an adap-tive learning algorithm-based framework,Twitter Sentiment Drift Analysis-Bidir-ectional Encoder Representations from Transformers(TSDA-BERT),which introduces a sentiment drift measure to detect drifts and a domain impact score to adaptively retrain the classification model with domain relevant data in real *** framework also works on static data by converting them to data streams using the Kafka *** experiments conducted on real time and simulated tweets of sports,health care andfinancial topics show that the proposed system is able to detect sentiment drifts and maintain the performance of the classification model,with accuracies of 91%,87%and 90%,*** the results have been provided only for a few topics,as a proof of concept,this framework can be applied to detect sentiment drifts and perform sentiment classification on real time data streams of any topic.

关键词： Sentiment drift sentiment classification big data BERT real time data streams twitter

来源：评论

学校读者我要写书评

暂无评论

CbcErDL: Classification of breast cancer from mammograms using enhance image reduction and deep learning framework

引用

Multimedia Tools and Applications 2025年第15期84卷 15501-15526页

作者： Agrawal, Rohit Singh, Navneet Pratap Shelke, Nitin Arvind Tripathi, Kuldeep Narayan Singh, Ranjeet Kumar Department of Computer Science and Engineering Madhav Institute of Technology & Science Race Course Road MP Gwalior474005 India School of AI Bennett University Uttar Pradesh Greater Noida201310 India School of Computer Science and Engineering Bennett University TechZone 2 UP Greater Noida201310 India

Breast cancer is a major health concern for women worldwide, and early detection is vital to improve treatment outcomes. While existing techniques in mammogram classification have demonstrated promising results, their limitations become apparent when applied to larger datasets. The decline in performance with increased dataset size highlights the need for further research and advancements in the field to enhance the scalability and generalizability of these techniques. In this study, we propose a framework to classify breast cancer from mammograms using techniques such as mammogram enhancement, discrete cosine transform (DCT) dimensionality reduction, and deep convolutional neural network (DCNN). The first step is to improve the mammogram display to improve the visibility of key features and reduce noise. For this, we use 2-stage Contrast Limited Adaptive Histogram Equalization (CLAHE). DCT is then used to enhance mammograms to reduce residual data. It can provide effective reduction while preserving important diagnostic information. In this way, we reduce the computational complexity and increase the results of subsequent classification algorithms. Finally, DCNN is used on size-reduced DCT coefficients to learn feature discrimination and classification of mammograms. DCNN architectures have been optimized with various techniques to improve their performance, including regularization and hyperparameter tuning. We perform experiments on the DDSM dataset, a large dataset containing approximately 55,000 mammogram images, and demonstrate the effectiveness of the proposed method. We assess the proposed model’s performance by computing the precision, recall, accuracy, F1-Score, and area under the receiver operating characteristic curve (AUC). We achieve Precision and Recall values of 0.929 and 0.963, respectively. The classification accuracy of the proposed models is 0.963. Moreover, the F1-Score and AUC values are 0.962 and 0.987, respectively. These results are better a

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Speech Enhancement Using Dynamic Learning in Knowledge Distillation via Reinforcement Learning

引用

IEEE Access 2023年 11卷 144421-144434页

作者： Chu, Shih-Chuan Wu, Chung-Hsien Su, Tsai-Wei National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

In recent years, most of the research on speech enhancement (SE) has applied different strategies to improve performance through deep neural network models. However, as the performance improves, the memory resources and computational requirements of the model also increase, making it difficult to directly apply them to edge computing. Therefore, various model compression and acceleration techniques are desired. This paper proposes a learning method that dynamically uses Knowledge Distillation (KD) to teach a small student model from a large teacher model by considering the learning ratio from the teacher's output and the real target based on reinforcement learning (RL). During the KD learning process, RL is adopted to estimate the learning ratio by considering the reward favoring the hard target (clean speech) or the soft target (the output of the teacher model) during the training of KD. The proposed method results in a more stable training process for the resulting smaller SE model and yields improved performance. In the experiment, we used the TIMIT and CSTR VCTK datasets and evaluated two representative SE models that employ different loss functions. On the TIMIT dataset, when we reduced the number of parameters in the Wave-U-Net student model from 10.3 million to 2.6 million, our method performed better than non-KD models with improvements of 0.05 in PESQ, 0.1 in STOI, and 0.47 in the scale-invariant signal-to-distortion ratio. Moreover, by utilizing prior knowledge from the pre-trained teacher model, our method effectively guided the learning process of the student model, achieving excellent performance even under low SNR conditions. Furthermore, we use Conv-Tasnet to further validate our proposed method. Finally, for ease of comparison, we conducted a comparison on the VCTK dataset as well. © 2013 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 3765-3779页

作者： Renkhoff, Justus Feng, Ke Meier-Doernberg, Marc Velasquez, Alvaro Song, Houbing Herbert Department of Information Systems BaltimoreMD21250 United States Embry-Riddle Aeronautical University Department of Electrical Engineering and Computer Science Daytona BeachFL32114 United States University of Colorado Department of Computer Science BoulderCO80309 United States

Neurosymbolic artificial intelligence (AI) is an emerging branch of AI that combines the strengths of symbolic AI and subsymbolic AI. Symbolic AI is based on the idea that intelligence can be represented using semantically meaningful symbolic rules and representations, while deep learning (DL), or sometimes called subsymbolic AI, is based on the idea that intelligence emerges from the collective behavior of artificial neurons that are connected to each other. A major drawback of DL is that it acts as a 'black box,' meaning that predictions are difficult to explain, making the testing & evaluation (T&E) and validation & verification (V&V) processes of a system that uses subsymbolic AI a challenge. Since neurosymbolic AI combines the advantages of both symbolic and subsymbolic AI, this survey explores how neurosymbolic applications can ease the V&V process. This survey considers two taxonomies of neurosymbolic AI, evaluates them, and analyzes which algorithms are commonly used as the symbolic and subsymbolic components in current applications. Additionally, an overview of current techniques for the T&E and V&V processes of these components is provided. Furthermore, it is investigated how the symbolic part is used for T&E and V&V purposes in current neurosymbolic applications. Our research shows that neurosymbolic AI has great potential to ease the T&E and V&V processes of subsymbolic AI by leveraging the possibilities of symbolic AI. Additionally, the applicability of current T&E and V&V methods to neurosymbolic AI is assessed, and how different neurosymbolic architectures can impact these methods is explored. It is found that current T&E and V&V techniques are partly sufficient to test, evaluate, verify, or validate the symbolic and subsymbolic part of neurosymbolic applications independently, while some of them use approaches where current T&E and V&V methods are not applicable by default, and adjustments or even new approaches are needed. Our research shows that th

关键词： Neural networks

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：