检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yang, Yifei Wu, Hongqiu Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (纸本)9782493814104

Named Entity Recognition (NER) is a cornerstone natural language processing task while its robustness has been given little attention. This paper rethinks the principles of the conventional text attack, as they can easily violate the label consistency between the original and adversarial NER samples. This is due to the fine-grained nature of NER, as even minor word changes in the sentence can result in the emergence or mutation of any entity, producing invalid adversarial samples. To this end, we propose a novel one-word modification NER attack based on a key insight, NER models are always vulnerable to the boundary position of an entity to make their decision. We thus strategically insert a new boundary into the sentence and trigger the victim model to make a wrong recognition either on this boundary word or on other words in the sentence. We call this attack Virtual Boundary Attack (ViBA), which is shown to be remarkably effective when attacking both English and Chinese models with a 70%-90% attack success rate on state-of-the-art language models, and also significantly faster than previous methods. We share the code in https://***/yangyifei729/ViBA. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Denial of Service (DoS) Attack Detection Using Feed Forward Neural Network in Cloud Environment 2

Denial of Service (DoS) Attack Detection Using Feed Forward ...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Kalpana, Ponugoti Srilatha, P. Krishna, Gudepu Sai Alkhayyat, Ahmad Mazumder, Debarshi Avn Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Chaitanya Bharathi Institute of Technology Department of Ai & Ds Hyderabad India Anurag University Department of Information Technology Hyderabad India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ai & Ds Bengaluru India

ISBN: (纸本)9798350373110

In the recent years, the Denial of Service (DoS) developed as a big security threats for networks. Preventing as well as identifying DoS attacks is a big task within the industries. There are IoT of existing methods are there to identify DoS attacks and minimize the damage. However, many of these methods do not efficiently distinguish noise from a signal. This research focuses on addressing the DoS problem and introduces a method called Feed forward Neural Network (FNN). First, the KDD cup 99 data set goes through a preprocessing step where data normalization is processed using Min-Max normalization which standardizes the data points values. This normalized data is then passed to the whale optimization method which selects the relevant features making the classification system easier. The selected features are then used by an FNN classifier to differentiate between normal and attacked data. The proposed method is implemented and simulated on MATLAB and tested experimentally resulting to a detection accuracy of 0.99. The proposed FNN classifier is compared with the existing classifiers such as Auto-encoder and LSTM where it outperformed in detecting DoS attacks efficiently. © 2024 IEEE.

关键词： auto-encoder denial of service feed forward neural network min-max normalization whale optimization

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Brain Tumor Using Machine Learning 3

Detection and Classification of Brain Tumor Using Machine Le...

引用

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

作者： Kale, Prachi V. Gadicha, Ajay B. Dalvi, G.D. P R Pote College of Engineering & Management Department of Computer Science and Engineering Maharashtra Amravati India P R Pote College of Engineering & Management Department of AI Maharashtra Amravati India Allard College Department of EXTC Maharashtra Pune India

ISBN: (纸本)9798350391565

Diagnosing a brain tumor typically necessitates the expertise of a radiologist, whose skills and knowledge are essential to the process. Since the overall number of individuals has grown, so too has the quantity of medical data required to be managed, rendering outdated methods extremely costly and inefficient. Many investigators looked into different techniques that had been quick and effective in identifying and categorizing brain tumours. Currently, Machine learning (ml) techniques have gained popularity in the development of computerized systems that can quickly and effectively diagnose or segment brain tumours. The deep learning (DL) enables the application of ml frameworks for brain tumor identification. This paper proposed various ml models to analyze the MRI images. First, preprocessing and augmentation algorithms were applied to the MRI brain images. We evaluated the performance of several models, including LR, SVC, kNN, NB, NN, RF, and K-means clustering. The analysis focused on accuracy, precision, recall, F1-score, and AUC. LR (96%), NN (95%), and RF (96%) showed the highest performance across all metrics, effectively distinguishing between tumor and no-tumor images and providing reliable results. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Bayesian Belief Network Analysis for SPAD System in Railways 4

Bayesian Belief Network Analysis for SPAD System in Railways

引用

4th International Conference on Multimedia Processing, Communication and Information Technology, MPCIT 2024

作者： Krishnamurthy, Manjunath Sargur Rahul, Bommisetty Bondala, Chandrahas Reddy Reddy, M. Vishnu Vardhan Magha Raghul, G. Ambika, B.J. JP Morgan & Chase Co. HoustonTX United States BMS Institute of Technology and Management Dept. of AI&ML Bengaluru India Manipal Institute of Technology Bengaluru Dept. of Computer Science and Engineering Karnataka Manipal576104 India

ISBN: (纸本)9798350375466

Even with a powerful network of signaling and warning systems in the country, there have been many examples of trains crossing the red signal due to various factors, even today. These occurrences, known as Signal Passed At Danger (SPAD) events, could potentially result in severe consequences such as train derailments, train collisions, infrastructure collisions, and other dangerous events. Traditionally, these events have been analyzed using the Fault Tree Analysis (FTA) approach Bayesian Network (BN) is considered to be a better model to represent this situation when it comes to handling complexity. Bayesian Network allows for integration and includes systematic knowledge about the system, which helps to get a very flexible concise, and simple graphed representation. This study demonstrates applications of Bayesian Belief Networks (BBN) analysing and enlightening the Signal Passed at Danger (SPAD) system in railway processes. Execution of BBN offers more dynamic and flexible models compared to outmoded Fault Tree Analysis (FTA), struggling with complexity. BBN efficiently catches the inter dependencies between factors that are contributing to SPAD events, such as signal conditions, human errors, and mechanical issues. Over simulations and probability calculations using OpenMarkov software, Study revealed key intuitions, such as identifying highly risk apparatuses within SPAD system. The outcomes include enhanced risk calculation accuracy and recommendations for improving signal systems and safety protocols. These conclusions contribute to a safer and reliable railway structure, highlighting the success of BBN for complex, safety critical systems in real world applications. © 2024 IEEE.

关键词： Derailments

来源：评论

学校读者我要写书评

暂无评论

Comparing Fine Tuned-LMs for Detecting LLM-Generated Text 3

Comparing Fine Tuned-LMs for Detecting LLM-Generated Text

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Shukla, Sanidhya Madhav Magoo, Chandni Garg, Puneet Manav Rachna University Computer Science and Engineering dept. Faridabad India Kiet Group of Institutions Department of CSE-AI U.P. Ghaziabad India

ISBN: (纸本)9798331518592

With the introduction of LLMs (Large Language Models), NLP has demonstrated strong skills in a variety of applications, including question answering, language translation, and text summarization. As a result, their use in our day-to-day activities and at work has gained general acceptability. It is nevertheless imperative to develop cutting-edge procedures or approaches since, despite their enormous capabilities, they are still unable to live up to human expectations. It is crucial to apply the cutting-edge methods that enable LLMs to specialize in specific fields and reduce any potential for abuse. In contrast, our study has concentrated on employing fine-tuned LLM as detectors to determine whether a text was produced by a machine or by a person. Comparing how well various fine-tuned LMs function as content detectors-that is, as indicators of whether or not material is generated by LLMs-is the goal of this research. Three distinct fine-tuned LLMs are used to solve this binary classification problem: Fas'I'Text, also known as Generative Pre- Trained Transformers;DistilBERT;and BERT, or Bidirectional Encoder Representations from Transformers. The models were tested using various performance metrics, including precision, recall, Fl score, MCC, NPV, and FDR. The results showed that the BERT model outperformed the FasTText and DistilBERT models, which displayed overfitting tendencies when fine-tuned under comparable settings. © 2024 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning in Mental Diseases Diagnosis 25

Application of Machine Learning in Mental Diseases Diagnosis

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Alsawi, Rahaf Alazaidah, Raed Samara, Ghassan Alzoui, Haneen Alidmat, Omar Elsoud, Esraa Abu Talat Khouj, Mohammed Katrawi, Anwar Alluwaici, Mo'Ath Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Applied Science Private University Faculty of Information Technology Department of Computer Science Amman Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Zarqa University Faculty of It Department of Computer Science Zarqa Jordan

ISBN: (纸本)9798331540012

Mental diseases, mental disorders, or psychological disorders is a large group of symptoms which causes changes to the state of mood and reflect this on the behavior of the person with the mental disorder. It affects the patient's way of thinking, which limits his ability to perform his simple daily needs, and thus, becomes a burden on the individual, and on the surrounding society as well. There are common types of mental disorders such as depression, anxiety disorders, schizophrenia, and bipolar disorder. In this research, two main objectives are considered. The first objective is determining which is the best classifier for predicting a person's mental disorder among six well-known classifiers. The second objective is determining what is the best feature selection technique to use with mental disorders datasets considering six popular techniques, and with respect to several evaluation metrics. The results revealed that Logistic Regression and Naïve Bayes are the two best classification models, while Info Gain Ratio is the best feature selection method. © 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

Detection and Classification of Arrhythmia Using Hybrid Deep Learning Model

Detection and Classification of Arrhythmia Using Hybrid Deep...

引用

Next Generation Electronics (NEleX), International Conference on

作者： Trinaya Kodavati M Rithani K Venkatraman SyamDev R S Department of Computer Science & Engineering Amrita School of Computing Chennai India Department of AI-ML New Horizon College of Engineering Bangalore India

Cardiovascular disorders, encompassing arrhythmias rhythms, represent noteworthy worldwide health issues that necessitate prompt identification and precise categorization to facilitate efficacious therapeutic measures. This study examines the status of the field's research at the moment, going into cardiac arrhythmias' physiological foundation, clinical ramifications, and diagnostic resources. The paper proposes a methodology that combines MobileNet V1 with Gated Recurrent Unit (GRU) for the detection and classification of Arrhythmia, which has achieved an accuracy of 99.4%, recall score of 0.98 and precision score of 0.99. The MIT-BIH Arrhythmia dataset, consisting of recordings by the BIH Arrhythmia Laboratory, is utilized for training and validation of the model. The findings demonstrate the potential of using the MobileNetV1+GRU model for detection and classification of different types of Arrhythmia, which can be applied for diagnosis in hospitals, clinics, emergency departments and screening programs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedded Language Translation Based on GRU Gated Attention Model

Embedded Language Translation Based on GRU Gated Attention M...

引用

Data science, Agents & Artificial Intelligence (ICDSAai), International Conference on

作者： Tharun A.P Tharun J.S Dr. D. Anu Disney Department of CSE With AI & Ml Sathyabama Institute of Science & Technology Chennai Tamilnadu India Department of Computer Science Sathyabama Institute of Science & Technology Chennai Tamilnadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The project "Embedded Language Translation Based on GRU Gated Attention Model" aims to develop an advanced machine translation system that seamlessly integrates Gated Recurrent Units (GRUs) with sophisticated attention mechanisms. This innovative model is specifically designed to handle sequential data effectively, addressing the common challenges of translating long sequences and maintaining contextual accuracy. By leveraging the selective focus capabilities of the attention mechanism, our system ensures more precise and contextually relevant translations. The comprehensive methodology includes meticulous data collection and preprocessing, model design and training, rigorous evaluation and fine-tuning, and seamless integration into resource-constrained environments such as mobile devices and IoT platforms. The ultimate goal is to deliver a robust, scalable, and high-performance embedded translation solution that can operate in real-time, thereby breaking language barriers and enhancing global communication.

关键词： Training Translation Attention mechanisms Accuracy Logic gates Data models Real-time systems Mobile handsets Machine translation Context modeling

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Diagnosis Using the Brute Force Algorithm and Machine Learning Techniques

引用

computers, Materials & Continua 2022年第8期72卷 3195-3211页

作者： Junaid Rashid Samina Kanwal Jungeun Kim Muhammad Wasif Nisar Usman Naseem Amir Hussain Department of Computer Science and Engineering Kongju National UniversityCheonan31080Korea Department of Computer Science COMSATS University IslamabadWah Campus47040Pakistan School of Computer Science University of SydneySydneyNSW 2006Australia Centre of AI and Data Science Edinburgh Napier UniversityEdinburghEH114DYUK

Heart disease is one of the leading causes of death in the world *** of heart disease is a prominent topic in the clinical data *** increase patient survival rates,early diagnosis of heart disease is an important field of research in the medical *** are many studies on the prediction of heart disease,but limited work is done on the selection of *** selection of features is one of the best techniques for the diagnosis of heart *** this research paper,we find optimal features using the brute-force algorithm,and machine learning techniques are used to improve the accuracy of heart disease *** performance evaluation,accuracy,sensitivity,and specificity are used with split and cross-validation *** results of the proposed technique are evaluated in three different heart disease datasets with a different number of records,and the proposed technique is found to have superior *** selection of optimized features generated by the brute force algorithm is used as input to machine learning algorithms such as Support Vector Machine(SVM),Random Forest(RF),K Nearest Neighbor(KNN),and Naive Bayes(NB).The proposed technique achieved 97%accuracy with Naive Bayes through split validation and 95%accuracy with Random Forest through *** Bayes and Random Forest are found to outperform other classification approaches when accurately *** results of the proposed technique are compared with the results of the existing study,and the results of the proposed technique are found to be better than other ***,our proposed approach plays an important role in the selection of important features and the automatic detection of heart disease.

关键词： Heart disease brute force machine learning feature selection

来源：评论

学校读者我要写书评

暂无评论

Scalable Cloud-Integrated Analytics and Visualization for Real-Time Smart Grid Management 7

Scalable Cloud-Integrated Analytics and Visualization for Re...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Santosh Kumar, B. Rangaiah, Yagateela Pandu Singh, Navdeep Reddy, K. Jyothsna Al-Rubaye, Taqi Mohammed Khattab Raju, K. Butchi New Horizon College of Engineering Department of Computer Science Engineering Bangalore India Institute of Aeronautical Engineering Department of Electronics and Communication Enfineering Dundigal Hyderabad500043 India Lovely Professional University Phagwara India Mlr Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India The Islamic University College of Medical Technologies Department of Medical Laboratory Technology Najaf Iraq Griet Department of Cse Bachupally Telangana Hyderabad India

ISBN: (纸本)9798350350067

The installation of new smart technologies has been growing exponentially, resulting in the creation of a large quantity of diverse data which require sophisticated tools for analysis. This paper presents CloudVIZ-GRID as a new cloud-based visual analytical framework that was developed to accommodate the severity of the big data issues in smart grids. CloudVIZ-GRID combines simple web-based grid accounts with up-to-date visualization tools and high-processing power to give a real time snap shot and 'finger on the pulse' of grid performance and operations, or deviations in energy usage. Using distributed data processing engines, CloudVIZ-GRID can process high velocity data feeds, and with limited latency deliver analytics output. Moreover, the application of the machine learning algorithms within the framework strengthens the predict ability and thus pre-empts the management of the grid. This study lays emphasis on the importance of addressing the issues of computation, which is even more challenging in case of complex systems such as smart grids;use of cloud based solutions enable the conversion of huge amount of data available in smart grid into valuable insights that can be helpful for grid operators and players in the energy sector. Due to having a modular structure, the CloudVIZ-GRID has the ability to change to fit future possible grids and additions, making it an essential part of the growing smart grid applications. © 2024 IEEE.

关键词： Cloud analytics

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：