检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Bhut, Shubham Kumar, Krishan Chugh, Tinkle Sahlot, Pankaj National Institute of Technology Kurukshetra Department of Mechanical Engineering Kurukshetra India National Institute of Technology Kurukshetra Department of Computer Engineering Kurukshetra India University of Exeter Department of Computer Science United Kingdom

ISBN: (纸本)9798350369960

The laser Powder Bed Fusion (LPBF) process has recently become popular due to its ability to manufacture complex shapes with high precision. Among the various alloys for LPBF, AlSi10Mg stands out differently due to its lightweight nature, corrosion resistance, and design flexibility. The two important quality indicators for LPBF manufactured parts are surface roughness and Energy density, which should be within optimal range to ensure high-quality production. This study aims to improve this optimization process through a new approach - using a machine-learning model to predict the requisite laser energy density to manufacture AlSi10Mg. The study utilized machine learning models that were trained using four input parameters: Laser Power (W) Scan Speed (mm/s) Hatch Spacing (microns) and Layer Thickness (microns). Four different machine learning models were employed to predict the required Energy Density: Linear regression, Poisson regression XGBoost and ExtraTrees regression. The Poisson regression model yielded the results with an RMSE value of 11.13 and an R square value of 0.99. The XGBoost gradient boosting model also achieved outcomes with an RMSE of 52.18 and R values of 0.94. Overall, the trained machine learning models proved effective, in predicting the optimal energy density necessary for LPBF thereby enhancing manufacturing process accuracy and quality. © 2023 IEEE.

关键词： Additive manufacturing AlSi10Mg Laser Powder Bed Fusion Machine learning Optimization

来源：评论

学校读者我要写书评

暂无评论

Facial emotion recognition using convolutional neural networks

引用

Materials Today: Proceedings 2023年 80卷 3560-3564页

作者： Sarvakar, Ketan Senkamalavalli, R. Raghavendra, S. Santosh Kumar, J. Manjunath, R. Jaiswal, Sushma Information Technology Department U.V. Patel College of Engineering Ganpat University Gujarat Mehsana384012 India CSE Department East Point College of Engineering Bangalore India Department of Computer Science and Engineering School of Engineering and Technology Christ Deemed to be University Bengaluru560074 India Department of Computer Science and Engineering K S School of Engineering and Management Bengaluru56019 India Department of Computer Science and Engineering R R Institute of Technology Bengaluru560090 India Bilaspur495009 India

Emotional expressivity has always been a simple job for people, but computer programming is much harder to accomplish. Image emotions may be recognised by recent developments in computer vision and machine learning. In this article, we present a new method to detect face emotion. Use neural networks convolutionary (FERC). The FERC is based on a CNN network of two parts: the first portion removed the backdrop of the image, the second part removed the face vector. The expressional vector (EV) is utilised in the FERC model to detect the fve different kinds of regular facial expressions. The double-level CNN is continuous and the weights and exponent values of the final perception layer vary with each iteration. In that it improves accuracy, FERC varies from widely utilised CNN single-level technology. Moreover, EV generation prevents the development of a number of issues before a new background removal process is used (for example distance from the camera). © 2021

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Robust multi-domain descriptive text classification leveraging conventional and hybrid deep learning models

引用

International Journal of Information technology (Singapore) 2024年第5期16卷 3219-3231页

作者： Bhowmik, Shovan Sultana, Sharmin Sajid, Ahmed Arian Reno, Saha Manjrekar, Aakash Department of Computer Science and Engineering Bangladesh Army International University of Science and Technology Syedpur Bangladesh Department of Computer and Information Sciences University of Delaware Newark United States Department of Computer Science University of Massachusetts Lowell Lowell United States Vidyalankar Institute of Technology University of Mumbai Mumbai India

Since an unprecedented amount of online information in the form of unstructured texts is generated daily, researchers have started to focus on the development of robust mechanisms with the help of Natural Language Processing (NLP) and Artificial Intelligence (AI) to predict sentiments. Reliable sentiment classification models can not only avoid the spreading of misinformation but also help people to sieve genuine data by creating fact-checking tools on the user end. The main focus of this work is to investigate the performance of six conventional Deep Learning (DL) models followed by one hybrid DL model in three domains (fake news identification, spam filtering, and cyberbullying detection) of opinion mining tasks by employing efficient deep architectures capable of predicting sentiments even if long sentences are provided. Our empirical results show the rigid performance of all models on a corpus with maximum accuracy of 99.55%, 97.57%, and 93.00% for fake news, spam email, and cyberbullying domains accomplished by Convolutional Neural Network (CNN), Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) hybrid, and CNN models accordingly. Our work also exhibits a comparison of compilation times for every model to speed up the training time in this state-of-the-art. Contrary to the previous studies, we have taken long descriptive paragraphs for training purposes with a maximum length of 3336 words in a single sentence. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Artificial Neural Network Convolutional Neural Network Cyberbullying Fake News Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection Using Machine Learning Approaches: A Review 4th

Plant Disease Detection Using Machine Learning Approaches: A...

引用

4th International Conference on Data, engineering, and Applications, IDEA 2022

作者： Saraf, Puja Dipak Patil, Jayantrao Bhaurao Department of Computer Engineering R. C. Patel Institute of Technology Shirpur425405 India

ISBN: (纸本)9789819700363

Agriculture plays an important role in the country’s development, and it is the key source of food for the population of the world. But in developing countries like India, Pakistan and Nepal, the condition of the agriculture sector is getting worse day by day. There are many reasons behind it, but one of the reasons is the degeneration of crops by pests and disease. Agriculture solely depends on the biological health of the seeds, crops, information on weather conditions soils and biotic features liable for the crop diseases. Robust diagnostic methods are accomplished by dispensation and scrutinizing large quantities of records near get additional consistent material and ample more accurate predictions remain vital. Deep learning, image processing, soft computing and data mining are likely to play a vital role in recognizing plant diseases. This paper aims to review existing studies and investigations using the recent practices to solve a variety of agricultural problems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Weedbot: Weed Easy Extraction Using Deep Learning with a Robotic System 21

Weedbot: Weed Easy Extraction Using Deep Learning with a Rob...

引用

21st International engineering Research Conference 2024, EURECA 2024

作者： Ilangovan, P. Meena, K. Sharmila Begum, M. Department of Computer Science and Engineering Periyar Maniammai Institute of Science & Technology Tamil Nadu Thanjavur India

Weeds refer to plants that a farmer does not intentionally cultivate because they interfere with or limit the growth and yield of crops. Due to their fast reproduction and spreading, weeds are well-known for quickly increasing in population over large areas. From the very beginning of the agricultural revolution, weed control used to be done by hand but as time and technology advanced so did methods for managing unwanted plants. Human Intervention or using a single-row weed cutter, weeds are removed from fields. Due to the difficulties of eliminating the background class from the image and increasing the accuracy of the navigation system of the bot, as well as the fact that it does not support the technique of extracting weeds from paddy fields, a vehicle method for removing weeds from the field has not been created. These difficulties have been tackled by combining computer vision with automation, minimizing the need for human exertion. The project aims to create a robotic chopper that deal with weeds and employ CNN (Convolutional Neural Network) algorithm for image categorization of weeds and crops. We use image processing techniques in the proposed system to identify weeds. The system is trained with 590 images of weeds and crops, and testing is performed with 254 images. The system obtained an accuracy of 80% towards processing weeds and then chopped by the robotic arm. The robotic arm cutter that has great precision and is simple to operate, inexpensive and does not require hazardous chemicals. © Published under licence by IOP Publishing Ltd.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

TRIP NEGOTIATOR: A Travel Persona-aware Reinforced Dialogue Generation Model for Personalized Integrative Negotiation in Tourism

TRIP NEGOTIATOR: A Travel Persona-aware Reinforced Dialogue ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Priya, Priyanshu Yasheshbhai, Desai Vishesh Joshi, Ratnesh Kumar Ramnani, Roshni Maitra, Anutosh Sengupta, Shubhashis Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India Accenture Labs Banglore India

ISBN: (纸本)9798891761681

A sophisticated negotiation dialogue system for tourism should engage in negotiations beyond mere price considerations, encompassing various other aspects and amenities inherent in the tourism package. To ensure such tailored interaction, it is imperative to understand the intricacies of traveler preferences, constraints, and expectations. Incorporating these personality facets allows for customizing negotiation strategies, resulting in a more personalized and integrative experience. With this aim, we take a pivotal step in advancing automated dialogue systems for personalized integrative negotiation tasks. We develop DEAL, a pioneering Dialogue datasEt for personALized integrative negotiation task in the tourism domain. Further, we propose TRIP NEGOTIATOR, a novel Travel persona-aware Reinforced dIalogue generation model for Personalized iNtegrative nEGOTIATion within the tOuRism domain. TRIP NEGOTIATOR is built to discern the traveler's persona and intent, systematically adjusts negotiation strategies, and directs the negotiation toward a pertinent phase to ensure effective negotiation. Through reinforcement learning with Proximal Policy Optimization (PPO), we guide TRIP NEGOTIATOR to generate coherent and diverse responses consistent with the traveler's personality. Extensive qualitative and quantitative analyses demonstrate the effectiveness of TRIP NEGOTIATOR in generating personalized responses during negotiation. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

From Data to Dialogue: Building a Domain-Agnostic Conversational Question Answering System

From Data to Dialogue: Building a Domain-Agnostic Conversati...

引用

2024 IEEE International Conference on Information technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Patil, Pranav Mathews, Justin James, Joel Patil, Aditya Rukhande, Smita Fr. C. Rodrigues Institute of Technology Department of Computer Engineering Navi Mumbai India

ISBN: (纸本)9798350382693

In the realm of natural language processing (NLP), the quest for domain-specific question answering has been a focal point, emphasizing the precise extraction of factual information from designated knowledge sources in response to targeted inquiries. This project introduces a versatile, adaptable open-domain question answering system primed for seamless integration across diverse sectors, including educational institutions, e-commerce platforms, and healthcare portals. Leveraging the prowess of BERT and TAPAS, augmented with RAG (Retrieval-Augmented Generation), our system offers a holistic solution catering to varied information retrieval needs. Through fine-tuning on domain-specific datasets, both BERT and TAPAS capitalize on their respective strengths: BERT's contextual understanding and TAPAS's structured reasoning capabilities. The ensemble model dynamically selects the most suitable approach for each query, ensuring flexibility in handling diverse linguistic nuances and query types. Moreover, the system integrates language translation and voice output features to further enhance its adaptability. Evaluation on benchmark datasets reaffirms the system's efficacy in delivering precise and coherent responses, underscoring its potential as a multifaceted tool for enhancing user interaction and information retrieval across educational, ecommerce, healthcare, and other domains. © 2024 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Optimized Biometric Key Management System for Enhanced Security 11th

Optimized Biometric Key Management System for Enhanced Secu...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Kaur, Prabhjot Kumar, Nitin School of Computing DIT University Uttarakhand India Department of Computer Science and Engineering National Institute of Technology Uttarakhand India Department of Computer Science and Engineering PEC Deemed to be University Chandigarh India

ISBN: (纸本)9789819717231

Biometric cryptosystems are security tools that use an individual’s distinctive physical or behavioral characteristics to secure sensitive data. Any biometric cryptosystem’s effectiveness is dependent on how well the features are extracted. The suggested solution uses an evolutionary algorithm to first optimize the retrieved attributes. Second, fuzzy vault is used to safeguard these optimized features. The fuzzy vault system is a well-known biometric cryptography device that creates a vault by using a polynomial equation, protecting the biometric information. However, if an attacker has access to the polynomial equation, the security of the fuzzy vault scheme may be jeopardized. The shuffled frog leaping algorithm (SFLA) method has been suggested as a way to improve the security of the fuzzy vault technique in order to overcome this drawback. The SFLA is a meta-heuristic optimization method that resolves challenging optimization issues by simulating the social behavior of frogs. This meta-heuristic technique is used in this paper’s suggested strategy to produce and secure optimized points. The experiments are performed onn AMI and MMU2 databases. The results achieve higher levels of performance compared to the traditional schemes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging XGBoost based GBM for Proactive Detection of Man-in-the-Middle Cyber Attacks

Leveraging XGBoost based GBM for Proactive Detection of Man-...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Manjaragi, Shivanand V. Asrani, Deepak Kumar, Arvind Sandesh, R. Maindola, Meenakshi Sai, Aarush Department of Computer Science and Engineering Hirasugar Institute of Technology Karnataka Nidasoshi591236 India Department of Computer Science and Engineering MIET Uttar Pradesh Greater Noida India SCA MRIIRS Haryana Faridabad India Department of Computer Science and Engineering ATME College of Engineering Karnataka Mysuru India Department of Computer Science Engineering Graphic Era Deemed to be University Uttarakhand Dehradun India Department of CSBS Gyan Ganga Institute of Technology and Sciences Madhya Pradesh Jabalpur India

ISBN: (纸本)9798350374933

Man-in-the-Middle (MitM) cyber-attacks provide a substantial risk to network security, since they allow hostile individuals to intercept and alter communications between two parties. Conventional detection approaches frequently fail to recognize these complex threats, requiring the creation of more resilient and precise solutions. This study introduces a model called XGBoost-based Gradient Boosting Machine (GBM) to identify MitM attacks in advance. The system employs extensive datasets from Kaggle, namely CICIDS 2017 and UNSW-NB15, for the purpose of training and evaluating the model. By carefully preparing the data, selecting relevant features, and doing thorough cross-validation with hyperparameter optimization, the suggested model attains exceptional performance metrics. The assessment findings indicate an accuracy of 0.98, precision of 0.97, recall of 0.96, F1-Score of 0.965, and a remarkable ROC-AUC score of 0.99. Our model regularly outperforms existing technologies like as Random Forest and Traditional GBM in identifying MitM attacks, achieving higher performance metrics across the board. This research demonstrates the effectiveness of the XGBoost-based GBM model in improving cybersecurity defenses and suggests that it might serve as a standard for future advancements in cyber-attack detection systems. The suggested system's exceptional accuracy and resilience make it an invaluable tool for proactively detecting and reducing MitM attacks. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Machine Reading Comprehension Using NLP 1

引用

4th International Conference on computer Vision, High-Performance Computing, Smart Devices, and Networks, CHSN 2023

作者： Vineela, A. Devi, G. Lavanya Poojitha, M. Deepika, K. Department of Computer Science and Engineering GMR Institute of Technology Rajam India Andhra University Visakhapatnam India

ISBN: (数字)9789819777945

ISBN: (纸本)9789819777938

Machine Reading Comprehension (MRC) is a type of question-answering mechanism that involves reading documents and responding to questions. The challenge of enabling machines to effectively interpret paragraphs, comprehend related inquiries, and generate appropriate responses has long persisted. Unlike humans, who possess the ability to grasp the logic and intent behind a question and formulate a fitting reply, machines struggle with this task. Thus, the primary goal of this project is to leverage Natural Language Processing (NLP) to enable machines to read paragraphs, understand questions, and provide coherent answers. The input for the reading comprehension model is the question and the context. The passage’s answer is the model’s output. A sort of writing and reading comprehension (RC) is becoming more and more popular in the study of natural language processing (NLP). Datasets like SQUAD (Stanford question answer dataset) are used. Various models like BERT, and ELECTRA, are used to predict the answers to respective questions. There are a few models that can answer the questions in the Telugu language. In this analysis, the MRC is implemented in the Telugu language using BERT model. Although existing MRC models surpass humans on numerous benchmark datasets in English language comprehension, there remains a significant disparity between these models and real-world human-level reading comprehension. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Natural language processing systems

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：