检索结果-内蒙古大学图书馆

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Annepu Sai Charan Dennis Singh Moirangthem Dept. of Computer Science and Engineering IIIT Manipur Imphal India

The paper presents a dual-model approach that can be used for categorizing the work experience data from resumes or other textual copra. The application tracking system (ATS), which is the main tool used to screen resumes, presents operational issues in the quickly changing software sector. Although this technique matches resumes with job descriptions effectively, it requires separate scans for every job posting, which could result in errors and inefficiencies. This initiative is motivated by the need to expedite the hiring process for tech companies and potential employees. The suggested approach presents a cutting-edge tool to improve and expedite job matching and resume analysis. The work attempts to improve the software industry’s hiring process efficiency by overcoming present system restrictions. This study presents a novel solution—a text classification model intended for resume analysis and shortlisting to address the operational difficulties with the modern resume screening process. Even though the Application Tracking System (ATS) is currently used, it requires separate scans for every job posting, which could lead to inefficiencies. We propose dual-model architecture which includes our custom Name Entity Recognition (NER) Model which is trained on annotated work experience data and a Multi-Layer Perceptron (MLP) model for multi label classification, aiming to streamline the resume screening process. This dual-model approach enhances accuracy and efficiency in resume classification, benefiting both aspirants and tech companies. This research is a pivotal step in optimizing recruitment in the dynamic software industry. The complete work can be found on GitHub 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiple language Discovery Abuse of Cyberspace with Advanced Transformer Architecture

Multiple language Discovery Abuse of Cyberspace with Advance...

引用

IoT, Communication and Automation Technology (ICICAT), International Conference on

作者： Arvind Singh Abhinandan Tripathi Dept. of Computer Science & Engineering Buddha Institute of Technology Gorakhpur

ISBN: (数字)9798350368109

ISBN: (纸本)9798350368116

The number of reported instances of cyber abuse has also increased in tandem with the growth in the quantity of people that are regularly using the internet. Users' online freedom and privacy are jeopardized by such occurrences. Traditionally, the removal of such content from the internet has been accomplished through manual moderation and reporting systems. This strategy has, however, certain drawbacks, such as a reliance on people, longer delays, and less privacy for data. Traditional recurrent sequence models and supervised machine learning have been used in previous attempts to automate this procedure, but they have a tendency to perform badly on non-English material. A versatile solution that can handle multilingual text is urgently needed, given the increasing diversity of consumers using the internet. Moreover, translations frequently lose important context and emotion from content written in vernacular languages. In this work, we offer a generative deep learning based method for the detection of cyber abuse throughout Hindi, English with mixed codes, and Hindi text. The method uses bidirectional transformer-based BERT *** the TRAC-1 standard aggressiveness identification task, the suggested architecture can get extremely positive outcomes on the task leaderboard for English and accomplish cutting-edge performance on the Hindi dataset with mixed codes. The outcomes show that the new strategy is superior to the current ones because they were obtained without the need of numerous models or ensemble-based methods. Effective models that utilize deep learning techniques to analyze multilingual text can process a wider variety of inputs, making them indispensable in combating these types of social ills.

关键词： Deep learning Privacy Codes Translation Text categorization Manuals Transformers Natural language processing Multilingual Standards

来源：评论

学校读者我要写书评

暂无评论

Classification of Foods based on Bijective Soft Set

Classification of Foods based on Bijective Soft Set

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Priyanka Das Rupam Bhattacharya Dept. of Computer Application and Science Institute of Engineering & Management Kolkata

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cuisine data is typically classified using images of the cuisine, cooking methods, cooking utensils, and, most importantly, ingredients. The vast amount of recipe data available on the internet necessitates the creation of specialised systems for storing, retrieving, and effectively utilising stored knowledge and data. Neural networks based expert systems are steadily being used to classify the cuisine data. But it lacks in dealing the vagueness present in the categorical cuisine data. Also, most of the popular recipes available online are mostly unhealthy. As a result, the Bijective soft set theory has been introduced into this study since it is an intelligent method for developing classification rules from food data and then recognising ambiguity and data reliance. The classification guidelines also address the necessity to select healthy/nutritious meals. The investigation outcomes from using bijective soft set analysis to a set of data samples are presented and appraised in this work. Furthermore, the classification rules derived from this approach provides valuable help for developing food recommendation systems. The accuracy of this classification scheme has got really influenced by application of the bijective soft set when compared to other state-of-the-art classifiers.

关键词： Accuracy Neural networks Set theory Expert systems Recommender systems Guidelines

来源：评论

学校读者我要写书评

暂无评论

Infrared-Based Gender Recognition from Facial Images: A Comparative Study Using Deep Learning 2

Infrared-Based Gender Recognition from Facial Images: A Comp...

引用

2nd International Conference on Optical Imaging and Measurement, ICOIM 2023

作者： Cao, Zhicheng Qin, Guoli Zhao, Heng Schmid, Natalia Pang, Liaojun Xidian University School of Life Science and Technology Xi'an China West Virginia University Lane Dept. of Computer Science and Electrical Engineering MorgantownWV United States

ISBN: (纸本)9798350358636

The gender is an important soft biometric trait of a person, upon which many social and economic functionalities depend or rely. Automatic recognition of the gender of individuals is crucial to many real-world applications, such as public video surveillance, gender-specific access and services, human-computer interaction, demographical studies. Up until now, most research works on gender recognition focus on the visible light, leaving the problem of infrared-based gender recognition scarcely studied. Thus, this research work studies IR facial images-based gender recognition, using deep learning models. We design a CNN model on top of ResNet using a multiscale technique (named as IR-GenderNet). Then, we compare the performance of gender recognition between the visible light and IR bands. We also compare the performance of IR-GenderNet against other methods in the literature that are either traditional or deep learning-based. Experimental results demonstrate that gender recognition using IR is not just feasible but even more beneficial than visible light. It is also proven that the proposed model of IR-GenderNet performs better than all other methods for the problem of IR-based gender recognition. Lastly, cross-dataset experiments also justify the generalization ability of IR-based gender recognition using the proposed algorithm. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Impact of Non-Code Text Block on Java Code Quality: Multi-Model Framework

Quantifying the Impact of Non-Code Text Block on Java Code Q...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Sriharsha VVS Pranav B Nair Akarsh S.V Nakka Narmada Peeta Basa Pati Dept. of Computer Science & Engineering Amrita School of Computing Bengaluru India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Non-code elements in programming, such as comments, documentation, and whitespace, play a crucial role in improving code readability, maintainability, and collaboration. However, their inclusion introduces overhead affecting code processing tools such as compilers and interpreters and static analyzers. In essence, this study investigates the impact of non-code blocks on the performance metrics of time complexity, space complexity, and execution time. A regression model was used to analyze the proportion of non-code elements in Java code and their effect on the performance metrics. The impact is quantified with the aim of providing empirical insights into how the density of non-code affects performance. Such findings are intended to help Java developers make decisions regarding code structuring and documentation while balancing aspects of maintainability and efficiency. The model's performance is validated by achieving an R2 score of 0.67, which demonstrates an improvement over previous methods and highlights its potential for real-world educational applications.

关键词： Dimensionality reduction Java Codes Reviews Transfer learning Documentation Robustness Integrated circuit modeling Time complexity Testing

来源：评论

学校读者我要写书评

暂无评论

Call Translator with Voice Cloning Using Transformers

Call Translator with Voice Cloning Using Transformers

引用

International Conference for Convergence of Technology (I2CT)

作者： Nawaz Fateen Khan Nandan Hemanth Navyae Goyal Pranav KR Pooja Agarwal Computer Science Engineering Dept. PES University Bangalore India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

Voice Cloning employs technology and algorithms to create an artificial or synthetic reproduction of a person’s voice. To understand and mimic the distinct vocal qualities of the target speaker, including tone, pitch, cadence, and pronunciation, a machine learning model must be trained on audio samples of the speaker. This project presents itself as a revolutionary approach to the enduring problem of successful cross-lingual interactions, the paper’s novel approach to speech-to-speech machine translation that incorporates voice cloning. This method allows us to synthesize speech in the target language while maintaining the original speaker’s vocal characteristics. The model algorithms such as Whisper AI(WER 5% for transcription, No-Language-Left-Behind-200(44% more accurate than other models) for translation, Tacotron for speech synthesis and multiple transformers for voice cloning will be incorporated. The Voice Cloning model operates effectively on unseen voices, transcending the limitations of voice cloning will be incorporated. The voice cloning model operates effectively on unseen voices, transcending the limitations of relying solely on pre-trained models. The model successfully clones users’ voices in a different language with an approximate latency of 10 seconds.

关键词： Machine learning algorithms Navigation Cloning Speech recognition Machine learning Linguistics Transformers

来源：评论

学校读者我要写书评

暂无评论

Optimizing CNN Using HPC Tools

arXiv

引用

arXiv 2024年

作者： Rahman, Shahrin Dept. of Computer Science and Engineering Brac University Dhaka Bangladesh

With its vast range of applications, including object recognition, image classification, and pattern recognition, the Convolutional Neural Network (CNN) algorithm has brought about a paradigm shift in the field of computer vision. How- ever, training massive CNN models requires a lot of computational power, which can be efficiently handled by using high- performance computing (HPC) techniques. The CNN method is optimized in this paper using HPC technologies to increase its effectiveness. By utilizing multi-core processors, graphics processing units (GPUs), and parallel computing frameworks like OpenMPI and CUDA, the proposed approach makes use of distributed computing and parallel processing techniques to speed up the training of the CNN model. Using benchmark datasets, a thorough assessment of the optimization strategy is carried out, demonstrating considerable improvements in the CNN algorithm’s performance and training time. Additionally, a comparison of the suggested approach with alternative optimization strategies is conducted, demonstrating its superiority in terms of training time and performance. Overall, this study persuasively demonstrates how HPC technologies may be used to refine the CNN method, resulting in faster and more accurate training of large-scale CNN models. The proposed method has the potential to be more broadly applicable to various deep learning algorithms, which is significant since it will develop effective and efficient machine learning *** Codes N/A © 2024, CC BY-NC-SA.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Intelligent Route Planning for Post-Earthquake Rescues Using IoT

Intelligent Route Planning for Post-Earthquake Rescues Using...

引用

International Conference on Electrical engineering and Information & Communication Technology (ICEEICT)

作者： Rahat Tamzid Ehfaz Faisal Mahee Ashikur Rahman Tahira Akhtar Tamanna Muntasir Rahman Md. Mamun Hossain Dept. of Computer Science and Engineering Bangladesh University of Business and Technology

ISBN: (数字)9798350385779

ISBN: (纸本)9798350385786

Starting rescue operations quickly after an earth-quake is the best way to save lives in such disasters. In the case of large-scale earthquakes, current post-earthquake response systems cannot determine which building or rescue route would save the most lives due to the lack of real-time data availability. Research gaps include a lack of automation in earthquake damage assessment of buildings, location identification, and estimation of the number of trapped people. To fill these gaps, this article proposed an innovative solution using advanced sensors and cloud services for post-earthquake rescue route planning systems. This system aims to improve rescue operations to save the maximum number of lives in the shortest time and minimize impacts by optimizing resource allocation and overall response efficiency. By filling the existing research gap, our system seeks to provide more responsive and effective solutions to post-earthquake emergencies. Tested in a simulated environment with 16 samples, our system successfully collects and processes data from IoT devices deployed in buildings, classifies structural damage, and estimates the number of people affected. Our approach significantly reduces the time required to initiate rescue operations by providing rescuers with optimized routes to disaster sites, which has potential implications for disaster management strategies.

关键词： Navigation Disasters Earthquakes Buildings Sensor systems Real-time systems Planning

来源：评论

学校读者我要写书评

暂无评论

A High Throughput Bloom Filter Based TCAM Architecture for Fast NIDS

A High Throughput Bloom Filter Based TCAM Architecture for F...

引用

Smart Electronics and Communication Systems (ISENSE), International Conference on

作者： Sameera Shaik Noor Mahammad SK. Dept. of Computer Science and Engineering IIITDM Kancheepuram Chennai Tamilnadu

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528133

One of the computationally most intensive tasks of an Network Intrusion Detection System (NIDS) is string/pattern matching where the payload of incoming packet is compared against predefined rule-set in order to detect any intrusion or threat. Although, various software algorithms and hardware architectures have been proposed to accelerate the performance of NIDS, wire-speed matching of these patterns still remains as a challenge. TCAMs are popularly used in many networking applications as they can perform the pattern matching in single clock cycle, but they always suffer with high power dissipation and delay due to their complex circuitry. Hence, most of the research focuses on efficient utilization of TCAM to cope up with high-speed links. In this paper, a high-throughput TCAM based architecture employed with Bloom filters is proposed. When a Bloom filter is deployed with TCAM, the number of patterns to be matched on TCAM reduces significantly since most of the patterns are eliminated in the prefiltering stage. There exist various Bloom filters such as Standard Bloom filter [1], Cuckoo filters [2], Counting Bloom filters [3] and Compressed filters [4]. Our proposed variant of Bloom filter outperforms all the existing filters in terms of speed while using less memory. We performed experiments on widely used open-source Snort NIDS and the proposed approach is able to achieve a throughput of 128Gbps for version 3.0c and 77.5Gbps for version 2.9.17.

关键词： Filters Memory management Software algorithms Throughput Software Power dissipation Delays Pattern matching Standards Clocks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Fake News Detection Model: Bagging and Logistic Regression Approach

Hybrid Fake News Detection Model: Bagging and Logistic Regre...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Shivam Kumar Naveen Kumar Tiwari Abhishek Bajpai Shashank Yadav Dept. of Computer Science and Engineering Rajkiya Engineering College Kannauj Kannauj UP India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

In Today’s world or from Past Scenario’s Fake News has a Huge Impact on Everyone’s Lives including Politics, Sports, Education, External Foreign Affairs, Defense, etc. This project aims to develop a model for identifying and detecting fake news. In this model, we implement an ensemble method that leverages the TF IDF vectorization technique to extract meaningful textual features and employ a Bagging Classifier with Logistic Regression as the base estimator to enhance classification accuracy. To build this classifier, we utilized the scikit learn library. Our work was implemented using Jupyter Notebook, an online platform. For feature extraction, we employed a well-known vectorizer called Term Frequency Inverse Document Frequency (TF-IDF). We split our data into training sets (75%) and test sets (25%). The proposed model achieves an accuracy of 99.15% on the test dataset, with a precision of 99.45%, a recall of 99%, and an F1-score of 99.17%. It outperforms standalone Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting classifiers.

关键词： Training Logistic regression Accuracy Social networking (online) Feature extraction Boosting Ensemble learning Fake news Bagging Random forests

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：