检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hasan, Md. Mehedi Ibrahim, Muhammad Ali, Md. Sawkat Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Computer Science and Engineering Univeristy of Dhaka Dhaka Bangladesh

The performance of convolutional neural networks (CNN) depends heavily on their architectures. Transfer learning performance of a CNN relies quite strongly on selection of its trainable layers. Selecting the most effective update layers for a certain target dataset often requires expert knowledge on CNN architecture which many practitioners do not posses. General users prefer to use an available architecture (e.g. GoogleNet, ResNet, EfficientNet etc.) that is developed by domain experts. With the ever-growing number of layers, it is increasingly becoming quite difficult and cumbersome to handpick the update layers. Therefore, in this paper we explore the application of genetic algorithm to mitigate this problem. The convolutional layers of popular pre-trained networks are often grouped into modules that constitute their building blocks. We devise a genetic algorithm to select blocks of layers for updating the parameters. By experimenting with EfficientNetB0 pre-trained on ImageNet and using Food-101, CIFAR-100 and MangoLeafBD as target datasets, we show that our algorithm yields similar or better results than the baseline in terms of accuracy, and requires lower training and evaluation time due to learning less number of parameters. We also devise a metric called block importance to measure each block’s efficacy as update block and analyze the importance of the blocks selected by our algorithm. © 2023, CC BY-NC-ND.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Device Distribution Scheme of Random Access in Space-Air-Ground Integrated Network for Massive IoT 13

Device Distribution Scheme of Random Access in Space-Air-Gro...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Oh, Joohyun Park, Joohan Youn, Jiseung Im, Jeong-Ju Cho, Sunghyun Major in Bio-Artificial Intelligence Hanyang University Dept. of Applied Artificial Intelligence Ansan Korea Republic of Hanyang University Dept. of Computer Science & Engineering Ansan Korea Republic of Major in Bio-Artificial Intelligence Hanyang University Dept. of Computer Science & Engineering Ansan Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

To support massive random access trials of devices with diverse QoS is a major challenge for massive machine-type communications. Space-air-ground integrated network(SAGIN) can be a promising solution for the congestion issues because the SAGIN can extend preamble pool. In this paper, we propose a device distribution scheme to maximize random access success rate while conserving delay of the packet in SAGIN. The proposed scheme consists of two phases. One is an algorithm in which the device selects the appropriate SAGIN infrastructure to maximize the random access success rate. The other is an algorithm in which devices that have failed previous random access select an infrastructure different from the previously selected infrastructure to resolve congestion. We compare the performance of the proposed algorithm with two benchmark algorithms in terms of random access success rate and delay. © 2022 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning Methods for Bangla Text Emotion Analysis

Evaluating Machine Learning Methods for Bangla Text Emotion ...

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Tahmina Akter Mst. Sharmin Akter Tanjim Mahmud Dilshad Islam Mohammad Shahadat Hossain Karl Andersson Dept. of Computer Science and Engineering Port City International University Chittagong Bangladesh Dept. of Computer Science and Engineering Rangamati Science and Technology University Rangamati Bangladesh Dept. of Physical and Mathematical Sciences Chattogram Veterinary and Animal Sciences University Bangladesh Dept. of Computer Science and Engineering University of Chittagong Chittagong Bangladesh Cybersecurity Laboratory Luleå University of Technology Luleå Sweden

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

Text-based emotion identification goes beyond simple sentiment analysis by capturing emotions in a more nuanced way, akin to shades of gray rather than just positive or negative sentiments. This paper details our experiments with emotion analysis on Bangla text. We collected a corpus of user comments from various social media groups discussing socioeconomic and political topics to identify six emotions: sadness, disgust, surprise, fear, anger, and joy. We evaluated the performance of four widely used machine learning algorithms—RF, DT, k-NN, and SVM—alongside three popular deep learning algorithms—CNNs, LSTM, and Transformer Learning—using TF-IDF feature extraction and word embedding techniques. The results showed that among the machine learning algorithms, DT, RF, k-NN, and SVM achieved accuracy scores of 82%, 84%, 73%, and 83%, respectively. In contrast, the deep learning models CNN and LSTM both achieved higher performance with an accuracy of 85% and 86% respectively. These findings highlight the effectiveness of traditional ML and DL approaches in detecting emotions from Bangla social media texts, indicating significant potential for further advancements in this area.

关键词： Deep learning Support vector machines Technological innovation Sentiment analysis Machine learning algorithms Accuracy Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Learning with Feature Pairing and Mean Discrepancy

Few-Shot Learning with Feature Pairing and Mean Discrepancy

引用

Sustainable Computing and Smart systems (ICSCSS), International Conference on

作者： K K Singh K Hima Bindu dept. of Computer Science and Engineering NIT Andhra Pradesh and RGUKT Nuzvid India dept. of Computer Science and Engineering NIT AP India

Few-Shot Learning (FSL) is a sub-area of machine learning which mainly deals with data where there is a scarcity of training supervised samples. Few shot learning (FSL) more closely resembles the human brain in comparing new concepts to others based on prior experience rather than identifying it exactly. FSL aims to generalize the model across the tasks (in meta learning) opposed to the classical supervised learning which generalizes across the data points. In general the FSL models may suffer from underfitting because of scarcity of supervised samples and at the same time it causes overfitting as it is likely to memorize task specific features of the training set. This work aims to reduce such problems and is presented as a metric based model ”Few Shot Learning with Feature Pairing and Mean Discrepancy” (FL-FPMD). As the title suggests, feature pairing is one among various data augmentations. It is observed that flip augmentation is more suitable in the context of pairing the features within the given task. Memorizing task specific features is reduced by incorporating the discrepancy of mean distributions of the query and the support embedding in the loss function. The training and the evaluation is performed at the miniImageNet dataset and the results indicate that the proposed model outperforms the state-of-the-art models of similar complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Question-Answering with Knowledge Graph Retrieval and Generation using LLMs

Enhancing Question-Answering with Knowledge Graph Retrieval ...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Supraj Gijre Rishi Agrawal Priyash Laddha Gunjan Keswani Dept. Computer Science and Engineering Shri Ramdeobaba College of Engineering and Management Nagpur India School of Computer Science and Engineering Ramdeobaba University Nagpur India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

This paper describes a novel technique to improving Large Language Models (LLMs) for document analysis that employs knowledge graphs and retrieval-augmented generation (RAG). We are working on constructing a chatbot system that can handle and analyze large documents from a variety of fields. Our approach addresses basic LLM issues including context maintenance and hallucination avoidance. The system combines document chunking, vector embedding, and similarity search with graph-based knowledge representation. Users can upload large papers and answer questions accurately. We show that integrating standard information retrieval approaches with graph-based storage and LLM capabilities improves context awareness and response accuracy across a wide range of document genres. This strategy is especially promising for complicated publications such as financial reports.

关键词： Text analysis Quantum computing Large language models Soft sensors Retrieval augmented generation Knowledge graphs Information retrieval Vectors Maintenance Standards

来源：评论

学校读者我要写书评

暂无评论

BanglaGPT: A Generative Pretrained Transformer-Based Model for Bangla Language

BanglaGPT: A Generative Pretrained Transformer-Based Model f...

引用

Information and Communication Technology for Sustainable Development (ICICT4SD), International Conference on

作者： Md. Shahidul Salim Hasan Murad Dola Das Faisal Ahmed Dept. of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh Dept. of Computer Science and Engineering Chattogram University of Engineering & Technology Chattogram Bangladesh

Natural Language Processing (NLP) has entered a new era with the advent of pre-trained language models, paving the way for constructing robust language models. Pretrained transformer-based models such as GPT-2 have become prevalent due to their cutting-edge efficiency. However, these approaches rely heavily on resource-intensive languages, forcing other languages to adopt multilingual frameworks (mGPT). The mGPT model could perform better for low-resource languages such as Bangla because the model has been trained on a diverse dataset spanning multiple languages. Recent studies show that the language-specific GPT model outperforms the multilingual mGPT model. In this research, we have proposed a pretrained monolingual GPT model called BanglaGPT using the objective of causal language modeling (CLM). Due to the lack of available large datasets for NLP tasks in Bangla, we have created a Bangla language model dataset called BanglaCLM using a 26.24 GB Bangla corpus scraped from several public websites. We have used a subword-based tokenization algorithm named Byte-Pair Encoding (BPE) for Bangla and finally trained the Bangla-GPT2 model from scratch using the BanglaCLM dataset. Our pretrained BanglaGPT provides state-of-the-art performance for Bangla text generation with a perplexity score of 2.86 and a loss score of 0.45 on the test set.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resource Virtualization with End-to-End Timing Guarantees for Multi-Hop Multi-Channel Real-Time Wireless Networks

Resource Virtualization with End-to-End Timing Guarantees fo...

引用

Real-Time systems Symposium (RTSS)

作者： Jiachen Wang Tianyu Zhang Xiaobo Sharon Hu Song Han Dept. of Computer Science and Engineering University of Connecticut Storrs CT Dept. of Computer Science and Engineering University of Notre Dame Notre Dame IN

Resource virtualization is a promising technique that has been increasingly deployed in industrial automation systems to support multiple time-critical applications sharing the same physical resources. Extensive studies have been reported on how to perform real-time virtualization on computing resources. However, when applying virtualization techniques on network resources (especially for real-time wireless networks), node dependency among applications, wireless channel contention and stringent end-to-end timing requirements of the real-time flows in the network pose severe challenges. To address this problem, this paper formulates the network virtualization problem for multi-hop multi-channel real-time wireless networks (RTWNs). We first present a Satisfiability Modulo Theory (SMT)-based exact solution to capture the constraints posted by each application's resource interfaces and node dependency graphs. A novel supply graph (SG)-based partitioning framework, SGP, is then proposed to determine the resource partitions for individual applications. SGP uses supply graph to maintain compliance with the regularity constraints while efficiently allocating resources. Experimental results from both a real-world testbed and extensive simulations show that SGP can achieve comparable success ratio with the SMT-based exact solution but reduce the computational overhead significantly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Mobile Prices with Machine Learning Techniques

Predicting Mobile Prices with Machine Learning Techniques

引用

Computational Intelligence and Computing Applications (ICCICA), International Conference on

作者： Deepak Singh Rana Shiv Ashish Dhondiyal Sumeshwar Singh Sanjeev Kukreti Ashish Dhyani Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Dept. of Computer Science and Engineering Jaypee Institute of Information Technology Department of Hospitality Management Graphic Era Deemed to be University Dehradun Uttrakahnd

ISBN: (数字)9798350306446

ISBN: (纸本)9798350306453

Smartphones are increasingly vital to people on a daily basis. Telephones are utilized in all aspects of life, ranging from personal to professional, due to technological advancements. It serves a function beyond making phone calls. It enables internet connectivity and email reading. when not using the computer. The characteristics of a mobile phone are a crucial consideration when buying *** overall objective of this research is to find the best way to apply machine learning to estimate the retail pricing of smartphones based on their individual specs. Individuals who frequently use their phone are more attentive to selecting features. When purchasing a cell phone, a comparison is done based on the price-performance ratio. Phone features are regarded as performance. This research aims to forecast if mobile phones with certain features are considered economical or *** work is capable of being utilized in various marketing and business contexts to assist in making informed purchasing decisions by maximizing features while minimizing costs.

关键词： Support vector machines Machine learning algorithms Costs Machine learning Pricing Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Printable Fused Silica Based Microchamber Integrated With Graphene Chemi-Resistive Sensors For Direct On-Chip Soil Testing

Printable Fused Silica Based Microchamber Integrated With Gr...

引用

2023 IEEE Applied Sensing Conference, APSCON 2023

作者： Jose, Sabitha Ann Atwa, Yahya Mitchell, Neil Shakeel, Hamza Queen's University Belfast School of Electronics Electrical Engineering and Computer Science Belfast United Kingdom Umm Al-Qura University Dept. Electrical Engineering Makkah Saudi Arabia

ISBN: (纸本)9781665461634

In this study, we demonstrate a graphene-based portable gas sensor with an integrated fused silica micro chamber for direct on-chip sample injection to detect a low concentration (-10 ppm) of acetone from a soil sample at room temperature and pressure. A chemiresistive gas sensor was first fabricated by a conformal transfer process using a commercial monolayer graphene film. Printable fused silica micro gas chamber (internal volume of 50 microliter), fabricated separately, was permanently attached with the graphene chemiresistor using an ultra-violet light source. A relative resistance change of 1% (-20 ppm of acetone) was achieved by injection of a headspace sample for acetone calibration. This direct on-chip injection method shows an excellent potential for detecting volatile organic compounds from a soil sample without requiring complex sample extraction steps © 2023 IEEE.

关键词： Fused silica

来源：评论

学校读者我要写书评

暂无评论

Hybrid Software Reliability Prediction Model Using Feature Selection and Support Vector Classifier 4

Hybrid Software Reliability Prediction Model Using Feature S...

引用

4th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2022

作者： Rath, Suneel Kumar Sahu, Madhusmita Das, Shom Prasad Mohapatra, Srikanta Kumar C. V. Raman Global University Dept. of Computer Science Engineering Odisha Bhubaneswar India Birla Global University Dept. of Computer Science Engineering Odisha Bhubaneswar India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9781665400732

The primary purpose of the software industry is to provide high-quality software. Software system failure is caused by faulty software components. The goal of reliable software is to reduce the amount of software programme failures. Software defect prediction is a crucial aspect of developing high-quality software. One can predict software failures by implement essential prediction metrics and previous fault information. A good software fault prediction model makes testing easier while also improving the quality and consistency of software. For defect prediction systems based on diverse parameters, several methodologies have been proposed. However, none of the models meet the criteria for software reliability defect prediction. So in this article we proposed a hybrid software reliability model using feature selection and support vector classifier. In terms of software reliability defect prediction, the provided methodology is acceptable for different software metrics with experimental approvals utilizing a standard dataset. In the methodology, the NASA Metrics Data Program datasets are used for real-time verification and validation. © 2022 IEEE.

关键词： Forecasting

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：