检索结果-内蒙古大学图书馆

International Conference on Optimization and Applications (ICOA)

作者： Esra’a Alhenawi Ruba Abu Khurma Pedro A. Castillo Maribel G. Arenas Ayat Mahmoud Al-Hinawi Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Computer Science MEU Research Unit Faculty of Information Technology Middle East University Amman Jordan University of Granada Granada Spain Department of Allied Engineering Sciences Hashemite University Zarqa Jordan

Text classification is a technique for grouping articles into pre-defined categories. Prior to categorization, text documents have to be set up and organised in a form that is compatible with the data mining techniques. That has produced many term weighting techniques have been developed in the literature to improve the functionality of text categorization systems. This paper compares techniques for text classification based on when stop words are eliminated from the documents once and when they are not. We used an Arabic data set of 322 papers grouped into six subjects (health, politics, science, education, agriculture and finance) to research which is the influence of prior weighting of features approaches on classification outcomes with regard to accuracy, recall, precision, and F-measure values. Each document subset includes 50 documents, except the health one that includes 61. We carried out four experiments and checked results getting that only for precision, the term frequency feature weighting approach with stop word removal are more or less the same than for binary method. Moreover the conclusion for accuracy, recall and F-measure is that Feature weighting approach with stop word outperforms the Binary one. Additionally, if the phrase for weighting is the same for both methods, to remove stop word increases classification accuracy for all the experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SML: A Backdoor Defense for Non-Intrusive Speech Quality Assessment via Semi-Supervised and Multi-Task Learning

SML: A Backdoor Defense for Non-Intrusive Speech Quality Ass...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ying Ren Wenjie Zhang Jiahong Ye Jie Li Diqun Yan Bin Ma Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China College of Digital Technology and Engineering Ningbo University of Finance and Economics Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Non-intrusive speech quality assessment (NISQA) is widely used in speech downstream tasks due to its ability to predict the quality of speech without a reference speech. However, few researchers have focused on the backdoor security of NISQA. Despite the backdoor defenses have been extensively studied to mitigate the threat of maliciously modifications in deep neural networks. In particular, semi-supervised based backdoor defenses have excellent defensive performance by depriving backdoor attacks of their most essential need. But these defense methods rely on data-augmentation consistency and thus cannot be applied to NISQA. In this work, we propose a backdoor defense based on semi-supervised and multi-task learning (SML). Semi-supervised learning is based on the simple assumption that the same input should be as consistent as possible in two similar models. Multi-task learning further improves the prediction performance of mean opinion score (MOS) by learning the tasks of perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI) and speech distortion index (SDI). Extensive experiments involving five backdoor defenses against five backdoor attacks on two benchmark datasets demonstrate the superiority of our SML approach.

关键词： Acoustic distortion Artificial neural networks Semisupervised learning Benchmark testing Multitasking Acoustics Quality assessment Security Indexes Speech processing

来源：评论

学校读者我要写书评

暂无评论

SIMPLEX: A LEXICAL TEXT SIMPLIFICATION ARCHITECTURE

arXiv

引用

arXiv 2023年

作者： Truică, Ciprian-Octavian Andrei-Ionut, Stan Apostol, Elena-Simona Department of Information Technology Uppsala University Uppsala Sweden Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania

Text simplification (TS) is the process of generating easy-to-understand sentences from a given sentence or piece of text. The aim of TS is to reduce both the lexical (which refers to vocabulary complexity and meaning) and syntactic (which refers to the sentence structure) complexity of a given text or sentence without the loss of meaning or nuance. In this paper, we present SIMPLEX, a novel simplification architecture for generating simplified English sentences. To generate a simplified sentence, the proposed architecture uses either word embeddings (i.e., Word2Vec) and perplexity, or sentence transformers (i.e., BERT, RoBERTa, and GPT2) and cosine similarity. The solution is incorporated into a user-friendly and simple-to-use software. We evaluate our system using two metrics, i.e., SARI, and Perplexity Decrease. Experimentally, we observe that the transformer models outperform the other models in terms of the SARI score. However, in terms of Perplexity, the Word-Embeddings-based models achieve the biggest decrease. Thus, the main contributions of this paper are: (1) We propose a new Word Embedding and Transformer based algorithm for text simplification;(2) We design SIMPLEX - a modular novel text simplification system - that can provide a baseline for further research;and (3) We perform an in-depth analysis of our solution and compare our results with two state-of-the-art models, i.e., LightLS [19] and NTS-w2v [44]. We also make the code publicly available online. © 2023, CC BY-NC-ND.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Detection of GAN Generated Fake Satellite Images Using Deep Learning 3

Detection of GAN Generated Fake Satellite Images Using Deep ...

引用

3rd International Conference on Applied Mathematics, Modeling and computer Simulation, AMMCS 2023

作者： Snehith, K. Anuradha, G. Vemuri Krishna N, Hari Sathishkumar, V.E. Abualigah, Laith Department of Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India Department of Industrial Engineering Hanyang University 222 Wangsimini-ro Seongdong-gu Seoul Korea Republic of Computer Science Department Prince Hussein Bin Abdullah Faculty for Information Technology Al Al-Bayt University Mafraq25113 Jordan Meu Research Unit Middle East University Amman Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan

ISBN: (纸本)9781643684581

Fake Images generation has become a common practice nowadays and this process has become elementary with the advent of Generative Adversarial Networks. Although though fake images are entertaining and have their benefits, they also have a few negative effects. Modern satellite images offer crucial data that aids in tracking various packages, including spatial decision, spectral properties, sensor sensitivity, and many others. Critical details needed for a few applications may be massively obtained from these photos. Yet, altering these images by removing, incorporating, or replicating objects leads to false perceptions of reality. It is our intention to come across those kind of fake satellite images. We use in-depth learning architectures to identify fake Satellite photos in order to distinguish between authentic and fake photos. © 2023 The Authors.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

MISROBÆRTA: TRANSFORMERS VERSUS MISinformation

arXiv

引用

arXiv 2023年

作者： Truicǎ, Ciprian-Octavian Apostol, Elena-Simona Department of Information Technology Uppsala University Uppsala Sweden Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania

Misinformation is considered a threat to our democratic values and principles. The spread of such content on social media polarizes society and undermines public discourse by distorting public perceptions and generating social unrest while lacking the rigor of traditional journalism. Transformers and transfer learning proved to be state-of-the-art methods for multiple wellknown natural language processing tasks. In this paper, we propose MisRoBÆRTa, a novel transformer-based deep neural ensemble architecture for misinformation detection. MisRoBÆRTa takes advantage of two state-of-the art transformers, i.e., BART and RoBERTa, to improve the performance of discriminating between real news and different types of fake news. We also benchmarked and evaluated the performances of multiple transformers on the task of misinformation detection. For training and testing, we used a large real-world news articles dataset (i.e., 100,000 records) labeled with 10 classes, thus addressing two shortcomings in the current research: (1) increasing the size of the dataset from small to large, and (2) moving the focus of fake news detection from binary classification to multi-class classification. For this dataset, we manually verified the content of the news articles to ensure that they were correctly labeled. The experimental results show that the accuracy of transformers on the misinformation detection problem was significantly influenced by the method employed to learn the context, dataset size, and vocabulary dimension. We observe empirically that the best accuracy performance among the classification models that use only one transformer is obtained by BART, while DistilRoBERTa obtains the best accuracy in the least amount of time required for fine-tuning and training. However, the proposed MisRoBÆRTa outperforms the other transformer models in the task of misinformation detection. To arrive at this conclusion, we performed ample ablation and sensitivity testing with MisRoBÆRTa on t

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Detection of Ganoderma Boninense Diseases of Palm Oil Trees Using Machine Learning

Detection of Ganoderma Boninense Diseases of Palm Oil Trees ...

引用

International Conference on computer Applications and Industrial Electronics (ICCAIE)

作者： Yu Hong Haw Zhen Zhao Yan Chai Hum Joon Huang Chuah Wingates Voon Siti Khairunniza-Bejo Nur Azuan Husin Por Lip Yee Khin Wee Lai Faculty of Engineering Universiti Malaya Kuala Lumpur Malaysia Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Selangor Malaysia Faculty of Engineering Universiti Putra Malaysia Serdang Malaysia Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

About one-third of the world’s vegetable oil and fat supply is made up of palm oil, of which 75% is consumed as food. Palm oil is a vital economic resource for nations like Malaysia. The Basal Stem Rot disease of oil palm trees is one of many obstacles to the production of palm oil. The infection is brought on by a fungus called Ganoderma Boninense, which colonizes trees. Early detection is difficult since the symptoms of infection are sometimes mild to non-existent. Terrestrial laser scanning was used to collect 88 photos of the oil palm tree’s grey-distribution canopy. The photos gathered were pre-processed to enhance the performance of the deep learning model. To train and verify the effectiveness of disease detection, a deep learning model called convolution neural network is used. The performance of disease detection is trained and tested using a convolutional neural network deep learning model, which divides the data into two classes: the healthy class and the non-healthy class. The improved DenseNet121 model reports a Macro F1-score of 0.7983. The model could only separate the images into two classes rather than categorizing the images into distinct infection levels, which is a limitation of our work. In order to investigate the feasibility of early oil palm disease diagnosis, it is advised for future research to undertake multi-class or multi-level classification using deep learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale

arXiv

引用

arXiv 2023年

作者： Hao, Zhiwei Guo, Jianyuan Han, Kai Hu, Han Xu, Chang Wang, Yunhe School of information and Electronics Beijing Institute of Technology China School of Computer Science Faculty of Engineering The University of Sydney Australia Huawei Noah’s Ark Lab

The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the small data pitfall that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1%, 84.3%, and 85.0% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://***/Hao840/vanillaKD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Retrieval Quality Through Big Data and AI Technologies

Enhancing Retrieval Quality Through Big Data and AI Technolo...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Abhinav Mishra Akhilendra Pratap Singh Amar Shankar Harshita Kaushik Divya K Disha S. Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Food Technology Faculty of Engineering and Technology JAIN (Deemed-to-be University) Ramnagar Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Wankhede Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA

Huge facts and AI technologies have superior speedy to end up the primary drivers of innovation and progress in lots of one-of-a-kind areas, along with statistics retrieval. through the evaluation of big datasets of formerly retrieved documents and question logs, AI algorithms are capable of expect and perceive the maximum applicable files and also are used to higher recognize and respond to consumer queries. additionally, AI technology which include natural language processing are already beginning to shape the manner human beings engage with engines like Google, permitting extra conversational, person-friendly seek experience. eventually, massive information and AI have the capability to help form semantically based collections of documents with keywords and entities robotically extracted from content, making it easier for a search engine to analyze and connect files higher. This may in the end result in better retrieval satisfactory and greater dynamic records exploration studies for users of search engines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Short-Term Load Forecasting with TDCI: Temporal Decomposition and Channel Independence 7

Short-Term Load Forecasting with TDCI: Temporal Decompositio...

引用

7th International Conference on Electrical, Mechanical and computer engineering, ICEMCE 2023

作者： Li, Wenxue Cheng, Chi Xu, Peihua Liu, Renfeng Zhang, Yun Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Prov. Wuhan430205 China Wuhan Institute of Technology Hubei Provincial Key Laboratory of Intelligent Robot Hubei Prov. Wuhan430205 China Hubei Meteorological Service Center Wuhan430079 China School of Educational Information Technology Central China Normal University Faculty of Artificial Intelligence Education Wuhan430079 China School of Mathematics and Computer Science Wuhan Polytechnic University Wuhan430023 China

ISBN: (纸本)9798350382877

Given the substantial load fluctuations, pronounced stochasticity, and non-linearity influenced by factors like weather and temperature in power load forecasting, we present a short-term load forecasting model based on TDCI. This model introduces several enhancements to boost forecasting accuracy. Firstly, TDCI employs temporal decomposition, separating time-series data into seasonal and trend components, enabling the capture of inherent seasonal patterns and long-term trends that significantly impact load forecasting accuracy. Additionally, the incorporation of locality-sensitive hashing attention efficiently processes relevant temporal patterns, enhancing model performance while reducing computational complexity. Lastly, a channel independence approach is applied to each variable, allowing tailored processing based on individual feature characteristics. This adaptive feature handling ensures effective capture of distinct properties, thereby enhancing forecasting accuracy. Experimental evaluations on a real-world power load dataset demonstrate the superior forecasting precision of our proposed model compared to existing models. © 2023 IEEE.

关键词： Electric power plant loads

来源：评论

学校读者我要写书评

暂无评论

Neural Network Algorithm in Financial Services: The Effect of Fraud Risk Management and Fraud Prevention

Neural Network Algorithm in Financial Services: The Effect o...

引用

Emerging Research in Computational Science (ICERCS), International Conference on

作者： Komal Singh Nitin Kulshrestha Nirmala B R. Divya N. SureshKumar D. Gobinath Indira School of Business Studies Pune Maharashtra Department of Commerce Finance and Accountancy Christ Deemed to be University Uttar Pradesh India Department of Computer Science and Engineering Sri Ramachandra Faculty of Engineering and Technology Tamilnadu India Department of Computer Science and Engineering JCT College of Engineering and Technology Tamilnadu India Department of Information Technology Sri Ramakrishna Engineering College Coimbatore India Department of AIML CMR University Bangalore Karnataka India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

The current financial crisis has made it such that microfinance institutions, in their fight for self-sufficiency, financial sustainability, and survival, cannot afford to ignore fraud risk management strategies. Many people throughout the world who are struggling financially would not have the means to obtain financial services if it weren't for microfinance institutions. This proposed system is a theoretical investigation on how microfinance institutions in Ghana might effectively manage the risk of fraud. By surveying and evaluating fraud risk management experts' and researchers' perspectives, the study takes an experimental approach. There are three steps to the suggested technique, which is preprocessing, feature selection, and training the model. The following procedures comprise data preprocessing, which aim to improve data quality and guarantee model performance: The following methods are employed: hybrid sampling strategy, outlier detection, duplicate removal, multiple imputation. Machine learning, pattern recognition, and statistics are just a few of the fields that have done extensive research on the feature selection problem. The proposed approach used the CNN-BiGRU to train the model. Compared to state-of-the-art alternatives like CNN and BiGRU, the proposed model obtains an average accuracy rate of 95.19%.

关键词： Neural networks Machine learning Data science Feature extraction Stability analysis Imputation Data models Fraud Pattern recognition Financial services

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：