检索结果-内蒙古大学图书馆

A Deep Learning Based Translation Performance Analysis of International Languages 3

A Deep Learning Based Translation Performance Analysis of In...

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Satpathy, Subhashree Mishra, Smita Prava Nayak, Ajit Ku. Soa Deemed to Be University Computer Science & Engineering Bhubaneswar India Computer Science & Information Technology Soa Deemed to Be University Bhubaneswar India

ISBN: (纸本)9798350354379

Machine Translation (MT) is a specialized domain within the broader field of Natural Language Processing (NLP) that utilizes machine learning algorithms to translate speech or text from one language to another language without human participation. The goal of such system construction is to find relatively high accuracy, cost effective and low error in the outcome. Numerous MT systems have been developed and deployed for widespread use with many individuals, particularly learners encountering difficulties while utilizing them. In recent times Recurrent Neural Networks (RNNs) and Long Short Term Memory (LSTM) techniques have shown promising results for machine translation as compared to other existing approaches of Neural Machine Translation (NMT). The current work compares performances of NMT and RNN methods in different international datasets (FRENCH-ENGLISH, RUSSIAN-ENGLISH, and ITALIANENGLISH). Their translation errors have been calculated by using Sparse Categorical Crossentropy loss function. We have observed the effect of size of the data in specified settings and found that there is no significant change in loss function after 50k training data. © 2024 IEEE.

关键词： Long Short Term Memory (LSTM) Machine Translation (MT) Natural Language Processing (NLP) Neural Machine Translation (NMT) Recurrent Neural Network (RNN)

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based compression and classification technique for whole slide histopathology images

引用

International Journal of Information Technology (Singapore) 2024年第7期16卷 4517-4526页

作者： Barsi, Agnes Nayak, Suvendu Chandan Parida, Sasmita Shukla, Raj Mani Computing and Information Science Anglia Ruskin University Cambridge United Kingdom Department of Computer Science & amp Engineering Silicon University Bhubaneswar India Department of Computer Science & amp Engineering SoA University Bhubaneswar India

This paper presents an autoencoder-based neural network architecture to compress histopathological images while retaining the denser and more meaningful representation of the original images. Current research into improving compression algorithms is focused on methods allowing lower compression rates for Regions of Interest (ROI-based approaches). Neural networks are great at extracting meaningful semantic representations from images and, therefore can select the regions to be considered of interest for the compression process. In this work, we focus on the compression of whole slide histopathology images. The objective is to build an ensemble of neural networks that enables a compressive autoencoder in a supervised fashion to retain a denser and more meaningful representation of the input histology images. Our proposed system is a simple and novel method to supervise compressive neural networks. We test the compressed images using transfer learning-based classifiers and show that they provide promising accuracy and classification performance. © The Author(s) 2024.

关键词： Compression Deep learning Image classification Whole slide histopathology images

来源：评论

学校读者我要写书评

暂无评论

Stacked Layer Based Deep Learning Approach for Fake News Classification 7

Stacked Layer Based Deep Learning Approach for Fake News Cla...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Dhal, Pradip Biswas, Deb Pragya Patra, Jayshree Mishra, Manima Asish Kumar Jha, Prakash Iter Soa University Department of Computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350304268

The growth of the global population's social., economic., and emotional spheres is impacted by fake news and misleading information. Several classification systems are available to help identify fake news., but they needed to be quicker., more secure., and as trustworthy as was required at the time. Since manually confirming the integrity of news is difficult and expensive., researchers have shown much interest in this area. Different techniques for spotting fake news., including sentiment-based., image-based., content-based., social context-based., and hybrid context-based categorization., were examined. In this paper., we have developed a lightweight Deep Learning (DL) network for Fake News Classification (FNC)., a sentiment-based classification. The deep network consists of a stacked layer based feature extraction approach. Here stack layer first extracts the global features by the network of Bidirectional-Long Short Term Memory (Bi-LSTM) and Bidirectional-Gated Recurrent Unit (Bi-GRU). The results of the global features we have extracted the local features by the Convolutional Neural Network (CNN). The experiment findings show that the suggested lightweight DL network is more successful in producing superior results than the other methods. © 2023 IEEE.

关键词： Bi-GRU Bi-LSTM CNN Fake news classification Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

PBb-LMFO: a levy flight integrated MFO inspired ensemble model for cancer diagnosis

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1397-1406页

作者： Behera, Sabita Rani Pati, Bibudhendu Parida, Sasmita Department of Computer Science Rama Devi Women’s University Bhubaneswar India Department of Computer Science and Engineering Institute of Technical Education and Research SoA Univesity Bhubaneswar India

To build a Cancer prediction model based on ML, one needs data of a certain sort, such as gene expression data or microarray data. To reduce the dataset's dimensionality, feature selection is proposed as an optimal solution to high dimensionality challenges and to deal with microarray data, this research work aims to perform the 2-stage feature selection. In the initial stage, the Particle Swarm Optimization (PSO) and Bare-bone PSO (BBPSO) are applied to the dataset separately. Then the common features selected by PSO and BBPSO are considered. Then Levy Flight Moth Flame Optimization (LFMFO) is applied to choose the final optimal set of features. Basic existing ML classifiers are used for the first prediction. Afterwards, the Majority Voting technique is applied to develop the ensemble technique. The proposed model is developed over four Cancer microarray datasets, including CNS, Lung Cancer, Ovarian Cancer, and Breast Cancer. The experimental analysis presents the proposed model obtains the highest accuracy of 98.81% for the Ovarian Cancer dataset. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Bare-bone PSO (BBPSO) Cancer Levy Flight Moth Flame Optimization (LFMFO) Majority voting PSO

来源：评论

学校读者我要写书评

暂无评论

Image Colorization Using Auto Encoders 3

Image Colorization Using Auto Encoders

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Panda, Susmita Ranjan Panda, Mohit Prakash, Abhigyan Dept. of Computer Science Engineering Iter Soa University Odisha Bhubaneswar India School of Computer Engineering Kiit Deemed to Be University Odisha Bhubaneswar India

ISBN: (纸本)9798350354379

Image colorization is a useful technique in various fields such as photography, art, and design. It can be used to restore old photos or add color to artistic renditions of real-world scenes and objects to make them appear more natural. It is a challenging task because it requires the model to understand the context and semantics of the image to predict accurate colors. The code uses a convolutional neural network (CNN) to predict the color of each pixel in an image based on its surrounding pixels. These techniques can be used for the restoration of old black and white photos. By colorizing these photos, they can be brought to life and preserved for future generations. This paper can benefit various domains such as art, history, and education. For instance, museums and historians can use this proposed method to enrich their collections and documents by adding color. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Optimal route planning for emergency transportation logistics based on time constraints

Advances in Transportation Studies

引用

Advances in Transportation Studies 2023年第Special issue期2卷 75-86页

作者： Wu, R.J. Patnaik, S. Henan Vocational College of Information and Statistics Henan Zhengzhou450000 China Department of Computer Science and Engineering SOA University Bhubaneswar751030 India

In the emergency logistics system, the planning of transportation routes becomes a key link in emergency rescue and plays an important role in the entire rescue process. In order to shorten the transportation time of emergency materials and improve transportation efficiency, this paper proposes an optimal route planning method for emergency transportation logistics based on time constraints. Firstly, analyze the characteristics of emergency transportation logistics transportation, and then calculate the impact weights of supply and demand points, analyzing the factors that affect route planning. Secondly, calculate the penalty coefficients for emergency transportation logistics transportation in hard and soft time windows under time constraints, and construct an objective function for the optimal route planning of emergency transportation logistics transportation. Finally, the optimal route planning result is obtained by solving the constructed objective function. The experimental results show that the proposed method has the highest efficiency of emergency transportation logistics transportation of about 99%, effectively improving the efficiency of emergency transportation logistics transportation. © 2023, Aracne Editrice. All rights reserved.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Technique Based Plant Disease Detection and Classification

Deep Learning Technique Based Plant Disease Detection and Cl...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Sethy, Abhisek Dash, Arabinda Patra, Prashanta Kumar Silicon Insitute of Technology Departemnt of Computer Science & Engineering Bhubaneswar India SOA University Dean SRIC Bhubaneswar India

ISBN: (纸本)9798350369175

Today, agricultural production drives the economy. Agriculture has numerous facets, and plant disease diagnosis is one of the most important. Plant diseases are very common. Disease detection prevents yield and quantity losses. Plant diseases are studied through studying plant patterns. Environmentally friendly farming requires monitoring plant health and leaf diseases. Traditional methods have detected plant leaf diseases for decades. Several research studies have shown that effective methods for plant disease identification are still needed. Thus, deep learning and image processing architectures recognize plant leaf diseases. Image Acquisition, Pre-Processing, Segmentation, Feature Extraction, and Classification comprise this illness detection method. Convolutional Neural Networks (CNN) are also used on input datasets. This method simplifies implementation because the CNN evaluates all discriminant features. CNN was compared to other classifiers in a comprehensive analysis. Brown spot, grey spot, rust, and other leaf spots can be treated immediately with the proposed work. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Image Captioning Model

Hybrid Image Captioning Model

引用

2022 OPJU International Technology Conference on Emerging Technologies for Sustainable Development, OTCON 2022

作者： Panigrahi, Lipismita Panigrahi, Raghab Ranjan Chandra, Saroj Kumar Kiit University Department of School of Computer Applications Bhubaneswar India Soa University Department of Computer Science and Engineering Bhubaneswar India Opju University Department of Computer Science and Engineering Raigarh India

ISBN: (纸本)9781665492942

Image captioning is implemented using Deep learning and NLP (Natural Language Processing) resulting in producing a description of an image. The proposed model generates a caption for an image using a Convolutional Neural Network (CNN) together with a Recurrent Neural Network (RNN) and area of attention. Previously, the image names were used as keys to map the images with descriptions. In order to achieve high performance, in the proposed model the image caption is based on the relationship between the areas of a picture (attention model), the words used in the caption, and the state of an RNN language model. The approach of progressive loading is employed for the loading of the image dataset. Further, for encoding the image dataset into a feature vector, VGG16 a pre-trained CNN is used. The extracted feature vector is given as input to the RNN model. These image encodings are output to a specific type of RNN model known as Long Short-Term Memory (LSTM) networks. Subsequently, the LSTM works on decoding the feature vector and predicts the sequence of words, resulting in the generation of descriptions or captions. The training performance is measured using one of the model's quantitative analysis metrics known as BLEU. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Identity Verification: Deep Learning for Real and Fake Face Classification in Medical Application 2

Enhancing Identity Verification: Deep Learning for Real and ...

引用

2nd International Conference on Ambient Intelligence in Health Care, ICAIHC 2023

作者： Panda, Susmita Panda, Mohit Ranjan SOA University Dept. of Computer Science Engineering ITER Bhubaneswar India School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar India

ISBN: (纸本)9798350344882

A crucial problem in enabling machines to distinguish real identities from fake ones is the classification of real and fake human looks. This research explores these complexities and presents practical solutions in light of the pervasive difficulties related to misleading personification. This study sets out to build a reliable facial identification model that can tell real from fake facial photos by utilizing the power of deep learning. Our research focuses on identifying the subtle differences between real and fake countenances using a dataset that has been enhanced with profile photographs. Our main goal is to create a sophisticated model that can recognize real and fake faces in the medical field. We want to create an innovative deep learning platform by combining a variety of cutting-edge deep learning approaches. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Comparative exploration of deep convolutional neural networks using real-time endoscopy images

Biomedical Technology

引用

Biomedical Technology 2024年 8卷 1-16页

作者： Mohapatra, Subhashree Jeji, Pukhraj Singh Pati, Girish Kumar Mishra, Manohar Swarnkar, Tripti Department of Computer Science & Engineering SOA Deemed to be University Odisha India Department of Gastroenterology Apollo Hospital Bhubaneswar India Department of Gastroenterology & Hepatobiliary Sciences IMS & SUM Hospital SOA Deemed to be University Odisha India Department of Electrical and Electronics SOA Deemed to be University Odisha India Department of Computer Application National Institute of Technology (NIT) Raipur India

Until now various deep convolutional neural networks are designed and trained for the purpose of classifying different medical conditions related to the domain of gastroenterology. Most of the study carried out have considered publicly available datasets to train the classification networks. Nevertheless, the main motive for carrying out different works in the field gastroenterology is to administer the developed models in healthcare centers in real-world set-ups. For doing so, it is important to check the generalizing ability of the designed systems by regulating them so as to classify endoscopy images captured in a specific hospital. In this regard, the foremost work completed is the collection of the endoscopy data from the hospital and then correctly annotating the images taking the help of a senior endoscopist with experience of more than 5 years. Once the data annotation is completed, the images are segregated into the class of normal and abnormal endoscopy images. Four different models are designed in the current work based on deep learning models, transfer learning models and ensemble approaches, and trained to classify the hospital endoscopy data as normal or abnormal. The models are then tested and evaluated based on various performance measures. It is observed from the comparative analysis that the transfer learning-based ensemble model has the best generalizing ability and gives the best specificity of 100 %. It is believed that deep learning-based models can assist endoscopists in add-on to human prediction efficiency. © 2024 The Authors

关键词：

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：