检索结果-内蒙古大学图书馆

Proceedings of the International conference on Data Science, Machine Learning and artificial Intelligence

作者： Shweta Patidar Meenakshi Tripathi Subham Kumar Gupta

ISBN: (纸本)9781450387637

Abstract---Computer networks and their applications have changed the daily aspects of human life considerably be it business, entertainment, work or travelling aspects. However, this dependency on computer networks has also made the networks prone to various attacks. Therefore, it becomes very important to secure the network from any type of suspicious activity. In place of securing each system individually, we can provide security solutions to network traffic data. The concepts of Deep Learning and Machine Learning have been effectively used in the fields of image processing, pattern recognition, NLP, etc. Considering the advantages of these concepts and the sequential nature of traffic data, we have proposed a solution for detecting intrusions in the computer network traffic using one of the Deep Learning approach called Long Short-Term Memory(LSTM). The proposed model makes use of LSTM combined with the loss function of SVM to detect intrusion in Kyoto University Honeypot Network Traffic Data. With an accuracy of 97.10%, true positive rate of a 98.50% and a false positive rate of 5.21%, the proposed LSTM model outperforms other existing models in detecting intrusions over Kyoto University Dataset.

关键词： deep learning intrusion detection system(IDS) long short-term memory (LSTM) machine learning recurrent neural network(RNN) squared hinge loss support vector machine(SVM)

来源：评论

学校读者我要写书评

暂无评论

Biometric Recognition of African Clawed Frogs 20th

Biometric Recognition of African Clawed Frogs

引用

20th International conference on Computer Analysis of images and Patterns (CAIP)

作者： Prins, Fabian L. Tomanin, Dario Kamenz, Julia Azzopardi, George Univ Groningen Bernoulli Inst Math Comp Sci & Artificial Intelli Groningen Netherlands Univ Groningen Groningen Biomol Sci & Biotechnol Inst Mol Syst Biol Groningen Netherlands

ISBN: (纸本)9783031442391;9783031442407

The African clawed frog (Xenopus laevis) is a commonly used model organism for cell biological, developmental, and biomedical research. For health monitoring and experimental quality control purposes, it is desirable to identify individual frogs regularly throughout their life. Current methods for identification are often invasive and associated with significant investment costs. Identification based on images of the biometric pattern on a frog's back has been implemented in some laboratories, but so far has been performed manually and therefore is time-consuming and limited to small group sizes. This work proposes a novel pipeline for data acquisition, pre-processing, and training of a classification model based on pattern recognition. The pipeline is structured around laboratory frog colonies and smartphone usage. In order to achieve a lightweight system in our evaluation we consider a MobileNet ConvNet pre-trained on imageNet. Two feature sets are evaluated on a new data set of 1,647 image samples collected from 160 frogs: RGB images, and 3-channel contour maps (i.e. CORF3D). The results indicate that the CORF3D feature set is favoured over RGB. CORF3D achieved the best performance of 99.94% average accuracy, while RGB had the best performance of 98.79%. Analysis of misclassifications shows that bad predictions are often caused by bad lens focus, light reflections, and positional inconsistency in pattern extraction, which can be addressed during data acquisition. The proposed methodology is, therefore, an effective solution for the recognition of Xenopus laevis.

关键词： Frog recognition Biometric analysis Convolutional neural networks Contour maps CORF3D

来源：评论

学校读者我要写书评

暂无评论

A machine learning-based approach for mercury detection in marine waters

A machine learning-based approach for mercury detection in m...

引用

IEEE International conference on Data Mining Workshops (ICDM Workshops)

作者： Francesco Piccialli Fabio Giampaolo Vincenzo Schiano di Cola Federico Gatta Diletta Chiaro Edoardo Prezioso Stefano Izzo Salvatore Cuomo Department of Mathematics and Applications “R. Caccioppoli” University of Naples Federico II Napoli Italy

Thanks to the widespread use of mobile devices, analyses that in the past had to be carried out in specifically designated and equipped laboratories and which required long processing times, may now take place outdoor and in real time. In the marine science, for example, the development of a mobile and compact system for the on-site detection of heavy metals contamination in seawater would be helpful for scientists and society in at least two ways: i) reduction of time and costs associated with these experiments; ii) the implementation of a strategy for outdoor analysis, eventually embeddable in a lab-on-hardware system. This paper falls within the context of machine learning (ML) for utility pattern mining applied on interdisciplinary domains: starting from wellplates images, we provide a novel proof-of-concept (PoC) machine learning-based framework to assist scientists in their daily research on seawater samples, proposing a system which automatically recognise wells in a multiwell firstly and then predicts the degree of fluorescence in each of them, thus showing possible presence of heavy metals.

关键词： image recognition Pipelines neural networks Metals Feature extraction Prediction algorithms Real-time systems

来源：评论

学校读者我要写书评

暂无评论

image and Video Captioning Using Deep Learning and Natural Language processing

Image and Video Captioning Using Deep Learning and Natural L...

引用

International conference on Computing Communication Control and Automation (ICCUBEA)

作者： Manoj Naidu Athrva Kulkarni Sahil Kadam Siddhesh Joshi Nilesh P. Sable Anuradha Yenkikar Department of CSE – Artificial Intelligence Vishwakarma Institute of Information Technology Pune India

ISBN: (数字)9798350391770

ISBN: (纸本)9798350391787

Deep learning models have been a huge success in image recognition which hence can be used for the purpose of text generation. In the field of imaging science, captioning images and videos is regarded as an intellectually difficult job. Visual Geometry Group (VGG); is a standard deep Convolutional neural Network (CNN) architecture with multiple layers, specifically focusing on the integration of CNN for image feature extraction. Exploring this underlying method, the use of another model is essential for caption generation. Here the Recurrent neural Network (RNN) comes in use for caption generation from the extracted features. Models named Long Short-Term Memory (LSTM) based on RNN and Bidirectional encoder representation transformer (BERT) based on Transformers have been prominent in ensuring accurate results. The Flicker8k dataset is used which provides a variety of information useful for model training. By testing validation data along with evaluation metrics, we analyze the effectiveness of different models to create consistent and descriptive headlines. Extending our inquiry to encompass title generation using transformer models, while also exploring learning techniques for real-time title generation and delivery using the Open-CV library available in Python to get the output from the camera and display it on screen. The result shows that the LSTM is the best model for captioning, with an accuracy of 65.07% at the epochs of 300 and the BERT model has an accuracy of 31% at the epochs of 2. The findings of this study not only contribute to advancing subtitle enhancement methodologies but also broaden the potential applications of deep learning techniques in this domain.

关键词： Deep learning Recurrent neural networks Accuracy Computational modeling Bidirectional control Transformers Feature extraction Encoding Data models Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Loop Closure Detection Based on Improved Hybrid Deep Learning Architecture

Loop Closure Detection Based on Improved Hybrid Deep Learnin...

引用

IEEE International Symposium on Parallel and Distributed processing with applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yuan Liu Rong Xiang Qieshi Zhang Ziliang Ren Jun Cheng Guilin University of Electronic Technology Guilin China Key Laboratory of Human-Machine Intelligence-Synergy Shenzhen China

ISBN: (纸本)9781728152103

Loop closure detection plays a vital role in the visual Simultaneous Localization and Mapping (SLAM) system. Traditional Bag-of-Visual-Word (BoVW) methods for loop closure detection has been successfully applied to various SLAM systems. The Convolutional neural networks (ConvNets) based methods can automatically learn feature representation from original image, and it is more robust to illumination changes. However, these two methods all have some limitations. In order to overcome the shortcomings of the traditional methods extract insufficient features, and the ConvNets based methods unable to adapt complex environment changes, in this paper, we propose an improved hybrid deep learning architecture (HDLA) to generate high-level semantic image features for loop closure detection specifically. This network is based on hybrid ConvNet modified by us to especially cope with robust and real-time feature extraction. We present extensive experiments on three real world datasets to evaluate each of the specific challenges in loop closure detection. The results demonstrate that the proposed method achieves superior performances and provides a feasible solution for loop closure detection.

关键词： convolutional neural nets feature extraction image classification image representation learning (artificial intelligence) object detection robot vision SLAM (robots) robot vision Feature extraction image representation Object detection image classification surgical closure Loops Contraceptive Coil Feasible Solution original image simultaneous localization and mapping

来源：评论

学校读者我要写书评

暂无评论

Recent progress in optoelectronic memristors for neuromorphic and in-memory computation

引用

NEUROMORPHIC COMPUTING AND ENGINEERING 2023年第2期3卷 022002-022002页

作者： Pereira, Maria Elias Martins, Rodrigo Fortunato, Elvira Barquinha, Pedro Kiazadeh, Asal NOVA Univ Lisbon NOVA Sch Sci & Technol & CEMOP Dept Mat Sci UNINOVA i3N-CENIMAT P-2829516 Caparica Portugal

Neuromorphic computing has been gaining momentum for the past decades and has been appointed as the replacer of the outworn technology in conventional computing systems. artificial neural networks (ANNs) can be composed by memristor crossbars in hardware and perform in-memory computing and storage, in a power, cost and area efficient way. In optoelectronic memristors (OEMs), resistive switching (RS) can be controlled by both optical and electronic signals. Using light as synaptic weigh modulator provides a high-speed non-destructive method, not dependent on electrical wires, that solves crosstalk issues. In particular, in artificial visual systems, OEMs can act as the artificial retina and combine optical sensing and high-level image processing. Therefore, several efforts have been made by the scientific community into developing OEMs that can meet the demands of each specific application. In this review, the recent advances in inorganic OEMs are summarized and discussed. The engineering of the device structure provides the means to manipulate RS performance and, thus, a comprehensive analysis is performed regarding the already proposed memristor materials structure and their specific characteristics. Moreover, their potential applications in logic gates, ANNs and, in more detail, on artificial visual systems are also assessed, taking into account the figures of merit described so far.

关键词： optoelectronic memristors (OEMs) photonic memristors resistive switching devices artificial neural networks (ANNs) artificial visual systems neuromorphic computing

来源：评论

学校读者我要写书评

暂无评论

Mobile Medical Assistant and Analytical System for Dengue Patients

Mobile Medical Assistant and Analytical System for Dengue Pa...

引用

Advancements in Computing (ICAC), 2019 International conference on

作者： K. T. K. Jayampathi M. A. C. Jananjaya E. P. C. Fernando Y. A. Liyanage M. G. N. M. Pemadasa G. W. D. A. Gunarathne Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9781665408639

Dengue fever is a vector-borne viral disease spread by the mosquito Aedes Aegypti. It is a public health problem, with an estimated 50-500 million infections each year and no effective vaccination. People's hectic schedules may not have enough time to see a doctor every time they have a fever. They may overlook their disease, believing it to be a common ailment. Prior medical assistance for dengue patients with fever to check their conditions reliably is a major problem. There is no easily accessible proper system to identify dengue patients at an early stage. This paper presents a mobile medical assistant and analytical system for dengue patients. With a novel approach, using the most appropriate technologies, the mobile application supports identifying dengue patients using the chatbot, analyzing skin conditions, analyzing blood reports, and analyzing dengue-infected areas' functionalities. The registered users can log in to the system and check their dengue condition. The development is carried out with Natural Language processing, artificial neural Network (ANN), Machine Learning, image processing, Convolutional neural Network (CNN), and Android technologies. A mobile application prototype is created and tested, with the possibility of future testing and implementation. The results show effective performances in analyzing dengue conditions.

关键词： Schedules Skin Mobile applications Vaccines Convolutional neural networks Reliability Viruses (medical)

来源：评论

学校读者我要写书评

暂无评论

Comprehensive investigation on Deep learning models: applications, Advantages, and Challenges

Comprehensive investigation on Deep learning models: Applica...

引用

International conference on Computing and Networking Technology (ICCNT)

作者： Rajiv Avacharmal Saigurudatta Pamulaparthyvenkata Dileep Kumar Pandiya R Krishna Prakash Piyush Ranjan Anandaganesh Balakrishnan S Maheswaran AI/ML expert University of Connecticut USA Independent Researcher ZoomInfo Technologies Department of Information Technology Sona College of Technology Salem Tamil Nadu IEEE USA Data Engineering American Water Department of Electronics and Communication Engineering Kongu Engineering College Perundurai Erode TamilNadu

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

artificial intelligence (AI) and machine learning (ML) have been completely transformed by deep learning (DL), which provides unmatched power in handling massive, unstructured information from a variety of fields. CNNs, neural networks with recurrent connections (RNNs), generative models, (DRL), and deep learning via transfer are the main deep learning models that are covered in detail in this article. The structure, uses, advantages, and drawbacks of each model are thoroughly investigated. In this work, we use the Fruit-360 dataset, a benchmark picture classification dataset, for an empirical investigation. Six well-known deep learning architectures are compared and evaluated: Bidirectional LSTM, CNN, Simple RNN, (LSTM), (GRU), and Bidirectional GRU. Analysis is done on performance parameters including accuracy, precision, recall, and computing efficiency to have a better understanding of how well they work on various tasks. The purpose of this survey is to give scholars, professionals, and enthusiasts a thorough grasp of the various uses and capacities of deep learning models. The study provides insights that help progress the discipline and direct the selection of suitable models for certain real-world problems.

关键词： Deep learning Training Surveys Computational modeling image processing Focusing Data models Spatial databases Classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Production of MusicXML from Locally Inclined Sheet-music Photo image by Using Measure-based Multi-modal Deep-learning-driven Assembly Method

引用

Transactions of the Japanese Society for artificial Intelligence 2023年第3期38卷

作者： Shishido, Tomoyuki Fati, Fehmiju Tokushige, Daisuke Ono, Yasuhiro Kumazawa, Itsuo Biomedical AI Research Unit Tokyo Institute of Technology Shishido&Associates Japan SK Intellectual Property Law Firm Japan Enspirea LLC Japan Laboratory for Future Interdisciplinary Research of Science and Technology Tokyo Institute of Technology Japan

Deep learning has been applied to optical music sheet recognition (OMR). However, OMR processing from various sheet-music images still lacks precision to be widely applicable. We propose a measure-based multimodal deep-learning-driven assembly (MMdA) method enabling end-to-end OMR processing from various images including inclined photo images. Using this method, measures are extracted using a deep-learning model, aligned, and resized to be used for inference of given musical-symbol components by using multiple deep-learning models in sequence or in parallel. The use of each standardized measure enables efficient training of the deep-learning models and accurate adjustment of five staff lines in each measure, which enables locally inclined sheet-music images to be precisely positioned. Thus, a score can be reproduced from the inclined image with the proposed MMdA method while current OMR applications cannot. Multiple musical-symbol-component deep-learning feature-category models with a small number of feature types can represent a diverse set of notes and other musical symbols including chords. The proposed MMdA method provides a solution to end-to-end OMR processing and enhances the utility of OMR of mobile phone-based sheet-music photo images. © 2023, Japanese Society for artificial Intelligence. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Automated Object Detection and Recognition in Satellite imagery Using CNNs

Automated Object Detection and Recognition in Satellite Imag...

引用

Innovations in Communications, Electrical and Computer Engineering (ICICEC), International conference on

作者： Shanthi H J G. Shobana E. Kamalanaban J. Senthil Murugan S. Nandhinieswari R. Stalinbabu Department of Computer Applications Hindustan Institute of Technology and Science Deemed to be University Padur School of Computer Science Takshashila University Department of Computer Science and Engineering Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College Kongunadu Arts and Science College Coimbatore Gounder Mills Coimbatore Artificial Intelligence and Machine Learning M. Kumarasamy College of Engineering Karur

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376524

As increasingly high-resolution satellite photography becomes available, it has led to a growing need for efficient and accurate methods to analyse large databases and extract valuable information. This research presents a comprehensive approach for automated item identification and detection in satellite data using Convolutional neural networks (CNNs). This research abstract outlines the critical steps involved in a suggested technique. These steps encompass data cleaning and organisation, model architecture development, training and evaluation, post- processing, deployment, and subsequent management. This study investigates the ability of CNNs to learn intricate spatial characteristics. The research focuses on carefully selecting and annotating training and validation datasets incorporating items of interest. This study uses data augmentation methods to enhance the generalisation capabilities of the model. This research abstract discusses the importance of the preprocessing stage in ensuring the consistent performance of a model by normalising the input data. This research abstract discusses the components of the CNN architecture, namely convolutional, pooling, and fully connected layers. The CNN architecture is specifically designed to capture hierarchical characteristics. This study investigates the utilisation of a cutting-edge optimiser in the training process to optimise a meticulously constructed loss function. This study examines the integration of the model into real-world applications, considering the trade-off between processing speed and resource constraints as crucial considerations for successful deployment. The findings suggest that this methodology holds promise as a valuable tool in various fields.

关键词： Training Technological innovation Accuracy Satellites image recognition Transfer learning Data augmentation Data models Satellite images Convolutional neural networks

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：