检索结果-内蒙古大学图书馆

1st International Conference on Computational science and Technology, ICCST 2022

作者： Annie Silviya, S.H. Pathmanaban, J. Kingsley, S. Sriman, B. Suryaa Narayanan, K. Santhosh Kumar, E. Rajalakshmi Institute of Technology Department of Computer Science Engineering TamilNadu Chennai India Sairam Engineering College Department of Computer Science Engineering Tamil Nadu Chennai India Rmk Engineering College Department of Computer Science Engineering Tamil Nadu Chennai India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India

ISBN: (纸本)9781665476553

Crime is a fragment of substantial and predominating concerns in our society and its preclusion is key task Day to day there are huge numbers of offense committed sequentially. This requisite retain track of all the offense and preserving a database for same which may be used for succeeding reference. The present problem faced are maintaining of appropriate dataset of crime and evaluating this data to help in predicting and solving crimes in future. The objective of this project is to dataset which includes several crimes and forecasting the crime types which may transpire in future determining upon various constraints. In this intend, we will be utilizing the technique of machine learning and data science. Prior implementing of the replica model data pre-processing will be done ensuring this feature preference and grading will be done so that precision obtained will be excessive. The K-Nearest Neighbour (KNN) categorization and various other algorithms will be examined for crime data prediction and prevention one with progressing accuracy will be used for implementing. Delusion of dataset will be accepted in terms of graphical depiction of many occurrence for case in point at which duration the culprit rates are huge or at which month the culprit activities are peak. The essence purpose of this intend is to provide a jest idea of how machine learning can be used by the law enforcement agencies to detect, predict and prevent solving crimes at a much quicker rate and thus decrease the crime data. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Temporal Threat Recognition in Supply Chains: Integrating Hidden Markov Models for Proactive Security with AI-Driven Automated Threat Hunting

Temporal Threat Recognition in Supply Chains: Integrating Hi...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and Engineering science, AMATHE 2024

作者： Rathor, Ketan Dhananjayamurthy, B.V. Abdul Jaleel, D. Pal, Subharun Bhavani, P. Nishant, Neerav Gyan Sys Inc. Mumbai India Nitte Meenakshi Institute Of Technology Department Of Mathematics Bangalore India Madanapalle Institute Of Technology & Science Department Of Computer Science & Technology Andhra Pradesh Madanapalle India India K Ramakrishnan College Of Engineering Department Of Artificial Intelligence And Data Science Tamilnadu Trichy India School Of Engineering Babu Banarasi Das University Department Of Cse Lucknow India

ISBN: (纸本)9798350371567

In order to tackle the pressing problem of 'Temporal Threat Recognition in Supply Chains,' this study presents a novel integrated model that combines RNNs with Hidden Markov Models (HMMs). Proactive security measures and operational integrity rely on the prompt and correct identification of temporal risks within the dynamic environment of supply chains. This is the crux of the issue statement. By combining RNN for fine-grained identification with HMM for high-level threat classification, our proposed system provides a holistic approach that can detect both broad patterns and subtle details. Our integrated model outperforms previous work in terms of performance measures, as seen by its 0.92 precision, 0.88 recall, 0.90 F1-Score, and 0.91 total accuracy. The model's usefulness in improving temporal threat identification is confirmed by its outperformance in precision, recall, accuracy, and AUC-ROC, as demonstrated in a comparative comparison with state-of-the-art approaches. The computational efficiency of the model makes it a viable option for realistic supply chain applications in the real world. In addition to bringing a fresh perspective to the field of temporal threat modelling, our study has practical implications for supply chain security and offers researchers and practitioners in the industry with a powerful and effective tool. © 2024 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Salient Region Detection in Images Based on U-Net and Deep Learning 2

Salient Region Detection in Images Based on U-Net and Deep L...

引用

2nd IEEE International Conference on Advanced Technologies in Intelligent Control, Environment, Computing and Communication Engineering, ICATIECE 2022

作者： Kumar, Krishna Marimuthu, M. Das Gupta, Ayan Pant, Bhasker Shukla, Surendra Kumar Kapila, Dhiraj Bansal Institute of Engineering and Technology Department of Computer Science and Engineering Lucknow India Coimbatore Institute of Technology Department of Computing-Data Science Coimbatore India Chandernagore Government College Department of Geography Hugli India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Lovely Professional University Department of Computer Science and Engineering Phagwara India

ISBN: (纸本)9781665493963

Image analysis tasks use salient object detection because it not only identifies important elements of a visual scene but also lessens computational complexity by removing unimportant elements. In this research, we propose a novel salient object recognition method based on a deep learning network that maintains picture information in the mid and low regions. Using a deep learning model, our technique generates a coarse saliency map for the entire target image. The map is then fine-Tuned utilising low-To-mid level information particular to the image. For detection of salient objects, we use a U-Net as our architecture. The saliency map can be predicted pixel by pixel, reducing low-level visual information loss. Our results show that our system regularly outperforms other approaches for detecting salient objects, resulting in superior precision and recall rates. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning for the Identification and Categorization of Fruit Diseases

Leveraging Deep Learning for the Identification and Categori...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Solanki, Shubhangi Singh Chouhan, Siddharth Dwivedi, Abhishek Singh, Uday Pratap Patel, Rajneesh Kumar SIT Lonavala SPPU Department of Computer Engineering 410401 India School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Sehore Kothrikalan466114 India Manipal University Jaipur Department of Data Science and Engineering Rajasthan Jaipur303007 India Central University of Jammu Department of Mathematics 181143 India

ISBN: (纸本)9798350379525

The precise assessment of fruit quality and the detection of illnesses are critical tasks in the agriculture sector. One important component that has a direct impact on consumers' physical well-being and inclination to buy is the freshness of fruits and vegetables. Analyzing the degree of freshness in fruits and vegetables is important since it has a big impact on how market prices are set. Fruit and vegetable classification and identification by machine vision is difficult because of their comparable colors, textures, and external environmental elements including illumination, reflections, and complicated backdrops. This study presents a comprehensive overview of methods for detecting and classifying the quality of fruits and plants using several strategies for feature extraction and classification. Several academics have suggested various ways including binarization, histogram-based approaches, Gray Level Co-occurrence matrix, machine learning techniques, and deep learning. The outcome of our study showcases the results obtained from different methodologies, together with their respective benefits and challenges. In conclusion, we will discuss potential areas for improvement and future directions for additional research. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

DPT‐tracker:Dual pooling transformer for efficient visual tracking

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Enhancing Lip Reading for the Hearing Impaired using CNN AND LSTM

Enhancing Lip Reading for the Hearing Impaired using CNN AND...

引用

International Conference on Computational Innovations and Engineering Sustainability (ICCIES)

作者： S. V. Vasantha M. Vineela Reddy S. Kruthika R. Sudhansh Mudhiraj Shanmugasundaram Hariharan Department of Computer Science and Engineering Vardhaman College of Engineering Hyderabad India Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798331536695

ISBN: (纸本)9798331536701

Speech recognition through lip reading can help people with hearing loss, especially in noisy environments. Traditional communication tools are not designed to handle the needs of people who are deaf or hard to hear. This study developed a method that combines short term neural networks (LSTM) with convolutional neural networks (CNN) to record spontaneous words based on the appearance of lips. It involves preprocessing video frames, including resizing and filling with black frames when necessary, and using transformations to increase the predicting ability of the model. This model uses Time Distributed CNN layers and bidirectional LSTM layers to identify the time dependent physical properties of the image. This integration allows the system to correctly interpret and convert movement of lip into text. The model is trained using a custom data generator application that generates augmented data. The results of this study show significant improvements in lip reading accuracy upto 95%. People with hearing loss can independently understand more of the spoken content without the constant assistance of an interpreter or translator.

关键词： Visualization Accuracy Translation Lips Video sequences Auditory system Speech recognition data augmentation data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Low-Resource Named Entity Recognition: Can One-vs-All AUC Maximization Help? 23

Low-Resource Named Entity Recognition: Can One-vs-All AUC Ma...

引用

23rd IEEE International Conference on data Mining, ICDM 2023

作者： Nguyen, Ngoc Dang Tan, Wei Du, Lan Buntine, Wray Beare, Richard Chen, Changyou Monash University Department of Data Science and Ai Melbourne Australia VinUniversity College of Engineering and Computer Science Hanoi Viet Nam Faculty of Medicine Peninsula Clinical School Melbourne Australia University at Buffalo Department of Cs and Engineering New York United States

ISBN: (纸本)9798350307887

Named entity recognition (NER), a task that identifies and categorizes named entities such as persons or organizations from text, is traditionally framed as a multi-class classification problem. However, this approach often overlooks the issues of imbalanced label distributions, particularly in low-resource settings, which is common in certain NER contexts, like biomedical NER (bioNER). To address these issues, we propose an innovative reformulation of the multi-class problem as a one-vs-all (OVA) learning problem and introduce a loss function based on the area under the receiver operating characteristic curve (AUC). To enhance the efficiency of our OVA-based approach, we propose two training strategies: one groups labels with similar linguistic characteristics, and another employs meta-learning. The superiority of our approach is confirmed by its performance, which surpasses traditional NER learning in varying NER settings. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING IMPROVEMENTS FOR SPARSE SPATIAL FIELD RECONSTRUCTION

arXiv

引用

arXiv 2024年

作者： Sunderhaft, Robert Frank, Logan Davis, Jim Department of Data Analytics Department of Computer Science and Engineering Ohio State University United States

Accurately reconstructing a global spatial field from sparse data has been a longstanding problem in several domains, such as Earth sciences and Fluid Dynamics. Historically, scientists have approached this problem by employing complex physics models to reconstruct the spatial fields. However, these methods are often computationally intensive. With the increase in popularity of machine learning (ML), several researchers have applied ML to the spatial field reconstruction task and observed improvements in computational efficiency. One such method [1] utilizes a sparse mask of sensor locations and a Voronoi tessellation with sensor measurements as inputs to a convolutional neural network for reconstructing the global spatial field. In this work, we propose multiple adjustments to the aforementioned approach and show improvements on geoscience and fluid dynamics simulation datasets. We identify and discuss scenarios that benefit the most using the proposed ML-based spatial field reconstruction approach. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Colon Cancer Tissue Classification Using ML 6

Colon Cancer Tissue Classification Using ML

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Tripathi, Ashish Kumar, Kuldeep Misra, Anuradha Chaurasia, Brijesh Kumar Amity University Lucknow Amity School of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Lucknow India Bond University Center for Data Analytics Bond Business School Gold CoastQLD Australia Pranveer Singh Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Kanpur India

ISBN: (纸本)9798350346961

In this paper, the classification of colon cancer tissues by means of machine learning approaches is evaluated. In today's world, a revolutionary advancement has come in the classification and diagnosis of diseases in the medical and healthcare sectors. Deep learning classifiers and machine learning methods are now broadly applied to accurately diagnose a number of diseases. Cancer is one of the world's most significant roots of death, appealing to the lives of one person out of every six. As per the national library of medicine, the third leading cause of death worldwide is colorectal cancer. Identifying an illness at a premature stage increases the chances of survival. Automated diagnosis and the classification of tissues from images can be completed much more quickly with the use of artificial intelligence. A publicly available IoT dataset CRC-VAL-HE-7K consisting of 7180 images, distributed among nine types of colorectal tissues: background, lymphocytes, adipose, mucus, colorectal adenocarcinoma epithelium, normal colon mucosa, debris, cancer-associated stroma, and, smooth muscle is used after preprocessing. Feature extraction is done by applying Differential-Box-Count on all blocks of images. The dataset is evaluated by these Machine Learning (ML) procedures: K-Nearest Neighbor, Support Vector Machine, Decision Tree, Random Forest, Extreme Gradient Boosting, and Gaussian Naive Bayes. Results show that the performance of Extreme Gradient Boosting is the best and most viable approach.. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

META-LEARNING TO CALIBRATE GAUSSIAN PROCESSES WITH DEEP KERNELS FOR REGRESSION UNCERTAINTY ESTIMATION A PREPRINT

arXiv

引用

arXiv 2023年

作者： Iwata, Tomoharu Kumagai, Atsutoshi NTT Communication Science Laboratories NTT Corporation NTT Computer and Data Science Laboratories NTT Corporation

Although Gaussian processes (GPs) with deep kernels have been succesfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propose a meta-learning method for calibrating deep kernel GPs for improving regression uncertainty estimation performance with a limited number of training data. The proposed method meta-learns how to calibrate uncertainty using data from various tasks by minimizing the test expected calibration error, and uses the knowledge for unseen tasks. We design our model such that the adaptation and calibration for each task can be performed without iterative procedures, which enables effective meta-learning. In particular, a taskspecific uncalibrated output distribution is modeled by a GP with a task-shared encoder network, and it is transformed to a calibrated one using a cumulative density function of a task-specific Gaussian mixture model (GMM). By integrating the GP and GMM into our neural network-based model, we can meta-learn model parameters in an end-to-end fashion. Our experiments demonstrate that the proposed method improves uncertainty estimation performance while keeping high regression performance compared with the existing methods using real-world datasets in few-shot settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

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：