检索结果-内蒙古大学图书馆

Multimodal Attention CNN for Human Emotion Recognition 1

International Conference on. Cryptology and Network Security with Machine Learning, ICCNSML 2023

作者： Tiwary, Gyanendra Chauhan, Shivani Goyal, Krishan Kumar Department of Computer Science and Engineering Bhagwant University Ajmer India Department of Computer Application Raja Balwant Singh Management Technical Campus Agra India

ISBN: (数字)9789819706419

ISBN: (纸本)9789819706402

The human face is the mirror of the mind. The face generally tells all that is going on in one’s heart and mind. Just by looking at the faces of our known ones, we may easily guess their mood. But many times, when we meet some unfamiliar person, it’s hard to get his or her mood just by looking at their faces. This is just because the person may have a certain facial structure that makes them by default look angry, happy, or sad. So, we need to spend some time with that person to analyse other parameters before concluding their state of mood. The current work proposed a novel approach that integrates facial images with electroencephalography (EEG) signals for facial expression recognition tasks. When attention-based deep CNN analyses the facial traits of the subject, a parallel Long Short-Term Memory (LSTM) network analyses the EEG signals. A late fusion network combines the features extracted from both networks, and finally, a classification network tells about what is the current mood of the subject. Combining multiple modalities for emotion recognition has shown promising results when compared with other state-of-the-art models. There are multiple real-life applications of emotion recognition models, such as Advertisement Industry, Human–Robot Interaction, Automatic Depression Detection, Mood Audio/Video Players, etc. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Medicine and Disease Association Prediction via Attention-Based Medical Heterogeneous Information Network Representation Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2022年第1期49卷 69-78页

作者： Zhang, Bin Yang, Dan Lin, Zhihuang Master of Computer Science and Software Engineering Department University of Science and Technology Liao Ning Anshan China School of Computer Science and Software Engineering University of Science and Technology Liao Ning Anshan China

Knowledge of medication and disease has been rapidly accumulated. Also, an increasing number of researchers have paid more attention to predicting medicine-disease associations by machine learning methods. The associations of entities in the medical heterogeneous information network involve different association types. In this paper, we propose MHIN-MD, a representation learning of medical heterogeneous network model to solve the association between medicines and diseases in medical heterogeneous information network. Specifically, we first construct a medical heterogeneous information network contains diseases, medicines, diagnosis, etc. Next, we design a neural network model to learn the feature vector representation of medical nodes information. We try to find the association between medicines and diseases through the characteristics of medicines structure and the interaction between medicines. Using the Euclidean distance to calculate medicine similarity and disease similarity, generates a set of similar nodes between medicines and diseases to prediction association between medicines and diseases. Finally, our extensive experiments on MIMIC- III datasets and DrugBank datasets, the result demonstrates that MHIN-MD can outperform baselines in the association prediction. © 2022. All Rights Reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model 4th

Weakly Supervised Intracranial Hemorrhage Segmentation with...

引用

4th International Workshop on Imaging and Treatment Challenges, SWITCH 2024, and 6th International Challenge on Ischemic Stroke Lesion Segmentation Challenge, ISLES 2024, Held in Conjunction with Medical Image Computing and computer Assisted Intervention, MICCAI 2024

作者： Spiegler, Pascal Rasoulian, Amirhossein Xiao, Yiming Department of Computer Science and Software Engineering Concordia University Montreal Canada NeuroRx Research Montreal Canada

ISBN: (纸本)9783031811005

Intracranial hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis to improve treatment outcomes and patient survival rates. Recent advancements in supervised deep learning have greatly improved the analysis of medical images, but often rely on extensive datasets with high-quality annotations, which are costly, time-consuming, and require medical expertise to prepare. To mitigate the need for large amounts of expert-prepared segmentation data, we have developed a novel weakly supervised ICH segmentation method that utilizes the YOLO object detection model and an uncertainty-rectified Segment Anything Model (SAM). In addition, we have proposed a novel point prompt generator for this model to further improve segmentation results with YOLO-predicted bounding box prompts. Our approach achieved a high accuracy of 0.933 and an AUC of 0.796 in ICH detection, along with a mean Dice score of 0.629 for ICH segmentation, outperforming existing weakly supervised and popular supervised (UNet and Swin-UNETR) approaches. Overall, the proposed method provides a robust and accurate alternative to the more commonly used supervised techniques for ICH quantification without requiring refined segmentation ground truths during model training. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Image Classification in Monkey Species using Image Classifiers of Keras 1

Image Classification in Monkey Species using Image Classifie...

引用

1st International Conference on software, Systems and Information Technology, SSITCON 2024

作者： Singh, Neelam Upreti, Manisha Dwivedi, Ayushi Rawat, Vandana Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department of Computer Application Dehradun India

ISBN: (纸本)9798350352931

A species is biologically basic classification and taxonomic rank of an organism. Among the many common names for the mammals that make up the suborder Simiiformes (sometimes known as the simians), 'monkey' is among the most common. The traditional classification of all members of the group currently known as simians as monkeys. Different classifiers are used to categorize the various kinds of monkeys based on their photos. Assigning a name or class to an image is the work of image classification. In the research paper, different image classifiers of Keras are used for image classification in monkey species. A dataset of 10 distinct monkey species was used to test out many different classifiers. Keras comes preloaded with a variety of Convolutional Neural Networks, including VGG16, VGG19, ResNet50, ResNet-50 V2, ResNeXt101, Inception V3, and Xception. We compared the performance of other classifiers and discovered that ResNeXt-101 achieved the best accuracy (99.98%). © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Boosting Write Performance of KV Stores: An NVM -Enabled Storage Collaboration Approach 40

Boosting Write Performance of KV Stores: An NVM -Enabled Sto...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Wang, Yi He, Jiajian Sun, Kaoyi Dong, Yunhao Chen, Jiaxian Ma, Chenlin Zhou, Amelie Chi Mao, Rui College of Computer Science and Software Engineering Shenzhen University China Hong Kong Baptist University Department of Computer Science Hong Kong

ISBN: (纸本)9798350317152

As the most common data structure for key-value stores, LogStructured Merge Tree (LSM-tree) can eliminate random write operations and keep acceptable read performance. However, write stall and write amplification introduced by the leveled compaction of LSM-tree significantly degrade the system performance. The emerging non-volatile memory (NVM) provides byte-addressable access and low-latency data persistence. Integrating DIMM-interface NVM in the design of the LSM-tree can potentially alleviate the write stall and write amplification issue, as the access speed of NVM is several orders of magnitude faster than hard disk drives or flash memory-based solid-state drives. This hybrid storage should be carefully designed, requiring new architectural and key-value structural support. This paper presents ZigZagDB, an NVM-enabled data man-agement scheme for LSM-tree-based key-value stores. ZigZagDB adds additional layers of key-value stores and uses non-volatile memory as the storage media to hold these additional layers of data. The newly designed key-value stores alternately access the data from either SSD or NVM. This 'ZigZag' shape of storage collaboration and synchronization can benefit write efficiency and space utilization. By utilizing the NVM with very limited capacity, the redesigned organization of LSM-tree can effectively solve the write stall and write amplification issue. We demonstrate the viability of the proposed ZigZagDB using a set of extensive experiments. Experimental results show that ZigZagDB can significantly reduce the write amplification and boost the throughput in comparison with representative schemes. © 2024 IEEE.

关键词： Flash memory

来源：评论

学校读者我要写书评

暂无评论

Home Automation-Based Health Assessment Along Gesture Recognition via Inertial Sensors

引用

computers, Materials & Continua 2023年第4期75卷 2331-2346页

作者： Hammad Rustam Muhammad Muneeb Suliman A.Alsuhibany Yazeed Yasin Ghadi Tamara Al Shloul Ahmad Jalal Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of Humanities and Social Science Al Ain UniversityAl Ain15551UAE Department of Computer Engineering Korea Polytechnic University237 Sangidaehak-ro Siheung-siGyeonggi-do15073Korea

Hand gesture recognition (HGR) is used in a numerous applications,including medical health-care, industrial purpose and sports *** have developed a real-time hand gesture recognition system using inertialsensors for the smart home application. Developing such a model facilitatesthe medical health field (elders or disabled ones). Home automation has alsobeen proven to be a tremendous benefit for the elderly and disabled. Residentsare admitted to smart homes for comfort, luxury, improved quality of life,and protection against intrusion and burglars. This paper proposes a novelsystem that uses principal component analysis, linear discrimination analysisfeature extraction, and random forest as a classifier to *** have achieved an accuracy of 94% over the publicly benchmarked HGRdataset. The proposed system can be used to detect hand gestures in thehealthcare industry as well as in the industrial and educational sectors.

关键词： Genetic algorithm human locomotion activity recognition human–computer interaction human gestures recognition principal hand gestures recognition inertial sensors principal component analysis linear discriminant analysis stochastic neighbor embedding

来源：评论

学校读者我要写书评

暂无评论

Robust steganographic approach using generative adversarial network and compressive autoencoder

引用

Multimedia Tools and applications 2024年 1-38页

作者： Qasaimeh, Malik Qtaish, Alaa Abu Aljawarneh, Shadi Department of Computer Information Systems Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan Department of Software Engineering co-joint with the Department of Cyber Security Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan

Nowadays, social media applications and websites have become a crucial part of people’s lives;for sharing their moments, contacting their families and friends, or even for their jobs. However, the fact that these valuable data are transferred via the Internet and open channels, which are vulnerable to attacks and espionage, requires using defense methods to improve the security of data transmission. Recently, the progress of Deep Learning (DL) inspired researchers to use it with security methods such as steganography, the art of hiding secret data in unrelated content. DL and steganography combined enhanced the hiding properties, especially in the Coverless Image Steganography (CIS) methods. In this paper, we propose a Compressive Coverless Image Steganography (CCIS) model, which is a generated-based CIS, to improve the capacity and robustness of Steganography. This model uses the compressive autoencoder to compress the message, thus increasing the capacity, and uses the Generative Adversarial Network (GAN) to generate a stego image from the compressed vector, thus enhancing concealment ability, besides using a regression model and optimization method to extract the data. Another version was designed to enable sending binary messages by replacing the compressive autoencoder network with a robust mapping rule. Experiments show that the proposed model could improve the characteristics of Steganography. Furthermore, the proposed model could extract binary messages with 256 bits from attacked stego images with 99% recovery accuracy. Thus, capacity and robustness were enhanced using our model with both images and text as secret messages. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

MemoChat App: An Advancement in Existing WhatsApp 1

MemoChat App: An Advancement in Existing WhatsApp

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Takkar, Hardik Sharma, Krishna Karun Kumar, Nagadamudi Vijay Jha, Manish Kumar Saraswat, Bal Krishna Tyagi, Himani Sharda University Computer Science and Engineering Department Uttar Pradesh Greater Noida India Sharda University Computer Science and Application Department Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350356816

With over 1 billion users in 180 countries, it's no surprise that WhatsApp is one of the most popular instant messaging apps available today. Whether you're looking to make voice or video calls, or simply share messages, photos, and videos with friends and family, this app is an excellent choice. Not only is it free of charge, but it's also incredibly reliable and easy to use. With its user-friendly interface and convenient features, WhatsApp is the perfect way to stay connected with loved ones, no matter where they are in the world. With regular updates, WhatsApp is becoming even more user-friendly and interactive. Though there may be some issues, solutions are always available. By addressing these problems head-on, WhatsApp can provide a unique and unparalleled messaging experience, setting itself apart from the competition. The future of WhatsApp is bright, and no one can't wait to see what's in store! Have you ever encountered the problem of not being able to send messages to specific members of a group? Unfortunately, with the current system, messages sent to a group are received by everyone in the group. However, there are ways to work around this issue. To access the Include and Exclude options while sending a message, simply click on the Arrow symbol located next to the attachment icon. This will open up a new section where you can choose which members to include or exclude from the message. It's a simple and effective way to ensure that your messages are only sent to the intended recipients. © 2024 IEEE.

关键词： Instant messaging applications

来源：评论

学校读者我要写书评

暂无评论

Classification of Potato Leaf Disease using Deep Learning 3

Classification of Potato Leaf Disease using Deep Learning

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Singh, Neelam Sharma, Deeksha Dev, Saurav Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Graphic Era Deemed to Be University Department of Computer Application Dehradun India

ISBN: (纸本)9798350354171

Deep learning is one of the subdomains of Artificial Intelligence. With the advantages of automatic learning and feature extraction, in recent years, it has become a hot topic in academic and industrial circles. Meanwhile, this has emerged as one of the hotspots within agricultural plant protection research, including plant disease recognition and pest range assessment. Deep learning in plant disease recognition can avoid the shortcomings of artificial selection of features of the disease spot, making the feature extraction of plant diseases more objective, promoting research efficiency, and increasing technological transformation speed. The goal of this work is to analyze potato leaf diseases using CNN in order to determine the model's optimal performance using a large dataset (10,000 photos) of potato leaves in the analysis. The most effective model will support farmers in making decisions that will keep potato production from declining. This investigation revealed that the model worked better when forty epochs were applied to the dataset of 10,000 photos. Additionally, three different epochs were applied and achieved 100% accuracy for 30 and 50 as achieved 99.97% and 99.98% respectively. By offering recommendations for how to categorise Potato Leaf Disease with the best result, the study made a substantial contribution to the agricultural industry and farmers. While working with big volumes of data, researchers should be concerned about the system because running code takes longer time. To focus this, a dataset including 2152 photos was gathered from Kaggle, with an additional 7848 images sourced from various platforms such as Google and raw data from Potato Field. To determine which epochs performed the best, a range of epochs were applied and results shows that 40 epochs led to 100% accuracy. © 2024 IEEE.

关键词： artificial intelligence deep learning potato disease

来源：评论

学校读者我要写书评

暂无评论

Identification of Age, Plumage, and Sex of Bird Species Using Pre-Trained Deep Convolutional Neural Network 2

Identification of Age, Plumage, and Sex of Bird Species Usin...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Banerjee, Sourik Gupta, Richa Pandian, J. Arun Saranya, S. Mariappan, L. Thanga Vellore Institute of Technology Department of Computer Application Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India K.Ramakrishnan College of Engineering Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350306415

The research aims to identify the age, plumage, and sex of bird species using standard Pre-trained Deep Convolutional Neural Networks (Pre-DCNNs). The proposed work involves collecting various bird images, which are then used for training and validating the pre-trained DCNNs. The dataset contains 200 images of four bird species. The dataset was split into twelve labeled classes of images based on age, plumage, and sex. The standard image manipulation techniques such as cropping, flipping, mirroring, rotating, shearing, and skewing were used as image augmentation techniques to increase the size of the proposed dataset. The proposed data is preprocessed, including feature extraction and data cleaning, to ensure the performance of the Pre-Trained DCNNs. The Pre-Trained DCNNs were trained on 90% of the dataset to recognize patterns in bird images. The accuracy of the pre-trained DCNNs was evaluated using metrics such as classification accuracy. The research acknowledged the advantages and limitations of the standard Pre-Trained DCNNs on the age, plumage, and sex of birds using the images. Also, it compares the performance of the Pre-Trained DCNNs on the proposed bird species image dataset. © 2024 IEEE.

关键词： Bird Plumage Identification Bird Species Identification Deep Convolutional Neural Networks Image Augmentation Pre-trained 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：