检索结果-内蒙古大学图书馆

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Deepa, R. Surendran, R. SRM Institute of Science and Technology Department of Computer Science and Applications Tamilnadu Chennai India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM institute of Science and Technology Department of Computing Technologies Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

In understanding human emotions, sentiment analysis has been invaluable in social media monitoring, consumer comment analysis, and psychological evaluations. Customer service, human-computer interface, and public mood comprehension depend on appropriate emotion categorisation. Despite its potential, sentiment analysis struggles with sarcasm, multimodal data integration, and emotion processing. Implementing real-time applications requires improving deep learning model computational complexity. Multimodal Optimised Emotion Analysis using Deep Learning (MOEA-DL) uses CNNs for image processing, RNNs for text., and LSTM networks for sequential audio data. This improves emotion recognition by combining modality strengths. Marketing sentiment, mental health monitoring, social media sentiment, and consumer feedback use MOEA-DL. Multimodal solutions are better than text-based ones for communicating emotion. Customer contacts, film reviews, and social media platforms are used to evaluate the proposed strategy. According to simulations, MOEA-DL categorises emotions more accurately and robustly than previous sentiment analysis methods. Its adaptive neural network lets the system learn and perform well in many cultural and language environments. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Securing Data storage in Cloud after Migration using Immutable Data Dispersion 4

Securing Data storage in Cloud after Migration using Immutab...

引用

4th International Conference for Emerging technology, INCET 2023

作者： Rajesh Kumar, C. Aroul Canessane, R. Sathyabama Institute of Science &technology Chennai India Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350335750

Cloud computing has emerged as a technology behemoth with applications in a wide range of fields. When data is being migrated from offline data centres and stored in multiple cloud environments part of the control is always with the Cloud Service Providers(CSPs) leads to security concerns. The data stored in the cloud may sometimes be compromised even though the CSPs may take precautions to avoid such situations. In this paper, we discuss securely storing the data using the data dispersion technique by breaking the data into multiple segments and combining it with encryption along with replication. The division of data and storing it in the cloud helps in protecting the complete data even if an attacker tries to access the data it will not be easy for him to make sense of the retrieved data because the data is already being encrypted and combined with dispersion and replication adds to the complexity of retrieval. Security is achieved as the dispersed data is spread across multiple locations which makes it difficult for an attacker to get all the segments. In most scenarios be able it depends on traditional encryption techniques alone to protect the data. Here, We propose focusing more on how data is stored in the cloud to relieve the system of costly computational methodologies. In this strategy, the trade-off between security and the data retrieval time must also be considered. © 2023 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Capsule Network Approach for Image Classification 4th

Capsule Network Approach for Image Classification

引用

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Marjit Singh, Moirangthem Kumar Sarkar, Nayan Department of Computer Science and Engineering North Eastern Regional Institute of Science and Technology Arunachal Pradesh Itanagar India

ISBN: (纸本)9789819994410

Numerous deep learning (DL) models based on convolutional neural network (CNN) have been developed for image classification. Though the CNN models attained outstanding performance, its architecture contains certain limitations such as loss of information in the pooling layer and no spatial relationship among the features of an object. The development of capsule network (CapsNet) has overcome the drawbacks of CNN. The CapsNet works on a set of capsules, and each capsule comprises a set of features. The CapsNet consists of a convolution layer, a primary capsule layer, image caps and a fully connected (FC) layer. In this paper, a variant of CapsNet approach is proposed by tuning the parameters of the original CapsNet and replacing ReLU with AReLU activation function in each FC layer. The classification performance of the proposed approach is evaluated on the Plant Village (PV) and Tomato datasets. 80% of the datasets were trained and 20% were tested. The proposed approach considering filter size of 5 × 5 in the feature extraction layer with AReLU activation function in each FC layer delivers 94.02% and 94.06% classification accuracies on PV and Tomato datasets respectively. Compared to other modern approaches, the proposed approach delivered better results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Investigation of Ce/BEA as a passive NO_(x)adsorber:*** occurrences of cerium and adsorption behavior

引用

Journal of Rare Earths 2024年第7期42卷 1265-1271,I0003页

作者： Minghui Yu Yiying Ding Xiaojie Yu Siwei Yan Meiqing Shen Jianqiang Wang Jun Wang Gurong Shen School of Materials Science and Engineering Tianjin UniversityTianjin300350China School of Chemical Engineering and Technology Tianjin UniversityTianjin300350China National Rare Earth Catalysis Research Institute Dongying257000China

Ce/BEA has great potential as a passive NO_(x)absorber(PNA)to reduce the NO_(x)emissions during the cold start phase especially in diesel engine for its high resistance to CO and suitable NO_(x)desorption temperature ***,as a novel material,its physical and chemical properties still remain *** this work,Ce/BEA was synthesized by ion-exchange method to identify the active species in NO_(x)adsorption,compared with aggregated Ce species in Ce/SiAlO_(x) prepared by impregnation method.X-ray diffraction(XRD),high resolution-transmission electron microscopy(HR-TEM)and aberration-corrected-scanning transmission electron microscopy(AC-STEM)were performed to confirm the isolated single atom formation of Ce species in Ce/***-vis diffraction reflection spectra(DRS)and X-ray photoelectron spectroscopy(XPS)were conducted to find the difference of chemical environment between the isolated Ce species and aggregated *** performance evaluation and temperature programmed reduction of hydrogen(H_(2)-TPR)results show the high NO_(x)storage capacity and active oxygen species quantity in Ce/*** is also found that the main NO_(x)adsorption species are Ce^(4+)-O^(∗)rather than Ce^(3+).NO_(x)-diffuse reflectance infrared Fourier transform spectroscopy(NO_(x)-DRIFTS)confirms that the bidentate nitrite species are the critical NO_(x)adsorption intermediates and the conception of NO_(x)adsorption and desorption processes is proposed.

关键词： Passive NO_(x)absorber Ce/BEA Isolated Ce species Rare earths

来源：评论

学校读者我要写书评

暂无评论

Biomolecular Analysis of Soil Samples and Rock Imagery for Tracing Evidence of Life Using a Mobile Robot 8

Biomolecular Analysis of Soil Samples and Rock Imagery for T...

引用

8th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2023

作者： Ahasan Siddique, Shah Md Rinath, Ragib Tahshin Mosharrof, Shakil Mahmud, Syed Tanjib Ahmed, Sakib Military Institute of Science and Technology Department of Mechanical Engineering Dhaka Bangladesh Military Institute of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350315516

The search for evidence of past life on Mars presents a tremendous challenge that requires the usage of very advanced robotic technologies to overcome it. Current digital microscopic imagers and spectrometers used for Astro biological examination suffer from limitations such as insufficient resolution, narrow detection range, and lack of portability. To overcome these challenges, this research study presents modifications to the Phoenix rover to expand its capability for detecting biosignatures on Mars. This paper examines the modifications implemented on the Phoenix rover to enhance its capability to detect a broader spectrum of biosignatures. One of the notable improvements comprises the integration of advanced digital microscopic imagers and spectrometers, enabling high-resolution examination of soil samples. Additionally, the mechanical components of the device have been reinforced to enhance maneuverability and optimize subsurface sampling capabilities. Empirical investigations have demonstrated that Phoenix has the capability to navigate diverse geological environments and procure samples for the purpose of biomolecular analysis. The biomolecular instrumentation and hybrid analytical methods showcased in this study demonstrate considerable potential for future astrobiology missions on Mars. The potential for enhancing the system lies in the possibility of broadening the range of detectable biomarkers and biosignatures. © 2023 IEEE.

关键词： Rovers

来源：评论

学校读者我要写书评

暂无评论

Optimized Crop Prediction System using Feature Selection Techniques with Machine Learning Classifiers 1

Optimized Crop Prediction System using Feature Selection Tec...

引用

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Sagana, C. Keerthika, P. Devendran, K. Thangatamilan, M. Karthikheyan, A.V. Magendraprasat, M.G. Mathiyalagan, M. Kongu Engineering College Computer Science and Engineering Erode India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350371185

The Crop Prediction System stands as a pioneering milestone in precision agriculture, harnessing the capabilities of data-driven decision-making to revolutionize crop forecasting and resource allocation. This comprehensive project meticulously collects and pre-processes data, employing feature selection techniques to streamline data input for machine learning models. An ensemble model, skillfully constructed, exemplifies the potential for precise crop recommendations, carrying wide-ranging implications for sustainable agriculture. The project unfolds with an introduction to the significance of precision agriculture, the process of data collection and pre-processing, and the incorporation of feature selection methods. Subsequently, it delves into the machine learning phase, exploring the performance of various classifiers and the selection of a robust ensemble model. Hyperparameter tuning and optimization techniques refine the system's accuracy and efficiency. The project is underscored by a user-friendly interface, ensuring accessibility to a diverse range of users. This innovation transcends borders, enabling farmers to make informed decisions and resource allocation for increased crop yields. The Crop Prediction System offers a glimpse of the future, where data-driven technologies are poised to revolutionize agriculture practices worldwide, promising a more sustainable, productive, and economically stable future. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Facial Expression Recognition through a Hierarchical Cross-Attention Graph Convolutional Network

Multi-Modal Facial Expression Recognition through a Hierarch...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Raman, Ramakrishnan Kumar, Vikram Pillai, Biju G. Rabadiya, Dhaval Patre, Smruti Meenakshi, R. India SRV Media Pvt. Ltd. India Faculty of Management It & Business Analytics India Parul Institute of Technology Parul University Computer Science and Engineering Faculty of Engineering and Technology India India Chennai Institute of Technology Computer Science and Engineering India

ISBN: (纸本)9798350359688

In the rapidly evolving field of computer vision and machine learning, recognizing human facial expressions with high accuracy remains a pivotal challenge. This paper introduces a novel Multi-Modal Facial Expression Recognition (MMFER) framework, leveraging a Hierarchical Cross-Attention Graph Convolutional Network (HCA-GCN) to enhance the accuracy and robustness of facial expression recognition. Our proposed HCA-GCN model systematically integrates multi-modal data sources, including visual imagery and depth information, to capture the complex and subtle nuances of human facial expressions. The hierarchical structure of our model allows for the efficient processing of multi-modal data through distinct pathways, ensuring that relevant features from each modality are effectively extracted and combined. The cross-attention mechanism within our framework meticulously aligns and emphasizes inter-modal features, fostering a synergistic integration that boosts the model's ability to discern intricate facial expressions. Through extensive experiments on benchmark datasets, our approach demonstrates significant improvements over existing methods, showcasing superior performance in recognizing a wide range of facial expressions under various conditions. The implementation details, including algorithms and mathematical expressions, are meticulously described to facilitate replication and further research. Results and discussions highlight the model's efficacy, underscored by comparative analysis and visualizations. Our findings indicate that the HCA-GCN model not only advances the state-of-the-art in facial expression recognition but also opens new avenues for research in multi-modal learning. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

A Disaster Prediction Ensemble Classifier Using Artificial Intelligence

A Disaster Prediction Ensemble Classifier Using Artificial I...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Bharathi, V. Saranya, A. Shukla, Garima Shekhawat, Deepika Awasthi, Vanshaj Kumar, C.N.S. Vinoth Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Amity University Amity School of Engineering and Technology Department of Computer Science and Engineering Mumbai India Amity University Department of Computer Science and Engineering Mumbai India Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur Chennai India

ISBN: (纸本)9798331533311

Natural and man-made disasters may have severe impacts, but disaster prediction can help lessen such effects. The natural catastrophes that strike India on a regular basis cause immense devastation in terms of human lives and material possessions. Predicting the start and development of disasters in real-time is essential for reducing their effect. For more precise and trustworthy catastrophe predictions, this research presents an AI-powered catastrophe Ensemble B-Classifier network (DE BCN). The DPEC ensemble technique improves forecast accuracy over individual models by integrating various predictive outputs from numerous machine learning models that specialise in distinct kinds of disasters. This is where the data was originally pulled from Kaggle. To finish off the preprocessing, the norma clash filter was used. The next step is to use the optimisation method known as mustard twin swarm to extract characteristics that are connected to the tragedy. With any luck, the calamity Ensemble-B Classifier network will be able to forecast the calamity. Python and the Kaggle database were the environments used to carry out the investigation. According to the results of the simulations, the suggested approach is better than the current standard for predicting the catastrophic state. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Autotrack: a framework for query-based vehicle tracking and retrieval from CCTV footages using machine learning at the edge

引用

International Journal of Information technology (Singapore) 2023年第7期15卷 3827-3837页

作者： Sreedhar, Sreela Philip, Abin Oommen Sreeja, M.U. Department of Computer Science and Engineering Toc H Institute of Science and Technology Ernakulam India Department of Electronics Cochin University of Science and Technology Kochi India Department of Computer Science and Engineering-Cybersecurity Indian Institute of Information Technology Kottayam (IIIT Kottayam) Kottayam India

Automobile theft and hit and run incidents have become ever rampant than before urging the need for automated tracking systems. However, prompt detection of the vehicle involved in incident and recovery of the stolen vehicle is crucial as these are immediately forged to reduce the chances of getting caught. Hence, the proposed model puts forth a query-based framework to intelligently detect and track vehicles from CCTV surveillance footages using queries involving custom input features such as model, make, colour and license plate number. The model uses a combination of techniques for detecting the vehicle make and model, tracking vehicle, and for identifying the license plate number based on You Only Look Once (YOLO), Kalman filters, and Tesseract respectively. Further, the model performs vehicle detection and tracking from multiple surveillance videos which can ensure that the suspicious vehicle which is reported of either theft, license plate forgery or any unusual activity like hit and run cases is located immediately. The detection model is trained and deployed on edge device integrated to CCTVs and hence overcoming the drawbacks associated with a centralized system. The performance of the proposed vehicle detection model compared to baseline models on the basis of popular classification metrics precision, recall and f1-score proves the superiority of the proposed model compared to the existing ones. Additional experimental analysis of the entire framework further establishes the relevance of the combination of selected input features as well as emphasizes the significance of query-based models over its generic counterparts. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Edge computing Kalman filter Object detection Tracking Vehicle detection YOLO

来源：评论

学校读者我要写书评

暂无评论

Phenolic Based Porous Carbon Fibers with Superior Surface Area and Adsorption Efficiency for Radioactive Protection

引用

Advanced Fiber Materials 2023年第4期5卷 1431-1446页

作者： Yufei Gao Ying Huo Mingyi Chen Xingdong Su Jie Zhan Liang Wang Feng Liu Jian Zhu Yuan Zeng Jie Fan Zesheng Li Rouxi Chen Hsing‑Lin Wang Department of Materials Science and Engineering Southern University of Science and TechnologyShenzhen 518055China School of Textiles Science and Engineering Tiangong University of TechnologyTianjin 300384China China Nuclear Power Technology Research Institute Co.Ltd Shenzhen 518028China Institute of Frontier and Intersectional Sciences Southern University of Science and TechnologyShenzhen 518055China

Radioactive iodine element mainly in CH3I is a key fission product of concern in the nuclear fuel cycle,which directly threat-ens human health if released into the *** capture of the I element is essential for human health *** iodine filter,consisting of an activated carbon inner core and cotton filter,is the most common radioactive iodine pro-tection ***,the activated carbon inside the iodine filter suffers from the weak adsorption efficiency and high ***,a process based on a strong alkali activation method was developed to significantly improve iodine absorption and reduce the cost.A series of flexible porous carbon fibers with a high specific surface area(up to about 1,500~2,200 m^(2)/g)were prepared by carbonation of the phenolic resin fibers(PF,prepared through melt spinning and crosslink)followed by activation via KOH ***,the nitrogen-doped sp^(2)-heterogeneous carbon atoms were prepared by add-ing nitrogen sources such as urea which led to a high surface area nano-porous fibers with an average pore size of~2.4 *** nitrogen-doped porous carbon fibers exhibit very high adsorption for liquid iodine and iodine *** liquid iodine adsorption capacity of nitrogen-doped porous carbon NDAC-4 prepared under 800°C reaches 2,120 mg/g,which is 2.1 times higher than that of the commercial iodine filter,and for iodine vapor the capacity can reach 5,330 mg/***,the CH_(3)I adsorption capacity is 510 mg/g,which is 3.4 times higher than that of commercial unmodified viscose fibers and has greater stability and ***,the research has met the requirements of industrial production,and the fabrication of phenolic-fibers-based protection equipment can be widely used in the nuclear radiation industry.

关键词： Iodine adsorption Phenolic resin Porous carbon fibers Nitrogen doped

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：