检索结果-内蒙古大学图书馆

Visualization of Real-Time Smart Home Data Using PowerBI

SN Computer Science 2024年第6期5卷 725页

作者： Narasimha, S Swamy Anna, Dheeraj Manirathnam Reddy, Akhil Vijayalakshmi, M.N. Raju, Kota Solomon Academy of Science and Industrial Research Department of Artificial Intelligence and Machine Learning RV College of Engineering CSIR-National Aerospace Laboratory

IoT has experienced tremendous advancement over the last decade;this is due to the benefits like data acquisition, data processing, and communication capabilities. Smart Home (SH) takes the key benefits of the IoT to increase the resident’s quality of life. In SH most of the devices ranging from toothbrushes to television are connected to the internet;these devices generate the massive amount of data and that needs to be analyzed. This article presents the real-time streaming analysis of smart home data. The proposed work comprises of three phases: (1) Data acquisition, (2) Data Processing, and (3) Data Analytics. In this work, the RasberryPi3 B models are used to collect data from the smart home environment. RaspberryPi3 is used as an edge node, and which is used to accomplish the data processing task. The processed data is used to create visuals, which helps in understanding the data, and to impart better decisions. This work uses PowerBI services to create visuals and notifications. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cloud service Edge computing Internet of things MQTT PowerBI Smart homes

来源：评论

学校读者我要写书评

暂无评论

Predicting Indian Sign Language Gestures Using Deep learning and machine learning Techniques 4

Predicting Indian Sign Language Gestures Using Deep Learning...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Fulkar, Bhushan Burle, Rushikesh Mahale, Pramod Pacaharaney, Utkrsha Datta Meghe institute of Higher Education and Research Department of Artificial intelligence And Data science Wardha India Department of Artificial Intelligence And Machine Learning Maharashtra Wardha India Datta Meghe institute of Higher Education and Research Department of Artificial Intelligence And Machine Learning Wardha India

ISBN: (纸本)9798331540364

Indian Sign Language is the language used by people with disabilities in India. Unfortunately, the general public's ignorance of sign language makes it difficult for the especially abled and the general public to communicate. We are releasing a strategy to reduce this difference. We have adopted two distinct strategies to deal with this problem. first by employing the depth+RGB data acquired with a Microsoft Kinect to make gesture predictions in real-time. To segment the hand region from the RGB-D camera data, we used affine transformation and 3D reconstruction to map the RGB and depth information. Convolutional neural networks were trained with inputs that were segmented hand images or videos. With 50 static Indian Sign Language hand gestures used for training, a 97.18% classification accuracy was achieved on test data. Furthermore, this model achieved a 97.71 % classification accuracy when we transferred learning American Sign Language. A convolutional kernel and an LSP were used to train twenty dynamic gestures. This model's classification accuracy was 98.88%. Nevertheless, as soon as we implemented this system, we found that the methodology was flawed. Essentially, it is absurd to need to carry around both a bulky Microsoft Kinect and a device capable of performing the computation required for human-to-person interaction. We attempted to address this issue by using semantic segmentation of the hands. U-Net and ResNet 101 were combined. © 2024 IEEE.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Benchmarking One Class Classification in Banking, Insurance, and Cyber Security 12th

Benchmarking One Class Classification in Banking, Insurance,...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Priyanka, Chaduvula Vivek, Yelleti Ravi, Vadlamani Center for Artificial Intelligence and Machine Learning Institute for Development and Research in Banking Technology Hyderabad500076 India

ISBN: (纸本)9789819601387

Given the inherent rarity observed in imbalanced datasets, adopting one-class classification (OCC) stands out as a pragmatic approach to counteract bias toward the predominant class. This research endeavors to thoroughly assess ten state-of-the-art OCC methodologies across a spectrum of five diverse challenges within the Banking, Insurance, and Cybersecurity sectors. Moreover, we introduce an innovative unsupervised learning technique wherein (i) K-Means clustering is utilized during the training phase on negative sample data. To determine the optimal number of clusters, we utilized the Silhouette index and employed the maximum intra-class centroid distance as a cluster-specific threshold. These thresholds play a pivotal role in distinguishing between positive and negative samples. (ii) In the testing phase, a majority voting mechanism is employed to evaluate the discriminative capability of these thresholds, facilitating precise classification of test data. Empirical findings unequivocally demonstrate that our proposed approach outperforms several state-of-the-art techniques, achieving superior classification accuracy across four out of the five datasets. This underscores the effectiveness and potential applicability of our novel methodology in tackling the intricate challenges prevalent in the Banking, Insurance, and Cybersecurity sectors, particularly in the domains of fraud detection and related areas. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Banking

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Jute Pest Detection Using Improved VGG-19 and XAI 15

A Novel Approach for Jute Pest Detection Using Improved VGG-...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Bragadeeshwaran, C. Sairam, R. Aishwarya, A. Moorthy, Rajalakshmi Shenbaga Department of Artificial Intelligence and Machine Learning Sri Ramachandra Institute of Higher Education and Research Chennai India

ISBN: (纸本)9798350370249

Jute, an important crop in many regions of India faces significant threats from pests, a local survey found that 18% of the harvest was damaged by pests. To solve this, the study proposes a deep learning model capable of accurately classifying 18 different classes of pests affecting jute cultivation. Deep learning models are utilized as they can scale well with large datasets and learn patterns making them suitable for this task. The proposed model utilizes the VGG19 architecture as a base model for feature extraction and combines various modifications to enhance its performance. These modifications include adding additional dense layers, dropout layers to reduce overfitting, and introducing additional convolutional layers for feature extraction. The proposed model achieves a validation accuracy of 92%. Also, the results are interpreted with the Lime method to explain the output obtained using the proposed VGG-19 included with batch normalization and drop out. ©2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Localization of Autonomous Vehicles in Tunnels Based on Roadside Multi-sensor Fusion

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Zhu, Kongtao Chen, Shitao Shi, Jiamin Zhu, Ziyu Zheng, Nanning National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China

Tunnels present significant challenges for the navigation and localization of autonomous vehicles due to the lack of GNSS signals and the presence of uniform scene textures. Current cooperative positioning strategies, which rely on RSS and ToF, are less effective in tunnel environments due to the unique electromagnetic conditions. To address this issue, a novel Vehicle-to-Infrastructure (V2I) cooperative localization methodology is introduced. The system comprises a roadside subsystem and a vehicle-side subsystem. In the roadside subsystem, data from multiple sensors is collected to calculate the vehicleâ's position. This information is then transmitted to the vehicle-side subsystem via V2I communication, where it is fused with onboard module data. A highly effective co-location process for the vehicle-side subsystem is proposed, along with an exemplary algorithm. This process resolves issues related to data dimension inconsistency, delay, and pose fusion commonly encountered during co-location. Furthermore, a comprehensive investigation and analysis explores factors that may impact positioning performance. This meticulous examination enhances the understanding of the framework and reveals its limitations. IEEE

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Leveraging Patient Flow Data to Reduce Hospital Readmissions: A Study Using Medical Dashboards 4

Leveraging Patient Flow Data to Reduce Hospital Readmissions...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Deshmukh, Santoshi Pacharaney, Utkarsha Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Data Science Wardha India Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Machine Learning Wardha India

ISBN: (纸本)9798331523923

Transparent reporting of patient outcomes is becoming more and more common as the inequalities in health outcomes amongst groups are being more widely acknowledged. In addition, documenting health outcomes over time across subgroups will be necessary for pay-for-equity programs like those put forth by the Centers for Medicare and Medicaid. One way to visualize data in the context of healthcare is through dashboards, which may be used to identify important differences in clinical outcomes, direct focused efforts toward quality improvement, and eventually enhance health equity. We assess every study that has documented the effective creation of a disparity dashboard in this viewpoint, and we also publish the information gathered and any unexpected repercussions that have been mentioned. We offer a framework for the systematic enhancement of equity via reward systems to lessen health inequalities and incentives for gathering and reporting health data. essential elements of efficient hospital management. A sophisticated approach is necessary to address the impact that hospital leadership has on patient outcomes. Because they embody patient-centered care in their everyday lives, these executives serve as the company's role models. The beliefs, vision, and leadership style of healthcare professionals greatly influence their behavior and performance. Competent leaders who inspire and empower their staff foster a culture of responsibility, creativity, and cooperation. They exhort healthcare professionals to put their patients' safety, satisfaction, and well-being first. Strategic planning, resource allocation, and decision-making are all components of good leadership that support the hospital's goal of offering the highest quality of care. essential elements of efficient hospital management. A sophisticated approach is necessary to address the impact that hospital leadership has on patient outcomes. Because they embody patient-centered care in their everyday lives, these ex

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Rule-based and AI-Driven Systems for Improving Customer Satisfaction and Engagement in E-Commerce using Chatbots Powered by artificial intelligence 6

A Comparative Analysis of Rule-based and AI-Driven Systems f...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Deshmukh, Santoshi Gundewar, Swapnil Department of Artificial Intelligence and Data Science Datta Meghe Institute of Higher Education and Research Wardha India Department of Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research Wardha India

ISBN: (纸本)9798331522667

Chatbots: Chatbots, as robots, are the most recent and intelligent live chat communication devices. Furthermore, these days, it is commonly one of the customer service methods as it is also perfect for providing an array o f services, like personalized offers, individual communication, responsive customer support, etc. The interaction between banks and other financial institutions and their consumers has been entirely transformed due to the marriage of financial technology and artificial intelligence (AI). This scientific investigation deals with artificial intelligence (AI) technology for better communication among people;its special focus is on the effective use of chatbots and natural language processing (NLP) in banking support. Banks are increasingly turning their efforts to AI-driven chatbots as valuable means of enhancing customer support while channeling communication effectively. We are now at the point where human creativity and technology will combine and reimagine finance principles. © 2025 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Event-enhanced synthetic aperture imaging

引用

Science China(Information Sciences) 2025年第3期68卷 388-390页

作者： Siqi LI Shaoyi DU Jun-Hai YONG Yue GAO Beijing National Research Center for Information Science and Technology School of SoftwareTsinghua University Institute for Brain and Cognitive Sciences Beijing Laboratory of Brain and Cognitive IntelligenceTsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsInstitute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Synthetic aperture imaging(SAI) methods aim to see through dense occlusions and reconstruct the target scene behind occlusions. Traditional frame-based SAI methods,e.g., DeOccNet [1], take the occluded light field ima...

关键词：

来源：评论

学校读者我要写书评

暂无评论

machine learning and Deep learning Approaches for Automated Diabetic Retinopathy Diagnosis

Machine Learning and Deep Learning Approaches for Automated ...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Fulkar, Bhushan Burle, Rushikesh Patil, Pawan Gaurkhade, Sanskruti Gundewar, Swapnil Pacharaney, Utkarsha Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Data Science Wardha India Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Department of Computer Science and Design Wardha India Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Machine Learning Wardha India

ISBN: (纸本)9798350375237

Since diabetic retinopathy (DR) is the primary cause of blindness in working-age adults worldwide, vision loss must be avoided by receiving early detection and treatment. In recent years, deep learning techniques have become more and more useful tools for automated drug discovery, possibly offering solutions to overcome the limitations of traditional screening methods. In-depth descriptions of the most recent deep learning methods for DR detection are provided in this review article. We begin by discussing the importance of DR screening, its prevalence, and the challenges faced by healthcare systems in managing this condition. Next, we discuss different deep learning architectures used for DR detection, such as CNNs and RNNs, and their combinations. We investigate how to improve the precision, resilience, and interpretability of DR detection models through the use of explainable AI, ensemble methods, transfer learning, and attention mechanisms. We also examine publicly available datasets, evaluation metrics, and preprocessing techniques that are commonly used to benchmark DR detection algorithms. We discuss the limitations and possible uses of deep learning-based deep readout detection, emphasizing the significance of large-scale, diverse datasets, the interpretability of the model, and real-world deployment concerns. The overall objectives of this review are to advance the field of automated DR detection by highlighting recent developments, compiling existing knowledge, and identifying areas that require further research. © 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

Robust and Scalable Model Editing for Large Language Models 30

Robust and Scalable Model Editing for Large Language Models

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Chen, Yingfa Zhang, Zhengyan Han, Xu Xiao, Chaojun Liu, Zhiyuan Chen, Chen Li, Kuai Yang, Tao Sun, Maosong DCST IAI BNRIST Tsinghua University Beijing China Tencent Machine Learning Platform China Shanghai Artificial Intelligence Laboratory China

ISBN: (纸本)9782493814104

Large language models (LLMs) can make predictions using parametric knowledge-knowledge encoded in the model weights-or contextual knowledge-knowledge presented in the context. In many scenarios, a desirable behavior is that LLMs give precedence to contextual knowledge when it conflicts with the parametric knowledge, and fall back to using their parametric knowledge when the context is irrelevant. This enables updating and correcting the model's knowledge by in-context editing instead of retraining. Previous works have shown that LLMs are inclined to ignore contextual knowledge and fail to reliably fall back to parametric knowledge when presented with irrelevant context. In this work, we discover that, with proper prompting methods, instruction-finetuned LLMs can be highly controllable by contextual knowledge and robust to irrelevant context. Utilizing this feature, we propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. To better evaluate the robustness of model editors, we collect a new dataset, that contains irrelevant questions that are more challenging than the ones in existing datasets. Empirical results show that our method outperforms current state-of-the-art methods by a large margin. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs (and vice versa). The source code can be found at https://***/thunlp/EREN. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

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：