检索结果-内蒙古大学图书馆

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Navale, Girish Jaysing Bhise, Archana Wagh, Kishor Department of Computer Science & Engineering Rajasthan Jhunjhunu India Aissms Institute of Information Technology Pune India

ISBN: (纸本)9798331527822

Alzheimer's disease is gradually losing the cognitive ability and memory functions necessary to meet the challenges of daily life and causes severe disability in affected individuals. It has been known that with a close study of potential environmental and lifestyle risk factors for Alzheimer's, the specific modifiable risk factors of Alzheimer's can be obtained. Exposure to air pollution and heavy metal toxicity leads to oxidative stress and inflammation, which further promotes neuronal damage. In these lifestyle factors, problems in terms of sedentary lifestyle, inappropriate diet, chronic stress might disturb cellular metabolism, in addition to promoting amyloid-beta deposition. Social isolation and disturbances in sleep exacerbate the decline in cognitive function. It links psychosocial factors to the pathogenesis of this disease. Elucidation of these influences may enhance the preventive strategies and identify the potential intervention points along with biomarker-based diagnostics toward more effective management of Alzheimer's disease. As the number one cause of dementia in the world it way affects millions of people all over the world. The disease is marked by the presence of amyloid-beta plaques and tau protein tangles in the brain that disrupts normal processes and leads to nerve cell death. Alzheimer's disease is the outcome of genetic susceptibility coupled with environmental factors and life style. The major genes linked with this ailment include the APP, PSEN1, and PSEN2 genes and any APOE ϵ4 allele. There are more recent risk variants that have been reported recently. The vast majority of the known risk variants for AD are connected to the established functions of APP, PSEN1, and APOE ϵ4;however, there is evidence that recent discoveries of risk variants in other genes, such as the TREM2 gene influencing immune response and amyloid processing, or BIN1, linked to tau pathology, are evidence of new areas of influence. Epigenetic mechanisms from DNA met

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Multimedia IoT Data Compression using Deep Learning Technique 2

Multimedia IoT Data Compression using Deep Learning Techniqu...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Yathavaraj, V. Karthikeyan, N. Kousalya, A. Sindhuja, P. Dr. N.G.P. Institute of Technology Department of Computer Science and Engineering Coimbatore India Sns College of Technology Department of Computer Science and Engineering Coimbatore India Sri Krishna College of Engineering and Technology Department of Information Technology Coimbatore India United Institute of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9781665456302

Due to the considerable complexity of the multimedia data acquired, IoT (Internet of Things) and multimedia will encounter a number of energy and communication overload limits. One well-known solution to the problem of large datasets is to use the lossy compression algorithm. However, the lower transmission rate required by current lossy compression techniques to ensure endurable apparent image/picture quality only results in a minor reduction in the amount of communicated data and, as a result, a minor reduction in power and bandwidth use. An effective firmness technique is required to strike a fair equilibrium flanked by information volume and visual degradation. A deep-learning super-resolution technique is utilized in this study to restore high-resolution photographs from damaged photos with a considerable compression ratio as input. The results of the study clearly show how the suggested approach improves the graphical fidelity of compressed and down scaled images. The suggested method reduces largely the communication transparency and energy consumption of constrained multimedia IoT framework components as a result. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Quantum-Accelerated Hyperparameter Tuning for Dynamic NLP Models 2

Quantum-Accelerated Hyperparameter Tuning for Dynamic NLP Mo...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Ravikumar, S. Raj, Arockia Babu, R. Vijay, K. Ramani, R. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamilnadu Chennai600062 India Department of Computer Science and Engineering PSNA College of Engineering and Technology Dindigul India Department of Computational Intelligence Faculty of College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Chennai603203 India Department of Computer Science and Engineering Rajalakshmi Engineering College Tamilnadu Chennai602117 India Department of Computer Science and Engineering P.S.R. Engineering College Tamilnadu Sivakasi626140 India

In the rapidly evolving field of natural language processing (NLP), performance optimization of large-scale NLP models is crucial. Through the application of Quantum-Accelerated Hyperparameter Tuning (QAHT), this abstract introduces a novel approach to addressing this issue. Our proposed framework leverages quantum computing capabilities to dynamically optimize NLP model hyperparameters in real-time, catering to the ever-changing character of textual data streams. Traditional hyperparameter optimisation methods usually rely on laborious grid searches or random exploration, which may not be suitable for dynamic NLP jobs. Contrarily, QAHT uses Quantum Neural Network (QNN) architectures that have been specially designed for hyperparameter optimisation. These QNNs improve performance and efficacy by dynamically modifying and improving model configurations. This abstract discusses the key elements of the QAHT architecture, including real-time model deployment, adaptive learning, and continuous data stream processing. In addition to speeding up the hyperparameter optimisation process, QAHT makes sure that NLP models are still flexible and responsive to shifts in the sentiment of the data and its distribution. This method has applications beyond NLP since it provides a foundation for effectively optimising machine learning models in complex, real-time situations. As quantum computing develops, QAHT represents a promising future in machine learning, where quantum-enhanced capabilities satisfy the needs of contemporary data-driven applications. © 2024 Elsevier B.V.. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Sentinel Watch: Harnessing AI and ML for Proactive Crime Prediction and Crowd Management 5

Sentinel Watch: Harnessing AI and ML for Proactive Crime Pre...

引用

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

作者： Menaga, D. Angelin, J Jenefa Priyadharshini, V Pallavi St. Joseph's Institute of Technology Department of Computer Science and Engineering Chennai119 India

ISBN: (纸本)9798331530013

This research aims to revolutionize crime prevention and public safety by integrating advanced machine learning techniques for real-time crime monitoring and analysis. The proposed system integrates location-based crime classification and video-based violence detection, delivering a comprehensive approach to crime recognition. Leveraging Random Forest, Decision Tree, and K-Nearest Neighbours (KNN) algorithms, the proposed system achieves 99.0% accuracy in classifying crime types using location data inputs. Complementing this, Convolutional Neural Networks (CNNs) are utilized for video analysis, distinguishing violent from non-violent content with 93% accuracy. By combining spatial data insights with real-time video analytics, the framework addresses the dual challenge of detecting crime trends and analysing violent incidents. The exceptional accuracy rates underscore the potential of the system to enhance public safety measures, optimize resource allocation, and enable proactive crime prevention strategies. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Anti-Sleep Glasses usingAI and ML to Prevent Accidents 15

Anti-Sleep Glasses usingAI and ML to Prevent Accidents

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kumara, Sunad A.N. Gowda, Jashwanth S. Keerthana, T.S. Raj, Keerthi J. Manoj, C.D. Department of Computer Science and Engineering Adichunchanagiri University BGS Institute of Technology Karnataka BG Nagara India

ISBN: (纸本)9798331300579

The "Anti-Sleep Glasses" uses artificial intelligence (AI) to solve the serious problem of accidents caused by *** system uses an ESP32 AI Cam board and customized glasses to integrate a machine learning (ML) model that is trained and implemented on the ESP32 in order to identify eye *** alarm sound is generated whenever the machine learning model detects that an eye has been closed for more than 300 *** helps avert mishaps that may arise from drowsy drivers or *** the use of sophisticated sensors and AI algorithms, these glasses can precisely identify indicators of weariness or exhaustion by tracking the wearer's pupil dilation, eye movement, and blink *** order to notify the user and avert any mishaps, the system quickly activates an alarm mechanism-which may be haptic, visual, or auditory-when it notices these *** the system learns and adapts to each user's unique patterns of alertness and fatigue, the integration of AI enables a high degree of accuracy and flexibility to diverse *** glasses may be worn for lengthy periods of time without causing pain because of their pleasant and non-intrusive *** technique has broader uses in numerous industries where attentiveness is crucial for safety, in addition to improving road safety by warning sleepy *** creation of these glasses marks a substantial advancement in the application of AI to enhance public safety and avoid accidents. © Grenze Scientific Society, 2024.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Towards Building a Global Robust Model for Heart Disease Detection

引用

SN computer Science 2023年第5期4卷 1-12页

作者： Mali, Bhabesh Saha, Santanu Brahma, Daimalu Pinninti, Ramakrishna Singh, Pranav Kumar Department of Computer Science and Engineering Central Institute of Technology Kokrajhar BTR Assam 783370 India

Heart disease is one of the most menacing non-communicable diseases. Heart disease prediction is one of the most popular topics in the field of biomedical engineering. Almost all the models for heart disease detection are based on centralized training of data where data are concentrated in a single server. Centralized training of the model may give a good accuracy to predict/detect, yet the models are not robust as only a single dataset is used to train and test the model. This is a major problem with centralized training. Therefore, in order to solve this problem of robustness, we decided to use and simulate federated learning (FL) to build a heart disease detection model through which we can use multiple datasets from different regions to train the model. We created four virtual workers where each one is representing a hospital present in a different location containing the local data. We have used the dataset downloaded from IEEE Dataport. It is a combination of five different datasets, including the Cleveland, Hungarian, Switzerland, Long Beach VA, and Statlog Heart Dataset. The final dataset contains 11 input features and the output label. We divided the dataset into training and testing data. The training data are divided into four sub-datasets using both IID (Independent and Identically Distributed) and non-IID approaches. Then, the sub-datasets are sent to these four hospitals differently for both approaches. We have used the artificial neural network as the FL base model. We trained both the IID and non-IID models and then tested the models with test data and got an accuracy of 84.87 and 86.55% for the IID and non-IID approaches, respectively. We have also checked the AUC score, sensitivity, and specificity for the IID and non-IID approaches. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Artificial neural network Federated averaging Federated learning Heart disease

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic Annotation for Mentions in Hindi Text

引用

SN computer Science 2023年第5期4卷 1-15页

作者： Lata, Kusum Singh, Pardeep Dutta, Kamlesh Department of Computer Science and Engineering National Institute of Technology Himachal Pradesh Hamirpur 177005 India

Annotated corpora are required for the development of modern, accurate, and robust techniques for Natural Language Processing (NLP) downstream applications. The annotated data contain additional information which is required to train the system in many tasks such as parsing, named entity recognizer, etc. For low-resource languages or domains, manually labeled datasets are costly to construct and often unavailable. An alternative way to annotate datasets in a faster and cheaper way is the automatic annotation approach. The evaluation and training of the Mention detection system need a lot of annotated resources. However, there is a scarcity of annotated corpus and annotation guidelines in the Hindi language. Annotation of mentions such as name, pronominal, and nominal in the document is very important for various NLP downstream applications such as Coreference Resolution (CR), Machine Translation (MT), Automatic Text Summarization (ATS), Information Extraction (IE), etc. Almost all these applications require correct identification of mentions. In contrast to English, Hindi is the language of free word order. This free word order imposes additional limitations on various NLP applications. The paper describes a proposal for semi-automatic annotation of mentions in Hindi text. The proposed method is based on Rule-based mention detection followed by post-editing and adopts the Begin Inside-Outside (BIO) format for annotating mentions in Hindi text. The dataset consists of 3.6 K sentences and 78 K tokens. We conclude that our approach can reduce the effort of extending a seed training corpus and show the inter-annotator agreement for Hindi text sentences. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Annotation tool Hindi language Mention detection

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Collective Decision-Making Systems and the Future Trends 15

AI-Powered Collective Decision-Making Systems and the Future...

引用

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

作者： Khan, Zainab Ambadekar, Sarita K. J. Somaiya Institute of Technology Department of Computer Engineering Sion Mumbai India

ISBN: (纸本)9798350370249

This paper presents an in-depth survey of the current state and future trends of artificial intelligence (AI) in augmenting collective decision-making processes. At the intersection of AI and group dynamics, this research explores how advanced AI technologies such as machine learning, reinforcement learning, natural language processing, predictive analytics, and swarm intelligence, revolutionize the way collective decisions are made in various sectors, including business, healthcare, governance, and finance. We delve into the theoretical foundations of collective decision-making, highlighting the pivotal role of AI in enhancing human judgment, overcoming cognitive limitations, and facilitating consensus in group settings. The paper examines the application of specific AI methodologies like decision trees, ensemble methods, Bayesian approaches, optimization algorithms, and simulation models in diverse decision-making scenarios. Real-world case studies are presented to illustrate the practical implications and transformative impact of AI in fields such as business strategy, healthcare decision support, financial market predictions, and public policy formulation. We address the challenges and limitations inherent in AI-driven decision systems, such as data quality, ethical concerns, biases, transparency, and integration with human processes. The abstract concludes by discussing emerging trends and future directions in AI collective decision-making, including advancements in explainable AI, ethical AI governance, integration of quantum computing, democratisation of decision-making, continuous learning in AI systems, and cross-disciplinary applications, underscoring the potential of AI to significantly enhance the efficacy and equity of collective decision-making across various domains. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Multiscale Feature Extraction Techniques for Emotion Recognition from Physiological Signal 1

Multiscale Feature Extraction Techniques for Emotion Recogni...

引用

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

作者： Taley, Shruti G. Pund, M.A. Prof. Ram Meghe Institute of Technology & Research Department of Computer Science & Engineering Amravati India

ISBN: (纸本)9798350356816

Emotion detection from physiological data is a growing field with important uses in affective computing, HCI, and medical imaging. To achieve significant progress in human-computer interaction, ability to recognise emotions is essential, particularly when using non-intrusive physiological sensors. This work investigates multiscale feature extraction methodologies used in emotion detection systems, with a focus on methodology and benefits. We examine physiological signals like electrocardiogram (ECG), galvanic skin response (GSR) & electroencephalogram (EEG) and we discuss state-of-the-art multiscale feature-based deep learning and machine learning methods. The aim of the paper is to present thorough assessment of state-of-the-art multi-scale machine learning techniques. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

An optimized CNN system to recognize handwritten characters in ancient documents in Grantha script

引用

International Journal of Information technology (Singapore) 2023年第4期15卷 1975-1983页

作者： Jindal, Amar Ghosh, Rajib Department of Computer Science and Engineering National Institute of Technology Patna Ashok Rajpath Patna India

An optical character recognition (OCR) system plays an important role in the digitization of ancient handwritten text document. Various adversaries of ancient documents such as ink stains, faded portion of text, humidity spots, and similar-shaped characters make the task of character recognition challenging and tedious. This research study proposes an optimized convolution neural network (CNN) based OCR system to recognize each and every character present in the ancient document handwritten in Grantha script. A set of convolutional layers present in the proposed system extracts the deep hierarchical feature vectors from the input character image. Two fully connected neural network (FCNN) layers have classified these feature vectors into its correct class. The values of the hyper-parameters of CNN architecture such as the number of filters in each convolution layer, size of the filter in each convolution layer, number of FCNN layers, and neurons in each FCNN layer have been optimized using the Bayesian optimization technique. The major contribution of this work is the proposal of an optimized CNN architecture to perform OCR in ancient documents in Grantha script. A character recognition accuracy of 99.30% has been obtained from the proposed OCR system on the ancient handwritten documents in Grantha script. The experimental results demonstrate that the proposed OCR method outperforms the existing state-of-the-art methods in this regard. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Ancient handwritten documents Character recognition Grantha script Optimized CNN

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：