检索结果-内蒙古大学图书馆

1st IEEE International Conference on Artificial Intelligence for Medicine, Health and Care, AIMHC 2024

作者： Guntunur, Shria Varma, Shreya Saxena, Shubangi Sagere, Supreeta Srinivasa, Gowri PES Center for Pattern Recognition Dept. Computer Science Engineering PES University Bengaluru India

ISBN: (纸本)9798350371987

Prognostic decisions made in the early days following cardiac arrest can significantly impact patient outcomes. This work leverages continuous electroencephalography (EEG) to predict neurological outcomes in patients who have become comatose after a cardiac arrest. We propose a two-stage stacked classifier (TSSC), combining an RNN model and an SVM model with a non-linear kernel, with KNN serving as the meta-classifier. This approach involves an analysis of EEG features extracted using Welch’s power spectral density, resulting in a reduced feature subset and a subsequent enhancement in accuracy. Experimental results demonstrate an impressive predictive accuracy of 95.1% with this approach. We also discuss the implications of our findings for clinical practice. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Enhanced Deep Learning Models for Real-Time Weed Classification on the Edge

Enhanced Deep Learning Models for Real-Time Weed Classifica...

引用

International Conference on Business Intelligence and Data Analytics, BIDA 2024

作者： Ramalakshmi, K.S. Karmakar, Kingshuk Bajaj, Krishna Abhimanyu, Kumar Srinivasa, Gowri PES Center for Pattern Recognition Department of Computer Science and Engineering PES University Bengaluru India

ISBN: (纸本)9789819777167

This paper presents a deep learning-based solution to the challenge of weed infestation in the context of modern agriculture. We leverage visual similarities of weed species through a hierarchical classification approach and explore real-time weed detection using state-of-the-art deep learning models. Our experiments using MobileNetV2 and NASNetMobile, optimized for edge applications, yield remarkable accuracies of 98.90 and 97.58%, respectively. Additionally, the paper explores real-time weed detection using the YOLOv7 and YOLOv8 framework, achieving a precision of 0.9860 and 0.9902, respectively. The deployment of these advanced technologies on the edge offers a transformative solution for weed management, ensuring precise and targeted weedicide application, thereby minimizing environmental harm and streamlining the weed management process for farmers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hierarchical Clustering Image Classification MobileNetV2 NASNetMobile Object Detection Weed Management YOLO

来源：评论

学校读者我要写书评

暂无评论

Mental Health in Tech: Analysis of Workplace Risk Factors and Impact of COVID-19

引用

SN computer science 2023年第2期4卷 197页

作者： Mitravinda, K.M. Nair, Devika S. Srinivasa, Gowri PES Center for Pattern Recognition Department of Computer Science and Engineering PES University Karnataka Bengaluru India

The psychological, emotional and social well-being of an individual determines their ability to contribute and function as a social member. Several studies over the years have proven that an alarming number of people live with mental illnesses, of which only a fraction is documented. Studies conducted by Open Sourcing Mental Illness (OSMI) organization have indicated that these figures are much higher in the tech industry. We present an analysis of patterns and infer contributory factors for mental illness in the tech industry, to aid in the early detection and assess employees’ risk of diagnosis. Towards this end, the study comprises a detailed analysis, models for prediction of diagnosis, risk-based clustering and investigation into existing literature on factors contributing to mental illness. In addition to this, we have attempted to understand the impact of Covid-19 through analyzing trends of the factors influencing mental health, pre- and post-pandemic. We conclude with an insight to the impact of the COVID-19 pandemic on global mental health and the actions taken in the workplace to mitigate this. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Clustering COVID-19 Mental health Prediction Risk

来源：评论

学校读者我要写书评

暂无评论

ScripTONES: Sentiment-Conditioned Music Generation for Movie Scripts 3

ScripTONES: Sentiment-Conditioned Music Generation for Movie...

引用

3rd International Conference on AI-ML Systems, AIMLSystems 2023

作者： Veerendranath, Vishruth Masti, Vibha Gupta, Utkarsh Chaudhuri, Hrishit Srinivasa, Gowri Pes Center For Pattern Recognition Department Of Computer Science And Engineering Pes University India

ISBN: (纸本)9798400716492

Film scores are considered an essential part of the film cinematic experience, but the process of film score generation is often expensive and infeasible for small-scale creators. Automating the process of film score composition would provide useful starting points for music in small projects. In this paper, we propose a two-stage pipeline for generating music from a movie script. The first phase is the Sentiment Analysis phase where the sentiment of a scene from the film script is encoded into the valence-arousal continuous space. The second phase is the Conditional Music Generation phase which takes as input the valence-arousal vector and conditionally generates piano MIDI music to match the sentiment. We study the efficacy of various music generation architectures by performing a qualitative user survey and propose methods to improve sentiment-conditioning in VAE architectures. © 2023 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Pipeline for the Detection of Multiple Ocular Diseases 4th

Deep Learning-Based Pipeline for the Detection of Multipl...

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Angadi, Ananya Bhat, Aneesh N. Ankitha, P. Kumar, Parul S. Srinivasa, Gowri PES Center for Pattern Recognition Department of Computer Science and Engineering PES University Bengaluru India

ISBN: (纸本)9789819900466

computer-aided diagnostic systems provide decision support for the early and accessible detection of ocular diseases. While predictive models exist for certain common diseases in isolation, there is a need to detect multiple diseases at the same time to ensure that rarer conditions do not go undiagnosed. In the present work, we propose a workflow to detect the presence of seven ocular diseases. We first determine the disease risk using EfficientNetB3 pre-trained on ImageNet. Next, for common diseases with a relatively larger representation of images in the dataset, we utilize a Vanilla CNN to classify each disease. For relatively less common diseases, characterized by fewer representative samples in the dataset, we employ transfer learning using EfficientNetB3 pre-trained on ImageNet. To deal with the class imbalance in the original data, we create representative datasets with respect to each disease. The resulting models were found to have high sensitivity (0.8–1.0) and promising accuracy (0.7–0.96). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Musical Brainwaves: Decoding Electroencephalography Signals Elicited by Musical Stimuli 1

Musical Brainwaves: Decoding Electroencephalography Signals ...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Ankitha C Juneja, Hita Bharadwaj, Ishita Varghese, Jeffrey S Honnavalli, Prasad B. Srinivasa, Gowri PES University Dept. of Computer Science Engg. Bengaluru India PES University PES Center for Information Security Forensics and Cyber Resilience Dept. of Computer Science Engg. Bengaluru India PES University PES Center of Pattern Recognition Dept. of Computer Science Engg. Bengaluru India

ISBN: (纸本)9798350353648

The influence of music on the human brain has been recognized for centuries, but recent advancements in brain-computer interfaces (BCIs) offer unparalleled opportunities to probe its complexities. This study investigates the effectiveness of music as a stimulus for driving BCIs using electroencephalography (EEG) signals. We analyze the neural correlates of music perception and imagination in the OpenMIIR dataset, employing advanced machine learning algorithms for EEG decoding. Exploiting various feature engineering techniques in time domain and frequency domain, we leverage convolutional neural networks and speech-inspired architectures like VLAAI to reconstruct the original audio stimuli from EEG data. Our results demonstrate a significant improvement in reconstructing music stimuli from EEG signals in the time domain, achieving a Pearson correlation of 0.35 compared to the current state-of-the-art performance of 0.11. Similarly, an increase in accuracy in classifying lyrical and non-lyrical musical excerpts based on participants' EEG responses was observed, rising from 49.6% to 57%. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Predicting the Price Direction of Bitcoin Using Twitter Data and Machine Learning 2

Predicting the Price Direction of Bitcoin Using Twitter Data...

引用

2nd IEEE International Conference on Data science and computer Application, ICDSCA 2022

作者： Kanji, Abdul Mannan Chaudhary, Ishita Shankar, Rithika Lakshmi Srinivasa, Gowri Pes University Pes Center for Pattern Recognition Dept. of Computer Science and Engineering Bengaluru India

ISBN: (数字)9781665472005

ISBN: (纸本)9781665472005

Bitcoin is a decentralized digital currency that was intro- duced in 2009 and since then, has become increasingly popular as one of the most known and highly valued currencies. Contributing factors to its rise include crypto Twitter influencers. An engaged audience on Twitter seems to have an influence on the cryptocurrency market. In this paper, we analyze the impact that tweets have on the price of Bitcoin. Using word-clouds and candlestick plots, we gain insight into the factors that affect Bitcoin prices. We also use various machine learning techniques to automatically classify the sentiment in Tweets related to cryptocurrencies. We incorporate these and other relevant features to build and compare the performance of multiple machine learning models to predict the direction (increase or decrease) of the price of Bitcoin. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Classifying Stages of Retinopathy of Prematurity

Deep Learning for Classifying Stages of Retinopathy of Prema...

引用

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

作者： Govind, Ayush Satish Gadad, Atharva Garodia, Dhruv Jyoti Gupta, Ayush Vinekar, Anand Srinivasa, Gowri Pes University Pes Center For Pattern Recognition Department Of Computer Science And Engineering Bengaluru India Department Of Pediatric Retina Narayana Nethralaya Bengaluru India

ISBN: (纸本)9798350371567

This work presents a deep learning based approach to classify stages of retinopathy of prematurity (ROP). In particular, the approach focuses on delineating stages 1, 2 and 3 that are relatively crucial for treatment. Training and validation of the models is carried out on multiple subsets of data from 82,295 images collected by Narayana Nethralaya, Bengaluru, using 3nethra fundus cameras. A pre-trained EfficientNetV2S model is used for feature extraction and the datasets are used to train classification models to predict stage, plus disease status and decision for treatment. Experimental results demonstrate the efficacy of training models only on images capturing the temporal region of the retina and manually filtering out images that show no visible signs of ROP, with the best performing model distinguishing stage 2 and stage 3 with an accuracy of 93.44%, AUC of 98.71% and sensitivity of 93.30%. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Road Traffic Accidents: Hotspot Analysis and Severity Prediction Using Machine Learning 4

A Comprehensive Study of Road Traffic Accidents: Hotspot Ana...

引用

4th IEEE Bombay Section Signature Conference, IBSSC 2022

作者： Gupta, Utkarsh Varun, M.K. Srinivasa, Gowri Pes University Dept. of Computer Science and Engineering Bengaluru India Pes University Pes Center for Pattern Recognition Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665492911

This study analyses road traffic accident data recorded over a period of time to gain insights to the underlying pain points in the infrastructure and policies. Such insight allows us to focus our efforts in the right direction to make the lives of people safer. The data includes various geographical and meteorological factors affecting the severity of these accidents. We use Kernel density estimation (KDE) plots to analyse hotspots of accident-prone areas weighed against severity over years to understand the evolution of these dangerous zones. Furthermore, we use machine learning algorithms to predict the accident severity given certain parameters and to understand the factors that have a major influence on the severity of the accident. We have studied a publicly available dataset of road traffic accidents in the UK as a proof of concept of the pipeline to understand the underlying patterns of accidents occurring in a region of interest. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of EEG Signals for Predicting Neurological Recovery in Post-Cardiac Arrest Comatose Patients

Analysis of EEG Signals for Predicting Neurological Recovery...

引用

Artificial Intelligence for Medicine, Health and Care (AIMHC), IEEE International Conference on

作者： Shria Guntunur Shreya Varma Shubangi Saxena Supreeta Sagere Gowri Srinivasa Dept. Computer Science Engineering PES Center for Pattern Recognition PES University Bengaluru India

Prognostic decisions made in the early days following cardiac arrest can significantly impact patient outcomes. This work leverages continuous electroencephalography (EEG) to predict neurological outcomes in patients who have become comatose after a cardiac arrest. We propose a two-stage stacked classifier (TSSC), combining an RNN model and an SVM model with a nonlinear kernel, with KNN serving as the meta-classifier. This approach involves an analysis of EEG features extracted using Welch's power spectral density, resulting in a reduced feature subset and a subsequent enhancement in accuracy. Experimental results demonstrate an impressive predictive accuracy of 95.1% with this approach. We also discuss the implications of our findings for clinical practice.

关键词：

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：