检索结果-内蒙古大学图书馆

Insightful Clinical Assistance for Anemia Prediction with Data Analysis and Explainable AI

Procedia computer science 2024年 233卷 45-55页

作者： E Kasthuri S. Subbulakshmi Rajasree Sreedharan Research Scholar Department of Computer Science and Engineering Assistant Professor Department of Computer Science and Applications Amrita School of Computing Amritapuri India Associate Professor Division of Nephrology Department of Pediatrics Medical College of Wisconsin Milwaukee Wisconsin USA

Anemia among young people has positive correlation with susceptibility and impede cognitive development. As per WHO 2019 statistics global prevalence rate of anemia is 33 percent. This work aims to predict anemia with inferences to identify the root cause of anemia. Prediction is done with machine learning algorithms with proper pre-processing, data normalization, and class imbalance approaches. Explainable AI, a transparent model, is used to enhance the prediction which enables to draw inferences. LGM Boost learning model prediction has a 91% accuracy and explainable AI framework predictions of most contributing attribute is accurate when compared to other models. This approach helps healthcare professionals make informed decisions on the most optimal treatment for anemia.

关键词： Explainable Artificial Intelligence Machine learning Anemia Data preprocessing

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deepfake Video Detection Techniques Using Deep Learning 2

A Survey on Deepfake Video Detection Techniques Using Deep L...

引用

2nd International Conference on Next Generation Intelligent Systems, ICNGIS 2022

作者： Das, Athirasree Viji, K.S Angel Sebastian, Linda College of Engineering M-Tech Scholar Dept. of Computer Science and Engg Kerala Kidangoor India Assistant Professor College of Engineering Dept. of Computer Science and Engg Kerala Kidangoor India

ISBN: (纸本)9781665467926

Deep learning is an effective technology that has been widely used in different ways. 'DeepFake' videos are generated using deep learning technology called generative adversarial network where the videos are created with swaped faces in a video, altered facial expressions, change of gender, creation of fake video content and altered facial features. Fake videos are used in the situations like extortion of money, terrorism events or create political agitation. The deepfake technologies are used for positive purposes, such as film-making and virtual reality. The good quality results from deepfakes are very hard to recognised with people eyes. Many deep learning techniques are built to detect deepfake content in images and videos. A comparative study of the performance of various deepfake videos detection models in the deep learning is preseted in this paper. Convolutional Neural Network (CNN) models include ResNet, VGG16, Efficientnet etc.. Recurrent Neural Network (RNN) model includes Long Short-Term Memory LSTM. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An In-Depth Exploration of Advanced Driver Drowsiness Detection Systems for Enhanced Road Safety

An In-Depth Exploration of Advanced Driver Drowsiness Detect...

引用

computer, Communication and Control (IC4), International Conference on

作者： A. Abirami S Bhuvaneswari M Vishnuvardhan Yadam Karthik Saisuraj Shankar Dept. of Computer Science and Engineering Assistant Professor of Easwari Engineering College Chennai India Dept. of Computer Science and Engineering Student of Easwari Engineering College Chennai India

Drowsiness, among drivers, plays a role in causing road accidents leading to loss of life, injuries, and financial setbacks. To address the issue of driver fatigue related accidents it is crucial to develop methods for detecting driver fatigue. This survey paper presents an overview of approaches used to identify driver fatigue. These approaches can be grouped into three categories: Behavioural, Vehicular and Physiological parameters. Behavioural parameters, such as eye closure percentage, blink rate patterns, yawning, head movements and facial expressions offer intrusive techniques that examine the physical state of the driver’s body and provide information about their drowsiness level. Vehicular parameter-based techniques evaluate drowsiness by observing vehicle behaviour such as lane deviations, pedal usage, and unpredictable steering movements. Physiological indicators are also employed to detect tiredness. The paper also discusses the methodology employed in the research study including image processing techniques classifiers used and measurement metrics utilized, proposed methodology of fatigue detection with adding some extra features and Lastly the paper presents conclusions based on a study that can guide future researchers in identifying potential areas for further exploration in this field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel random finite element model for holistically modeling of the frost effects on soils and cold region pavements

引用

Journal of Infrastructure Preservation and Resilience 2022年第1期3卷 1-14页

作者： Dong, Shaoyang Jiang, Yusheng Yu, Xiong Graduate Research Assistant Department of Civil and Environmental Engineering Case Western Reserve University ClevelandOH United States Opal J. and Richard A. Vanderhoof Professor and Chair Department of Civil and Environmental Engineering Professor of Electrical Engineering and Computer Science Case Western Reserve University ClevelandOH United States

This paper describes the development of a random finite element model (RFEM) that allows holistic simulation of frozen soil behaviors, including the effects of phase transition and the consequent internal stress and volume changes. The performance of the model is firstly validated with laboratory experiments. The model is implemented to simulate the effects of frost action on pavement. The coupled thermal-mechanical actions including the mechanical responses of subgrade soils subjected to freezing temperature and its effects on the pavement structure are analyzed. The results show that the frost action and expansion of ice lenses change the interaction modes between pavement layers. This leads to increase of stress and deformation in the pavement layer. Methods to mitigate the effects of frost heave are analyzed with this model. The simulation results indicate that the detrimental effects of frost heave on the pavement structure can be mitigated by increasing the thickness of base layer, use of thermal insulation layer or improve drainage in the subgrade layer. The RFEM combines the advantages of discrete element model (DEM) in holistically describing the microstructure effects and in the finite element model (FEM) in terms of computational efficiency. This allows to focus research on understanding the behaviors of individual soils phase and their interfacial interactions. © The Author(s) 2022.

关键词： Pavements

来源：评论

学校读者我要写书评

暂无评论

Predicting Malware Classification and Family using Machine Learning: A Cuckoo Environment Approach with Automated Feature Selection

引用

Procedia computer science 2024年 235卷 2434-2451页

作者： Niveditha S Prianka Rr Sathya K Shreyanth S Nandhagopal Subramani Balakrishnan Deivasigamani Karthikeyan S Department of Biotechnology Rajalakshmi Engineering College Thandalam Chennai Tamil Nadu India 602105 Senior Assistant Professor Department of AIML New Horizon College of Engineering Bengaluru Karnataka India 560103 Assistant Professor senior grade-1 School of Computer Science and Engineering VIT Vellore Tamilnadu India 632014 MTech in Data Science and Engineering Birla Institute of Technology and Science Pilani Rajasthan India 333031 Assistant Professor Department of CSE(AI and ML) KPR Institute of Engineering and Technology Coimbatore Tamil Nadu India 641407 Assistant Professor Department of Information Technology KSR Institute for Engineering and Technology

Malware’s increasing menace in the digital realm needs the development of powerful detection and classification systems. This study presents a unique method for predicting malware category and family using machine learning, leveraging the Cuckoo environment and automated feature selection. To undertake an exhaustive examination of malware activity, we combined the Cuckoo environment with cutting-edge machine learning methods, such as the k-Nearest Neighbors (KNN) technique. The dynamic analysis of malware samples within the Cuckoo environment, which captured their interactions with the execution environment, provided remarkable insights into their malicious behaviors. The Boruta method aided automated feature selection, improving the feature set and optimizing model performance. A comparison with existing models yielded striking findings. Notably, Test Case 3 surpassed earlier cases by incorporating Automated Feature Selection + Cross-Validation. In identifying phishing attempts, it displayed outstanding specificity (90%), precision (93%), recall (96%), and an impressive F1-Score (92%), indicating its proficiency in reliably recognizing this frequent threat. Test Case 3 showed considerable increases as well, with a surprising 7.0% increase in precision and a notable 14.6% increase in recall when compared to Test Case 1. Furthermore, in the field of ransomware detection, Test Case 4, which solely focused on Automated Feature Selection, obtained excellent results, with 91% specificity, 92% accuracy, and a recall rate of 93%. These developments highlight the importance of the Boruta algorithm in optimizing the model’s performance.

关键词： Malware Classification Malware Family Prediction Machine Learning (ML) Random Forest Classifier (RFC) Cuckoo Environment Cybersecurity k-Nearest Neighbors (KNN) Boruta Algorithm Automated Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Decision Making and Recognition of String Characters using NN-Fuzzy Implication System

引用

Procedia computer science 2025年 258卷 893-902页

作者： Santosh Kumar Henge Avinash Bhagat Sanjeev Kumar Mandal Nikhil Reddy Viraati Ravleen Singh K. Rushi Kedhar Associate Professor Department of Computer Science and Engineering School of Computer Science and Artificial Intelligence SR University Warangal 506371 India Associate Professor School of Computer Applications Lovely Professional University Phagwara Punjab India Assistant Professor Department of CS and IT Jain (Deemed-to-be University) Bangalore India Department of Data Insights Crisp Shared Services 7160 Columbia Gateway Dr Columbia United States of America Assistant Professor Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddewaram AP India BE-CSE RV Institute of Technology and Management Bengaluru India

This research proposes the neural network (NN)-fuzzy logic control (FLC)-based methodology, which is designed with two stages of execution. Stage-1 is composed with the NN approach; it takes the input from the scanned image, the input from the classified clustered group, processes it with hidden layers, and generates the final output, which is input to the FLC in stage 2. The input of stage 2 converts the input into fuzzified data (0s and 1s) and trains the FLC system with fuzzified set values. The trained data has been simulated for further stages in the FLC-based decision-making approach and integrated to identify the character patterns based on the trained dataset. FLC-based planting and normalization techniques are integrated for re-training the data. The dataset has been framed with more than 6200 handwritten image characters, which were written by 235 writers. It aligned with the pre-processing, classification, and filtering stages and achieved a 99.8% recognition rate.

关键词： Fuzzy Logic Control (FLC) Artificial Neural Network (ANN) Multiple Layered Perceptron (MLP) Convolutional Neural Network (CNN) Feed Forward Neural Network (FNN) Optical Character Recognition (OCR) Handwritten (HW)

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Deep Learning-based Model for Indoor Environment: with Virtual Reference Tag Allocation

引用

Procedia computer science 2024年 233卷 254-268页

作者： N. Mathavan Dr. S. Sivaranjani Assistant Professor Department of Electronics &Communication Engineering Nadar Saraswathi College of Engineering and Technology Vadapudupatti Theni Tamil Nadu India Professor Department of Computer Science and Engineering Sethu Institute of Technology Kariyapatti Virudhunagar Tamil Nadu India

By the evolution of context-aware application, indoor location positioning gains much more attention worldwide. Radio Frequency Identification (RFID) is one such wireless positioning technology adopted widely. Moreover, enhancing the tracking accuracy and thus reducing the tracking error remains a challenging task in RFID based indoor environment. So as to overcome this aspect, a localization and tracking method depending on virtual reference tag (VRT) is employed in the indoor environment. This research work includes four modules like (i) data collection and Received Signal Strength Indication (RSSI) estimation;(ii) Optimal allocation of VRT using Spider Monkey Optimization (SMO) at which the allocation of VRT is made by considering number of tags, environmental factors (humidity and temperature), and SNR. Based on this data, the RFID reader allocates VRT for each grid so as to increase the tracking accuracy; (iii) Artificial Neural Network (ANN) module-based localization at which the localization of unknown tags is made; and (iv) tracking of moving target tag is carried based on Aquila Swarm Optimization-Long short-term memory (ASO-LSTM) approach. The optimization at this stage is employed to choose optimal position which enhances the accuracy of tracking. Thus, finally the location estimation is carried by this approach. The simulation is carried in NS3.26 network simulator and the performance are estimated in terms of SNR, tracking error, mean error, tracking accuracy, mean time, and standard deviation. The performance value is then compared with traditional models to show the enhancement of proposed mode over the other conventional techniques .

关键词： Radio Frequency Identification (RFID) Received Signal Strength Indication (RSSI) localization tracking moving target virtual reference tag Spider Monkey Optimization (SMO) Artificial Neural Network (ANN) Aquila Swarm Optimization-Long short-term memory (ASO-LSTM) tracking error tracking accuracy

来源：评论

学校读者我要写书评

暂无评论

Enhancing Relational Database Interaction through Open AI and Stanford Core NLP-Based on Natural Language Interface

Enhancing Relational Database Interaction through Open AI an...

引用

Recent Trends in computer science and Technology (ICRTCST), International Conference on

作者： Surjeet Kumar Md Shamsher Alam Zeeshan Khursheed Shadan Bashar Neha Kalam Computer Science & Engineering Assistant Professor in Government Engineering College Sheikhpura Bihar India Computer Science and Engineering Associate Professor in R.V.S College of Engineering & Technology Jamshedpur India DGM Jio Platform Limited Mumbai India Master of Computer Application Assistant Professor in R.V.S College of Engineering & Technology Jamshedpur India Computer Science and Engineering Student R.V.S College of Engineering & Technology Jamshedpur India

ISBN: (数字)9798350351378

ISBN: (纸本)9798350351385

In the contemporary digital era, data has evolved into the cornerstone of myriad sectors, encompassing academia, commerce, and medical research. Yet, the acquisition of insights from this expansive reservoir of information has historically demanded a level of proficiency in formal languages such as SQL, thereby imposing a substantial barrier for individuals lacking technical expertise. In response to this pervasive challenge, the advent of Natural Language Interface to Databases (NLIDB) has emerged as a promising and transformative solution. NLIDB offers users the capability to engage with databases through the utilization of their natural language, whether expressed in textual or verbal form. This paradigm shift empowers both seasoned experts and neophytes to effortlessly extract valuable information from databases without the prerequisite of specialized technical skills. In this research paper, we propose an innovative system that capitalizes on an intermediary SQL generation process, facilitating the seamless bridge between natural language input and subsequent database retrieval. This novel approach eliminates the need for users to possess awareness of the intricate underlying complexities of the database management process. By simplifying the interaction between users and databases, our system endeavours to democratize data access and promote the universal utilization of this invaluable resource across diverse domains.

关键词： Structured Query Language Databases Natural languages Semantics Relational databases Manuals Reservoirs

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks for MRI-Based Brain Tumor Classification 3

Convolutional Neural Networks for MRI-Based Brain Tumor Clas...

引用

3rd International Conference on Computation, Automation and Knowledge Management, ICCAKM 2022

作者： Soewu, Taiwo Singh, Dalwinder Rakhra, Manik Chakraborty, Gouri Shankar Singh, Arun Lovely Professional University Department of Computer Science and Engineering Phagwara India Lovely Professional University Department Computer Science and Engineering Phagwara India Lovely Professional University Assistant Professor Department of Computer Science and Engineering Phagwara India Lovely Professional University Phagwara Student IEEE Member Department of Computer Science and Engineering Punjab India

ISBN: (数字)9781665453196

ISBN: (纸本)9781665453196

Recently, the rate at which people die from cancer disease is very alarming. The major reason is because the cancer cells were not detected at the early stages. It may be difficult for medical professionals to evaluate the results of medical imaging techniques such as magnetic resonance imaging (MRI) because cancer cells may not be adequately represented for detection. This is why deep learning techniques are needed for earlier detection of cancer cells so as to reduce the death rate from *** this paper, we have applied the convolutional neural network on some MRI image dataset downloaded from Kaggle. The model was trained to be able to detect tumors in brain MRI images. The performance of the model was evaluated and it achieved 97.8% score for the accuracy, 98.5% specificity, 96.2% recall, 98.5% F1-score and 97.3% precision. A graph was drawn to compare the training loss to the validation loss, as well as the training accuracy to the validation accuracy. © 2022 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Prediction of agricultural waste compost maturity using fast regions with convolutional neural network(R-CNN)

引用

Materials Today: Proceedings 2023年

作者： Sangeetha, J. Govindarajan, Priya Senior Assistant Professor Department of Computer Science & Engineering Srinivasa Ramanujan Centre SASTRA Deemed University Kumbakonam India. Assistant Professor Department of Computer Science AMRITA VISHWA VIDYAPEETHAM Deemed University Mysuru India.

In agriculture production, the enormous volume of wastage production is a major concern. Therefore, composting a massive amount of thrash will transform from agricultural wastage to stabilized, disinfected, and pollution-less yields, allowing important nutrients to be retained and the fertility of soil to be enhanced. Carbon to Nitrogen proportion (C:N) or estimating seed germination index (GI) is the most well-known technique for deciding the compost development of agricultural throwaway, they are both tedious and hard to carry out. Thus, various powerful feature extraction calculations were utilized in the literature. These broadly utilized texture feature extraction strategies could obtain only single-level characteristics, however, the Faster R - CNN model can separate multilevel image attributes since it has a bunch of cascaded layers of convolution and activation functions that could make sense of color and texture features of composts at different levels. Thus, Fast Regions with Convolutional Neural Network(R-CNN) was acquainted in order to rapidly evaluate compost maturity by examining pictures of different composting phases. © 2023 Elsevier Ltd. All rights reserved.

关键词： Feature extraction

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：