检索结果-内蒙古大学图书馆

Emerging Technology (INCET), International Conference for

作者： T Sathwik Tadi Sai Vishruth Reddy Talluri Charitha Rimjhim Padam Singh Sneha Kanchan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Internet Engineering and Computer science Universiti Tunku Abdul Rahman Malaysia

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Medulloblastoma a heterogeneous pediatric brain tumor, requires specific subtype identification in order to determine the most effective treatment strategies. To evaluate the accuracy of classification, this study examines state-of-art leading Convolutional Neural Network (CNN), models like ResNet-50, MobileNet, Xception model, ensembles, etc in differentiating between medulloblastoma subtypes using histopathological images. The models undergo rigorous training and fine-tuning using a comprehensive benchmark dataset encompassing a variety of medulloblastoma subtypes. We also employ advanced image pre-processing techniques to optimize feature extraction. Through comparative analyses based on the accuracy, sensitivity, and specificity and precision of each model to uncover their unique strengths and weaknesses, the work identifies the top performing model for medulloblastoma subtypes classification. Then considering unique strengths of these models, we propose an ensemble methodology that combines top performing models for the underlying problem. Through experimentation, our ensemble approach proves to have the highest accuracy in medulloblastoma subtype classification. The combination of ResNet-50's depth, MobileNet's efficiency, and Xception's feature extraction abilities contribute to the ensemble's outstanding performance with 97% of acuuracy and F-score

关键词： Training Analytical models Pediatrics Accuracy Sensitivity and specificity Brain modeling Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Estimating Anthropometric Soft Biometrics:An Empirical Method

引用

Intelligent Automation & Soft computing 2023年第9期37卷 2727-2743页

作者： Bilal Hassan Hafiz Husnain Raza Sherazi Mubashir Ali Yusra Siddiqi Engineering&Environment Northumbria UniversityLondon CampusLondonE17HTUK School of Computing and Engineering University of West LondonLondonW55RFUK School of Computer Science University of BirminghamBirminghamB152TTUK

Following the success of soft biometrics over traditional biomet-rics,anthropometric soft biometrics are emerging as candidate features for recognition or retrieval using an image/*** soft biometrics uses a quantitative mode of annotation which is a relatively better method for annotation than qualitative annotations adopted by traditional ***,one of the most challenging tasks is to achieve a higher level of accuracy while estimating anthropometric soft biometrics using an image or *** level of accuracy is usually affected by several contextual factors such as overlapping body components,an angle from the camera,and ambient *** and developing such a collection of anthropometric soft biometrics that are less sensitive to contextual factors and are relatively easy to estimate using an image or video is a potential research domain and it has a lot of value for improved recognition or *** this purpose,anthro-pometric soft biometrics,which are originally geometric measurements of the human body,can be computed with ease and higher accuracy using landmarks information from the human *** this end,several key contributions are made in this paper;i)summarizing a range of human body pose estimation tools used to localize dozens of different multi-modality landmarks from the human body,ii)a critical evaluation of the usefulness of anthropometric soft biometrics in recognition or retrieval tasks using state of the art in the field,iii)an investigation on several benchmark human body anthropometric datasets and their usefulness for the evaluation of any anthropometric soft biometric system,and iv)finally,a novel bag of anthropometric soft biomet-rics containing a list of anthropometrics is presented those are practically possible to measure from an image or *** the best of our knowledge,anthropometric soft biometrics are potential features for improved seamless recognition or retrieval in both constrained

关键词： Anthropometrics soft biometrics landmark localization estimation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Trip Planning with Integrated Street View: A Seamless AI-driven Approach

Intelligent Trip Planning with Integrated Street View: A Sea...

引用

Innovations in Power and Advanced computing Technologies (i-PACT)

作者： Siva Sankar A Nirmal Kumar K Sidharth M Dinesh S Abhishek Anjali T Department of Computer Science and Engineering Amrita School of Computing Amritapuri India

The advent and widespread adoption of AI-powered trip planners have revolutionized how travelers engage in travel planning. These intelligent systems leverage artificial intelligence algorithms and data to provide users with personalized, efficient, and immersive planning experiences. In this research the indispensable role played by immersive street view experiences within AI trip planners. Integrating immersive street view experiences within AI trip planners empowers travelers to make well-informed choices, as they can virtually navigate and assess potential destinations, accommodations, and attractions. These intelligent systems leverage artificial intelligence algorithms and data to provide users with personalized, efficient, and immersive planning experiences. The findings reveal that immersive street view experiences significantly elevate the effectiveness of travel planning and decision-making processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Segmenting the Brain Tumor using Deep Learning Techniques

Segmenting the Brain Tumor using Deep Learning Techniques

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Ch. Lakshmi Pranitha R. Sumathi V.Harshitha N.Kavya A.Soni Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamil Nadu India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamil Nadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

This study presents a U-Net architecture with EfficientNet-B7 as the feature extraction backbone is used to propose a robust brain tumor segmentation method. Using cutting-edge deep learning techniques, the suggested model precisely segments MRI images with an emphasis on identifying and defining tumor anomalies. A thorough preprocessing pipeline that handles missing values, augments data with albumentations, and normalizes data guarantees the consistency and resilience of the incoming data. The segmentation procedure uses a hybrid loss function that combines Soft Dice Loss and Binary Cross-Entropy (BCE), improving the model's ability to strike a compromise between segmentation consistency and pixel-level precision. To ensure efficiency and generalizability, the model training is optimized using the Adam optimizer in conjunction with a learning rate scheduler. Additionally, an early halting mechanism is incorporated to minimize overfitting. Using a standardized dataset, performance evaluation is carried out with 70%, 15%, and 15% splits for training, validation, and testing, respectively. To evaluate the quality of segmentation, important metrics are employed, such as the Dice Coefficient and the Intersection over Union (IoU). The accuracy of the model in identifying tumor boundaries is illustrated by visualizations of the anticipated segmentation results. The potential of combining U-Net with cutting-edge feature extractors such as EfficientNet-B7 to produce dependable, effective, and clinically significant segmentation results in medical imaging is demonstrated by this approach.

关键词： Training Deep learning Image segmentation Renewable energy sources Magnetic resonance imaging Brain tumors Feature extraction Brain modeling Testing Resilience

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Credit Card Fraud Detection in Massive Datasets Using SMOTE and Random Sampling

A Machine Learning Approach for Credit Card Fraud Detection ...

引用

IEEE Recent Advances in Intelligent Computational Systems (RAICS)

作者： Sreenivas Prasad B Akash Babu N Harthikeswar Reddy Rimjhim Padam Singh Sneha Kanchan Department of Computer Science & Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India Department of Internet Engineering & Computer science Universiti Tunku Abdul Rahman Malaysia

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381696

The surge in digital transactions has paved the way for an alarming rise in credit card fraud, compelling the need for robust detection systems. The swift progress of technology has transformed customer payment habits, driving them toward a cashless society, with the rise of digital payments making it easier for fraudsters to commit fraud. The impact of credit card fraud on revenue can be significant. No matter the scale of the businesses, credit card fraud will have a significant effect on the businesses. This paper addresses the escalating threat by proposing a fraud detection model utilizing the ’IEEE CIS Credit Fraud Detection’ dataset from Kaggle, constructing a machine learning model aimed at enhancing the accuracy of fraudulent transaction identification, presenting an integrated approach to credit card fraud detection that combines user separation and innovative techniques for improved accuracy and real-world impact, ultimately strengthening the global financial ecosystem.

关键词： Surveys Accuracy Systematics Sensitivity Stacking Credit cards Fraud Ensemble learning Surges Business

来源：评论

学校读者我要写书评

暂无评论

Autograding of Programming Skills

Autograding of Programming Skills

引用

International Conference for Convergence of Technology (I2CT)

作者： Nakka Narmada Peeta Basa Pati Department of Computer Science and Engineering Amrita School of Computing Bangalore India

To evaluate a learner’s knowledge of programming language skills, assessments are given. Grading of these is usually done manually which not only is tedious but prone to error due to repetition and fatigue. In this work, we employ pre-trained language models to perform automated grading of "C" programming language. Embeddings from different transformers on pre-assessed codes are used as feature vectors to train a wide range of regressors for the scoring task. Root-mean-square error (RMSE) is the metric utilized to compare the scores of these regressors. It’s observed that embeddings from T5-model with CatBoost regressor gives the least error around 15%.

关键词： Measurement computer languages Codes Bit error rate Programming Predictive models Transformers

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization Based Long Short-Term Memory for Android Malware Detection

Hybrid Optimization Based Long Short-Term Memory for Android...

引用

2023 International Conference on Evolutionary Algorithms and Soft computing Techniques, EASCT 2023

作者： Lande, Jayapal Maheswari, M. Kamali, S.M. Dineshkumar, R. Priyanka, M.S. Sr University School of Computer Science & Artificial Intelligence Warangal India Srm Institue of Science and Technology School of Computing Department of Computational Intelligence Chennai India Annapoorana Engineering College Department of Electrical and Electronics Engineering Salem India Saveetha School of Engineering Department of Ece Sriperumbudur Thandalam India Nitte Meenakshi Institute of Technology Department of Ai and Ml Yelahanka Bengaluru India

ISBN: (纸本)9798350313413

Malware detection is process of detecting the suspicious files and activities, that can classify as benign and malicious depends on different characters like capability of infection, structure of malware and speed rate. In this paper, proposed a Particle Swarm Optimization and Ant Colony Optimization (HPSALO) based Long Short-Term Memory (LSTM) model for malware detection and classification. The combination of these two algorithms that leads to the balance between exploration and exploitation. The dataset utilized for the research is DREBIN dataset and process of data cleaning is performed by NumPy library. The feature selection is performed by combination of hybrid PSALO algorithms and selected features are given to Long Short-Term Memory (LSTM) classifier that classifies as benign and malware files. The performance of proposed method is estimated by performance metrics of accuracy, precision, recall and f1-score. The proposed method attained accuracy of 99.38%, precision of 99.30%, recall of 99.08% and f1-score of 99.42% which is comparatively higher than other existing methods like Whale Optimization Algorithm-LSTM (WOA-LSTM), Cat Swarm Optimization-LSTM (CSO-LSTM), Particle Swarm Optimization-LSTM and Ant Lion Optimization-LSTM. © 2023 IEEE.

关键词： Ant Lion Optimization Long Short-Term Memory Malware Detection NumPy and Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

Ortho Vision: Autoencoder-CNN Fusion Approach for Fracture Detection

Ortho Vision: Autoencoder-CNN Fusion Approach for Fracture D...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： S Abhiram Amal Krishna K Vaishnav G M Anjali T Abhishek S Department of Computer Science and Engineering Amrita School of Computing Amritapuri India

We propose an advanced framework for automated fracture detection in medical X-ray images., harnessing the power of hybrid deep learning methodologies. Through the fusion of autoencoders” adeptness in feature extraction and a convolutional neural networks (CNN) efficiency in recognizing the complex patterns., the proposed model achieves remarkable accuracy in identifying fractures. By integrating data augmentation and preprocessing strategies., the system demonstrates enhanced robustness in handling variations in image quality and presentation. This innovation holds substantial promise in revolutionizing the field of medical diagnostics by offering a reliable and efficient tool for clinicians to expedite fracture diagnosis., facilitate treatment decisions., and ultimately improve patient care. The amalgamation of diverse techniques not only establishes a robust fracture detection mechanism but also showcases the potential of interdisciplinary approaches. The proposed approach demonstrated excellent accuracy in fracture detection with a 92% percentage., which can greatly improve medical diagnosis and treatment planning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face Recognition in Different Scenarios Using Siamese Network 3

Face Recognition in Different Scenarios Using Siamese Networ...

引用

3rd IEEE Global Conference for Advancement in Technology, GCAT 2022

作者： Mathi, Rohith Mothukuri, Jaswanth Venkat Pasumarthy, Venkata Akhil Suja, Palaniswamy Subramani, R. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mathematics Bengaluru India

ISBN: (数字)9781665468558

ISBN: (纸本)9781665468534

Face detection and face recognition are the most sought applications in image processing and computer vision domains. Face recognition has a wide range of applications, and some of its performance must be improved in unconstrained and surveillance applications. In this paper, face recognition has been performed for a person with different backgrounds and different people around him and in various costumes, which is helpful for surveillance applications and HRI. This work proposes an algorithm to recognize a person by matching similarities between the two faces using Siamese Architecture alongside VGG-Face and MTCNN algorithms. The system gives the similarity score for both images with 90% accuracy. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Predicting the Coronary Heart Disease Risk Over the Next Decade through Ensemble Methodologies

Predicting the Coronary Heart Disease Risk Over the Next Dec...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Aashna Arun Rimjhim Padam Singh Sneha Kanchan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Internet Engineering and Computer Science Universiti Tunku Abdul Rahman Malaysia

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Ascertaining diagnosis for Coronary Heart Disease (CHD) is a difficult procedure & must be completed precisely within a stipulated period. Numerous researchers have taken a gander at coronary illness risk factors & recommended specific Machine Learning (ML) & Artificial Intelligence (AI) models. This paper attempts to demonstrate the development of various predictive models for the risk of CHD over the next decade using the Framingham dataset with relevant features. The data undergoes thorough preprocessing, including handling missing values, outliers, & duplicates based on which a predictive model was built & evaluated. The work encapsulates essential steps, emphasizing the approach to predicting CHD & providing insights for potential healthcare applications. Attempting to improvise the predictive accuracy the work proposes implementing several ensemble approaches, combining the strengths of multiple models which showcased exceptional performance. Through the ensemble techniques, the individual models were integrated to mitigate weaknesses & enhance overall predictive performance that contributes to a more advanced and accurate prediction of CHD. The various strategic ensemble approaches enhance the reliability of the predictive model, offering a more effective tool for healthcare practitioners in assessing the likelihood of CHD in subjects.

关键词： Heart Accuracy Stacking Medical services Predictive models Ensemble learning Usability

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：