检索结果-内蒙古大学图书馆

2nd International Conference on computational Systems and Communication, ICCSC 2023

作者： Saha, Anirban Sarkar, Indranil Indian Institute of Science Dept. of Computational and Data Sciences Bengaluru India Sister Nivedita University Dept.of CSE Kolkata India

ISBN: (纸本)9781665493932

Proteins are the main building blocks for any form of life known to us as of now, and it is the actuators of biophysical and chemical events occurring in living organisms. Biological functions are enabled by their naive structure, which plays a very important and crucial role in the design of vaccines and drugs. This acts as one of the main sources of motivation in predicting protein structure from its sequence of amino acids coupled with other information to get highly accurate prediction and classification, which indeed is one of the fundamental computational biology problems. As of now, not much focus has been given to the inclusion of sidechain structure information and prediction of the protein backbone. In this paper, it is shown that a new dataset called SidechainNet, which extends from the ProteinNet dataset, can be used to predict and classify the structure of proteins more accurately. This is because SidechainNet consists of angle and atomic coordinate information, which describes almost all the heavy atoms of each and every protein structure. The background information on the availability of data on the protein structure and the importance of ProteinNet is discussed. It is followed by the beneficial inclusion of additional information that SidechainNet has, which helps in predicting the structure of the protein more accurately. At last, it is shown how using a Machine Learning model, a highly accurate protein structure is obtained by applying SidechainNet as its dataset. © 2023 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Development of an AI based Priority Formation Mechanism in Criminal Law 3

Development of an AI based Priority Formation Mechanism in C...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Sharma, Kashish Amburle, Ankita Shelake, Vijay Chauhan, Ashvini Ashok Dept. of Computer Engineering Fr. Conceicao Rodrigues College of Engineering Mumbai India Dept. of Artificial Intelligence and Data Science Fr. Conceicao Rodrigues College of Engineering Mumbai India

ISBN: (纸本)9798331532420

Nowadays, there is a necessity to tackle a number of pending crime cases across different parts of the world through effective scheduling and management. AI and ML can be used in handling unfinalized criminal cases in India can be one of the possible ways of improving the functioning of the criminal justice system in this country. The approach to this project is to create an AI system that will filter through the open cases and then rank them according to complexity, time-sensitivity, prior performances, and location. Since priority in a case is explained through the use of a supervised learning based on selected set, then law enforcement as well as legal personnel are able to shift most of their attention to other significant cases. Despite feature engineering and data preprocessing being in the construction of the system from the data collected from the various sources such as court records. This means that there is than models such as;Random Forest, Apriori and Rule-Based in an effort to establish the most suitable model. Perhaps the application of this AI based mechanism to form priorities could aid India in better organization of resources and with the assistance of backlog decrease – the justice system in India. But as the right touch to measure artificial use is considered, themes of privacy, bias, and fairness must also be addressed appropriately. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Improving Domain Adaptation Through Class Aware Frequency Transformation

arXiv

引用

arXiv 2024年

作者： Kumar, Vikash Patil, Himanshu Lal, Rohit Chakraborty, Anirban Dept. of Computational and Data Science Indian Institute of Science India

In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the Domain Adaptation task. Most of the Unsupervised Domain Adaptation (UDA) algorithms focus on reducing the global domain shift between labelled source and unlabelled target domains by matching the marginal distributions under a small domain gap assumption. UDA performance degrades for the cases where the domain gap between source and target distribution is large. In order to bring the source and the target domains closer, we propose a novel approach based on traditional image processing technique Class Aware Frequency Transformation (CAFT) that utilizes pseudo label based class consistent low-frequency swapping for improving the overall performance of the existing UDA algorithms. The proposed approach, when compared with the state-of-the-art deep learning based methods, is computationally more efficient and can easily be plugged into any existing UDA algorithm to improve its performance. Additionally, we introduce a novel approach based on absolute difference of top-2 class prediction probabilities (ADT2P) for filtering target pseudo labels into clean and noisy sets. Samples with clean pseudo labels can be used to improve the performance of unsupervised learning algorithms. We name the overall framework as CAFT++. We evaluate the same on the top of different UDA algorithms across many public domain adaptation datasets. Our extensive experiments indicate that CAFT++ is able to achieve significant performance gains across all the popular benchmarks. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Robust EfficientNet Architecture for Brain Tumor Classification and Identification Using MRI Image 11

A Robust EfficientNet Architecture for Brain Tumor Classific...

引用

11th International Conference on Intelligent Systems and Embedded Design, ISED 2023

作者： Pathak, Manisha Chaudhary, Deevesh Sharma, Kratika Sharma, Akhilesh K Gupta, Ashish Sharma, Brij Kishore Mits Dept. of Cse Gwalior India Manipal University Jaipur Dept. of Data Science & Engineering Jaipur India

ISBN: (纸本)9798350318159

The most common method for classifying brain tumors is by using biopsy, but this procedure is only carried out after surgery in which a tiny piece of brain tissue is takeout as well as analyzed under an electronic microscope to see a tumor. Since technology has advanced, particularly in ML and AI, we are now able to identify and categorize tumors without undergoing surgery by feeding the machine's classification engine the current data from various MRI images. By doing our study, we present a approach for the identification of tumors utilizing EfficientNet, an architecture that has already been trained utilizing the transfer learning methodology. This study emphasizes on the EfficientNet-B2, EfficientNet-B3, as well as EfficientNet-B4 algorithms from the group of EfficientNet approach. The suggested approach makes use of thresholds to enhance the dataset for more effective accuracy as well as data augmentation to improve the variety of brain images in the data in addition to the previously-trained approach to enhance the effectiveness of training an improved the model. Because it utilizes the compound coefficient to scale all three dimensions of an image with a fixed value of ratio, dept., width, and resolution - EfficientNet relatives of models outperform earlier CNN architecture, according to preliminary results. The outcomes also showed that scaling the previous approaches, enabled the model to capture complex features, improving the accuracy of the model. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Enhanced IoT Wearable Device for Monitoring and Providing Feedback on Stuttering 3

A Machine Learning-Enhanced IoT Wearable Device for Monitori...

引用

3rd International Conference on computational Modelling, Simulation and Optimization, ICCMSO 2024

作者： Suttarwala, Hussain Kumar, Ritesh Deorankar, Madhavi L. Daulat Sarpate, Dikshendra Shingade, Pallavi Kumar Sharma, Surender More, Vrushali Patkar, Uday Chandrakant Sharma, Deepak K. American Express Senior Software Engineer PhoenixAZ85054 United States Dr. Akhilesh Das Gupta Institute of Professional Studies Dept. of AI and Data Science Delhi New Delhi110053 India Marathwada Mitramandal College of Engineering Dept. of Electronics and Telecommunications Maharashtra Pune411052 India Zeal College of Engineering and Research Dept. of AI and Data Science MaharashtraNarhe Pune411041 India D Y Patil College of Engineering Dept. of AI and Data Science Akurdi Pune411041 India Poornima University Dept. of Electrical Engineering Jaipur India Genba Sopanrao Moze College of Engineering Dept. of AI and Data Science Balewadi Maharashtra Pune411045 India Bharati Vidyapeeth's College of Engineering Department of Computer Engineering Lavale Pune412115 India Savitribai Phule Pune University Dept. of AI and Data Science Maharashtra Pune India

ISBN: (纸本)9798350361391

This study introduces an innovative IoT-enabled wearable device tailored for monitoring and providing feedback on stuttering, leveraging advanced machine learning algorithms to enhance precision and real-time responsiveness. The device integrates an array of hardware and software elements, including sensors, microcontrollers, and communication protocols, to accurately capture speech patterns and movements. Utilizing machine learning techniques such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), the device performs real-time analysis to identify stuttering instances. Detailed discussions cover the criteria for selecting machine learning models, the training and testing procedures, and the metrics used for performance evaluation. The prototype underwent extensive testing and validation, showcasing high accuracy, sensitivity, and specificity in differentiating stuttered from fluent speech. User feedback emphasized the ergonomic design, user-friendly interface, and real-time feedback features, highlighting its potential to significantly enhance stuttering therapy outcomes. Comparative analysis with existing solutions revealed the device's superior performance, indicating strong potential for clinical application. The study discusses the implications for stuttering therapy, acknowledges the limitations, outlines future research directions, and underscores the device's contributions to personalized and effective stuttering interventions. This research advances the field of assistive technologies in speech therapy and demonstrates the promise of IoT-based wearable devices integrated with machine learning for improving the quality of life for individuals with stuttering disorders. © 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

DeepCensored: Deep-Learning Based Probabilistic Forecasting Framework for Censored data 23

DeepCensored: Deep-Learning Based Probabilistic Forecasting ...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Tian, Jiahao Porter, Michael D. School of Data Science University of Virginia CharlottesvilleVA United States School of Data Science University of Virginia Dept. of Systems and Information Engineering CharlottesvilleVA United States

ISBN: (纸本)9798350374889

Accurate time series forecasting is critical in various fields, including resource allocation and crime prevention. While traditional approaches often focus on continuous data, count data forecasting, especially with partially observed (censored) data, remains challenging. This paper introduces DeepCensored, a novel deep learning-based framework that combines the Expectation-Maximization (EM) algorithm with deep neural networks to deliver robust probabilistic forecasts. DeepCensored naturally handles interval-censored event data, where exact event times are unknown but fall within a specific interval. Through extensive simulations and real-world crime data analysis, our method significantly outperforms traditional forecasting approaches, reducing the Mean Absolute Error (MAE) by 50% and better detection of emerging crime trends. These results highlight DeepCensored's potential to provide actionable insights for law enforcement and public safety by predicting crime intensity and enabling resource-efficient policing strategies. © 2024 IEEE.

关键词： Expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dental Diagnosis through Automated Detection of Teeth Diseases in Panoramic Radiographs

Enhancing Dental Diagnosis through Automated Detection of Te...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Rawashdeh, Majdi Bdair, Tariq Salhi, DhaiEddine Al-Yamamah University Software Engineering Dept. Riyadh Saudi Arabia Psut Business Information Technology Dept. Amman Jordan Psut Data Science Dept. Amman Jordan

ISBN: (纸本)9798350351255

Edge learning has shown promising solutions to address diseases by exploiting edge computing capabilities. On the other hand, the analysis of dental radiographs is a crucial step in clinical routine practice since the dentist must evaluate tooth-related issues throughout the clinical diagnosis. Further, errors in manual human analysis may lead to false predictions. Fortunately, the automated approach for identifying and categorizing dental issues can help in the early diagnosis of diseases and prevent tooth loss. This paper aims to create a model that may offer a second viewpoint and simplify dental diagnosis for dentists. The proposed method utilizes state-of-the-art deep learning architecture for object detection. It provides panoramic teeth radiograph images to the proposed network to detect four teeth diseases: conservative (fillings and crowns), implant, RCT (root canal treatment), and bridges. After data preprocessing and augmentation, our framework is used to detect the above teeth diseases with high detection quality and accuracy with mAP and F1-score at 0.902 and 0.86, respectively. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Phishing URLs Using Machine Learning Hybrid Stacking Classifier Approach with XGBoost, Random Forest and Extra Trees

Phishing URLs Using Machine Learning Hybrid Stacking Classif...

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Chitteti, Chengamma Divya Sree, Tanguturi Sai Madhavi, K. Reddy Pooja, Pikkili Jayanth, Sannapaneni Reddy, Middi Harshavardhan Dept. of Data Science Tirupathi India Sree Vidyanikethan Engineering College Dept. of Information Technology Tirupathi India Mohan Babu University Dept. of Ai & Ml Tirupati India

ISBN: (纸本)9798350382693

Within the dynamic field of cybersecurity threats, phishing remains a prevalent and sophisticated tactic employed by malicious actors to deceive consumers. This paper presents a novel approach that leverages the strengths of Random Forest, ExtraTrees, and XGBoost in a machine learning framework to enhance the detection of phishing URLs through a hybrid stacking classifier. The suggested method combines the best features of all three ensemble learning techniques to provide a phishing detection model that is reliable and precise. An ensemble of classifiers is formed by combining XGBoost, which is well-known for its boosting abilities, with the highly randomized ExtraTrees method and the adaptable Random Forest algorithm. By using the various decision limits of each base learner, the hybrid stacking model combines their particular capabilities in the best possible way to provide higher prediction performance. Preprocessing is done on the training dataset to extract pertinent characteristics such as content, URL structure, and contextual data. The efficacy of the suggested method in detecting phishing URLs is assessed by extensive testing on an extensive dataset. The results indicate how well the hybrid stacking classifier performs in comparison to separate classifiers and highlight the possibility for improved phishing detection in practical situations. The study has importance as it presents a novel and efficient machine learning-based approach to counteract the rising danger of phishing assaults, hence propelling the area of cybersecurity forward. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Forecasting Air Pollution of Urban Chennai Localities using Artificial Intelligence 3

Forecasting Air Pollution of Urban Chennai Localities using ...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Faiz, Rayaan Agarwal, Tisha Rajeswari, D. Srm Institute of Science and Technology School of Computing College of Engineering and Technology Dept. of Data Science and Business Systems Chennai603203 India

ISBN: (纸本)9798350375190

India's air quality deteriorated significantly in 2023, ranking third worst globally, highlighting the urgency for effective monitoring and mitigation measures. To comprehend past trends and predict future patterns, historical air pollution data from seven urban areas in Chennai was analyzed using the XGBoost Algorithm. This study aims to gain insights into Chennai's air quality, identify abnormalities, and issue timely warnings to the public and governing authorities. XGBoost was employed to forecast AQI, NO2, PM2.5, NOx, PM10, CO, SO2, NH3, and Ozone levels, outperforming traditional LSTM, Prophet, and ARIMA models. Evaluation using RMSE and MAE scores revealed XGBoost's efficacy, with scores of 20.65 and 14.35, respectively. The research highlights regions like Alandur, Arumbakkam, and Manali with notable concentrations of contaminants, emphasizing the need for immediate action. These findings highlight the significance of utilizing advanced algorithms for accurate air quality forecasting and proactive pollution management. © 2024 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Earthquake Prediction Through Machine Learning Approach 4

Earthquake Prediction Through Machine Learning Approach

引用

4th International Conference on Technological Advancements in computational sciences, ICTACS 2024

作者： Shrote, Pratik Dasarwar, Priya Dongre, Snehlata Khobragade, Prashant Intern Center of Excellence Data Science Gh Raisoni College of Engineering Nagpur India Nagpur Campus Pune India Gh Raisoni College of Engineering Dept. of Computer Science and Engineering Nagpur India H Raisoni College of Engineering Dept. of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798350387490

The population of earthquake-prone areas is growing, as is the number of people killed and injured by earthquakes. The problem of the increasing number of populated regions that are vulnerable to earthquakes is being addressed by a shortage of experts in earthquake engineering. This implies the requirement for automated intelligence-monitored mitigation and warning systems. Predicting earthquakes is still a major problem for disaster management around the globe. The objective of this work is to build a machine learning (ML) approach that uses geographic coordinates (latitude, longitude) and elevation (height) as inputs to forecast earthquake magnitude. The estimated magnitude is used to classify the seismic risk level for a given site into high, low, or no risk categories using Richter's scale. The study offers a thorough analysis of the methodology, covering feature engineering, data collecting, preprocessing, and model construction. A variety of machine learning methods are investigated, and relevant measures are used to assess their effectiveness. © 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

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：