检索结果-内蒙古大学图书馆

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Partha Pratim Saha Ponchanon Datta Rone Debabrata Sarkar Md Abu Yusuf Md Iqbal Hossan Md Shah Jalal Mazumder Mohammed Mahbubur Rahman Mohammad Jakaria Hossain Md Moynul Islam Department of Computer Science Maharishi International University IA USA Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

Accurate prediction of CO 2 emissions is significant in the development of appropriate strategies to mitigate climate change. This study applies machine learning methodologies for the forecast of CO 2 emissions using a global dataset from I960 to 2022. The dataset used from Kaggle comprises all the relevant features: power output from fossil fuels, nuclear, and renewables, in addition to GDP and land area. Three machine learning models were constructed and evaluated for their effectiveness in prediction: Random Forest, Gradient Boosting, and Linear Regression. The Random Forest model had the highest accuracy, as demonstrated by its R 2 score of 0.995, which showcases its strength in handling intricate, nonlinear interactions and identifying key variables, such as dependence on fossil fuels. The R 2 score for Gradient Boosting was 0.987, which shows that this model is similarly good at identifying complex relationships between features. Conversely, Linear Regression underperformed despite its processing efficiency due to its constraints with nonlinear data. This study highlights the efficacy of ensemble models in predicting CO 2 emissions. It offers practical recommendations for policymakers to formulate strategies to decrease fossil fuel use and promote renewable energy utilization. Future endeavors will include real-time data and investigate hybrid models to enhance temporal forecasting and practical application.

关键词： Renewable energy sources Climate change Accuracy Linear regression Predictive models Boosting Real-time systems Fossil fuels Random forests Carbon emissions

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adaptation, and Enhanced Predictive Modeling for Diabetes Risk Assessment

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adap...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Hole, Shreyas Rajendra Kolluru, Vinothkumar Gangul, Ranita Kolekar, Sagar Chintakunta, Advaitha Naidu Mungara, Sudeep Bangalore India Institute of Technology Department of Data Science Stevens HobokenNJ07030 United States Delaware State University Computer Science & Engineering Bangalore India Department of Civil Engineering Pune India University of North Carolina at Charlotte Department of Computer Science CharlotteNC28223 United States Masters in Information Systems Stevens Institute of Technology HobokenNJ07030 United States

ISBN: (纸本)9798331508685

With advancements in artificial intelligence, it is natural for the health industry to focus on IOT devices. AI could promote a paradigm shift in how doctors and patients interact through immediate updates, predictive features, and remote access. The focus of this study is the outreach and employment aspects revolving around AI-enabled health care, with special attention to mHealth solutions. We searched through published data and came across 112 relevant studies identifying keywords such as accessibility, empowerment, and workforce. One of the most interesting findings was the fact that AI targeting mobile applications has the possibility of increasing access to health services by approximately 60 percent for rural areas, as well as increasing the patient cooperative rate by approximately 45%, where a predictive health tracking device has been utilized. We proposed two new measures: the Physical Activity and Nutrition Index (PANI) and Health Status Index (HSI), allowing for better diabetes risk predictions with a 0.82 AUC-ROC and better generalizability than traditional baselines, with an improvement of 12%. When identifying the best available ML models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and Bayesian Neural Networks, we found that the hybrid Random Forest + Linear SVC model had the best performance with recall and accuracy of 0.77 and 0.72, respectively. The ability of the model to demonstrate both interpretability and specificity was evident. It was also observed that synthetic data augmentation (SMOTE) increased the recall for minority class predictions by 18% but did not reduce specificity. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

BOISHOMMO: Holistic Approach for Bangla Hate Speech

arXiv

引用

arXiv 2025年

作者： Abdullah Al Kafi, Md. Banshal, Sumit Kumar Sadman Shakib, Md. Azam, Showrov Tabashom, Tamanna Alam Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Alliance University Bangalore562106 India

One of the most alarming issues in digital society is hate speech (HS) on social media. The severity is so high that researchers across the globe are captivated by this domain. A notable amount of work has been conducted to address the identification and alarm system. However, a noticeable gap exists, especially for low-resource languages. Comprehensive datasets are the main problem among the constrained resource languages, such as Bangla. Interestingly, hate speech or any particular speech has no single dimensionality. Similarly, the hate component can simultaneously have multiple abusive attributes, which seems to be missed in the existing datasets. Thus, a multi-label Bangla hate speech dataset named "BOISHOMMO" has been compiled and evaluated in this work. That includes categories of HS across race, gender, religion, politics, and more. With over two thousand annotated examples, BOISHOMMO provides a nuanced understanding of hate speech in Bangla and highlights the complexities of processing non-Latin scripts. Apart from evaluating with multiple algorithmic approaches, it also highlights the complexities of processing Bangla text and assesses model performance. This unique multi-label approach enriches future hate speech detection and analysis studies for low-resource languages by providing a more nuanced, diverse dataset.9 © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CPS-DERMS: Cyber-Physical Security and Impact Analysis of DERMS Against MITM Attacks

CPS-DERMS: Cyber-Physical Security and Impact Analysis of DE...

引用

IEEE Green Technologies Conference (IEEE-Green)

作者： Sai Chandana Vallam Kondu Gelli Ravikumar Sathya Narayana Mohan Department of Electrical and Computer Engineering Computer Science Iowa State University Ames IA USA

ISBN: (数字)9798331520182

ISBN: (纸本)9798331520199

The growing integration of Distributed Energy Resources (DERs) into modern power grids, managed via DER Management Systems (DERMS), has introduced significant cybersecurity challenges. Communication vulnerabilities in DERMS architecture create opportunities for adversarial attacks, such as Man-in-the-Middle (MITM), that intercept and manipulate critical data flows, disrupting grid operations and compromising reliability. This paper investigates MITM attacks targeting three critical nodes in DER-DERMS communication: (i) DER gateway routers, (ii) inter-router pathways, and (iii) DERMS gateway routers. To analyze these vulnerabilities, we developed CPS-DERMS, a multi-co-simulation hardware-in-the-loop testbed integrating grid-side simulations with OPAL-RT, large-scale cyber simulations using NS-3, and an indige-nous Python-based DERMS platform. The study demonstrates innovative strategies for executing MITM attacks, including maintaining payload integrity and bypassing detection mechanisms, while highlighting the critical vulnerabilities within DER-DERMS communication systems. We considered a real utility's DER-integrated distribution grid as a case study. Experimental results reveal that MITM attacks can cause overvoltages, reactive power imbalances, and increased tap-changer operations, significantly degrading power quality and grid reliability.

关键词： Reactive power Analytical models Power quality Logic gates Power system reliability Distributed power generation Smart grids Reliability Surges Resilience

来源：评论

学校读者我要写书评

暂无评论

EAPCET College List Recommendation System

EAPCET College List Recommendation System

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Y.V.Bhaskar Reddy C Satya Kumar Parise Sai Niteesh Gunda Ravi Teja P. Ashok Reddy M. Babu Reddy Department of Computer Science and Engineering Lakireddy Bali Reddy College of Engineering (Autonomous) Mylavaram India Department of Computer Science and Engineering Vardhaman College of Engineering Engineering Lakireddy Bali Reddy College of Engineering (Autonomous) Mylavaram India Department of Computer Science Krishna University Machilipatnam

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

After finishing Intermediate, selecting the right engineering college by the student is a big challenge for them which strongly effects on their career if they neglects to select. Nowadays, there are many engineering colleges in our state to choose from, and students will struggle to make careful decisions among them. To help them with this challenge, we suggest using a College List Recommendation System that uses machine learning techniques to recommend the list of colleges which are suitable for them. This system is designed to give personal suggestions to the students based on their details like EAPCET rank, gender, caste and so on. Our recommendation system relies on a detailed dataset that includes the rank cutoffs for colleges from the previous year in different categories, gender, caste, college code and so on. By using a supervised learning approach, our machine learning model trains and finds insight patterns of the dataset. Thus, our recommendation system allows the model to provide smart recommendations, offering a suitable list of colleges that matches the student details. This approach targets to simplify the decision-making process for students, providing guidance as they navigate through the many available college options.

关键词： Filters Navigation engineering profession Supervised learning Decision making Education Machine learning Reliability Recommender systems Finishing

来源：评论

学校读者我要写书评

暂无评论

Recognition of the Hornbill Eye’s Iris Using Bit Plane Processing, Un-sharp Masking and High Boost Filtering 2nd

Recognition of the Hornbill Eye’s Iris Using Bit Plane Proc...

引用

2nd Analytics Global Conference, AGC 2024

作者： De, Parthasarathi Chakrabarti, Samiddha Department of Computer Science and Engineering Sister Nivedita University Kolkata India Department of Computer Science and Engineering Narula Institute of Technology Kolkata India

ISBN: (纸本)9783031751561

This research focuses on advancing the recognition capabilities of the Hornbill Eye’s Iris through the integration of sophisticated image processing methodologies. Similar to humans, iris patterns of any animals are unique and stable in nature which makes a reliable source for the identity of any individual, this can be particularly valuable in wildlife conservation and management. Animal iris recognition can be employed in the development of monitoring systems for wildlife. This can be crucial for tracking endangered species, monitoring population dynamics, and studying migration patterns. A novel method for the recognition of Iris of the Hornbill is proposed in the paper where collected iris images are processed through Canny Edge Detector for precise edge extraction, followed by Circular Hough Transform for the Localization of the Region of Interest (ROI) that is eye’s iris, and then for the Image Enhancement Un-Sharp Masking is applied to accentuate subtle details and edges;and High Boost Filtering to refines the image by amplifying high-frequency components. The boosted grey Scale Image corresponding to the four LSB’s are used for matching purpose by weighted arithmetic mean of the intensity values. The results obtained are found to give higher accuracy in terms of Recognition rate where Equal error rate, False Acceptance Ratio and False rejection ratio are compared with Human iris Recognition. The experimental results demonstrate the efficiency of the proposed method in achieving robust and reliable recognition outcomes, making it a valuable contribution to the field of biometric animal identification systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Integrated Framework for Equitable Healthcare AI: Bias Mitigation, Community Participation, and Regulatory Governance

Integrated Framework for Equitable Healthcare AI: Bias Mitig...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Joydeep Chandra Ramanjot Kaur Rashi Sahay Dept. of Computer Science and Engineering Chandigarh University Mohali Punjab India Dept. of Computer Science and Engineering MRIIRS Faridabad India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Artificial intelligence (AI) has revolutionized healthcare by enhancing diagnostic precision, personalizing treatments, and optimizing clinical workflows. However, algorithmic biases arising from imbalanced training data dis-proportionately affect marginalized populations, perpetuating health disparities. For instance, a widely-used predictive model underprioritized Black patients by equating healthcare costs with illness severity, restricting access to essential care. To address these challenges, this paper introduces an integrated framework combining adversarial debiasing, reinforcement learning (RL)-driven threshold optimization, synthetic data augmentation, and community engagement strategies. Empirical evaluations using the MIMIC-III dataset demonstrate near-perfect Area Under the ROC Curve (AUC = 0.994) alongside significant reductions in demographic parity (DP = 0.000) and error rate differences across subgroups. While the RL-optimized threshold ensures no missed diagnoses, it increases false positives, highlighting the trade-offs between fairness and precision. This work underscores the importance of synthesizing technical, regulatory, and community-driven approaches to promote equitable AI deployments. By embedding participatory design principles and aligning with emerging governance frameworks like the European Union’s AI Act, the proposed methodology offers a scalable pathway toward transparent, accountable, and high-impact healthcare AI solutions.

关键词： Ethics Prevention and mitigation Training data Medical services Reinforcement learning Prediction algorithms Optimization Standards Synthetic data Guidelines

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis on Optimal Routing in Wireless Mesh Network Using Optimization and Machine/Deep Learning Algorithms

Comprehensive Analysis on Optimal Routing in Wireless Mesh N...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Kaata Ranjith Kumar K. Bala Kalyanapu Srinivas Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Computer Science and Engineering Vaagdevi Engineering College Warangal India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Wireless Mesh Networks (WMNs) is an important component of wireless communications by enhancing the network coverage. The mesh network topology is interconnecting all nodes in the cluster. However, the existing approaches utilized for optimal routing in WMN face challenges such as increased delays, packet loss, network congestion that lead to inefficient data transmission. WMN has an ability to deliver efficient performance even with a large number of devices. Additionally, WMNs support a wide range of applications, by using its effectiveness in various scenarios. The fundamental architecture of a mesh network integrates multiple wireless nodes interconnected through base stations for efficient routing communication. Mesh networks able to adopt different client-based structures, including infrastructure and hybrid configurations. Optimization, learning techniques and Software defined network methods are utilized for efficient optimal routing to enhance the efficiency of data transmission, while reducing delay. In this study, routing-based optimization and Machine (ML), Deep Learning (DL) algorithms are reviewed along with its advantages and limitations. The performance ML or DL model is utilized for optimal routing in WMN is evaluated based on performance metrics such as Delay, Throughput, Packet Delivery Ratio (PDR) and Connected Client Ration (CCR).

关键词： Wireless communication Mesh networks Network topology Wireless mesh networks Packet loss Routing Delays Topology Data communication Optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Medical Image Processing for Tumor Detection Using Hybrid CNN Framework

Efficient Medical Image Processing for Tumor Detection Using...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Vijayalakshmi. DM G. Fathima Department of Computer Science & Engineering Adhiyamaan College of Engineering (Autonomous) Hosur India Department of Computer Science and Engg Adhiyamaan College of Engineering (Autonomous) Hosur India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Medical image processing is a critical field that supports early diagnosis and treatment planning for various diseases, including tumors. Tumors, if detected at an early stage, can significantly improve patient outcomes. However, the complexity of medical imaging data, including noise, artifacts, and variations in tumor shapes and sizes, presents significant challenges. This research proposes an innovative framework, CNN-Extreme Learning Machine Hybrid Algorithm (CNELM-Hybrid). The framework leverages the feature extraction capabilities of Convolutional Neural Networks (CNN) and the ultra-fast classification efficiency of Extreme Learning Machine (ELM). CNELM-Hybrid integrates these techniques into a unified architecture, CNELM-Edge, to deliver a robust and scalable solution for real-time medical image analysis. Simulation analysis was carried out using performance metrics such as classification accuracy, processing speed, sensitivity and specificity. The results demonstrate that CNELM-Hybrid achieves superior performance and significantly reduced computational time. Furthermore, the hybrid model exhibited enhanced capability in handling complex and imbalanced datasets, which are common challenges in medical image processing. These findings underscore the potential of CNELM-Hybrid in advancing tumor detection methodologies and its applicability in real-time clinical environments.

关键词： Accuracy Image analysis Medical services Sensitivity and specificity Feature extraction Real-time systems Convolutional neural networks Biomedical image processing Medical diagnostic imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

PhishVQC: Optimizing Phishing URL Detection with Correlation Based Feature Selection and Variational Quantum Classifier

PhishVQC: Optimizing Phishing URL Detection with Correlation...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Md. Farhan Shahriyar Gazi Tanbhir Abdullah Md Raihan Chy Mohammed Abdul Al Arafat Tanzin Md. Jisan Mashrafi Dept. of Computer Science and Engineering World University of Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering Southern University Bangladesh Chittagong Bangladesh Dept. of Computer Science and Engineering Brac University Dhaka Bangladesh

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Phishing URL detection is crucial in cybersecurity as malicious websites disguise themselves to steal sensitive information. Traditional machine learning techniques struggle to perform well in complex real-world scenarios due to large datasets and intricate patterns. Motivated by quantum computing, this paper proposes using Variational Quantum Classifiers (VQC) to enhance phishing URL detection. We present PhishVQC, a quantum model that combines quantum feature maps and variational ansatzes such as RealAmplitude and EfficientSU2. The model is evaluated across two experimental setups with varying dataset sizes and feature map repetitions. PhishVQC achieves a maximum macro average F1-score of 0.89, showing a 22% improvement over prior studies. This highlights the potential of quantum machine learning to improve phishing detection accuracy. The study also notes computational challenges, with execution wall times increasing as dataset size grows.

关键词： Uniform resource locators Quantum computing Correlation Accuracy Phishing Computational modeling Machine learning Feature extraction Intelligent systems

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：