检索结果-内蒙古大学图书馆

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Selvaraj, P. Shalma, H. Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computing Technologies Chennai Tamil Nadu Kattankulathur603203 India Sphoorthy Engineering College Department of Artificial Intelligence and Machine Learning Telengana Hyderabad India

ISBN: (纸本)9798331504403

This work aims to employ machine learning methods and visualization techniques for evaluating water quality by measuring its potability, a numerical indicator of water quality. The work utilizes water quality parameters to determine the stability condition using pH, Temperature, Dissolved Oxygen, Conductivity, Nitrate, Fecal Coliform, and Total Coliform to evaluate the overall water quality. ARIMA is utilized to identify and categorize water potability based on its features. Using Tableau's interactive dashboarding, we created an interactive dashboard to visually simplify water potability metrics in India. The study utilized both real datasets from various locations around the country using government data sourced directly from the Central Pollution Control Board (CPCB). Based on the results of the experiments, the ARIMA was found to be superior to other classifiers in accurately predicting water potability. © 2024 IEEE.

关键词： Water pollution control

来源：评论

学校读者我要写书评

暂无评论

Predictive Salary Modelling: Leveraging Data science Skills and Machine Learning for Accurate Forecasting 9

Predictive Salary Modelling: Leveraging Data Science Skills ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Haseeb, Mohammed Ayman Viswanathan, Rishi Iyer, Kaushik Hota, Anish Raj Prathaban, Banu Priya School of Computing Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur Chennai India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Kattankulathur Chennai India

ISBN: (纸本)9798350377972

In approaching predictive salary modeling, this article identified important job positions and skills in the data science business environment. They show the need for a model that would allow employers to calculate the required starting salary while considering sectors, Python known languages, SQL, and ML. It also analyzes linear regression models, Random Forests, and neural network point of view about salary prediction. Analyzing the findings, it is proved that skill-based salary models should be further developed to meet industry requirements, advise students, and support employers. We have applied various models as follows with random forest performing the best giving out an R2 score of 0.971. The ideas for building faultless, precision, and skill-based salary estimation models are presented to the readers at the end of the article. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance of an Incremental Classifier using Clustered-C4.5 Algorithm for Processing Big Data Streams 5

Evaluating the Performance of an Incremental Classifier usin...

引用

5th IEEE International Conference on Communication, computing and Industry 6.0, C2I6 2024

作者： Banu, E. Afreen Robert, P. Shah & Anchor Kutchhi Engineering College Dept of Computer Engineering Maharashtra Mumbai India Srm Institute of Science & Technology Dept of Computing Technologies Tamilnadu Kattankulathur India

ISBN: (纸本)9798350379884

Currently, the inevitability of big data stream processing is increasingly becoming more critical and imperative due to the incremental nature of the heterogeneous and massive volume of data engendered by various sources. C4.5 is the most renowned algorithm to address the problem of data stream classification in online mode by constructing decision trees. But, the traditional C4.5 algorithm has a significant adverse impact on the speed of data stream processing in real-time scenarios. To handle this problem, we propose a new variant of the C4.5 classifier, named the Clustered-C4.5 (CC4.5) algorithm to classify data streams in online mode. This work integrates a Correlation-based Feature selection and Bat Optimization Technique (CFBOT) with the CC4.5 algorithm to improve the classification performance. The CFBOT is employed to measure the dependencies among selected features and to determine the ideal subset for training and testing tasks. Meanwhile, CC4.5 organizes the data into smaller clusters instead of building a single decision tree. The integration of the CC4.5 algorithm and CFBOT helps the system classify imbalanced and multi-class datasets effectively. The performance of the proposed classifier is cautiously studied on the real-world dataset (i.e., UCI-heart disease dataset) by relating its enactment with many state-of-the-art approaches regarding classification accuracy, sensitivity, specificity, the area under the receiver operating characteristic curve (AUC), and intersection over-union (IoU). Additionally, the Wilcoxon rank-sum test is employed to assess whether our classification technique offers a statistically significant improvement over other classifier methods. The experimental results demonstrate that the proposed classifier outperforms other approaches with superior accuracy, sensitivity, specificity, AUC, and IoU of 93.6%, 96.2%, 79.3%, 92.3%, and 90.3%, correspondingly. Accordingly, we can conclude that CC4.5 is the better data stream classific

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Knowledge engineering Approach for Mapping Implicit Aspects to Explicit Aspects

引用

Computers, Materials & Continua 2022年第2期70卷 3491-3509页

作者： Jibran Mir Azhar Mahmood Shaheen Khatoon Computer Science Department Shaheed Zulfikar Ali Bhutto Institute of Science and Technology(SZABIST)Faculty of Computing and Engineering SciencesIslamabadPakistan Department of Computer Science Capital University of Science&TechnologyFaculty of ComputingIslamabad College of Computer Science and Information Technology King Faisal UniversitySaudi Arabia

Aspect’s extraction is a critical task in aspect-based sentiment analysis,including explicit and implicit aspects *** extensive research has identified explicit aspects,little effort has been put forward on implicit aspects extraction due to the complexity of the ***,existing research on implicit aspect identification is widely carried out on product reviews targeting specific aspects while neglecting sentences’dependency ***,in this paper,a multi-level knowledge engineering approach for identifying implicit movie aspects is *** proposed method first identifies explicit aspects using a variant of BiLSTM and CRF(Bidirectional Long Short Memory-Conditional Random Field),which serve as a memory to process dependent sentences to infer implicit *** can identify implicit aspects from four types of sentences,including independent and three types of dependent *** study is evaluated on a largemovie reviews dataset with 50k *** experimental results showed that the explicit aspect identification method achieved 89%F1-score and implicit aspect extraction methods achieved 76%*** addition,the proposed approach also performs better than the state-of-the-art techniques(NMFIAD andML-KB+)on the product review dataset,where it achieved 93%precision,92%recall,and 93%F1-score.

关键词： Movie NEs(named entities) aspects opinion words annotation process memory implicit aspects implicit aspects mapping word embedding and BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review on Early Diagnosis of Oral Squamous Cell Carcinoma by Deep Learning Techniques

Systematic Literature Review on Early Diagnosis of Oral Squa...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Sumathy, V. Pretty Diana Cyril, C. Department of Computing Technologies SRM Institute of Science and Technology SRM Nagar TN Kattankulathur603203 India Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar TN Kattankulathur603203 India

ISBN: (纸本)9798350305708

Oral Squamous Cell Carcinoma (OSCC) is the seventh most prevalent type of cancer in the neck and head. The prognosis and survival rate of the patient is significantly improved by early identification of OSCC. Due to tumor heterogeneity, such a diagnosis requires much time and a high-efficiency human experience. As a result, artificial intelligence systems assist professionals and physicians in making precise diagnoses. Recent advances in computer vision-based techniques and Computational Intelligence (CI) improve accuracy in medical images. This study aims to develop hybrid methodologies based on fused features to produce excellent outcomes for the early detection of OSCC. This systematic review aims to estimate deep learning (DL) based algorithms for early diagnosis OSCC to assist clinicians in oral cancer diagnosis and screening. The terms "squamous cell carcinoma, " "early diagnosis, " "oral cavity, " "histopathological image, " "biomarker, " "Optical Coherence Tomography (OCT) image, " and "deep learning" were used in a Google Scholar Cochrane and MEDLINE (PubMed), Embase and WoS databases (January 2018 to July 2023) to find relevant articles. The inclusion criteria were the use of deep learning approaches for early diagnosis of OSCC, articles older than 5 years, and publications written in English. Case reports and studies written in foreign languages met the exclusion criteria. 70 publications were chosen to be included in the systematic review out of the 194 studies that were initially found through the search. Deep learning techniques based on hybrid features are examined in evaluating performance metrics and superior results of the present systems employing biomedical images for OSCC diagnosis. It has been established that the deep learning-based early identification method for biomedical images has the ability to offer decision support for efficient oral cancer diagnosis and screening. © 2023 IEEE.

关键词： convolutional neural network deep learning hybrid method OCT Oral Squamous Cell Carcinoma

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Identification of Fake Indian Currency Using Ensemble Decision Tree in Comparison with Ridge Linear Classification 4

Enhancing the Identification of Fake Indian Currency Using E...

引用

4th IEEE International Conference on Data engineering and Communication Systems, ICDECS 2024

作者： Kishore Kumar, R. Nelson Kennedy Babu, C. Saveetha Institute of Medical and Technical Science Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamilnadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Cloud Computing Tamilnadu Chennai India

ISBN: (纸本)9798350393354

The objective of this work is Identification of Fake Indian Currency using Ensemble Decision Tree in Comparison with Ridge Linear Classification for better accuracy. Materials and Methods: For predicting the fake currency, an Ensemble Decision Tree is used in comparison to a Ridge Linear Classification with different training and testing splits. The EDT classifier model, which is suggested as the recommended choice, is trained using 80% of the dataset, while the remaining 20% is reserved for testing purposes. For SPSS analysis, the outcome of two classifiers is categorized as two groups and each group consists of 10 outcome values under different functional operations;finally, it counts 20. During SPSS analysis, the parameters CI of 95% and G power of 0.85 are used. The dataset contains 1,050 unique values related to the currencies and the factors considered are size, color, special attributes. Result: The SPSS analysis performed with the outcome of group 1 and group 2 and achieved mean accuracy of 88.47% and 85.759% respectively. It shows that there is no statistical significance difference between the Novel EDT algorithm and Ridge Linear algorithm with p=0.203 (p>0.05). Conclusion: The suggested approach - Ensemble Decision Tree successfully attained better accuracy in predicting the fake currency in comparison with Ridge Linear Classification. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Comparison of Novel Yolo V5 Algorithm in Identifying Land Cover Area of Geographical Regions over Single Shot Detector Algorithm Accuracy 2

Evaluation and Comparison of Novel Yolo V5 Algorithm in Iden...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in computing, Electrical and Electronics, ICIITCEE 2024

作者： Aravind, K. Kumar, S. Pradeep Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Science Department of Computer Science and Engineering Tamilnadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Cloud Computing Tamilnadu Chennai India

ISBN: (纸本)9798350306415

The research aims to evaluate and compare the Land cover Image detection accuracy rate of Novel Yolo v5 algorithm to Single Shot Detection. The images of the land areas are sourced with a count of 5109 from the Kaggle website. Accuracy rate of the Novel Yolo v5 algorithm and Single Shot Detection is assessed in this study. The prediction of image detection is carried out with an iteration size of twenty, with ten coming from Group 1 and ten coming from Group 2. The goal is to get a higher rate of accuracy from the prediction. The Novel Yolo v5 approach has a success percentage of 96.81 percent, which is much higher than the Single shot detector (SSD) technique, which has a success rate of 91.62 percent. A statistically significant difference may be seen between these two methods, as shown by a p value of 0.00 (p © 2024 IEEE.

关键词： Image detection Land conservation Machine learning Novel Yolo v5 Algorithm Prediction Single Shot Detector

来源：评论

学校读者我要写书评

暂无评论

An Accurate Blood Pressure Prediction Based on Clinical and Physiological Data Using Machine Learning

An Accurate Blood Pressure Prediction Based on Clinical and ...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Sivaji, U. Chatrapathy, K. Kiran, Ajmeera Shaker Reddy, Pundru Chandra Rao, P Varaprasada Partheeban, N. Institute of Aeronautical Engineering Department of Information Technology Dundigal Hyderabad India Reva University School of Computing & Information Technology Karnataka Bengaluru India Mlr Institute of Technology Computer Science and Engineering Dundigal Telangana Hyderabad India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Gokaraju Rangaraju Institute of Engineering and Technology Computing Science and Engineering Telangana Hyderabad India Galgotias University School of Computing Science and Engineering Utter Pradesh Greater Noida India

ISBN: (纸本)9798350308167

When attempting to diagnose hypertension or cardiovascular illness, blood pressure (BP) is an essential biological feature. Taking a reading is interrupted and can be painful when done with cuff-based equipment like a sphygmomanometer. Recently, a cuff-free approach has been presented that uses electrocardiogram (ECG) and photoplethysmography (PPG) signals. Due to the need for extensive multi-sensor collections, however, this approach is time-consuming and expensive. The current research uses a machine-learning(ML) strategy called classification-tree to examine the relationship between BMI, waist-circumference(WC), hip-circumference(HC), and waist-hip-ratio(WHR) in predicting hypertension(IBP). 400 college students, ranging in age from 16 to 63 (with women making up 56.3% of the sample), provided the data. In the training set, fifteen trees were generated for each sex by varying the number and order of predictors. Due to their low variance (89.56), low misclassification (.18), and high pseudo R2 (.43), BMI, WC, and WHR are the combination that yields the best anticipation for women. In the validation set, the model showed sensitivity of 82.54% and specificity of 83.68%, whereas in the test set, those numbers dropped to 45.65% and 65.15%, respectively. The lowest deviation (54.79), misclassification (.17), and highest pseudo R2 (.46) were found for BMI, WC, HC, and WHC when predicting male health. In the training set, this model showed sensitivity of 69% and specificity of 87.54%, whereas in the test set, these figures dropped to 58.38% and 69.70%, respectively. In the end, the classification-tree examination result was contrasted to the standard logistic-regression(LR) method, showing that the former was more accurate. © 2023 IEEE.

关键词： Blood Pressure Clinical data Hypertension Machine learning Physiological data prediction

来源：评论

学校读者我要写书评

暂无评论

Secured Normalized Tagged Response for Patient Critical Care Monitoring System: A Unified approach

Secured Normalized Tagged Response for Patient Critical Care...

引用

2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023

作者： Sivakumar, Soubraylu Vinay, B. Sai Arulmurugan, A. Prakash, U.M. Kumar, T. Rajesh Sridevi, S. Srm Institute of Science and Technology Computer Technologies School of Computing Chennai Kattankulathur India Saveetha Institute of Medical and Technical Sciences Computer Science and Engineering Saveetha School of Engineering Chennai India Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Chennai India

ISBN: (纸本)9798350344387

In the rapidly advancing realm of healthcare, ensuring the well-being of critical care patients stands as a paramount mission. Various cutting-edge sensors are available in the market, proficient in monitoring vital health. A substantial number of healthcare facilities still rely on manual processes, a practice that is not only repetitive and labor-intensive but also fraught with the potential for human errors. This pressing need for immediate, accurate responses in the context of critical care has driven the development of a comprehensive solution. Our proposed system brings together security, data normalization, and efficient data exchange, underpinned by a unified approach. Security, a cornerstone of healthcare, finds its realization in the implementation of JSON Web Tokens (JWT). This technology ensures the privacy and integrity of communication between healthcare entities. Crucial patient data, including personal particulars, lifeline parameters, and historical records, is securely housed in a scalable and non-redundant Postgres SQL database. In emergencies, time is of the essence. To expedite responses, an innovative tagged QR code technique is introduced. The unified approach doesn't simply prioritize security;it underscores the significance of data standardization and efficient data exchange. A robust security framework has been meticulously designed to protect sensitive patient information, minimize the risk of data breaches, and prevent unauthorized access. Furthermore, data normalization ensures that patient data is consistently structured and formatted, facilitating compatibility with diverse healthcare platforms and devices. The normalization additionally enhances interoperability, enabling seamless information exchange between different systems and healthcare providers. In summary, our unified approach, marked by state-of-the-art security, data normalization, and efficient data tagging, sets a new standard for patient care in critical settings, ensurin

关键词： Critical Care Emergency Health Care JSON Web Token Patient monitoring Postgres SQL QR Code

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

science China(Information sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

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：