检索结果-内蒙古大学图书馆

4th International Conference on Communication and Intelligent systems, ICCIs 2022

作者： Mohanavel, Adithya Asmath Haseena, M.I. sabiyath Fatima, N. Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India

ISBN: (纸本)9789819920990

In the cutting-edge era, stock prediction is soaring to a new peak since the investors forsake risking the economy. so, they exhibit more interest in prognosticating the future value of the company or any product before they buy which reverberates in gain. stock prediction drastically increases the accuracy of prognosticating profit and loss by comparing the pattern with the previous data set. This paper deals with both technical and fundamental stock analysis. It uses a boolean-b.s.d algorithm for searching for any pattern match in the trend of the data with the historical data warehouse of stocks and if any, subsequently applying time series algorithms to predict the profit or loss behaviour of the pattern. It treats the technical data analysis in a way to improvise accuracy. The recorded data is fed into the hybrid algorithm which is the combination of five top-performing trading algorithms namely Exponential moving average, Relative strength index, Average directional index, standard deviation index, and On-balance volume. The result of technical and fundamental data analysis is then integrated to procure the overall profit percentage. The inter-day trading profit is acquired using technical data analysis and the intraday trading profit is reaped through fundamental data analysis. © 2023, The Author(s), under exclusive license to springer Nature singapore Pte Ltd.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

smart Traffic Monitoring system 3rd

Smart Traffic Monitoring System

引用

3rd International Conference on Information Technology, InCITe 2023

作者： bragadeesh, A. Harish, s. Fatima, N. sabiyath Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India

ISBN: (纸本)9789819959938

This paper presents a prototype design for a smart traffic system to be used at junction roads. This project uses traffic cameras for vehicle detection where automatically the signal timing changes by sensing the traffic data. Here, the parameters of the traffic dataset are the number of vehicles, speed, and vehicle type. If there is no vehicle on the road with a green signal, the traffic keeps accumulating on other roads of the junction. The conventional traffic system uses a fixed time, and its performance is considered poor in efficiency. To provide an alternative to conventional traffic systems, this proposed system is designed to effectively manage traffic congestion. This proposed method uses computer vision and analyzer algorithms to detect the vehicle’s speed and calculate whether or not the vehicle will be able to reach the stop line to pass through within the available green signal time in real-time. If there is no vehicle in the green zone of a traffic light that has the green light, then it will check the other camera which is planted at a particular distance away from the stop line to detect vehicles and if there is a vehicle crossing this camera, the computer vision and the analyzer will check the speed, of the vehicle and calculates whether the vehicle will pass the traffic light before the red light is ON. If the detected vehicle will not pass on time the traffic light will automatically change to Red and the next road will get a green light instantaneously. so, the road traffic can be cleared and the signal time can be used effectively, Thus it will address the problem which causes traffic congestion at the junctions and more importantly prioritize green signal changes for emergency vehicles in real-time scenarios. © The Author(s), under exclusive license to springer Nature singapore Pte Ltd 2023.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of a Handwritten Digit Recognition Using CNN-WOA 5

Performance Analysis of a Handwritten Digit Recognition Usin...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Nandhini Devi, s. Fatima, N. sabiyath B.S. Abdur Rahman Crescent Institute of Science & Technology Department of Computer Science and Engineering TanilNadu Chennai India

ISBN: (纸本)9798350321425

Handwritten Digit Recognition (HDR) techniques are acquiring favor in academia and b.s.ness. because of their complex and irregular patterns, handwritten texts are difficult to recognize. Word retrieval in limited-resource scripts is complex and time-consuming. Randomizing samples and increasing the size of training datasets enhance deep learning and neural network, models. HDR techniques heavily rely on manually-programmed key point information. The writing styles and dimensions of the input sample make numerical identification and categorization difficult. This work circumvents these limitations by employing a CNN model and an effective HDR scheme. HDR enhances the classification accuracy of the MNIsT dataset. The Gaussian filter and the Convolution algorithm polish the numbers. CNN-WOA is indicated as the model because the Algorithm for Whale Optimization Algorithm (WOA) fine-tunes CNN parameters. Using accuracy, precision, recall, specificity, AUC, F1-score, and false positive rate, simulation outcomes of the CNN-WOA model are compared to state-of-the-art techniques. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

short-term Wind Power Ramp Forecasting Using sequential Approach

Short-term Wind Power Ramp Forecasting Using Sequential Appr...

引用

2024 IEEE International Conference on Modeling, simulation and Intelligent Computing, MosICom 2024

作者： Gopalakrishnan, Leechita barrera, Julian L Cardenas Fatima, N. sabiyath B.S. Abdur Rahman Crescent Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India University of New Brunswick Dept. of Electrical and Computer Engineering Fredericton Canada

ISBN: (纸本)9798331533311

As wind energy becomes a key player in the global transition to renewable energy, its variability presents significant challenges. Accurate wind ramp forecasting is crucial for managing such rapid fluctuations in wind power output, ensuring grid stability, and enhancing the reliability of renewable energy integration. This paper presents a short-term wind ramp forecasting model using a sequential approach: initially forecasting wind power through the integration of Variational Mode Decomposition (VMD) and the XGboost algorithm, and subsequently detecting wind ramps using the Definition b.s.d sign Indicator (DsI) method. The historical wind speed and power data for Turkey was obtained from Kaggle. The dataset comprises readings from a wind turbine's sCADA system in Turkey, with measurements recorded at 10minute intervals. Variational Mode Decomposition (VMD) was applied to deconstruct and restore the historical wind power of the wind field, resulting in the formation of three training datasets. Wind power projections for the subsequent 8 hours, at 10 -minute intervals, are generated using historical wind power, wind speed, and wind direction as inputs. The DsI algorithm is employed to identify ramps. To assess the predictive capability of the proposed model, two algorithms, sVR and XGboost, were employed for forecasting and the resulting error is minimal. The proposed model, VMD + XGbOOsT is also compared without VMD to evaluate the performance. Taking mean square error (MsE), root mean square error (RMsE) mean absolute error (MAE), and symmetric mean absolute percentage error (sMAPE) as evaluation indicators, the results show that the forecasted accuracy of wind power is significantly improved after VMD processing. The performance of XGbOOsT is better than sVR in the two evaluation indicators. Precision, Recall, and F1-score are calculated to evaluate the accuracy of the predicted wind ramps. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive beamforming Model for 5G Millimeter Wave Uplink Communication system 2

A Novel Adaptive Beamforming Model for 5G Millimeter Wave Up...

引用

2nd International Conference on Artificial Intelligence and smart Energy, ICAIs 2022

作者： borse, Indrabhan Patil, Hitendra D. Ssvps B.S. Deore College of Engineering Department of Computer Engineering Dhule India

ISBN: (纸本)9781665400527

Millimeter wave (MMW) communication systems are emerging model for satisfying the increased necessity of high data rate of future generation cellular communications. The MMW frequencies give the prospective of increment in magnitude orders in terms of capacity. Though, MMW network links suffers from faster differentiation in quality and vulnerable to blockage. The main intent of this paper is to develop an adaptive beamforming technique of uplink communication in 5G millimeter wave cellular network. This paper optimizes the weight of narrowband in adaptive beamforming for enhancing the performance of MMW communication. Here, the adaptiveness in the beamforning is also accomplished by modifying the weight updating strategy of adaptive beamforming, which is performed by the hybrid meta-heuristic algorithm called salp-bird swarm optimization (s-bsO) using shark smell optimization (ssO) and bird swarm Algorithm (bsA). The comparison is done over the existing models to prove the effective performance of the proposed adaptive beamforming. © 2022 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Convolutional-Neural Network b.s.s speaker Emotion Detection b.s.d on Human-computer Interaction 1

Convolutional-Neural Network Bases Speaker Emotion Detection...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Nithya, b. saranya, R. Joseph, Mary Josphineleela, R. Thirunagalingam, Arunkumar Kodali, Arun Kumar B.S. Abdur Rahman Crescent Institute of Science and Technology Dept of Computer Science and Engineering Chennai India V.S.B. Engineering College Department of Computer Science and Engineering Karur India St. Joseph's Institute of Technology OMR Department of IT Chennai119 India Panimalar Engineering College Department of Computer Science and Engineering India Mckesson Corporation United States Mphasis Corporation

ISBN: (纸本)9798331518578

The present investigation proposes a Convolutional Neural Network (CNN)-b.s.d method for human-computer interaction (HCI) speaker emotion identification. Optimising the user experience through clearer and sympathetic connections is made possible by emotional knowledge. Conventional techniques for detecting emotions depend on manually created characteristics, which are frequently laborious and less resilient to speech variability. by using CNNs' automatic feature extraction capabilities, the suggested system analyses speech signal spectrograms and extracts crucial emotional indicators. The method obtains notable gains in emotion classification accuracy by retraining the system on a varied collection of emotional speech samples. Important emotional states like happiness, anger, sadness, and neutrality are all successfully distinguished using the CNN model. This study demonstrates how deep learning can help develop emotion-sensitive HCI systems and promote more organic and contextually aware human-machine interactions. Applications in customer service, healthcare, and virtual assistants can benefit from the technique's adaptability and versatility. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

bubble Prediction in stock Markets: Leveraging sVM and Technical Indicators for High Accuracy 3

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

3rd International Conference on Electronics and Renewable systems, ICEARs 2025

作者： Yuvaraj, s. Chenni Kumaran, J. Manogar, E. Doss, P.Lourdu Mahimai Gunasekaran, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TamilNadu Chennai India B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai India

ISBN: (纸本)9798331509675

Predicting stock market bubbles is indispensable for risk control and refinement of trading strategies. Therefore, this study presents a Machine-Learning Framework to detect price bubble formations b.s.d on support Vector Machine (sVM) and through important technical indicators. Among these are momentum indicators, such as the Relative strength Index (RsI), and the Moving Average Convergence Divergence (MACD) histogram, which are complemented with volatility measures from bollinger bands and with normalized volume indicators, all to improve predictive accuracy. Recent historical stock data were fed to the model during training and testing, yielding exceptional accuracy: 98.54% on the test set and 98.95% on the training set. The performance evaluation was carried out b.s.d on Classification Reports, Confusion Matrices, Receiver Operating Characteristic (ROC) curve, and Precision-Recall metrics, thus confirming the performance efficiency of the developed framework. With this approach, bubbles' early detection allows traders and analysts a powerful tool to make informed decisions in risk mitigation or strategic enhancement. © 2025 IEEE.

关键词： support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis and Prediction of Diabetes Using Machine Learning Approaches 5th

A Comparative Analysis and Prediction of Diabetes Using Mach...

引用

5th Doctoral symposium on Computational Intelligence, DosCI 2024

作者： Ansari, Gufran Ahmad bhat, salliah shafi bhoite, sachin Department of Computer Science and Engineering and Software Engineering University of Hail Hail Saudi Arabia Computer Applications B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai600048 India Pune411 038 India

ISBN: (纸本)9789819763177

Diabetes is a leading cause of death. People with type 1 diabetes (T1D) can face a number of consequences from their illness. Hyperglycemia is a symptom of T1D disease. Hyperglycemia can be symptoms that can be used for predicting diabetes in patients using the machine learning approach (MLA). Learning algorithms play a role in disease detection and prediction of decision-making. The leading cause of diabetes is really a high blood sugar level or a lack of insulin. As a consequence, it is critical to develop a reliable method to predict diabetes. Once it becomes a serious health concern, it will damage different organs such as the lungs, brain, nerves, blood vessels and heart as a result. several approaches for detecting diabetes have been used in recent decades. Early diabetic diagnosis is currently very important to help the patients’ health, and this can be done by utilizing a variety of procedures. Tenfold cross-validation technique was used to train dataset for classification. In this paper, authors use different classifications of algorithms such as random forest, decision tree, logistic regression and multilayer perceptron for finding T1D patients. The accuracy of MLP is 98.077% which is the highest among other algorithms. © The Author(s), under exclusive license to springer Nature singapore Pte Ltd. 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Precise diagnosis of Alzheimer’s disease using Recursive Feature Elimination (RFE) method

International Journal of Systematic Innovation

引用

International Journal of systematic Innovation 2022年第3期7卷 27-36页

作者： Ansari, Gufran Ahmad sivakani, R. srisakthi, s. Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Tamilnadu VandalurChennai India Department of Computer Application B.S. Abdur Rahman Crescent Institute of Science and Technology Tamilnadu VandalurChennai India

One of the prevalent diseases that the elderly tend to have patients has been Alzheimer's disease (AD). It is a neurological disease where the brain cells start to deteriorate. As the disease progresses it eventually leads to the death of the brain cells. Death in brain cells results in various problems like memory loss change in behavior patterns and many more. The most challenging problem has been in predicting an early diagnosis of AD in patients. The importance of the disease is that it is detected early. If early detection is done, the death of brain cells can be reduced. The disease is predicted b.s.d on the various features of the patient. Feature selection has been one of the important steps in predicting the disease. This paper takes the OAsIs data set and implements the different algorithms and proposes a model. The proposed model identifies the salient feature by recursively considering smaller and smaller sets of the features. The classification has been done for evaluating the feature selection. The result has been compared before the feature selection method and after the feature selection method. The performance metrics show improved scores after applying the feature section concept. © 2022,International Journal of systematic Innovation. All Rights Reserved.

关键词： Alzheimer Early diagnosis Feature selection Recursive feature elimination

来源：评论

学校读者我要写书评

暂无评论

Enhancing stock Market Prediction with an LsTM-Attention Model Integrating Macroeconomic and sentiment Features

Enhancing Stock Market Prediction with an LSTM-Attention Mod...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and smart Electrical systems, ICsEs 2024

作者： suberiya begum, s. Fatima, N. sabiyath Abb.s. Mohamed B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Vandalur600048 India Peri Institute of Technology Department of Mechanical Engineering Chennai600048 India

ISBN: (纸本)9798331543617

The forecasting of stock price movements has remained an open issue for a long time because of the unpredictable and nonlinear patterns of the data. To improve the precision of time series models for stock market prediction, this paper presents a new LsTM -attention model. The proposed method is different from statistical and machine learning models as LsTM can model long-term dependencies in the temporal data and attention layer is used to handle with noise in stock price temporal data. Furthermore, this paper proposes an enhancement to feature engineering where the model has more contexts about the market through the use of macroeconomic indicators, sentiment analysis of financial news articles, and historical stock prices. Application of the model to historical data of major indices is shown in experiments that at an average of 89.7% prove the model to be a notable improvement over the b.s.line models. The methodology for time series forecasting is considered to be an improvement over current approaches for advancing accuracy of predictions in financial applications, especially stock markets, and is useful for investors and analysts in decision-making. © 2024 IEEE.

关键词： Prediction models

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：