Prediction of stock market trends has been an area great interest both to those who wish profit by trading stocks in the and for researchers attempting uncover information hidden data.Applications data mining techniques prediction, is research which receiving a lot attention recently.This work presents design performance evaluation hybrid decision tree-rough set based system predicting next days" trend Bombay Stock Exchange (BSE-SENSEX).Technical indicators are used present study extract...

Bearing fault, Impeller seal fault and cavitation are the main causes of breakdown in a mono block centrifugal pump hence, detection diagnosis these mechanical faults is very crucial for its reliable operation. Based on continuous acquisition signals with data system, it possible to classify faults. This achieved by extraction features from measured employing mining approaches explore structural information hidden acquired. In present study, statistical derived vibration used as features....

Prediction of surface roughness is always considered important in the manufacturing field. A product may require a particular that be specified by designer for various reasons, either functional requirement or aesthetic appeal. While modern systems and machines have contributed towards better control quality, computational facilities availability newer algorithms attract researchers to understand prediction quality manner. In this paper, multiple regression analysis presented. The predictors...

Stock price time series are extremely nonlinear in nature and hence, accurate stock forecasting has been a challenge. Accurate prediction of prices the direction movement is also essential for trader/investor order to trade profitably. A deep learning approach presented this study. total fourteen different models based on Long-Short Term Memory (LSTM), Gated Recurring Unit (GRU), Convolutional Neural Networks (CNN) Extreme Learning Machines (ELM) designed empirically evaluated all stocks S&P...

Most of the humps in India are not being constructed and maintained according to public safety guidelines Indian Road Congress (IRC) i.e., IRC099, which is resulting damage vehicles, severe discomfort driver even causing loss direction control leading fatalities. Very few methods were discussed literature for un-marked speed hump/bump detection. We propose a method that detects informs about upcoming marked real time using deep learning techniques gives distance vehicle away from it...

Deep learning-based models are ideally suited for accurately predicting electrical load in a smart grid. However, the computational overhead training and identifying optimal hyperparameters challenging problems. Two important challenges addressed this study. Firstly, novel technique is proposed to accelerate model process by selecting mini-batch size. The second challenge encountered maintaining operationalizing individual consumption forecasting as they not easily scalable. A methodology...

Monoblock centrifugal pumps are widely used in a variety of applications. Defects and malfunctions (faults) these result significant economic loss. Therefore, the must be under constant monitoring. When possible fault is detected, diagnosis carried out to pinpoint it. In many applications, role monoblock critical condition monitoring essential. Vibration-based analysis using machine-learning approach gaining momentum. particular, Artificial Neural Networks (ANNs), fuzzy logic roughsets have...

Dashboard cameras are becoming increasingly prevalent in vehicles, leading to a sig-nificant demand for reliable methods extract essential metadata, such as timestamps,geolocation, and speed, from recorded footage. This metadata is contextual-izing events captured by these cameras, facilitating tasks accident reconstruction,security monitoring, forensic analysis. However, many modern low-cost dashboardcameras overlay text directly onto video rather than logging separately. Thisstudy aims...

Stock market prediction is of great interest to stock traders and applied researchers. Main issues in developing a fully automated system are: feature extraction from the data, selection for highest accuracy, dimensionality reduction selected set accuracy robustness system. In this paper, an decision tree-adaptive neuro-fuzzy hybrid trend proposed. The proposed uses technical analysis (traditionally used by traders) tree selection. Selected features are then subjected reduced dataset...

Financial forecasting is an area of research which has been attracting a lot attention recently from practitioners in the field artificial intelligence. Apart economic benefits accurate financial prediction, inherent nonlinearities data make task analyzing and extremely challenging task. This paper presents survey more than 100 articles published over two centuries (from 1933 up to 2013) attempt identify developments trends with focus on application intelligence for purpose. The findings...

A system combining deep learning and stereovision for detection, tagging distance estimation of objects ahead, is presented in this study. Convolutional Neural Network (CNN) used to detect identify the field vision stereo camera. Once are detected identified, their from camera estimated by first constructing 3D point cloud using triangulation method. The implemented on Nvidia® Jetson TX1 with a Zed® camera, tested found be capable detection accuracy around 84% average error less than 4.7% up...

Generating consistent profits from stock markets is considered to be a challenging task, especially due the nonlinear nature of price movements. Traders need have deep understanding market behavior patterns in order trade

Abstract Recent years have witnessed the rise of supercapacitor as effective energy storage device. Specifically, carbon-based electrodes been experimentally well studied and used in fabrication supercapacitors due to their excellent electrochemical properties. publications reported use Machine Learning (ML) techniques study correlation between structural features performance metrics. However, poor R-squared values (i.e., large deviations from ideal value unity) RMSE these works reflect lack...

Stock market prediction is an important area of financial forecasting, which great interest to stock investors, traders and applied researchers. Main issues in developing a fully automated system are: feature extraction from the data, selection for highest accuracy, dimensionality reduction selected set accuracy robustness system. In this paper, decision tree-adaptive neuro-fuzzy hybrid proposed. The proposed uses technical analysis (traditionally used by traders) tree selection....

Monoblock centrifugal pumps are a crucial part of many industrial plants. Early detection faults in can increase their reliability, reduce energy consumption, service and maintenance costs, life-cycle safety, thus resulting significant reduction life-time costs. It is clear that the fault diagnosis condition monitoring important issues cannot be ignored. Machine learning-based approach to becoming very popular, mainly due high accuracy when compared older statistical methods. There set...

Chatter is the main reason behind failure of any part in machining centre and lowers productivity. occurs as a dynamic interaction between tool work piece resulting poor surface finish, high-pitch noise premature failure. In this paper, chatter prediction done by active method considering parameters like spindle speed, depth cut, feed rate including dynamics both workpiece. The vibration signals are acquired using an accelerometer closed environment. From discrete wavelet transformation...