scholarly journals Static and Dynamic Activity Detection with Ambient Sensors in Smart Spaces

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 804 ◽  
Author(s):  
Sagar Shelke ◽  
Baris Aksanli
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Real Time ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Connected Components ◽  
Activity Detection ◽  
Smart Space ◽  
Smart Spaces ◽  
Feed Forward

Convergence of Machine Learning, Internet of Things, and computationally powerful single-board computers has boosted research and implementation of smart spaces. Smart spaces make predictions based on historical data to enhance user experience. In this paper, we present a low-cost, low-energy smart space implementation to detect static and dynamic human activities that require simple motions. We use low-resolution (4 × 16) and non-intrusive thermal sensors to collect data. We train six machine learning algorithms, namely logistic regression, naive Bayes, support vector machine, decision tree, random forest and artificial neural network (vanilla feed-forward) on the dataset collected in our lab. Our experiments reveal a very high static activity detection rate with all algorithms, where the feed-forward neural network method gives the best accuracy of 99.96%. We also show how data collection methods and sensor placement plays an important role in the resulting accuracy of different machine learning algorithms. To detect dynamic activities in real time, we use cross-correlation and connected components of thermal images. Our smart space implementation, with its real-time properties, can be used in various domains and applications, such as conference room automation, elderly health-care, etc.

EMOTIONS RECOGNITION IN HUMAN SPEECH USING DEEP NEURAL NETWORKS

2021 ◽  
pp. 44-51
Author(s):  
E. Yu. Shchetinin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Recurrent Neural Network ◽  
Deep Neural Networks ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Audio Recordings ◽  
Computer Studies

The recognition of human emotions is one of the most relevant and dynamically developing areas of modern speech technologies, and the recognition of emotions in speech (RER) is the most demanded part of them. In this paper, we propose a computer model of emotion recognition based on an ensemble of bidirectional recurrent neural network with LSTM memory cell and deep convolutional neural network ResNet18. In this paper, computer studies of the RAVDESS database containing emotional speech of a person are carried out. RAVDESS-a data set containing 7356 files. Entries contain the following emotions: 0 – neutral, 1 – calm, 2 – happiness, 3 – sadness, 4 – anger, 5 – fear, 6 – disgust, 7 – surprise. In total, the database contains 16 classes (8 emotions divided into male and female) for a total of 1440 samples (speech only). To train machine learning algorithms and deep neural networks to recognize emotions, existing audio recordings must be pre-processed in such a way as to extract the main characteristic features of certain emotions. This was done using Mel-frequency cepstral coefficients, chroma coefficients, as well as the characteristics of the frequency spectrum of audio recordings. In this paper, computer studies of various models of neural networks for emotion recognition are carried out on the example of the data described above. In addition, machine learning algorithms were used for comparative analysis. Thus, the following models were trained during the experiments: logistic regression (LR), classifier based on the support vector machine (SVM), decision tree (DT), random forest (RF), gradient boosting over trees – XGBoost, convolutional neural network CNN, recurrent neural network RNN (ResNet18), as well as an ensemble of convolutional and recurrent networks Stacked CNN-RNN. The results show that neural networks showed much higher accuracy in recognizing and classifying emotions than the machine learning algorithms used. Of the three neural network models presented, the CNN + BLSTM ensemble showed higher accuracy.

scholarly journals Near-Optimal Sparse Neural Trees for Supervised Learning

2021 ◽  
Author(s):  
Tanujit Chakraborty
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Decision Tree ◽  
Classification Tree ◽  
Mathematical Formulation ◽  
Machine Learning Algorithms ◽  
Optimal Decision ◽  
Feed Forward ◽  
Feed Forward Network ◽  
Tree Algorithms

Decision tree algorithms have been among the most popular algorithms for interpretable (transparent) machine learning since the early 1980s. On the other hand, deep learning methods have boosted the capacity of machine learning algorithms and are now being used for non-trivial applications in various applied domains. But training a fully-connected deep feed-forward network by gradient-descent backpropagation is slow and requires arbitrary choices regarding the number of hidden units and layers. In this paper, we propose near-optimal neural regression trees, intending to make it much faster than deep feed-forward networks and for which it is not essential to specify the number of hidden units in the hidden layers of the neural network in advance. The key idea is to construct a decision tree and then simulate the decision tree with a neural network. This work aims to build a mathematical formulation of neural trees and gain the complementary benefits of both sparse optimal decision trees and neural trees. We propose near-optimal sparse neural trees (NSNT) that is shown to be asymptotically consistent and robust in nature. Additionally, the proposed NSNT model obtain a fast rate of convergence which is near-optimal up to some logarithmic factor. We comprehensively benchmark the proposed method on a sample of 80 datasets (40 classification datasets and 40 regression datasets) from the UCI machine learning repository. We establish that the proposed method is likely to outperform the current state-of-the-art methods (random forest, XGBoost, optimal classification tree, and near-optimal nonlinear trees) for the majority of the datasets.

scholarly journals Deep Convolutional Neural Network Feed Forward and Back Prop a gation (DCNN F BP) Algorithm f or Predicting Heart Disease u sing Internet o f Things

2021 ◽  
Vol 11 (1) ◽  
pp. 283-287
Author(s):  
Saranya N ◽  
◽  
Kavi Priya S ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Heart Disease ◽  
Convolutional Neural Network ◽  
Back Propagation ◽  
High Volume ◽  
Deep Convolutional Neural Network ◽  
Machine Learning Algorithms ◽  
Batch Size ◽  
Feed Forward

In recent years, due to the increasing amounts of data gathered from the medical area, the Internet of Things are majorly developed. But the data gathered are of high volume, velocity, and variety. In the proposed work the heart disease is predicted using wearable devices. To analyze the data efficiently and effectively, Deep Canonical Neural Network Feed-Forward and Back Propagation (DCNN-FBP) algorithm is used. The data are gathered from wearable gadgets and preprocessed by employing normalization. The processed features are analyzed using a deep convolutional neural network. The DCNN-FBP algorithm is exercised by applying forward and backward propagation algorithm. Batch size, epochs, learning rate, activation function, and optimizer are the parameters used in DCNN-FBP. The datasets are taken from the UCI machine learning repository. The performance measures such as accuracy, specificity, sensitivity, and precision are used to validate the performance. From the results, the model attains 89% accuracy. Finally, the outcomes are juxtaposed with the traditional machine learning algorithms to illustrate that the DCNN-FBP model attained higher accuracy.

Development of Failure Prediction Models for Subsea Blowout Preventers Using Data Analytics and AI

2021 ◽  
Author(s):  
Rodrigo Chamusca Machado ◽  
Fabbio Leite ◽  
Cristiano Xavier ◽  
Alberto Albuquerque ◽  
Samuel Lima ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Data Analytics ◽  
Historical Data ◽  
Learning Algorithms ◽  
Failure Prediction ◽  
Machine Learning Algorithms ◽  
Time Data ◽  
Real Time Data ◽  
Operational Data

Objectives/Scope This paper presents how a brazilian Drilling Contractor and a startup built a partnership to optimize the maintenance window of subsea blowout preventers (BOPs) using condition-based maintenance (CBM). It showcases examples of insights about the operational conditions of its components, which were obtained by applying machine learning techniques in real time and historic, structured or unstructured, data. Methods, Procedures, Process From unstructured and structured historical data, which are generated daily from BOP operations, a knowledge bank was built and used to develop normal functioning models. This has been possible even without real-time data, as it has been tested with large sets of operational data collected from event log text files. Software retrieves the data from Event Loggers and creates structured database, comprising analog variables, warnings, alarms and system information. Using machine learning algorithms, the historical data is then used to develop normal behavior modeling for the target components. Thereby, it is possible to use the event logger or real time data to identify abnormal operation moments and detect failure patterns. Critical situations are immediately transmitted to the RTOC (Real-time Operations Center) and management team, while less critical alerts are recorded in the system for further investigation. Results, Observations, Conclusions During the implementation period, Drilling Contractor was able to identify a BOP failure using the detection algorithms and used 100% of the information generated by the system and reports to efficiently plan for equipment maintenance. The system has also been intensively used for incident investigation, helping to identify root causes through data analytics and retro-feeding the machine learning algorithms for future automated failure predictions. This development is expected to significantly reduce the risk of BOP retrieval during the operation for corrective maintenance, increased staff efficiency in maintenance activities, reducing the risk of downtime and improving the scope of maintenance during operational windows, and finally reduction in the cost of spare parts replacementduring maintenance without impact on operational safety. Novel/Additive Information For the near future, the plan is to integrate the system with the Computerized Maintenance Management System (CMMS), checking for historical maintenance, overdue maintenance, certifications, at the same place and time that we are getting real-time operational data and insights. Using real-time data as input, we expect to expand the failure prediction application for other BOP parts (such as regulators, shuttle valves, SPMs (Submounted Plate valves), etc) and increase the applicability for other critical equipment on the rig.

Sign in / Sign up

Export Citation Format

Share Document