Context-Aware Winter Sports Based on Multivariate Sequence Learning

In this paper, we present an intelligent system that is capable of estimating the status of a player engaging in winter activities based on the sequence analysis of multivariate time-series sensor signals. Among the winter activities, this paper mainly focuses on downhill winter sports such as alpine skiing and snowboarding. Assuming that the mechanical vibrations generated by physical interaction between the ground surface and ski/snowboard in motion can describe the ground conditions and playing contexts, we utilize inertial and vibration signals to categorize the motion context. For example, the proposed system estimates whether the player is sitting on a ski lift or standing on the escalator, or skiing on wet or snowy ground, etc. To measure the movement of a player during a game or on the move, we develop a custom embedded system comprising a motion sensor and piezo transducer. The captured multivariate sequence signals are then trained in a supervised fashion. We adopt artificial neural network approaches (e.g., 1D convolutional neural network, and gated recurrent neural networks, such as long short-term memory and gated recurrent units). The experimental results validate the feasibility of the proposed approach.

Download Full-text

Forex exchange rate forecasting using deep recurrent neural networks

Digital Finance ◽

10.1007/s42521-020-00019-x ◽

2020 ◽

Vol 2 (1-2) ◽

pp. 69-96 ◽

Cited By ~ 1

Author(s):

Alexander Jakob Dautel ◽

Wolfgang Karl Härdle ◽

Stefan Lessmann ◽

Hsin-Vonn Seow

Keyword(s):

Neural Network ◽

Deep Learning ◽

Exchange Rate ◽

Language Processing ◽

Short Term Memory ◽

Recurrent Network ◽

Network Architectures ◽

Exchange Rate Forecasting ◽

Trading Model ◽

Gated Recurrent Units

Abstract Deep learning has substantially advanced the state of the art in computer vision, natural language processing, and other fields. The paper examines the potential of deep learning for exchange rate forecasting. We systematically compare long short-term memory networks and gated recurrent units to traditional recurrent network architectures as well as feedforward networks in terms of their directional forecasting accuracy and the profitability of trading model predictions. Empirical results indicate the suitability of deep networks for exchange rate forecasting in general but also evidence the difficulty of implementing and tuning corresponding architectures. Especially with regard to trading profit, a simpler neural network may perform as well as if not better than a more complex deep neural network.

Download Full-text

Crop Yield Estimation Using Deep Learning Based on Climate Big Data and Irrigation Scheduling

Energies ◽

10.3390/en14113004 ◽

2021 ◽

Vol 14 (11) ◽

pp. 3004

Author(s):

Khadijeh Alibabaei ◽

Pedro D. Gaspar ◽

Tânia M. Lima

Keyword(s):

Neural Network ◽

Deep Learning ◽

Energy Consumption ◽

Short Term Memory ◽

Irrigation Scheduling ◽

Climate Data ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Gated Recurrent Units

Deep learning has already been successfully used in the development of decision support systems in various domains. Therefore, there is an incentive to apply it in other important domains such as agriculture. Fertilizers, electricity, chemicals, human labor, and water are the components of total energy consumption in agriculture. Yield estimates are critical for food security, crop management, irrigation scheduling, and estimating labor requirements for harvesting and storage. Therefore, estimating product yield can reduce energy consumption. Two deep learning models, Long Short-Term Memory and Gated Recurrent Units, have been developed for the analysis of time-series data such as agricultural datasets. In this paper, the capabilities of these models and their extensions, called Bidirectional Long Short-Term Memory and Bidirectional Gated Recurrent Units, to predict end-of-season yields are investigated. The models use historical data, including climate data, irrigation scheduling, and soil water content, to estimate end-of-season yield. The application of this technique was tested for tomato and potato yields at a site in Portugal. The Bidirectional Long Short-Term memory outperformed the Gated Recurrent Units network, the Long Short-Term Memory, and the Bidirectional Gated Recurrent Units network on the validation dataset. The model was able to capture the nonlinear relationship between irrigation amount, climate data, and soil water content and predict yield with an MSE of 0.017 to 0.039. The performance of the Bidirectional Long Short-Term Memory in the test was compared with the most commonly used deep learning method, the Convolutional Neural Network, and machine learning methods including a Multi-Layer Perceptrons model and Random Forest Regression. The Bidirectional Long Short-Term Memory outperformed the other models with an R2 score between 0.97 and 0.99. The results show that analyzing agricultural data with the Long Short-Term Memory model improves the performance of the model in terms of accuracy. The Convolutional Neural Network model achieved the second-best performance. Therefore, the deep learning model has a remarkable ability to predict the yield at the end of the season.

Download Full-text

Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting

Electronics ◽

10.3390/electronics8080876 ◽

2019 ◽

Vol 8 (8) ◽

pp. 876 ◽

Cited By ~ 17

Author(s):

Renzhuo Wan ◽

Shuping Mei ◽

Jun Wang ◽

Min Liu ◽

Fan Yang

Keyword(s):

Neural Network ◽

Time Series ◽

Prediction Accuracy ◽

Time Series Data ◽

Short Term Memory ◽

Time Series Prediction ◽

Multivariate Time Series ◽

Series Data ◽

Asymmetric Structure ◽

Convolutional Network

Multivariable time series prediction has been widely studied in power energy, aerology, meteorology, finance, transportation, etc. Traditional modeling methods have complex patterns and are inefficient to capture long-term multivariate dependencies of data for desired forecasting accuracy. To address such concerns, various deep learning models based on Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) methods are proposed. To improve the prediction accuracy and minimize the multivariate time series data dependence for aperiodic data, in this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model. In this model, multi-variable time series prediction is constructed as a sequence-to-sequence scenario for non-periodic datasets. The multichannel residual blocks in parallel with asymmetric structure based on deep convolution neural network is proposed. The results are compared with rich competitive algorithms of long short term memory (LSTM), convolutional LSTM (ConvLSTM), Temporal Convolution Network (TCN) and Multivariate Attention LSTM-FCN (MALSTM-FCN), which indicate significant improvement of prediction accuracy, robust and generalization of our model.

Download Full-text

Neuroevolution of a Modular Memory-Augmented Neural Network for Deep Memory Problems

Evolutionary Computation ◽

10.1162/evco_a_00239 ◽

2019 ◽

Vol 27 (4) ◽

pp. 639-664 ◽

Cited By ~ 2

Author(s):

Shauharda Khadka ◽

Jen Jen Chung ◽

Kagan Tumer

Keyword(s):

Neural Network ◽

Gradient Descent ◽

Short Term Memory ◽

Extended Period ◽

New Class ◽

Neural Architecture ◽

Memory Block ◽

Memory Problems ◽

Long Short Term Memory ◽

Gated Recurrent Units

We present Modular Memory Units (MMUs), a new class of memory-augmented neural network. MMU builds on the gated neural architecture of Gated Recurrent Units (GRUs) and Long Short Term Memory (LSTMs), to incorporate an external memory block, similar to a Neural Turing Machine (NTM). MMU interacts with the memory block using independent read and write gates that serve to decouple the memory from the central feedforward operation. This allows for regimented memory access and update, giving our network the ability to choose when to read from memory, update it, or simply ignore it. This capacity to act in detachment allows the network to shield the memory from noise and other distractions, while simultaneously using it to effectively retain and propagate information over an extended period of time. We train MMU using both neuroevolution and gradient descent, and perform experiments on two deep memory benchmarks. Results demonstrate that MMU performs significantly faster and more accurately than traditional LSTM-based methods, and is robust to dramatic increases in the sequence depth of these memory benchmarks.

Download Full-text

Cloud Enabled Neural Network with Intelligent Sensor nodes for HVAC

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.b7890.129219 ◽

2019 ◽

Vol 9 (2) ◽

pp. 3613-3616

Keyword(s):

Neural Network ◽

Embedded System ◽

Indoor Air ◽

Indoor Air Pollution ◽

Sensor Nodes ◽

Intelligent Sensor ◽

Environment Quality ◽

Processing Power ◽

The Status ◽

Embedded Electronics

HVAC (Heating, Ventilation and Air Conditioning) is the technology of indoor and vehicular environmental comfort and to control these systems. The status of building energy consumption is increasingly prominent. Indoor air pollution is 10times danger than outdoor due to incorrect functionality of heating, ventilation, and air condition system. For indoor environment quality, a novel real-time method for HVAC system operation is developed. Internet of things is used to monitor the indoor air quality by using embedded electronics, software and sensors and connectivity. This project aims to integrate air condition, ventilation and protected system on a single embedded system that alerts early warning for the unpredictable dangers. The wireless sensor nodes have limited processing power and memory. In order to embed intelligence into sensor nodes, a hybrid algorithm is proposed containing RNN (Random Neural Network) and LNP (Linear Non-linear Poisson) cascade model.

Download Full-text

The Use of Fuzzy Logic for Online Monitoring of Manufacturing Machine: An Intelligent System

Circulation in Computer Science ◽

10.22632/ccs-2017-252-61 ◽

2017 ◽

Vol 2 (11) ◽

pp. 31-39 ◽

Cited By ~ 3

Author(s):

Ashner Gerald P. Novilla ◽

August Anthony N. Balute ◽

Dennis B. Gonzales

Keyword(s):

Fuzzy Logic ◽

Embedded System ◽

Monitoring System ◽

Intelligent System ◽

Human Labor ◽

The Status ◽

Fuzzy Logic Approach ◽

Iot Devices ◽

Mean Time ◽

Manufacturing Machine

Internet of Things (IoT) has positioned itself at the front of rapid technological advancements in order to lessen human labor. The concept of making the world smart arises from the basis that “things” can be connected using the Internet. In this paper, the researchers will be describing an effective implementation of an intelligent monitoring system for manufacturing machine unit which is used in industry environment. The propose system design can be installed in manufacturing machines in order to solve management problems, maintenance, shortens the mean time to repair and predict mean time to fail. The researchers have designed a system based on internet of thing for monitoring using the fuzzy logic approach. It consists of monitoring the normal activities of the manufacturing machines in order to build a reference of its condition; then a real-time monitoring and analysis of gathered data from the sensors is accomplished. The status is carried out using a Fuzzy Logic based network. It will give the users the current activity of the manufacturing machine and will also provide information about health status. This system had been incorporated through internet using host, network, Ethernet module, embedded system gateway, sensors, microcontroller unit (MCU) and other components. This paper discusses how monitoring system can be implemented and how the use of cloud computing technology along with IoT devices can be used so that the data collected by these devices can be safely stored, monitored and analyzed.

Download Full-text

Research on Bearing Fault Diagnosis Method Based on Filter Features of MOMLMEDA and LSTM

Entropy ◽

10.3390/e21101025 ◽

2019 ◽

Vol 21 (10) ◽

pp. 1025

Author(s):

Yong Li ◽

Gang Cheng ◽

Xihui Chen ◽

Yusong Pang

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Short Term Memory ◽

Recognition Rate ◽

Selection Criterion ◽

Minimum Entropy ◽

Efficient Operation ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

The Status

As the supporting unit of rotating machinery, bearing can ensure efficient operation of the equipment. Therefore, it is very important to monitor the status of bearings accurately. A bearing fault diagnosis mothed based on Multipoint Optimal Minimum Local Mean Entropy Deconvolution Adjusted (MOMLMEDA) and Long Short-Term Memory (LSTM) is proposed. MOMLMEDA is an improved algorithm based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA). By setting the local kurtosis mean as a new selection criterion, it can effectively avoid the interference of false kurtosis caused by noise and improve the accuracy of optimal kurtosis position. The optimal filter designed by optimal kurtosis position has periodic and amplitude characteristics, which are used as the fault feature in this paper. However, this feature has temporal characteristics and cannot be used as input of general neural network directly. LSTM is selected as the classification network in this paper. It can effectively avoid the influence of the temporal problem existing in feature vectors. Accurate diagnosis of bearing faults is realized by training classification neural network with samples. The overall recognition rate is up to 93.50%.

Download Full-text

Recurrent Convolutional Neural Networks for Large Scale Bird Species Classification

10.21203/rs.3.rs-275942/v1 ◽

2021 ◽

Author(s):

Gaurav Gupta ◽

Meghana Kshirsagar ◽

Ming Zhong ◽

Shahrzad Gholami ◽

Juan Lavista Ferres

Keyword(s):

Neural Network ◽

Large Scale ◽

Short Term Memory ◽

Bird Species ◽

Species Classification ◽

Average Accuracy ◽

Audio Recordings ◽

Gated Recurrent Units ◽

Channel Patterns ◽

Memory Channel

Abstract We present a deep learning approach towards the large-scale prediction and analysis of bird acoustics from 100 different bird species. We use spectrograms constructed on bird audio recordings from the Cornell Bird Challenge (CBC) dataset, which includes recordings with background noise, of multiple and potentially overlapping bird vocalizations per audio. Our experiments show that a hybrid modeling approach that involves a Convolutional Neural Network (CNN) for learning the representation for a slice of the spectrogram and a Recurrent Neural Network (RNN) for the temporal component to combine across time-points leads to the most accurate model on this dataset. We show results on a spectrum of models ranging from stand-alone CNNs to hybrid models of various types obtained by combining CNNs with CNNs or RNNs of the following types: Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU) and Legendre Memory Units (LMU). The best performing model achieves an average accuracy of 67% over the 100 different bird species, with the highest accuracy of 90% for the Red crossbill. We further analyze the learned representations visually and find them to be intuitive, where we find that related bird species are clustered close together. We present a novel way to empirically interpret the representations learned by the LMU-based hybrid model which shows how memory channel patterns over time change with spectrograms.

Download Full-text

SACNN: Self-attentive Convolutional Neural Network Model for Natural Language Inference

ACM Transactions on Asian and Low-Resource Language Information Processing ◽

10.1145/3426884 ◽

2021 ◽

Vol 20 (3) ◽

pp. 1-16

Author(s):

Waris Quamer ◽

Praphula Kumar Jain ◽

Arpit Rai ◽

Vijayalakshmi Saravanan ◽

Rajendra Pamula ◽

...

Keyword(s):

Neural Network ◽

Natural Language ◽

Short Term Memory ◽

Local Context ◽

Short Term ◽

Proposed Model ◽

Long Short Term Memory ◽

Complex Relationships ◽

Gated Recurrent Units

Inference has been central problem for understanding and reasoning in artificial intelligence. Especially, Natural Language Inference is an interesting problem that has attracted the attention of many researchers. Natural language inference intends to predict whether a hypothesis sentence can be inferred from the premise sentence. Most prior works rely on a simplistic association between the premise and hypothesis sentence pairs, which is not sufficient for learning complex relationships between them. The strategy also fails to exploit local context information fully. Long Short Term Memory (LSTM) or gated recurrent units networks (GRU) are not effective in modeling long-term dependencies, and their schemes are far more complex as compared to Convolutional Neural Networks (CNN). To address this problem of long-term dependency, and to involve context for modeling better representation of a sentence, in this article, a general Self-Attentive Convolution Neural Network (SACNN) is presented for natural language inference and sentence pair modeling tasks. The proposed model uses CNNs to integrate mutual interactions between sentences, and each sentence with their counterparts is taken into consideration for the formulation of their representation. Moreover, the self-attention mechanism helps fully exploit the context semantics and long-term dependencies within a sentence. Experimental results proved that SACNN was able to outperform strong baselines and achieved an accuracy of 89.7% on the stanford natural language inference (SNLI) dataset.

Download Full-text

Comparing recurrent convolutional neural networks for large scale bird species classification

Scientific Reports ◽

10.1038/s41598-021-96446-w ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Gaurav Gupta ◽

Meghana Kshirsagar ◽

Ming Zhong ◽

Shahrzad Gholami ◽

Juan Lavista Ferres

Keyword(s):

Neural Network ◽

Large Scale ◽

Short Term Memory ◽

Bird Species ◽

Species Classification ◽

Average Accuracy ◽

Audio Recordings ◽

Gated Recurrent Units ◽

Channel Patterns ◽

Memory Channel

AbstractWe present a deep learning approach towards the large-scale prediction and analysis of bird acoustics from 100 different bird species. We use spectrograms constructed on bird audio recordings from the Cornell Bird Challenge (CBC)2020 dataset, which includes recordings of multiple and potentially overlapping bird vocalizations with background noise. Our experiments show that a hybrid modeling approach that involves a Convolutional Neural Network (CNN) for learning the representation for a slice of the spectrogram, and a Recurrent Neural Network (RNN) for the temporal component to combine across time-points leads to the most accurate model on this dataset. We show results on a spectrum of models ranging from stand-alone CNNs to hybrid models of various types obtained by combining CNNs with other CNNs or RNNs of the following types: Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU), and Legendre Memory Units (LMU). The best performing model achieves an average accuracy of 67% over the 100 different bird species, with the highest accuracy of 90% for the bird species, Red crossbill. We further analyze the learned representations visually and find them to be intuitive, where we find that related bird species are clustered close together. We present a novel way to empirically interpret the representations learned by the LMU-based hybrid model which shows how memory channel patterns change over time with the changes seen in the spectrograms.

Download Full-text