scholarly journals Learning Dynamic Factors to Improve the Accuracy of Bus Arrival Time Prediction via a Recurrent Neural Network

2019 ◽  
Vol 11 (12) ◽  
pp. 247
Author(s):  
Xin Zhou ◽  
Peixin Dong ◽  
Jianping Xing ◽  
Peijia Sun
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Public Transportation ◽  
Prediction Accuracy ◽  
Arrival Time ◽  
Attention Mechanism ◽  
Experimental Results ◽  
Support Vector ◽  
Data Set ◽  
Dynamic Factors

Accurate prediction of bus arrival times is a challenging problem in the public transportation field. Previous studies have shown that to improve prediction accuracy, more heterogeneous measurements provide better results. So what other factors should be added into the prediction model? Traditional prediction methods mainly use the arrival time and the distance between stations, but do not make full use of dynamic factors such as passenger number, dwell time, bus driving efficiency, etc. We propose a novel approach that takes full advantage of dynamic factors. Our approach is based on a Recurrent Neural Network (RNN). The experimental results indicate that a variety of prediction algorithms (such as Support Vector Machine, Kalman filter, Multilayer Perceptron, and RNN) have significantly improved performance after using dynamic factors. Further, we introduce RNN with an attention mechanism to adaptively select the most relevant input factors. Experiments demonstrate that the prediction accuracy of RNN with an attention mechanism is better than RNN with no attention mechanism when there are heterogeneous input factors. The experimental results show the superior performances of our approach on the data set provided by Jinan Public Transportation Corporation.

scholarly journals Exploiting the Relationship between Pruning Ratio and Compression Effect for Neural Network Model Based on TensorFlow

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Bo Liu ◽  
Qilin Wu ◽  
Yiwen Zhang ◽  
Qian Cao
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Prediction Accuracy ◽  
Computing Time ◽  
Experimental Results ◽  
Data Set ◽  
Compression Effect ◽  
Model Based ◽  
The Relationship

Pruning is a method of compressing the size of a neural network model, which affects the accuracy and computing time when the model makes a prediction. In this paper, the hypothesis that the pruning proportion is positively correlated with the compression scale of the model but not with the prediction accuracy and calculation time is put forward. For testing the hypothesis, a group of experiments are designed, and MNIST is used as the data set to train a neural network model based on TensorFlow. Based on this model, pruning experiments are carried out to investigate the relationship between pruning proportion and compression effect. For comparison, six different pruning proportions are set, and the experimental results confirm the above hypothesis.

scholarly journals Improvement of Short-Term BIPV Power Predictions Using Feature Engineering and a Recurrent Neural Network

Energies ◽  
2019 ◽  
Vol 12 (17) ◽  
pp. 3247 ◽  
Author(s):  
Dongkyu Lee ◽  
Jinhwa Jeong ◽  
Sung Hoon Yoon ◽  
Young Tae Chae
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Recurrent Neural Network ◽  
Power Output ◽  
Prediction Accuracy ◽  
Support Vector ◽  
Feature Engineering ◽  
Short Term ◽  
Interaction Detection ◽  
Photovoltaic Power

The time resolution and prediction accuracy of the power generated by building-integrated photovoltaics are important for managing electricity demand and formulating a strategy to trade power with the grid. This study presents a novel approach to improve short-term hourly photovoltaic power output predictions using feature engineering and machine learning. Feature selection measured the importance score of input features by using a model-based variable importance. It verified that the normative sky index in the weather forecasted data had the least importance as a predictor for hourly prediction of photovoltaic power output. Six different machine-learning algorithms were assessed to select an appropriate model for the hourly power output prediction with onsite weather forecast data. The recurrent neural network outperformed five other models, including artificial neural networks, support vector machines, classification and regression trees, chi-square automatic interaction detection, and random forests, in terms of its ability to predict photovoltaic power output at an hourly and daily resolution for 64 tested days. Feature engineering was then used to apply dropout observation to the normative sky index from the training and prediction process, which improved the hourly prediction performance. In particular, the prediction accuracy for overcast days improved by 20% compared to the original weather dataset used without dropout observation. The results show that feature engineering effectively improves the short-term predictions of photovoltaic power output in buildings with a simple weather forecasting service.

scholarly journals KOMPARASI MODEL SUPPORT VECTOR MACHINES (SVM) DAN NEURAL NETWORK UNTUK MENGETAHUI TINGKAT AKURASI PREDIKSI TERTINGGI HARGA SAHAM

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
R. Hadapiningradja Kusumodestoni ◽  
Sarwido Sarwido
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Stock Prices ◽  
Prediction Accuracy ◽  
High Accuracy ◽  
Stock Index ◽  
Support Vector ◽  
Accuracy Rate ◽  
Trend Prediction ◽  
Data Set

There are many types of investments to make money, one of which is in the form of shares. Shares is a trading company dealing with securities in the global capital markets. Stock Exchange or also called stock market is actually the activities of private companies in the form of buying and selling investments. To avoid losses in investing, we need a model of predictive analysis with high accuracy and supported by data - lots of data and accurately. The correct techniques in the analysis will be able to reduce the risk for investors in investing. There are many models used in the analysis of stock price movement prediction, in this study the researchers used models of neural networks (NN) and a model of support vector machine (SVM). Based on the background of the problems that have been mentioned in the previous description it can be formulated the problem as follows: need an algorithm that can predict stock prices, and need a high accuracy rate by adding a data set on the prediction, two algorithms will be investigated expected results last researchers can deduce where the algorithm accuracy rate predictions are the highest or accurate, then the purpose of this study was to mengkomparasi or compare between the two algorithms are algorithms Neural Network algorithm and Support Vector Machine which later on the end result has an accuracy rate forecast stock prices highest to see the error value RMSEnya. After doing research using the model of neural network and model of support vector machine (SVM) to predict the stock using the data value of the shares on the stock index hongkong dated July 20, 2016 at 16:26 pm until the date of 15 September 2016 at 17:40 pm as many as 729 data sets within an interval of 5 minute through a process of training, learning, and then continue the process of testing so the result is that by using a neural network model of the prediction accuracy of 0.503 +/- 0.009 (micro 503) while using the model of support vector machine (SVM) accuracy of the predictions for 0477 + / - 0.008 (micro: 0477) so that after a comparison can be concluded that the neural network models have trend prediction accuracy higher than the model of support vector machine (SVM).

scholarly journals Music Feature Classification Based on Recurrent Neural Networks with Channel Attention Mechanism

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jie Gan
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Traditional Music ◽  
Attention Mechanism ◽  
Feature Classification ◽  
Data Set ◽  
Hard Drives ◽  
Music Classification ◽  
Online Music ◽  
Convolution Structure

With the advancement of multimedia and digital technologies, music resources are rapidly increasing over the Internet, which changed listeners’ habits from hard drives to online music platforms. It has allowed the researchers to use classification technologies for efficient storage, organization, retrieval, and recommendation of music resources. The traditional music classification methods use many artificially designed acoustic features, which require knowledge in the music field. The features of different classification tasks are often not universal. This paper provides a solution to this problem by proposing a novel recurrent neural network method with a channel attention mechanism for music feature classification. The music classification method based on a convolutional neural network ignores the timing characteristics of the audio itself. Therefore, this paper combines convolution structure with the bidirectional recurrent neural network and uses the attention mechanism to assign different attention weights to the output of the recurrent neural network at different times; the weights are assigned for getting a better representation of the overall characteristics of the music. The classification accuracy of the model on the GTZAN data set has increased to 93.1%. The AUC on the multilabel labeling data set MagnaTagATune has reached 92.3%, surpassing other comparison methods. The labeling of different music labels has been analyzed. This method has good labeling ability for most of the labels of music genres. Also, it has good performance on some labels of musical instruments, singing, and emotion categories.

scholarly journals Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France

2018 ◽  
Vol 10 (8) ◽  
pp. 1217 ◽  
Author(s):  
Emile Ndikumana ◽  
Dinh Ho Tong Minh ◽  
Nicolas Baghdadi ◽  
Dominique Courault ◽  
Laure Hossard
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Land Cover ◽  
Recurrent Neural Network ◽  
Agricultural Land ◽  
Support Vector ◽  
Data Set ◽  
Radar Images ◽  
Deep Recurrent Neural Network ◽  
F Measure

The development and improvement of methods to map agricultural land cover are currently major challenges, especially for radar images. This is due to the speckle noise nature of radar, leading to a less intensive use of radar rather than optical images. The European Space Agency Sentinel-1 constellation, which recently became operational, is a satellite system providing global coverage of Synthetic Aperture Radar (SAR) with a 6-days revisit period at a high spatial resolution of about 20 m. These data are valuable, as they provide spatial information on agricultural crops. The aim of this paper is to provide a better understanding of the capabilities of Sentinel-1 radar images for agricultural land cover mapping through the use of deep learning techniques. The analysis is carried out on multitemporal Sentinel-1 data over an area in Camargue, France. The data set was processed in order to produce an intensity radar data stack from May 2017 to September 2017. We improved this radar time series dataset by exploiting temporal filtering to reduce noise, while retaining as much as possible the fine structures present in the images. We revealed that even with classical machine learning approaches (K nearest neighbors, random forest, and support vector machines), good performance classification could be achieved with F-measure/Accuracy greater than 86% and Kappa coefficient better than 0.82. We found that the results of the two deep recurrent neural network (RNN)-based classifiers clearly outperformed the classical approaches. Finally, our analyses of the Camargue area results show that the same performance was obtained with two different RNN-based classifiers on the Rice class, which is the most dominant crop of this region, with a F-measure metric of 96%. These results thus highlight that in the near future these RNN-based techniques will play an important role in the analysis of remote sensing time series.

scholarly journals Automatic Image Captioning Based on ResNet50 and LSTM with Soft Attention

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Yan Chu ◽  
Xiao Yue ◽  
Lei Yu ◽  
Mikhailov Sergei ◽  
Zhengkui Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Recurrent Neural Network ◽  
Attention Mechanism ◽  
Experimental Results ◽  
Challenging Problem ◽  
Image Captioning ◽  
Training Images ◽  
Fixed Length ◽  
The Given

Captioning the images with proper descriptions automatically has become an interesting and challenging problem. In this paper, we present one joint model AICRL, which is able to conduct the automatic image captioning based on ResNet50 and LSTM with soft attention. AICRL consists of one encoder and one decoder. The encoder adopts ResNet50 based on the convolutional neural network, which creates an extensive representation of the given image by embedding it into a fixed length vector. The decoder is designed with LSTM, a recurrent neural network and a soft attention mechanism, to selectively focus the attention over certain parts of an image to predict the next sentence. We have trained AICRL over a big dataset MS COCO 2014 to maximize the likelihood of the target description sentence given the training images and evaluated it in various metrics like BLEU, METEROR, and CIDEr. Our experimental results indicate that AICRL is effective in generating captions for the images.

scholarly journals DAN: Deep Attention Neural Network for News Recommendation

2019 ◽  
Vol 33 ◽  
pp. 5973-5980 ◽  
Author(s):  
Qiannan Zhu ◽  
Xiaofei Zhou ◽  
Zeliang Song ◽  
Jianlong Tan ◽  
Li Guo
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Real World ◽  
Attention Mechanism ◽  
Experimental Results ◽  
Data Sets ◽  
Challenging Problem ◽  
World News ◽  
Sequential Information ◽  
News Recommendation

With the rapid information explosion of news, making personalized news recommendation for users becomes an increasingly challenging problem. Many existing recommendation methods that regard the recommendation procedure as the static process, have achieved better recommendation performance. However, they usually fail with the dynamic diversity of news and user’s interests, or ignore the importance of sequential information of user’s clicking selection. In this paper, taking full advantages of convolution neural network (CNN), recurrent neural network (RNN) and attention mechanism, we propose a deep attention neural network DAN for news recommendation. Our DAN model presents to use attention-based parallel CNN for aggregating user’s interest features and attention-based RNN for capturing richer hidden sequential features of user’s clicks, and combines these features for new recommendation. We conduct experiment on real-world news data sets, and the experimental results demonstrate the superiority and effectiveness of our proposed DAN model.

scholarly journals An Implicit Preference-Aware Sequential Recommendation Method Based on Knowledge Graph

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Haiyan Wang ◽  
Kaiming Yao ◽  
Jian Luo ◽  
Yi Lin
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Recommendation System ◽  
Attention Mechanism ◽  
Experimental Results ◽  
Knowledge Graph ◽  
Data Overload ◽  
Current Sequence

Sequential recommendation system has received widespread attention due to its good performance in solving data overload. However, most of the sequential recommendation methods assume that user’s preferences only depend on specific items in the current sequence and do not consider user’s implicit interests. In addition, most of the previous works mainly focus on exploiting relationships between items in the sequence and seldom consider quantifying the degree of preferences for items implied by user’s different behaviors. In order to address these above two problems, we propose an implicit preference-aware sequential recommendation method based on knowledge graph (IPAKG). Firstly, this method introduces knowledge graph to exploit user’s implicit preference representations. Secondly, we integrate recurrent neural network and attention mechanism to capture user’s evolving interests and relationships between different items in the sequence. Thirdly, we introduce the concept of behavior intensity and design a behavior activation unit to exploit the degree of preferences for items implied by a user’s different behaviors. Through the activation unit, the user’s preferences on different items are further quantified. Finally, we conduct experiments on an Amazon electronics dataset and Tmall dataset to evaluate the performance of our method. Experimental results demonstrate that our proposed method has better performance than those baseline methods.

scholarly journals Multistep Prediction of Bus Arrival Time with the Recurrent Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Zhi-Ying Xie ◽  
Yuan-Rong He ◽  
Chih-Cheng Chen ◽  
Qing-Quan Li ◽  
Chia-Chun Wu
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Traffic Congestion ◽  
Arrival Time ◽  
Short Term Memory ◽  
Model Simulation ◽  
Accurate Prediction ◽  
Data Set ◽  
Arrival Times ◽  
Public Transport System

Accurate predictions of bus arrival times help passengers arrange their trips easily and flexibly and improve travel efficiency. Thus, it is important to manage and schedule the arrival times of buses for the efficient deployment of buses and to ease traffic congestion, which improves the service quality of the public transport system. However, due to many variables disturbing the scheduled transportation, accurate prediction is challenging. For accurate prediction of the arrival time of a bus, this research adopted a recurrent neural network (RNN). For the prediction, the variables affecting the bus arrival time were investigated from the data set containing the route, a driver, weather, and the schedule. Then, a stacked multilayer RNN model was created with the variables that were categorized into four groups. The RNN model with a separate multi-input and spatiotemporal sequence model was applied to the data of the arrival and leaving times of a bus from all of a Shandong Linyi bus route. The result of the model simulation revealed that the convolutional long short-term memory (ConvLSTM) model showed the highest accuracy among the tested models. The propagation of error and the number of prediction steps influenced the prediction accuracy.

Research on behavior recognition based on feature fusion of automatic coder and recurrent neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Author(s):  
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Behavior Pattern ◽  
Rapid Development ◽  
Video Data ◽  
Support Vector ◽  
Behavior Recognition ◽  
Learning Methods ◽  
The Impact ◽  
Internet Of Things Technology

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

Sign in / Sign up

Export Citation Format

Share Document