Find research datasets worth reusing

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 1. Methodology used in the research by (Egmont-Petersen et al., 2002)

Figure 1 shows the methodology used by Egmont-Petersen et al. (2002) to come up with an answer to their research question. Their study says that image recognition using neural networks goes through the stages shown in Figure 1. In our research we shall use this general proposed approach.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 10. Training Neural Network for Images

The dataset of the real images is also treated the same way as the dataset of the sketches. Total tree images used = 86 Total car images used = 54 Learning rate = 0.3 Momentum = 0.2 Number of epochs = 500 70% of data is used to train the neural network and the remaining 30% is used for testing the trained neural network. Figure 10 shows the neural network for images.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 2. The used approach

In this section we present in details the methodology used for this research. Figure 2 depicts the used methodology. The adopted approach is based on first training the system to be able to recognize certain sketches by providing it with various hand-drawn examples such as trees, cars and mountains. Secondly, the system has to be trained again to recognize real images by providing it with real images such as trees, cars and mountains.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 7. Cropping image

This function takes five parameters, a WriteableBitmap type of object, the location of the starting point on x coordinate, the location of the starting point on y coordinate, width and height. It crops the image according to these parameters as shown in Figure 7.

BRAIN Journal-Image Finder Mobile Application Based on Neural Networks-Figure 9. Weka Results for Sketches

the sketches and the data is converted to 20x20=400 integer numbers to give it as input to Weka. Our experimentation includes only two objects for recognition i.e. trees and cars. Total tree sketches used = 175 Total car sketches used = 72 Learning rate = 0.3 Momentum = 0.2 Number of epochs = 500 70% of data is used to train the neural network and the remaining 30% is used for testing the trained neural network. Figure 8 shows the neural network for sketches. The results are shown in Figure 9 and are as follows: Total Correct Recognition = 100%

opencc-by-4.0Jul 2017View details →

BRAIN Journal-About the Design of QUIC Firefox Transport Protocol-Figure 3. An example of a network switch

Seamless network transition: While switching networks, QUIC can adapt to a network or a subnet switch (illustrated in Figure 3). This means that if the IP address of the device is changed, then the QUIC connection is not broken or lost. Unlike the TCP protocol where the connection is defined by the IP address and a port number, QUIC connections are defined by a connection ID. Whenever a network switch occurs, QUIC detects it and sends a piggybacked notification to the other party by indicating the new IP address and connection ID. In this way, the communication can resume normally. In contrast, TCP a new connection has to be established.

opencc-by-4.0Feb 2018View details →

Pore network modeling data for Fontainebleau and Berea Sandstones

This data set contains results from pore network modeling of one sample of dry Fontainebleau sandstone (Case 1), and two samples of Berea sandstones (dry, Case 2, oil and water saturated, case 3). For each sample, there are two .csv file. One file containing information about pockets (pores) and the other containing information about throats. The content of each column is described in the heading of the files.

opencc-by-4.0Mar 2018View details →

Dataset for "Resonance with subthreshold oscillatory drive organizes activity and optimizes learning in neural networks"

This is the experimental dataset for the paper "Resonance with subthreshold oscillatory drive organizes activity and optimizes learning in neural networks", doi/10.1073/pnas.1716933115.

opencc-by-4.0Mar 2018View details →

Internet AS-Graph Edgelist for Network Analysis

This edgelist serves network analyses.

Dataset for: IoT deployment for city scale air quality monitoring with Low-Power Wide Area Networks

Air Quality (AQ) is a very topical issue for many cities and has a direct impact on the health of its citizens. We propose to investigate the air quality of a large UK city using low-cost commodity Particulate Matter (PM) sensors, and compare them with government operated air quality stations. In this  pilot deployment we design and build six AQ IoT devices, each with four different  low-cost PM sensors and deploy them at two locations within the city. These devices are equipped with LoRaWAN wireless network transceivers to test city scale Low-Power Wide-Area Network network coverage. We conclude that some low-cost PM sensors are viable for monitoring AQ and demonstrate that our device design can be used via LoRaWAN to facilitate more granular city coverage without limitations of network access. Based on these findings we intend to deploy a larger LoRaWAN enabled Air Quality sensor network deployment across the city.

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 5. An example of a convolutional layer (Convolutional Neural Networks (LeNet), 2018)

Figure 5 shows an example of a convolutional layer. Layer m-1 includes four feature maps. The m is a hidden layer and it includes two feature maps such as h0 and h1. The neuron outputs at h0 and h1 are calculated from the neuron outputs entering the 2x2 receiving area at the layer below layer m-1. Thus, the weights are W0, and W1 and h,0 and h1 are weight tensors that have three dimensions. The leading dimension indexes the map entries summaries, pointing to the other two neuron outputs. To combine all of them Wijkl , with each pixel of the layer's minus k map, it refers to the weight of the link between neuron outputs (i, j) in the coordinates of the feature map m-1 (Convolutional Neural Networks (LeNet), 2018).

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 4. a) Sparse Connectivity, b) Shared Weights (Convolutional Neural Networks (LeNet), 2018)

A CNNs are biologically inspired variants of a multilayer perceptron. CNNs establish a built-in local correlation by applying a local link model between the neurons of adjacent layers. As shown in Figure 4a, the inputs of the hidden units in the m-layer are obtained from a subset of the units having the built-in areas in the m-1 layer. This ensures that a number of layers arrive consecutively, resulting in a filtration. It can encode 5 features such as a neuron in the m+1 hidden layer. On CNNs, each filter hi is repeated on the entire image surface. These repeated units form a feature map that shares the weight and bias parameters. 3 hidden units of the same feature map are shown in Figure 4b. The weights shown by parallel lines in the figure were also limited as same. To learn such shared parameters, the gradient method can be used with only a small modification to the original parameters. The sum of the inverse gradients of the shared parameters equals the gradient of the shared weights.

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 2. PCGs for sample sound file of 103-1305031931979-B

Heart sounds that provide valuable diagnostic information in clinical examinations are among the most important physiological signals in the human body. However, heart sounds include noise, such as external sounds and lung sounds, caused by signal recording conditions. Noisy heart sound signal negatively affects the diagnosis of the doctor (Denga & Hanb, 2018). Digital filters are often used to filter biomedical signal. Digital filtering is defined as the acquisition of desired frequency values according to the characterization of the desired filter in order to improve the signal according to the intended use (Shenoi, 2005; Thede, 1995). Based on the experience gained from previous studies, an elliptic filter was used in this study (Deperlioglu, 2018; Guraksin et. al., 2009) . The heart sound signal covering the first two steps is given in Figure 2 for sample sound file of 103_1305031931979_B in the PASCAL Btraining data set.

Stable Modeling on Resource Usage Parameters of MapReduce Application-Department of Networked Systems and Services, Budapest University of Technology and Economics, Budapest, Hungary

In Figure 5, the positive dependency of different strength between each resource usage parameter and the corresponding previous usage parameter is exhibited for all MapReduce applications. It indicates that all current resource usage parameters are positively dependent on the previous values to some extent degree. Except for these common dependencies, there exist some special dependencies for different applications. On the top-left panel of Figure 5, CPU usage of Pi application shows the strongest positive dependency to lagged CPU usage, the Teragen application had the weakest positive dependency, and others exhibit the moderate positive dependency.

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 1. Block diagram of classification process

Heart and vascular diseases are the first cause of death in the world. The heartbeat, which is the result of the blood pumping of the heart, gives information about the functioning of the heart valves. Thus, features can be obtained that can differentiate between normal and abnormal heart sound signals. With the ECG signal, it is possible to visualize the parts of the heartbeat signal. However, ECG measurement is usually expensive and requires extra time. For this reason, studies for the detection of heart diseases generally focus on the analysis of heart sounds. In this context, it is aimed to make a successful classification using deep learning method in this study. The block diagram of the application is shown in Figure 1. The details of each block in the diagram are explained as follows. For all classification study, MATLAB r2017a software was used.

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 6. Confusion matrix of multilayer feedforward network

Multilayer feedforward network was used for classification with ANN. In this application, the ANN structure and parameters were obtained after a review of previous studies and very much number of trial runs. There is a total of 10 neurons in the hidden layer in ANN. The Bayesian regularization backpropagation was used for learning algorithm and the mean square error function was also used the performance algorithm. 134 samples in the data set were used for training data, 29 samples were used for validation data, and 29 samples were used for testing data. The confusion matrix obtained at the end of the classification was given in Figure 6. As seen from the confusion matrix, the accuracy of classification 82.8% was achieved in the ANN classification. The ANN performed with a sensitivity of 92.40% and a specificity of 88.82%.

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 3. Multilayer feed forward network (Gurney, 2004)

Feedforward network is a non-repeating network with the processing units or nodes in the layer, and all nodes in a layer are linked to the nodes of the previous layers. There are different weights on the connection. There is no feedback loop, the signal input can only flow in one direction. Multilayer feedforward network is feedforward ANN concept with multiple weighted layers as seen figure 3. This network is called hidden layers because it has one or more hidden layers between the input and output layers (Gurney, 2004; Tutorials Point, 2017).

Classification of Phonocardiograms with Convolutional Neural Networks-Figure 7. Confusion matrix of convolutional neural network

The final layer of CNN is the classification layer. This layer uses the possibilities returned by the softmax activation function for each input to mutually assign one of the special classes. The confusion matrix obtained at the end of the classification was given in Figure 7. As seen from the confusion matrix, the accuracy of classification 97.9% was achieved in the CNN classification. The CNN performed with sensitivity of 99.47% and specificity of 98.42%.

A Facial Motion Capture System Based on Neural Network Classifier Using RGB-D Data-Figure 11. Accuracy of different method for unseen faces

Table 3 shows the mode detection accuracy of the proposed method and its combination with two other methods (uniform LBP and circular LBP) for different people. The overall accuracy of the proposed procedure is calculated as this way one video is chosen as input, and after mode detection the three aforementioned steps are applied on this video. The obtained feature vectors are given to the neural network and the corresponding labels to each frame are regarded as output. Afterwards, the overall accuracy is calculated from the confusion matrix. However, it should be noted that the expression detection criteria are the observation of a certain number of subsequent similar labels and in the case of observing a limited or sparse number of different labels the final label would not change. Figure 10 and 11 show result of different methods for seen and unseen data respectively. Table 4 shows results for seen data with proposed method and uniform LBP.

A Facial Motion Capture System Based on Neural Network Classifier Using RGB-D Data-