NN Method Research Articles

A Semantic Conceptualization Using Tagged Bag-of-Concepts for Sentiment Analysis

Sentiment could be expressed implicitly or explicitly in the text. Hence, it is the main challenge for current sentiment analysis (SA) approaches to identify hidden sentiments, other common challenges include false classification of opinion words, ignoring context information, and bad handling of a short text that arise from the bad interpretation of the text and lack of enough data required for analysis tasks. In this study, a semantic conceptualization method using tagged bag-of-concepts for SA is proposed to detect the correct sentiment towards the actual target entity that considers all affective and conceptual information conveyed in the text with a special focus on the short text. Tagged bag-of-concepts (TBoC) is a novel approach to analyze and decompose text to uncover latent sentiments while preserving all relations and vital information to boost the accuracy of SA. This study answers questions: Does the information provided via TBoC enhance sentiment classification results on different analysis levels? Is building a structure of concepts increases the accuracy of overall sentiment towards specific opinion target? Does TBoC approach enhance SA results for short text messages? The proposed solution has been applied on two datasets from the restaurant domain, sentiment analysis is performed using the TBoCs structure on multiple levels including document, aspect, aspect-category, and topic levels. TBoC method with domain-specific sentiment lexicon showed exceptional performance and outperformed other state-of-the-art NB, SVM, and NN methods, especially for aspect-level SA. The use of TBoC within the semantic conceptualization model that leverages NLP tasks, Ontology, and semantic methods proved its high capabilities for concept extraction while preserving the information about the context, interrelations, and latent feelings.

Invariant moment and learning vector quantization (LVQ NN) for images classification

Image classification need two main components, i.e., features and classifier. The feature commonly used for classification of images with different scale is invariant moment; its value is invariant against the spatial transformation dealing with translation, scale and rotation. The classifier that is widely used for classification is LVQ NN. It is shallow network containing only two layers, the initial value of its weight is more fixed so that its output is more stable and its algorithm is relatively simple thus both training and testing process are run fast. Based on these facts, therefore, this research proposed a combination method of invariant moment and LVQ NN (IM-LVQ). The ability of the proposed method would be compared with two other methods. Firstly, the combination method of invariant moment and Euclidean distance (IM-ED). Secondly, the combination of invariant moment and principal component analysis (IM-PCA). The performance of the three methods was evaluated quantitatively with several metrics, viz.: Confusion Matrix, Accuracy, Precision, True Positive Rate, False Positive Rate, ROC graph and training time. The evaluation of the metrics was based upon the changing (reduction) of the scale/size of training image. The results showed that IM-LVQ method outperformed the other two methods in aforementioned metrics.

Intercomparison of Data-Driven and Learning-Based Interpolations of Along-Track Nadir and Wide-Swath SWOT Altimetry Observations

Over the last few years, a very active field of research has aimed at exploring new data-driven and learning-based methodologies to propose computationally efficient strategies able to benefit from the large amount of observational remote sensing and numerical simulations for the reconstruction, interpolation and prediction of high-resolution derived products of geophysical fields. In this paper, we investigate how they might help to solve for the oversmoothing of the state-of-the-art optimal interpolation (OI) techniques in the reconstruction of sea surface height (SSH) spatio-temporal fields. We focus on two small 10°×10° GULFSTREAM and 8°×10° OSMOSIS regions, part of the North Atlantic basin: the GULFSTREAM area is mainly driven by energetic mesoscale dynamics, while OSMOSIS is less energetic but with more noticeable small spatial patterns. Based on observation system simulation experiments (OSSE), we used a NATL60 high resolution deterministic ocean simulation of the North Atlantic to generate two types of pseudo-altimetric observational dataset: along-track nadir data for the current capabilities of the observation system and wide-swath SWOT data in the context of the upcoming SWOT (Surface Water Ocean Topography) mission. We briefly introduce the analog data assimilation (AnDA), an up-to-date version of the DINEOF algorithm, and a new neural networks-based end-to-end learning framework for the representation of spatio-temporal irregularly-sampled data. The main objective of this paper consists of providing a thorough intercomparison exercise with appropriate benchmarking metrics to assess whether these approaches help to improve the SSH altimetric interpolation problem and to identify which one performs best in this context. We demonstrate how the newly introduced NN method is a significant improvement with a plug-and-play implementation and its ability to catch up the small scales ranging up to 40 km, inaccessible by the conventional methods so far. A clear gain is also demonstrated when assimilating jointly wide-swath SWOT and (aggregated) along-track nadir observations.

Practical Multi-Keyword Ranked Search With Access Control Over Encrypted Cloud Data

With the explosive growth of data volume in the cloud computing environment, data owners are increasingly inclined to store their data on the cloud. Although data outsourcing reduces computation and storage costs for them, it inevitably brings new security and privacy concerns, as the data owners lose direct control of sensitive data. Meanwhile, most of the existing ranked keyword search schemes mainly focus on enriching search efficiency or functionality, but lack of providing efficient access control and formal security analysis simultaneously. To address these limitations, in this article we propose an efficient and privacy-preserving <b>M</b> ulti-keyword <b>R</b> anked <b>S</b> earch scheme with <b>F</b> ine-grained access control (MRSF). MRSF can realize highly accurate ciphertext retrieval by combining coordinate matching with Term Frequency-Inverse Document Frequency (TF-IDF) and improving the secure <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula> NN method. Besides, it can effectively refine users’ search privileges by utilizing the polynomial-based access strategy. Formal security analysis shows that MRSF is secure in terms of confidentiality of outsourced data and the privacy of index and tokens. Extensive experiments further show that, compared with existing schemes, MRSF achieves higher search accuracy and more functionalities efficiently.

EXTRACTION OF SCATTERED SMALL-SCALE LANDSLIDES DISTRIBUTION BY OBJECT-BASED CLASSIFICATION USING OPTICAL HIGH-RESOLUTION SATELLITE IMAGES

Abstract. Continuous heavy rain for a long duration over mountainous terrain, where the elevation is relatively low and the topography is complex leads to multiple small-scale landslides over a wide area. Detailed investigations of small-scale landslides have been effectively carried out using optical high-resolution satellite images with spatial resolution of about 2 m or less. In this study, the sediment-related disaster caused by heavy rain in northern Kyushu, Japan that occurred in July 2017 was selected as a typical example of small-scale landslide. For this landslide event, the applicability of the conventional superpixel segmentation for landslide separation was examined. The applicability of the representative SLIC and SLICO methods in the superpixel segmentation method by image interpretation in the case of a large number of small-scale landslides in a wide area was assessed. These results suggest that in the case of such a disaster, segmentation by the SLICO method will be better. In addition, the set value of the area size for the area division was systematically examined from the distribution tendency of the average NDVI value in the divided area. It was shown that the landslide region can be extracted with relatively high accuracy by the land cover classification process by the NN method by using the appropriate region size examined by the SLICO method.

Distributed Reflectometry for Soft Fault Identification in Wired Networks Using Neural Network and Genetic Algorithm

Based on the Multi-Carrier Time Domain Reflectometry (MCTDR) technique, new methods which could detect, locate and characterize multiple soft faults in complex wired networks are proposed in this paper. The first method combines the MCTDR with the Multi-Layer Perceptron Neural Network (MLP-NN), the second one combines the MCTDR with the well-known genetic algorithm (GA). Furthermore, in order to allow effective monitoring without ambiguity, a branched network is diagnosed by several reflectometers (sensors) at the different extremities. The main novelty here lies in the fact that the NN and GA methods are used for data fusion from several distributed reflectometers. The needed datasets for training and testing the NN are generated by simulation using MCTDR responses. These are obtained using a numerical direct model which describes the signal propagation in the branched network. The GA is used to reduce the differences between the measured responses and the simulated responses given by the direct model. The numerical and experimental results provided at the end of the paper confirm the performance of both approaches (MCTDR-NN & MCTDR-GA) in merging data between reflectometers and in eliminating diagnosis ambiguities.

Reducing error in small-area estimates of multi-source forest inventory by multi-temporal data fusion

Abstract Since the 1990s, forest resource maps and forest variable estimates for small areas have been produced by combining national forest inventory (NFI) field plot data, optical satellite images and numerical map data. A non-parametric $k$-NN method has frequently been employed. In Finland, such multi-source NFI (MS-NFI) forest variable estimates for municipalities have been produced eight times. A relatively large variation has been observed between subsequent estimates. In this study, a large-scale evaluation of small-area estimates from an MS-NFI conducted in 2013 was carried out in comparison with pure NFI field data-based estimates and error estimates. The proportion of municipalities with significant differences was larger than expected, e.g. over 10% for the mean volume, which indicates systematic error in the small-area estimates. A multi-temporal data fusion combining MS-NFI estimators from three time points—2011, 2013 and 2015—was tested as a means to improve single time point MS-NFI estimates of the mean volumes of growing stock and of tree species groups. A generalized least squares (GLS) technique and unweighted averaging were tested. The improvement was small but consistent when validated against the NFI field data-based estimates for the municipalities. The unweighted averaging worked nearly as well as a GLS estimator.

A Neural Network-Based Adaptive Backstepping Control Law With Covariance Resetting for Asymptotic Output Tracking of a CSTR Plant

A robust nonlinear adaptive controller merging a backstepping approach with neural networks is proposed for a nonlinear non-affine model. The work presented here is evaluated on a complex uncertain model of a continuous stirred tank reactor plant including an unknown varying parameter that enters the complexity model. By exploiting NN and adaptive backstepping approximation methods, an equivalent adaptive NN controller is constructed to achieve robust asymptotic output tracking control. The robustness to uncertainties as well as the lack of informative process data is the main enhancement of this work. This is attained through the implementation of the covariance resetting algorithm in the least square estimation of the NN weight tuning algorithm. The proposed novel control algorithm has been analyzed using Lyapunov analysis. In addition to excellent output trajectory tracking performance, the proposed approach has a profound benefit in terms of substantially lower control effort in comparison to the established work in the literature. In terms of applications in the petrochemical industry, lower control effort can translate to a more energy-efficient actuator, leading to lower costs over a long-run operation. The proposed method's feasibility for chemical process control was shown via numerical simulation.

A Hybrid Dynamic Wavelet-Based Modeling Method for Blood Glucose Concentration Prediction in Type 1 Diabetes.

Background:Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction of blood glucose concentration (BGC) is essential to improve the therapy of type 1 DM (T1DM).Methods:Having considered the risk of hyper- and hypo-glycemia, we provide a new hybrid modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN) model, including a heuristic input selection. The proposed models include a hybrid dynamic WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet-based networks are designed based on dominant wavelets selected by the genetic algorithm-orthogonal least square method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction, an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on real data from 12 T1DM patients and also simulated data from 33 virtual patients with an UVa/ Padova simulator, an approved simulator by the US Food and Drug Administration.Results:A comparison study is performed in terms of new glucose-based assessment metrics, such as gFIT, glucose-weighted form of ESODn (gESODn), and glucose-weighted R2 (gR2). For real patients’ data, the values of the mentioned indices are accomplished as gFIT = 0.97 ± 0.01, gESODn = 1.18 ± 0.38, and gR2 = 0.88 ± 0.07. HDFWNN, HDWNN and jump NN method showed the prediction error (root mean square error [RMSE]) of 11.23 ± 2.77 mg/dl, 10.79 ± 3.86 mg/dl and 16.45 ± 4.33 mg/dl, respectively.Conclusion:Furthermore, the generalized estimating equation and post hoc tests show that proposed models perform better compared with other proposed methods.

Tree-Structured Regional CNN-LSTM Model for Dimensional Sentiment Analysis

Dimensional sentiment analysis aims to recognize continuous numerical values in multiple dimensions such as the valence-arousal (VA) space. Compared to the categorical approach that focuses on sentiment classification such as binary classification (i.e., positive and negative), the dimensional approach can provide a more fine-grained sentiment analysis. This article proposes a tree-structured regional CNN-LSTM model consisting of two parts: regional CNN and LSTM to predict the VA ratings of texts. Unlike a conventional CNN which considers a whole text as input, the proposed regional CNN uses a part of the text as a region, dividing an input text into several regions such that the useful affective information in each region can be extracted and weighted according to their contribution to the VA prediction. Such regional information is sequentially integrated across regions using LSTM for VA prediction. By combining the regional CNN and LSTM, both local (regional) information within sentences and long-distance dependencies across sentences can be considered in the prediction process. To further improve performance, a region division strategy is proposed to discover task-relevant phrases and clauses to incorporate structured information into VA prediction. Experimental results on different corpora show that the proposed method outperforms lexicon-, regression-, conventional NN and other structured NN methods proposed in previous studies.

QoE Evaluation Methods for 360-Degree VR Video Transmission

Virtual reality (VR) videos, especially 360-degree VR videos, have attracted substantial research interests with the explosion of mobile VR devices in recent years. In this work, we propose a VR quality of experience (QoE) evaluation framework including online, offline and mixed scenarios that can meet the requirement of real applications. Under this framework, we further develop a subjective evaluation method and an objective QoE evaluation model based on network transmission parameters. A VR panoramic video database is established with nine different contents. This database contains 468 different samples coming from nine original contents. Then, in the subjective evaluation part, we propose to adopt four dimensions, i.e., quality score, immersion score, non-spinning sensation score and global score for the subjective evaluation purpose. These dimensions can meet the interaction and immersion features of the VR video service. In the objective evaluation part, an improved two-step neural network (INN) model is developed by using the features of the physiological psychology and cognitive neurology. This model captures the intrinsic link between the initial input network parameters and the final perception in VR transmission. Our results suggest that the proposed INN can achieve a higher pearson correlation coefficients than the other methods. Especially, it increases by 8.9% than the traditional NN method. Our work can make up for the shortage of traditional evaluation methods in term of the VR QoE subjective and objective evaluation in transmission scopes.

Model for predicting cost of rural road projects in Thailand

Nowadays, construction cost plays an essential role in various projects, which are buildings, roads, railways, and bridges projects. Conceptual cost estimation in feasibility study is require high accuracy and less validation error especially in construction projects at early stages. The more improvement of estimation techniques, it would lead to the lesser problems of cost overrun, and extra expenses. This paper developed a cost estimation model for new constructed rural road projects. Considering the estimation methods for predicting the cost model, parametric method based on regression learner and NN method are applied. Previously, many researchers studied the cost applicable model by using various computer applications, so that this paper differed to compare these methods based on MATLAB. Accordingly, 44 road projects were compiled from DRR database, after that identifying the effective cost parameters referred on collected data. Subsequently, the data implementation process was focusing with regression learner based on automated regression training, and lastly, with NN toolbox concentrated on nftool for simulating the cost models. Another 7 road projects are tested with holdout validation process for these models. Due to this validation, we compare the predicted cost models within these methods. Finally, the developed models are reliable for not only the conceptual phase of future rural road projects but also the related construction fields can be recovered about the cost model creation.

Transformed Secure Feed Forward Supervised Learning Method for Authentication in Multi-Model Biometric System

Biometric is an automated detection of the characteristics of an individual on the basis of the biological and social features. Detection of the uni-modal biometric system is based on the biometric data of an individual. Some issue of distortion level spoofing threats are more accessible to biometric data. Some of the issues overcome by multimodal biometric scheme in which signature of the biometric data are determine for better security of the data. Multimodal biometric is used on variety of the application areas which are human computer interface, detection of the sensor through unique method. The physical and social characteristics are used for the identification of an individual using multimodal biometric system. Multi-model biometric system applications are security system developed in banking sectors, business phase and Industry (MNC) companies. In existing work, using ESVM method to recognize the biometric traits and problem occurs in existing phase is distortion and degrades the image quality present and reduces the recognition rate and high error rates. In proposed research, determined the biometric features finger print, face and iris through CASIA dataset. Then, distortion rate is recognised through salt and pepper method and removal of interference using filtration technique. After that, discrete wavelet transformation is used for the extraction of the features of the biometric system through face, fingerprint and eye that determine the graphical features. Along with that, feed forward neural network algorithm developed for classification and recognition of multi modal biometric behaviour characteristics. The Encrypted NN method conducts simulation work on the metrics like as a recognition rate, true positive rate and computation time. The experimental results demonstrate that Encrypted NN method is able to enhance the image quality, recognition rate and TPR and reduces the computational time of Multi-model Biometric System when compared with existing work and simulation tool used MATLAB 2016a.

Feed forward neural network based ionospheric model for the East African region

In this paper, a neural network based regional ionospheric model is developed using GPS-TEC data from 01 January 2012 to 31 December 2015. For this purpose, nine GPS station TEC data in the time intervals 2012 to 2014 were used to determine model parameters. TEC data obtained in various years and geographical locations which are excluded in the training time are used to validate the performance of the model. For the first case, TEC data from each station in the year 2015 is used to validate the performance of the model. In the second case, GPS observations at Metu, Robe, and Serb stations are used to investigate the model’s performance in the year 2012, 2014 and 2013–2014, respectively. In both cases, to validate the accuracy and quality of the model, GPS-TEC values were compared with the predicted TEC. The results indicate that the proposed model can capture most of the spatio-temporal variations of the regional TEC. The present model reproduces the observed hourly TEC with RMS values that lie around 3 to 6.05 TECU at different geographical locations for both one hour and one day ahead prediction. For one day ahead prediction, a comparison of the NN method using NeQuick 2 model outputs with GPS derived measurements have also been conducted. The results indicate that the NN TEC model proposed has a good performance in representing TEC variations compared to climate NeQuick 2 model.

CRACK PATTERN PREDICTION OF LATERALLY LOADED PANELS WITH OPENINGS BASED ON ANN METHOD

In this paper, a Back Propagation Neural Network (BPNN) is used to predict crack pattern for masonry panels with opening subjected to lateral loading. The cellular automata method is used to digitalize the panels, including two steps-dividing a panel into a certain number of cells and calculating cell state values by use of a Von Neumann neighborhood model. These digitalized values are used as input data of NN model, respectively. All the experimental data is collected, including panel configuration, material property, opening ratio and location, state values, and crack pattern. The NN model is trained repeatedly, taking part of the data as a training set, to determine parameters, and the rest of the data is taken to check the model. Well-trained NN models can predict the crack pattern of any other panel. The results show that NN method is suitable for prediction of crack pattern. Comparing the two ways of prediction, the Fragility Coefficient Method gets a more precise pattern. The predicted cracks are distributed successively in some specific areas, especially in high similarity, compared with experimental crack pattern.

Improved $k$NN-Based Monitoring Schemes for Detecting Faults in PV Systems

This paper presents a model-based anomaly detection method for supervising the direct current (dc) side of photovotaic (PV) systems. Toward this end, a framework combining the benefits of $k$ -nearest neighbors ( $k$ NN) with univariate monitoring approaches has been proposed. Specifically, $k$ NN-based Shewhart and exponentially weighted moving average (EWMA) schemes with parametric and nonparametric thresholds have been introduced to suitably detect faults in PV systems. The choice of $k$ NN method to separate normal and abnormal features is motivated by its capacity to handle nonlinear features and do not make assumptions on the underlying data distribution. In addition, because the EWMA approach is sensitive in detecting small changes. First, a simulation model for the inspected PV array is constructed. Then, residuals generated from this model are employed as the input for $k$ NN-based schemes for anomaly detection. Parametric and nonparametric thresholds using kernel density estimation have been used to detect faults. The effectiveness of the $k$ NN-based procedures is verified using actual measurements from a 9.54-kWp grid-connected system in Algeria. Results proclaim the efficiency of the proposed strategy to supervise the dc side of PV systems.

Adaptive Non Playable Character in RPG Game Using Logarithmic Learning For Generalized Classifier Neural Network (L-GCNN)

Non-playable Character (NPC) is one of the important characters in the game. An autonomous and adaptive NPC can adjust actions with player actions and environmental conditions. To determine the actions of the NPC, the previous researchers used the Neural Network method but there were weaknesses, namely the action produced was not in accordance with the desired so the accuracy was not good. This study overcomes the problem of poor accuracy by using the Logarithmic Learning for Generalized Classifier Neural Network (L-GCNN) method with 6 input parameters, NPC health, distance from players, other NPCs involved, attack power, number of NPCs and NPC levels. While the output is to attack itself, attack in groups and move away. For testing, this study was tested on RPG games. From the results of the experiments conducted, it shows that the L-GCNN method has better accuracy than the 3 methods compared to 7% better than NN and SVM and 8% better than RBFNN because in the L-GCNN method there is an encapsulation process that is data have the same class will. Whereas the L-GCNN training time is 30% longer than the NN method because on L-GCNN one neuron consists of one data where there are fewer NNs in the hidden layer.

Study on quick judgment of power system stability using improved k‐ NN and LASSO method

Dynamic security assessment is widely used in dispatching operation systems, and calculation speed is one of its most important performance indices. In this study, an improved k-nearest neighbour (k-NN) method is proposed aiming to predict the stability indicators of power system, for example, critical clearing time. The method is much faster than the simulation and suitable for online analysis. Firstly, a simulation sample database is constructed based on historical online data and a logistic regression model with least absolute shrinkage and selection operator is trained to pick the stability features, which are chosen from static quantities like running state and active power of electric elements. While a new operation mode needs to be evaluated, a weighted k-NN is implemented to obtain the most familiar samples in the database using the chosen features; the final result will be determined comprehensively by the familiar samples. The validity of the proposed method is verified by simulation using online data of State Grid Corp of China and different key faults. It is proved that the method meets the requirements for speed and accuracy of online analysis system.

Solution to the Outlier Samples Problem in Function Approximation Based on an Adapted Neural Fuzzy Inference System

This paper describes a novel application of the Adapted Neural Fuzzy Inference System (ANFIS) to function approximation. Several functions in one dimension are realised in this work, including a Gaussian function and a combination of sine waves with exponential functions, in order to confirm the efficiency of the ANFIS method; these results are then compared with those from a Radial Basis Function Neural Network (RBFNN) and Fuzzy Inference System (FIS), which have previously been successfully applied to function approximation problems. This paper introduces the ANFIS as a robust method that mitigates, or is insensitive to, outliers. The results show that the ANFIS method can solve the outlier samples problem, and that the performance of ANFIS proposed in this work is thus better than that of the NN and FIS methods; the function approximated outputs of the presented ANFIS are more faithful to the original test functions and RMSEs of the ANFIS are also lower, especially during the checking process.

Global and local clustering with kNN and local PCA

This paper proposes a new clustering method that combines the k Near Neighbor (k NN) method and the local Principal Component Analysis (PCA) to consider the global and local information of data points for clustering. Specifically, we propose firstly preserving the local information of samples using the k NN method to obtain a neighborhood subset and a covariance matrix for each data point, and then preserving the global information of the data by conducting the local PCA on each covariance matrix to obtain a binary affinity matrix of the data. Furthermore, our method conducts clustering on the resulting affinity matrix without the assignment of clustering number. Experimental analysis on 8 UCI benchmark datasets showed that our proposed method outperformed the state-of-the-art clustering methods in terms of clustering performance.