Nonlinear Decision Research Articles

Characteristics of Radio-Signal Detection for the Nonlinear Decision Function of a Threshold Device

We consider the characteristics of radio-signal detection using the nonlinear decision function of a threshold device. This work is aimed at estimating the influence of the difference between the nonlinear decision function of the receiver threshold device and the step function on the characteristics of detecting radio signals with a random initial phase and random initial phase and amplitude. New analytical expressions for the probabilities of correct detection of radio signals and false alarm are obtained.

Classification of air pollutants API Inter-Correlation using decision tree algorithms

The automated classification of ambient air pollutants is an important task in air pollution hazards assessment and life quality research. Faced with various classification algorithms, environmental scientists should select the most appropriate method according to their requirements and data availability. This study describes several types of Decision Tree algorithms for finding the inter-correlation between dominant air pollution index (API) for PM10 percentile values and four other air pollutants such as Sulphur Dioxide (SO2), Ozone (O3), Nitrogen Dioxide (NO2) and Carbon monoxide (CO), in addition to two other meteorological parameters: ambient temperature and humidity, using 22 months records of active air monitoring station in Penang island (northern Malaysia). Classification analysis for the PM10 API was then performed using non-linear Decision Trees within the R programming environment including: Boosted C5.0, Random Forest, PART, and Naive Bayes tree (NBtree). This is in addition to rpart and tree algorithms, which were used to plot the classification trees. The classification performance of the methods is presented and the best classifier in terms of accuracy and processing time was recommended. In R statistical environment, the process of classification by decision tree methods and the classification rules were easy to obtain, while geographic information systems (GIS) software’ was used for mapping the study area. Furthermore, the results are clear and easy to understand for environmental and geospatial scientists and relevant agencies, which will facilitate the mitigation of air pollution related disasters in the affected communities.

Using Machine Learning and Natural Language Processing to Review and Classify the Medical Literature on Cancer Susceptibility Genes.

The medical literature relevant to germline genetics is growing exponentially. Clinicians need tools that help to monitor and prioritize the literature to understand the clinical implications of pathogenic genetic variants. We developed and evaluated two machine learning models to classify abstracts as relevant to the penetrance-risk of cancer for germline mutation carriers-or prevalence of germline genetic mutations. We conducted literature searches in PubMed and retrieved paper titles and abstracts to create an annotated data set for training and evaluating the two machine learning classification models. Our first model is a support vector machine (SVM) which learns a linear decision rule on the basis of the bag-of-ngrams representation of each title and abstract. Our second model is a convolutional neural network (CNN) which learns a complex nonlinear decision rule on the basis of the raw title and abstract. We evaluated the performance of the two models on the classification of papers as relevant to penetrance or prevalence. For penetrance classification, we annotated 3,740 paper titles and abstracts and evaluated the two models using 10-fold cross-validation. The SVM model achieved 88.93% accuracy-percentage of papers that were correctly classified-whereas the CNN model achieved 88.53% accuracy. For prevalence classification, we annotated 3,753 paper titles and abstracts. The SVM model achieved 88.92% accuracy and the CNN model achieved 88.52% accuracy. Our models achieve high accuracy in classifying abstracts as relevant to penetrance or prevalence. By facilitating literature review, this tool could help clinicians and researchers keep abreast of the burgeoning knowledge of gene-cancer associations and keep the knowledge bases for clinical decision support tools up to date.

Estimation of the Smoothing Parameter in Probabilistic Neural Network Using Evolutionary Algorithms

The probabilistic neural network (PNN) is an efficient approach that can compute nonlinear decision boundaries, widely used for classification. In this paper, the often used Gaussian distribution function is replaced by a new probability density function which provides a new variant of the PNN method. Most of the higher-dimensional data are statistically found to be not from the normal distribution, and hence, we have replaced it by the symmetric Laplace distribution. Further, the estimation of the smoothing parameter in the proposed PNN model is carried out with three different evolutionary algorithms, namely bat algorithm (BA), grey wolf optimizer (GWO), and whale optimization algorithm (WOA) with a novel fitness function. These different proposed PNN models with variable smoothing parameter estimation methods are tested on five different benchmark data sets. The performance of proposed three Laplace distribution-based variants of PNN incorporated with BA, GWO, and WOA are reported and compared with Gaussian-based variants of PNN and also other commonly used classifiers: the conventional PNN, extreme learning machine, and K-nearest neighbor in terms of measurement accuracy. The results demonstrate that the proposed approaches using evolutionary algorithms can provide as much as a ten percent increase in accuracy over the conventional PNN method.

Multiple Kernel Based Remote Sensing Vegetation Classifier with Levy Optimized Subspace

Vegetation classification in remote sensing (RS) applications details a rich source of information on land use/land cover decision making. To classify the mixed land-cover area of diverse categories through RS imagery, robust classification methods and their techniques act as a substratum for thematic interpretation. Though many classification techniques have been raised for the study of remote sensing images, support vector machine (SVM) has received huge attention. In order to handle non-linear separable high dimensional feature space, optimized subspace-based classifier acts as a bedrock for improved accuracy as accuracy is still a primary concern to design efficient classifiers for nonlinear separable feature space. In this work, a classifier Enhanced Entropy based Multiple Kernel Support Vector Machine with Levy optimized subspace has experimented for vegetation classification. Since SVMs are a typically linear methods, they can be easily derived into non-linear decision criteria by substituting the inner products with kernel functions. The results indicate that the proposed method is getting better accuracy than the existing Methods.

The impact of government subsidy of manufacturing firm innovative decision in the background of low-carbon

In the low-carbon background, the green manufacturing and a new road to industrialization should be developed in China. Government subsidies can promote the promotion of low-energy products, and thus control the total carbon emissions. Aiming at an innovation-decision dilemma of a kind of self-research and development manufacturing firms, the characteristics of disruptive innovation and sustaining innovation were analyzed in the viewpoint of the firms’ dynamic competitive advantages. A 0-1 nonlinear decision model was built with consumer surplus as the optimization objective. This model can provide guidance for government policy strategy and manufacturing firm innovation decision. A genetic algorithm was developed to solve the 0-1 nonlinear decision model. A case study of an automobile was reported to demonstrate the feasibility and rationality of this approach.

Research on the relationship between government policy and enterprise production decision in green background

In the low-carbon background, China must develop green manufacturing actively, and take a new road to industrialization. Government subsidies can promote the promotion of low-energy products, and thus control the total carbon emissions. Aiming at production decision of a kind of manufacturing business, A 0-1 Nonlinear decision model was built with consumer surplus as the optimization objective. This model provided guidance for the government policy decision and the firm production decision. A genetic algorithm was put forward to solve the 0-1 nonlinear decision model. A case study of refrigerator was reported to demonstrate the feasibility and rationality of this approach.

Optimized Conditioning Factors Using Machine Learning Techniques for Groundwater Potential Mapping

Assessment of the most appropriate groundwater conditioning factors (GCFs) is essential when performing analyses for groundwater potential mapping. For this reason, in this work, we look at three statistical factor analysis methods—Variance Inflation Factor (VIF), Chi-Square Factor Optimization, and Gini Importance—to measure the significance of GCFs. From a total of 15 frequently used GCFs, 11 most effective ones (i.e., altitude, slope angle, plan curvature, profile curvature, topographic wetness index, distance from river, distance from fault, river density, fault density, land use, and lithology) were finally selected. In addition, 917 spring locations were identified and used to train and test three machine learning algorithms, namely Mixture Discriminant Analysis (MDA), Linear Discriminant Analysis (LDA) and Random Forest (RF). The resultant trained models were then applied for groundwater potential prediction and mapping in the Haraz basin of Mazandaran province, Iran. MDA has been successfully applied for soil erosion and landslide mapping, but has not yet been fully explored for groundwater potential mapping (GPM). Although other discriminant methods, such as LDA, exist, MDA is worth exploring due to its capability to model multivariate nonlinear relationships between variables; it also undertakes a mixture of unobserved subclasses with regularization of non-linear decision boundaries, which could potentially provide more accurate classification. For the validation, areas under Receiver Operating Characteristics (ROC) curves (AUC) were calculated for the three algorithms. RF performed better with AUC value of 84.4%, while MDA and LDA yielded 75.2% and 74.9%, respectively. Although MDA performance is lower than RF, the result is satisfactory, because it is within the acceptable standard of environmental modeling. The outcome of factor analysis and groundwater maps emphasizes on optimization of multicolinearity factors for faster spatial modeling and provides valuable information for government agencies and private sectors to effectively manage groundwater in the region.

Bat algorithm-based weighted Laplacian probabilistic neural network

Probabilistic neural network (PNN) is a single-pass feed-forward neural network with the capability of providing nonlinear decision boundaries. In this work, we propose the modifications to the existing PNN approach. Contributions are threefold: First, symmetric Laplace distribution has been used instead of Gaussian distribution in the pattern layer of the PNN approach. Second, a new weight coefficients’ estimation method has been introduced between the pattern and summation layers of PNN. Third, a novel convex fitness function has been designed for the bat algorithm to obtain an optimal smoothing parameter vector. The designed fitness function maintains a balance between the sensitivity and specificity values. The performance of the proposed algorithm “bat algorithm-based weighted Laplacian probabilistic neural network” is compared with that of conventional PNN, weighted PNN, extreme learning method, optimal pruned extreme learning machine and K-nearest neighbor. Experimental evaluation is carried out on eleven benchmark data sets using different performance measures such as accuracy, sensitivity, specificity and Youden’s index. The comparative performance evaluation of the proposed model has been made with the PNN, and other standard algorithms outperform the compared approaches in terms of classification accuracy. Friedman test is used for statistical evaluation of the proposed approach.

Mitigation of Nonlinear Impairments by Using Support Vector Machine and Nonlinear Volterra Equalizer

A support vector machine (SVM) based detection is applied to different equalization schemes for a data center interconnect link using coherent 64 GBd 64-QAM over 100 km standard single mode fiber (SSMF). Without any prior knowledge or heuristic assumptions, the SVM is able to learn and capture the transmission characteristics from only a short training data set. We show that, with the use of suitable kernel functions, the SVM can create nonlinear decision thresholds and reduce the errors caused by nonlinear phase noise (NLPN), laser phase noise, I/Q imbalances and so forth. In order to apply the SVM to 64-QAM we introduce a binary coding SVM, which provides a binary multiclass classification with reduced complexity. We investigate the performance of this SVM and show how it can improve the bit-error rate (BER) of the entire system. After 100 km the fiber-induced nonlinear penalty is reduced by 2 dB at a BER of 3.7 × 10 − 3 . Furthermore, we apply a nonlinear Volterra equalizer (NLVE), which is based on the nonlinear Volterra theory, as another method for mitigating nonlinear effects. The combination of SVM and NLVE reduces the large computational complexity of the NLVE and allows more accurate compensation of nonlinear transmission impairments.

Collective Decision Making in Human Crowds: Majority Rule Emerges From Local Averaging

Collective motion in human crowds emerges when each pedestrian averages the motion of their neighbors (Warren, CDPS, 2018). Previously, we found that a participant is influenced by a weighted average of visible neighbors, with a weight that decays exponentially with distance (Rio, Dachner & Warren, PRSB, 2018). Yet crowds also make collective decisions, such as whether to follow a subgroup, that seem to imply a nonlinear decision rule (Pillot, et al., 2011; Leonard, et al., 2012). Faced with such a decision, does a pedestrian follow the group average, a quorum, the majority, or the minority?Our neighborhood model seems to suggest they would average the two groups. To test the question, we asked participants to “walk with” a virtual crowd (N=8 or 16) that split into two subgroups. Participants walked in a 12×14m tracking area while wearing a head-mounted display, and head position was recorded. On each trial, the virtual crowd walked forward (1–2 s), then a subgroup turned left (50%, 63%, 75%, 88% of the crowd) and the rest turned right by the same amount (angle between them α = 10°, 15°, 20°, 25°, 30°). Interestingly, both the participants and the neighborhood model tend to follow the majority. A regression analysis shows that the neighborhood model accounts for 42% of the variance in the human final heading. Thus, an apparently nonlinear decision does not require a nonlinear decision rule. Rather, the nonlinearity stems from the spatial separation of the two groups over time: The initial response is biased by the majority of near neighbors, who pull the participant away from the minority and increasingly dominate the neighborhood. To test this explanation, Exp. 2 eliminates the spatial separation by using two continuous streams of virtual neighbors. Conclusion: nonlinear decision-making emerges from spatial averaging over a small neighborhood.

Dynamic postponement design for crowdsourcing in open manufacturing: A hierarchical joint optimization approach

Open manufacturing and crowdsourcing have been envisioned as a trend for industries to promote collaboration across different firms and support the sharing and exchange of knowledge and services throughout the value chain. Incorporating postponement decisions with the crowdsourcing strategy helps reduce the risk and uncertainty associated with product variety in an open manufacturing environment. The inherent coupling of product design and postponement decisions in an open manufacturing environment necessitates joint optimization of product family design and postponement planning. This article formulates a Dynamic Postponement Design (DPD) problem that considers an undefined product architecture that interacts with the postponement design according to optimal planning of open manufacturing activities. The DPD problem differs from traditional (static) postponement design models in that the latter assumes that a (fixed) product architecture is available at the outset. This article r develops a Hierarchical Joint Optimization (HJO) model based on Stackelberg game theory. The HJO model deploys a bi-level mixed 0-1 nonlinear programing decision structure to reveal the coupling of product design and postponement decisions. To solve the bi-level programing model, a nested genetic algorithm is developed and implemented. A case study of smart refrigerator design for postponement is reported to illustrate the DPD problem and the proposed HJO approach.

PENGGUNAAN MODEL HIDDEN MARKOV DAN METODE NEURAL NETWORK SEBAGAI PENERAPAN TEKNOLOGI PENGENALAN WAJAH

The human face recognition system is one of the fields that is quite developed at this time, where applications can be applied in the field of security (security system) such as permission to access room, surveillance (surveillance), as well as the search for individual identities in the police database. The face recognition approach aims to detect faces in 2-dimensional images and sequential images of videos that have many methods such as local, global, and hybrid approaches. Hidden Model Markov (HMM) is another promising method that works well for images with different lighting variations, facial expressions, and orientations. HMM is a set of statistical models used to characterize signal properties. An artificial neural network-based approach is learned from image examples and relies on techniques from machine learning to find relevant facial image characteristics. The characteristics studied were in the form of discriminant functions (ie non-linear decision surfaces), then used for face recognition. In this study there will be an application to compare Hidden Markov Models and Neural Network Method as a Face Recognition Technology Algorithm Model.

Public information, heterogeneous attention and market instability

In this paper, we investigate how market instability is formed with investment decision models of heterogeneous agents who are characterized by different selectivities of attention to public information. In the nonlinear dynamic decision model, agents make decisions on trading volume based on their own volume and marginal payoff of the previous period, as well as their selective attention to public information. One goal of this paper is to use the model to explore the condition under which public information could trigger the market instability. A second, related, goal is to study whether there is other investor behavior factor that leads to market instability. We find that some traders’ significant attention to bad news or most traders’ significant attention to good news can lead to market instability. We also find that whole market also may develop into chaos through bifurcation, with increasing relative trading adjustment speed responding to marginal payoff for some traders, although all traders pay no attention to public information. The relative trading adjustment speed responding to marginal payoff is more likely to cause market instability than public information. Our findings reveal an extremely simple stylized fact that market instability always occurs when there is no public information.

Machine Learning Algorithms for Automatic Lithological Mapping Using Remote Sensing Data: A Case Study from Souk Arbaa Sahel, Sidi Ifni Inlier, Western Anti-Atlas, Morocco

Remote sensing data proved to be a valuable resource in a variety of earth science applications. Using high-dimensional data with advanced methods such as machine learning algorithms (MLAs), a sub-domain of artificial intelligence, enhances lithological mapping by spectral classification. Support vector machines (SVM) are one of the most popular MLAs with the ability to define non-linear decision boundaries in high-dimensional feature space by solving a quadratic optimization problem. This paper describes a supervised classification method considering SVM for lithological mapping in the region of Souk Arbaa Sahel belonging to the Sidi Ifni inlier, located in southern Morocco (Western Anti-Atlas). The aims of this study were (1) to refine the existing lithological map of this region, and (2) to evaluate and study the performance of the SVM approach by using combined spectral features of Landsat 8 OLI with digital elevation model (DEM) geomorphometric attributes of ALOS/PALSAR data. We performed an SVM classification method to allow the joint use of geomorphometric features and multispectral data of Landsat 8 OLI. The results indicated an overall classification accuracy of 85%. From the results obtained, we can conclude that the classification approach produced an image containing lithological units which easily identified formations such as silt, alluvium, limestone, dolomite, conglomerate, sandstone, rhyolite, andesite, granodiorite, quartzite, lutite, and ignimbrite, coinciding with those already existing on the published geological map. This result confirms the ability of SVM as a supervised learning algorithm for lithological mapping purposes.

(Invited) Single Nanoarray Sensor for Multi-Analyte Detection

Chemical sensors usually adopted a single resistance-metric mode, which has a drawback of significant cross-sensitivities in mixed analytes scenario, thus showing a poor selectivity towards target analytes. By integration of multiple sensors in a so-called sensor array platform, multi-analyte detection and enhanced selectivity can be achieved. However such a strategy requires significant device integration work involving sophisticated electrical interconnects with increasing circuit complexity. In the past few years, we has been focused on establishing a multi-mode sensing platform based on a single nanostructure array (nanoarray) device. Such a single device platform can be operated at variable temperatures with different modes such as photocurrent, resistance, and impedance. These nanoarray sensors have been fabricated with good scalability using a variety of synthetic methods ranging from vapor to solution phase depositions. The array composition could be rationally designed from pristine homogeneous to dissimilar heterogeneous across metals, ceramics, and polymers. Depending on the comprised material composition, decoration of a nanolayer of perovskite, metal oxide, or noble metal may enable formation of electronic and catalytic sensitizers, as well as hetero-contacts that can drastically boost sensor performance under various gaseous analyte atmospheres. Toward mixed multi-analyte conditions, such a new type of multi-mode nanoarray sensors allows selective and sensitive detection of multiple chemical species in a single-device configuration. By relating the multiple sensing modes using a single nanoarray sensor, efficient and selective detection of multiple gas analytes has been accomplished. A database was established based on multiple sets of data, namely the sensitivities for different analytes obtained from the outputs of different sensing modes. The signals of multiple gas analytes could be differentiated through the principal component analysis process. The linear and non-linear decision boundaries could be readily derived for pattern recognition, and the multi-analyte quantification and detection.

A coordinated optimization framework for flexible operation of pumped storage hydropower system: Nonlinear modeling, strategy optimization and decision making

Pumped storage hydropower system has now become a key support for integration of variable renewable energy. Along with the large-scale development of pumped storage plants all over the world, the importance of operation strategy is rapidly increasing with the fast-growing demand of flexibility. How to direct flexible operation and improve the stability of the system has become a key issue. This paper proposes a novel optimization framework to derive optimal operating policies for pumped storage hydropower system, which is divided into three coordinated stages: nonlinear modeling, strategy optimization and decision making. The real-time accurate equivalent circuit model is proposed in first stage, which can reconcile the conflict between simulation efficiency and accuracy, owing to the novel pump-turbine model and space-time discretization. The search corridor which consists of multiple constraints is defined to improve search efficiency. Reference vector guided evolutionary algorithm is performed to handle non-normalization objectives, multiple constraints and irregular Pareto fronts in second stage. Further, fuzzy analytic hierarchy process is innovatively introduced to select compatible solution under extreme conditions. The originality of the framework is embodied in multiple trade-offs, i.e. trade-off between accuracy and efficiency in the nonlinear model, trade-off between convergence and diversity in the strategy optimization, and trade-off in conflicting objectives of the decision making. Compared with the on-site operation, the maximum water pressure of volute and the vacuum at draft tube can be improved by 5.59% and 9.6%, the rotational speed oscillation also decreases with this framework in load rejection. The proposed framework can specify the optimal policy to enhance the system reliability, which can also serve as the basis for smart operation in various conditions.

Making sense of kernel spaces in neural learning

Kernel-based and Deep Learning methods are two of the most popular approaches in Computational Natural Language Learning. Although these models are rather different and characterized by distinct strong and weak aspects, they both had impressive impact on the accuracy of complex Natural Language Processing tasks. An advantage of kernel-based methods is their capability of exploiting structured information induced from examples. For instance, Sequence or Tree kernels operate over structures reflecting linguistic evidence, such as syntactic information encoded in syntactic parse trees. Deep Learning approaches are very effective as they can learn non-linear decision functions: however, general models require input instances to be explicitly modeled via vectors or tensors, and operating on structured data is made possible only by using ad-hoc architectures.In this work, we discuss a novel architecture that efficiently combines kernel methods and neural networks, in the attempt at squeezing the best from the two paradigms. The so-called Kernel-based Deep Architecture (KDA) adopts a Nyström-based projection function to approximate any valid kernel function and convert any structure they operate on (for instance, linguistic structures, such as trees) into dense linear embeddings. These can be used as input of a Deep Feed-forward Neural Network that exploits such embeddings to learn non-linear classification functions. KDA is a mathematically justified integration of expressive kernel functions and deep neural architectures, with several advantages: it (i) directly operates over complex non-tensor structures, e.g., trees, without ad hoc manual feature engineering or architectural design, (ii) achieves a drastic reduction of the computational cost w.r.t. pure kernel methods, and (iii) exploits the non-linearity of Deep Architectures to produce accurate models. We experimented the KDA in three rather different semantic inference tasks: Semantic Parsing, Question Classification, and Community Question Answering. Results show that the KDA achieves state-of-the-art accuracy, with a computational cost that is much lower than the one necessary to train and test a pure kernel-based method, such as the SVM algorithm.

QAM classification methods by SVM machine learning for improved optical interconnection

High-order quadrature amplitude modulation (QAM) formats are very effective for increasing the transmission capacity due to the highly increased spectral efficiency. However, the signal-to-noise-ratio (SNR) hungry and dense constellation of QAM make it very sensitive to nonlinear distortion. The nonlinear decision boundary adaptively generated by machine learning method of support vector machine (SVM) can be effectively used for the classification of the symbols. The different classification methods have different performance in terms of classification complexity. We experimentally investigated five SVM multi-classification methods for machine learning assisted adaptive nonlinear mitigation, including the one versus rest (OvR), the symbol encoding (SE), the binary encoding (BE), the constellation rows and columns (RC), and the in-phase and quadrature components (IQC). The comprehensive results with comparisons are demonstrated, indicating significant nonlinear mitigation with BER reductions. The SVM multi-classifier based on the in-phase and quadrature components is relatively optimal, considering the calculation and storage.

Deep Convolutional Neural Network for Flood Extent Mapping Using Unmanned Aerial Vehicles Data.

Flooding is one of the leading threats of natural disasters to human life and property, especially in densely populated urban areas. Rapid and precise extraction of the flooded areas is key to supporting emergency-response planning and providing damage assessment in both spatial and temporal measurements. Unmanned Aerial Vehicles (UAV) technology has recently been recognized as an efficient photogrammetry data acquisition platform to quickly deliver high-resolution imagery because of its cost-effectiveness, ability to fly at lower altitudes, and ability to enter a hazardous area. Different image classification methods including SVM (Support Vector Machine) have been used for flood extent mapping. In recent years, there has been a significant improvement in remote sensing image classification using Convolutional Neural Networks (CNNs). CNNs have demonstrated excellent performance on various tasks including image classification, feature extraction, and segmentation. CNNs can learn features automatically from large datasets through the organization of multi-layers of neurons and have the ability to implement nonlinear decision functions. This study investigates the potential of CNN approaches to extract flooded areas from UAV imagery. A VGG-based fully convolutional network (FCN-16s) was used in this research. The model was fine-tuned and a k-fold cross-validation was applied to estimate the performance of the model on the new UAV imagery dataset. This approach allowed FCN-16s to be trained on the datasets that contained only one hundred training samples, and resulted in a highly accurate classification. Confusion matrix was calculated to estimate the accuracy of the proposed method. The image segmentation results obtained from FCN-16s were compared from the results obtained from FCN-8s, FCN-32s and SVMs. Experimental results showed that the FCNs could extract flooded areas precisely from UAV images compared to the traditional classifiers such as SVMs. The classification accuracy achieved by FCN-16s, FCN-8s, FCN-32s, and SVM for the water class was 97.52%, 97.8%, 94.20% and 89%, respectively.