Pruning Growing Self-Organizing Map Network for Human Physical Activity Identification

Human physical activity identification based on wearable sensors is of great significance to human health analysis. A large number of machine learning models have been applied to human physical activity identification and achieved remarkable results. However, most human physical activity identification models can only be trained based on labeled data, and it is difficult to obtain enough labeled data, which leads to weak generalization ability of the model. A Pruning Growing SOM model is proposed in this paper to address the limitations of small-scale labeled dataset, which is unsupervised in the training stage, and then only a small amount of labeled data is used for labeling neurons to reduce dependency on labeled data. In training stage, the inactive neurons in network can be deleted by pruning mechanism, which makes the model more consistent with the data distribution and improves the identification accuracy even on unbalanced dataset, especially for the action categories with poor identification effect. In addition, the pruning mechanism can also speed up the inference of the model by controlling its scale.

Supervised Kohonen Self-Organizing Maps of Acute Asthma from Air Pollution Exposure

There are unanswered questions with regards to acute respiratory outcomes, particularly asthma, due to environmental exposures. In contribution to asthma research, the current study explored a computational intelligence paradigm of artificial neural networks (ANNs) called self-organizing maps (SOM). To train the SOM, air quality data (nitrogen dioxide, sulphur dioxide and particulate matter), interpolated to geocoded addresses of asthmatics, were used with clinical data to classify asthma outcomes. Socio-demographic data such as age, gender and race were also used to perform the classification by the SOM. All pollutants and demographic traits appeared to be important for the correct classification of asthma outcomes. Age was more important: older patients were more likely to have asthma. The resultant SOM model had low quantization error. The study concluded that Kohonen self-organizing maps provide effective classification models to study asthma outcomes, particularly when using multidimensional data. SO2 was concluded to be an important pollutant that requires strict regulation, particularly where frail subpopulations such as the elderly may be at risk.

Selection of Optimized Retaining Wall Technique Using Self-Organizing Maps

Construction projects in urban areas tend to be associated with high-rise buildings and are of very large-scales; hence, the importance of a project’s underground construction work is significant. In this study, a rational model based on machine learning (ML) was developed. ML algorithms are programs that can learn from data and improve from experience without human intervention. In this study, self-organizing maps (SOMs) were utilized. An SOM is an alternative to existing ML methods and involves a subjective decision-making process because a developed model is used for data training to classify and effectively recognize patterns embedded in the input data space. In addition, unlike existing methods, the SOM can easily create a feature map by mapping multidimensional data to simple two-dimensional data. The objective of this study is to develop an SOM model as a decision-making approach for selecting a retaining wall technique. N-fold cross-validation was adopted to validate the accuracy of the SOM model and evaluate its reliability. The findings are useful for decision-making in selecting a retaining wall method, as demonstrated in this study. The maximum accuracy of the SOM was 81.5%, and the average accuracy was 79.8%.

Automatic detection of rare observations during production tests using statistical models

Engines are verified through production tests before delivering them to customers. During those tests, lot of measures are taken on different parts of the engine, considering multiple physical parameters. Unexpected measures can be observed. For this very reason, it is important to assess if these unusual observations are statistically significant. However, anomaly detection is a difficult problem in unsupervised learning. The obvious reason is that, unlike supervised classification, there is no ground truth against which we could evaluate results. Therefore, we propose a methodology based on two independent statistical algorithms to double check our results. One approach is the Isolation Forest (IF) model which is specific to anomaly detection and able to handle a large number of variables. The goal of the algorithm is to find rare items, events or observations which raise suspicions by differing significantly from the majority of the data and, at the same time, it discriminates non-informative variables to improve. One main issue of IF is its lack of interpretability. Within this scope, we extend the shapley values, interpretation indicators, to the unsupervised context to interpret the model outputs. The second approach is the Self-Organizing Map (SOM) model which has nice properties for data mining by providing both clustering and visual representation. The performance of the method and its interpretability depends on the chosen subset of variables. In this respect, we first implement a sparse-weighted K-means to reduce the input space, allowing the SOM to give an interpretable discretized representation. We apply the two methodologies on data on aircraft engines measurements. Both approaches show similar results which are easily interpretable and exploitable by the experts.

The Effects and Implications of Mood on Moral Judgements

Vladimir A. Lefebvre [1, 2] proposed an algebraic model of self-reflection that predicts individuals will judge ambiguous stimuli positively with a proportional frequency of .618. While a number of studies have empirically supported this prediction [3, 4], Anderson and colleagues [5] found only partial support for Lefebvre’s model. They moreover suggested that Schwartz and Garmoni’s States of Mind (SOM; [7]) model could potentially explain the disparate findings as well as the variability of positive judgements seen across individuals. Consequently, this study explored whether ratios of psychological functioning posited by the SOM model correspond with proportions of positive judgements of ambiguous stimuli (viz., pairs of pinto beans). Results revealed that, while Lefebvre’s predicted proportion of positive judgments was again replicated, individuals with relatively high positive affect were not more likely to rate greater proportions of the ambiguous stimuli positively.

An Artificial Neural Network Model for Assessing Frailty-Associated Factors in the Thai Population

Frailty, one of the major public health problems in the elderly, can result from multiple etiologic factors including biological and physical changes in the body which contribute to the reduction in the function of multiple bodily systems. A diagnosis of frailty can be reached using a variety of frailty assessment tools. In this study, general characteristics and health data were assessed using modified versions of Fried’s Frailty Phenotype (mFFP) and the Frail Non-Disabled (FiND) questionnaire (mFiND) to construct a Self-Organizing Map (SOM). Trained data, composed of the component planes of each variable, were visualized using 2-dimentional hexagonal grid maps. The relationship between the variables and the final SOM was then investigated. The SOM model using the modified FiND questionnaire showed a correct classification rate (%CC) of about 66% rather than the model responded to mFFP models. The SOM Discrimination Index (SOMDI) identified cataracts/glaucoma, age, sex, stroke, polypharmacy, gout, and sufficiency of income, in that order, as the top frailty-associated factors. The SOM model, based on the mFiND questionnaire frailty assessment, is an appropriate tool for assessment of frailty in the Thai elderly. Cataracts/glaucoma, stroke, polypharmacy, and gout are all modifiable early prediction factors of frailty in the Thai elderly.

A Fuzzy-SOM Method for Fraud Detection in Power Distribution Networks with High Penetration of Roof-Top Grid-Connected PV

This study proposes a fuzzy self-organized neural networks (SOM) model for detecting fraud by domestic customers, the major cause of non-technical losses in power distribution networks. Using a bottom-up approach, normal behavior patterns of household loads with and without photovoltaic (PV) sources are determined as normal behavior. Customers suspected of energy theft are distinguished by calculating the anomaly index of each subscriber. The bottom-up method used is validated using measurement data of a real network. The performance of the algorithm in detecting fraud in old electromagnetic meters is evaluated and verified. Types of energy theft methods are introduced in smart meters. The proposed algorithm is tested and evaluated to detect fraud in smart meters also.

Cognition of a Robotic Manipulator Using the Q-Learning Based Situation-Operator Model

In this article, we have applied cognition on robot using Q-learning based situation operator model. The situation operator model takes the initial situation of the mobile robot and applies a set of operators in order to move the robot to the destination. The initial situation of the mobile robot is defined by a set of characteristics inferred by the sensor inputs. The Situation-Operator Model (SOM) model comprises of a planning and learning module which uses certain heuristics for learning through the mobile robot and a knowledge base which stored the experiences of the mobile robot. The control and learning of the robot is done using q-learning. A camera sensor and an ultrasonic sensor were used as the sensory inputs for the mobile robot. These sensory inputs are used to define the initial situation, which is then used in the learning module to apply the valid operator. The results obtained by the proposed method were compared to the result obtained by Reinforcement-Based Artificial Neural Network for path planning.

On building early-warning systems for preventing the deterioration of financial institutions’ performance

This paper assesses the financial performance of Romania’s non-banking financial institutions (NFIs) using a neural network training algorithm proposed by Kohonen, namely the Self-Organizing Maps algorithm. The algorithm takes the financial dataset and positiones each observation into a self-organizing map (a two-dimensional map) which can be latter used to visualize the trajectories of an individual NFI and explain it based on different performance dimensions, such as capital adequacy, assets’ quality and profitability. Further, we use the map as an early-warning system that would accurately forecast the NFIs future performance (whether they would stay or be eliminated from the NFI’s Special Register three quarters into the future). The results are promising: the model is able to correctly predict NFIs’ performance movements. Finally, we compared the results of our SOM-based model with those obtained by applying a multivariate logit-based model. The SOM model performed worse in discriminating the NFIs’ performance: the performance classes were not clearly defined and the model lacked the interpretability of the results. In the contrary, the multivariate logit coefficients have nice interpretability and an individual default probability estimate is obtained for each new observation. However, we can benefit from the results of both techniques: the visualization capabilities of the SOM model and the interpretability of multivariate logit-based model.