Constructing Event Corpus from Inverted Index for Sentence Level Crime Event Detection and Classification

In this paper, we investigate a semi-supervised method, that is, self-training algorithm in event detection and type recognition. First, we get two kinds of feature vectors of sentences for event detection and type recognition task respectively. Second, we use self-training algorithm to filter the non-event instances and identify type for every event instance. The experimental result on the ACE2005 corpus shows that our model using self-training algorithm can identify the majority of non-event instances and also has a good precision and recall rate in event type recognition.KeywordsEvent ExtractionSemi-supervised LearningFeature Selection

The paper proposes phrase-level emotion patterns using Neuro-Fuzzy model. At the initial stage, the emotional patterns at phrase level are obtained using POS Tags and EMOT Actifiers that results into 16 patterns. These patterns works well with the sentences having single emotion and classifies them into Positive and Negative polarities. However, it is observed that these patterns are unable to define the exact boundary between positive and negative polarities of these sentence patterns. Thus, this issue will affect the classification accuracy due to imprecise boundary between the sentences. Mixed emotions exist in long sentences with multi phrases and therefore the sentences are broken at Phrase-level. The patterns are extracted at phrase-level and converted as fuzzy rules for the classification of mixed emotion patterns. Intensity grades are calculated for the patterns based on the features of phrases and their structure in the sentence. These intensity grades classify the patterns at phrase level into Positive and Negative emotions. Based on the intensity grades, a suitable weighing mechanism is proposed for the multi phrasal sentence structure which decides the degree of Positive and Negative polarities of emotion in a sentence. Higher weighted phrasal pattern decides the Positive and Negative polarities of emotion in a sentence. Proposed approach performs well and achieves good F-Scores compared with other comparative approaches on benchmark datasets.

Predictive systems use historical and other available data to predict an event. In this paper we tries to compare the power of Artificial Neural Network (ANN) and Decision Tree (DT) in prediction of aerology events with time series streams and events stream using combination of K-means clustering algorithm and Decision Tree C5 algorithm and ANN. We try to find the effective parameters on events occurrences. Firstly, we find the closest time series record for any events; therefore, we have gathered different parameters value when an event is occurring. Using K-means we add a field to dataset which determines the cluster of each record and after that we predict the events using C5 algorithm and ANN. This framework and time series model can predict future events efficiently. We gathered 1961 until 2005 data of aerology organization for Tehran Mehrabad Station. This data contains some fields such as wet bulb, relative humidity, amount of cloud, wind speed and etc. This dataset includes 17 types of events. Using this framework the closest event can be predicted. The C5 method is able to predict events with 79.55% accuracy and ANN with 72.87% accuracy. Applying K-means clustering algorithm the prediction increase to 94.59% for C5 and 92.66% accuracies for ANN. We use 10-fold cross validation to evaluate our prediction rate. This framework is the first estimation in the area of event prediction for a huge dataset of aerology and can be extended in many different datasets in any other environments.

Event Detection (ED) aims to identify event trigger words from a given text and classify it into an event type. Most current methods to ED rely heavily on training instances, and almost ignore the correlation of event types. Hence, they tend to suffer from data scarcity and fail to handle new unseen event types. To address these problems, we formulate ED as a process of event ontology population: linking event instances to pre-defined event types in event ontology, and propose a novel ED framework entitled OntoED with ontology embedding. We enrich event ontology with linkages among event types, and further induce more event-event correlations. Based on the event ontology, OntoED can leverage and propagate correlation knowledge, particularly from data-rich to data-poor event types. Furthermore, OntoED can be applied to new unseen event types, by establishing linkages to existing ones. Experiments indicate that OntoED is more predominant and robust than previous approaches to ED, especially in data-scarce scenarios.

The World Wide Web is growing at an uncontrollable rate. Hundreds of thousands of web sites appear every day, with the added challenge of keeping the web directories up-to-date. Further, the uncontrolled nature of web presents difficulties for Web page classification. As the number of Internet users is growing, so is the need for classification of web pages with greater precision in order to present the users with web pages of their desired class. However, web page classification has been accomplished mostly by using textual categorization methods. Herein, we propose a novel approach for web page classification that uses the HTML information present in a web page for its classification. There are many ways of achieving classification of web pages into various domains. This paper proposes an entirely new dimension towards web page classification using Artificial Neural Networks (ANN). Index Terms: World Wide Web, Web page classification, textual categorization, HTML, Artificial Neural Networks, ANN.

Part of speech (POS) tagging is an initial task for many natural language applications. POS tagging for Amharic is in its infancy. This study contributes towards the improvement of Amharic POS tagging by experimenting using Deep Learning and Conditional Random Fields (CRF) approaches. Word embedding is integrated into the system to enhance performance. The model was applied to an Amharic news corpus tagged into 11 major part of speeches and achieved accuracies of 91.12% and 90% for the Bidirectional LSTM and CRF methods respectively. The result shows that the Bidirectional LSTM approach performance is better than the CRF method. More enhancement is expected in the future by increasing the size and diversity of Amharic corpus.

Unlimited access to information and data sharing wherever and at any time for anyone and anything is a fundamental component of fifth-generation (5G) wireless communication and beyond. Therefore, it has become inevitable to exploit the super-high frequency (SHF) and millimeter-wave (mmWave) frequency bands for future wireless networks due to their attractive ability to provide extremely high data rates because of the availability of vast amounts of bandwidth. However, due to the characteristics and sensitivity of wireless signals to the propagation effects in these frequency bands, more accurate path loss prediction models are vital for the planning, evaluating, and optimizing future wireless communication networks. This paper presents and evaluates the performance of several well-known machine learning methods, including multiple linear regression (MLR), polynomial regression (PR), support vector regression (SVR), as well as the methods using decision trees (DT), random forests (RF), K-nearest neighbors (KNN), artificial neural networks (ANN), and artificial recurrent neural networks (RNN). RNNs are mainly based on long short-term memory (LSTM). The models are compared based on measurement data to provide the best fitting machine-learning-based path loss prediction models. The main results obtained from this study show that the best root-mean-square error (RMSE) performance is given by the ANN and RNN-LSTM methods, while the worst is for the MLR method. All the RMSE values for the given learning techniques are in the range of to dB. Furthermore, this work shows that the models (except for the MLR model) perform excellently in fitting actual measurement data for wireless communications in enclosed indoor environments since they provide R-squared and correlation values higher than and , respectively. The paper shows that these learning methods could be used as accurate and stable models for predicting path loss in the mmWave frequency regime.

This paper proposes universal coarse-grained reconfigurable computing architecture for hardware implementation of decision trees (DTs), artificial neural networks (ANNs), and support vector machines (SVMs), suitable for both field programmable gate arrays (FPGA) and application specific integrated circuits (ASICs) implementation. Using this universal architecture, two versions of DTs (functional DT and axis-parallel DT), two versions of SVMs (with polynomial and radial kernel) and two versions of ANNs (multi layer perceptron ANN and radial basis ANN) machine learning classifiers, have been implemented in FPGA. Experimental results, based on 18 benchmark datasets of standard UCI machine learning repository database, show that FPGA implementation provides significant improvement (1–2 orders of magnitude) in the average instance classification time, in comparison with software implementations based on R project.

To categorize and synthesize medication safety event detection methods in the critically ill in order to provide clinicians and administrators with approaches to event detection that are intended to expand and complement traditional voluntary reporting systems. A literature search of OvidMEDLINE was performed to identify articles related to medication safety involving critically ill patients in the intensive care unit setting. The inclusion of articles was restricted to comparative studies. The bibliographies of all retrieved articles were reviewed to obtain additional articles of relevance. The various event detection methods were compared by: evidence supporting their use; number, type and severity of events detected; phase of the medication use process in which events were detected; and ease and cost of implementation. Major limitations of each method were also collated. There are a number of methods that can be used to identify medication safety events in the critically ill. These can broadly be categorized as: 1) voluntary reporting, 2) record review, 3) rules/triggers and 4) direct observation and 5) interviews/surveys. Relatively few studies have directly compared these assessment methods in the ICU setting, although the limitations of the traditional voluntary reporting system as the sole method of event detection are well established. Although not truly dichotomous, these methods can be broken down into more proactive and reactive approaches. Rules/triggers and direct observation of the medication use process in the ICU are examples of proactive approaches to event detection, while the traditional unsolicited voluntary reporting is typically reactive. However, each of the event detection methods has advantages and disadvantages, so the methods should not be considered mutually exclusive with respect to obtaining information about medication safety. Given the limitations of traditional voluntary reporting systems, a multimodal approach used to identify medication safety events is most likely to capture the largest number and type of events. We would advise not trying to implement additional approaches beyond voluntary reporting systems all at once. This would be difficult and costly. Rather, we suggest a systematic implementation of additional event detection approaches that takes into account hospital-specific considerations.

Newer analytic approaches for developing predictive models provide a method of creating decision support to translate findings into practice. The aim of this study was to develop and validate a clinically interpretable predictive model for 12-month mortality risk among community-dwelling older adults. This is done by using routinely collected nursing assessment data to aide homecare nurses in identifying older adults who are at risk for decline, providing an opportunity to develop care plans that support patient and family goals for care. A retrospective secondary analysis of Medicare and Medicaid data of 635,590 Outcome and Assessment Information Set (OASIS-C) start-of-care assessments from January 1, 2012, to December 31, 2012, was linked to the Master Beneficiary Summary File (2012-2013) for date of death. The decision tree was benchmarked against gold standards for predictive modeling, logistic regression, and artificial neural network (ANN). The models underwent k-fold cross-validation and were compared using area under the curve (AUC) and other data science metrics, including Matthews correlation coefficient (MCC). Decision tree variables associated with 12-month mortality risk included OASIS items: age, (M1034) overall status, (M1800-M1890) activities of daily living total score, cancer, frailty, (M1410) oxygen, and (M2020) oral medication management. The final models had good discrimination: decision tree, AUC = .71, 95% confidence interval (CI) [.705, .712], sensitivity = .73, specificity = .58, MCC = .31; ANN, AUC = .74, 95% CI [.74, .74], sensitivity = .68, specificity = .68, MCC = .35; and logistic regression, AUC = .74, 95% CI [.735, .742], sensitivity = .64, specificity = .70, MCC = .35. The AUC and 95% CI for the decision tree are slightly less accurate than logistic regression and ANN; however, the decision tree was more accurate in detecting mortality. The OASIS data set was useful to predict 12-month mortality risk. The decision tree is an interpretable predictive model developed from routinely collected nursing data that may be incorporated into a decision support tool to identify older adults at risk for death.

Machine learning has become useful in daily life thanks to improvements in machine learning techniques. Text classification as an important part in machine learning. There are already many methods used for text classification such as Artificial Neural Network (ANN), Naïve Bayes, SVM, Decision Tree etc. ANN is a branch in machine learning which approximate the function of natural neural network. ANN have been used extensively for classification. In this research a simple architecture of ANN is used. But it needs to be pointed out that the architecture used in this research is relatively simple compared to the cutting edge in ANN development and research to show the potential that ANN have compared to other classification method. ANN, Naïve Bayes and SVM performance are measured using f1-macro. Performance of classification model is measured of multiple single-label and multi-label dataset. This research found that in single-label classification ANN have a comparable f1-macro with 0.79 compared to 0.82 for SVM. In multi-label classification ANN have the best f1-macro with 0.48 compared to 0.44 in SVM.

This article investigates the competence of ensemble learning techniques in solar irradiance prediction. It was seen from the literature survey, an ensemble tree model, random forests is studied more frequently as ensemble models. However, ensemble of support vector regression (SVR) and artificial neural networks (ANN) is also possible. So, this study is the first detailed evaluation of ensemble models in solar irradiance estimation domain. Boosting and bagging ensembles of SVR, ANN and decision tree (DT), are developed to estimate solar irradiance in hourly basis in five cities in Turkey. First frequently used base models (SVR, ANN, and DT) are created and tested with the use of 5 years meteorological data. Then boosting and bagging ensembles of the base models are developed and tested with the same data. The base models are compared with their ensemble counterparts in terms of average coefficient of determination (R2) and root mean squared error (RMSE). The comparative results show that boosting and bagging ensemble models improve SVR, ANN, and DT in terms of RMSE between 4.6 and 14.6% in average. The results show empirically that ensemble models improve prediction accuracies of various base regression models and it can be applied to other machine learning models used in solar irradiance prediction.

The demand for high-resolution soil mapping is growing increasingly, in particular for the purpose of land degradation studies. The objective of this study focuses on applying the methods for digital predictive soil mapping in inaccessible, land degradation-prone areas. Artificial Neural Network (ANN) and Decision Tree (DT) were employed within the GIS environment to comply with the complexity of the soil forming factors governing the soil formation. Following the principles of the geopedologic approach to soil survey, a digital predictive soil mapping was carried out in Hoi Num Rin sub-watershed, covering an area about 20 km2. Both ANN and DT were applied to properly integrate the parameterized soil forming factors. To describe soil predictors to train the ANN and to formulate the decision trees, 4 organism types, 7 relief type units, 9 lithological units, 3 time series, 4 landscape units and 8 landform units were extracted from the map and databases. The results, the 10 soil class names were extrapolated to the unsampled areas to obtain the geopedologic map. In conclusion, the geopedologic approach to soil survey, which is based on understanding of landscape-soil relationship, is helpful to obtain spatial soil information in inaccessible areas, using ANN and/or DT are useful techniques in modeling the complex interactions among the soil forming factors. The difference, however, is that ANN, once it is well learnt, is faster, thus more recommendable in terms of time and cost saving.

Churn is a customer's behaviour to quit using product or service and then move to another company. Customer churn is serious problem that must be handled to keep company survive. Handling of churn customers starts from predicting which customers will churn. One approach in predicting customer churn is data mining. This study compares two classification methods in data mining namely artificial neural networks and decision trees in banking industry case. The result showed that the artificial neural network has accuracy 86% and precision 71%, which is better than the decision tree. However, the decision tree has a better recall value than the artificial neural network, which is 58%..

The use of decision trees and artificial neural networks (ANNs) in health-care research is widespread, as they enable health-care providers with the tools they need to make better medical decisions with their patients. ANNs specifically are extremely helpful in predictive research as they can provide investigators with knowledge about future trends and patterns. However, a major downside to ANNs is their lack of interpretability. Understandability of the model is important as it ensures the outcomes are true to the dataset’s original labels and are not impacted by algorithmic bias. In comparison, decision trees map out their entire process before providing the results, which leads to a higher level of trust in the model and the conclusions it supplies the investigators with. This is essential as many historical datasets lack equal and fair representation of all races and sexes, which might directly correlate to a lesser treatment given to females and individuals in minority groups. Here, we review existing work around the differences and connections between ANNs and decision trees with implications for research in health care.