Recognition of English information and semantic features based on SVM and machine learning

Anaphora Resolution ◽

Semantic Features ◽

Feature Combination ◽

Candidate Model ◽

Current Event ◽

Semantic Roles ◽

With the deepening of people’s research on event anaphora, a large number of methods will be used in the identification and resolution of event anaphora. Although there has been some progress in the resolution of the current event, the difficult problems have not yet been completely resolved. This study analyzes the English information anaphora resolution based on SVM and machine learning algorithms and uses the CNN three-layer network as the basis to model the structure. Moreover, this study improves the semantic features by adding semantic roles and analyzes and compares the performance of the improved semantic features with those before the improvement. In addition, this study combines semantic features to compare and analyze each feature combination and uses a dual candidate model to improve the system. Finally, this study analyzes the experimental results. The results show that the performance of the system using the dual candidate model is better than that of the single candidate model system.

Exploring the Use of Machine Learning to Automate the Qualitative Coding of Church-related Tweets

Fieldwork in Religion ◽

10.1558/firn.40610 ◽

2020 ◽

Vol 14 (2) ◽

pp. 140-159

Author(s):

Anthony-Paul Cooper ◽

Emmanuel Awuni Kolog ◽

Erkki Sutinen

Keyword(s):

Machine Learning ◽

Online Community ◽

High Volume ◽

Supervised Machine Learning ◽

Social Media Data ◽

Twitter Data ◽

Resource Intensity ◽

Media Data ◽

This article builds on previous research around the exploration of the content of church-related tweets. It does so by exploring whether the qualitative thematic coding of such tweets can, in part, be automated by the use of machine learning. It compares three supervised machine learning algorithms to understand how useful each algorithm is at a classification task, based on a dataset of human-coded church-related tweets. The study finds that one such algorithm, Naïve-Bayes, performs better than the other algorithms considered, returning Precision, Recall and F-measure values which each exceed an acceptable threshold of 70%. This has far-reaching consequences at a time where the high volume of social media data, in this case, Twitter data, means that the resource-intensity of manual coding approaches can act as a barrier to understanding how the online community interacts with, and talks about, church. The findings presented in this article offer a way forward for scholars of digital theology to better understand the content of online church discourse.

Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity

Sensors ◽

10.3390/s21134618 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4618

Author(s):

Francisco Oliveira ◽

Miguel Luís ◽

Susana Sargento

Keyword(s):

Machine Learning ◽

Cellular Networks ◽

Real Data ◽

Emerging Technology ◽

Base Stations ◽

Aerial Vehicle ◽

Positioning Algorithm ◽

The Military ◽

Unmanned Aerial Vehicle (UAV) networks are an emerging technology, useful not only for the military, but also for public and civil purposes. Their versatility provides advantages in situations where an existing network cannot support all requirements of its users, either because of an exceptionally big number of users, or because of the failure of one or more ground base stations. Networks of UAVs can reinforce these cellular networks where needed, redirecting the traffic to available ground stations. Using machine learning algorithms to predict overloaded traffic areas, we propose a UAV positioning algorithm responsible for determining suitable positions for the UAVs, with the objective of a more balanced redistribution of traffic, to avoid saturated base stations and decrease the number of users without a connection. The tests performed with real data of user connections through base stations show that, in less restrictive network conditions, the algorithm to dynamically place the UAVs performs significantly better than in more restrictive conditions, reducing significantly the number of users without a connection. We also conclude that the accuracy of the prediction is a very important factor, not only in the reduction of users without a connection, but also on the number of UAVs deployed.

Algorithmic and human prediction of success in human collaboration from visual features

Scientific Reports ◽

10.1038/s41598-021-81145-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Martin Saveski ◽

Edmond Awad ◽

Iyad Rahwan ◽

Manuel Cebrian

Keyword(s):

Machine Learning ◽

Visual Cues ◽

Success Factors ◽

Group Performance ◽

Learning Algorithms ◽

Adventure Game ◽

Group Success ◽

The Relationship ◽

AbstractAs groups are increasingly taking over individual experts in many tasks, it is ever more important to understand the determinants of group success. In this paper, we study the patterns of group success in Escape The Room, a physical adventure game in which a group is tasked with escaping a maze by collectively solving a series of puzzles. We investigate (1) the characteristics of successful groups, and (2) how accurately humans and machines can spot them from a group photo. The relationship between these two questions is based on the hypothesis that the characteristics of successful groups are encoded by features that can be spotted in their photo. We analyze >43K group photos (one photo per group) taken after groups have completed the game—from which all explicit performance-signaling information has been removed. First, we find that groups that are larger, older and more gender but less age diverse are significantly more likely to escape. Second, we compare humans and off-the-shelf machine learning algorithms at predicting whether a group escaped or not based on the completion photo. We find that individual guesses by humans achieve 58.3% accuracy, better than random, but worse than machines which display 71.6% accuracy. When humans are trained to guess by observing only four labeled photos, their accuracy increases to 64%. However, training humans on more labeled examples (eight or twelve) leads to a slight, but statistically insignificant improvement in accuracy (67.4%). Humans in the best training condition perform on par with two, but worse than three out of the five machine learning algorithms we evaluated. Our work illustrates the potentials and the limitations of machine learning systems in evaluating group performance and identifying success factors based on sparse visual cues.

2020 IEEE 26th International Conference on Parallel and Distributed Systems (ICPADS) ◽

Using Configuration Semantic Features and Machine Learning Algorithms to Predict Build Result in Cloud-Based Container Environment

10.1109/icpads51040.2020.00042 ◽

2020 ◽

Author(s):

Yiwen Wu ◽

Yang Zhang ◽

Junsheng Chang ◽

Bo Ding ◽

Tao Wang ◽

...

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Semantic Features

Application of machine learning algorithms to predict permeability in tight sandstone formations

Nafta-Gaz ◽

10.18668/ng.2021.05.01 ◽

2021 ◽

Vol 77 (5) ◽

pp. 283-292

Author(s):

Tomasz Topór ◽

Keyword(s):

Machine Learning ◽

Oil And Gas ◽

Learning Algorithms ◽

Confining Pressure ◽

Core Material ◽

Confining Stress ◽

Tight Sandstone ◽

Oil And Gas Exploration ◽

The application of machine learning algorithms in petroleum geology has opened a new chapter in oil and gas exploration. Machine learning algorithms have been successfully used to predict crucial petrophysical properties when characterizing reservoirs. This study utilizes the concept of machine learning to predict permeability under confining stress conditions for samples from tight sandstone formations. The models were constructed using two machine learning algorithms of varying complexity (multiple linear regression [MLR] and random forests [RF]) and trained on a dataset that combined basic well information, basic petrophysical data, and rock type from a visual inspection of the core material. The RF algorithm underwent feature engineering to increase the number of predictors in the models. In order to check the training models’ robustness, 10-fold cross-validation was performed. The MLR and RF applications demonstrated that both algorithms can accurately predict permeability under constant confining pressure (R2 0.800 vs. 0.834). The RF accuracy was about 3% better than that of the MLR and about 6% better than the linear reference regression (LR) that utilized only porosity. Porosity was the most influential feature of the models’ performance. In the case of RF, the depth was also significant in the permeability predictions, which could be evidence of hidden interactions between the variables of porosity and depth. The local interpretation revealed the common features among outliers. Both the training and testing sets had moderate-low porosity (3–10%) and a lack of fractures. In the test set, calcite or quartz cementation also led to poor permeability predictions. The workflow that utilizes the tidymodels concept will be further applied in more complex examples to predict spatial petrophysical features from seismic attributes using various machine learning algorithms.

Predicting Health Material Cognitive Accessibility Using Multidimensional Semantic Features and Readability Tools as Predicators (Preprint)

10.2196/preprints.29175 ◽

2021 ◽

Author(s):

Meng Ji ◽

Yanmeng Liu ◽

Tianyong Hao

Keyword(s):

Machine Learning ◽

Health Education ◽

Health Information ◽

Domain Knowledge ◽

Learning Algorithms ◽

Semantic Features ◽

Integrated Models ◽

Advanced Education ◽

Cognitive Accessibility

BACKGROUND Much of current health information understandability research uses medical readability formula (MRF) to assess the cognitive difficulty of health education resources. This is based on an implicit assumption that medical domain knowledge represented by uncommon words or jargons form the sole barriers to health information access among the public. Our study challenged this by showing that for readers from non-English speaking backgrounds with higher education attainment, semantic features of English health texts rather than medical jargons can explain the lack of cognitive access of health materials among readers with better understanding of health terms, yet limited exposure to English health education materials. OBJECTIVE Our study explored combined MRF and multidimensional semantic features (MSF) for developing machine learning algorithms to predict the actual level of cognitive accessibility of English health materials on health risks and diseases for specific populations. We compare algorithms to evaluate the cognitive accessibility of specialised health information for non-native English speaker with advanced education levels yet very limited exposure to English health education environments. METHODS We used 108 semantic features to measure the content complexity and accessibility of original English resources. Using 1000 English health texts collected from international health organization websites, rated by international tertiary students, we compared machine learning (decision tree, SVM, discriminant analysis, ensemble tree and logistic regression) after automatic hyperparameter optimization (grid search for the best combination of hyperparameters of minimal classification errors). We applied 10-fold cross-validation on the whole dataset for the model training and testing, calculated the AUC, sensitivity, specificity, and accuracy as the measured of the model performance. RESULTS Using two sets of predictor features: widely tested MRF and MSF proposed in our study, we developed and compared three sets of machine learning algorithms: the first set of algorithms used MRF as predictors only, the second set of algorithms used MSF as predictors only, and the last set of algorithms used both MRF and MSF as integrated models. The results showed that the integrated models outperformed in terms of AUC, sensitivity, accuracy, and specificity. CONCLUSIONS Our study showed that cognitive accessibility of English health texts is not limited to word length and sentence length conventionally measured by MRF. We compared machine learning algorithms combing MRF and MSF to explore the cognitive accessibility of health information from syntactic and semantic perspectives. The results showed the strength of integrated models in terms of statistically increased AUC, sensitivity, and accuracy to predict health resource accessibility for the target readership, indicating that both MRF and MSF contribute to the comprehension of health information, and that for readers with advanced education, semantic features outweigh syntax and domain knowledge.

Pathways to Consumers’ Minds: Using Machine Learning and Multiple EEG Metrics to Increase Preference Prediction Above and Beyond Traditional Measurements

10.1101/317073 ◽

2018 ◽

Cited By ~ 3

Author(s):

Adam Hakim ◽

Shira Klorfeld ◽

Tal Sela ◽

Doron Friedman ◽

Maytal Shabat-Simon ◽

...

Keyword(s):

Machine Learning ◽

Predictive Power ◽

Rank Order ◽

Marketing Research ◽

Great Promise ◽

Neural Signals ◽

Novel Approach ◽

First Time ◽

AbstractA basic aim of marketing research is to predict consumers’ preferences and the success of marketing campaigns in the general population. However, traditional behavioral measurements have various limitations, calling for novel measurements to improve predictive power. In this study, we use neural signals measured with electroencephalography (EEG) in order to overcome these limitations. We record the EEG signals of subjects, as they watched commercials of six food products. We introduce a novel approach in which instead of using one type of EEG measure, we combine several measures, and use state-of-the-art machine learning algorithms to predict subjects’ individual future preferences over the products and the commercials’ population success, as measured by their YouTube metrics. As a benchmark, we acquired measurements of the commercials’ effectiveness using a standard questionnaire commonly used in marketing research. We reached 68.5% accuracy in predicting between the most and least preferred items and a lower than chance RMSE score for predicting the rank order preferences of all six products. We also predicted the commercials’ population success better than chance. Most importantly, we demonstrate for the first time, that for all of our predictions, the EEG measurements increased the prediction power of the questionnaires. Our analyses methods and results show great promise for utilizing EEG measures by managers, marketing practitioners, and researchers, as a valuable tool for predicting subjects’ preferences and marketing campaigns’ success.

A Comparative Study of Machine Learning Methods for Automatic Classification of Academic and Vocational Guidance Questions

International Journal of Interactive Mobile Technologies (iJIM) ◽

10.3991/ijim.v14i08.13005 ◽

2020 ◽

Vol 14 (08) ◽

pp. 43 ◽

Cited By ~ 1

Author(s):

Omar Zahour ◽

El Habib Benlahmar ◽

Ahmed Eddaouim ◽

Oumaima Hourrane

Keyword(s):

Machine Learning ◽

Comparative Study ◽

Automatic Classification ◽

Vocational Guidance ◽

Holland's Theory ◽

Machine Learning Methods ◽

The Right ◽

Academic and vocational guidance is a particularly important issue today, as it strongly determines the chances of successful integration into the labor market, which has become increasingly difficult. Families have understood this because they are interested, often with concern, in the orientation of their child. In this context, it is very important to consider the interests, trades, skills, and personality of each student to make the right decision and build a strong career path. This paper deals with the problematic of educational and vocational guidance by providing a comparative study of the results of four machine-learning algorithms. The algorithms we used are for the automatic classification of school orientation questions and four categories based on John L. Holland's Theory of RIASEC typology. The results of this study show that neural networks work better than the other three algorithms in terms of the automatic classification of these questions. In this sense, our model allows us to automatically generate questions in this domain. This model can serve practitioners and researchers in E-Orientation for further research because the algorithms give us good results.

Novel Privacy Preserving Non-Invasive Sensing-Based Diagnoses of Pneumonia Disease Leveraging Deep Network Model

Sensors ◽

10.3390/s22020461 ◽

2022 ◽

Vol 22 (2) ◽

pp. 461

Author(s):

Mujeeb Ur Rehman ◽

Arslan Shafique ◽

Kashif Hesham Khan ◽

Sohail Khalid ◽

Abdullah Alhumaidi Alotaibi ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Medical Records ◽

Learning Algorithms ◽

X Ray ◽

Non Invasive ◽

Proposed Model ◽

Pneumonia Diagnosis ◽

This article presents non-invasive sensing-based diagnoses of pneumonia disease, exploiting a deep learning model to make the technique non-invasive coupled with security preservation. Sensing and securing healthcare and medical images such as X-rays that can be used to diagnose viral diseases such as pneumonia is a challenging task for researchers. In the past few years, patients’ medical records have been shared using various wireless technologies. The wireless transmitted data are prone to attacks, resulting in the misuse of patients’ medical records. Therefore, it is important to secure medical data, which are in the form of images. The proposed work is divided into two sections: in the first section, primary data in the form of images are encrypted using the proposed technique based on chaos and convolution neural network. Furthermore, multiple chaotic maps are incorporated to create a random number generator, and the generated random sequence is used for pixel permutation and substitution. In the second part of the proposed work, a new technique for pneumonia diagnosis using deep learning, in which X-ray images are used as a dataset, is proposed. Several physiological features such as cough, fever, chest pain, flu, low energy, sweating, shaking, chills, shortness of breath, fatigue, loss of appetite, and headache and statistical features such as entropy, correlation, contrast dissimilarity, etc., are extracted from the X-ray images for the pneumonia diagnosis. Moreover, machine learning algorithms such as support vector machines, decision trees, random forests, and naive Bayes are also implemented for the proposed model and compared with the proposed CNN-based model. Furthermore, to improve the CNN-based proposed model, transfer learning and fine tuning are also incorporated. It is found that CNN performs better than other machine learning algorithms as the accuracy of the proposed work when using naive Bayes and CNN is 89% and 97%, respectively, which is also greater than the average accuracy of the existing schemes, which is 90%. Further, K-fold analysis and voting techniques are also incorporated to improve the accuracy of the proposed model. Different metrics such as entropy, correlation, contrast, and energy are used to gauge the performance of the proposed encryption technology, while precision, recall, F1 score, and support are used to evaluate the effectiveness of the proposed machine learning-based model for pneumonia diagnosis. The entropy and correlation of the proposed work are 7.999 and 0.0001, respectively, which reflects that the proposed encryption algorithm offers a higher security of the digital data. Moreover, a detailed comparison with the existing work is also made and reveals that both the proposed models work better than the existing work.

Comparing Machine Learning Algorithms for Predicting ICU Admission and Mortality in COVID-19

10.1101/2020.11.20.20235598 ◽

2020 ◽

Author(s):

Sonu Subudhi ◽

Ashish Verma ◽

Ankit B. Patel ◽

C. Corey Hardin ◽

Melin J. Khandekar ◽

...

Keyword(s):

Machine Learning ◽

Clinical Decision Making ◽

Learning Algorithms ◽

Disease Outbreaks ◽

Clinical Decision ◽

Healthcare Database ◽

Icu Admission ◽

Infectious Disease Outbreaks ◽

AbstractAs predicting the trajectory of COVID-19 disease is challenging, machine learning models could assist physicians determine high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) healthcare database, we developed and internally validated models using patients presenting to Emergency Department (ED) between March-April 2020 (n = 1144) and externally validated them using those individuals who encountered ED between May-August 2020 (n = 334). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and procalcitonin levels were important for ICU admission models whereas eGFR <60 ml/min/1.73m2, ventilator use, and potassium levels were the most important variables for predicting mortality. Implementing such models would help in clinical decision-making for future COVID-19 and other infectious disease outbreaks.