Decision Forest Algorithm Research Articles

Do Acoustic Characteristics of Dysarthria in People With Parkinson's Disease Differ Across Languages?

Cross-language studies suggest more similarities than differences in how dysarthria affects the speech of people with Parkinson's disease (PwPD) who speak different languages. In this study, we aimed to identify the relative contribution of acoustic variables to distinguish PwPD from controls who spoke varieties of two Romance languages, French and Portuguese. This bi-national, cross-sectional, and case-controlled study included 129 PwPD and 124 healthy controls who spoke French or Portuguese. All participants underwent the same clinical examinations, voice/speech recordings, and self-assessment questionnaires. PwPD were evaluated off and on optimal medication. Inferential analyses included Disease (controls vs. PwPD) and Language (French vs. Portuguese) as factors, and random decision forest algorithms identified relevant acoustic variables able to distinguish participants: (a) by language (French vs. Portuguese) and (b) by clinical status (PwPD on and off medication vs. controls). French-speaking and Portuguese-speaking individuals were distinguished from each other with over 90% accuracy by five acoustic variables (the mean fundamental frequency and the shimmer of the sustained vowel /a/ production, the oral diadochokinesis performance index, the relative sound level pressure and the relative sound pressure level standard deviation of the text reading). A distinct set of parameters discriminated between controls and PwPD: for men, maximum phonation time and the oral diadochokinesis speech proportion were the most significant variables; for women, variables calculated from the oral diadochokinesis were the most discriminative. Acoustic variables related to phonation and voice quality distinguished between speakers of the two languages. Variables related to pneumophonic coordination and articulation rate were the more effective in distinguishing PwPD from controls. Thus, our research findings support that respiration and diadochokinesis tasks appear to be the most appropriate to pinpoint signs of dysarthria, which are largely homogeneous and language-universal. In contrast, identifying language-specific variables with the speech tasks and acoustic variables studied was less conclusive.

ML-Enhanced Live Video Streaming in Offline Mobile Ad Hoc Networks: An Applied Approach

Live video streaming has become one of the main multimedia trends in networks in recent years. Providing Quality of Service (QoS) during live transmissions is challenging due to the stringent requirements for low latency and minimal interruptions. This scenario has led to a high dependence on cloud services, implying a widespread usage of Internet connections, which constrains contexts in which an Internet connection is not available. Thus, alternatives such as Mobile Ad Hoc Networks (MANETs) emerge as potential communication techniques. These networks operate autonomously with mobile devices serving as nodes, without the need for coordinating centralized components. However, these characteristics lead to challenges to live video streaming, such as dynamic node topologies or periods of disconnection. Considering these constraints, this paper investigates the application of Artificial Intelligence (AI)-based classification techniques to provide adaptive streaming in MANETs. For this, a software-driven architecture is proposed to route stream in offline MANETs, predicting the stability of individual links and compressing video frames accordingly. The proposal is implemented and assessed in a laboratory context, in which the model performance and QoS metrics are analyzed. As a result, the model is implemented in a decision forest algorithm, which provides 95.9% accuracy. Also, the obtained latency values become assumable for video streaming, manifesting a reliable response for routing and node movements.

Estimating the structural diversity introduced by decision forest algorithms : A probabilistic approach

Structurally diverse decision trees are important for knowledge discovery and classification/prediction accuracy. Over the years, researchers have devoted much effort to the development of algorithms to increase diversity among the trees within an ensemble. While Kappa is commonly used to measure diversity among the decision trees, it does not measure the ability of the tree building algorithms to introduce diversity. Further, Kappa does not consider the structural diversity amongst the trees. Instead, Kappa measures the diversity of the predictions made from the trees produced, and are dependent on the datasets used. This paper presents a novel data-independent metric, called R index, for measuring the diversity that can be introduced by a decision forest algorithm without building the entire decision forest. The proposed measure is applied to five well-known algorithms that involve bagging and random subspacing. An efficient practical approach for calculating the R index empirically – R finder – is also proposed, and is implemented. Both R finder and Kappa were applied to thirty-two publicly available benchmark datasets under various algorithms to estimate the resulting diversity. The results indicate a generally strong negative correlation between R finder and Kappa, implying that R finder is effective at estimating the diversity of trees without the added computational costs associated with calculating Kappa.

MACHINE LEARNING MODEL FOR THE PREDICTION OF CONDITION OF MUSEUM OBJECTS

An accurate prediction of the future condition of museum objects is crucial for developing appropriate proactive maintenance and preservation strategies. Despite this, there are very few such damage models that can be used in practice. The main reasons, for this lack of deterioration models, include complexity of deterioration problem and lack of understanding of the degradation mechanisms affecting various materials and objects, and lack of reliable quantitative approaches. In the article, we discuss the machine learning model, which predicts the future condition of museum objects. For this purpose, the model uses the data of MuIS (Estonian Museum Information System). To predict deterioration, we experimented primarily with various tree-based machine learning algorithms, such as the decision tree, the random forest, and XGBoost. The best results were obtained using the decision forest algorithm, which was able to identify 92% of deteriorating museum objects with 50% accuracy. The machine learning model provides a way to model ageing processes of museum objects over the course of time and thus better plan the preservation work of museums.

Random decision forest (RDF) and crystal structure algorithm (CryStAl) for uncertainty consideration of RES & load demands with optimal design of hybrid CCHP systems

This manuscript proposes a multi-objective random development mode of hybrid Combined Cooling, Heating, And Power (CCHP) system, supply configuration, enclosing a turbine, cooler/heater, battery and storage tank, and photovoltaic/thermal collectors. The proposed optimal strategy is consolidation of Random Decision Forest (RDF) and Crystal Structure Algorithm (CryStAl), hence it is called RDF-CryStAl technique. The Power center models of power converters along with storage devices are create by assuming the characteristics of non-design elements. The annual value rate falls when system confidence levels drop and uncertainty is used. The yearly value savings rate is shown to be highly sensitive to the price of fossil-fuels as a result of the sensitivity analysis of economic-frontiers based on important economic factors. As a result, the inversion of star-collectors includes a robust impact of the turbine.

The prediction model of nitrogen nutrition in cotton canopy leaves based on hyperspectral visible-near infrared band feature fusion.

Hyperspectral remote sensing technology is becoming increasingly popular in various fields due to its ability to provide detailed information about crop growth and nutritional status. The use of hyperspectral technology to predict SPAD (Soil and Plant Analyzer Development) values during cotton growth and adopt precise fertilization management measures is crucial for achieving high yield and fertilizer efficiency. To detect the nitrogen nutrition in cotton canopy leaves quickly, a non-destructive nitrogen nutrition retrieval model was proposed based on the spectral fusion features of the cotton canopy. The hyperspectral vegetation index and multifractal features were fused to predict the SPAD value and identify the amount of fertilizer applied at different levels. The random decision forest algorithm was used as the model predictor and classifier. A method was introduced which was widely used in the fields of finance and stocks (MF-DFA) into the field of agriculture to extract fractal features of cotton spectral reflectance. Comparing the fusion feature with multi-fractal feature and vegetation index, the results showed that the fusion feature parameters had higher accuracy and better stability than using a single feature or feature combination. The R2 was as high as 0.8363, and the RMSE was 1.8767%. Our intelligent model provides a new idea for detecting nitrogen nutrition in cotton canopy leaves rapidly.

Classifying Big Medical Data through Bootstrap Decision Forest Using Penalizing Attributes

Decision forest is a well-renowned machine learning technique to address the detection and prediction problems related to clinical data. But, the traditional decision forest (DF) algorithms have lower classification accuracy and cannot handle high-dimensional feature space effectively. In this work, we propose a bootstrap decision forest using penalizing attributes (BFPA) algorithm to predict heart disease with higher accuracy. This work integrates a significance-based attribute selection (SAS) algorithm with the BFPA classifier to improve the performance of the diagnostic system in identifying cardiac illness. The proposed SAS algorithm is used to determine the correlation among attributes and to select the optimum subset of feature space for learning and testing processes. BFPA selects the optimal number of learning and testing data points as well as the density of trees in the forest to realize higher prediction accuracy in classifying imbalanced datasets effectively. The effectiveness of the developed classifier is cautiously verified on the real-world database (i.e., Heart disease dataset from UCI repository) by relating its enactment with many advanced approaches with respect to the accuracy, sensitivity, specificity, precision, and intersection over-union (IoU). The empirical results demonstrate that the intended classification approach outdoes other approaches with superior enactment regarding the accuracy, precision, sensitivity, specificity, and IoU of 94.7%, 99.2%, 90.1%, 91.1%, and 90.4%, correspondingly. Additionally, we carry out Wilcoxon’s rank-sum test to determine whether our proposed classifier with feature selection method enables a noteworthy enhancement related to other classifiers or not. From the experimental results, we can conclude that the integration of SAS and BFPA outperforms other classifiers recently reported in the literature.

Predicting the future land-use change and evaluating the change in landscape pattern in Binh Duong province, Vietnam

The main purpose of this study is to simulate future land use up to 2030 and to evaluate the change in landscape pattern due to land-use change from 1995 to 2030 in Binh Duong province, Vietnam. Land-use maps generated from multi-temporal Landsat images from 1995 to 2020 and various physical and social driving variables were used as inputs. Markov chain and Decision Forest algorithm integrated in Land Change Modeler application of IDRISI software were used to predict quantity and location of future land-use allocation. Meanwhile, FRAGSTATS software was used to calculate landscape metrics at class and landscape levels. The simulation results showed that there will be 253.8 km2 of agricultural land urbanized in the period from 2020 to 2030. The urban areas will gradually expand from the edge of the existing zones and fill the newly planned areas from South to North and Northeast of the province. The results also revealed that the studied landscape was decreasing in dominance and increasing diversity and heterogeneity at landscape level. The processes of dispersion and aggregation were taking place at the same time in the entire landscape and in the urban class. Meanwhile, the classes of agriculture, mining, and greenspace were increasingly dispersed, but the shape of patches was becoming more regular. The water class increased the dispersion and the irregularity of the patch shape. Finally, the landscape metrics of the unused land fluctuated over time.

Algoritmid museaale uurimas: masinõppemudeli Sälli kasutamine objektide säilivuse prognoosimiseks

The primary task of museums is to preserve museum objects in the form of physical objects. Despite its apparent simplicity and comprehensibility, damage to man-made objects – artefacts – is a complex and complicated field. Damage processes are grouped as being physical, chemical, mechanical, and biological. In most cases, different processes work together, damaging the materials and structure of the artefacts. A number of factors, the most important of which are the composition and structure of materials, environmental conditions, and human impacts, affect damage processes. It is very difficult, and in most cases impossible, to take all these factors into account. At the same time, modelling the aging of museum objects is especially important for their successful preservation. Modelling of damage processes makes it possible to assess the extent of such processes (which objects have been damaged and what the degree of damage is), the speed of damage processes, and thereby changes in the number of damaged objects over time, and finally, the effectiveness of possible management measures.
 In this article, we discuss the machine learning model Sälli, which predicts the durability of museum objects. For this purpose, the machine learning model uses data from MuIS (Estonian Museum Information System). The condition of objects is assessed in MuIS with four values: ‘good’, ‘satisfactory’, ‘poor’, and ‘very poor’. Almost 3.7 million condition assessments have been entered into MuIS. The development of a condition prediction model based on these data requires at least pairs of consecutive condition assessments in order to attempt to determine what correlates with the change in condition, whether it be one or another event, or a property (nature, material, age, techniques) of a museum object, or some combination of such factors. There are more than 1.4 million such pairs among the museum objects with several condition assessments. Almost 32,000 of them, or a little over 2%, consist of two different condition assessments, i.e., they indicate a change in condition. According to the data entered in MuIS, almost 30,000 museum objects, i.e., less than one percent of all museum objects, have been subject to a change in condition.
 As data points, we used at least two condition assessments for each museum object, to which we added the characteristics of the respective museum object and other features that help to predict the deterioration of the condition of the museum object. These data included static data related to the museum object: museum, museum collection, nature, material, material group, technology, exhibitability, and dating. As additional information, we used the history of the museum object, i.e., a summary of the events related to the museum object, taking into account only the events that took place during the condition assessment (because we do not have information on the future). The model finds the probability that the condition of the museum object will deteriorate in the next n years. If the probability of deterioration is greater than or equal to a set threshold, the model responds with ‘deterioration’. In finding the optimal decision threshold, we used a 10-year forecast period, i.e., we trained the decision-makers to predict deterioration over the next 10 years.
 The best results were obtained using the decision forest algorithm, which was able to identify 92% of deteriorating museum objects with 50% accuracy. This model was also used to create the Sälli prototype. The task of the Kratt Sälli prototype is to draw the attention of museum staff to museum objects, the condition of which may deteriorate in the next 10 years and the situation of which should therefore be reviewed. For testing, a prototype of the 1,000 highest-risk museum objects from that museum was added to each test museum. To test the usefulness and usability of the machine learning model predictions, we created a simple web application that was tested in pilot museums. We found that the available data have the potential to predict deterioration, but the data still need to be improved and the model trained on them is not yet mature enough.

Speech as a Biomarker for COVID-19 Detection Using Machine Learning.

The use of speech as a biomedical signal for diagnosing COVID-19 is investigated using statistical analysis of speech spectral features and classification algorithms based on machine learning. It is established that spectral features of speech, obtained by computing the short-time Fourier Transform (STFT), get altered in a statistical sense as a result of physiological changes. These spectral features are then used as input features to machine learning-based classification algorithms to classify them as coming from a COVID-19 positive individual or not. Speech samples from healthy as well as “asymptomatic” COVID-19 positive individuals have been used in this study. It is shown that the RMS error of statistical distribution fitting is higher in the case of speech samples of COVID-19 positive speech samples as compared to the speech samples of healthy individuals. Five state-of-the-art machine learning classification algorithms have also been analyzed, and the performance evaluation metrics of these algorithms are also presented. The tuning of machine learning model parameters is done so as to minimize the misclassification of COVID-19 positive individuals as being COVID-19 negative since the cost associated with this misclassification is higher than the opposite misclassification. The best performance in terms of the “recall” metric is observed for the Decision Forest algorithm which gives a recall value of 0.7892.

The Construction of Big Data Computational Intelligence System for E-Government in Cloud Computing Environment and Its Development Impact.

The traditional E-government big data system fills and classifies algorithms with low accuracy and poor work efficiency. With the development and wide application of big data, the internet of things, and other technologies, the integration of information resources has become the key to information construction. In the process of information resource integration, there are still outstanding problems such as incomplete government information resource system, different standards of government information resource management system construction, and serious threats to network and information security. In order to solve this problem, a new E-government big data system filling and classification algorithm is studied in the cloud computing environment; E-government big data filling is carried out on the basis of complete compatibility theory; and the E-government big data computing intelligence system in the cloud computing environment is constructed and its development impact, so as to parallelize the data, classify the data through decision trees, and realize incremental update decision forest parallelization processing. To verify the effectiveness of the method, comparative experiments are set, and the results demonstrate that experiment one is randomly built into the classification model, and according to the decision forest algorithm, the optimal number of decision trees is 24.

Low voltage ride through enhancement in DFIG based WECS by hybrid method

ABSTRACT This paper proposes a hybrid technique for the enhancement of Low Voltage Ride Through (LVRT) capacity in a Doubly Fed Induction Generator (DFIG) based Wind Energy Conversion System (WECS). The proposed hybrid technique is the joint execution of S-shaped binary version of Whale Optimisation Algorithm (S-bWOA) and Random Decision Forest (RDF), hence it called S-bWOA-RDF method. The major objective is to ensure the LVRT capacity in the WECS at voltage drop including failure stages. S-bWOA model is used to identify the optimal solutions for offline mode as an available search location under objective function and generates the training dataset. In light of proficient dataset, RDF performs and predicts better feasible machine side with grid side converter control signals. The proposed technique is activated in MATLAB/Simulink site, and the efficiency of the proposed S-bWORDF method is compared with the existing methods, such as Random Decision Forest and Whale Optimisation Algorithm. The IAE and ITAE of the proposed and existing methods are also analysed. The IAE and ITAE of the proposed hybrid technique are identified as 5.0071 and 54.0475. The comparison results demonstrate the efficiency of the S-bWORDF method and confirm its potential for enhancing the LVRT of DFIG based WECS.

Prediction of Tissue Damage Using a User-Independent Machine Learning Algorithm vs. Tmax Threshold Maps

(1) Background: To test the accuracy of a fully automated stroke tissue estimation algorithm (FASTER) to predict final lesion volumes in an independent dataset in patients with acute stroke; (2) Methods: Tissue-at-risk prediction was performed in 31 stroke patients presenting with a proximal middle cerebral artery occlusion. FDA-cleared perfusion software using the AHA recommendation for the Tmax threshold delay was tested against a prediction algorithm trained on an independent perfusion software using artificial intelligence (FASTER). Following our endovascular strategy to consequently achieve TICI 3 outcome, we compared patients with complete reperfusion (TICI 3) vs. no reperfusion (TICI 0) after mechanical thrombectomy. Final infarct volume was determined on a routine follow-up MRI or CT at 90 days after the stroke; (3) Results: Compared to the reference standard (infarct volume after 90 days), the decision forest algorithm overestimated the final infarct volume in patients without reperfusion. Underestimation was observed if patients were completely reperfused. In cases where the FDA-cleared segmentation was not interpretable due to improper definitions of the arterial input function, the decision forest provided reliable results; (4) Conclusions: The prediction accuracy of automated tissue estimation depends on (i) success of reperfusion, (ii) infarct size, and (iii) software-related factors introduced by the training sample. A principal advantage of machine learning algorithms is their improved robustness to artifacts in comparison to solely threshold-based model-dependent software. Validation on independent datasets remains a crucial condition for clinical implementations of decision support systems in stroke imaging.

BDF: A new decision forest algorithm

The foremost requirement for a decision forest to achieve better ensemble accuracy is building a set of accurate and diverse individual decision trees as base classifiers. Existing decision forest algorithms mainly differ from each other on how they induce diversity among the decision trees. At the same time, most of the drawbacks of existing algorithms originate from their induction processes of diversity. In this paper, we propose a new decision forest algorithm that is more balanced through effective synchronization between different sources of diversity. The proposed algorithm is balanced theoretically and empirically. We carried out experiments on 25 well-known data sets that are publicly available from the UCI Machine Learning Repository, to perform an extensive empirical evaluation. The experimental results indicate that the proposed algorithm has the best average ensemble accuracy rank of 1.8 compared to its closest competitor at 3.5. Using the Friedman and Bonferroni-Dunn tests, we also show that such an improvement is indeed statistically significant. In addition, the proposed algorithm is found to be competitive in terms of complexity and other relevant parameters.

Advanced cuttlefish optimizer-random decision forest (ACORDF) based design of fractional order PID controller for higher-order time-delay system

Purpose The purpose of this manuscript, a state feedback gain depends on the optimal design of fractional order PID controller to time-delay system is established. In established optimal design known as advanced cuttlefish optimizer and random decision forest that is combined performance of random decision forest algorithm (RDFA) and advanced cuttlefish optimizer (ACFO). Design/methodology/approach The proposed ACFO uses the concept of crossover and mutation operator depend on position upgrading to enhance its search behavior, calculational speed as well as convergence profile at basic cuttlefish optimizer. Findings Fractional order proportional-integrator-derivative (FOPID) controller, apart from as tuning parameters (kp, ki and kd) it consists of two extra tuning parameters λ and µ. In established technology, the increase of FOPID controller is adjusted to reach needed responses that demonstrated using RDFA theory as well as RDF weight matrices is probable to the help of the ACFO method. The uniqueness of the established method is to decrease the failure of the FOPID controller at greater order time delay method with the help of controller maximize restrictions. The objective of the established method is selected to consider parameters set point as well as achieved parameters of time-delay system. Originality/value In the established technique used to evade large order delays as well as reliability restrictions such as small excesses, time resolution, as well as fixed condition defect. These methods is implemented at MATLAB/Simulink platform as well as outcomes compared to various existing methods such as Ziegler-Nichols fit, curve fit, Wang method, regression and invasive weed optimization and linear-quadratic regression method.

Abstract PO-001: Deep learning-based image analysis of the histological Glasgow Microenvironment Score in patients with colorectal cancer

Abstract Background: Efforts to prognostically stratify colorectal cancer (CRC) patients using histological samples has led to the development of the Glasgow Microenvironment Score (GMS). However, the subjective nature of the GMS assessment criteria makes reproducing the score challenging. Therefore, the aim of the current study was to assess the clinical utility of an image analysis-based approach. Methods: In two cohorts of patients (a test cohort of 297 Stage II/III CRC patients from Norway and a validation cohort of 233 Stage II/III CRC patients from Scotland), one H&E section representing the deepest point of tumour invasion was assessed for Tumour Stroma Percentage (TSP) and the Klintrup-Makinen (KM) local immune grade to produce the GMS. A decision forest-based classifier was built to segment the tumour and stroma compartments, having been trained on a hand annotated subset of the test cohort. A UNET convolutional neural network was trained on the same training set as the decision forest algorithm to segment and quantify the tumour and stroma components. Each section was also annotated for the invasive margin and a manually built, threshold-based lymphocyte detection algorithm applied to quantify the local immune grade. Results: The decision forest classifier was able to stratify the test cohort patients for cancer specific survival (P = 0.009) based on the patients TSP, however failed to stratify patients from the validation cohort (P = 0.055) for TSP without retraining, therefore the deep learning approach was used for this cohort. Individually, the TSP (P = 0.001) generated from the UNET based classifier and the quantification of the local immune grade (P = 0.005), both significantly stratified validation cohort patients for survival. When the individual scores were combined into a digital version of the GMS, not only did the image analysis approach significantly stratify patient survival (P < 0.0001), it also significantly correlated with the manual scores both statistically (Chi Square = 32, P = 1.5 × 10−8) and in terms of survival estimates per patient group (GMS 0 - manual = 159 months vs digital = 159 months; GMS 1 – manual = 136 months vs digital = 139 months ; GMS2 – manual 101 months vs 97 months). To negate the need for any annotation prior to analysis, the lymphocyte detection algorithm was applied to the stroma areas determined by the UNET algorithm. This fully automated digital version of the GMS was able to stratify validation cohort patients into the 3 prognostic groups based on CSS (P < 0.001), however, GMS 0 had a lower survival estimate (automated = 148 vs annotated = 159 months). Conclusion: An H&E based image analysis approach to the GMS, on a single H&E slide, holds prognostic significance for CRC patients and correlates significantly with manual pathological assessment, making the assessment of the GMS more time efficient, reproducible, and clinically relevant. Citation Format: Christopher J. Bigley, John Waller, Alison Bigley, Karin Oien, Joanne Edwards, Antonia Roseweir. Deep learning-based image analysis of the histological Glasgow Microenvironment Score in patients with colorectal cancer [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-001.

Machine Learning Methods with Decision Forests for Parkinson’s Detection

Biomedical engineers prefer decision forests over traditional decision trees to design state-of-the-art Parkinson’s Detection Systems (PDS) on massive acoustic signal data. However, the challenges that the researchers are facing with decision forests is identifying the minimum number of decision trees required to achieve maximum detection accuracy with the lowest error rate. This article examines two recent decision forest algorithms Systematically Developed Forest (SysFor), and Decision Forest by Penalizing Attributes (ForestPA) along with the popular Random Forest to design three distinct Parkinson’s detection schemes with optimum number of decision trees. The proposed approach undertakes minimum number of decision trees to achieve maximum detection accuracy. The training and testing samples and the density of trees in the forest are kept dynamic and incremental to achieve the decision forests with maximum capability for detecting Parkinson’s Disease (PD). The incremental tree densities with dynamic training and testing of decision forests proved to be a better approach for detection of PD. The proposed approaches are examined along with other state-of-the-art classifiers including the modern deep learning techniques to observe the detection capability. The article also provides a guideline to generate ideal training and testing split of two modern acoustic datasets of Parkinson’s and control subjects donated by the Department of Neurology in Cerrahpaşa, Istanbul and Departamento de Matemáticas, Universidad de Extremadura, Cáceres, Spain. Among the three proposed detection schemes the Forest by Penalizing Attributes (ForestPA) proved to be a promising Parkinson’s disease detector with a little number of decision trees in the forest to score the highest detection accuracy of 94.12% to 95.00%.

A novel approach to build accurate and diverse decision tree forest.

Decision tree is one of the best expressive classifiers in data mining. A decision tree is popular due to its simplicity and straightforward visualization capability for all types of datasets. Decision tree forest is an ensemble of decision trees. The prediction accuracy of the decision tree forest is more than a decision tree algorithm. Constant efforts are going on to create accurate and diverse trees in the decision tree forest. In this paper, we propose Tangent Weighted Decision Tree Forest (TWDForest), which is more accurate and diverse than random forest. The strength of this technique is that it uses a more accurate and uniform tangent weighting function to create a weighted decision tree forest. It also improves performance by taking opinions from previous trees to best fit the successor tree and avoids the toggling of the root node. Due to this novel approach, the decision trees from the forest are more accurate and diverse as compared to other decision forest algorithms. Experiments of this novel method are performed on 15 well known, publicly available UCI machine learning repository datasets of various sizes. The results of the TWDForest method demonstrate that the entire forest and decision trees produced in TWDForest have high prediction accuracy of 1–7% more than existing methods. TWDForest also creates more diverse trees than other forest algorithms.

Study of Forecasting and Estimation Methodology of Oilfield Development Cost Based on Machine Learning

Due to the oil price fluctuations in recent decades, international and national oil companies have developed programs of strategically oriented development and assets optimization. Many companies have also promptly promoted opportunities for oilfield joint ventures. Therefore, a fast and accurate assessment methodology of oilfield assets, including planning and costs assessment, is expected to be proposed. Oilfield development cost assessment can be dynamically affected by a number of factors, including oilfield internal indexes and macroeconomic indexes. Based on a machine learning algorithm and combining mathematical and statistical methodology, the Microsoft Azure machine learning studio has been used for modeling the oilfield development cost. The proposed method has adopted three algorithms: a neural network, a boosted decision tree, and a decision forest. Results showed that the boosted decision tree and decision forest algorithms can achieve PFI ranking with stable training results. The results of the machine training model have been analyzed, and they showed that the permutation feature importance (PFI) model can provide reasonable scientific and technical support for oil companies and help to attain more effective and accurate estimation and prediction of oilfield assets.

Applying Artificial Intelligence for Diagnostic Classification of Korean Autism Spectrum Disorder.

ObjectiveThe primary objective of this study was to predict subgroups of autism spectrum disorder (ASD) based on the Diagnostic Statistical Manual for Mental Disorders-IV Text Revision (DSM-IV-TR) by machine learning (ML). The secondary objective was to set up a ranking of Autism Diagnostic Interview-Revised (ADI-R) diagnostic algorithm items based on ML, and to confirm whether ML can sufficiently predict the diagnosis with these minimum items. MethodsIn the first experiment, a multiclass decision forest algorithm was applied, and the diagnostic algorithm score value of 1,269 Korean ADI-R test data was used for prediction. In the second experiment, we used 539 Korean ADI-R case data (over 48 months with verbal language) to apply mutual information to rank items used in the ADI diagnostic algorithm. ResultsIn the first experiment, the results of predicting in the case of pervasive developmental disorder not otherwise specified as “ASD” were almost three times higher than predicting it as “No diagnosis.” In the second experiment, the top 10 ranking items of ADI-R were mainly related to the quality abnormality of communication. ConclusionIn conclusion, we verified the applicability of ML in diagnosis and found that the application of artificial intelligence for rapid diagnosis or screening of ASD patients may be useful.