Binary Decision Tree Research Articles

Tourists' willingness to pay to improve sustainability and experience at destination

Consolidated tourism destinations face certain challenges derived from aspects such as new client demands, growing competition, the problems of overtourism and tourism-phobia, and the modernization of infrastructures. The creation of taxes and/or public fees that affect tourism activities is one potential option for public managers facing these difficulties. The objective of this study is to determine tourists’ willingness to pay in order to increase the income of public managers to create these types of policies. The study was carried out in Andalusia, a region of southern Spain with high rates of tourism, which received some 32.4 million tourists in 2019. A survey was conducted on 1068 tourists at the main tourism arrival points of this region. First, factors influencing the willingness and amount to be paid by each tourist were identified; for this, distinct statistical techniques were used (binary logistic regression and decision trees). Second, the sensitivity of tourism demand was analyzed with regard to the establishment of these types of taxes and public fees, concluding that tourism demand is inelastic in the face of a moderate increase in prices resulting from the creation of taxes and/or public fees. • Three out of every four tourists demonstrated their willingness to pay. • Income, budget, sex, age and education level have been determinant to the WTP. • Income and budget have the greatest association with the amount to be paid. • Tourism demand is inelastic in the face of a moderate increase in prices.

A Fully Automatic Procedure for Brain Tumor Segmentation from Multi-Spectral MRI Records Using Ensemble Learning and Atlas-Based Data Enhancement

The accurate and reliable segmentation of gliomas from magnetic resonance image (MRI) data has an important role in diagnosis, intervention planning, and monitoring the tumor’s evolution during and after therapy. Segmentation has serious anatomical obstacles like the great variety of the tumor’s location, size, shape, and appearance and the modified position of normal tissues. Other phenomena like intensity inhomogeneity and the lack of standard intensity scale in MRI data represent further difficulties. This paper proposes a fully automatic brain tumor segmentation procedure that attempts to handle all the above problems. Having its foundations on the MRI data provided by the MICCAI Brain Tumor Segmentation (BraTS) Challenges, the procedure consists of three main phases. The first pre-processing phase prepares the MRI data to be suitable for supervised classification, by attempting to fix missing data, suppressing the intensity inhomogeneity, normalizing the histogram of observed data channels, generating additional morphological, gradient-based, and Gabor-wavelet features, and optionally applying atlas-based data enhancement. The second phase accomplishes the main classification process using ensembles of binary decision trees and provides an initial, intermediary labeling for each pixel of test records. The last phase reevaluates these intermediary labels using a random forest classifier, then deploys a spatial region growing-based structural validation of suspected tumors, thus achieving a high-quality final segmentation result. The accuracy of the procedure is evaluated using the multi-spectral MRI records of the BraTS 2015 and BraTS 2019 training data sets. The procedure achieves high-quality segmentation results, characterized by average Dice similarity scores of up to 86%.

SDTR: Soft Decision Tree Regressor for Tabular Data

Deep neural networks have been proved a success in multiple fields. However, researchers still favor traditional approaches to obtain more interpretable models, such as Bayesian methods and decision trees when processing heterogeneous tabular data. Such models are hard to differentiate, thus inconvenient to be integrated into end-to-end settings. On the other hand, traditional neural networks are differentiable but perform poorly on tabular data. We propose a hierarchical differentiable neural regression model, Soft Decision Tree Regressor (SDTR). SDTR imitates a binary decision tree by a differentiable neural network and is plausible for ensemble schemes like bagging and boosting. The SDTR method was evaluated on multiple tabular-based regression tasks (YearPredictionMSD, MSLR-Web10K, Yahoo LETOR, SARCOS and Wine quality). Its performance is comparable with non-differentiable models (gradient boosting decision trees) and better than uninterpretable models (regular FCNN). On top of that, it can produce fair results with a restricted number of parameters, only using a small forest or even a single tree. We also propose an “average entropy” metric to evaluate the level of interpretability of a trained, soft decision tree neural network. This metric also helps to select proper structure and hyperparameters for such networks.

ПОПУЛЯЦИОННЫЙ АЛГОРИТМ ПОСТРОЕНИЯ ДЕРЕВА РЕШЕНИЙ МЕТОДОМ КРИСТАЛЛИЗАЦИИ РОССЫПИ АЛЬТЕРНАТИВ

In some cases, it becomes necessary to establish a correspondence between the declaredand actual value of a categorical variable on the basis of a set of object characteristics. In thiscase, there is a need for a classifier with an optimal sequence of the considered attributes with agiven value of the objective function. The target variable can be: yes, no, variety number, classnumber, etc. This paper solves the problem of constructing a classification model in the form of anoptimal sequence of the considered attributes and their values included in the route from the rootvertex to the terminal vertex with a given value of the target variable. If a classifier is requiredthat includes the possibility of alternative answers, then first, independently from each other, optimalroutes are built for each value of the target variable, and then these routes are combined("glued") into a single binary decision tree. In the algorithm for constructing a classifier based onthe method of crystallization of a placer of alternatives, each solution Qk is interpreted as an orientedroute Mk on a binary decision tree. Let us call the ordinal number of an element in the directedroute Mk the position siS={si|i=1,2,…,nA}. An element of the route Mk is the pair (xi, ui-),where xi corresponds to Ai. ui- in the route Mk is an edge outgoing from xi and corresponds to thevalue Ai chosen together with Ai. The second index of the element ui- is determined after the choiceof Ai, placed in the position sj+1 adjacent to sj. The work of the decision tree construction algorithmis based on the use of collective evolutionary memory, which is understood as informationreflecting the history of the search for a solution. The algorithm takes into account the tendency touse alternatives from the best solutions found. The peculiarities are the presence of an indirectexchange of information – stigmerges. The totality of data on alternatives and their assessmentsconstitutes a scattering of alternatives. The key points of the analysis of alternatives in the processof evolutionary collective adaptation are considered. Experimental studies have shown that thedeveloped algorithm finds solutions that are not inferior in quality, and sometimes surpass theircounterparts by an average of 3–4 %. The time complexity of the algorithm, obtained experimentally,lies within O(n2)-O(n3).

Machine Learning-Based Human Recognition Scheme Using a Doppler Radar Sensor for In-Vehicle Applications.

In this paper, we propose a Doppler spectrum-based passenger detection scheme for a CW (Continuous Wave) radar sensor in vehicle applications. First, we design two new features, referred to as an ‘extended degree of scattering points’ and a ‘different degree of scattering points’ to represent the characteristics of the non-rigid motion of a moving human in a vehicle. We also design one newly defined feature referred to as the ‘presence of vital signs’, which is related to extracting the Doppler frequency of chest movements due to breathing. Additionally, we use a BDT (Binary Decision Tree) for machine learning during the training and test steps with these three extracted features. We used a 2.45 GHz CW radar front-end module with a single receive antenna and a real-time data acquisition module. Moreover, we built a test-bed with a structure similar to that of an actual vehicle interior. With the test-bed, we measured radar signals in various scenarios. We then repeatedly assessed the classification accuracy and classification error rate using the proposed algorithm with the BDT. We found an average classification accuracy rate of 98.6% for a human with or without motion.

Brain wave classification for divergent hand movements

Brain-Computer Interface (BCI) is an emerging technology in medical diagnosis and rehabilitation. In this study, by the acquisition of Electroencephalogram (EEG) signals from 30 healthy participants who perform four different hand movements, necessary features are extracted and classified to determine their accuracies. Statistical time domain features are extracted from the mu and beta frequency band. The Event related desynchronization (ERD)/Event related synchronization (ERS) measurements are extracted, from which it was evident that both mu and beta frequency bands are more efficient in the C3 channel. By applying the Paired Samples t-test, the extracted features are analyzed and were determined to have a 95% significant level of difference between the mu and beta band, being statistically efficient in the beta band of the C3 channel. By employing different classifiers such as Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Naïve Bayesian classifier and Binary Decision Tree (BDT) algorithms on both channel’s mu and beta frequency bands, it was observed that the performance of beta frequency band classifiers shows 90% accuracy in binary class classification. In the comparative study of all these classifiers, LDA and Naïve Bayes show above 95% accuracy for binary class classification.

Study on the TB and non-TB diagnosis using two-step deep learning-based binary classifier

A deep learning-based binary classifier was proposed to diagnose tuberculosis (TB) and non-TB disease using a chest X-ray radiograph. The proposed classifier comprised two-step binary decision trees, each trained by a deep learning model with convolution neural network (CNN) based on the PyTorch frame. Normal and abnormal images of chest X-ray was classified in the first step. The abnormal images were predicted to be classified into TB and non-TB disease by the second step of the process. The accuracies of first and second step were 98% and 80% respectively. Moreover, re-training could improve the stability of prediction accuracy for images in different data groups.

PERBANDINGAN KLASIFIKASI ALGORITMA C5.0 DENGAN CLASSIFICATION AND REGRESSION TREE (STUDI KASUS : DATA SOSIAL KEPALA KELUARGA MASYARAKAT DESA TELUK BARU KECAMATAN MUARA ANCALONG TAHUN 2019)

Decision tree is a algorithm used as a reasoning procedure to get answers from problems are entered. Many methods can be used in decision trees, including the C5.0 algorithm and Classification and Regression Tree (CART). C5.0 algorithm is a non-binary decision tree where the branch of tree can be more than two, while the CART algorithm is a binary decision tree where the branch of tree consists of only two branches. This research aims to determine the classification results of the C5.0 and CART algorithms and to determine the comparison of the accuracy classification results from these two methods. The variables used in this research are the average monthly income (Y), employment (X1), number of family members (X2), last education (X3) and gender (X4). After analyzing the results obtained that the accuracy rate of C5.0 algorithm is 79,17% while the accuracy rate of CART is 84,63%. So it can be said that the CART method is a better method in classifying the average income of the people of Teluk Baru Village in Muara Ancalong District in 2019 compared to the C5.0 algorithm method.
 
 Keywords: C5.0 Algorithm, CART, Classification, Decision Tree.

Automated diagnosis of encephalitis in pediatric patients using EEG rhythms and slow biphasic complexes.

Slow biphasic complexes (SBC) have been identified in the EEG of patients suffering for inflammatory brain diseases. Their amplitude, location and frequency of appearance were found to correlate with the severity of encephalitis. Other characteristics of SBCs and of EEG traces of patients could reflect the grade of pathology. Here, EEG rhythms are investigated together with SBCs for a better characterization of encephalitis. EEGs have been acquired from pediatric patients: ten controls and ten encephalitic patients. They were split by neurologists into five classes of different severity of the pathology. The relative power of EEG rhythms was found to change significantly in EEGs labeled with different severity scores. Moreover, a significant variation was found in the last seconds before the appearance of an SBC. This information and quantitative indexes characterizing the SBCs were used to build a binary classification decision tree able to identify the classes of severity. True classification rate of the best model was 76.1% (73.5% with leave-one-out test). Moreover, the classification errors were among classes with similar severity scores (precision higher than 80% was achieved considering three instead of five classes). Our classification method may be a promising supporting tool for clinicians to diagnose, assess and make the follow-up of patients with encephalitis.

Deep Learning-Based Decision-Tree Classifier for COVID-19 Diagnosis From Chest X-ray Imaging.

The global pandemic of coronavirus disease 2019 (COVID-19) has resulted in an increased demand for testing, diagnosis, and treatment. Reverse transcription polymerase chain reaction (RT-PCR) is the definitive test for the diagnosis of COVID-19; however, chest X-ray radiography (CXR) is a fast, effective, and affordable test that identifies the possible COVID-19-related pneumonia. This study investigates the feasibility of using a deep learning-based decision-tree classifier for detecting COVID-19 from CXR images. The proposed classifier comprises three binary decision trees, each trained by a deep learning model with convolution neural network based on the PyTorch frame. The first decision tree classifies the CXR images as normal or abnormal. The second tree identifies the abnormal images that contain signs of tuberculosis, whereas the third does the same for COVID-19. The accuracies of the first and second decision trees are 98 and 80%, respectively, whereas the average accuracy of the third decision tree is 95%. The proposed deep learning-based decision-tree classifier may be used in pre-screening patients to conduct triage and fast-track decision making before RT-PCR results are available.

Reliability evaluation of integrated detritiation system for fusion reactors based on DBDT approach

Integrated detritiation system (IDS) would play a key role in controlling the tritium release and atmosphere cleanup under accident scenarios in fusion reactors, and thus it is very significant to evaluate and ensure its reliability. Up to now, many conceptual designs for IDS have been developed worldwide, yet few are focused on its reliability studies. Due to complex redundant designs and functional dependence, this system has notable temporal failure behaviors that traditional static fault trees (SFT) are unavailable to capture and evaluate. In this contribution, motivated to understand the effect of temporal failure behaviors on reliability of IDS, dynamic fault trees (DFT) are first to be adopted to study its reliability through using dynamic binary decision tree (DBDT) approach. The results show the reliability indexes for IDS calculated by DFTs are one to two times lower than those obtained by traditional SFT, which means some overly conservative reliability requirements on IDS could be relaxed. The results also demonstrate that the DFT-based reliability evaluation method would be of great help for the fusion energy system’s optimization design in the future.

A linear multivariate binary decision tree classifier based on K-means splitting

A novel linear multivariate decision tree classifier, Binary Decision Tree based on K-means Splitting (BDTKS), is presented in this paper. The unsupervised K-means clustering is recursively integrated into the binary tree, building a hierarchical classifier. The introduction of the unsupervised K-means clustering provides the powerful generalization ability for the resulting BDTKS model. Then, the good generalization ability of BDTKS ensures the classification performance. A novel non-split condition with an easy-setting hyperparameter which focuses more on minority classes of the current node is proposed and applied in the BDTKS model, avoiding ignoring the minority classes in the class imbalance cases. Furthermore, the K-means centroid based BDTKS model is converted into the hyperplane based decision tree, speeding up the process of classification. Extensive experiments on the publicly available data sets have demonstrated that the proposed BDTKS matches or outperforms the previous decision trees.

Quantitative Structure-Property Relationship (QSPR) models for Minimum Ignition Energy (MIE) prediction of combustible dusts using machine learning

Quantitative Structure-Property Relationship (QSPR) classification models for Minimum Ignition Energy (MIE) classification of 65 combustible dusts have been developed using machine learning algorithms Random Forests (RF) and Decision Trees (DT). Combustible dusts were categorized based on their MIE values: dusts having MIE > 10 mJ and dusts having MIE < 10 mJ. In this work, an important macroscopic property, dust median diameter (d50) was also used as one of the parameters along with the molecular descriptors for model development. The machine learning Random Forest (RF) algorithm was used for identification of the 13 molecular descriptors having maximum effect on MIE prediction accuracy. Thereafter, these descriptors were used as input parameters to develop binary classification Random Forest (RF) and Decision Tree (DT) models. The RF and DT algorithms displayed good MIE category predictability validated through the test set Receiver Operating Characteristic- Area Under Curve (ROC-AUC) of 0.95 for both the models. Thus, this work has displayed that Random Forests can be used as an important tool for descriptor reduction in QSPR studies and can prove to be a valuable resource for MIE category prediction.

МЕТОД ЗБЕРІГАННЯ ДАНИХ РЕКОМЕНДАЦІЙНОЇ СИСТЕМИ НА ОСНОВІ БІНАРНИХ ДІАГРАМ РІШЕНЬ

Стаття присвячена дослідженню методів збереження даних рекомендаційних систем. Запропоновано та досліджено використання бінарних діаграм рішень для збереження таких даних. Внаслідок великого розміру рекомендаційних систем суттєвими є обмеження по оперативній пам'яті. Метою роботи є розробка методу зберігання даних рекомендаційної системи у формі бінарних діаграм рішень та порівняння з методами збереження на основі інших структур даних. Дані рекомендаційної системи зберігаються у вигляді графу із вершинами, які представляють користувачів системи та об'єкти системи, а ребра – дії користувачів системи, відношення подібності, зв'язки рекомендацій тощо. Для підвищення ефективності у випадку інтенсивного редагування графу запропоновано збереження даних на основі “гарячого” (хеш-таблиця) та “холодного” (бінарна діаграма рішень) сховищ.Проведено серію експериментів для перевірки ефективності розробленого способу зберігання даних, для чого розроблено програмну модель спрощеної рекомендаційної системи та описано алгоритм роботи такої системи. В чисельному експерименті пропонований спосіб зберігання даних на основі бінарних дерев рішень порівнюється із трьома іншими: на основі бітових масивів, зв'язних списків та хеш-таблиць. Розглянуто переваги та недоліки реалізації кожного із вказаних методів. В ході експерименту для різних значень кількості агентів, предметів, сесій та вподобань досліджено максимальні та мінімальні значення використаної оперативної пам'яті, а також час генерації лайків, сесій та рекомендацій. Встановлено, що у випадку застосування бінарних діаграм рішень обсяг використаної оперативної пам’яті є нижчим за інші способи при меншій швидкодії, що частково може бути компенсовано декількома застосованими оптимізаціями. Завдяки меншому використанню оперативної пам'яті можна зберігати інформацію про більшу кількість вподобань, що може виявитися корисним у випадку великих розмірів графу рекомендаційної системи. Можливість для бінарних діаграм рішень пошуку даних за частковими ключами додатково дозволяє зберігати дані більшої розмірності

Soil water drives distribution of northern boreal conifers Picea abies and Pinus sylvestris

Considering the climate change the role of edaphic drivers for the distribution of cold-hardy conifers, Norway spruce (Picea abies (L.) Karst.), and Scots pine (Pinus sylvestris L.) is crucial. Even though both species reach latitude 70oN, P. abies forest line is located at exceptionally lower latitudes in Fennoscandia compared to P. sylvestris tree line. Hence the divergence in mafic (basic) and felsic (acidic) lithologies and thereby physicochemical properties of parent glacial tills may play a critical role in tree species distributions. The objective of this study was to explore soil water content (SWC) and nutrient regimes in Finnish Lapland by transecting the main lithological units; mafic Central Lapland Greenstone Belt (CLGB) in the south and felsic Lapland Granulite Belt (LGB) in the north. Eight one ha in size plots were sampled at 10 m intervals for soil chemistry and texture and measured for SWC, gamma-ray, electrical conductivity, temperature and matric potential. In binary decision tree (DT) analysis, soil physics explained the growth sites of P. abies and P. sylvestris with 97% accuracy, the most important variable being SWC. The constraint for P. sylvestris was SWC > 0.24 m3m−3. Based to the soil chemistry DT, 95.4% of the P. abies and P. sylvestris growth sites were correctly classified. The most important variables were Cr, Ti, Mn and P. Distribution of conifers follows lithology, such that P. abies occupies mesic-wet tills derived from ultramafic and mafic rocks of the CLGB, whereas P. sylvestris thrives only on dry and coarse-textured, often granitoid tills. We argue that dry and nutrient-poor tills of felsic garnet gneisses of the LGB constitute a dispersal barrier for P. abies. The above tree species specific constraints provide guidance for future dispersal models.

Improvement of electrocardiographic diagnostic accuracy of left ventricular hypertrophy using a Machine Learning approach.

The electrocardiogram (ECG) is the most common tool used to predict left ventricular hypertrophy (LVH). However, it is limited by its low accuracy (<60%) and sensitivity (30%). We set forth the hypothesis that the Machine Learning (ML) C5.0 algorithm could optimize the ECG in the prediction of LVH by echocardiography (Echo) while also establishing ECG-LVH phenotypes. We used Echo as the standard diagnostic tool to detect LVH and measured the ECG abnormalities found in Echo-LVH. We included 432 patients (power = 99%). Of these, 202 patients (46.7%) had Echo-LVH and 240 (55.6%) were males. We included a wide range of ventricular masses and Echo-LVH severities which were classified as mild (n = 77, 38.1%), moderate (n = 50, 24.7%) and severe (n = 75, 37.1%). Data was divided into a training/testing set (80%/20%) and we applied logistic regression analysis on the ECG measurements. The logistic regression model with the best ability to identify Echo-LVH was introduced into the C5.0 ML algorithm. We created multiple decision trees and selected the tree with the highest performance. The resultant five-level binary decision tree used only six predictive variables and had an accuracy of 71.4% (95%CI, 65.5–80.2), a sensitivity of 79.6%, specificity of 53%, positive predictive value of 66.6% and a negative predictive value of 69.3%. Internal validation reached a mean accuracy of 71.4% (64.4–78.5). Our results were reproduced in a second validation group and a similar diagnostic accuracy was obtained, 73.3% (95%CI, 65.5–80.2), sensitivity (81.6%), specificity (69.3%), positive predictive value (56.3%) and negative predictive value (88.6%). We calculated the Romhilt-Estes multilevel score and compared it to our model. The accuracy of the Romhilt-Estes system had an accuracy of 61.3% (CI95%, 56.5–65.9), a sensitivity of 23.2% and a specificity of 94.8% with similar results in the external validation group. In conclusion, the C5.0 ML algorithm surpassed the accuracy of current ECG criteria in the detection of Echo-LVH. Our new criteria hinge on ECG abnormalities that identify high-risk patients and provide some insight on electrogenesis in Echo-LVH.

An analysis of boosted ensembles of binary fuzzy decision trees

Classification is a functionality that plays a central role in the development of modern expert systems, across a wide variety of application fields: using accurate, efficient, and compact classification models is often a prime requirement. Boosting (and AdaBoost in particular) is a well-known technique to obtain robust classifiers from properly-learned weak classifiers, thus it is particularly attracting in many practical settings. Although the use of traditional classifiers as base learners in AdaBoost has already been widely studied, the adoption of fuzzy weak learners still requires further investigations. In this paper we describe FDT-Boost, a boosting approach shaped according to the SAMME-AdaBoost scheme, which leverages fuzzy binary decision trees as multi-class base classifiers. Such trees are kept compact by constraining their depth, without lowering the classification accuracy. The experimental evaluation of FDT-Boost has been carried out using a benchmark containing eighteen classification datasets. Comparing our approach with FURIA, one of the most popular fuzzy classifiers, with a fuzzy binary decision tree, and with a fuzzy multi-way decision tree, we show that FDT-Boost is accurate, getting to results that are statistically better than those achieved by the other approaches. Moreover, compared to a crisp SAMME-AdaBoost implementation, FDT-Boost shows similar performances, but the relative produced models are significantly less complex, thus opening up further exploitation chances also in memory-constrained systems.

Demographic-Dependent Risk of Developing Novel Psychiatric Disorders Following Concussion

Importance: Current guidelines for patients who have experienced a concussion or mild traumatic brain injury (mTBI) often focus on conservative care and observation. However, mTBI may increase the risk of novel psychiatric disorders (NPDs) within 180 days, and long-term management of mTBI should include psychiatric evaluation for high-risk populations. Objective: To investigate the association between NPDs and mTBI. Design, Setting, and Participants: This retrospective cohort analysis was conducted using 8-years of the National Readmission Database. All individuals who were admitted for a diagnosis of concussion and were readmitted within 180 days following discharge were queried; patients without complete follow-up were excluded. This cohort was then subdivided based on age (by quartile), sex, and whether the individual experienced loss of consciousness (LOC) to control for demographic-dependent confounding. Analysis was conducted for the total and subdivided cohorts, and the results were used to develop a binary decision tree to provide recommendations for high-risk patient populations. Main Outcomes and Measures: Development of NPDs within 180 days, including: depression, anxiety, suicidal ideation, and homicidal ideation. All psychiatric disorders were identified using International Classification of Diseases, Ninth Revision (ICD-9) and International Classification of Diseases, Tenth Revision (ICD-10) codes. Results: Analysis was conducted with a cohort of 12,080 patients (mean age: 59.5±21.6; 49.8% female) who were admitted initially for concussion. Males and females with LOC had higher rates of depression in all age quartiles within 180 days (p<0.05 for all). Females in the first two age quartiles with LOC also had an increased rate of suicidal ideation (p<0.01 for all), and those older than 25 years had increased rates of anxiety upon readmission within 180 days (p<0.005 for all). Males younger than 75 with LOC and significantly increased rates of suicidal ideation (p<0.002 for all) and those in the second and fourth quartile for age had increased rates of anxiety at readmission (p<0.05 for all). Males in the first, second, and fourth age quartile without LOC had significantly increased rates of depression (p<0.005 for all), with men in the second quartile also at higher risk of developing anxiety at readmission (p<0.05). Females without LOC showed the fewest number of NPDs within 180 days, with those below 25 years of age having significantly higher rates of anxiety (p<0.05) and those above 75 years of age having significantly higher rates of suicidal ideation at readmission (p<0.05). Conclusions and Relevance: Our findings suggest that concussion may be associated with an increased rate of NPDs within the first 6 months following discharge. We use this data to develop recommendations for psychiatric screening of high-risk patient populations. Other factors may contribute towards the development of NPDs, and further research is necessary to understand the associations between mild traumatic brain injury and psychiatric illness. Funding Statement: There are no disclosures of funding for this study. Declaration of Interests: Chan: receives non-study related research support from Orthofix, Inc.

Doppler-Spectrum Feature-Based Human-Vehicle Classification Scheme Using Machine Learning for an FMCW Radar Sensor.

In this paper, we propose a Doppler-spectrum feature-based human–vehicle classification scheme for an FMCW (frequency-modulated continuous wave) radar sensor. We introduce three novel features referred to as the scattering point count, scattering point difference, and magnitude difference rate features based on the characteristics of the Doppler spectrum in two successive frames. We also use an SVM (support vector machine) and BDT (binary decision tree) for training and validation of the three aforementioned features. We measured the signals using a 24-GHz FMCW radar front-end module and a real-time data acquisition module and extracted three features from a walking human and a moving vehicle in the field. We then repeatedly measured the classification decision rate of the proposed algorithm using the SVM and BDT, finding that the average performance exceeded 99% and 96% for the walking human and the moving vehicle, respectively.

Representing probabilistic models of knowledge space theory by multinomial processing tree models

Knowledge Space Theory (KST) aims at modeling the hierarchical relations between items or skills in a learning process. For example, when studying mathematics in school, students first need to master the rules of summation before being able to learn multiplication. In KST, the knowledge states of individuals are represented by means of partially ordered latent classes. In probabilistic KST models, conditional probability parameters are introduced to model transitions from latent knowledge states to observed response patterns. Since these models account for discrete data by assuming a finite number of latent states, they can be represented by Multinomial Processing Tree (MPT) models (i.e., binary decision trees with parameters referring to the conditional probabilities of entering different states). We prove that standard probabilistic models of KST such as the Basic Local Independence Model (BLIM) and the Simple Learning Model (SLM) can be represented as specific instances of MPT models. Given this close link, MPT methods may be applied to address theoretical and practical issues in KST. By highlighting the MPT–KST link and its implications for modeling violations of local stochastic independence in Item Response Theory (IRT), we hope to facilitate an exchange of theoretical results, statistical methods, and software across these different domains of mathematical psychology and psychometrics.