Abstract: Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.
Abstract: This paper presents a Machine Learning (ML) approach to support Meningitis diagnosis in patients at a children’s hospital in Sao Paulo, Brazil. The aim is to use ML techniques to reduce the use of invasive procedures, such as cerebrospinal fluid (CSF) collection, as much as possible. In this study, we focus on predicting the probability of Meningitis given the results of a blood and urine laboratory tests, together with the analysis of pain or other complaints from the patient. We tested a number of different ML algorithms, including: Adaptative Boosting (AdaBoost), Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Random Forest and Support Vector Machines (SVM). Decision Tree algorithm performed best, with 94.56% and 96.18% accuracy for training and testing data, respectively. These results represent a significant aid to doctors in diagnosing Meningitis as early as possible and in preventing expensive and painful procedures on some children.
Abstract: With the widespread adoption of the Internet-connected
devices, and with the prevalence of the Internet of Things (IoT)
applications, there is an increased interest in machine learning
techniques that can provide useful and interesting services in the
smart home domain. The areas that machine learning techniques
can help advance are varied and ever-evolving. Classifying smart
home inhabitants’ Activities of Daily Living (ADLs), is one
prominent example. The ability of machine learning technique to find
meaningful spatio-temporal relations of high-dimensional data is an
important requirement as well. This paper presents a comparative
evaluation of state-of-the-art machine learning techniques to classify
ADLs in the smart home domain. Forty-two synthetic datasets and
two real-world datasets with multiple inhabitants are used to evaluate
and compare the performance of the identified machine learning
techniques. Our results show significant performance differences
between the evaluated techniques. Such as AdaBoost, Cortical
Learning Algorithm (CLA), Decision Trees, Hidden Markov Model
(HMM), Multi-layer Perceptron (MLP), Structured Perceptron and
Support Vector Machines (SVM). Overall, neural network based
techniques have shown superiority over the other tested techniques.
Abstract: Android operating system has been recognized by most application developers because of its good open-source and compatibility, which enriches the categories of applications greatly. However, it has become the target of malware attackers due to the lack of strict security supervision mechanisms, which leads to the rapid growth of malware, thus bringing serious safety hazards to users. Therefore, it is critical to detect Android malware effectively. Generally, the permissions declared in the AndroidManifest.xml can reflect the function and behavior of the application to a large extent. Since current Android system has not any restrictions to the number of permissions that an application can request, developers tend to apply more than actually needed permissions in order to ensure the successful running of the application, which results in the abuse of permissions. However, some traditional detection methods only consider the requested permissions and ignore whether it is actually used, which leads to incorrect identification of some malwares. Therefore, a machine learning detection method based on the actually used permissions combination and API calls was put forward in this paper. Meanwhile, several experiments are conducted to evaluate our methodology. The result shows that it can detect unknown malware effectively with higher true positive rate and accuracy while maintaining a low false positive rate. Consequently, the AdaboostM1 (J48) classification algorithm based on information gain feature selection algorithm has the best detection result, which can achieve an accuracy of 99.8%, a true positive rate of 99.6% and a lowest false positive rate of 0.
Abstract: This paper presents an efficient fusion algorithm for
iris images to generate stable feature for recognition in unconstrained
environment. Recently, iris recognition systems are focused on real
scenarios in our daily life without the subject’s cooperation. Under
large variation in the environment, the objective of this paper is to
combine information from multiple images of the same iris. The
result of image fusion is a new image which is more stable for further
iris recognition than each original noise iris image. A wavelet-based
approach for multi-resolution image fusion is applied in the fusion
process. The detection of the iris image is based on Adaboost
algorithm and then local binary pattern (LBP) histogram is then
applied to texture classification with the weighting scheme.
Experiment showed that the generated features from the proposed
fusion algorithm can improve the performance for verification system
through iris recognition.
Abstract: Recently GPS data is used in a lot of studies to
automatically reconstruct travel patterns for trip survey. The aim is to
minimize the use of questionnaire surveys and travel diaries so as to
reduce their negative effects. In this paper data acquired from GPS and
accelerometer embedded in smart phones is utilized to predict the
mode of transportation used by the phone carrier. For prediction,
Support Vector Machine (SVM) and Adaptive boosting (AdaBoost)
are employed. Moreover a unique method to improve the prediction
results from these algorithms is also proposed. Results suggest that the
prediction accuracy of AdaBoost after improvement is relatively better
than the rest.
Abstract: This paper presents a weighted approach to unconstrained iris recognition. In nowadays, commercial systems are usually characterized by strong acquisition constraints based on the subject’s cooperation. However, it is not always achievable for real scenarios in our daily life. Researchers have been focused on reducing these constraints and maintaining the performance of the system by new techniques at the same time. With large variation in the environment, there are two main improvements to develop the proposed iris recognition system. For solving extremely uneven lighting condition, statistic based illumination normalization is first used on eye region to increase the accuracy of iris feature. The detection of the iris image is based on Adaboost algorithm. Secondly, the weighted approach is designed by Gaussian functions according to the distance to the center of the iris. Furthermore, local binary pattern (LBP) histogram is then applied to texture classification with the weight. Experiment showed that the proposed system provided users a more flexible and feasible way to interact with the verification system through iris recognition.
Abstract: This paper presents content-based image retrieval (CBIR) frameworks with relevance feedback (RF) based on combined learning of support vector machines (SVM) and AdaBoosts. The framework incorporates only most relevant images obtained from both the learning algorithm. To speed up the system, it removes irrelevant images from the database, which are returned from SVM learner. It is the key to achieve the effective retrieval performance in terms of time and accuracy. The experimental results show that this framework had significant improvement in retrieval effectiveness, which can finally improve the retrieval performance.
Abstract: Several combinations of the preprocessing algorithms,
feature selection techniques and classifiers can be applied to the data
classification tasks. This study introduces a new accurate classifier,
the proposed classifier consist from four components: Signal-to-
Noise as a feature selection technique, support vector machine,
Bayesian neural network and AdaBoost as an ensemble algorithm.
To verify the effectiveness of the proposed classifier, seven well
known classifiers are applied to four datasets. The experiments show
that using the suggested classifier enhances the classification rates for
all datasets.
Abstract: We here propose improved version of elastic graph matching (EGM) as a face detector, called the multi-scale EGM (MS-EGM). In this improvement, Gabor wavelet-based pyramid reduces computational complexity for the feature representation often used in the conventional EGM, but preserving a critical amount of information about an image. The MS-EGM gives us higher detection performance than Viola-Jones object detection algorithm of the AdaBoost Haar-like feature cascade. We also show rapid detection speeds of the MS-EGM, comparable to the Viola-Jones method. We find fruitful benefits in the MS-EGM, in terms of topological feature representation for a face.
Abstract: Ensemble learning algorithms such as AdaBoost and
Bagging have been in active research and shown improvements in
classification results for several benchmarking data sets with mainly
decision trees as their base classifiers. In this paper we experiment to
apply these Meta learning techniques with classifiers such as random
forests, neural networks and support vector machines. The data sets
are from MAGIC, a Cherenkov telescope experiment. The task is to
classify gamma signals from overwhelmingly hadron and muon
signals representing a rare class classification problem. We compare
the individual classifiers with their ensemble counterparts and
discuss the results. WEKA a wonderful tool for machine learning has
been used for making the experiments.
Abstract: In this paper, the application of multiple Elman neural networks to time series data regression problems is studied. An ensemble of Elman networks is formed by boosting to enhance the performance of the individual networks. A modified version of the AdaBoost algorithm is employed to integrate the predictions from multiple networks. Two benchmark time series data sets, i.e., the Sunspot and Box-Jenkins gas furnace problems, are used to assess the effectiveness of the proposed system. The simulation results reveal that an ensemble of boosted Elman networks can achieve a higher degree of generalization as well as performance than that of the individual networks. The results are compared with those from other learning systems, and implications of the performance are discussed.
Abstract: We present a system that finds road boundaries and
constructs the virtual lane based on fusion data from a laser and a
monocular sensor, and detects forward vehicle position even in no lane
markers or bad environmental conditions. When the road environment
is dark or a lot of vehicles are parked on the both sides of the road, it is
difficult to detect lane and road boundary. For this reason we use
fusion of laser and vision sensor to extract road boundary to acquire
three dimensional data. We use parabolic road model to calculate road
boundaries which is based on vehicle and sensors state parameters and
construct virtual lane. And then we distinguish vehicle position in each
lane.
Abstract: Facial features are frequently used to represent local
properties of a human face image in computer vision applications. In
this paper, we present a fast algorithm that can extract the facial
features online such that they can give a satisfying representation of a
face image. It includes one step for a coarse detection of each facial
feature by AdaBoost and another one to increase the accuracy of the
found points by Active Shape Models (ASM) in the regions of interest.
The resulted facial features are evaluated by matching with artificial
face models in the applications of physiognomy. The distance measure
between the features and those in the fate models from the database is
carried out by means of the Hausdorff distance. In the experiment, the
proposed method shows the efficient performance in facial feature
extractions and online system of physiognomy.
Abstract: Several works regarding facial recognition have dealt with methods which identify isolated characteristics of the face or with templates which encompass several regions of it. In this paper a new technique which approaches the problem holistically dispensing with the need to identify geometrical characteristics or regions of the face is introduced. The characterization of a face is achieved by randomly sampling selected attributes of the pixels of its image. From this information we construct a set of data, which correspond to the values of low frequencies, gradient, entropy and another several characteristics of pixel of the image. Generating a set of “p" variables. The multivariate data set with different polynomials minimizing the data fitness error in the minimax sense (L∞ - Norm) is approximated. With the use of a Genetic Algorithm (GA) it is able to circumvent the problem of dimensionality inherent to higher degree polynomial approximations. The GA yields the degree and values of a set of coefficients of the polynomials approximating of the image of a face. By finding a family of characteristic polynomials from several variables (pixel characteristics) for each face (say Fi ) in the data base through a resampling process the system in use, is trained. A face (say F ) is recognized by finding its characteristic polynomials and using an AdaBoost Classifier from F -s polynomials to each of the Fi -s polynomials. The winner is the polynomial family closer to F -s corresponding to target face in data base.
Abstract: This paper proposes a new approach to perform the
problem of real-time face detection. The proposed method combines
primitive Haar-Like feature and variance value to construct a new
feature, so-called Variance based Haar-Like feature. Face in image
can be represented with a small quantity of features using this
new feature. We used SVM instead of AdaBoost for training and
classification. We made a database containing 5,000 face samples
and 10,000 non-face samples extracted from real images for learning
purposed. The 5,000 face samples contain many images which have
many differences of light conditions. And experiments showed that
face detection system using Variance based Haar-Like feature and
SVM can be much more efficient than face detection system using
primitive Haar-Like feature and AdaBoost. We tested our method on
two Face databases and one Non-Face database. We have obtained
96.17% of correct detection rate on YaleB face database, which is
higher 4.21% than that of using primitive Haar-Like feature and
AdaBoost.
Abstract: SoftBoost is a recently presented boosting algorithm,
which trades off the size of achieved classification margin and
generalization performance. This paper presents a performance
evaluation of SoftBoost algorithm on the generic object recognition
problem. An appearance-based generic object recognition
model is used. The evaluation experiments are performed using
a difficult object recognition benchmark. An assessment with respect
to different degrees of label noise as well as a comparison to
the well known AdaBoost algorithm is performed. The obtained
results reveal that SoftBoost is encouraged to be used in cases
when the training data is known to have a high degree of noise.
Otherwise, using Adaboost can achieve better performance.
Abstract: Traffic Management and Information Systems, which rely on a system of sensors, aim to describe in real-time traffic in urban areas using a set of parameters and estimating them. Though the state of the art focuses on data analysis, little is done in the sense of prediction. In this paper, we describe a machine learning system for traffic flow management and control for a prediction of traffic flow problem. This new algorithm is obtained by combining Random Forests algorithm into Adaboost algorithm as a weak learner. We show that our algorithm performs relatively well on real data, and enables, according to the Traffic Flow Evaluation model, to estimate and predict whether there is congestion or not at a given time on road intersections.
Abstract: Leo Breimans Random Forests (RF) is a recent
development in tree based classifiers and quickly proven to be one of
the most important algorithms in the machine learning literature. It
has shown robust and improved results of classifications on standard
data sets. Ensemble learning algorithms such as AdaBoost and
Bagging have been in active research and shown improvements in
classification results for several benchmarking data sets with mainly
decision trees as their base classifiers. In this paper we experiment to
apply these Meta learning techniques to the random forests. We
experiment the working of the ensembles of random forests on the
standard data sets available in UCI data sets. We compare the
original random forest algorithm with their ensemble counterparts
and discuss the results.
Abstract: Current systems for face recognition techniques often
use either SVM or Adaboost techniques for face detection part and use
PCA for face recognition part. In this paper, we offer a novel method
for not only a powerful face detection system based on
Six-segment-filters (SSR) and Adaboost learning algorithms but also
for a face recognition system. A new exclusive face detection
algorithm has been developed and connected with the recognition
algorithm. As a result of it, we obtained an overall high-system
performance compared with current systems. The proposed algorithm
was tested on CMU, FERET, UNIBE, MIT face databases and
significant performance has obtained.