Andreu Català

K-SVCR. A support vector machine for multi-class classification

Abstract The problem of multi-class classification is usually solved by a decomposing and reconstruction procedure when two-class decision machines are implied. During the decomposing phase, training data are partitioned into two classes in several manners and two-class learning machines are trained. To assign the class for a new entry, machines’ outputs are evaluated in a specific pulling scheme. This article introduces the “Support Vector Classification-Regression” machine for K -class classification purposes ( K -SVCR), a new training algorithm with ternary outputs {−1,0,+1} based on Vapniks Support Vector theory. This new machine evaluates all the training data into a 1-versus-1-versus-rest structure during the decomposing phase by using a mixed classification and regression SV Machine (SVM) formulation. For the reconstruction, a specific pulling scheme considering positive and negative votes has been designed, making the overall learning architecture more fault-tolerant as it will be demonstrated.

A wearable inertial measurement unit for long-term monitoring in the dependency care area

Human movement analysis is a field of wide interest since it enables the assessment of a large variety of variables related to quality of life. Human movement can be accurately evaluated through Inertial Measurement Units (IMU), which are wearable and comfortable devices with long battery life. The IMUs movement signals might be, on the one hand, stored in a digital support, in which an analysis is performed a posteriori. On the other hand, the signal analysis might take place in the same IMU at the same time as the signal acquisition through online classifiers. The new sensor system presented in this paper is designed for both collecting movement signals and analyzing them in real-time. This system is a flexible platform useful for collecting data via a triaxial accelerometer, a gyroscope and a magnetometer, with the possibility to incorporate other information sources in real-time. A μSD card can store all inertial data and a Bluetooth module is able to send information to other external devices and receive data from other sources. The system presented is being used in the real-time detection and analysis of Parkinsons disease symptoms, in gait analysis, and in a fall detection system.

Rule-Based Learning Systems for Support Vector Machines

In this article, we propose some methods for deriving symbolic interpretation of data in the form of rule based learning systems by using Support Vector Machines (SVM). First, Radial Basis Function Neural Networks (RBFNN) learning techniques are explored, as is usual in the literature, since the local nature of this paradigm makes it a suitable platform for performing rule extraction. By using support vectors from a learned SVM it is possible in our approach to use any standard Radial Basis Function (RBF) learning technique for the rule extraction, whilst avoiding the overlapping between classes problem. We will show that merging node centers and support vectors explanation rules can be obtained in the form of ellipsoids and hyper-rectangles. Next, in a dual form, following the framework developed for RBFNN, we construct an algorithm for SVM. Taking SVM as the main paradigm, geometry in the input space is defined from a combination of support vectors and prototype vectors obtained from any clustering algorithm. Finally, randomness associated with clustering algorithms or RBF learning is avoided by using only a learned SVM to define the geometry of the studied region. The results obtained from a certain number of experiments on benchmarks in different domains are also given, leading to a conclusion on the viability of our proposal.

Home detection of freezing of gait using support vector machines through a single waist-worn triaxial accelerometer

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy.

Position and orientation tracking in a ubiquitous monitoring system for Parkinson disease patients with freezing of gait symptom

Background Freezing of gait (FoG) is one of the most disturbing and least understood symptoms in Parkinson disease (PD). Although the majority of existing assistive systems assume accurate detections of FoG episodes, the detection itself is still an open problem. The specificity of FoG is its dependency on the context of a patient, such as the current location or activity. Knowing the patients context might improve FoG detection. One of the main technical challenges that needs to be solved in order to start using contextual information for FoG detection is accurate estimation of the patients position and orientation toward key elements of his or her indoor environment. Objective The objectives of this paper are to (1) present the concept of the monitoring system, based on wearable and ambient sensors, which is designed to detect FoG using the spatial context of the user, (2) establish a set of requirements for the application of position and orientation tracking in FoG detection, (3) evaluate the accuracy of the position estimation for the tracking system, and (4) evaluate two different methods for human orientation estimation. Methods We developed a prototype system to localize humans and track their orientation, as an important prerequisite for a context-based FoG monitoring system. To setup the system for experiments with real PD patients, the accuracy of the position and orientation tracking was assessed under laboratory conditions in 12 participants. To collect the data, the participants were asked to wear a smartphone, with and without known orientation around the waist, while walking over a predefined path in the marked area captured by two Kinect cameras with non-overlapping fields of view. Results We used the root mean square error (RMSE) as the main performance measure. The vision based position tracking algorithm achieved RMSE = 0.16 m in position estimation for upright standing people. The experimental results for the proposed human orientation estimation methods demonstrated the adaptivity and robustness to changes in the smartphone attachment position, when the fusion of both vision and inertial information was used. Conclusions The system achieves satisfactory accuracy on indoor position tracking for the use in the FoG detection application with spatial context. The combination of inertial and vision information has the potential for correct patient heading estimation even when the inertial wearable sensor device is put into an a priori unknown position.

Validation of a Portable Device for Mapping Motor and Gait Disturbances in Parkinson’s Disease

Background Patients with severe idiopathic Parkinson’s disease experience motor fluctuations, which are often difficult to control. Accurate mapping of such motor fluctuations could help improve patients’ treatment. Objective The objective of the study was to focus on developing and validating an automatic detector of motor fluctuations. The device is small, wearable, and detects the motor phase while the patients walk in their daily activities. Methods Algorithms for detection of motor fluctuations were developed on the basis of experimental data from 20 patients who were asked to wear the detector while performing different daily life activities, both in controlled (laboratory) and noncontrolled environments. Patients with motor fluctuations completed the experimental protocol twice: (1) once in the ON, and (2) once in the OFF phase. The validity of the algorithms was tested on 15 different patients who were asked to wear the detector for several hours while performing daily activities in their habitual environments. In order to assess the validity of detector measurements, the results of the algorithms were compared with data collected by trained observers who were accompanying the patients all the time. Results The motor fluctuation detector showed a mean sensitivity of 0.96 (median 1; interquartile range, IQR, 0.93-1) and specificity of 0.94 (median 0.96; IQR, 0.90-1). Conclusions ON/OFF motor fluctuations in Parkinsons patients can be detected with a single sensor, which can be worn in everyday life.

K-SVCR. A Multi-class Support Vector Machine

Support Vector Machines for pattern recognition are addressed to binary classification problems. The problem of multi-class classification is typically solved by the combination of 2-class decision functions using voting scheme methods or decison trees. We present a new multi-class classification SVM for the separable case, called K-SVCR. Learning machines operating in a kernel-induced feature space are constructed assigning output +1 or -1 if training patterns belongs to the classes to be separated, and assigning output 0 if patterns have a different label to the formers. This formulation of multi-class classification problem ever assigns a meaningful answer to every input and its architecture is more fault-tolerant than standard methods one.

Support vector machines with symbolic interpretation

In this work, a procedure for rule extraction from support vector machines (SVMs) is proposed. Our method first determines the prototype vectors by using k-means. Then, these vectors are combined with the support vectors using geometric methods to define ellipsoids in the input space, which are later translated to if-then rules. In this way, it is possible to give an interpretation to the knowledge acquired by the SVM. On the other hand, the extracted rules render possible the integration of SVMs with symbolic AI systems.

Basketball Activity Recognition using Wearable Inertial Measurement Units

The analysis and evaluation of human movement is a growing research area within the field of sports monitoring. This analysis can help support the enhancement of an athletes performance, the prediction of injuries or the optimization of training programs. Although camera-based techniques are often used to evaluate human movements, not all movements of interest can be analyzed or distinguished effectively with computer vision only. Wearable inertial systems are a promising technology to address this limitation. This paper presents a new wearable sensing system to record human movements for sports monitoring. A new paradigm is presented with the purpose of monitoring basketball players with multiple inertial measurement units. A data collection plan has been designed and implemented, and experimental results show the potential of the system in basketball activity recognition.

Advances in Artificial Neural Networks and Computational Intelligence

IWANN is a biennial conference that seeks to provide a discussion forum for scientists, engineers, educators and students about the latest ideas and realizations in the foundations, theory, models and applications of hybrid systems inspired on nature (neural networks, fuzzy logic and evolutionary systems) as well as in emerging areas related to the above items. As in previous editions of IWANN, it also aims to create a friendly environment that could lead to the establishment of scientific collaborations and exchanges among attendees. Since the first edition in Granada (LNCS 540, 1991), the conference has evolved and matured, and most of the topics involved have achieved a maturity and reinforced consolidation. The twelveth edition of the IWANN conference “International Work-Conference on Artificial Neural Networks” was held in Puerto de la Cruz, Tenerife, (Spain) during June 12–14, 2013. The list of topics in the successive Call for Papers has also evolved, resulting in the following list for the present edition: