Weighted Voting Procedure Research Articles

Ensemble of RNN Classifiers for Activity Detection Using a Smartphone and Supporting Nodes.

Nowadays, sensor-equipped mobile devices allow us to detect basic daily activities accurately. However, the accuracy of the existing activity recognition methods decreases rapidly if the set of activities is extended and includes training routines, such as squats, jumps, or arm swings. Thus, this paper proposes a model of a personal area network with a smartphone (as a main node) and supporting sensor nodes that deliver additional data to increase activity-recognition accuracy. The introduced personal area sensor network takes advantage of the information from multiple sensor nodes attached to different parts of the human body. In this scheme, nodes process their sensor readings locally with the use of recurrent neural networks (RNNs) to categorize the activities. Then, the main node collects results from supporting sensor nodes and performs a final activity recognition run based on a weighted voting procedure. In order to save energy and extend the network's lifetime, sensor nodes report their local results only for specific types of recognized activity. The presented method was evaluated during experiments with sensor nodes attached to the waist, chest, leg, and arm. The results obtained for a set of eight activities show that the proposed approach achieves higher recognition accuracy when compared with the existing methods. Based on the experimental results, the optimal configuration of the sensor nodes was determined to maximize the activity-recognition accuracy and reduce the number of transmissions from supporting sensor nodes.

Weighted voting procedure having a unique blocker

The Goods and Services Tax (GST) Council of India has a non-conventional weighted voting procedure having a primary player who is a blocker and a set of secondary players. The voting weights are not fixed and are determined based on the subset of players which participate in the voting. We introduce the notion of voting schema to formally model such a voting procedure. Individual voting games arise from a voting schema depending on the subset of secondary players who participate in the voting. We make a detailed formal study of the trade-off between the minimal sizes of winning and blocking coalitions in the voting games that can arise from a voting schema. Finally, the GST voting procedure is assessed using the theoretical results leading to suggestions for improvement.

Cardiac Arrhythmia Classification Using Boosted Decision Trees

An intelligent system for the classification of Electrocardiograph (ECG) beat signal would play an important role in the diagnosis of cardiac arrhythmias. This paper employed a recently invented C5.0 decision trees (DTs) algorithm to develop a supervised ECG beat classifier. In general, decision tree algorithms have proved remarkable ability to derive meaning from complicated or imprecise data. Accordingly, they can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computational techniques. They are nonparametric methods with no assumptions about the space distribution and the classifier structure. This study investigated the performance of the C5.0 decision tree model with boosting on the diagnosis of ECG features' dataset. Boosting process significantly improves the accuracy of a C5.0 model. The algorithm builds up multiple decision-tree models in a sequential manner; the first model is built in the standard way. Then, each of the subsequent models focuses on the misclassified samples by the preceding model. Finally, new samples are classified by ensemble these models using a weighted voting procedure to combine the separate decisions into one overall choice. The objective of this work is to classify an ECG characteristic feature vector as either normal or arrhythmia. The classification performance of boosted C5.0 DTs is evaluated and compared to the one that achieved by multilayer feed-forward neural network. Experimental results showed that the boosted C5.0 DTs model has achieved a remarkable performance that reached 99% classification accuracy on both training and testing subsets.

Robust deformable and occluded object tracking with dynamic graph.

While some efforts have been paid to handle deformation and occlusion in visual tracking, they are still great challenges. In this paper, a dynamic graph-based tracker (DGT) is proposed to address these two challenges in a unified framework. In the dynamic target graph, nodes are the target local parts encoding appearance information, and edges are the interactions between nodes encoding inner geometric structure information. This graph representation provides much more information for tracking in the presence of deformation and occlusion. The target tracking is then formulated as tracking this dynamic undirected graph, which is also a matching problem between the target graph and the candidate graph. The local parts within the candidate graph are separated from the background with Markov random field, and spectral clustering is used to solve the graph matching. The final target state is determined through a weighted voting procedure according to the reliability of part correspondence, and refined with recourse to a foreground/background segmentation. An effective online updating mechanism is proposed to update the model, allowing DGT to robustly adapt to variations of target structure. Experimental results show improved performance over several state-of-the-art trackers, in various challenging scenarios.

A recognition method based on collective decision making using systems of regularities of various types

A new recognition method that implies weighted voting on systems of “syndromes,” i.e., subregions of the attribute space where objects of one class dominate, is given. It is a modified version of statistically weighted syndromes developed previously. To find syndromes, it searches for optimal partitions within several models of different levels of complexity. Syndromes to be included in the final set used in collective decision making are selected by the criterion for the partitioning degree of classes and by the parameter related to the complexity of the partitioning model involved. The weighted voting procedure can be interpreted as the convex correction of sets of predictors. The generalizing potential of such procedures is discussed. Experimental results of comparing the given method with the previous version (SWS) and alternative techniques are presented. To estimate the efficiency, several criteria are used, including a way to analyze recognition accuracy on the totality of all possible decision rules (ROC analysis).

Bayesian Protein Secondary Structure Prediction With Near-Optimal Segmentations

Secondary structure prediction is an invaluable tool in determining the 3-D structure and function of proteins. Typically, protein secondary structure prediction methods suffer from low accuracy in beta-strand predictions, where nonlocal interactions play a significant role. There is a considerable need to model such long- range interactions that contribute to the stabilization of a protein molecule. In this paper, we introduce an alternative decoding technique for the hidden semi-Markov model (HSMM) originally employed in the BSPSS algorithm, and further developed in the IPSSP algorithm. The proposed method is based on the N-best paradigm where a set of most likely segmentations is computed. To generate suboptimal segmentations (i.e., alternative prediction sequences), we developed two N-best search algorithms. The first one is an A* stack decoder algorithm that extends paths (or hypotheses) by one symbol at each iteration. The second algorithm locally keeps the end positions of the highest scoring K previous segments and performs backtracking. Both algorithms employ the hidden semi- Markov model described in Aydin etal. [5], and use Viterbi scoring to compute the N-best list. The availability of near-optimal segmentations and the utilization of the Viterbi scoring enable the sequences to be rescored using more complex dependency models that characterize nonlocal interactions in beta-sheets. After the score update, one can either keep the segmentations to be employed in 3-D structure prediction or predict the secondary structure by applying a weighted voting procedure to a set of top scoring M ges 1 segmentations. The accuracy measures of the N-best method when used to predict the secondary structure are shown to be comparable or better than the classical Viterbi decoder (MAP estimator), tested under the single-sequence condition. When no rescoring is applied, the stack decoder algorithm with sufficiently large M improves the overall sensitivity measure (Q3) of the Viterbi algorithm by 1.1%. At the same M value, the N-best Viterbi algorithm improves the Q3 measure by 0.25% as well as the sensitivity measures specific for each secondary structure type (Qobs alpha, Qobs beta, Qobs L). When the sequences are rescored using the posterior probability distribution computed by the posterior decoding algorithm (MPM estimator), N-best Viterbi improves the Q3 measure of the Viterbi algorithm by 2.6%. The rescored N-best list approach also enables us to generate suboptimal segmentations that are valid sequences (i.e., realizable from the hidden semi-Markov model). Although the N-best algorithms and the score update procedure brought significant improvements over the Viterbi algorithm, they were not able to outperform the posterior decoding algorithm in the single-sequence condition. Further improvements in the prediction accuracy should be possible with the incorporation of sophisticated models for nonlocal interactions and other physical constraints that stabilize the overall structure of a protein.

Triangle Taste Tests: Are the Subjects who Respond Correctly Lucky or Good?

When a triangle taste test, i.e., “Which of these three stimuli is different from the other two?”, is given twice to each subject, a natural question to ask is: “Are the subjects who got both tests correct really better discriminators than the other subjects who got 0 or 1 correct?” Surprisingly enough, the answer to this question has nothing to do with the number of subjects who got both correct, i.e., the twos. Rather, it is the ratio of the ones to the zeroes that supplies the necessary information. This information on the subject's abilities to discriminate can be used to develop a weighted voting procedure for subsequent preference tests.