Abstract: Human motion recognition has been extensively increased in recent years due to its importance in a wide range of applications, such as human-computer interaction, intelligent surveillance, augmented reality, content-based video compression and retrieval, etc. However, it is still regarded as a challenging task especially in realistic scenarios. It can be seen as a general machine learning problem which requires an effective human motion representation and an efficient learning method. In this work, we introduce a descriptor based on Laban Movement Analysis technique, a formal and universal language for human movement, to capture both quantitative and qualitative aspects of movement. We use Discrete Hidden Markov Model (DHMM) for training and classification motions. We improve the classification algorithm by proposing two DHMMs for each motion class to process the motion sequence in two different directions, forward and backward. Such modification allows avoiding the misclassification that can happen when recognizing similar motions. Two experiments are conducted. In the first one, we evaluate our method on a public dataset, the Microsoft Research Cambridge-12 Kinect gesture data set (MSRC-12) which is a widely used dataset for evaluating action/gesture recognition methods. In the second experiment, we build a dataset composed of 10 gestures(Introduce yourself, waving, Dance, move, turn left, turn right, stop, sit down, increase velocity, decrease velocity) performed by 20 persons. The evaluation of the system includes testing the efficiency of our descriptor vector based on LMA with basic DHMM method and comparing the recognition results of the modified DHMM with the original one. Experiment results demonstrate that our method outperforms most of existing methods that used the MSRC-12 dataset, and a near perfect classification rate in our dataset.
Abstract: A Markov model defines a system of states, composed
by the feasible transition paths between those states, and the
parameters of those transitions. The paths and parameters may be
a representative way to address healthcare issues, such as to identify
the most likely sequence of patient health states given the sequence
of observations. Furthermore estimating the length of stay (LoS) of
patients in hospitalization is one of the challenges that Markov models
allow us to solve. However, finding the maximum probability of
any path that gets to state at time t, can have high computational
cost. A quantum approach allows us to take advantage of quantum
computation since the calculated probabilities can be in several states,
ending up to outperform classical computing due to the possible
superposition of states when handling large amounts of data. The
aid of quantum physics-based architectures and machine learning
techniques are therefore appropriated to address the complexity of
healthcare.
Abstract: Speech disfluencies are common in spontaneous speech. The primary purpose of this study was to distinguish linguistic disfluencies from stuttering disfluencies in bilingual Tamil–English (TE) speaking children. The secondary purpose was to determine whether their disfluencies are mediated by native language dominance and/or on an early onset of developmental stuttering at childhood. A detailed study was carried out to identify the prosodic and acoustic features that uniquely represent the disfluent regions of speech. This paper focuses on statistical modeling of repetitions, prolongations, pauses and interjections in the speech corpus encompassing bilingual spontaneous utterances from school going children – English and Tamil. Two classifiers including Hidden Markov Models (HMM) and the Multilayer Perceptron (MLP), which is a class of feed-forward artificial neural network, were compared in the classification of disfluencies. The results of the classifiers document the patterns of disfluency in spontaneous speech samples of school-aged children to distinguish between Children Who Stutter (CWS) and Children with Language Impairment CLI). The ability of the models in classifying the disfluencies was measured in terms of F-measure, Recall, and Precision.
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: With global aging, people who require care, such as people with dementia (PwD), are increasing within many developed countries. And PwDs may wander and unconsciously set foot outdoors, it may lead serious accidents, such as, traffic accidents. Here, round-the-clock monitoring by caregivers is necessary, which can be a burden for the caregivers. Therefore, an automatic wandering detection system is required when an elderly person wanders outdoors, in which case the detection system transmits a ‘moving’ followed by an ‘absence’ state. In this paper, we focus on the transition from the ‘resting’ to the ‘absence’ state, via the ‘moving’ state as one of the wandering transitions. To capture the transition of the three states, our method based on the hidden Markov model (HMM) is built. Using our method, the restraint where the ‘resting’ state and ‘absence’ state cannot be transmitted to each other is applied. To validate our method, we conducted the experiment with 10 subjects. Our results show that the method can classify three states with 0.92 accuracy.
Abstract: The Internet of Things (IoT) was designed for widespread convenience. With the smart tag and the sensing network, a large quantity of dynamic information is immediately presented in the IoT. Through the internal communication and interaction, meaningful objects provide real-time services for users. Therefore, the service with appropriate decision-making has become an essential issue. Based on the science of human behavior, this study employed the environment model to record the time sequences and locations of different behaviors and adopted the probability module of the hierarchical Hidden Markov Model for the inference. The statistical analysis was conducted to achieve the following objectives: First, define user behaviors and predict the user behavior routes with the environment model to analyze user purposes. Second, construct the hierarchical Hidden Markov Model according to the logic framework, and establish the sequential intensity among behaviors to get acquainted with the use and activity fabric of the intelligent environment. Third, establish the intensity of the relation between the probability of objects’ being used and the objects. The indicator can describe the possible limitations of the mechanism. As the process is recorded in the information of the system created in this study, these data can be reused to adjust the procedure of intelligent design services.
Abstract: Part of Speech Tagging has always been a challenging task in the era of Natural Language Processing. This article presents POS tagging for Nepali text using Hidden Markov Model and Viterbi algorithm. From the Nepali text, annotated corpus training and testing data set are randomly separated. Both methods are employed on the data sets. Viterbi algorithm is found to be computationally faster and accurate as compared to HMM. The accuracy of 95.43% is achieved using Viterbi algorithm. Error analysis where the mismatches took place is elaborately discussed.
Abstract: Hidden Markov Model (HMM) has been used in prediction and determination of states that generate different neural activations as well as mental working conditions. This paper addresses two applications of HMM; one to determine the optimal sequence of states for two neural states: Active (AC) and Inactive (IA) for the three emission (observations) which are for No Working (NW), Waiting (WT) and Working (W) conditions of human beings. Another is for the determination of optimal sequence of intentionality i.e. Believe (B), Desire (D), and Intention (I) as the states and three observational sequences: NW, WT and W. The computational results are encouraging and useful.
Abstract: In this paper, we present an optimization technique or
a learning algorithm using the hybrid architecture by combining the
most popular sequence recognition models such as Recurrent Neural
Networks (RNNs) and Hidden Markov models (HMMs). In order to
improve the sequence/pattern recognition/classification performance
by applying a hybrid/neural symbolic approach, a gradient descent
learning algorithm is developed using the Real Time Recurrent
Learning of Recurrent Neural Network for processing the knowledge
represented in trained Hidden Markov Models. The developed hybrid
algorithm is implemented on automata theory as a sample test beds
and the performance of the designed algorithm is demonstrated and
evaluated on learning the deterministic finite state automata.
Abstract: This research study aims to present a retrospective
study about speech recognition systems and artificial intelligence.
Speech recognition has become one of the widely used technologies,
as it offers great opportunity to interact and communicate with
automated machines. Precisely, it can be affirmed that speech
recognition facilitates its users and helps them to perform their daily
routine tasks, in a more convenient and effective manner. This
research intends to present the illustration of recent technological
advancements, which are associated with artificial intelligence.
Recent researches have revealed the fact that speech recognition is
found to be the utmost issue, which affects the decoding of speech. In
order to overcome these issues, different statistical models were
developed by the researchers. Some of the most prominent statistical
models include acoustic model (AM), language model (LM), lexicon
model, and hidden Markov models (HMM). The research will help in
understanding all of these statistical models of speech recognition.
Researchers have also formulated different decoding methods, which
are being utilized for realistic decoding tasks and constrained
artificial languages. These decoding methods include pattern
recognition, acoustic phonetic, and artificial intelligence. It has been
recognized that artificial intelligence is the most efficient and reliable
methods, which are being used in speech recognition.
Abstract: In this paper, we present a new maintenance model
for a partially observable system subject to two failure modes,
namely a catastrophic failure and a failure due to the system
degradation. The system is subject to condition monitoring and the
degradation process is described by a hidden Markov model. A
cost-optimal Bayesian control policy is developed for maintaining
the system. The control problem is formulated in the semi-Markov
decision process framework. An effective computational algorithm is
developed, illustrated by a numerical example.
Abstract: In this paper, we investigate the residual life prediction
problem for a partially observable system subject to two failure
modes, namely a catastrophic failure and a failure due to the system
degradation. The system is subject to condition monitoring and the
degradation process is described by a hidden Markov model with
unknown parameters. The parameter estimation procedure based on
an EM algorithm is developed and the formulas for the conditional
reliability function and the mean residual life are derived, illustrated
by a numerical example.
Abstract: This paper proposes a hierarchical hidden Markov model (HHMM) to model the detection of M vehicles in a wireless sensor network (WSN). The HHMM model contains an extra level of hidden Markov model to model the temporal transitions of each
state of the first HMM. By modeling the temporal transitions, only those hypothesis with nonzero transition probabilities needs to be tested. Thus, this method efficiently reduces the computation load, which is preferable in WSN applications.This paper integrates several techniques to optimize the detection performance. The output of the states of the first HMM is modeled as Gaussian Mixture Model (GMM), where the number of states and the number of Gaussians are experimentally determined, while the other parameters are estimated using Expectation Maximization (EM). HHMM is used to model the sequence of the local decisions which are based on multiple hypothesis testing with maximum likelihood approach. The states in the HHMM represent various combinations of vehicles of different types. Due to the statistical advantages of multisensor data fusion, we propose a heuristic based on fuzzy weighted majority voting to enhance cooperative classification of moving vehicles within a region that is monitored by a wireless sensor network. A fuzzy inference system weighs each local decision based on the signal to noise
ratio of the acoustic signal for target detection and the signal to noise ratio of the radio signal for sensor communication. The spatial correlation among the observations of neighboring sensor nodes is efficiently utilized as well as the temporal correlation. Simulation results demonstrate the efficiency of this scheme.
Abstract: Many approaches to pattern recognition are founded on probability theory, and can be broadly characterized as either generative
or discriminative according to whether or not the distribution of the image features. Generative and discriminative models have
very different characteristics, as well as complementary strengths and weaknesses. In this paper, we study these models to recognize the patterns of alphabet characters (A-Z) and numbers (0-9). To handle isolated pattern, generative model as Hidden Markov Model (HMM) and discriminative models like Conditional Random Field (CRF), Hidden Conditional Random Field (HCRF) and Latent-Dynamic Conditional Random Field (LDCRF) with different number of window size are applied on extracted pattern features. The gesture recognition rate is improved initially as the window size increase, but degrades as window size increase further. Experimental results show that the LDCRF is the best in terms of results than CRF, HCRF and HMM at window size equal 4. Additionally, our results show that; an overall recognition rates are 91.52%, 95.28%, 96.94% and 98.05% for CRF,
HCRF, HMM and LDCRF respectively.
Abstract: In this paper, an extreme learning machine with an automatic segmentation algorithm is applied to heart disorder classification by heart sound signals. From continuous heart sound signals, the starting points of the first (S1) and the second heart pulses (S2) are extracted and corrected by utilizing an inter-pulse histogram. From the corrected pulse positions, a single period of heart sound signals is extracted and converted to a feature vector including the mel-scaled filter bank energy coefficients and the envelope coefficients of uniform-sized sub-segments. An extreme learning machine is used to classify the feature vector. In our cardiac disorder classification and detection experiments with 9 cardiac disorder categories, the proposed method shows significantly better performance than multi-layer perceptron, support vector machine, and hidden Markov model; it achieves the classification accuracy of 81.6% and the detection accuracy of 96.9%.
Abstract: An adaptive Chinese hand-talking system is presented
in this paper. By analyzing the 3 data collecting strategies for new
users, the adaptation framework including supervised and unsupervised
adaptation methods is proposed. For supervised adaptation,
affinity propagation (AP) is used to extract exemplar subsets, and enhanced
maximum a posteriori / vector field smoothing (eMAP/VFS)
is proposed to pool the adaptation data among different models. For
unsupervised adaptation, polynomial segment models (PSMs) are
used to help hidden Markov models (HMMs) to accurately label
the unlabeled data, then the "labeled" data together with signerindependent
models are inputted to MAP algorithm to generate
signer-adapted models. Experimental results show that the proposed
framework can execute both supervised adaptation with small amount
of labeled data and unsupervised adaptation with large amount
of unlabeled data to tailor the original models, and both achieve
improvements on the performance of recognition rate.
Abstract: The paper presents an on-line recognition machine
(RM) for continuous/isolated, dynamic and static gestures that arise
in Flight Deck Officer (FDO) training. RM is based on generic pattern
recognition framework. Gestures are represented as templates using
summary statistics. The proposed recognition algorithm exploits temporal
and spatial characteristics of gestures via dynamic programming
and Markovian process. The algorithm predicts corresponding index
of incremental input data in the templates in an on-line mode.
Accumulated consistency in the sequence of prediction provides a
similarity measurement (Score) between input data and the templates.
The algorithm provides an intuitive mechanism for automatic detection
of start/end frames of continuous gestures. In the present paper,
we consider isolated gestures. The performance of RM is evaluated
using four datasets - artificial (W TTest), hand motion (Yang) and
FDO (tracker, vision-based ). RM achieves comparable results which
are in agreement with other on-line and off-line algorithms such as
hidden Markov model (HMM) and dynamic time warping (DTW).
The proposed algorithm has the additional advantage of providing
timely feedback for training purposes.
Abstract: In this paper we propose a segmentation system for unconstrained Arabic online handwriting. An essential problem addressed by analytical-based word recognition system. The system is composed of two-stages the first is a newly special designed hidden Markov model (HMM) and the second is a rules based stage. In our system, handwritten words are broken up into characters by simultaneous segmentation-recognition using HMMs of unique design trained using online features most of which are novel. The HMM output characters boundaries represent the proposed segmentation points (PSP) which are then validated by rules-based post stage without any contextual information help to solve different segmentation errors. The HMM has been designed and tested using a self collected dataset (OHASD) [1]. Most errors cases are cured and remarkable segmentation enhancement is achieved. Very promising word and character segmentation rates are obtained regarding the unconstrained Arabic handwriting difficulty and not using context help.
Abstract: In this paper, the potential use of an exponential
hidden Markov model to model a hidden pavement deterioration
process, i.e. one that is not directly measurable, is investigated. It is
assumed that the evolution of the physical condition, which is the
hidden process, and the evolution of the values of pavement distress
indicators, can be adequately described using discrete condition states
and modeled as a Markov processes. It is also assumed that condition
data can be collected by visual inspections over time and represented
continuously using an exponential distribution. The advantage of
using such a model in decision making process is illustrated through
an empirical study using real world data.
Abstract: We present a hybrid architecture of recurrent neural
networks (RNNs) inspired by hidden Markov models (HMMs). We
train the hybrid architecture using genetic algorithms to learn and
represent dynamical systems. We train the hybrid architecture on a
set of deterministic finite-state automata strings and observe the
generalization performance of the hybrid architecture when presented
with a new set of strings which were not present in the training data
set. In this way, we show that the hybrid system of HMM and RNN
can learn and represent deterministic finite-state automata. We ran
experiments with different sets of population sizes in the genetic
algorithm; we also ran experiments to find out which weight
initializations were best for training the hybrid architecture. The
results show that the hybrid architecture of recurrent neural networks
inspired by hidden Markov models can train and represent dynamical
systems. The best training and generalization performance is
achieved when the hybrid architecture is initialized with random real
weight values of range -15 to 15.