Search

Autonomous driving systems for unmanned ground vehicles (UGV) operating in enclosed environments strongly rely on LiDAR localization with a prior map. Precise initial pose estimation is critical during system startup or when tracking is lost, ensuring safe UGV operation. Existing LiDAR-based place recognition methods often suffer from reduced accuracy due to only matching descriptors from individual LiDAR keyframes. This paper proposes a multi-frame descriptor-matching approach based on the hidden Markov model (HMM) to address this issue. This method enhances the place recognition accuracy and robustness by leveraging information from multiple frames. Experimental results from the KITTI dataset demonstrate that the proposed method significantly enhances the place recognition performance compared with the scan context-based single-frame descriptor-matching approach, with an average performance improvement of 5.8% and with a maximum improvement of 15.3%.

In this paper, we propose an improved clustering algorithm for wireless sensor networks (WSNs) that aims to increase network lifetime and efficiency. We introduce an enhanced fuzzy spider monkey optimization technique and a hidden Markov model-based clustering algorithm for selecting cluster heads. Our approach considers factors such as network cluster head energy, cluster head density, and cluster head position. We also enhance the energy-efficient routing strategy for connecting cluster heads to the base station. Additionally, we introduce a polling control method to improve network performance while maintaining energy efficiency during steady transmission periods. Simulation results demonstrate a 1.2% improvement in network performance using our proposed model.

Short message services (SMS), microblogging tools, instant message apps, and commercial websites produce numerous short text messages every day. These short text messages are usually guaranteed to reach mass audience with low cost. Spammers take advantage of short texts by sending bulk malicious or unwanted messages. Short texts are difficult to classify because of their shortness, sparsity, rapidness, and informal writing. The effectiveness of the hidden Markov model (HMM) for short text classification has been illustrated in our previous study. However, the HMM has limited capability to handle new words, which are mostly generated by informal writing. In this paper, a hybrid model is proposed to address the informal writing issue by weighting new words for fast short text filtering with high accuracy. The hybrid model consists of an artificial neural network (ANN) and an HMM, which are used for new word weighting and spam filtering, respectively. The weight of a new word is calculated based on the weights of its neighbor, along with the spam and ham (i.e., not spam) probabilities of short text message predicted by the ANN. Performance evaluations on benchmark datasets, including the SMS message data maintained by University of California, Irvine; the movie reviews, and the customer reviews are conducted. The hybrid model operates at a significantly higher speed than deep learning models. The experiment results show that the proposed hybrid model outperforms other prominent machine learning algorithms, achieving a good balance between filtering throughput and accuracy.

Managing mood disorders poses challenges in counseling and drug treatment, owing to limitations. Counseling is the most effective during hospital visits, and the side effects of drugs can be burdensome. Patient empowerment is crucial for understanding and managing these triggers. The daily monitoring of mental health and the utilization of episode prediction tools can enable self-management and provide doctors with insights into worsening lifestyle patterns. In this study, we test and validate whether the prediction of future depressive episodes in individuals with depression can be achieved by using lifelog sequence data collected from digital device sensors. Diverse models such as random forest, hidden Markov model, and recurrent neural network were used to analyze the time-series data and make predictions about the occurrence of depressive episodes in the near future. The models were then combined into a hybrid model. The prediction accuracy of the hybrid model was 0.78; especially in the prediction of rare episode events, the F1-score performance was approximately 1.88 times higher than that of the dummy model. We explored factors such as data sequence size, train-to-test data ratio, and class-labeling time slots that can affect the model performance to determine the combinations of parameters that optimize the model performance. Our findings are especially valuable because they are experimental results derived from large-scale participant data analyzed over a long period of time.

The field of computational paralinguistics emerged from automatic speech processing, and it covers a wide range of tasks involving different phenomena present in human speech. It focuses on the non-verbal content of human speech, including tasks such as spoken emotion recognition, conflict intensity estimation and sleepiness detection from speech, showing straightforward application possibilities for remote monitoring with acoustic sensors. The two main technical issues present in computational paralinguistics are (1) handling varying-length utterances with traditional classifiers and (2) training models on relatively small corpora. In this study, we present a method that combines automatic speech recognition and paralinguistic approaches, which is able to handle both of these technical issues. That is, we trained a HMM/DNN hybrid acoustic model on a general ASR corpus, which was then used as a source of embeddings employed as features for several paralinguistic tasks. To convert the local embeddings into utterance-level features, we experimented with five different aggregation methods, namely mean, standard deviation, skewness, kurtosis and the ratio of non-zero activations. Our results show that the proposed feature extraction technique consistently outperforms the widely used x-vector method used as the baseline, independently of the actual paralinguistic task investigated. Furthermore, the aggregation techniques could be combined effectively as well, leading to further improvements depending on the task and the layer of the neural network serving as the source of the local embeddings. Overall, based on our experimental results, the proposed method can be considered as a competitive and resource-efficient approach for a wide range of computational paralinguistic tasks.

Packet loss is a major problem for wireless networks and has significant effects on the perceived quality of many internet services. Packet loss models are used to understand the behavior of packet losses caused by several reasons, e.g., interferences, coexistence, fading, collisions, and insufficient/excessive memory buffers. Among these, the Gilbert-Elliot (GE) model, based on a two-state Markov chain, is the most used model in communication networks. However, research has proven that the GE model is inadequate to represent the real behavior of packet losses in Wi-Fi networks. In this last category, variables of a single network layer are used, usually the physical one. In this article, we propose a new packet loss model for Wi-Fi that simultaneously considers the temporal behavior of losses and the variables that describe the state of the network. In addition, the model uses two important variables, the signal-to-noise ratio and the network occupation, which none of the packet loss models available for Wi-Fi networks simultaneously take into account. The proposed model uses the well-known Hidden Markov Model (HMM), which facilitates training and forecasting. At each state of HMM, the burst-length of losses is characterized using probability distributions. The model was evaluated by comparing computer simulation and real data samples for validation, and using the log-log complementary distribution of burst-length. We compared the proposed model with competing models through the analysis of mean square error (MSE) using a validation sample collected from a real network. Results demonstrated that the proposed model outperforms the currently available models for packet loss in Wi-Fi networks.

It is important to find signals of interest (SOIs) when operating sonar systems. A threshold-based method is generally used for SOI detection. However, it induces a high false alarm rate at a low signal-to-noise ratio. On the other side, machine-learning-based detection is performed to obtain more reliable detection results using abundant training data, costing intensive time and labor. We propose a method with favorable detection performance by using a hidden Markov model (HMM) for sequential acoustic data, which requires no separate training data. Since the detection results from HMM are significantly affected by the random initial parameters of HMM, the genetic algorithm (GA) is adopted to reduce the sensitivity of the initial parameters. The tuned initial parameters from GA are used as a start point for the subsequent Baum–Welch algorithm updating the HMM parameters. Furthermore, multiple measurements from arrays are exploited both in determining the proper initial parameters with GA and updating the parameters with the Baum–Welch algorithm. In contrast to the standard random selection of the initial point with single measurement, a stable initial point setting by the GA ensures improved SOI detections with the Baum–Welch algorithm using the multiple measurements, which are demonstrated in passive and active acoustic data. Particularly, the proposed method shows the most confidential detection in finding weak elastic surface waves from target, compared to existing methods such as conventional HMM.

With the exponential growth of data, solving classification or regression tasks by mining time series data has become a research hotspot. Commonly used methods include machine learning, artificial neural networks, and so on. However, these methods only extract the continuous or discrete features of sequences, which have the drawbacks of low information utilization, poor robustness, and computational complexity. To solve these problems, this paper innovatively uses Wasserstein distance instead of Kullback–Leibler divergence and uses it to construct an autoencoder to learn discrete features of time series. Then, a hidden Markov model is used to learn the continuous features of the sequence. Finally, stacking is used to ensemble the two models to obtain the final model. This paper experimentally verifies that the ensemble model has lower computational complexity and is close to state-of-the-art classification accuracy.

Currently, hidden Markov-based multi-step attack detection models are mainly trained using the unsupervised Baum–Welch algorithm. The Baum–Welch algorithm is sensitive to the initial values of model parameters. However, its training uses random or average parameter initialization methods, which frequently results in the model training into a local optimum, thus, making the model unable to fit the alert logs well and thereby reducing the detection effectiveness of the model. To solve this issue, we propose a pre-training method for multi-step attack detection models based on the high semantic similarity of alerts in the same attack phase. The method first clusters the alerts based on their semantic information and pre-classifies the attack phase to which each alert belongs. Then, the distance of the alert vector to each attack stage is converted into the probability of generating alerts in each attack stage, replacing the initial value of Baum–Welch. The effectiveness of the proposed method is evaluated using the DARPA 2000 dataset, DEFCON21 CTF dataset, and ISCXIDS 2012 dataset. The experimental results show that the hidden Markov multi-step attack detection method based on pre-training of the proposed model parameters had higher detection accuracy than the Baum–Welch-based, K-means-based, and transfer learning differential evolution-based hidden Markov multi-step attack detection methods.

Visible light communication (VLC) channel quality depends on line-of-sight (LoS) transmission, which cannot guarantee continuous transmission due to interruptions caused by blockage and user mobility. Thus, integrating VLC with radio frequency (RF) such asWireless Fidelity (WiFi), provides good quality of experience (QoE) to users. A vertical handover (VHO) scheme that optimizes both the cost of switching and dwelling time of the hybrid VLC–WiFi system is required since blockage on VLC LoS usually occurs for a short period. Hence, an automated VHO algorithm for the VLC–WiFi system based on the hidden Markov model (HMM) is developed in this article. The proposed VHO prediction scheme utilizes the channel characterization of the networks, specifically, the measured received signal strength (RSS) values at different locations. Effective RSS are extracted from the huge datasets using principal component analysis (PCA), which is adopted with HMM, and thus reducing the computational complexity of the model. In comparison with state-of-the-art VHO handover prediction methods, the proposed HMM-based VHO scheme accurately obtains the most likely next assigned access point (AP) by selecting an appropriate time window. The results show a high VHO prediction accuracy and reduced mixed absolute percentage error performance. In addition, the results indicate that the proposed algorithm improves the dwell time on a network and reduces the number of handover events as compared to the threshold-based, fuzzy-controller, and neural network VHO prediction schemes. Thus, it reduces the ping-pong effects associated with the VHO in the heterogeneous VLC–WiFi network.

The use of assistive technologies can mitigate or reduce the challenges faced by individuals with motor disabilities to use computer systems. However, those who feature severe involuntary movements often have fewer options at hand. This work describes an application that can recognize the user’s head using a conventional webcam, track its motion, model the desired functional movement, and recognize it to enable the use of a virtual keyboard. The proposed classifier features a flexible structure and may be personalized for different user need. Experimental results obtained with participants with no neurological disorders have shown that classifiers based on Hidden Markov Models provided similar or better performance than a classifier based on position threshold. However, motion segmentation and interpretation modules were sensitive to involuntary movements featured by participants with cerebral palsy that took part in the study.

Gait analysis, as a common inspection method for human gait, can provide a series of kinematics, dynamics and other parameters through instrumental measurement. In recent years, gait analysis has been gradually applied to the diagnosis of diseases, the evaluation of orthopedic surgery and rehabilitation progress, especially, gait phase abnormality can be used as a clinical diagnostic indicator of Alzheimer Disease and Parkinson Disease, which usually show varying degrees of gait phase abnormality. This research proposed an inertial sensor based gait analysis method. Smoothed and filtered angular velocity signal was chosen as the input data of the 15-dimensional temporal characteristic feature. Hidden Markov Model and parameter adaptive model are used to segment gait phases. Experimental results show that the proposed model based on HMM and parameter adaptation achieves good recognition rate in gait phases segmentation compared to other classification models, and the recognition results of gait phase are consistent with ground truth. The proposed wearable device used for data collection can be embedded on the shoe, which can not only collect patients’ gait data stably and reliably, ensuring the integrity and objectivity of gait data, but also collect data in daily scene and ambulatory outdoor environment.

Smart wristbands and watches have become an important accessory to fitness, but their application to healthcare is still in a fledgling state. Their long-term wear facilitates extensive data collection and evolving sensitivity of smart wristbands allows them to read various body vitals. In this paper, we hypothesized the use of heart rate variability (HRV) measurements to drive an algorithm that can pre-empt the onset or worsening of an affliction. Due to its significance during the time of the study, SARS-Cov-2 was taken as the case study, and a hidden Markov model (HMM) was trained over its observed symptoms. The data used for the analysis was the outcome of a study hosted by Welltory. It involved the collection of SAR-Cov-2 symptoms and reading of body vitals using Apple Watch, Fitbit, and Garmin smart bands. The internal states of the HMM were made up of the absence and presence of a consistent decline in standard deviation of NN intervals (SSDN), the root mean square of the successive differences (rMSSD) in R-R intervals, and low frequency (LF), high frequency (HF), and very low frequency (VLF) components of the HRV measurements. The emission probabilities of the trained HMM instance confirmed that the onset or worsening of the symptoms had a higher probability if the HRV components displayed a consistent decline state. The results were further confirmed through the generation of probable hidden states sequences using the Viterbi algorithm. The ability to pre-empt the exigent state of an affliction would not only lower the chances of complications and mortality but may also help in curbing its spread through intelligence-backed decisions.

With the rapid development of LBSs (location-based services) in recent years, researchers have increasingly taken an interest in trying to make travel routes more practicable and individualized. Despite the fact that many studies have been conducted on routes using LBS data, the specific routes are deficient in dynamic scalability and the correlations between environmental constraints and personal choices have not been investigated. This paper proposes an improved HMM-based (hidden Markov model) method for planning personalized routes with crowd sourcing spatiotemporal data. It tries to integrate the dynamic public preferences, the individual interests and the physical road network space in the same spatiotemporal framework, ensuring that reasonable routes will be generated. A novel dual-layer mapping structure has been proposed to bridge the gap from brief individual preferences to specific entries of POIs (points-of-interest) inside realistic road networks. A case study on Changsha city has proven that the proposed method can not only flexibly plan people’s travel routes under different spatiotemporal backgrounds but also is close to people’s natural selection by the perception of the group.

Map-matching is a popular method that uses spatial information to improve the accuracy of positioning methods. The performance of map matching methods is closely related to spatial characteristics. Although several studies have demonstrated that certain map matching algorithms are affected by some spatial structures (e.g., parallel paths), they focus on the analysis of single map matching method or few spatial structures. In this study, we explored how the most commonly-used four spatial characteristics (namely forks, open spaces, corners, and narrow corridors) affect three popular map matching methods, namely particle filtering (PF), hidden Markov model (HMM), and geometric methods. We first provide a theoretical analysis on how spatial characteristics affect the performance of map matching methods, and then evaluate these effects through experiments. We found that corners and narrow corridors are helpful in improving the positioning accuracy, while forks and open spaces often lead to a larger positioning error. We hope that our findings are helpful for future researchers in choosing proper map matching algorithms with considering the spatial characteristics.

The number of wireless sensors in use—for example, the global positioning system (GPS) intelligent sensor—has increased in recent years. These intelligent sensors generate a vast amount of spatiotemporal data, which can assist in finding patterns of movements. These movement patterns can be used to predict the future location of moving objects; for example, the movement of an emergency vehicle can be predicted for health care decision-making. Although there is a body of research work regarding motion trajectory prediction, there are no guidelines for choosing algorithms best suited for individual needs in uncertain and complex situations and as per the application domains. In this paper, we surveyed existing trajectory prediction algorithms. These algorithms are further ranked scientifically in terms of accuracy (performance), ease of use, and best fit as per the available datasets. Our results show three top algorithms, namely NextPlace, the Markov model, and the hidden Markov model. This study can be beneficial for multicriteria decision-making for various disciplines, including health care.

Sensor devices in wireless sensor networks are vulnerable to faults during their operation in unmonitored and hazardous environments. Though various methods have been proposed by researchers to detect sensor faults, only very few research studies have reported on capturing the dynamics of the inherent states in sensor data during fault occurrence. The continuous density hidden Markov model (CDHMM) is proposed in this research to determine the dynamics of the state transitions due to fault occurrence, while neural networks are utilized to classify the faults based on the state transition probability density generated by the CDHMM. Therefore, this paper focuses on the fault detection and classification using the hybridization of CDHMM and various neural networks (NNs), namely the learning vector quantization, probabilistic neural network, adaptive probabilistic neural network, and radial basis function. The hybrid models of each NN are used for the classification of sensor faults, namely bias, drift, random, and spike. The proposed methods are evaluated using four performance metrics which includes detection accuracy, false positive rate, F1-score, and the Matthews correlation coefficient. The simulation results show that the learning vector quantization NN classifier outperforms the detection accuracy rate when compared to the other classifiers. In addition, an ensemble NN framework based on the hybrid CDHMM classifier is built with majority voting scheme for decision making and classification. The results of the hybrid CDHMM ensemble classifiers clearly indicates the efficacy of the proposed scheme in capturing the dynamics of change of statesm which is the vital aspect in determining rapidly-evolving instant faults that occur in wireless sensor networks.

Gait-phase recognition is a necessary functionality to drive robotic rehabilitation devices for lower limbs. Hidden Markov Models (HMMs) represent a viable solution, but they need subject-specific training, making data processing very time-consuming. Here, we validated an inter-subject procedure to avoid the intra-subject one in two, four and six gait-phase models in pediatric subjects. The inter-subject procedure consists in the identification of a standardized parameter set to adapt the model to measurements. We tested the inter-subject procedure both on scalar and distributed classifiers. Ten healthy children and ten hemiplegic children, each equipped with two Inertial Measurement Units placed on shank and foot, were recruited. The sagittal component of angular velocity was recorded by gyroscopes while subjects performed four walking trials on a treadmill. The goodness of classifiers was evaluated with the Receiver Operating Characteristic. The results provided a goodness from good to optimum for all examined classifiers (0 < G < 0.6), with the best performance for the distributed classifier in two-phase recognition (G = 0.02). Differences were found among gait partitioning models, while no differences were found between training procedures with the exception of the shank classifier. Our results raise the possibility of avoiding subject-specific training in HMM for gait-phase recognition and its implementation to control exoskeletons for the pediatric population.

In this paper, we propose a new method for spotting and recognizing continuous human actions using a vision sensor. The method is comprised of depth-MHI-HOG (DMH), action modeling, action spotting, and recognition. First, to effectively separate the foreground from background, we propose a method called DMH. It includes a standard structure for segmenting images and extracting features by using depth information, MHI, and HOG. Second, action modeling is performed to model various actions using extracted features. The modeling of actions is performed by creating sequences of actions through k-means clustering; these sequences constitute HMM input. Third, a method of action spotting is proposed to filter meaningless actions from continuous actions and to identify precise start and end points of actions. By employing the spotter model, the proposed method improves action recognition performance. Finally, the proposed method recognizes actions based on start and end points. We evaluate recognition performance by employing the proposed method to obtain and compare probabilities by applying input sequences in action models and the spotter model. Through various experiments, we demonstrate that the proposed method is efficient for recognizing continuous human actions in real environments.

Video-based human activity recognition (HAR) means the analysis of motions and behaviors of human from the low level sensors. Over the last decade, automatic HAR is an exigent research area and is considered a significant concern in the field of computer vision and pattern recognition. In this paper, we have presented a robust and an accurate activity recognition system called WS-HAR that consists of wavelet transform coupled with stepwise linear discriminant analysis (SWLDA) followed by hidden Markov model (HMM). Symlet wavelet has been employed in order to extract the features from the activity frames. The most prominent features were selected by proposing a robust technique called stepwise linear discriminant analysis (SWLDA) that focuses on selecting the localized features from the activity frames and discriminating their class based on regression values (i.e., partial F-test values). Finally, we applied a well-known sequential classifier called hidden Markov model (HMM) to give the appropriate labels to the activities. In order to validate the performance of the WS-HAR, we utilized two publicly available standard datasets under two different experimental settings, n??fold cross validation scheme based on subjects; and a set of experiments was performed in order to show the effectiveness of each approach. The weighted average recognition rate for the WS-HAR was 97% across the two different datasets that is a significant improvement in classication accuracy compared to the existing well-known statistical and state-of-the-art methods.

Due to the recent rise in the use of lower-limb exoskeletons as an alternative for gait rehabilitation, gait phase detection has become an increasingly important feature in the control of these devices. In addition, highly functional, low-cost recovery devices are needed in developing countries, since limited budgets are allocated specifically for biomedical advances. To achieve this goal, this paper presents two gait phase partitioning algorithms that use motion data from a single inertial measurement unit (IMU) placed on the foot instep. For these data, sagittal angular velocity and linear acceleration signals were extracted from nine healthy subjects and nine pathological subjects. Pressure patterns from force sensitive resistors (FSR) instrumented on a custom insole were used as reference values. The performance of a threshold-based (TB) algorithm and a hidden Markov model (HMM) based algorithm, trained by means of subject-specific and standardized parameters approaches, were compared during treadmill walking tasks in terms of timing errors and the goodness index. The findings indicate that HMM outperforms TB for this hardware configuration. In addition, the HMM-based classifier trained by an intra-subject approach showed excellent reliability for the evaluation of mean time, i.e., its intra-class correlation coefficient (ICC) was greater than 0.75 . In conclusion, the HMM-based method proposed here can be implemented for gait phase recognition, such as to evaluate gait variability in patients and to control robotic orthoses for lower-limb rehabilitation.

Lane changing is considered as one of the most dangerous driving behaviors because drivers have to deal with the traffic conflicts on both the current and target lanes. This study aimed to propose a method of predicting the driving risks during the lane-changing process using drivers’ physiology measurement data and vehicle dynamic data. All the data used in the proposed model were obtained by portable sensors with the capability of recording data in the actual driving process. A hidden Markov model (HMM) was proposed to link driving risk with drivers’ physiology information and vehicle dynamic data. The two-factor indicators were established to evaluate the performances of eye movement, heart rate variability, and vehicle dynamic parameters on driving risk. The standard deviation of normal to normal R−R intervals of the heart rate (SDNN), fixation duration, saccade range, and average speed were then selected as the input of the HMM. The HMM was trained and tested using field-observed data collected in Xi’an City. The proposed model using the data from the physiology measurement sensor can identify dangerous driving state from normal driving state and predict the transition probability between these two states. The results match the perceptions of the tested drivers with an accuracy rate of 90.67%. The proposed model can be used to develop proactive crash prevention strategies.

The usage of multiple flow tables (MFT) has significantly extended the flexibility and applicability of software-defined networking (SDN). However, the size of MFT is usually limited due to the use of expensive ternary content addressable memory (TCAM). Moreover, the pipeline mechanism of MFT causes long flow processing time. In this paper a novel approach called Agg-ExTable is proposed to efficiently manage the MFT. Here the flow entries in MFT are periodically aggregated by applying pruning and the Quine−Mccluskey algorithm. Utilizing the memory space saved by the aggregation, a front-end ExTable is constructed, keeping popular flow entries for early match. Popular entries are decided by the Hidden Markov model based on the match frequency and match probability. Computer simulation reveals that the proposed scheme is able to save about 45% of space of MFT, and efficiently decrease the flow processing time compared to the existing schemes.

Hydraulic pump is a driving device of the hydraulic system, always working under harsh operating conditions, its fault diagnosis work is necessary for the smooth running of a hydraulic system. However, it is difficult to collect sufficient status information in practical operating processes. In order to achieve fault diagnosis with poor information, a novel fault diagnosis method that is the based on Symbolic Perceptually Important Point (SPIP) and Hidden Markov Model (HMM) is proposed. Perceptually important point technology is firstly imported into rotating machine fault diagnosis; it is applied to compress the original time-series into PIP series, which can depict the overall movement shape of original time series. The PIP series is transformed into symbolic series that will serve as feature series for HMM, Genetic Algorithm is used to optimize the symbolic space partition scheme. The Hidden Markov Model is then employed for fault classification. An experiment involves four operating conditions is applied to validate the proposed method. The results show that the fault classification accuracy of the proposed method reaches 99.625% when each testing sample only containing 250 points and the signal duration is 0.025 s. The proposed method could achieve good performance under poor information conditions.

Over the past decades, there has been significant research effort dedicated to the development of intelligent vehicles and V2X systems. This paper proposes a road traffic risk assessment method for road traffic accident prevention of intelligent vehicles. This method is based on HMM (Hidden Markov Model) and is applied to the prediction of steering angle status to (1) evaluate the probabilities of the steering angle in each independent interval and (2) calculate the road traffic risk in different analysis regions. According to the model, the road traffic risk is quantified and presented directly in a visual form by the time-varying risk map, to ensure the accuracy of assessment and prediction. Experiment results are presented, and the results show the effectiveness of the assessment strategies.

Strapdown inertial navigation systems (INS) need an alignment process to determine the initial attitude matrix between the body frame and the navigation frame. The conventional alignment process is to compute the initial attitude matrix using the gravity and Earth rotational rate measurements. However, under mooring conditions, the inertial measurement unit (IMU) employed in a ship’s strapdown INS often suffers from both the intrinsic sensor noise components and the external disturbance components caused by the motions of the sea waves and wind waves, so a rapid and precise alignment of a ship’s strapdown INS without any auxiliary information is hard to achieve. A robust solution is given in this paper to solve this problem. The inertial frame based alignment method is utilized to adapt the mooring condition, most of the periodical low-frequency external disturbance components could be removed by the mathematical integration and averaging characteristic of this method. A novel prefilter named hidden Markov model based Kalman filter (HMM-KF) is proposed to remove the relatively high-frequency error components. Different from the digital filters, the HMM-KF barely cause time-delay problem. The turntable, mooring and sea experiments favorably validate the rapidness and accuracy of the proposed self-alignment method and the good de-noising performance of HMM-KF.

In a health management system, prognostics, which is an engineering discipline that predicts a system’s future health, is an important aspect yet there is currently limited research in this field. In this paper, a hybrid approach for prognostics is proposed. The approach combines the least squares support vector regression (LSSVR) with the hidden Markov model (HMM). Features extracted from sensor signals are used to train HMMs, which represent different health levels. A LSSVR algorithm is used to predict the feature trends. The LSSVR training and prediction algorithms are modified by adding new data and deleting old data and the probabilities of the predicted features for each HMM are calculated based on forward or backward algorithms. Based on these probabilities, one can determine a system’s future health state and estimate the remaining useful life (RUL). To evaluate the proposed approach, a test was carried out using bearing vibration signals. Simulation results show that the LSSVR/HMM approach can forecast faults long before they occur and can predict the RUL. Therefore, the LSSVR/HMM approach is very promising in the field of prognostics.

Activities of daily living are good indicators of elderly health status, and activity recognition in smart environments is a well-known problem that has been previously addressed by several studies. In this paper, we describe the use of two powerful machine learning schemes, ANN (Artificial Neural Network) and SVM (Support Vector Machines), within the framework of HMM (Hidden Markov Model) in order to tackle the task of activity recognition in a home setting. The output scores of the discriminative models, after processing, are used as observation probabilities of the hybrid approach. We evaluate our approach by comparing these hybrid models with other classical activity recognition methods using five real datasets. We show how the hybrid models achieve significantly better recognition performance, with significance level p < 0:05, proving that the hybrid approach is better suited for the addressed domain.

Long term continuous monitoring of electrocardiogram (ECG) in a free living environment provides valuable information for prevention on the heart attack and other high risk diseases. This paper presents the design of a real-time wearable ECG monitoring system with associated cardiac arrhythmia classification algorithms. One of the striking advantages is that ECG analog front-end and on-node digital processing are designed to remove most of the noise and bias. In addition, the wearable sensor node is able to monitor the patient’s ECG and motion signal in an unobstructive way. To realize the real-time medical analysis, the ECG is digitalized and transmitted to a smart phone via Bluetooth. On the smart phone, the ECG waveform is visualized and a novel layered hidden Markov model is seamlessly integrated to classify multiple cardiac arrhythmias in real time. Experimental results demonstrate that the clean and reliable ECG waveform can be captured in multiple stressed conditions and the real-time classification on cardiac arrhythmia is competent to other workbenches.

The purpose of this study was to classify, and model various physical activities performed by a diverse group of participants in a supervised lab-based protocol and utilize the model to identify physical activity in a free-living setting. Wrist-worn accelerometer data were collected from ( N = 152 ) adult participants; age 18⁻64 years, and processed the data to identify and model unique physical activities performed by the participants in controlled settings. The Gaussian mixture model (GMM) and the hidden Markov model (HMM) algorithms were used to model the physical activities with time and frequency-based accelerometer features. An overall model accuracy of 92.7% and 94.7% were achieved to classify 24 physical activities using GMM and HMM, respectively. The most accurate model was then used to identify physical activities performed by 20 participants, each recorded for two free-living sessions of approximately six hours each. The free-living activity intensities were estimated with 80% accuracy and showed the dominance of stationary and light intensity activities in 36 out of 40 recorded sessions. This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models. In summary, this study contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free-living settings.

In pedestrian navigation systems, the position of a pedestrian is computed using an inertial navigation algorithm. In the algorithm, the zero velocity updating plays an important role, where zero velocity intervals are detected and the velocity error is reset. To use the zero velocity updating, it is necessary to detect zero velocity intervals reliably. A new zero detection algorithm is proposed in the paper, where only one gyroscope value is used. A Markov model is constructed using segmentation of gyroscope outputs instead of using gyroscope outputs directly, which makes the zero velocity detection more reliable.

Regular inspection for the maintenance of the wind turbines is difficult because of their remote locations. For this reason, condition monitoring systems (CMSs) are typically installed to monitor their health condition. The purpose of this study is to propose a fault detection algorithm for the mechanical parts of the wind turbine. To this end, long-term vibration data were collected over two years by a CMS installed on a 3 MW wind turbine. The vibration distribution at a specific rotating speed of main shaft is approximated by the Weibull distribution and its cumulative distribution function is utilized for determining the threshold levels that indicate impending failure of mechanical parts. A Hidden Markov model (HMM) is employed to propose the statistical fault detection algorithm in the time domain and the method whereby the input sequence for HMM is extracted is also introduced by considering the threshold levels and the correlation between the signals. Finally, it was demonstrated that the proposed HMM algorithm achieved a greater than 95% detection success rate by using the long-term signals.

The map matching (MM) model plays an important role in revising the locations of floating car data (FCD) on a digital map. However, most existing MM models have multiple shortcomings, such as a low matching accuracy for complex roads, long running times, an inability to take full advantage of historical FCD information, and challenges in maintaining the topological adjacency and obeying traffic rules. To address these issues, an enhanced hidden Markov map matching (EHMM) model is proposed by adopting explicit topological expressions, using historical FCD information and introducing traffic rules. The EHMM model was validated against areal ground dataset at various sampling intervals and compared with the spatial and temporal matching model and the ordinary hidden Markov matching model. The empirical results reveal that the matching accuracy of the EHMM model is significantly higher than that of the reference models regarding real FCD trajectories at medium and high sampling rates. The running time of the EHMM model was notably shorter than those of the reference models. The matching results of the EHMM model retained topological adjacency and complied with traffic regulations better than the reference models.

The enhancement of ubiquitous and pervasive computing brings new perspectives in medical rehabilitation. In that sense, the present study proposes a smart, web-based platform to promote the reeducation of patients after hip replacement surgery. This project focuses on two fundamental aspects in the development of a suitable tele-rehabilitation application, which are: (i) being based on an affordable technology, and (ii) providing the patients with a real-time assessment of the correctness of their movements. A probabilistic approach based on the development and training of ten Hidden Markov Models (HMMs) is used to discriminate in real time the main faults in the execution of the therapeutic exercises. Two experiments are designed to evaluate the precision of the algorithm for classifying movements performed in the laboratory and clinical settings, respectively. A comparative analysis of the data shows that the models are as reliable as the physiotherapists to discriminate and identify the motion errors. The results are discussed in terms of the required setup for a successful application in the field and further implementations to improve the accuracy and usability of the system.

This paper proposes an immunity-based anomaly detection system with sensor agents based on the specificity and diversity of the immune system. Each agent is specialized to react to the behavior of a specific user. Multiple diverse agents decide whether the behavior is normal or abnormal. Conventional systems have used only a single sensor to detect anomalies, while the immunity-based system makes use of multiple sensors, which leads to improvements in detection accuracy. In addition, we propose an evaluation framework for the anomaly detection system, which is capable of evaluating the differences in detection accuracy between internal and external anomalies. This paper focuses on anomaly detection in user’s command sequences on UNIX-like systems. In experiments, the immunity-based system outperformed some of the best conventional systems.

We introduce a high precision localization and tracking method that makes use of cheap Bluetooth low-energy (BLE) beacons only. We track the position of a moving sensor by integrating highly unreliable and noisy BLE observations streaming from multiple locations. A novel aspect of our approach is the development of an observation model, specifically tailored for received signal strength indicator (RSSI) fingerprints: a combination based on the optimal transport model of Wasserstein distance. The tracking results of the entire system are compared with alternative baseline estimation methods, such as nearest neighboring fingerprints and an artificial neural network. Our results show that highly accurate estimation from noisy Bluetooth data is practically feasible with an observation model based on Wasserstein distance interpolation combined with the sequential Monte Carlo (SMC) method for tracking.

Human gait analysis plays an important role in musculoskeletal disorder diagnosis. Detecting anomalies in human walking, such as shuffling gait, stiff leg or unsteady gait, can be difficult if the prior knowledge of such a gait pattern is not available. We propose an approach for detecting abnormal human gait based on a normal gait model. Instead of employing the color image, silhouette, or spatio-temporal volume, our model is created based on human joint positions (skeleton) in time series. We decompose each sequence of normal gait images into gait cycles. Each human instant posture is represented by a feature vector which describes relationships between pairs of bone joints located in the lower body. Such vectors are then converted into codewords using a clustering technique. The normal human gait model is created based on multiple sequences of codewords corresponding to different gait cycles. In the detection stage, a gait cycle with normality likelihood below a threshold, which is determined automatically in the training step, is assumed as an anomaly. The experimental results on both marker-based mocap data and Kinect skeleton show that our method is very promising in distinguishing normal and abnormal gaits with an overall accuracy of 90.12%.

With the rapid development of smartphones and wireless networks, indoor location-based services have become more and more prevalent. Due to the sophisticated propagation of radio signals, the Received Signal Strength Indicator (RSSI) shows a significant variation during pedestrian walking, which introduces critical errors in deterministic indoor positioning. To solve this problem, we present a novel method to improve the indoor pedestrian positioning accuracy by embedding a fuzzy pattern recognition algorithm into a Hidden Markov Model. The fuzzy pattern recognition algorithm follows the rule that the RSSI fading has a positive correlation to the distance between the measuring point and the AP location even during a dynamic positioning measurement. Through this algorithm, we use the RSSI variation trend to replace the specific RSSI value to achieve a fuzzy positioning. The transition probability of the Hidden Markov Model is trained by the fuzzy pattern recognition algorithm with pedestrian trajectories. Using the Viterbi algorithm with the trained model, we can obtain a set of hidden location states. In our experiments, we demonstrate that, compared with the deterministic pattern matching algorithm, our method can greatly improve the positioning accuracy and shows robust environmental adaptability.

Machine learning methods have been widely used for gait assessment through the estimation of spatio-temporal parameters. As a further step, the objective of this work is to propose and validate a general probabilistic modeling approach for the classification of different pathological gaits. Specifically, the presented methodology was tested on gait data recorded on two pathological populations (Huntington’s disease and post-stroke subjects) and healthy elderly controls using data from inertial measurement units placed at shank and waist. By extracting features from group-specific Hidden Markov Models (HMMs) and signal information in time and frequency domain, a Support Vector Machines classifier (SVM) was designed and validated. The 90.5% of subjects was assigned to the right group after leave-one-subject–out cross validation and majority voting. The long-term goal we point to is the gait assessment in everyday life to early detect gait alterations.