A Predictive Initialization of Hidden State Parameters in a Hidden Markov Model for Hand Gesture Recognition

This paper presents a lightweight convolutional neural network (CNN) model for hand gesture recognition and implements it on a nano drone for flight control. Specifically, the nano drone captures images and determines its flight direction based on the hand gesture recognition results of the captured images. Due to limited hardware resources, the nano drone has only a 64KB L1 cache, a 512KB L2 cache, and a RISC-V CPU, which makes CNN deployment challenging. To address this issue, we design and optimize a 10-layer simplified CNN model and quantize the computations to INT8. Experimental results show that the proposed model achieves 90% accuracy in 5-class hand gesture recognition while maintaining a compact size of only 72.5 KB. Furthermore, it operates at a recognition speed of 7 FPS, enabling real-time performance.

Gesture recognition has multiple applications in medical and engineering fields. The problem of hand gesture recognition consists of identifying, at any moment, a given gesture performed by the hand. In this work, we propose a new model for hand gesture recognition in real time. The input of this model is the surface electromyography measured by the commercial sensor the Myo armband placed on the forearm. The output is the label of the gesture executed by the user at any time. The proposed model is based on the Λ-nearest neighbor and dynamic time warping algorithms. This model can learn to recognize any gesture of the hand. To evaluate the performance of our model, we measured and compared its accuracy at recognizing 5 classes of gestures to the accuracy of the proprietary system of the Myo armband. As a result of this evaluation, we determined that our model performs better (86% accurate) than the Myo system (83%).

Human hand recognition plays an important role in a wide range of applications ranging from sign language translators, gesture recognition, augmented reality, surveillance and medical image processing to various Human Computer Interaction (HCI) domains. Human hand is a complex articulated object consisting of many connected parts and joints. Therefore, for applications that involve HCI one can find many challenges to establish a system with high detection and recognition accuracy for hand posture and/or gesture. Hand posture is defined as a static hand configuration without any movement involved. Meanwhile, hand gesture is a sequence of hand postures connected by continuous motions. During the past decades, many approaches have been presented for hand posture and/or gesture recognition. In this paper, we provide a survey on approaches which are based on Hidden Markov Models (HMM) for hand posture and gesture recognition for HCI applications.

Prediction of 24-hour-average PM2.5 concentrations using a hidden Markov model with different emission distributions in Northern California

The state-dependent speciation and extinction (SSE) models have recently been criticized due to their high rates of "false positive" results. Many researchers have advocated avoiding SSE models in favor of other "nonparametric" or "semiparametric" approaches. The hidden Markov modeling (HMM) approach provides a partial solution to the issues of model adequacy detected with SSE models. The inclusion of "hidden states" can account for rate heterogeneity observed in empirical phylogenies and allows for reliable detection of state-dependent diversification or diversification shifts independent of the trait of interest. However, the adoption of HMM has been hampered by the interpretational challenges of what exactly a "hidden state" represents, which we clarify herein. We show that HMMs in combination with a model-averaging approach naturally account for hidden traits when examining the meaningful impact of a suspected "driver" of diversification. We also extend the HMM to the geographic state-dependent speciation and extinction (GeoSSE) model. We test the efficacy of our "GeoHiSSE" extension with both simulations and an empirical dataset. On the whole, we show that hidden states are a general framework that can distinguish heterogeneous effects of diversification attributed to a focal character.

Hand gesture recognition for human-computer interaction has become very popular in recent times. The main problem of this technology is how the system can recognize the presence of a gesture in a streaming video. In this paper, we propose a model that can recognize hand motion gesture in avideo stream using Support Vector Machine and Hidden-Markov model. Support Vector Machine has the advantage of generalizing classification. On the other hand, Hidden Markov Model is a statistical model that is capable of modeling Spatial-temporal time series. This system is divided into two main processes. First, this system recognizes hand posture using SMV (static gesture recognition) and generates sequence observation which is used for the second process later. The second process is recognizing dynamic hand gesture with the sequence observation from the static gesture. The implementation shows that static hand gesture recognition achieves average accuracy at 91% using testing dataset. Meanwhile,dynamically isolated hand gesture recognition gets average accuracy at 89% using testing dataset. We also have tested the system with continuous dynamic gesture using video stream. The system can recognize the gesture very well with accuracy of 83%. This achievement shows that the model can be used in human computer-interaction with specific supports such as Vector Machine and Hidden Markov Model parameter.

In this paper, we propose a hand gesture-based interface for navigating 3D virtual space using Leap Motion and machine learning. Using the interface, the user can control an avatar in a first-person perspective by making it move in 4 directions, rotate its viewpoint, grasp/release an object, and adjust moving/rotating speed. After defining 9 types of hand gesture, we used the leap motion device to capture 150 hand skeletal datasets for each type, and converted them into feature datasets, with which we developed a heuristic algorithm and a machine learning (multilayer perceptron) model for hand gesture recognition. Experimental results showed that the machine learning model was much more accurate than the heuristic algorithm. We also implemented 3 methods for 3D virtual space navigation: the use of keyboard and mouse (KB) and the use of the leap motion device with the heuristic algorithm (HA) and the machine learning model (ML). After conducting a user study in which each of 15 subjects was guided to find a target object and move it to a start position with the methods, we found from the user study that the method ML outperformed the others in task time and in most of qualitative aspects.

In this paper, we purpose a Hand gesture recognition model which can be used in real time application. This model is based on the mediapipe frame work of the google, Tensor flow in openCv and python and classification using feed forward neural network with keras model. The structure of the proposed work consists of 3 modules: Grabbing the frames, detecting hand landmarks and classification. The proposed model has the accuracy 95.7% at recognizing 10 kinds of hand gestures(Thumbs up, Thumbs down, Peace, Smile, Rock, Ok, Fist, livelong, call me, stop). A hand gesture recognition model that reacts rapidly and with generally acceptable accuracy is one of this work’s primary achievements and pre trained model for feature extraction. The unique approach of the suggested approach is that it detects hand landmarks using Google’s MediaPipe, which is faster and more accurate than traditional methods that rely on geometry, form, and edge data. For modelling sequence data and for recognising gestures, the LSTM model has proven to be quite successful.

Multiply correlated datasets have become increasingly common in genome-wide location analysis of regulatory proteins and epigenetic modifications. Their correlation can be directly incorporated into a statistical model to capture underlying biological interactions, but such modeling quickly becomes computationally intractable. We present sparsely correlated hidden Markov models (scHMM), a novel method for performing simultaneous hidden Markov model (HMM) inference for multiple genomic datasets. In scHMM, a single HMM is assumed for each series, but the transition probability in each series depends on not only its own hidden states but also the hidden states of other related series. For each series, scHMM uses penalized regression to select a subset of the other data series and estimate their effects on the odds of each transition in the given series. Following this, hidden states are inferred using a standard forward-backward algorithm, with the transition probabilities adjusted by the model at each position, which helps retain the order of computation close to fitting independent HMMs (iHMM). Hence, scHMM is a collection of inter-dependent non-homogeneous HMMs, capable of giving a close approximation to a fully multivariate HMM fit. A simulation study shows that scHMM achieves comparable sensitivity to the multivariate HMM fit at a much lower computational cost. The method was demonstrated in the joint analysis of 39 histone modifications, CTCF and RNA polymerase II in human CD4+ T cells. scHMM reported fewer high-confidence regions than iHMM in this dataset, but scHMM could recover previously characterized histone modifications in relevant genomic regions better than iHMM. In addition, the resulting combinatorial patterns from scHMM could be better mapped to the 51 states reported by the multivariate HMM method of Ernst and Kellis. The scHMM package can be freely downloaded from http://sourceforge.net/p/schmm/ and is recommended for use in a linux environment.

Hand gesture recognition (HGR) systems using electromyography (EMG) bracelet-type sensors are currently largely used over other HGR technologies. However, bracelets are susceptible to electrode rotation, causing a decrease in HGR performance. In this work, HGR systems with an algorithm for orientation correction are proposed. The proposed orientation correction method is based on the computation of the maximum energy channel using a synchronization gesture. Then, the channels of the EMG are rearranged in a new sequence which starts with the maximum energy channel. This new sequence of channels is used for both training and testing. After the EMG channels are rearranged, this signal passes through the following stages: pre-processing, feature extraction, classification, and post-processing. We implemented user-specific and user-general HGR models based on a common architecture which is robust to rotations of the EMG bracelet. Four experiments were performed, taking into account two different metrics which are the classification and recognition accuracy for both models implemented in this work, where each model was evaluated with and without rotation of the bracelet. The classification accuracy measures how well a model predicted which gesture is contained somewhere in a given EMG, whereas recognition accuracy measures how well a model predicted when it occurred, how long it lasted, and which gesture is contained in a given EMG. The results of the experiments (without and with orientation correction) executed show an increase in performance from 44.5% to 81.2% for classification and from 43.3% to 81.3% for recognition in user-general models, while in user-specific models, the results show an increase in performance from 39.8% to 94.9% for classification and from 38.8% to 94.2% for recognition. The results obtained in this work evidence that the proposed method for orientation correction makes the performance of an HGR robust to rotations of the EMG bracelet.

Hand gestures have been widely applied to interface as the way of interaction between human and computers. Since a human hand can express various shapes of gestures, previous models for recognizing them cannot distinguish them accurately since they use only single model for recognition. For efficient hand gesture recognition with its enhanced performance, we propose the fuzzy c-means clustering based mixture-of-experts (FME). The proposed method uses multiple local experts obtained via fuzzy c-means clustering and decisions from them are combined with the gating network. To evaluate the performance of the proposed method, we conduct experiments including comparisons with alternative models for hand gesture recognition. As the result of experiments, the proposed model shows improved gesture recognition performance, especially performance on similar hand gesture recognition.

This paper describes the study of techniques used in hand gesture recognition in sign language interpretation. The study is discussed from two aspects: the process of hand gesture recognition and the techniques of feature extraction in hand gesture recognition. The techniques of feature extraction in hand gesture recognition are grouped into five categories: Hidden Markov Model (HMM), Artificial Neural Networks (ANN), Support Vector Machines (SVM), Dynamic Bayesian Network (DBN), and Dynamic Time Warping (DTW). The main ideas and the application of each technique are described in detail.

Eye-tracking allows researchers to infer cognitive processes from eye movements that areclassified into distinct events. Parsing the events is typically done by algorithms. Here weaim at developing an unsupervised, generative model that can be fitted to eye-movementdata using maximum likelihood estimation. This approach allows hypothesis testing aboutfitted models, next to being a method for classification. We developed gazeHMM, an algorithmthat uses a hidden Markov model as a generative model, has few critical parametersto be set by users, and does not require human coded data as input. The algorithm classifiesgaze data into fixations, saccades, and optionally postsaccadic oscillations and smooth pursuits.We evaluated gazeHMM’s performance in a simulation study, showing that it successfullyrecovered hidden Markov model parameters and hidden states. Parameters wereless well recovered when we included a smooth pursuit state and/or added even small noiseto simulated data. We applied generative models with different numbers of events to benchmarkdata. Comparing them indicated that hidden Markov models with more events thanexpected had most likely generated the data. We also applied the full algorithm to benchmarkdata and assessed its similarity to human coding and other algorithms. For static stimuli,gazeHMM showed high similarity and outperformed other algorithms in this regard. Fordynamic stimuli, gazeHMM tended to rapidly switch between fixations and smooth pursuitsbut still displayed higher similarity than most other algorithms. Concluding that gazeHMMcan be used in practice, we recommend parsing smooth pursuits only for exploratory purposes.Future hidden Markov model algorithms could use covariates to better capture eyemovement processes and explicitly model event durations to classify smooth pursuits moreaccurately.

In fact, millions of people in the world speak many languages. In order to communicate with each other, it is necessary to know the language we use to perform this operation. The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in the daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3 challenge source. We proposed an Arabic Dialect Identification System called "Building a System for Arabic Dialects Identification based on Speech Recognition using Hidden Markov Models (HMMs)" that takes Input as speech utterances and produces output as dialect being spoken. During the training phase, speech utterances from one or more dialects were analyzed to capture the important properties of audio signals in terms of time and frequency. During the testing phase, previously unseen test utterances were utilized to the system, and the system outputs the dialect associated with the model of dialect that most closely matches the test utterance. The proposed model of the system shows promising results of the model for each dialects match.

A comparative study of two state-of-the-art sequence processing techniques for hand gesture recognition