اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدA 1000-fold Acceleration of Hidden Markov Model Fitting using Graphical Processing Units, with application to Nonvolcanic Tremor Classification
46
0
0.0
(
0
)
نشر من قبل
Stephanus Marnus Stoltz
تاريخ النشر
2020
مجال البحث
الاحصاء الرياضي
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Hidden Markov models (HMMs) are general purpose models for time-series data widely used across the sciences because of their flexibility and elegance. However fitting HMMs can often be computationally demanding and time consuming, particularly when the the number of hidden states is large or the Markov chain itself is long. Here we introduce a new Graphical Processing Unit (GPU) based algorithm designed to fit long chain HMMs, applying our approach to an HMM for nonvolcanic tremor events developed by Wang et al.(2018). Even on a modest GPU, our implementation resulted in a 1000-fold increase in speed over the standard single processor algorithm, allowing a full Bayesian inference of uncertainty related to model parameters. Similar improvements would be expected for HMM models given large number of observations and moderate state spaces (<80 states with current hardware). We discuss the model, general GPU architecture and algorithms and report performance of the method on a tremor dataset from the Shikoku region, Japan.
قيم البحث
اقرأ أيضاً
Scattering maps from strained or disordered nano-structures around a Bragg reflection can either be computed quickly using approximations and a (Fast) Fourier transform, or using individual atomic positions. In this article we show that it is possibl
e to compute up to 4.10^10 $reflections.atoms/s using a single graphic card, and we evaluate how this speed depends on number of atoms and points in reciprocal space. An open-source software library (PyNX) allowing easy scattering computations (including grazing incidence conditions) in the Python language is described, with examples of scattering from non-ideal nanostructures.
Many modern statistical applications involve inference for complicated stochastic models for which the likelihood function is difficult or even impossible to calculate, and hence conventional likelihood-based inferential echniques cannot be used. In
such settings, Bayesian inference can be performed using Approximate Bayesian Computation (ABC). However, in spite of many recent developments to ABC methodology, in many applications the computational cost of ABC necessitates the choice of summary statistics and tolerances that can potentially severely bias the estimate of the posterior. We propose a new piecewise ABC approach suitable for discretely observed Markov models that involves writing the posterior density of the parameters as a product of factors, each a function of only a subset of the data, and then using ABC within each factor. The approach has the advantage of side-stepping the need to choose a summary statistic and it enables a stringent tolerance to be set, making the posterior less approximate. We investigate two methods for estimating the posterior density based on ABC samples for each of the factors: the first is to use a Gaussian approximation for each factor, and the second is to use a kernel density estimate. Both methods have their merits. The Gaussian approximation is simple, fast, and probably adequate for many applications. On the other hand, using instead a kernel density estimate has the benefit of consistently estimating the true ABC posterior as the number of ABC samples tends to infinity. We illustrate the piecewise ABC approach for three examples; in each case, the approach enables exact matching between simulations and data and offers fast and accurate inference.
We use autoregressive hidden Markov models and a time-frequency approach to create meaningful quantitative descriptions of behavioral characteristics of cerebellar ataxias from wearable inertial sensor data gathered during movement. Wearable sensor d
ata is relatively easily collected and provides direct measurements of movement that can be used to develop useful behavioral biomarkers. Sensitive and specific behavioral biomarkers for neurodegenerative diseases are critical to supporting early detection, drug development efforts, and targeted treatments. We create a flexible and descriptive set of features derived from accelerometer and gyroscope data collected from wearable sensors while participants perform clinical assessment tasks, and with them estimate disease status and severity. A short period of data collection ($<$ 5 minutes) yields enough information to effectively separate patients with ataxia from healthy controls with very high accuracy, to separate ataxia from other neurodegenerative diseases such as Parkinsons disease, and to give estimates of disease severity.
Intrusion detection is only a starting step in securing IT infrastructure. Prediction of intrusions is the next step to provide an active defense against incoming attacks. Current intrusion prediction methods focus mainly on prediction of either intr
usion type or intrusion category and do not use or provide contextual information such as source and target IP address. In addition most of them are dependant on domain knowledge and specific scenario knowledge. The proposed algorithm employs a bag-of-words model together with a hidden Markov model which not depend on specific domain knowledge. Since this algorithm depends on a training process it is adaptable to different conditions. A key advantage of the proposed algorithm is the inclusion of contextual data such as source IP address, destination IP range, alert type and alert category in its prediction, which is crucial for an eventual response. Experiments conducted using a public data set generated over 2500 alert predictions and achieved accuracy of 81% and 77% for single step and five step predictions respectively for prediction of the next alert cluster. It also achieved an accuracy of prediction of 95% and 92% for single step and five step predictions respectively for prediction of the next alert category. The proposed methods achieved a prediction accuracy improvement of 5% for alert category over existing variable length Markov chain intrusion prediction methods, while providing more information for a possible defense.
A framework is presented to model instances and degrees of local item dependence within the context of diagnostic classification models (DCMs). The study considers an undirected graphical model to describe dependent structure of test items and draws
inference based on pseudo-likelihood. The new modeling framework explicitly addresses item interactions beyond those explained by latent classes and thus is more flexible and robust against the violation of local independence. It also facilitates concise interpretation of item relations by regulating complexity of a network underlying the test items. The viability and effectiveness are demonstrated via simulation and a real data example. Results from the simulation study suggest that the proposed methods adequately recover the model parameters in the presence of locally dependent items and lead to a substantial improvement in estimation accuracy compared to the standard DCM approach. The analysis of real data demonstrates that the graphical DCM provides a useful summary of item interactions in regards to the existence and extent of local dependence.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
