The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Children with autism often experience sudden meltdowns which not only makes the moment tough for the caretakers/parents but also make the children hurt themselves physically. Studies have discovered that children with autistic spectrum disorder exhibit certain actions through which we can anticipate mutilating meltdowns in them. The objective of our project is to build a system that can recognize...
This paper describes an algorithm that parallelizes support vector machines. The data is split into subsets and optimized separately with multiple SVMs, instead of analyzing the whole training set in one optimization step. The partial results are combined and filtered in a cascade of SVMs. The process terminates when the global optimum is reached. The Cascade SVM is spread over multiple processors...
Some pattern recognition techniques may present a high computational cost for learning samples' behaviour. The Optimum-Path Forest (OPF) classifier has been recently developed in order to overcome such drawbacks. Although it can achieve faster training steps when compared to some state-of-art techniques, OPF can be slower for testing in some situations. Therefore, we propose in this paper an implementation...
In this paper, we presented a Graphics Processing Unit (GPU)-based training algorithm for Optimum-Path Forest (OPF) classifier. The proposed approach employs the idea of a vector-matrix multiplication to speed up both traditional OPF training algorithm and a recently proposed Central Processing Unit (CPU)-based OPF training algorithm. Experiments in several public datasets have showed the efficiency...
Support vector machine (SVM) is a popular classifier dealing with small-scale datasets. It has outstanding performance compared to other classifiers. However the execution time is extremely long when training Big Data. The Graphics Processing Unit (GPU) is a massively parallel device which performs very well as a co-processor. NVIDIA proposed a programming platform, CUDA, in 2006, which makes it much...
This paper presents performance evaluation of GPU-accelerated Support Vector Machines (SVMs) using large datasets. Although SVMs algorithm is popular among machine learning researchers and data mining practitioners, its computational time is too long and impractical for large datasets due to its complex Quadratic Programming (QP) solver. The result shows that using GPU-accelerated SVMs can significantly...
In recent years, with the improvement of sensor technologies, the volumes of remote sensing data are increased dramatically. The feature extraction of hyper spectral remotely sensed images can reduce such high-dimensional datasets, solve the big data problem, avoid the Hughes phenomena and improve the classification performance. Accordingly, this paper presents a framework for feature extraction of...
This brief proposes a continuously-valued Markov random field (MRF) model with separable filter bank, denoted as MRFSepa, which significantly reduces the computational complexity in the MRF modeling. In this framework, we design a novel gradient-based discriminative learning method to learn the potential functions and separable filter banks. We learn MRFSepa models with 2-D and 3-D separable filter...
The goal of face detection is to determine the presence of faces in arbitrary images, along with their locations and dimensions. As it happens with any graphics workloads, these algorithms benefit from data-level parallelism. Existing parallelization efforts strictly focus on mapping different divide and conquer strategies into multicore CPUs and GPUs. However, even the most advanced single-chip many-core...
Facial recognition techniques are of interest for tracking and identification in densely populated areas where security is an important concern. Traditional recognition techniques have yielded acceptable results with high repeatability but require special conditions such as a voluntary and stationary subject, close proximity, and appropriate lighting. Because no single algorithm yields robust results...
Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. Our biologically plausible, wide and deep artificial neural network architectures can. Small (often minimal) receptive fields of convolutional winner-take-all neurons yield large network depth, resulting in roughly as many sparsely connected...
Owing to the high upgrade speed of computer hardware, the courses of computer hardware and the cor-relative software courses are eager to be updated synchronously. College faculties are the key resource of higher education, so faculty training of computer hardware courses is vital. In this paper, we propose a faculty training program for the college faculties of computer hardware courses, which combines...
Twitter is an online social network service to supply the place to be released the short sentences as free. Recently, this service has a few hundred million users, and we can collect their Tweets easily. In this paper, we propose the climatic hazard detection method by using Twitter as a social sensor and by using neural network as a machine learning method. However the data size of the text classification...
We present a new pedestrian detector that improves both in speed and quality over state-of-the-art. By efficiently handling different scales and transferring computation from test time to training time, detection speed is improved. When processing monocular images, our system provides high quality detections at 50 fps. We also propose a new method for exploiting geometric context extracted from stereo...
Liquid chromatography-based tandem mass spectrometry (LC-MS) technique allows for identification and quantification of thousands of proteins in parallel. This technique coupled with a feed-forward artificial neural network provides a technique to analyze and select protein panels for use in multi-biomarker panel discovery applications. In this study, we enhance this technique by utilizing massively...
Ordered-statistic constant false alarm rate (OS-CFAR) detectors provide improved robustness over cell-averaging CFAR (CA-CFAR) detectors in multiple target and heterogeneous clutter environments. However, this benefit comes at the cost of generally increased processing time due to the need for a rank-ordering of the CFAR training data. Realtime implementations of OS-CFAR must consider this additional...
Quantitative structure activity relationship (QSAR) modeling using high-throughput screening (HTS) data is a powerful technique which enables the construction of predictive models. These models are utilized for the in silico screening of libraries of molecules for which experimental screening methods are both cost- and time-expensive. Machine learning techniques excel in QSAR modeling where the relationship...
Forecasting the volatility of multivariate asset return is an important issue in financial econometric analysis, where the volatility is represented by a conditional covariance matrix (CCM). Traditional models for predicting CCM such as GARCH(1, 1) models are not capable of dealing with high-dimensional case for there are $N(N+1)/2$ necessary entries in the CCM of $N$-variant asset return. We propose...
The training procedure of Hidden Markov Model (HMM) based Speech Recognition is often very time consuming because of its high computational complexity. The new parallel hardware like GPU can provide multi-thread processing and very high floating-point capability. We take advantage of GPU to accelerate a popular HMM-based Speech Recognition package ¨C HTK. Based on the sequential code of HTK, we design...
Face recognition is the most complex approach for identifying people in biometrics. Other biometric approaches, such as iris recognition, finger print, etc, for human recognition require close contact with the person. Traditional algorithm for face recognition are concerned with both accuracy and timing. Timing issue is more critical when dealing with real time images, thus, attention was directed...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.