Audio streams, such as news broadcasting, meeting rooms, and special video comprise sound from an extensive variety of sources. The detection of audio events including speech, coughing, gunshots, etc. leads to intelli...
详细信息
Audio streams, such as news broadcasting, meeting rooms, and special video comprise sound from an extensive variety of sources. The detection of audio events including speech, coughing, gunshots, etc. leads to intelligent audio event detection (AED). With substantial attention geared to AED for various types of applications, such as security, speech recognition, speaker recognition, home care, and health monitoring, scientists are now more motivated to perform extensive research on AED. The deployment of AED is actually a more complicated task when going beyond exclusively highlighting audio events in terms of feature extraction and classification in order to select the best features with high detection accuracy. To date, a wide range of different detection systems based on intelligent techniques have been utilized to create machine learning-based audio event detection schemes. Nevertheless, the preview study does not encompass any state-of-the-art reviews of the proficiency and significances of such methods for resolving audio event detection matters. The major contribution of this work entails reviewing and categorizing existing AED schemes into preprocessing, feature extraction, and classification methods. The importance of the algorithms and methodologies and their proficiency and restriction are additionally analyzed in this study. This research is expanded by critically comparing audio detection methods and algorithms according to accuracy and false alarms using different types of datasets.
In this work, we describe and analyze algorithms for 2D wavelet packet (WP) decomposition for multicomputers and multiprocessors. In the case of multicomputers, the main goal is the generalization of former parallel W...
详细信息
In this work, we describe and analyze algorithms for 2D wavelet packet (WP) decomposition for multicomputers and multiprocessors. In the case of multicomputers, the main goal is the generalization of former parallel WP algorithms which are constrained to a number of processor elements equal to a power of 4. For multiprocessors, we discuss several optimizations of shared-memory algorithms and finally we compare the results obtained on multicomputers and multi-processors employing the message passing (MPI) and shared-memory programming (OpenMP) paradigm, respectively. (C) 2002 Elsevier Science Ltd. All rights reserved.
A simple fatigue life prediction algorithm using the modified NASGRO equation is proposed in this paper. The NASGRO equation is modified by introducing the concept of intrinsic effective threshold stress intensity fac...
详细信息
A simple fatigue life prediction algorithm using the modified NASGRO equation is proposed in this paper. The NASGRO equation is modified by introducing the concept of intrinsic effective threshold stress intensity factor (SIF) range (Delta K-eff)(th). One advantage of the proposed method is that the complex growth behavior analysis of small cracks can be avoided, and then the fatigue life can be calculated by directly integrating the crack growth model from the initial defect size to the critical crack size. The fatigue limit and the intrinsic effective threshold SIF range (Delta K-eff)(th) are used to calculate the initial defect size or initial flaw size. The value of (Delta K-eff)(th) is determined by extrapolating the crack propagation rate curves. Instead of using the fatigue limit determined by the fatigue strength at the specific fatigue life, the fatigue limit is selected based on the horizontal tendency of the S-N curve. The calculated fatigue lives are compared to the experimental data of two different alloys. The predicted S-N curves agree with the test data well. Besides, the prediction results are compared with that calculated using the FASTRAN code. Results indicate that the proposed life prediction algorithm is simple and efficient.
Kernel Fisher discriminant analysis (KFDA) method has demonstrated its success in extracting facial features for face recognition. Compared to linear techniques, it can better describe the complex and nonlinear variat...
详细信息
Kernel Fisher discriminant analysis (KFDA) method has demonstrated its success in extracting facial features for face recognition. Compared to linear techniques, it can better describe the complex and nonlinear variations of face images. However, a single kernel is not always suitable for the applications of face recognition which contain data from multiple, heterogeneous sources, such as face images under huge variations of pose, illumination, and facial expression. To improve the performance of KFDA in face recognition, a novel algorithm named multiple data-dependent kernel Fisher discriminant analysis (MDKFDA) is proposed in this paper. The constructed multiple data-dependent kernel (MDK) is a combination of several base kernels with a data-dependent kernel constraint on their weights. By solving the optimization equation based on Fisher criterion and maximizing the margin criterion, the parameter optimization of data-dependent kernel and multiple base kernels is achieved. Experimental results on the three face databases validate the effectiveness of the proposed algorithm.
Using local invariant features has been proven by published literature to be powerful for image processing and pattern recognition tasks. However, in energy aware environments, these invariant features would not scale...
详细信息
Using local invariant features has been proven by published literature to be powerful for image processing and pattern recognition tasks. However, in energy aware environments, these invariant features would not scale easily because of their computational requirements. Motivated to find an efficient building recognition algorithm based on scale invariant feature transform (SIFT) keypoints, we present in this paper uSee, a supervised learning framework which exploits the symmetrical and repetitive structural patterns in buildings to identify subsets of relevant clusters formed by these keypoints. Once an image is captured by a smart phone, uSee preprocesses it using variations in gradient angle-and entropy-based measures before extracting the building signature and comparing its representative SIFT keypoints against a repository of building images. Experimental results on 2 different databases confirm the effectiveness of uSee in delivering, at a greatly reduced computational cost, the high matching scores for building recognition that local descriptors can achieve. With only 14.3% of image SIFT keypoints, uSee exceeded prior literature results by achieving an accuracy of 99.1% on the Zurich Building Database with no manual rotation;thus saving significantly on the computational requirements of the task at hand.
Broadcasting and multicasting are fundamental operations. In this work we develop algorithms for performing broadcast and multicast in clusters of workstations. In this model, sending a message to a machine in the sam...
详细信息
Broadcasting and multicasting are fundamental operations. In this work we develop algorithms for performing broadcast and multicast in clusters of workstations. In this model, sending a message to a machine in the same cluster takes 1 time unit, and sending a message to a machine in a different cluster takes C(a parts per thousand yen1) time units. The clusters may have arbitrary sizes. Lowekamp and Beguelin proposed heuristics for this model, but their algorithms may produce broadcast times that are arbitrarily worse than optimal. We develop the first constant factor approximation algorithms for this model. Algorithm LCF (Largest Cluster First) for the basic model is simple, efficient and has a worst case approximation guarantee of 2. We then extend these models to more complex models where we remove the assumption that an unbounded amount of communication may happen using the global network. The algorithms for these models build on the LCF method developed for the basic problem. Finally, we develop broadcasting algorithms for the postal model where the sending node does not block for C time units when the message is in transit.
A batch process can be viewed as a two-dimensional (2D) system with dynamics in both time and batch directions. To tackle these 2D dynamics, many control algorithms have been proposed by combining iterative learning c...
详细信息
A batch process can be viewed as a two-dimensional (2D) system with dynamics in both time and batch directions. To tackle these 2D dynamics, many control algorithms have been proposed by combining iterative learning control (TLC) with high-performance continuous control algorithms under a 2D framework. However, these algorithms require large computational load and memory, which are often demanding for the software and hardware of the controllers in several fast batch processes. In this paper, a 2D predictive functional control algorithm that combines ILC with predictive functional control (PFC) is proposed. Owing to the compactness and effectiveness of PFC, the proposed control algorithm can reduce the required computational load and memory. Other than the general form of the control law, two concise and practical forms are provided as well. The proposed control scheme is tested through simulations and implementation in an injection molding process, which is a typical fast batch process. Results confirm the good performance of the proposed control algorithm.
This paper presents and analyses an iterative process for the numerical realization of contact problems with Coulomb friction which is based on the method of successive approximations combined with a splitting type ap...
详细信息
This paper presents and analyses an iterative process for the numerical realization of contact problems with Coulomb friction which is based on the method of successive approximations combined with a splitting type approach. Numerical examples illustrate the efficiency of this method. (C) 2002 Elsevier Science B.V. All rights reserved.
The advantage of a new scheme for balanced detection has been investigated to reduce the influence of optical interference fringes when performing diode laser gas absorption spectroscopy employing lock-in amplifiers a...
详细信息
The advantage of a new scheme for balanced detection has been investigated to reduce the influence of optical interference fringes when performing diode laser gas absorption spectroscopy employing lock-in amplifiers and pigtailed lasers. The influence of the fringes has been reduced by comparing the lock-in 2 f signal due to the gas sample with that of a reference beam. The frequency regions outside the absorption feature have been used to obtain information on the interference fringe impact on the signal of interest. We have demonstrated an efficient way to reduce the influence of such fringes by employing this technique combined with non-linear signal processing methods. The different steps of the algorithm are presented. In the experimental arrangement presented, a reduction of the optical interference fringes by about 10 times is achieved, as demonstrated in measurements on molecular oxygen around 761 nm. The new technique is compared with an analog technique for balanced detection and certain advantages of the computer algorithm are pointed out. In particular, the emerging field of gas spectroscopy in scattering solid media strongly benefits from the technique presented.
This paper reviews an active control algorithm adopted for an active-passive composite tuned mass damper, which is a unique vibration control device equipped into an office building in Tokyo in 1993. The main purpose ...
详细信息
This paper reviews an active control algorithm adopted for an active-passive composite tuned mass damper, which is a unique vibration control device equipped into an office building in Tokyo in 1993. The main purpose of this device is to subdue the response motion of tall buildings under random disturbances such as wind pressures and small earthquakes. The main topics in this paper are: (1) the principle of the acceleration feedback algorithm, (2) the expected control performance, (3) the multi-modal control algorithm, (4) the observed performance of the applications using the algorithm.
暂无评论