Yoichi Muraoka

Real-time beat tracking for drumless audio signals: chord change detection for musical decisions

Abstract This paper describes a real-time beat-tracking system that detects a hierarchical beat structure in musical audio signals without drum-sounds. Most previous systems have dealt with MIDI signals and had difficulty in applying, in real time, musical heuristics to audio signals containing sounds of various instruments and in tracking beats above the quarter-note level. Our system not only tracks beats at the quarter-note level but also detects beat structure at the half-note and measure levels. To make musical decisions about the audio signals, we propose a method of detecting chord changes that does not require chord names to be identified. The method enables the system to track beats at different rhythmic levels – for example, to find the beginnings of half notes and measures – and to select the best of various hypotheses about beat positions. Experimental results show that the proposed method was effective to detect the beat structure in real-world audio signals sampled from compact discs of popular music.

A beat tracking system for acoustic signals of music

This paper presents a beat tracking system that processes acoustic signals of music and recognizes temporal positions of beats in time. Musical beat tracking is needed by various multimedia applications such as video editing, audio editing, and stage lighting control. Previous systems were not able to deal with acoustic signals that contained sounds of various instruments, especially drums. They dealt with either MIDI signals or acoustic signals played on a few instruments, and in the latter case, did not work in real time. Our system deals with popular music in which drums maintain the beat. Because our system examines multiple hypotheses in parallel, it can follow beats without losing track of them, even if some hypotheses become wrong. Our system has been implemented on a parallel computer, the Fujitsu AP1000. In our experiment, the system correctly tracked beats in 27 out of 30 commercially distributed popular songs.

Predicting mostly disordered proteins by using structure-unknown protein data

Predicting intrinsically disordered proteins is important in structural biology because they are thought to carry out various cellular functions even though they have no stable three-dimensional structure. We know the structures of far more ordered proteins than disordered proteins. The structural distribution of proteins in nature can therefore be inferred to differ from that of proteins whose structures have been determined experimentally. We know many more protein sequences than we do protein structures, and many of the known sequences can be expected to be those of disordered proteins. Thus it would be efficient to use the information of structure-unknown proteins in order to avoid training data sparseness. We propose a novel method for predicting which proteins are mostly disordered by using spectral graph transducer and training with a huge amount of structure-unknown sequences as well as structure-known sequences. When the proposed method was evaluated on data that included 82 disordered proteins and 526 ordered proteins, its sensitivity was 0.723 and its specificity was 0.977. It resulted in a Matthews correlation coefficient 0.202 points higher than that obtained using FoldIndex, 0.221 points higher than that obtained using the method based on plotting hydrophobicity against the number of contacts and 0.07 points higher than that obtained using support vector machines (SVMs). To examine robustness against training data sparseness, we investigated the correlation between two results obtained when the method was trained on different datasets and tested on the same dataset. The correlation coefficient for the proposed method is 0.14 higher than that for the method using SVMs. When the proposed SGT-based method was compared with four per-residue predictors (VL3, GlobPlot, DISOPRED2 and IUPred (long)), its sensitivity was 0.834 for disordered proteins, which is 0.052–0.523 higher than that of the per-residue predictors, and its specificity was 0.991 for ordered proteins, which is 0.036–0.153 higher than that of the per-residue predictors. The proposed method was also evaluated on data that included 417 partially disordered proteins. It predicted the frequency of disordered proteins to be 1.95% for the proteins with 5%–10% disordered sequences, 1.46% for the proteins with 10%–20% disordered sequences and 16.57% for proteins with 20%–40% disordered sequences. The proposed method, which utilizes the information of structure-unknown data, predicts disordered proteins more accurately than other methods and is less affected by training data sparseness.BackgroundPredicting intrinsically disordered proteins is important in structural biology because they are thought to carry out various cellular functions even though they have no stable three-dimensional structure. We know the structures of far more ordered proteins than disordered proteins. The structural distribution of proteins in nature can therefore be inferred to differ from that of proteins whose structures have been determined experimentally. We know many more protein sequences than we do protein structures, and many of the known sequences can be expected to be those of disordered proteins. Thus it would be efficient to use the information of structure-unknown proteins in order to avoid training data sparseness. We propose a novel method for predicting which proteins are mostly disordered by using spectral graph transducer and training with a huge amount of structure-unknown sequences as well as structure-known sequences.ResultsWhen the proposed method was evaluated on data that included 82 disordered proteins and 526 ordered proteins, its sensitivity was 0.723 and its specificity was 0.977. It resulted in a Matthews correlation coefficient 0.202 points higher than that obtained using FoldIndex, 0.221 points higher than that obtained using the method based on plotting hydrophobicity against the number of contacts and 0.07 points higher than that obtained using support vector machines (SVMs). To examine robustness against training data sparseness, we investigated the correlation between two results obtained when the method was trained on different datasets and tested on the same dataset. The correlation coefficient for the proposed method is 0.14 higher than that for the method using SVMs. When the proposed SGT-based method was compared with four per-residue predictors (VL3, GlobPlot, DISOPRED2 and IUPred (long)), its sensitivity was 0.834 for disordered proteins, which is 0.052–0.523 higher than that of the per-residue predictors, and its specificity was 0.991 for ordered proteins, which is 0.036–0.153 higher than that of the per-residue predictors. The proposed method was also evaluated on data that included 417 partially disordered proteins. It predicted the frequency of disordered proteins to be 1.95% for the proteins with 5%–10% disordered sequences, 1.46% for the proteins with 10%–20% disordered sequences and 16.57% for proteins with 20%–40% disordered sequences.ConclusionThe proposed method, which utilizes the information of structure-unknown data, predicts disordered proteins more accurately than other methods and is less affected by training data sparseness.

HPC Benchmarks on Amazon EC2

Cloud computing is grabbing people’s attention rapidly as a convenient resource of computational power, and several commercial cloud computing services are accelerating the situation. While priced cloud computing services save pains to maintain the computational environment, there are several drawbacks such as overhead of virtual machines, possibility to share one physical machine with several virtual machines, and indeterminacy of topological allocation of their own virtual machines. This paper verifies usability of Amazon Elastic Computing Cloud (Amazon EC2) from the view of both value as a research tool, and cost performance as an alternative high performance computing environment to supercomputers. We evaluated computational performance through some experiments with several high performance computing benchmarks, and estimated the operational cost.

Extended forecast of CPU and network load on computational Grid

To achieve effective load balancing and a robust Grid environment, extended load forecast for computational resources is increasingly required. Thus, this paper proposes a method of predicting network and CPU load variance within a wide range, from several minutes to over a week. This is the widest range of prediction of the existing algorithms in the load of computational resources for the Grid environment. The distinctiveness of our algorithm is in using seasonal load variation for both load variance and one-step-ahead prediction. We apply seasonal fluctuation in CPU load to network load variation especially for network load variance prediction. Furthermore, the Markov model-based meta-predictor is used for one-step-ahead prediction, which is sensitive to late trends. The results of the experiments demonstrate that our algorithm gives a good curve for expected 8-day-long load variance, and makes accurate one-step-ahead predictions. The mean error rate for one-step-ahead predictions is 9.4% in the case of network load, and 6.2% in the case of CPU load. Moreover, the least mean error rate for wider range forecasts is 5.5% for network load variation, and 3.6% for CPU load variation.

Real-time image mosaicing from a video sequence

The paper describes a fast and robust image registration method that can be used to create a panoramic image/video from video sequences. To estimate alignment parameters for image registration, the method computes pseudo motion vectors that are rough estimates of optical flows at each selected pixel. Using the proposed method, we implemented a software system that can, with a low-cost PC, create and display panoramic images/videos in real time.

Experiments of collecting WWW information using distributed WWW robots

This paper presents the experiments of collecting the documents on the WWW using distributed WWW robots. We propose distributed WWW robots to collect the documents quickly. Our final goal is to collect all of the documents on the WWW in Japan within one day. Currently, eight distributed WWW Robots are running in Japan. The experimental results show that we are able to gain 5.8 to 9.7 times speedup when four distributed WWW robots are placed at different places in comparison with when only one WWW robot is used.

Asynchronous migration of execution context in Java Virtual Machines

Abstract The migration of the execution context has been applied to remote execution and mobile agents, and asynchronous migration can be applied to even more applications, such as load balancing. We have therefore designed a system for the migration of Java threads, one that allows asynchronous and heterogeneous migration of the execution context of the running code. This paper describes an overview of the system, the problems we have faced in designing its facilities, and the results of preliminary evaluations of its performance.

A panorama-based technique for annotation overlay and its real-time implementation

The panorama-based annotation method described uses a panoramic image as the source of information about the positions of the annotations. It finds image alignment parameters between an input frame and the panoramic image and then maps the positions of annotations from the panoramic image to the input frame and displays the input frame overlaid with those annotations. Camera movement from place to place is made possible by preparing a set of panoramic images in advance. The panoramic image that gives the least mean squares error of the image alignment is selected automatically and is appropriately switched as the camera moves around. The position of the camera can be tracked by monitoring the switching of selected panoramic images. Experimental results show that this method can find image alignment parameters, display input frames overlaid with the annotations, and switch the panoramic image appropriately in real-time.

ANGLE: A SEQUENCING ERRORS RESISTANT PROGRAM FOR PREDICTING PROTEIN CODING REGIONS IN UNFINISHED cDNA

In the process of making full-length cDNA, predicting protein coding regions helps both in the preliminary analysis of genes and in any succeeding process. However, unfinished cDNA contains artifacts including many sequencing errors, which hinder the correct evaluation of coding sequences. Especially, predictions of short sequences are difficult because they provide little information for evaluating coding potential. In this paper, we describe ANGLE, a new program for predicting coding sequences in low quality cDNA. To achieve error-tolerant prediction, ANGLE uses a machine-learning approach, which makes better expression of coding sequence maximizing the use of limited information from input sequences. Our method utilizes not only codon usage, but also protein structure information which is difficult to be used for stochastic model-based algorithms, and optimizes limited information from a short segment when deciding coding potential, with the result that predictive accuracy does not depend on the length of an input sequence. The performance of ANGLE is compared with ESTSCAN on four dataset each of them having a different error rate (one frame-shift error or one substitution error per 200-500 nucleotides) and on one dataset which has no error. ANGLE outperforms ESTSCAN by 9.26% in average Matthewss correlation coefficient on short sequence dataset (< 1000 bases). On long sequence dataset, ANGLE achieves comparable performance.