detection of filled pauses is a challenging research problem which has several practical applications. It can be used to evaluate the spoken fluency skills of the speaker, to improve the performance of automatic speec...
详细信息
detection of filled pauses is a challenging research problem which has several practical applications. It can be used to evaluate the spoken fluency skills of the speaker, to improve the performance of automatic speech recognition systems or to predict the mental state of the speaker. This paper presents an algorithm for filled pause detection that is based on the premise that the vocal tract characteristics, and hence the formants, are stable during the production of a filled pause. The performance of the proposed algorithm is evaluated on real-life recordings of call center agents where the locations of the filled pauses are hand labeled. The proposed algorithm outperforms a standard cepstral stability based filled pause detection algorithm and a standard pitch-based detection technique.
This work is involved the threshold-free detection of QRS complexes in an abdominal electrocardiogram (AECG) waveform. The precision in the identification of QRS complexes is of great importance for on-line maternal h...
详细信息
This work is involved the threshold-free detection of QRS complexes in an abdominal electrocardiogram (AECG) waveform. The precision in the identification of QRS complexes is of great importance for on-line maternal heart rate calculation and, will lead to on line fetal heart detection. During the last century much work has been carried out in this field, using various methods ranging from filtering and threshold methods, through wavelet methods, to neural networks, and others, each of which has different effectiveness and weaknesses. Although their performance is generally good, but, the main weakness is that, they are threshold dependent. In the proposed algorithm a RR moving interval is calculated, based on normal maximum and minimum heart rate (HR). This has the advantage of ensuring that every R-peak is contained between the edges of the moving interval. Thus the effectiveness of this algorithm is that, it is threshold independent, and after every peak detection the RR moving interval is updated to calculate the next peak contained between its edges. The complete algorithm is implemented using MATLAB 7.4. The method is validated using 20 recorded data. The average sensitivity and average positive predictivity of the detection method are 99.05% and 99.8% respectively.
In this paper we investigate spectrum sensing for cognitive radio (CR) by using multiple spectrum sensors. We explore sensing schemes based on soft information combining, hard information combining and a two-stage det...
详细信息
ISBN:
(纸本)9781424425143
In this paper we investigate spectrum sensing for cognitive radio (CR) by using multiple spectrum sensors. We explore sensing schemes based on soft information combining, hard information combining and a two-stage detection scheme that uses both soft information combining and hard information combining. The two-stage detection scheme is shown to provide improved performance compared to sensing based on either hard information combining or soft information combining alone with a trade-off of sensing time. Computer simulation results are provided to validate the concept.
This paper presents a novel approach for automatic recognition of group activities for video surveillance applications. We propose to use a group representative to handle the recognition with flexible or varying numbe...
详细信息
ISBN:
(纸本)9781424438273
This paper presents a novel approach for automatic recognition of group activities for video surveillance applications. We propose to use a group representative to handle the recognition with flexible or varying number of group members, and use an asynchronous hidden Markov model (AHMM) to model the relationship between two people. Furthermore, we propose a group activity detection algorithm which can handle symmetric and asymmetric group activities, and demonstrate that this approach enables the detection of hierarchical interactions between people. Experimental results show the effectiveness of our approach.
Clustered microcalcifications (MCs) are one of the early signs of breast cancer, and they are of great importance for an early diagnosis. Moreover, the spatial distribution and the shape of the microcalcifications hav...
详细信息
Clustered microcalcifications (MCs) are one of the early signs of breast cancer, and they are of great importance for an early diagnosis. Moreover, the spatial distribution and the shape of the microcalcifications have a significant impact in medical practice to evaluate the probability of malignancy of the tumor. In this paper we investigate an approach based on boosted twin support vector (Boosting-TWSVM) for detection of microcalcifications clusters (MCs) in digital *** the algorithm, we formulate MCs detection as a supervised-learning problem and apply the trained Boosted-TWSVM classifier to develop the detection algorithm. We tested the proposed method using DDSM database of 80cases mammograms containing about 980 MCs. detection performance of the proposed method is evaluated by using receiver operating characteristic (ROC) curves. We compared the proposed algorithm with other existing methods. In our experiments, the proposed detection method outperformed the other methods tested. In particular, a sensitivity as high as 92.35% was achieved by our detection algorithm at an error rate of 8.3%. The experiment results suggest that Boosted-TWSVM is a promising technique for MCs detection.
This paper presents a novel WLAN-based system configuration employing Coded Multi-Carrier Code-Division- Multiplexing technology (CMC-CDM), as a potentially superior alternative to the currently standardized Coded OFD...
详细信息
This paper presents a novel WLAN-based system configuration employing Coded Multi-Carrier Code-Division- Multiplexing technology (CMC-CDM), as a potentially superior alternative to the currently standardized Coded OFDM (COFDM) technology. To further improve the performance of the system and reduce its complexity, a new concept of Chase detection is applied at the receiver. A comprehensive investigation has shown that under the appropriate conditions, the proposed system is able to show considerable advantage over COFDM. We believe that this work will contribute to the motivation of deploying CMC-CDM as an alternative approach for Next Generation of wireless systems.
We study the problem of distributed detection, where a set of nodes are required to decide between two hypotheses based on their measurements. We seek fully distributed implementations, where all nodes make individual...
详细信息
We study the problem of distributed detection, where a set of nodes are required to decide between two hypotheses based on their measurements. We seek fully distributed implementations, where all nodes make individual decisions by communicating with their immediate neighbors, and no fusion center is necessary. This scheme provides the network with more flexibility, saves energy for communication and networking resources. Our distributed detection algorithm is based on a previously proposed distributed estimation algorithm. We establish the connection between the detection and estimation problems, propose a distributed detection algorithm, and analyze the performance of the algorithm in terms of its probabilities of detection and false alarm. We also provide simulation results comparing with other cooperation schemes.
In order to solve the problem of slowly moving object detection and tracking, this paper proposes a new weighted accumulative difference method and works out a weights setting algorithm to fast detect the slowly movin...
详细信息
In order to solve the problem of slowly moving object detection and tracking, this paper proposes a new weighted accumulative difference method and works out a weights setting algorithm to fast detect the slowly moving object. We obtain the interest points from the moving area detected, then fix the matching range with the maximum velocity principle and work out a non-retrospective mismatch detection algorithm with the consistency principle. These methods upwards can enhance the efficiency and precision of our tracking system.
In autonomous hyperspectral remote sensing systems, the physical causes of false alarms are not all understood. Some arise from vagaries in sensor performance, especially in non-visible wavelengths. Consequently, many...
详细信息
In autonomous hyperspectral remote sensing systems, the physical causes of false alarms are not all understood. Some arise from vagaries in sensor performance, especially in non-visible wavelengths. Consequently, many false target declarations are characterized simply as outliers, anomalies conforming to no physical or statistical models. Other false alarms arise from clutter spectra too similar to target spectra. To eliminate the recurrence of such difficult errors, deployed systems should allow operator feedback to their signal processing systems. Here we describe how a hyperspectral system using even advanced detection algorithms, based on a elliptically contoured distribution models, can be enhanced by allowing it to learn from its mistakes.
In this paper, we address the problem of unsupervised detection of anomalies in hyperspectral images. Our proposed method is based on a novel statistical background modeling approach that combines local and global app...
详细信息
In this paper, we address the problem of unsupervised detection of anomalies in hyperspectral images. Our proposed method is based on a novel statistical background modeling approach that combines local and global approaches. The local-global background model has the ability to adapt to all nuances of the background process like local approaches but avoids over-fitting due to a too high number of degrees of freedom, which produces a high false alarm rate. This is done by constraining the local background models to be interrelated. The results strongly prove the effectiveness of the proposed algorithm. We experimentally show that our local-global algorithm performs better than several other global or local anomaly detection techniques, such as the well known RX or its Gaussian Mixture version (GMRX).
暂无评论