Táto práca sa zaoberá rozpoznávaním výstrelov a pridruženými problémami. Ako prvé je celá vec predstavená a rozdelená na menšie kroky. Ďalej je poskytnut...
详细信息
Táto práca sa zaoberá rozpoznávaním výstrelov a pridruženými problémami. Ako prvé je celá vec predstavená a rozdelená na menšie kroky. Ďalej je poskytnutý prehľad zvukových databáz, významné publikácie, akcie a súčasný stav veci spoločne s prehľadom možných aplikácií detekcie výstrelov. Druhá časť pozostáva z porovnávania príznakov pomocou rôznych metrík spoločne s porovnaním ich výkonu pri rozpoznávaní. Nasleduje porovnanie algoritmov rozpoznávania a sú uvedené nové príznaky použiteľné pri rozpoznávaní. Práca vrcholí návrhom dvojstupňového systému na rozpoznávanie výstrelov, monitorujúceho okolie v reálnom čase. V závere sú zhrnuté dosiahnuté výsledky a načrtnutý ďalší postup.
Detailed within is an attempt to implement a real-time radar signal classification system to monitor and count bee activity at the hive entry. There is interest in keeping records of the productivity of honeybees. Act...
详细信息
Detailed within is an attempt to implement a real-time radar signal classification system to monitor and count bee activity at the hive entry. There is interest in keeping records of the productivity of honeybees. Activity at the entrance can be a good measure of overall health and capacity, and a radar-based approach could be cheap, low power, and versatile, beyond other techniques. Fully automated systems would enable simultaneous, large-scale capturing of bee activity patterns from multiple hives, providing vital data for ecological research and business practice improvement. Data from a Doppler radar were gathered from managed beehives on a farm. Recordings were split into 0.4 s windows, and Log Area Ratios (LARs) were computed from the data. Support vector machine models were trained to recognize flight behavior from the LARs, using visual confirmation recorded by a camera. Spectrogram deep learning was also investigated using the same data. Once complete, this process would allow for removing the camera and accurately counting the events by radar-based machine learning alone. Challenging signals from more complex bee flights hindered progress. System accuracy of 70% was achieved, but clutter impacted the overall results requiring intelligent filtering to remove environmental effects from the data.
V rámci bakalářské práce byl vytvořen program pro hodnocení kvality řeči. Tento program byl vytvořen v programovacím jazyku MATLAB s využitím programovacího prostředí GUI. ...
详细信息
V rámci bakalářské práce byl vytvořen program pro hodnocení kvality řeči. Tento program byl vytvořen v programovacím jazyku MATLAB s využitím programovacího prostředí GUI. Pomocí vytvořeného programu byla zpracována skupina nahrávek zarušených různými hluky z reálného prostředí. Jako objektivní metody hodnocení kvality řeči byly vybrány Základní metoda SNR, Segmentální metoda SNR s využitím detektoru řečové aktivity, PESQ, Itakurova míra, Itakurova – Saitova míra. K programu byl vytvořen návod k obsluze. V práci jsou popsány výše zmíněné objektivní metody hodnocení kvality řeči a dále proces vytváření lidské řeči, modelování lidské řeči a lineární prediktivní analýza.
Fault isolation in electronic circuits is a trending area of interest as analog circuits find valuable application in industry. The failures in circuit systems cause severe issues in the normal functioning of the syst...
详细信息
Fault isolation in electronic circuits is a trending area of interest as analog circuits find valuable application in industry. The failures in circuit systems cause severe issues in the normal functioning of the system that insists on the need for an automatic method of fault isolation in analog circuits. Literature conveys the issues associated with the fault isolation and hence, to address the severity of the faults, a novel model is proposed to isolate the fault causing component in the circuit. The proposed Multi-Rider Optimization-based Neural Network (M-RideNN) isolates the faulty part of the circuit from the fault-free areas such that the fault diagnosis is structured in an effective way. The fault isolation is progressed as four major steps such as establishing the fault dictionary, signal normalization using linear predictive coding (LPC), effective dimensional reduction methodology using Probabilistic Principal Component Analysis (PPCA), and fault isolation using the proposed M-RideNN classifier. Finally, the experimentation using three circuits, namely Triangular Wave Generator (TWG), Bipolar Transistor Amplifier (BTA), differentiator (DIF), and an application circuit, Solar Power Converter (SPC), proves that the proposed M-RideNN classifier offers better classification accuracy of 93.18% with a minimum Mean Square Error (MSE) of 0.0682.
This paper develops a technique for identifying dynamic loads acting on a structure based on impulse response of the structure, also referred to as the system Markov parameters, and structure response measured at opti...
详细信息
This paper develops a technique for identifying dynamic loads acting on a structure based on impulse response of the structure, also referred to as the system Markov parameters, and structure response measured at optimally placed sensors on the structure. Inverse Markov parameters are computed from the forward Markov parameters using a linear prediction algorithm and have the roles of input and output reversed. The applied loads are then reconstructed by convolving the inverse Markov parameters with the system response to the loads measured at optimal locations on the structure. The structure essentially acts as its own load transducer. It has been noted that the computation of inverse Markov parameters, like most other inverse problems, is ill-conditioned which causes their convolution with the measured response to become quite sensitive to errors in system modeling and response measurements. The computation of inverse Markov parameters (and thereby the quality of load estimates) depends on the locations of sensors on the structure. To ensure that the computation of inverse Markov parameters is well-conditioned, a solution approach, based on the construction of D-optimal designs, is presented to determine the optimal sensor locations such that precise load estimates are obtained.
In this correspondence, a two-stage approach based on Karhunen-Loeve transform and 2-D prediction is proposed for efficient quantization of line spectrum pair (LSP) parameters of speech. Besides, a switched classifier...
详细信息
In this correspondence, a two-stage approach based on Karhunen-Loeve transform and 2-D prediction is proposed for efficient quantization of line spectrum pair (LSP) parameters of speech. Besides, a switched classifier is incorporated with this approach to reduce the outlier frames (spectral distortion greater than 2 dB) down to about 0.27% and to eliminate frames with spectral distortion greater than 4 dB at an average bit-rate below 19 b/frame.
Conventional photoplesthymograph (PPG) measurements for heart rate (HR) determination require direct contact between the patient and the PPG device sensor. When using the conventional method, it is possible for users ...
详细信息
Conventional photoplesthymograph (PPG) measurements for heart rate (HR) determination require direct contact between the patient and the PPG device sensor. When using the conventional method, it is possible for users to suffer undesirable skin irritation, discomfort and soreness. Thus, the development of non-contact PPG has been investigated with various technologies and methods. One of the technologies that able to measure PPG in a non-contact way and at low cost is using digital cameras such as webcams. Various filters have been implemented to do non-contact PPG using digital cameras. This paper proposes a non-contact PPG filter system utilizing singular value decomposition (SVD) and Burg's algorithm. The main role of SVD is for noise removal and as PPG signal extractor. As for the Burg algorithm, it was utilized for estimating the heart rate value from the filtered PPG signal. In this paper, we show and analyze an experiment for HR measurement using our method and a previous method that used independent component analysis (ICA). We compare and contrast both of them with HR measurements acquired by a commercial oximeter. The experiments were conducted at various distance between 30 similar to 110 cm and light intensities between 5 similar to 2000 lux. The estimated HR showed 2.25 bpm of mean error and 0.73 of Pearson correlation coefficient. The optimal distance between the mirror and user for HR measurement was 50 cm with medium light intensity, around 550 lux.
This paper proposes a real-time heart rate detection method based on 77 GHz FMCW radar. Firstly, the method establishes a new motion model according to respiratory and heartbeat rules, and extracts the motion signals ...
详细信息
This paper proposes a real-time heart rate detection method based on 77 GHz FMCW radar. Firstly, the method establishes a new motion model according to respiratory and heartbeat rules, and extracts the motion signals of the chest and the abdomen;then, the random body motion (RBM) signal is eliminated by a combination of polynomial fitting and recursive least squares (RLS) adaptive filtering;lastly, multi-detection-point adaptive harmonics cancellation (AHC) is used to eliminate respiratory harmonics. In addition, the method introduces a spectrum analysis algorithm based on linear predictive coding (LPC). The experimental results show that the method can effectively eliminate the RBM signal and respiratory harmonics, and that the average real-time heart rate detection error rate is 2.925%.
This paper presents the investigation of acoustic characteristics of ethnically diverse accents in Malaysian English across genders. The study of Malaysian English is still at infancy and the cues of how accents can b...
详细信息
This paper presents the investigation of acoustic characteristics of ethnically diverse accents in Malaysian English across genders. The study of Malaysian English is still at infancy and the cues of how accents can be differentiated by human are less understandable. Understanding this through the use of formants would discover the importance of these features that can be used to drive the classification results. It was found that males and females differ in terms of all formants scores that correlate to accents in great details using two-way and one-way analysis of variance and the plots of normal fit of individual formant.
Accurate depiction of the vocal tract shape is essential for development of speech training aids for hearing impaired. Speech therapists have concluded from their research that if speech disorders are detected at an e...
详细信息
Accurate depiction of the vocal tract shape is essential for development of speech training aids for hearing impaired. Speech therapists have concluded from their research that if speech disorders are detected at an early stage then the rectification of those becomes faster and to a great accuracy. In case of adults, the vocal tract shape estimation can be performed by using techniques like X-Ray, MRI or using articulatory analysis by synthesis. Due to certain difficulties present in the methods mentioned like radiation effect and loud sound impulses produced by rapid switching of magnetic field are not considered suitable for children. Thus there is lack of availability of vocal tract shape data for children due to inability to use direct estimation methods for children. So it becomes necessary to carry out comparative study of vocal tract shape estimation techniques of children using indirect vocal tract shape estimation techniques. This paper aims to make available a considerable amount of data to researchers for study towards children's vocal tract shape using implemented techniques. The final objective of research work is to perform a detailed study on techniques available for vocal tract shape estimation, to implement and further compare the covariance and lattice methods for children using MATLAB software. Currently, the vocal tract shape estimation based on autocorrelation method is implemented and the results obtained are presented.
暂无评论