Mühendislik Fakültesi / Faculty of Engineering
Permanent URI for this collectionhttps://hdl.handle.net/11727/1401
Browse
10 results
Search Results
Item Audio-based Event Detection in Office Live Environments Using Optimized MFCC-SVM Approach(2015) Kucukbay, Selver Ezgi; Sert, Mustafa; 0000-0002-7056-4245; AAB-8673-2019Audio data contains several sounds and is an important source for multimedia applications. One of them is unstructured Environmental Sounds (also referred to as audio events) that have noise-like characteristics with flat spectrums. Therefore, in general, recognition methods applied for music and speech data are not appropriate for the Environmental Sounds. In this paper, we propose an MFCC-SVM based approach that exploits the effect of feature representation and learner optimization tasks for efficient recognition of audio events from audio signals. The proposed approach considers efficient representation of MFCC features using different window and hop sizes by changing the number of Mel coefficients in the analyses as well as optimizing the SVM parameters. Moreover, 16 different audio events from the IEEE Audio and Acoustic Signal Processing (AASP) Challenge Dataset, namely alert, clear throat, cough, door slam, drawer, keyboard, keys, knock, laughter, mouse, page turn, pen drop, phone, printer, speech, and switch that are collected from office live environments are utilized in the evaluations. Our empirical evaluations show that, when the results of the proposed methods are chosen for MFFC feature and SVM classifier, the tests conducted through using 5-fold cross validation gives the results of 62%, 58% and 55% for Precision, Recall and F-measure scores, respectively. Extensive experiments on audio-based event detection using the IEEE AASP Challenge dataset show the effectiveness of the proposed approach.Item Video Scene Classification Using Spatıal Pyramid Based Features(2014) Sert, Mustafa; Ergun, Hilal; https://orcid.org/0000-0002-7056-4245; AAB-8673-2019Recognition of video scenes is a challenging problem due to the unconstrained structure of the video content. Here, we propose a spatial pyramid based method for the recognition of video scenes and explore the effect of parameter optimization to the recognition accuracy. In the experiments different sampling methods, dictionary sizes, kernel methods, and pyramid levels are examined. Support Vector Machine (SVM) is employed for classification due to the success in pattern recognition applications. Our experiments show that, the size of dictionary and proper pyramid levels in feature representation drastically enhance the recognition accuracy.Item Sleep Apnea Detection Using Blood Pressure Signal(2018) Aksahin, Mehmet Feyzi; Oltu, Burcu; Karaca, Busra KubraSleep apnea is a common respiratory disease. Apnea affects sleep quality, reduces people's life standards, and it can result in death at advanced stage. Therefore the ability to detect the apnea quickly and accurately is important for the treatment of this disease. Apnea is diagnosed by specialists however this is a long and exhausting process. Accordingly, a decision support system that automatically diagnoses apnea has been developed to facilitate this process and make it more objective. The developed decision support system in this study is based on patient's blood pressure signals instead of traditional Polysomnography (PSG) records, which requires various physiological signals measured from the patients. In the examined blood pressure signals, the change that results from each heart beat was determined and heart rate variability (HRV) was calculated based on these changes. At the same time, maximum and minimum amplitude values were found for each change period and amplitude variability vector was created. The features for each epoch were determined using the generated amplitude variability vector and HRV data. Presence of apnea in each epoch is classified with determined features and with the use of "Quadratic SVM" classifier. The Quadratic SVM classifier was trained with 87.5% accuracy and then the system is tested. As a result 75.4% sensitivity and 75% positive predictive values were obtained.Item Facial Action Unit Detection using Variable Decision Thresholds(2016) Aksoy, Nukhet; Sert, Mustafa; 0000-0002-7056-4245; D-3080-2015Detection of facial action units (AUs) is an important research field for recognizing emotional states in facial expressions. Here, we propose a novel, yet effective method, that utilizes variable decision thresholds at the prediction stage of a binary learning method for AU detection. The method performs a thresholding technique to find optimum values for each AU and make use of these thresholds as the decision threshold of the support vector machine (SVM) algorithm. Our experiments on Extended Cohn- Kanade (CK+) dataset show significant improvements on most of the AUs with an average F1 score of 6 .383 % compared with the baseline method.Item Development of a MFCC-SVM Based Turkish Speech Recognition System(2016) Tombaloglu, Burak; Erdem, HamitIn this study, a SVM-MFCC based Turkish Speech Recognition system is devoloped. In the structure, Mel Frequency Cepstral Coefficients (MFCC) are used for feature extraction and Support Vector Machines(SVM) are used for classification of the phonemes. Three more phoneme recognition methods are applied to same dataset and their perfomance is compared. The applied methods are the combination of the Linear Prediction Cepstral Coefficients (LPCC), which is a commonly used method of feature extraction and Hidden Markov Method (HMM) which is a known classification method. The applied feature extraction and classification methods has been selected due to phoneme-based property of the Turkish language.Item Continuous Wavelet Transform Based Method For Detection Of Arousal(2017) Kantar, Tugce; Erdamar, Aykut; 0000-0001-8588-480X; AAA-6844-2019Sleeping is a vital biological requirement in the homeostatic mechanism. Sleep disorders can cause personal health problems and life quality deterioration. Transient waveforms (k-complexes, sleep spindles, arousal, etc.) happens instantaneously in sleep, have distinctive structural features, amplitudes and frequencies, and are difficult to distinguish from the background of electroencephalography (EEG) which are called the microstructure of the EEG. Microstructure analysis is important for brain research, sleep studies, sleep stage scorings and assessment of sleep disorders. Detection of arousal, one of these structures, is performed by visual scoring of all night sleep records by an expert sleep physician. In particular, visual analysis of the microstructure is difficult and time-consuming task so it increases error rates in scoring. The aim of this study is automatic detection of arousals from EEG signals. A computer-aided diagnosis system that can detect arousal can give more objective results to the expert sleep experts for diagnosing. In this study, continuous wavelet transform analysis of scored EEG signals was performed and features were obtained As a result, a decision support system algorithm for arousal has been developed using the obtained features and support vector machines. The specificity of the algorithm is 100% and sensitivity is 95.45%.Item Detection of K-complexes in Sleep EEG With Support Vector Machines(2017) Kantar, Tugce; Erdamar, Aykut; 0000-0001-8588-480X; AAA-6844-2019Sleep is a state that can be characterized by the electrical oscillations of nerve cells, where brain activity is more stable than waking. Transient waveforms observed in sleep electroencephalography are structures with specific amplitude and frequency characteristics that can occur in some stages of sleep. The determination of the k-complex, which is one of these structures, is performed by visual scoring of all night sleep recordings by expert physicians. For this reason, a decision support system that allows automatic detection of the k-complex can give physicians more objective results in diagnosis. In this study, sleep EEG records scored by a physician were analyzed in different methods from the literature. Three features have been determined that express the k-complex presence and k-complexes were detected using these features and support vector machines. As a result, the performance of the algorithm was evaluated and sensitivity and specificity were determined as 70.83% and 85.29%, respectively.Item Use of Acoustic and Vibration Sensor Data to Detect Objects in Surveillance Wireless Sensor Networks(2017) Kucukbay, Selver Ezgi; Sert, Mustafa; Yazici, Adnan; 0000-0002-7056-4245; AAB-8673-2019Nowadays, people are using stealth sensors to detect intruders due to their low power consumption and wide coverage. It is very important to use lightweight sensors for detecting real time events and taking actions accordingly. In this paper, we focus on the design and implementation of wireless surveillance sensor network with acoustic and seismic vibration sensors to detect objects and/or events for area security in real time. To this end, we introduce a new environmental sensing based system for event triggering and action. In our system, we first design an appropriate hardware as a part of multimedia surveillance sensor node and use proper classification technique to classify acoustic and vibration data that are collected by sensors in real-time. According to the type of acoustic data, our proposed system triggers a camera event as an action for detecting intruder (human or vehicle). We use Mel Frequency Cepstral Coefficients (MFCC) feature extraction method for acoustic sounds and Support Vector Machines (SVM) as classification method for both acoustic and vibration data. We have also run some experiments to test the performance of our classification approach. We show that our proposed approach is efficient enough to be used in real life.Item Automated Tuberculosis Detection Using Pre-Trained CNN and SVM(2021) Oltu, Burcu; Guney, Selda; Dengiz, Berna; Agildere, MuhtesemTuberculosis (TB) is a dreadfully contagious and life-threatening disease if left untreated. Therefore, early and accurate diagnosis is critical for treatment. Today, invasive, expensive, or time-consuming tests are performed for diagnosis. Unfortunately, accurate TB diagnosis is still a major challenge. In the proposed study, a decision support system that can automatically separate normal and TB chest X-ray (CXR) images is presented for objective and accurate diagnosis. In the presented methodology, first various data augmentation methods were applied to the data set, then pre-trained networks (VGG16, MobileNet), were employed as feature extractors from augmented CXR's. Afterward, the extracted features for all images were fed into a support vector machine classifier. In training process, 5-fold cross-validation was applied. As a result of this classification, it was concluded that TB can be diagnosed with an accuracy of 96,6% and an area under the ROC curve (AUC) of 0,99.Item Computational intelligence models for PIV based particle (cuttings) direction and velocity estimation in multi-phase flows(2019) Tombul, Hatice; Ozbayoglu, A. Murat; Ozbayoglu, M. EvrenIn multi-phase flow, the gas phase, the liquid phase and the particles (cuttings) within the liquid have different flow behaviors. Particle velocity and particle direction are two of the important aspects for determining the drilling particle behavior in multi-phase flows. There exists a lack of information about particle behavior inside a drilling annular wellbore. This paper presents an approach for particle velocity and direction estimation based on data obtained through Particle Image Velocimetry (PIV) techniques fed into computational intelligence models, in particular Artificial Neural Networks (ANNs) and Support Vector Machines (SVM). In this work, feed forward neural networks, support vector machines, support vector regression, linear regression and nonlinear regression models are used for estimating both particle velocity and particle direction. The proposed system was trained and tested using the experimental data obtained from an eccentric pipe configuration. Experiments have been conducted at the Cuttings Transport and Multi-phase Flow Laboratory of the Department of Petroleum and Natural Gas Engineering at Middle East Technical University. A high speed digital camera was used for recording the flow at the laboratory. Collected experimental data set consisted of 1080 and 1235 data points for 15 degrees inclined wellbores, 1087 and 1552 data points for 30 degrees inclined wellbores and 885 and 1119 data points for horizontal (0 degrees), wellbores respectively to use in estimation and classification problems. Results obtained from computational intelligence models are compared with each other through some performance metrics. The results showed that the SVM model was the best estimator for direction estimation, meanwhile the SVR model was the best estimator for velocity estimation. The direction and speed of the particles were estimated with a reasonable accuracy; hence the proposed model can be used in eccentric pipes in the field.