Browsing by Subject "Markov models"

Now showing 1 - 7 of 7

Open Access
A performance evaluation framework of a rate-controlled MPEG video transmission over UMTS networks
(IEEE, 2007-07) Akar, Nail; Barbera, M.; Budzisz, L.; Ferrùs, R.; Kankaya, Emre; Schembra, G.
UMTS is designed to offer high bandwidth radio access with QoS assurances for multimedia communications. In particular, real-time video communications services are expected to become a successful experience under UMTS networks. In this context, a video transmission service can be designed over the basis that UMTS can provide either a constant bit rate data channel or a dynamic variable bit rate data channel adapted to load conditions. In this latter approach, which is more efficient for both the user and the service provider, multimedia sources have to be timely designed in order to adapt their output rate to the instantaneous allowed channel rate. The target of this paper is to define an analytical model of adaptive real-time video sources in a UMTS network where system resources are dynamically shared among active users. © 2007 IEEE.
Open Access
A resampling-based Markovian model for automated colon cancer diagnosis
(Institute of Electrical and Electronics Engineers, 2012-01) Ozdemir, E.; Sokmensuer, C.; Gunduz Demir, C.
In recent years, there has been a great effort in the research of implementing automated diagnostic systems for tissue images. One major challenge in this implementation is to design systems that are robust to image variations. In order to meet this challenge, it is important to learn the systems on a large number of labeled images from a different range of variation. However, acquiring labeled images is quite difficult in this domain, and hence, the labeled training data are typically very limited. Although the issue of having limited labeled data is acknowledged by many researchers, it has rarely been considered in the system design. This paper successfully addresses this issue, introducing a new resampling framework to simulate variations in tissue images. This framework generates multiple sequences from an image for its representation and models them using a Markov process. Working with colon tissue images, our experiments show that this framework increases the generalization capacity of a learner by increasing the size and variation of the training data and improves the classification performance of a given image by combining the decisions obtained on its sequences.
Open Access
Resampling-based Markovian modeling for automated cancer diagnosis
(2011) Özdemir, Erdem
Correct diagnosis and grading of cancer is very crucial for planning an effective treatment. However, cancer diagnosis on biopsy images involves visual interpretation of a pathologist, which is highly subjective. This subjectivity may, however, lead to selecting suboptimal treatment plans. In order to circumvent this problem, it has been proposed to use automatic diagnosis and grading systems that help decrease the subjectivity levels by providing quantitative measures. However, one major challenge for designing these systems is the existence of high variance observed in the biopsy images due to the nature of biopsies. Thus, for successful classifications of unseen images, these systems should be trained with a large number of labeled images. However, most of the training sets in this domain have limited size of labeled data since it is quite difficult to collect and label histopathological images. In this thesis, we successfully address this issue by presenting a new resampling framework. This framework relies on increasing the generalization capacity of a classifier by augmenting the size and variation in the training set. To this end, we generate multiple sequences from an image, each of which corresponds to a perturbed sample of the image. Each perturbed sample characterizes different parts of the image, and hence, they are slightly different from each other. The use of these perturbed samples for representing the image increases the size and variability of the training set. These samples are modeled with Markov processes which are used to classify unseen image. Working with histopathological tissue images, our experiments demonstrate that the proposed framework is more effective for both larger and smaller training sets compared against other approaches. Additionally, they show that the use of perturbed samples is effective in a voting scheme which boosts the performance of the classifier.
Open Access
A robust system for counting people using an infrared sensor and a camera
(Elsevier BV, 2015) Erden, F.; Alkar, A. Z.; Çetin, A. Enis
In this paper, a multi-modal solution to the people counting problem in a given area is described. The multi-modal system consists of a differential pyro-electric infrared (PIR) sensor and a camera. Faces in the surveillance area are detected by the camera with the aim of counting people using cascaded AdaBoost classifiers. Due to the imprecise results produced by the camera-only system, an additional differential PIR sensor is integrated to the camera. Two types of human motion: (i) entry to and exit from the surveillance area and (ii) ordinary activities in that area are distinguished by the PIR sensor using a Markovian decision algorithm. The wavelet transform of the continuous-time real-valued signal received from the PIR sensor circuit is used for feature extraction from the sensor signal. Wavelet parameters are then fed to a set of Markov models representing the two motion classes. The affiliation of a test signal is decided as the class of the model yielding higher probability. People counting results produced by the camera are then corrected by utilizing the additional information obtained from the PIR sensor signal analysis. With the proof of concept built, it is shown that the multi-modal system can reduce false alarms of the camera-only system and determines the number of people watching a TV set in a more robust manner.
Open Access
Simulated annealing for texture segmentation with Markov models
(IEEE, 1989) Yalabık, M. Cemal; Yalabık, N.
Binary textured images are segmented into regions of different textures. The binary Markov model is used, and model parameters are assumed to be unknown prior to segmentation. The parameters are estimated using a weighted-least-squares method, while segmentation is performed iteratively using simulated annealing. To speed up the annealing process, an initial coarse segmentation algorithm that quickly determines the approximate region categories using k-means clustering algorithm is used. The results look promising, and the computational costs can be reduced further by optimization of the computations.
Open Access
VOC gas leak detection using pyro-electric infrared sensors
(IEEE, 2010) Erden, Fatih; Soyer, E. B.; Toreyin, B. U.; Çetin, A. Enis
In this paper, we propose a novel method for detecting and monitoring Volatile Organic Compounds (VOC) gas leaks by using a Pyro-electric (or Passive) Infrared (PIR) sensor whose spectral range intersects with the absorption bands of VOC gases. A continuous time analog signal is obtained from the PIR sensor. This signal is discretized and analyzed in real time. Feature parameters are extracted in wavelet domain and classified using a Markov Model (MM) based classifier. Experimental results are presented. ©2010 IEEE.
Open Access
Wavelet based flickering flame detector using differential PIR sensors
(Elsevier, 2012-07-06) Erden, F.; Toreyin, B. U.; Soyer, E. B.; Inac, I.; Gunay, O.; Kose, K.; Çetin, A. Enis
A Pyro-electric Infrared (PIR) sensor based flame detection system is proposed using a Markovian decision algorithm. A differential PIR sensor is only sensitive to sudden temperature variations within its viewing range and it produces a time-varying signal. The wavelet transform of the PIR sensor signal is used for feature extraction from sensor signal and wavelet parameters are fed to a set of Markov models corresponding to the flame flicker process of an uncontrolled fire, ordinary activity of human beings and other objects. The final decision is reached based on the model yielding the highest probability among others. Comparative results show that the system can be used for fire detection in large rooms.