Browsing by Author "Barshan, Billur"

Now showing 1 - 20 of 57

Embargo
A new CNN-LSTM architecture for activity recognition employing wearable motion sensor data: enabling diverse feature extraction
(Elsevier, 2023-06-28) Koşar, Enes; Barshan, Billur
Extracting representative features to recognize human activities through the use of wearables is an area of on-going research. While hand-crafted features and machine learning (ML) techniques have been sufficiently well investigated in the past, the use of deep learning (DL) techniques is the current trend. Specifically, Convolutional Neural Networks (CNNs), Long Short Term Memory Networks (LSTMs), and hybrid models have been investigated. We propose a novel hybrid network architecture to recognize human activities through the use of wearable motion sensors and DL techniques. The LSTM and the 2D CNN branches of the model that run in parallel receive the raw signals and their spectrograms, respectively. We concatenate the features extracted at each branch and use them for activity recognition. We compare the classification performance of the proposed network with three single and three hybrid commonly used network architectures: 1D CNN, 2D CNN, LSTM, standard 1D CNN-LSTM, 1D CNN-LSTM proposed by Ordóñez and Roggen, and an alternative 1D CNN-LSTM model. We tune the hyper-parameters of six of the models using Bayesian optimization and test the models on two publicly available datasets. The comparison between the seven networks is based on four performance metrics and complexity measures. Because of the stochastic nature of DL algorithms, we provide the average values and standard deviations of the performance metrics over ten repetitions of each experiment. The proposed 2D CNN-LSTM architecture achieves the highest average accuracies of 95.66% and 92.95% on the two datasets, which are, respectively, 2.45% and 3.18% above those of the 2D CNN model that ranks the second. This improvement is a consequence of the proposed model enabling the extraction of a broader range of complementary features that comprehensively represent human activities. We evaluate the complexities of the networks in terms of the total number of parameters, model size, training/testing time, and the number of floating point operations (FLOPs). We also compare the results of the proposed network with those of recent related work that use the same datasets.
Open Access
A novel heuristic fall-detection algorithm based on double thresholding, fuzzy logic, and wearable motion sensor data
(Institute of Electrical and Electronics Engineers, 2023-05-25) Barshan, Billur; Turan, M. S.
We present a novel heuristic fall-detection algorithm based on combining double thresholding of two simple features with fuzzy logic techniques. We extract the features from the acceleration and gyroscopic data recorded from a waist-worn motion sensor unit. We compare the proposed algorithm to 15 state-of-the-art heuristic fall-detection algorithms in terms of five performance metrics and runtime on a vast benchmarking fall data set that is publicly available. The data set comprises recordings from 2880 short experiments (1600 fall and 1280 non-fall trials) with 16 participants. The proposed algorithm exhibits superior average accuracy (98.45%), sensitivity (98.31%), and F-measure (98.59%) performance metrics with a runtime that allows real-time operation. Besides proposing a novel heuristic fall-detection algorithm, this work has comparative value in that it provides a fair comparison on the relative performances of a considerably large number of existing heuristic algorithms with the proposed one, based on the same data set. The results of this research are encouraging in the development of fall-detection systems that can function in the real world for reliable and rapid fall detection.
Open Access
Activity recognition invariant towearable sensor unit orientation using differential rotational transformations represented by quaternions
(MDPI AG, 2018) Yurtman, Aras; Barshan, Billur; Fidan B.
Wearable motion sensors are assumed to be correctly positioned and oriented in most of the existing studies. However, generic wireless sensor units, patient health and state monitoring sensors, and smart phones and watches that contain sensors can be differently oriented on the body. The vast majority of the existing algorithms are not robust against placing the sensor units at variable orientations. We propose a method that transforms the recorded motion sensor sequences invariantly to sensor unit orientation. The method is based on estimating the sensor unit orientation and representing the sensor data with respect to the Earth frame. We also calculate the sensor rotations between consecutive time samples and represent them by quaternions in the Earth frame. We incorporate our method in the pre-processing stage of the standard activity recognition scheme and provide a comparative evaluation with the existing methods based on seven state-of-the-art classifiers and a publicly available dataset. The standard system with fixed sensor unit orientations cannot handle incorrectly oriented sensors, resulting in an average accuracy reduction of 31.8%. Our method results in an accuracy drop of only 4.7% on average compared to the standard system, outperforming the existing approaches that cause an accuracy degradation between 8.4 and 18.8%. We also consider stationary and non-stationary activities separately and evaluate the performance of each method for these two groups of activities. All of the methods perform significantly better in distinguishing non-stationary activities, our method resulting in an accuracy drop of 2.1% in this case. Our method clearly surpasses the remaining methods in classifying stationary activities where some of the methods noticeably fail. The proposed method is applicable to a wide range of wearable systems to make them robust against variable sensor unit orientations by transforming the sensor data at the pre-processing stage.
Open Access
Classification of fall directions via wearable motion sensors
(Academic Press, 2022-06-15) Turan, M. Ş.; Barshan, Billur
Effective fall-detection and classification systems are vital in mitigating severe medical and economical consequences of falls to people in the fall risk groups. One class of such systems is based on wearable sensors. While there is a vast amount of academic work on this class of systems, not much effort has been devoted to the investigation of effective and robust algorithms and like-for-like comparison of state-of-the-art algorithms using a sufficiently large dataset. In this article, fall-direction classification algorithms are presented and compared on an extensive dataset, comprising a total of 1600 fall trials. Eight machine learning classifiers are implemented for fall-direction classification into four basic directions (forward, backward, right, and left). These are, namely, Bayesian decision making (BDM), least squares method (LSM), k-nearest neighbor classifier (k-NN), artificial neural networks (ANNs), support vector machines (SVMs), decision-tree classifier (DTC), random forest (RF), and adaptive boosting or AdaBoost (AB). BDM achieves perfect classification, followed by k-NN, SVM, and RF. Data acquired from only a single motion sensor unit, worn at the waist of the subject, are processed for experimental verification. Four of the classifiers (BDM, LSM, k-NN, and ANN) are modified to handle the presence of data from an unknown class and evaluated on the same dataset. In this robustness analysis, ANN and k-NN yield accuracies above 96.2%. The results obtained in this study are promising in developing real-world fall-classification systems as they enable fast and reliable classification of fall directions.
Open Access
Classification of leg motions by processing gyroscope signals
(IEEE, 2009) Tunçel, Orkun; Altun, Kerem; Barshan, Billur
In this study, eight different leg motions are classified using two single-axis gyroscopes mounted on the right leg of a subject with the help of several pattern recognition techniques. The methods of least squares, Bayesian decision, k-nearest neighbor, dynamic time warping, artificial neural networks and support vector machines are used for classification and their performances are compared. This study comprises the preliminary work for our future studies on motion recognition with a much wider scope.
Open Access
Classifying daily and sports activities invariantly to the positioning of wearable motion sensor units
(IEEE, 2020) Barshan, Billur; Yurtman, Aras
We propose techniques that achieve invariance to the positioning of wearable motion sensor units on the body for the recognition of daily and sports activities. Using two sequence sets based on the sensory data allows each unit to be placed at any position on a given rigid body part. As the unit is shifted from its ideal position with larger displacements, the activity recognition accuracy of the system that uses these sequence sets degrades slowly, whereas that of the reference system (which is not designed to achieve position invariance) drops very fast. Thus, we observe a tradeoff between the flexibility in sensor unit positioning and the classification accuracy. The reduction in the accuracy is at acceptable levels, considering the convenience and flexibility provided to the user in the placement of the units. We compare the proposed approach with an existing technique to achieve position invariance and combine the former with our earlier methodology to achieve orientation invariance. We evaluate our proposed methodology on a publicly available data set of daily and sports activities acquired by wearable motion sensor units. The proposed representations can be integrated into the preprocessing stage of existing wearable systems without significant effort.
Open Access
Comparative analysis of different approaches to target classification and localization with sonar
(IEEE, 2001-08) Ayrulu, Birsel; Barshan, Billur
The comparison of different classification and fusion techniques was done for target classification and localization with sonar. Target localization performance of artificial neural networks (ANN) was found to be better than the target differentiation algorithm (TDA) and fusion techniques. The target classification performance of non-parametric approaches was better than that of parameterized density estimator (PDE) using homoscedastic and heteroscedastic NM for statistical pattern recognition techniques.
Open Access
A comparative study of map building techniques by processing sonar arc-maps
(2005) Kurt, Arda; Barshan, Billur
In this study, four signal processing schemes regarding sonar sensor based map-building applications were compared. The newly proposed method, Directional Maximum is found to be successful in terms of reducing the innate angular ambiguity of the sonar sensors. With respect to several works presented earlier in the same field and specifically map-building related studies, the new method is successful both in terms of mean absolute error and computational cost.
Open Access
A comparative study on the processing of ultrasonic arc maps
(IEEE, 2008-08) Barshan, Billur
The directional maximum (DM) technique for processing ultrasonic arc maps is proposed and compared to previously existing techniques. The method processes ultrasonic arc maps directionally to extract the map of the environment and overcome the intrinsic angular uncertainty of ultrasonic sensors. It also eliminates noise and cross-talk related misreadings successfully. The comparison is based on experimental data and three complementary error criteria. The DM technique offers a very good compromise between mean absolute error and correct detection rate, with a processing time less than tenth of a second. It is superior to existing techniques in range accuracy and in eliminating artifacts, resulting in the best overall performance. The results indicate several trade-offs in the choice of ultrasonic arc-map processing techniques.
Open Access
A comparison of two methods for fusing information from a linear array of sonar sensors for obstacle localization
(IEEE, 1995) Arıkan, Orhan; Barshan, Billur
The performance of a commonly employed linear array of sonar sensors is assessed for point-obstacle localization intended for robotics applications. Two different methods of combining time-of-flight information from the sensors are described to estimate the range and azimuth of the obstacle: pairwise estimate method and the maximum likelihood estimator. The variances of the methods are compared to the Cramer-Rao Lower Bound, and their biases are investigated. Simulation studies indicate that in estimating range, both methods perform comparably; in estimating azimuth, maximum likelihood estimate is superior at a cost of extra computation. The results are useful for target localization in mobile robotics.
Open Access
A compression method based on compressive sampling for 3-D laser range scans of indoor environments
(Springer, Dordrecht, 2010) Dobrucalı, Oğuzcan; Barshan, Billur
When 3-D models of environments need to be transmitted or stored, they should be compressed efficiently to increase the capacity of the communication channel or the storage medium. We propose a novel compression technique based on compressive sensing, applied to sparse representations of 3-D range measurements. We develop a novel algorithm to generate sparse innovations between consecutive range measurements along the axis of the sensor's motion, since the range measurements do not have highly sparse representations in common domains. Compared with the performances of widely used compression techniques, the proposed method offers the smallest compression ratio and provides a reasonable balance between reconstruction error and processing time. © 2011 Springer Science+Business Media B.V.
Open Access
Detection and evaluation of physical therapy exercises by dynamic time warping using wearable motion sensor units
(Springer, 2014) Yurtman, Aras; Barshan, Billur
We develop an autonomous system that detects and evaluates physical therapy exercises using wearable motion sensors. We propose an algorithm that detects all the occurrences of one or more template signals (representing exercise movements) in a long signal acquired during a physical therapy session. In matching the signals, the algorithm allows some distortion in time, based on dynamic time warping (DTW). The algorithm classifies the executions in one of the exercises and evaluates them as correct/incorrect, giving the error type if there is any. It also provides a quantitative measure of similarity between each matched execution and its template. To evaluate the performance of the algorithm in physical therapy, a dataset consisting of one template execution and ten test executions of each of the three execution types of eight exercises performed by five subjects is recorded, having a total of 120 and 1,200 exercise executions in the training and test sets, respectively, as well as many idle time intervals in the test signals. The proposed algorithm detects 1,125 executions in the whole test set. 8.58 % of the 1,200 executions are missed and 4.91 % of the idle time intervals are incorrectly detected as executions. The accuracy is 93.46 % only for exercise classification and 88.65 % for simultaneous exercise and execution type classification. The proposed system may be used for both estimating the intensity of the physical therapy session and evaluating the executions to provide feedback to the patient and the specialist.
Open Access
Differentiation and localization of target primitives using infrared sensors
(IEEE, 2002-09-10) Aytaç, Tayfun; Barshan, Billur
This study investigates the use of low-cost infrared sensors in the differentiation and localization of commonly encountered target primitives in indoor environments, such as planes, corners, edges, and cylinders. The intensity readings from such sensors are highly dependent on target location and properties in a way which cannot be represented in a simple manner, making the differentiation and localization process difficult. In this paper, we propose the use of angular intensity scans and present an algorithm to process them. This approach can determine the target type independent of its position. Once the target type is identified, its position can also be estimated. The method is verified experimentally. An average correct classification rate of 97% over all target types is achieved and targets are localized within absolute range and azimuth errors of 0.8 cm and 1.6°, respectively. The proposed method should facilitate the use of infrared sensors in mobile robot applications for differentiation and localization beyond their common usage as simple proximity sensors for object detection and collision avoidance.
Open Access
Directional processing of ultrasonic arc maps and its comparison with existing techniques
(IEEE, 2007) Barshan, Billur; Altun, Kerem
Directional maximum (DM) technique for processing ultrasonic arc maps (UAMs) is proposed and compared to existing techniques. It employs directional processing in extracting the map of the environment from UAMs. DM aims at overcoming the intrinsic angular uncertainty of ultrasonic sensors in map building, as well as eliminating noise and cross-talk related misreadings. The comparison is based on experiments with a mobile robot which ac-quired ultrasonic range measurements through wall following. Three complementary performance criteria are used. The DM technique offers a very good compromise between mean absolute error and correct detection rate, with a processing time less than one tenth of a second. It is also superior in range accuracy and in eliminating artifacts, resulting in the best overall performance. The results indicate several trade-offs in the choice of UAM processing techniques.
Open Access
Directional processing of ultrasonic arc maps and its comparison with existing techniques
(Sage Publications Ltd., 2007) Barshan, Billur
A new technique for processing ultrasonic arc maps is proposed and compared to six existing techniques for map-building purposes. These techniques are simple point marking along the line-of-sight, voting and thresholding, morphological processing, Bayesian update scheme for occupancy grids, arc-transversal median algorithm, and triangulation-based fusion. The directional maximum technique, newly proposed in this paper, employs directional processing to extract the map of the environment from ultrasonic arc maps. It aims at overcoming the intrinsic angular uncertainty of ultrasonic sensors in map building, as well as eliminating noise and cross-talk related misreadings. The compared techniques are implemented with a wall-following motion-planning scheme for ground coverage. The comparison is based on experimental data and three complementary error criteria: mean absolute error, correct detection rate for full and empty regions, and computational cost in terms of CPU time. The directional maximum technique offers a very good compromise between mean absolute error and correct detection rate, with a processing time less than one-tenth of a second. Compared to the existing techniques, the directional maximum method is also superior in range accuracy and in eliminating artifacts, resulting in the best overall performance. The results indicate several trade-offs in the choice of ultrasonic arc-map processing techniques.
Open Access
Employing active contours and artificial neural networks in representing ultrasonic range data
(IEEE, 2008-08) Altun, Kerem; Barshan, Billur
Active snake contours and Kohonen's self-organizing feature maps (SOM) are considered for efficient representation and evaluation of the maps of an environment obtained with different ultrasonic arc map (UAM) processing techniques. The mapping results are compared with a reference map acquired with a very accurate laser system. Both approaches are convenient ways of representing and comparing the map points obtained with different techniques among themselves, as well as with an absolute reference. Snake curve fitting results in more accurate maps than SOM since it is more robust to outliers. The two methods are sufficiently general that they can be applied to discrete point maps acquired with other mapping techniques and other sensing modalities as well. copyright by EURASIP.
Open Access
Evidential logical sensing using multiple sonars for the identification of target primitives in a mobile robot's environment
(IEEE, 1996) Ayrulu, Birsel; Barshan, Billur; Erkmen, İ.; Erkmen, A.
Physical models are used to model reflections from target primitives commonly encountered in mobile robot applications. These targets are differentiated by employing a multi-transducer pulse/echo system which relies on both amplitude and time-of-flight (TOF) data in the feature fusion process, allowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused for multiple logical sonars at different geographical sites. This evidential approach helps to overcome the vulnerability of echo amplitude to noise and enables the modeling of non-parametric uncertainty. Feature data from multiple logical sensors are fused with Dempster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Using three sensing nodes, improvement in differentiation is between 20-40% without false decision, at the cost of additional computation. Simulation results are verified by experiments with a real sonar system. This evidential approach helps to overcome the vulnerability of the echo amplitude to noise and enables the modeling of non-parametric uncertainty in real time.
Open Access
Extraction of target features using infrared intensity signals
(IEEE, 2005-09) Aytaç, Tayfun; Barshan, Billur
We propose the use of angular intensity signals obtained with low-cost infrared (IR) sensors and present an algorithm to simultaneously extract the geometry and surface properties of commonly encountered features or targets in indoor environments. The method is verified experimentally with planes, 90° corners, and 90° edges covered with aluminum, white cloth, and Styrofoam packaging material. An average correct classification rate of 80% of both geometry and surface over all target types is achieved and targets are localized within absolute range and azimuth errors of 1.5 cm and 1.1°, respectively. Taken separately, the geometry and surface type of targets can be correctly classified with rates of 99% and 81%, respectively, which shows that the geometrical properties of the targets are more distinctive than their surface properties, and surface determination is the limiting factor. The method demonstrated shows that simple IR sensors, when coupled with appropriate signal processing, can be used to extract substantially more information than such devices are commonly employed for.
Open Access
Filtering in fractional Fourier domains and their relation to chirp transforms
(IEEE, 1994-04) Özaktaş, Haldun M.; Barshan, Billur; Onural, Levent; Mendlovic, D.
Fractional Fourier transforms, which are related to chirp and wavelet transforms, lead to the notion of fractional Fourier domains. The concept of filtering of signals in fractional domains is developed, revealing that under certain conditions one can improve upon the special cases of these operations in the conventional space and frequency domains. Because of the ease of performing the fractional Fourier transform optically, these operations are relevant for optical information processing.
Open Access
Fizik tedavi egzersizlerinin giyilebilir hareket algılayıcıları işaretlerinden dinamik zaman bükmesiyle sezimi ve değerlendirilmesi
(IEEE, 2014-04) Yurtman, Aras; Barshan, Billur
Giyilebilir hareket algılayıcılarından kaydedilen sinyalleri işleyerek fizik tedavi egzersizlerini algılamak ve değerlendirmek için özerk bir sistem geliştirilmiştir. Bir fizik tedavi seansındaki bir ya da birden fazla egzersiz tipini algılamak için, temeli dinamik zaman bükmesi (DZB) benzeşmezlik ölçütüne dayanan bir algoritma geliştirilmiştir. Algoritma, egzersizlerin doğru ya da yanlış yapıldığını değerlendirmekte ve varsa hata türünü saptamaktadır. Algoritmanın başarımını degerlendirmek için, beş katılımcı tarafından yapılan sekiz egzersiz hareketinin üç yürütüm türü için birer şablon ve 10’ar sınama yürütümünden oluşan bir veri kümesi kaydedilmiştir. Dolayısıyla, eğitim ve sınama kümelerinde sırasıyla 120 ve 1,200 egzersiz yürütümü bulunmaktadır. Sınama kümesi, boş zaman dilimleri de içermektedir. Öne sürülen algoritma, sınama kümesindeki 1,200 yürütümün % 8.58’ini kaçırmakta ve boş zaman dilimlerinin % 4.91’ini yanlış sezim olarak değerlendirerek toplam 1,125 yürütüm algılamaktadır. Doğruluk, sadece egzersiz sınıflandırması ele alındığında ˘ % 93.46, hem egzersiz hem de yürütüm türü sınıflandırması içinse % 88.65’tir. Sistemin bilinmeyen egzersizlere karşı davranışını sınamak için, algoritma, her egzersiz için, o egzersizin şablonları dışarıda bırakılarak çalıştırılmış ve 1,200 egzersizin sadece 10’u yanlış sezilmiştir. Bu sonuç, sistemin bilinmeyen hareketlere karşı gürbüz olduğunu göstermektedir. Öne sürülen sistem, hem bir fizik tedavi seansının yoğunluğunu kestirmek, hem de hastaya ve fizik tedavi uzmanına geribildirim vermek amacıyla egzersiz hareketlerini değerlendirmek için kullanılabilir.