In recent years, due to the widespread usage of various sensors action recognition is becoming more popular in many fields such as person surveillance, human-robot interaction etc. In this study, we aimed to develop an action recognition system by using only limited accelerometer and gyroscope data. Several deep learning methods like Convolutional Neural Network(CNN), Long-Short Term Memory (LSTM) with classical machine learning algorithms and their combinations were implemented and a performance analysis was carried out. Data balancing and data augmentation methods were applied and accuracy rates were increased noticeably. We achieved new stateof-the-art result on the UCI HAR dataset by 97.4% accuracy rate with using 3 layer LSTM model. Also, we implemented same model on collected dataset (ETEXWELD) and 99.0% accuracy rate was obtained which means a solid contribution. Moreover, the performance analysis is not only based on accuracy results, but also includes precision, recall and f1-score metrics. Additionally, a real-time application was developed by using 3 layer LSTM network for evaluating how the best model classifies activities robustly.

Despite the importance of respiration and metabolism measurement in daily life, they are not widely available to ordinary people because of sophisticated and expensive equipment. Here, we first report a straightforward and economical approach to monitoring respiratory function and metabolic rate using a wearable piezoelectric airflow transducer (WPAT). A self-shielded bend sensor is designed by sticking two uniaxially drawn piezoelectric poly l -lactic acid films with different cutting angles, and then the bend sensor is mounted on one end of a plastic tube to engineer the WPAT. The airflow sensing principle of the WPAT is theoretically determined through finite element simulation, and the WPAT is calibrated with a pulse calibration method. We prove that the WPAT has similar accuracy (correlation coefficient >0.99) to a pneumotachometer in respiratory flow and lung volume assessment. We demonstrate metabolism measurement using the WPAT and the relationship between minute volume and metabolic rates via human wear trials. The mean difference of measured metabolic rates between the WPAT and a Biopac indirect calorimeter is 0.015 kcal/min, which shows comparable performance. Significantly, unlike the Biopac indirect calorimeter with an airflow sensor, an oxygen gas sensor, and a carbon dioxide gas sensor, we merely use the simple-structured WPAT to measure metabolism. Thus, we expect the WPAT technology to provide a precise, convenient, and cost-effective respiratory and metabolic monitoring solution for next-generation medical home care applications and wearable healthcare systems.

No abstract

No abstract

The target of the study is to determine which sub-components are used to account for character-based and behavior-based factors, which are the two main primary deviant consumer behavior types in Turkey. In Literature, researches aiming at identifying the general structure of consumer deviance have been conducted. However, there is not a study which has attempted to develop a pilot conceptual-based scale and a classification for the main groups. As a result of the confirmatory factor analysis, it was depicted that the 10-items revised fourfactor model for character-based consumer deviance behavior has strong construct validity. As for the actionbased four-factor model, the unrevised version was seen to be more reliable.Jel Classification: M31, M37. SAPKIN MÜŞTERİLERİN EYLEM VE KARAKTER ÖZELİNDE SINIFLANDIRILMASI ÖZÇalışmanın hedefi, Türkiye'deki temel sapkın tüketici davranışı olan karakter temelli ve davranış temelli etkenlerin oluşturulması için alt bileşenlerin belirlenmesidir. İlgili yazında, tüketici sapkınlığının genel yapısının tanımlanmasını amaçlayan çalışmalar söz konusudur. Ancak, ana grupların sınıflandırılması ve kavramsal temelli bir pilot ölçek geliştirilmesini amaçlayan bir çalışma mevcut değildir. Faktör analizi sonucunda, karakter temelli müşteri sapkınlığı davranışının güçlü yapısal geçerliliği belirlenmiştir. Eylem temelli modeled ise revise edilmemiş olan model daha güvenilir bulunmuştur.Anahtar Kelimeler: Sapkın Davranış, Karakter Temelli Model, Eylem Temelli Model