Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors

Driver identification is an important research area in intelligent transportation systems, with applications in commercial freight transport and usage-based insurance. One way to perform the identification is to use smartphones as sensor devices. By extracting features from smartphone-embedded sensors, various machine learning methods can identify the driver. The identification becomes particularly challenging when the number of drivers increases. In this situation, there is often not enough data for successful driver identification. This paper uses a Generative Adversarial Network (GAN) for data augmentation to solve the problem of lacking data. Since GAN diversifies the drivers' data, it extends the applicability of the driver identification. Although GANs are commonly used in image processing for image augmentation, their use for driving signal augmentation is novel. Our experiments prove their utility in generating driving signals emanating from the Discrete Wavelet Transform (DWT) on smartphones' accelerometer and gyroscope signals. After collecting the augmented data, their histograms along the overlapped windows are fed to machine learning methods covered by a Stacked Generalization Method (SGM). The presented hybrid GAN-SGM approach identifies drivers with 97% accuracy, 98% precision, 97% recall, and 97% F1-measure that outperforms standard machine learning methods that process features extracted by the statistical, spectral, and temporal approaches.

Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors

Driver identification is an important research area in intelligent transportation systems, with applications in commercial freight transport and usage-based insurance. One way to perform the identification is to use smartphones as sensor devices. By extracting features from smartphone-embedded sensors, various machine learning methods can identify the driver. The identification becomes particularly challenging when the number of drivers increases. In this situation, there is often not enough data for successful driver identification. This paper uses a Generative Adversarial Network (GAN) for data augmentation to solve the problem of lacking data. Since GAN diversifies the drivers' data, it extends the applicability of the driver identification. Although GANs are commonly used in image processing for image augmentation, their use for driving signal augmentation is novel. Our experiments prove their utility in generating driving signals emanating from the Discrete Wavelet Transform (DWT) on smartphones' accelerometer and gyroscope signals. After collecting the augmented data, their histograms along the overlapped windows are fed to machine learning methods covered by a Stacked Generalization Method (SGM). The presented hybrid GAN-SGM approach identifies drivers with 97% accuracy, 98% precision, 97% recall, and 97% F1-measure that outperforms standard machine learning methods that process features extracted by the statistical, spectral, and temporal approaches.

Recurrent HBV Integration Targets as Potential Drivers in Hepatocellular Carcinoma

Chronic hepatitis B virus (HBV) infection is the major etiology of hepatocellular carcinoma (HCC), frequently with HBV integrating into the host genome. HBV integration, found in 85% of HBV-associated HCC (HBV–HCC) tissue samples, has been suggested to be oncogenic. Here, we investigated the potential of HBV–HCC driver identification via the characterization of recurrently targeted genes (RTGs). A total of 18,596 HBV integration sites from our in-house study and others were analyzed. RTGs were identified by applying three criteria: at least two HCC subjects, reported by at least two studies, and the number of reporting studies. A total of 396 RTGs were identified. Among the 28 most frequent RTGs, defined as affected in at least 10 HCC patients, 23 (82%) were associated with carcinogenesis and 5 (18%) had no known function. Available breakpoint positions from the three most frequent RTGs, TERT, MLL4/KMT2B, and PLEKHG4B, were analyzed. Mutual exclusivity of TERT promoter mutation and HBV integration into TERT was observed. We present an RTG consensus through comprehensive analysis to enable the potential identification and discovery of HCC drivers for drug development and disease management.