The appearance of cars has raised materialistic civilization and living standard to an unprecedented level. Today, it is hard to imagine how we human beings can live without cars. Yet, motor vehicles can cause a great number of deaths and injuries as well as considerable economic losses, which have constituted the global burden. Understanding of the occurrence and development of road traffic injuries will contribute to the prevention and control of crash and to the implementation of "everybody has the right to enjoy health" proposed by WHO.

Road traffic injuries.

Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many real-world time series applications may be limited such as classification in medical time series and anomaly detection in AIOps. As an effective way to enhance the size and quality of the training data, data augmentation is crucial to the successful application of deep learning models on time series data. In this paper, we systematically review different data augmentation methods for time series. We propose a taxonomy for the reviewed methods, and then provide a structured review for these methods by highlighting their strengths and limitations. We also empirically compare different data augmentation methods for different tasks including time series anomaly detection, classification, and forecasting. Finally, we discuss and highlight five future directions to provide useful research guidance.

/pdf/time-series-data-augmentation-for-deep-learning-a-survey-8b9ejcq10z.pdf

Time Series Data Augmentation for Deep Learning: A Survey

Advances in technology are not only changing the world around us but also driving the wireless industry to develop the next generation of network technology. There is a lot of buzz building over the advent of 5G that will facilitate the entire planet through continuous and ubiquitous communication connecting anybody to anything, anywhere, anytime, and anyhow regardless of the device, service, network, or geographical existence. 5G will also prove to be a paradigm shift including high carrier frequencies with massive bandwidths, having a large number of antennas, and with an extreme base station and device densities. In this paper, we investigate the potential beneficiaries of 5G and identify the use-cases, where 5G can make an impact. In particular, we consider three main use-cases: vehicle-to-everything (V2X) communication, drones, and healthcare. We explore and highlight the problems and deficiencies of current cellular technologies with respect to these use-cases and identify how 5G will overcome those deficiencies. We also identified the open research problems and provide possible future directions to cope with those issues.

/pdf/5g-communication-an-overview-of-vehicle-to-everything-drones-4bpco17vun.pdf

5G Communication: An Overview of Vehicle-to-Everything, Drones, and Healthcare Use-Cases

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.

/pdf/an-empirical-survey-of-data-augmentation-for-time-series-5bdy19uq2z.pdf

An empirical survey of data augmentation for time series classification with neural networks.

To understand human behavior and intrinsically anticipate human intentions, research into human activity recognition HAR) using sensors in wearable and handheld devices has intensified. The ability for a system to use as few resources as possible to recognize a user's activity from raw data is what many researchers are striving for. In this paper, we propose a holistic deep learning-based activity recognition architecture, a convolutional neural network-long short-term memory network (CNN-LSTM). This CNN-LSTM approach not only improves the predictive accuracy of human activities from raw data but also reduces the complexity of the model while eliminating the need for advanced feature engineering. The CNN-LSTM network is both spatially and temporally deep. Our proposed model achieves a 99% accuracy on the iSPL dataset, an internal dataset, and a 92 % accuracy on the UCI HAR public dataset. We also compared its performance against other approaches. It competes favorably against other deep neural network (DNN) architectures that have been proposed in the past and against machine learning models that rely on manually engineered feature datasets.

A CNN-LSTM Approach to Human Activity Recognition

Wearable inertial measurement unit (IMU) sensors are powerful enablers for acquisition of motion data Specifically, in human activity recognition (HAR), IMU sensor data collected from human motion are categorically combined to formulate datasets that can be used for learning human activities However, successful learning of human activities from motion data involves the design and use of proper feature representations of IMU sensor data and suitable classifiers Furthermore, the scarcity of labelled data is an impeding factor in the process of understanding the performance capabilities of data-driven learning models To tackle these challenges, two primary contributions are in this article: first; by using raw IMU sensor data, a spectrogram-based feature extraction approach is proposed Second, an ensemble of data augmentations in feature space is proposed to take care of the data scarcity problem Performance tests were conducted on a deep long term short term memory (LSTM) neural network architecture to explore the influence of feature representations and the augmentations on activity recognition accuracy The proposed feature extraction approach combined with the data augmentation ensemble produces state-of-the-art accuracy results in HAR A performance evaluation of each augmentation approach is performed to show the influence on classification accuracy Finally, in addition to using our own dataset, the proposed data augmentation technique is evaluated against the University of California, Irvine (UCI) public online HAR dataset and yields state-of-the-art accuracy results at various learning rates

/pdf/feature-representation-and-data-augmentation-for-human-401xplylib.pdf

Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network.

Position-estimation systems for indoor localization play an important role in everyday life. The global positioning system (GPS) is a popular positioning system, which is mainly efficient for outdoor environments. In indoor scenarios, GPS signal reception is weak. Therefore, achieving good position estimation accuracy is a challenge. To overcome this challenge, it is necessary to utilize other position-estimation systems for indoor localization. However, other existing indoor localization systems, especially based on inertial measurement unit (IMU) sensor data, still face challenges such as accumulated errors from sensors and external magnetic field effects. This paper proposes a position-estimation algorithm that uses the combined features of the accelerometer, magnetometer, and gyroscope data from an IMU sensor for position estimation. In this paper, we first estimate the pitch and roll values based on a fusion of accelerometer and gyroscope sensor values. The estimated pitch values are used for step detection. The step lengths are estimated by using the pitching amplitude. The heading of the pedestrian is estimated by the fusion of magnetometer and gyroscope sensor values. Finally, the position is estimated based on the step length and heading information. The proposed pitch-based step detection algorithm achieves 2.5% error as compared with acceleration-based step detection approaches. The heading estimation proposed in this paper achieves a mean heading error of 4.72° as compared with the azimuth- and magnetometer-based approaches. The experimental results show that the proposed position-estimation algorithm achieves a high position accuracy that significantly outperforms that of conventional estimation methods used for validation in this paper.

/pdf/an-indoor-position-estimation-algorithm-using-smartphone-imu-1z9xvqh8lq.pdf

An Indoor Position-Estimation Algorithm Using Smartphone IMU Sensor Data

Hand-eye calibration enables proper perception of the environment in which a vision guided robot operates. Additionally, it enables the mapping of the scene in the robots frame. Proper hand-eye calibration is crucial when sub-millimetre perceptual accuracy is needed. For example, in robot assisted surgery, a poorly calibrated robot would cause damage to surrounding vital tissues and organs, endangering the life of a patient. A lot of research has gone into ways of accurately calibrating the hand-eye system of a robot with different levels of success, challenges, resource requirements and complexities. As such, academics and industrial practitioners are faced with the challenge of choosing which algorithm meets the implementation requirements based on the identified constraints. This review aims to give a general overview of the strengths and weaknesses of different hand-eye calibration algorithms available to academics and industrial practitioners to make an informed design decision, as well as incite possible areas of research based on the identified challenges. We also discuss different calibration targets, which is an important part of the calibration process that is often overlooked in the design process.

/pdf/a-comparative-review-of-hand-eye-calibration-techniques-for-5doh83q8dc.pdf

A Comparative Review of Hand-Eye Calibration Techniques for Vision Guided Robots

Ultra wide band (UWB) systems use time information instead of the popular received signal strength indication (RSSI). UWB is known for its high position accuracy in localization. RSSI-based localization is easily affected by signal attenuation and has a poor localization accuracy as compared to the time of arrival (TOA) technique. In this paper, different localization algorithms for the UWB system were analytically reviewed. The performance of the localization algorithms is discussed in terms of root mean square and cumulative distribution function of localization errors. The experiment results demonstrate the effectiveness of different localization algorithms for UWB indoor positioning. The fingerprint estimation algorithm shows better performance compared to linearized least square estimation and weighted centroid estimation algorithms. The experimental results show that the linearized least square algorithm has poor performance for UWB indoor localization.

Localization Error Analysis of Indoor Positioning System Based on UWB Measurements

Localization is one of the current challenges in indoor navigation research. The conventional global positioning system (GPS) is affected by weak signal strengths due to high levels of signal interference and fading in indoor environments. Therefore, new positioning solutions tailored for indoor environments need to be developed. In this paper, we propose a deep learning approach for indoor localization. However, the performance of a deep learning system depends on the quality of the feature representation. This paper introduces two novel feature set extractions based on the continuous wavelet transforms (CWT) of the received signal strength indicators’ (RSSI) data. The two novel CWT feature sets were augmented with additive white Gaussian noise. The first feature set is CWT image-based, and the second is composed of the CWT PSD numerical data that were dimensionally equalized using principal component analysis (PCA). These proposed image and numerical data feature sets were both evaluated using CNN and ANN models with the goal of identifying the room that the human subject was in and estimating the precise location of the human subject in that particular room. Extensive experiments were conducted to generate the proposed augmented CWT feature set and numerical CWT PSD feature set using two analyzing functions, namely, Morlet and Morse. For validation purposes, the performance of the two proposed feature sets were compared with each other and other existing feature set formulations. The accuracy, precision and recall results show that the proposed feature sets performed better than the conventional feature sets used to validate the study. Similarly, the mean localization error generated by the proposed feature set predictions was less than those of the conventional feature sets used in indoor localization. More particularly, the proposed augmented CWT-image feature set outperformed the augmented CWT-PSD numerical feature set. The results also show that the Morse-based feature sets trained with CNN produced the best indoor positioning results compared to all Morlet and ANN-based feature set formulations.

https://www.mdpi.com/2076-3417/11/4/1806/pdf

Odongo Steven Eyobu

Papers

Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network.

An Indoor Position-Estimation Algorithm Using Smartphone IMU Sensor Data

A Comparative Review of Hand-Eye Calibration Techniques for Vision Guided Robots

Localization Error Analysis of Indoor Positioning System Based on UWB Measurements

Augmented CWT Features for Deep Learning-Based Indoor Localization Using WiFi RSSI Data