A Multi-Feature Deep Learning Algorithm for Urban Traffic Classification with Limited Labeled Data

Acoustic sensors, if embedded in smart street lights, can help in capturing the activities (car honking, sirens, events, traffic, etc.) in cities. Needless to say, the acoustic data from such scenarios are complex due to multiple audio streams originating from different events, and when decomposed to independent signals, the amount of retrieved data volume is small in quantity which is inadequate to train deep neural networks. So, in this paper, we address the two challenges: a) separating the mixed signals, and b) developing an efficient acoustic classifier under data paucity. So, to address these challenges, we propose an architecture with supervised deep learning, where the initial captured mixed acoustics data are analyzed with Fast Fourier Transformation (FFT), followed by filtering the noise from the signal, and then decomposed to independent signals by fast independent component analysis (Fast ICA). To address the challenge of data paucity, we propose a multi feature-based deep neural network with high performance that is reflected in our experiments when compared to the conventional convolutional neural network (CNN) and multi-layer perceptron (MLP).

Multi-Sensor Image Fusion for Visible and Infrared Thermal Images

This paper is motivated by the importance of multi-sensor image fusion with specific focus on Infrared (IR) and Visible image (VI) fusion for various applications including military reconnaissance. Image fusion can be defined as the process of combining two or more source images into a single composite image with extended information content that improves visual perception or feature extraction. These images can be from different modalities like Visible camera & IR Thermal Imager. While visible images are captured by reflected radiations in the visible spectrum, the thermal images are formed from thermal radiation (IR) that may be reflected or self-emitted. A digital color camera captures the visible source image and a thermal IR camera acquires the thermal source image. In this paper, some image fusion algorithms based upon Multi-Scale Transform (MST) and region-based selection rule with consistency verification have been proposed and presented. This research includes implementation of the proposed image fusion algorithm in MATLAB along with a comparative analysis to decide the optimum number of levels for MST and the coefficient fusion rule. The results are presented, and several commonly used evaluation metrics are used to assess the suggested method's validity. Experiments show that the proposed approach is capable of producing good fusion results. While deploying our image fusion algorithm approaches, we observe several challenges from the popular image fusion methods. While high computational cost and complex processing steps of image fusion algorithms provide accurate fused results, but they also make it hard to become deployed in system and applications that require real-time operation, high flexibility and low computation ability. So, the methods presented in this paper offer good results with minimum time complexity.

A Deep Learning Framework for Polarimetric SAR Change Detection Using Capsule Network

The Earth's surface is constantly changing through forces of nature and human activities. Reliable, accurate, and timely change detection is critical to environmental monitoring, resource management, and planning activities. Recently, interest in deep learning algorithms, especially convolutional neural networks, has increased in the field of image change detection due to their powerful ability to extract multi-level image features automatically. However, these networks are prone to drawbacks that limit their applications, which reside in their inability to capture spatial relationships between image instances, as this necessitates a large amount of training data. As an alternative, Capsule Network has been proposed to overcome these shortcomings. Although its effectiveness in remote sensing image analysis has been experimentally verified, its application in change detection tasks remains very sparse. Motivated by its greater robustness towards improved hierarchical object representation, this study aims to apply a capsule network for PolSAR image Change Detection. The experimental results demonstrate that the proposed change detection method can yield a significantly higher detection rate compared to methods based on convolutional neural networks.

Quantifying the Second-Level Digital Divide on Sub-National Level

Digital divide, the gap in the access to the world of digital technologies and the socio-economic opportunities that they create is an important phenomenon of the XXI century. This gap may exist between countries, regions within a country or socio-demographic groups, creating the classes of “digital have and have nots”. While the 1st-level divide (the difference in opportunities to access the digital networks) was demonstrated to diminish with time, the issues of 2nd level divide (the difference in skills and usage of digital systems) and 3rd level divide (the difference in effects obtained from digital technology) may grow. The paper offers a systemic review of literature on the measurement of the digital divide, noting the certain conceptual stagnation due to the lack of effective instruments that would capture the complex nature of the phenomenon. As a result, many important concepts do not receive the empiric exploration they deserve. As a solution the paper suggests a composite Digital Life Index, that studies separately the digital supply and demand across seven independent dimensions providing for 14 subindices. The Index is based on Internet-borne data, a distinction from traditional research approaches that rely on official statistics or surveys. The application of the model to the study of the digital divide between Russian regions and between cities in China have brought promising results. The paper advances the existing methodological literature on the 2nd level digital divide and can also inform practical decision-making regarding the strategies of national and regional digital development.

Depth Camera Aided Dead-Reckoning Localization of Autonomous Mobile Robots in Unstructured Global Navigation Satellite System Denied Environments

In global navigation satellite system (GNSS) denied settings, such as indoor environments, autonomous mobile robots are often limited to dead-reckoning navigation techniques to determine their position, velocity, and attitude (PVA). Localization is typically accomplished by employing an inertial measurement unit (IMU), which, while precise in nature, accumulates errors rapidly and severely degrades the localization solution. Standard sensor fusion methods, such as Kalman filtering, aim to fuse precise IMU measurements with accurate aiding sensors to establish a precise and accurate solution. In indoor environments, where GNSS and no other a priori information is known about the environment, effective sensor fusion is difficult to achieve, as accurate aiding sensor choices are sparse. However, an opportunity arises by employing a depth camera in the indoor environment. A depth camera can capture point clouds of the surrounding floors and walls. Extracting attitude from these surfaces can serve as an accurate aiding source, which directly combats errors that arise due to gyroscope imperfections. This configuration for sensor fusion leads to a dramatic reduction of PVA error compared to traditional aiding sensor configurations. This paper provides the theoretical basis for the depth camera aiding sensor method, initial expectations of performance benefit via simulation, and hardware implementation thus verifying its veracity. Hardware implementation is performed on the Quanser Qbot 2™ mobile robot, with a Vector-Nav VN-200™ IMU and Kinect™ camera from Microsoft.

Sustainable Energy Policy for Africa (Nigeria) and Europe: A Comparative Study

The purpose of this paper was to develop a policy and associated regulatory actions together with legislations that could help in sustainable energy development in Africa and Nigeria in particular. As a result of depletion of fossil fuels in most African countries, renewable energy options such as solar, wind and hydropower biomass are considered to be alternative sources in sustaining the energy security in the continent and particularly Nigeria. Corruption level is another factor that hinders economic growth and development in Nigeria. A review of the past literature on sustainable energy policy from Europe has been carried out. The countries investigated include: The United Kingdom, Germany, Norway and Finland. Their policies have been examined, and this helps suggest new policies on sustainable energy for Nigeria and Africa as a continent. The policies analyzed focused on incentives such as Feed-in-Tariff (FiT). Renewable energy sources potential and renewable have been investigated in Nigeria and that could help in formulating new sustainable energy policy for the country. Some of the proposed policies includes: Renewable Obligation (RO), Cogeneration, FiT, Carbon Capture and Storage (CCS), Renewable Integration, and Heat Entrepreneurship. These are some the new policies that could help sustain the energy security, reduce the level of poverty and corruption in Nigeria as well as Africa in general. If these policies are well designed and properly implemented as observed in this research, Nigeria can achieve sustainable energy and economic growth and development in the near future. Each proposed policy was assigned a timeframe for it to be achieved.

Real Time Data Communication with FlightGear Using Simulink over a UDP Protocol

Simulation and modelling of Unmanned Aerial Vehicle (UAV) has gained wide popularity in front of aerospace community. The demand of designing and modelling optimized control system for UAV has increased ten folds since last decade, as next generation warfare is dependent on unmanned technologies. Therefore, this research focuses on the simulation of nonlinear UAV dynamics on Simulink and its integration with Flightgear. There has been lots of research on implementation of optimizing control using Simulink, however, there are fewer known techniques to simulate these dynamics over Flightgear and a tedious technique of acquiring data has been tackled in this research horizon. Sending data to Flightgear is easy but receiving it from Simulink is not that straight forward, i.e. we can only receive control data on the output. However, in this research we have managed to get the data out from the Flightgear by implementation of level 2 s-function block within Simulink. Moreover, the results captured from Flightgear over a Universal Datagram Protocol (UDP) communication are then compared with the attitude signal that were sent previously. This provide useful information regarding the difference in outputs attained from Simulink to Flightgear. It was found that values received on Simulink were in high agreement with that of the Flightgear output. And complete study has been conducted in a discrete way.

Development of Nondestructive Imaging Analysis Method Using Muonic X-Ray with a Double-Sided Silicon Strip Detector

In recent years, a nondestructive elemental analysis method based on muonic X-ray measurements has been developed and applied for various samples. Muonic X-rays are emitted after the formation of a muonic atom, which occurs when a negatively charged muon is captured in a muon atomic orbit around the nucleus. Because muonic X-rays have a higher energy than electronic X-rays due to the muon mass, they can be measured without being absorbed by a material. Thus, estimating the two-dimensional (2D) elemental distribution of a sample became possible using an X-ray imaging detector. In this work, we report a non-destructive imaging experiment using muonic X-rays at Japan Proton Accelerator Research Complex. The irradiated target consisted of a polypropylene material, and a double-sided silicon strip detector, which was developed as an imaging detector for astronomical obervation, was employed. A peak corresponding to muonic X-rays from the carbon atoms in the target was clearly observed in the energy spectrum at an energy of 14 keV, and 2D visualizations were successfully reconstructed to reveal the projection image from the target. This result demonstrates the potential of the nondestructive elemental imaging method that is based on muonic X-ray measurement. To obtain a higher position resolution for imaging a smaller target, a new detector system will be developed to improve the statistical analysis in further research.

Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories

In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. To approach this problem, we present a convolutional neural network (CNN) approach where we initially represent the multiagent behavior as an image. To encode the adversarial nature of basketball, we use a multichannel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories we use “fading.” We find that this approach is superior to a traditional FFN model. By using gradient ascent, we were able to discover what the CNN filters look for during training. Last, we find that a combined FFN+CNN is the best performing network with an error rate of 39%.

Strongly Coupled Finite Element Formulation of Electromechanical Systems with Integrated Mesh Morphing using Radial Basis Functions

The paper introduces a method to efficiently simulate nonlinear changing electrostatic fields occurring in micro-electromechanical systems (MEMS). Large deflections of the capacitor electrodes usually introduce nonlinear electromechanical forces on the mechanical system. Traditional finite element methods require a time-consuming remeshing process to capture exact results for this physical domain interaction. In order to accelerate the simulation process and eliminate the remeshing process, a formulation of a strongly coupled electromechanical transducer element will be introduced which uses a combination of finite-element with an advanced mesh morphing technique using radial basis functions (RBF). The RBF allows large geometrical changes of the electric field domain while retain high element quality of the deformed mesh. Coupling effects between mechanical and electrical domains are directly included within the element formulation. Fringing field effects are described accurate by using traditional arbitrary shape functions.

Automatic Classification of the Stand-to-Sit Phase in the TUG Test Using Machine Learning

Over the past several years, researchers have shown a great interest in assessing the mobility of elderly people to measure their functional status. Usually, such an assessment is done by conducting tests that require the subject to walk a certain distance, turn around, and finally sit back down. Consequently, this study aims to provide an at home monitoring system to assess the patient’s status continuously. Thus, we proposed a technique to automatically detect when a subject sits down while walking at home. In this study, we utilized a Doppler radar system to capture the motion of the subjects. More than 20 features were extracted from the radar signals out of which 11 were chosen based on their Intraclass Correlation Coefficient (ICC > 0.75). Accordingly, the sequential floating forward selection wrapper was applied to further narrow down the final feature vector. Finally, five features were introduced to the Linear Discriminant Analysis classifier and an accuracy of 93.75% was achieved as well as a precision and recall of 95% and 90% respectively.

An Approach to Capture, Evaluate and Handle Complexity of Engineering Change Occurrences in New Product Development

This paper represents the conception that complex problems do not necessary need similar complex solutions in order to cope with the complexity. Furthermore, a simple solution based on established methods can provide a sufficient way dealing with the complexity. To verify this conception, the presented paper focuses on the field of change management as a part of new product development process in automotive sector. In the field of complexity management, dealing with increasing complexity is essential, while, only non-flexible rigid processes that are not designed to handle complexity are available. The basic methodology of this paper can be divided in four main sections: 1) analyzing the complexity of the change management, 2) literature review in order to identify potential solutions and methods, 3) capturing and implementing expertise of experts from change management filed of an automobile manufacturing company and 4) systematical comparison of the identified methods from literature and connecting these with defined requirements of the complexity of the change management in order to develop a solution. As a practical outcome, this paper provides a method to capture the complexity of engineering changes (EC) and includes it within the EC evaluation process, following case-related process guidance to cope with the complexity. Furthermore, this approach supports the conception that dealing with complexity is possible while utilizing rather simple and established methods by combining them in to a powerful tool.

Effect of Birks Constant and Defocusing Parameter on Triple-to-Double Coincidence Ratio Parameter in Monte Carlo Simulation-GEANT4

This project concerns with the detection efficiency of the portable Triple-to-Double Coincidence Ratio (TDCR) at the National Institute of Metrology of Ionizing Radiation (INMRI-ENEA) which allows direct activity measurement and radionuclide standardization for pure-beta emitter or pure electron capture radionuclides. The dependency of the simulated detection efficiency of the TDCR, by using Monte Carlo simulation Geant4 code, on the Birks factor (kB) and defocusing parameter has been examined especially for low energy beta-emitter radionuclides such as 3H and 14C, for which this dependency is relevant. The results achieved in this analysis can be used for selecting the best kB factor and the defocusing parameter for computing theoretical TDCR parameter value. The theoretical results were compared with the available ones, measured by the ENEA TDCR portable detector, for some pure-beta emitter radionuclides. This analysis allowed to improve the knowledge of the characteristics of the ENEA TDCR detector that can be used as a traveling instrument for in-situ measurements with particular benefits in many applications in the field of nuclear medicine and in the nuclear energy industry.

6D Posture Estimation of Road Vehicles from Color Images

Currently, in the field of object posture estimation, there is research on estimating the position and angle of an object by storing a 3D model of the object to be estimated in advance in a computer and matching it with the model. However, in this research, we have succeeded in creating a module that is much simpler, smaller in scale, and faster in operation. Our 6D pose estimation model consists of two different networks – a classification network and a regression network. From a single RGB image, the trained model estimates the class of the object in the image, the coordinates of the object, and its rotation angle in 3D space. In addition, we compared the estimation accuracy of each camera position, i.e., the angle from which the object was captured. The highest accuracy was recorded when the camera position was 75°, the accuracy of the classification was about 87.3%, and that of regression was about 98.9%.

Lagrangian Flow Skeletons Captured in the Wake of a Swimming Nematode C. elegans Using an Immersed Boundary Fluid-Structure Interaction Approach

In this paper, Lagrangian coherent structure (LCS) concept is applied to wake flows generated in the up/down-stream of a swimming nematode C. elegans in an intermediate Re number range, i.e., 250-1200. It materializes Lagrangian hidden structures depicting flow transport barriers. To pursue the goals, nematode swimming in a quiescent fluid flow environment is numerically simulated by a two-way fluid-structure interaction (FSI) approach with the aid of immersed boundary method (IBM). In this regard, incompressible Navier-Stokes equations, fully-coupled with Lagrangian deformation equations for the immersed body, are solved using IB2d code. For all simulations, nematode’s body is modeled with a parametrized spring-fiber built-in case available in the computational code. Reverse von-Kármán vortex street formation and vortex shedding characteristics are studied and discussed in details via LCS approach, including grid resolution, integration time and Reynolds number effects. Results unveil presence of different flow regions with distinct fluid particle fates in the swimming animal’s wake and formation of so-called ‘mushroom-shaped’ structures in attracting LCS identities.

Image Processing Approach for Detection of Three-Dimensional Tree-Rings from X-Ray Computed Tomography

Tree-ring analysis is an important part of the quality assessment and the dating of (archaeological) wood samples. It provides quantitative data about the whole anatomical ring structure, which can be used, for example, to measure the impact of the fluctuating environment on the tree growth, for the dendrochronological analysis of archaeological wooden artefacts and to estimate the wood mechanical properties. Despite advances in computer vision and edge recognition algorithms, detection and counting of annual rings are still limited to 2D datasets and performed in most cases manually, which is a time consuming, tedious task and depends strongly on the operator’s experience. This work presents an image processing approach to detect the whole 3D tree-ring structure directly from X-ray computed tomography imaging data. The approach relies on a modified Canny edge detection algorithm, which captures fully connected tree-ring edges throughout the measured image stack and is validated on X-ray computed tomography data taken from six wood species.

Manual Pit Emptiers and Their Heath: Profiles, Determinants and Interventions

The global sanitation workforce bridges the gap between sanitation infrastructure and the provision of sanitation services through essential public service work. Manual pit emptiers often perform the work at the cost of their dignity, safety, and health as their work requires repeated heavy physical activities such as lifting, carrying, pulling, and pushing. This exposes them to occupational and environmental health hazards and risking illness, injury, and death. The study will extend the studies by presenting occupational health risks and suggestions for improvement in informal settlements of Nairobi, Kenya. This is a qualitative study conducted among sanitation stakeholders in Korogocho, Mukuru and Kibera informal settlements in Nairobi. Data were captured using digital voice recorders, transcribed and thematically analysed. The discussion notes were further supported by observational notes made during the interviews. These formed the basis for a robust picture of occupational health of manual pit emptiers; a lack or inappropriate use of protective clothing, and prolonged duration of working hours were described to contribute to the occupational health hazard. To continue working, manual pit emptiers had devised coping strategies which include working in groups, improvised protective clothing, sharing the available protective clothing, working at night and consuming alcohol drinks while at work. Many of these strategies are detrimental to their health. Occupational health hazards among pit emptiers are key for effective working and is as a result of a lack of collaboration amongst stakeholders linked to health, safety and lack of PPE of pit emptiers. Collaborations amongst sanitation stakeholders is paramount for health, safety, and in ensuring the provision and use of personal protective devices.

Photovoltaic Array Cleaning System Design and Evaluation

Dust accumulation on the photovoltaic module's surface results in appreciable loss and negatively affects the generated power. Hence, in this paper, the design of a photovoltaic array cleaning system is presented. The cleaning system utilizes one drive motor, two guide rails, and four sweepers during the cleaning process. The cleaning system was experimentally implemented for one month to investigate its efficiency on PV array energy output. The energy capture over a month for PV array cleaned using the proposed cleaning system is compared with that of the energy capture using soiled PV array. The results show a 15% increase in energy generation from PV array with cleaning. From the results, investigating the optimal scheduling of the PV array cleaning could be an interesting research topic.

Identifying Network Subgraph-Associated Essential Genes in Molecular Networks

Essential genes play an important role in the survival of an organism. It has been shown that cancer-associated essential genes are genes necessary for cancer cell proliferation, where these genes are potential therapeutic targets. Also, it was demonstrated that mutations of the cancer-associated essential genes give rise to the resistance of immunotherapy for patients with tumors. In the present study, we focus on studying the biological effects of the essential genes from a network perspective. We hypothesize that one can analyze a biological molecular network by decomposing it into both three-node and four-node digraphs (subgraphs). These network subgraphs encode the regulatory interaction information among the network’s genetic elements. In this study, the frequency of occurrence of the subgraph-associated essential genes in a molecular network was quantified by using the statistical parameter, odds ratio. Biological effects of subgraph-associated essential genes are discussed. In summary, the subgraph approach provides a systematic method for analyzing molecular networks and it can capture useful biological information for biomedical research.

Geometric Contrast of a 3D Model Obtained by Means of Digital Photogrametry with a Quasimetric Camera on UAV Classical Methods

Nowadays, the use of drones has been extended to practically any human activity. One of the main applications is focused on the surveying field. In this regard, software programs that process the images captured by the sensor from the drone in an almost automatic way have been developed and commercialized, but they only allow contrasting the results through control points. This work proposes the contrast of a 3D model obtained from a flight developed by a drone and a non-metric camera (due to its low cost), with a second model that is obtained by means of the historically-endorsed classical methods. In addition to this, the contrast is developed over a certain territory with a significant unevenness, so as to test the model generated with photogrammetry, and considering that photogrammetry with drones finds more difficulties in terms of accuracy in this kind of situations. Distances, heights, surfaces and volumes are measured on the basis of the 3D models generated, and the results are contrasted. The differences are about 0.2% for the measurement of distances and heights, 0.3% for surfaces and 0.6% when measuring volumes. Although they are not important, they do not meet the order of magnitude that is presented by salespeople.