Applied Sciences

20 pages, 1650 KiB

Open AccessArticle

Mutual Information Input Selector and Probabilistic Machine Learning Utilisation for Air Pollution Proxies

by Martha A. Zaidan, Lubna Dada, Mansour A. Alghamdi, Hisham Al-Jeelani, Heikki Lihavainen, Antti Hyvärinen and Tareq Hussein

Appl. Sci. 2019, 9(20), 4475; https://doi.org/10.3390/app9204475 - 22 Oct 2019

Cited by 22 | Viewed by 3347

Abstract

An air pollutant proxy is a mathematical model that estimates an unobserved air pollutant using other measured variables. The proxy is advantageous to fill missing data in a research campaign or to substitute a real measurement for minimising the cost as well as [...] Read more.

An air pollutant proxy is a mathematical model that estimates an unobserved air pollutant using other measured variables. The proxy is advantageous to fill missing data in a research campaign or to substitute a real measurement for minimising the cost as well as the operators involved (i.e., virtual sensor). In this paper, we present a generic concept of pollutant proxy development based on an optimised data-driven approach. We propose a mutual information concept to determine the interdependence of different variables and thus select the most correlated inputs. The most relevant variables are selected to be the best proxy inputs, where several metrics and data loss are also involved for guidance. The input selection method determines the used data for training pollutant proxies based on a probabilistic machine learning method. In particular, we use a Bayesian neural network that naturally prevents overfitting and provides confidence intervals around its output prediction. In this way, the prediction uncertainty could be assessed and evaluated. In order to demonstrate the effectiveness of our approach, we test it on an extensive air pollution database to estimate ozone concentration. Full article

(This article belongs to the Special Issue Air Quality Prediction Based on Machine Learning Algorithms)

► Show Figures

Graphical abstract

32 pages, 3834 KiB

Open AccessReview

Remote Monitoring of Vital Signs in Diverse Non-Clinical and Clinical Scenarios Using Computer Vision Systems: A Review

by Fatema-Tuz-Zohra Khanam, Ali Al-Naji and Javaan Chahl

Appl. Sci. 2019, 9(20), 4474; https://doi.org/10.3390/app9204474 - 22 Oct 2019

Cited by 62 | Viewed by 9358

Abstract

Techniques for noncontact measurement of vital signs using camera imaging technologies have been attracting increasing attention. For noncontact physiological assessments, computer vision-based methods appear to be an advantageous approach that could be robust, hygienic, reliable, safe, cost effective and suitable for long distance [...] Read more.

Techniques for noncontact measurement of vital signs using camera imaging technologies have been attracting increasing attention. For noncontact physiological assessments, computer vision-based methods appear to be an advantageous approach that could be robust, hygienic, reliable, safe, cost effective and suitable for long distance and long-term monitoring. In addition, video techniques allow measurements from multiple individuals opportunistically and simultaneously in groups. This paper aims to explore the progress of the technology from controlled clinical scenarios with fixed monitoring installations and controlled lighting, towards uncontrolled environments, crowds and moving sensor platforms. We focus on the diversity of applications and scenarios being studied in this topic. From this review it emerges that automatic multiple regions of interest (ROIs) selection, removal of noise artefacts caused by both illumination variations and motion artefacts, simultaneous multiple person monitoring, long distance detection, multi-camera fusion and accepted publicly available datasets are topics that still require research to enable the technology to mature into many real-world applications. Full article

(This article belongs to the Special Issue Contactless Vital Signs Monitoring)

► Show Figures

Figure 1

26 pages, 1545 KiB

Open AccessArticle

A Graph Representation Learning Algorithm for Low-Order Proximity Feature Extraction to Enhance Unsupervised IDS Preprocessing

by Yiran Hao, Yiqiang Sheng and Jinlin Wang

Appl. Sci. 2019, 9(20), 4473; https://doi.org/10.3390/app9204473 - 22 Oct 2019

Cited by 3 | Viewed by 2663

Abstract

Most existing studies on an unsupervised intrusion detection system (IDS) preprocessing ignore the relationship among packets. According to the homophily hypothesis, the local proximity structure in the similarity relational graph has similar embedding after preprocessing. To improve the performance of IDS by building [...] Read more.

Most existing studies on an unsupervised intrusion detection system (IDS) preprocessing ignore the relationship among packets. According to the homophily hypothesis, the local proximity structure in the similarity relational graph has similar embedding after preprocessing. To improve the performance of IDS by building a relationship among packets, we propose a packet2vec learning algorithm that extracts accurate local proximity features based on graph representation by adding penalty to node2vec. In this algorithm, we construct a relational graph G′ by using each packet as a node, calculate the cosine similarity between packets as edges, and then explore the low-order proximity of each packet via the penalty-based random walk in G′. We use the above algorithm as a preprocessing method to enhance the accuracy of unsupervised IDS by retaining the local proximity features of packets maximally. The original features of the packet are combined with the local proximity features as the input of a deep auto-encoder for IDS. Experiments based on ISCX2012 show that the proposal outperforms the state-of-the-art algorithms by 11.6% with respect to the accuracy of unsupervised IDS. It is the first time to introduce graph representation learning for packet-embedded preprocessing in the field of IDS. Full article

(This article belongs to the Section Computing and Artificial Intelligence)

► Show Figures

Graphical abstract

14 pages, 2184 KiB

Open AccessArticle

Locating Multiple Sources of Contagion in Complex Networks under the SIR Model

by Xiang Li, Yangyang Liu, Chengli Zhao, Xue Zhang and Dongyun Yi

Appl. Sci. 2019, 9(20), 4472; https://doi.org/10.3390/app9204472 - 22 Oct 2019

Cited by 14 | Viewed by 2513

Abstract

Simultaneous outbreaks of contagion are a great threat against human life, resulting in great panic in society. It is urgent for us to find an efficient multiple sources localization method with the aim of studying its pathogenic mechanism and minimizing its harm. However, [...] Read more.

Simultaneous outbreaks of contagion are a great threat against human life, resulting in great panic in society. It is urgent for us to find an efficient multiple sources localization method with the aim of studying its pathogenic mechanism and minimizing its harm. However, our ability to locate multiple sources is strictly limited by incomplete information about nodes and the inescapable randomness of the propagation process. In this paper, we present a valid approach, namely the Potential Concentration Label method, which helps locate multiple sources of contagion faster and more accurately in complex networks under the SIR(Susceptible-Infected-Recovered) model. Through label assignment in each node, our aim is to find the nodes with maximal value after several iterations. The experiments demonstrate that the accuracy of our multiple sources localization method is high enough. With the number of sources increasing, the accuracy of our method declines gradually. However, the accuracy remains at a slight fluctuation when average degree and network scale make a change. Moreover, our method still keeps a high multiple sources localization accuracy with noise of various intensities, which shows its strong anti-noise ability. I believe that our method provides a new perspective for accurate and fast multi-sources localization in complex networks. Full article

(This article belongs to the Special Issue Implementation of Vehicular Cloud Networks Using Wireless Sensor)

► Show Figures

Figure 1

10 pages, 3949 KiB

Open AccessArticle

Comparisons of Scotopic/Photopic Ratios Using 2- and 10-Degree Spectral Sensitivity Curves

by Jianhua Ding, Qi Yao and Lei Jiang

Appl. Sci. 2019, 9(20), 4471; https://doi.org/10.3390/app9204471 - 22 Oct 2019

Cited by 2 | Viewed by 2830

Abstract

Despite the fact that a 2-degree spectral sensitivity curve (SSC) is extensively used in scientific research and relevant applications, the choice between the 10-degree or the 2-degree photopic SSCs in practical applications for the calculation of scotopic/photopic ratios (S/P ratios) [...] Read more.

Despite the fact that a 2-degree spectral sensitivity curve (SSC) is extensively used in scientific research and relevant applications, the choice between the 10-degree or the 2-degree photopic SSCs in practical applications for the calculation of scotopic/photopic ratios (S/P ratios) depends on actual needs. We examined S/P ratios for more than 300 light sources for correlated colour temperatures (CCTs) from 2000 K to 8000 K and blackbody radiant spectra from 10000 K to 45000 K using 2- and 10-degree SSCs. Results showed that the ratio of the S/P values calculated using the 10-degree and 2-degree SSCs was approximately equal to 0.916. The average mesopic luminance difference increased from 0% to 5.7% at a photopic adaptation luminance from 0.005 to 5 cd/m². For most practical applications, the mesopic luminance values calculated using these two SSCs were different by several percentage units, yet these differences could be neglected. At extremely high CCTs over 10000 K, the mesopic luminance difference may approximate the maximum value of 16%. This work proposes the conversion coefficients for S/P ratios and the transforming mesopic luminance values calculated for 2- and 10-degree SSC systems. These results may help researchers clarify differences between the S/P ratios calculated using different SSCs. Full article

(This article belongs to the Section Optics and Lasers)

► Show Figures

Figure 1

4 pages, 160 KiB

Open AccessEditorial

Special Issue on Advanced DSP Techniques for High-Capacity and Energy-Efficient Optical Fiber Communications

by Zhongqi Pan and Yang Yue

Appl. Sci. 2019, 9(20), 4470; https://doi.org/10.3390/app9204470 - 22 Oct 2019

Viewed by 1783

Abstract

The rapid proliferation of the Internet has been driving communication networks closer and closer to their limits, while available bandwidth is disappearing due to ever-increasing network loads [...] Full article

(This article belongs to the Special Issue Advanced DSP Techniques for High-Capacity and Energy-Efficient Optical Fiber Communications)

11 pages, 3089 KiB

Open AccessArticle

Automated Real-Time Assessment of Stay-Cable Serviceability Using Smart Sensors

by Seunghoo Jeong, Young-Joo Lee, Do Hyoung Shin and Sung-Han Sim

Appl. Sci. 2019, 9(20), 4469; https://doi.org/10.3390/app9204469 - 22 Oct 2019

Cited by 7 | Viewed by 2446

Abstract

The number of cable-stayed bridges being built worldwide has been increasing owing to the increasing demand for long-span bridges. As the stay-cable is one of critical load-carrying members of cable-stayed bridges, its maintenance has become a significant issue. The stay-cable has an inherently [...] Read more.

The number of cable-stayed bridges being built worldwide has been increasing owing to the increasing demand for long-span bridges. As the stay-cable is one of critical load-carrying members of cable-stayed bridges, its maintenance has become a significant issue. The stay-cable has an inherently low damping ratio with high flexibility, which makes it vulnerable to vibrations owing to wind, rain, and traffic. Excessive vibration of the stay-cable can cause long-term fatigue problems in the stay-cable as well as the cable-stayed bridge. Therefore, civil engineers are required to carry out maintenance measures on stay-cables as a high priority. For the maintenance of the stay-cables, an automated real-time serviceability assessment system using wireless smart sensors was developed in this study. When the displacement of the cable in the mid-span exceeds either the upper or the lower bound provided in most bridge design codes, it is considered as a serviceability failure. The system developed in this study features embedded on-board processing, including the measurement of acceleration, estimation of displacement from measured acceleration, serviceability assessment, and monitoring through wireless communication. A series of laboratory tests were carried out to verify the performance of the developed system. Full article

(This article belongs to the Special Issue Recent Advances in Structural Health Monitoring and Nondestructive Testing in Civil Engineering)

► Show Figures

Figure 1

15 pages, 5318 KiB

Open AccessArticle

Design and Research of a Color Discrimination Method for Polycrystalline Silicon Cells Based on Laser Detection System

by Zijian Chen, Shiyu Wang, Lian Zhang and Zenghong Ma

Appl. Sci. 2019, 9(20), 4468; https://doi.org/10.3390/app9204468 - 22 Oct 2019

Cited by 1 | Viewed by 2077

Abstract

In this paper, a method of color discrimination based on sample sensitivity to light wavelength is proposed based on the reflection spectra of a large number of samples and the statistical calculation of the measurement data. A laser detection system is designed to [...] Read more.

In this paper, a method of color discrimination based on sample sensitivity to light wavelength is proposed based on the reflection spectra of a large number of samples and the statistical calculation of the measurement data. A laser detection system is designed to realize the color discrimination. For the color discrimination of polycrystalline silicon cells, the most sensitive wavelength, 434 nm, and the least sensitive wavelength, 645 nm, of polycrystalline silicon cells is obtained according to this method. A laser detection system was built to measure the polycrystalline silicon cells. This system consists of two lasers, optical shutters, collimating beam expanding systems, an optical coaxial system, sample platform, collecting lens, and optical power meter or optical sensor. Two laser beams of different wavelengths are beamed coaxially through the optical coaxial system onto a polycrystalline silicon cell and are reflected or scattered. The reflected or scattered lights are collected through a lens with a high number aperture and received separately by the optical power meter. Then the color value of the polycrystalline silicon cell in this system is characterized by the ratio of light intensity data received. The system measured a large number of previous polycrystalline silicon cells to form the different color categories of polycrystalline silicon cells of this system in the computer database. When a new polycrystalline silicon cell is measured, the color discrimination system can automatically classify the new polycrystalline silicon cell to a certain color category in order to achieve color discrimination. Full article

(This article belongs to the Special Issue Next Generation Solar Cells, Modules and Applications)

► Show Figures

Figure 1

13 pages, 2575 KiB

Open AccessArticle

Optimization of the CO₂ Liquefaction Process-Performance Study with Varying Ambient Temperature

by Steven Jackson and Eivind Brodal

Appl. Sci. 2019, 9(20), 4467; https://doi.org/10.3390/app9204467 - 22 Oct 2019

Cited by 10 | Viewed by 4203

Abstract

In carbon capture utilization and storage (CCUS) projects, the transportation of CO₂ by ship can be an attractive alternative to transportation using a pipeline, particularly when the distance between the source and usage or storage location is large. However, a challenge associated [...] Read more.

In carbon capture utilization and storage (CCUS) projects, the transportation of CO₂ by ship can be an attractive alternative to transportation using a pipeline, particularly when the distance between the source and usage or storage location is large. However, a challenge associated with this approach is that the energy consumption of the liquefaction process can be significant, which makes the selection of an energy-efficient design an important factor in the minimization of operating costs. Since the liquefaction process operates at low temperature, its energy consumption varies with ambient temperature, which influences the trade-off point between different liquefaction process designs. A consistent set of data showing the relationship between energy consumption and cooling temperature is therefore useful in the CCUS system modelling. This study addresses this issue by modelling the performance of a variety of CO₂ liquefaction processes across a range of ambient temperatures applying a methodical approach for the optimization of process operating parameters. The findings comprise a set of data for the minimum energy consumption cases. The main conclusions of this study are that an open-cycle CO₂ process will offer lowest energy consumption below 20 °C cooling temperature and that over the cooling temperature range 15 to 50 °C, the minimum energy consumption for all liquefaction process rises by around 40%. Full article

(This article belongs to the Special Issue Carbon Capture and Utilization)

► Show Figures

Figure 1

20 pages, 4201 KiB

Open AccessArticle

Analysis of Coastal Zone Data of Northern Yantai Collected by Remote Sensing from 1990 to 2018

by Min Zhou, Mengquan Wu, Guangzong Zhang, Lianjie Zhao, Xiaoyun Hou and Yi Yang

Appl. Sci. 2019, 9(20), 4466; https://doi.org/10.3390/app9204466 - 22 Oct 2019

Cited by 9 | Viewed by 2076

Abstract

Using remote sensing images of different time phases from 1990 to 2018, the surface coverage information of northern Yantai (coastline, 2 km from coastline to land) was extracted by means of average high tide line and visual interpretation. The end point change rate [...] Read more.

Using remote sensing images of different time phases from 1990 to 2018, the surface coverage information of northern Yantai (coastline, 2 km from coastline to land) was extracted by means of average high tide line and visual interpretation. The end point change rate (EPR) and linear regression rate were used to study the coastline change rate, the fractal dimension of the coastline in the study area was analyzed, and the change of the type of coastal surface cover was analyzed by the transition matrix. The results show that: (1) Form 1990 to 2018, a significant trend of a continuous increase in the total length of coastline was observed with an increase of 181.08 km (43.18%). In the study area, the coastline of Laizhou had the greatest change rate with an EPR value of 33.67 m/a, whereas the coastline of Laishan had the smallest change rate with an EPR value of 0.30 m/a. (2) Over the past 30 years, with the rapid economic development of Yantai and the ensuant urbanization, the total surface area of the coastal zone in the study area has increased by 144.94 km², mainly in the areas covered by structures and forests/grasses, by 112.96 km² and 96.08 km², respectively, while the areas of desert/bare land and water have decreased by 92.26 km² and 12.32 km², respectively. (3) The changes among different types in the study area were clear, mainly from desert/bare land, cultivated land, and building areas to forests/grasses cover and structures. The change areas were mainly concentrated in Laizhou, Longkou, Zhifu, and Penglai. Frequent human activities are an important factor affecting the continuous expansion of the coastal areas of Jiaodong Peninsula to the sea. Aquaculture, coastal construction, construction of artificial islands, and expansion of port terminals have seriously affected the sustainability of ecological resources in the coastal areas. At the same time, the changes in the ecological environment in the coastal zone will have a greater impact on the health of the coastal zone. Full article

(This article belongs to the Section Optics and Lasers)

► Show Figures

Figure 1

14 pages, 2882 KiB

Open AccessArticle

Rolling Bearing Incipient Fault Detection Based on a Multi-Resolution Singular Value Decomposition

by Jiesi Luo and Shaohui Zhang

Appl. Sci. 2019, 9(20), 4465; https://doi.org/10.3390/app9204465 - 22 Oct 2019

Cited by 9 | Viewed by 2049

Abstract

The periodic impulse characteristics caused by rolling bearing damage are weak in the incipient failure stage. Thus, these characteristics are always drowned out by background noise and other harmonic interference. A novel approach based on multi-resolution singular value decomposition (MRSVD) is proposed in [...] Read more.

The periodic impulse characteristics caused by rolling bearing damage are weak in the incipient failure stage. Thus, these characteristics are always drowned out by background noise and other harmonic interference. A novel approach based on multi-resolution singular value decomposition (MRSVD) is proposed in order to extract the periodic impulse characteristics for incipient fault detection. With the MRSVD method, the vibration signal is first decomposed to obtain a group of approximate signals and detailed signals with different resolutions. The first detail signal is mainly composed of noise and the last approximate signal is mainly composed of harmonic interference. Combined with the kurtosis index, the hidden periodic impulse signal will be extracted from the detail signals (in addition to the first detail signal). Thus, the incipient fault detection of a rolling bearing can be fulfilled according to the envelope demodulation spectrum of the extracted periodic impulse signal. The effectiveness of the proposed method has been demonstrated with both simulation and experimental analyses. Full article

(This article belongs to the Section Mechanical Engineering)

► Show Figures

Figure 1

16 pages, 9034 KiB

Open AccessArticle

An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications

by Xuyue Yin, Xiumin Fan, Xu Yang, Shiguang Qiu and Zhinan Zhang

Appl. Sci. 2019, 9(20), 4464; https://doi.org/10.3390/app9204464 - 22 Oct 2019

Cited by 6 | Viewed by 3313

Abstract

Industrial augmented reality (AR) applications demand high on the visual consistency of virtual-real registration. To present, the marker-based registration method is most popular because it is fast, robust, and convenient to obtain the registration matrix. In practice, the registration matrix should multiply an [...] Read more.

Industrial augmented reality (AR) applications demand high on the visual consistency of virtual-real registration. To present, the marker-based registration method is most popular because it is fast, robust, and convenient to obtain the registration matrix. In practice, the registration matrix should multiply an offset matrix that describes the transformation between the attaching position and the initial position of the marker relative to the object. However, the offset matrix is usually measured, calculated, and set manually, which is not accurate and convenient. This paper proposes an accurate and automatic marker–object offset matrix calibration method. First, the normal direction of the target object is obtained by searching and matching the top surface of the CAD model. Then, the spatial translation is estimated by aligning the projected and the imaged top surface. Finally, all six parameters of the offset matrix are iteratively optimized using a 3D image alignment framework. Experiments were performed on the publicity monocular rigid 3D tracking dataset and an automobile gearbox. The average translation and rotation errors of the optimized offset matrix are 2.10 mm and 1.56 degree respectively. The results validate that the proposed method is accurate and automatic, which contributes to a universal offset matrix calibration tool for marker-based industrial AR applications. Full article

(This article belongs to the Special Issue Augmented Reality: Current Trends, Challenges and Prospects)

► Show Figures

Figure 1

15 pages, 8184 KiB

Open AccessArticle

Effects of Laser Beam Parameters on Bendability and Microstructure of Stainless Steel in Three-Dimensional Laser Forming

by Daniyal Abolhasani, Seyed Mohammad Hossein Seyedkashi, Mohammad Hoseinpour Gollo and Young Hoon Moon

Appl. Sci. 2019, 9(20), 4463; https://doi.org/10.3390/app9204463 - 22 Oct 2019

Cited by 11 | Viewed by 2392

Abstract

In this study, the effects of beam diameter and hatch spacing between the scanning paths on the bendability and microstructural behavior of an AISI 316 stainless-steel sheet in three-dimensional laser forming were investigated. The strain on the heating lines and that between the [...] Read more.

In this study, the effects of beam diameter and hatch spacing between the scanning paths on the bendability and microstructural behavior of an AISI 316 stainless-steel sheet in three-dimensional laser forming were investigated. The strain on the heating lines and that between the scanning tracks were numerically investigated to elucidate the effects of process parameters. The strain on heating lines and that between scanning tracks were numerically investigated. The increase in hatch spacing caused a larger amount of counter bending to be retained in the unaffected areas between the tracks through a process dominated by a temperature gradient mechanism (TGM), and also caused a lower deformation. The formation of small equiaxed dendrite grains instead of coarse and inhomogeneous austenite grains occurred during the process at a larger beam diameter and smaller hatch spacing, which increased the bendability of the material, owing to the decrease in anisotropy in the microstructure. Moreover, the increase in the grain size of the reheated overlap region of the deformed sample led to a higher bendability. Under these conditions, the microhardness was also increased owing to the grain boundary strengthening effect. Full article

(This article belongs to the Section Mechanical Engineering)

► Show Figures

Figure 1

15 pages, 1540 KiB

Open AccessArticle

Feasibility Study of Native Ureolytic Bacteria for Biocementation Towards Coastal Erosion Protection by MICP Method

by Md Al Imran, Shuya Kimura, Kazunori Nakashima, Niki Evelpidou and Satoru Kawasaki

Appl. Sci. 2019, 9(20), 4462; https://doi.org/10.3390/app9204462 - 21 Oct 2019

Cited by 36 | Viewed by 5162

Abstract

In recent years, traditional material for coastal erosion protection has become very expensive and not sustainable and eco-friendly for the long term. As an alternative countermeasure, this study focused on a sustainable biological ground improvement technique that can be utilized as an option [...] Read more.

In recent years, traditional material for coastal erosion protection has become very expensive and not sustainable and eco-friendly for the long term. As an alternative countermeasure, this study focused on a sustainable biological ground improvement technique that can be utilized as an option for improving the mechanical and geotechnical engineering properties of soil by the microbially induced carbonate precipitation (MICP) technique considering native ureolytic bacteria. To protect coastal erosion, an innovative and sustainable strategy was proposed in this study by means of combing geotube and the MICP method. For a successful sand solidification, the urease activity, environmental factors, urease distribution, and calcite precipitation trend, among others, have been investigated using the isolated native strains. Our results revealed that urease activity of the identified strains denoted as G1 (Micrococcus sp.), G2 (Pseudoalteromonas sp.), and G3 (Virgibacillus sp.) relied on environment-specific parameters and, additionally, urease was not discharged in the culture solution but would discharge in and/or on the bacterial cell, and the fluid of the cells showed urease activity. Moreover, we successfully obtained solidified sand bearing UCS (Unconfined Compressive Strength) up to 1.8 MPa. We also proposed a novel sustainable approach for field implementation in a combination of geotube and MICP for coastal erosion protection that is cheaper, energy-saving, eco-friendly, and sustainable for Mediterranean countries, as well as for bio-mediated soil improvement. Full article

(This article belongs to the Special Issue Coastal Deposits: Environmental Implications, Mathematical Modeling and Technological Development)

► Show Figures

Figure 1

10 pages, 3140 KiB

Open AccessArticle

Characterization and Application of Agave salmiana Cuticle as Bio-membrane in Low-temperature Electrolyzer and Fuel Cells

by Cristhian H. Arredondo, Guadalupe Aguilar-Lira, Irma Perez-Silva, Jose Antonio Rodriguez, Gabriela Islas and Prisciliano Hernandez

Appl. Sci. 2019, 9(20), 4461; https://doi.org/10.3390/app9204461 - 21 Oct 2019

Cited by 4 | Viewed by 3447

Abstract

This work describes the application of the Agave salmiana cuticle as a new protonic exchange biological membrane (0.080 ± 0.001 mm thickness). Different chemical, electrochemical and mechanical treatments were evaluated to stimulate the ionic exchange properties of the cuticle. Thermal treatment was adequate [...] Read more.

This work describes the application of the Agave salmiana cuticle as a new protonic exchange biological membrane (0.080 ± 0.001 mm thickness). Different chemical, electrochemical and mechanical treatments were evaluated to stimulate the ionic exchange properties of the cuticle. Thermal treatment was adequate for its application in a two-chamber electrolyzer. Under optimal conditions an ionic conductivity value of 10 ± 3 mS cm⁻¹ was obtained; this value is similar to the value achieved using a Nafion membrane. The thermally-activated bio-membrane was also evaluated in a fuel cell, where the highest potential was obtained using methanol and hydrogen (0.46 ± 0.01 V). This result makes the Agave salmiana cuticle a competitive choice to replace the commercial membrane. Its surface morphology and their functional groups were evaluated through scanning electron microscopy (SEM), infrared spectroscopy and impedance spectroscopy. This thermally-treated Agave salmiana cuticle is an ecofriendly alternative to replace Nafion membranes in electrolyzer and fuel cells. Full article

(This article belongs to the Section Chemical and Molecular Sciences)

► Show Figures

Figure 1

18 pages, 3716 KiB

Open AccessFeature PaperArticle

Deep LSTM with Reinforcement Learning Layer for Financial Trend Prediction in FX High Frequency Trading Systems

by Francesco Rundo

Appl. Sci. 2019, 9(20), 4460; https://doi.org/10.3390/app9204460 - 21 Oct 2019

Cited by 44 | Viewed by 20125

Abstract

High-frequency trading is a method of intervention on the financial markets that uses sophisticated software tools, and sometimes also hardware, with which to implement high-frequency negotiations, guided by mathematical algorithms, that act on markets for shares, options, bonds, derivative instruments, commodities, and so [...] Read more.

High-frequency trading is a method of intervention on the financial markets that uses sophisticated software tools, and sometimes also hardware, with which to implement high-frequency negotiations, guided by mathematical algorithms, that act on markets for shares, options, bonds, derivative instruments, commodities, and so on. HFT strategies have reached considerable volumes of commercial traffic, so much so that it is estimated that they are responsible for most of the transaction traffic of some stock exchanges, with percentages that, in some cases, exceed 70% of the total. One of the main issues of the HFT systems is the prediction of the medium-short term trend. For this reason, many algorithms have been proposed in literature. The author proposes in this work the use of an algorithm based both on supervised Deep Learning and on a Reinforcement Learning algorithm for forecasting the short-term trend in the currency FOREX (FOReign EXchange) market to maximize the return on investment in an HFT algorithm. With an average accuracy of about 85%, the proposed algorithm is able to predict the medium-short term trend of a currency cross based on the historical trend of this and by means of correlation data with other currency crosses using techniques known in the financial field with the term arbitrage. The final part of the proposed pipeline includes a grid trading engine which, based on the aforementioned trend predictions, will perform high frequency operations in order to maximize profit and minimize drawdown. The trading system has been validated over several financial years and on the EUR/USD cross confirming the high performance in terms of Return of Investment (98.23%) in addition to a reduced drawdown (15.97 %) which confirms its financial sustainability. Full article

(This article belongs to the Special Issue Advanced Bio-Inspired Mathematical Modeling and Machine Learning Algorithms for Quantitative Finance Applications)

► Show Figures

Figure 1

15 pages, 3714 KiB

Open AccessArticle

Glucose Data Classification for Diabetic Patient Monitoring

by Amine Rghioui, Jaime Lloret, Lorena Parra, Sandra Sendra and Abdelmajid Oumnad

Appl. Sci. 2019, 9(20), 4459; https://doi.org/10.3390/app9204459 - 21 Oct 2019

Cited by 21 | Viewed by 6748

Abstract

Living longer and healthier is the wish of all patients. Therefore, to design effective solutions for this objective, the concept of Big Data in the health field can be integrated. Our work proposes a patient monitoring system based on Internet of Things (IoT) [...] Read more.

Living longer and healthier is the wish of all patients. Therefore, to design effective solutions for this objective, the concept of Big Data in the health field can be integrated. Our work proposes a patient monitoring system based on Internet of Things (IoT) and a diagnostic prediction tool for diabetic patients. This system provides real-time blood glucose readings and information on blood glucose levels. It monitors blood glucose levels at regular intervals. The proposed system aims to prevent high blood sugar and significant glucose fluctuations. The system provides a precise result. The collected and stored data will be classified by using several classification algorithms to predict glucose levels in diabetic patients. The main advantage of this system is that the blood glucose level is reported instantly; it can be lowered or increased. Full article

(This article belongs to the Special Issue The Application of Data Mining to Health Data)

► Show Figures

Figure 1

20 pages, 10151 KiB

Open AccessArticle

Dynamic Performance Optimization of Circular Sawing Machine Gearbox

by Yangyu Wang, Pengcheng Ni, Donghui Wen, Qiong Lin, Dejie Wang, Changqing Ma, Yanjin Rao, Hanpeng Wang and Dapeng Tan

Appl. Sci. 2019, 9(20), 4458; https://doi.org/10.3390/app9204458 - 21 Oct 2019

Cited by 10 | Viewed by 3567

Abstract

To optimize the rigidity and dynamic mechanical properties of a sawing machine and improve its processing quality and stability, a design method for the sawing machine’s gearbox was proposed. First, a lightweight design of the gearbox was realized by topology optimization. Second, the [...] Read more.

To optimize the rigidity and dynamic mechanical properties of a sawing machine and improve its processing quality and stability, a design method for the sawing machine’s gearbox was proposed. First, a lightweight design of the gearbox was realized by topology optimization. Second, the sensitivity of different design variables of the new gearbox was determined via sensitivity analysis of the objective function. Finally, multi-objective optimization was used to obtain the optimal solution for the gearbox. Considering the complexity of the internal structure of the gearbox assembly and the accuracy of the numerical calculation process, a modeling method with mass points was proposed. A comparison between the numerical calculation results and the operation mode analysis revealed that the former was accurate and can be applied to the verification of the optimized gearbox. By optimizing the vibration signals before and after, and the analysis of the end face quality of the workpiece, the results revealed that the optimized gearbox has a significantly reduced amplitude under various operating conditions. In addition, the vibration stability was improved, and the end face quality of the workpiece was significantly enhanced compared to that before optimization. This study serves as a theoretical reference for multi-body dynamics modeling and optimization of machine tools, and also outlines technical solutions for high-speed stable cutting with sawing machines. Full article

(This article belongs to the Section Acoustics and Vibrations)

► Show Figures

Figure 1

12 pages, 5250 KiB

Open AccessArticle

Iterative Phase-Only Hologram Generation Based on the Perceived Image Quality

by Haining Yang and Daping Chu

Appl. Sci. 2019, 9(20), 4457; https://doi.org/10.3390/app9204457 - 21 Oct 2019

Cited by 4 | Viewed by 2326

Abstract

Image quality metrics are a critical element in the iterative Fourier transform algorithms (IFTAs) for the computer generation of phase-only holograms. Conventional image quality metrics such as root-mean-squared error (RMSE) are sensitive to image content and unable to reflect the perceived image quality [...] Read more.

Image quality metrics are a critical element in the iterative Fourier transform algorithms (IFTAs) for the computer generation of phase-only holograms. Conventional image quality metrics such as root-mean-squared error (RMSE) are sensitive to image content and unable to reflect the perceived image quality accurately. This would have a significant impact on the calculation speed and the quality of the generated hologram. In this work, the structure similarity (SSIM) was proposed as an image quality metric in IFTAs due to its ability to predict the perceived image quality in the presence of the white Gaussian noise and its independence on the image content. This would enable IFTAs to terminate when further iterations would no longer lead to improvement in the perceived image quality. As a result, up to 75% of unnecessary iterations were eliminated by the use of SSIM as the image quality metric. Full article

(This article belongs to the Special Issue Practical Computer-Generated Hologram for 3D Display)

► Show Figures

Figure 1

14 pages, 580 KiB

Open AccessFeature PaperArticle

Analysis of Seaweeds from South West England as a Biorefinery Feedstock

by Tracey A. Beacham, Isobel S. Cole, Louisa S. DeDross, Sofia Raikova, Christopher J. Chuck, John Macdonald, Leopoldo Herrera, Tariq Ali, Ruth L. Airs, Andrew Landels and Michael J. Allen

Appl. Sci. 2019, 9(20), 4456; https://doi.org/10.3390/app9204456 - 21 Oct 2019

Cited by 14 | Viewed by 3453

Abstract

Seaweeds contain many varied and commercially valuable components, from individual pigments and metabolites through to whole biomass, and yet they remain an under cultivated and underutilised commodity. Currently, commercial exploitation of seaweeds is predominantly limited to whole biomass consumption or single product extracts [...] Read more.

Seaweeds contain many varied and commercially valuable components, from individual pigments and metabolites through to whole biomass, and yet they remain an under cultivated and underutilised commodity. Currently, commercial exploitation of seaweeds is predominantly limited to whole biomass consumption or single product extracts for the food industry. The development of a seaweed biorefinery, based around multiple products and services, could provide an important opportunity to exploit new and currently underexplored markets. Here, we assessed the native and invasive seaweeds on the South West coast of the UK to determine their characteristics and potential for exploitation through a biorefinery pipeline, looking at multiple components including pigments, carbohydrates, lipids, proteins and other metabolites. Full article

(This article belongs to the Special Issue Effective Biorefineries through the Co-production of Chemicals and Biofuels)

► Show Figures

Figure 1

18 pages, 4008 KiB

Open AccessArticle

An FCM–GABPN Ensemble Approach for Material Feeding Prediction of Printed Circuit Board Template

by Shengping Lv, Rongheng Xian, Denghui Li, Binbin Zheng and Hong Jin

Appl. Sci. 2019, 9(20), 4455; https://doi.org/10.3390/app9204455 - 21 Oct 2019

Cited by 2 | Viewed by 2136

Abstract

Accurate prediction of material feeding before production for a printed circuit board (PCB) template can reduce the comprehensive cost caused by surplus and supplemental feeding. In this study, a novel hybrid approach combining fuzzy c-means (FCM), feature selection algorithm, and genetic algorithm (GA) [...] Read more.

Accurate prediction of material feeding before production for a printed circuit board (PCB) template can reduce the comprehensive cost caused by surplus and supplemental feeding. In this study, a novel hybrid approach combining fuzzy c-means (FCM), feature selection algorithm, and genetic algorithm (GA) with back-propagation networks (BPN) was developed for the prediction of material feeding of a PCB template. In the proposed FCM–GABPN, input templates were firstly clustered by FCM, and seven feature selection mechanisms were utilized to select critical attributes related to scrap rate for each category of templates before they are fed into the GABPN. Then, templates belonging to different categories were trained with different GABPNs, in which the separately selected attributes were taken as their inputs and the initial parameter for BPNs were optimized by GA. After training, an ensemble predictor formed with all GABPNs can be taken to predict the scrap rate. Finally, another BPN was adopted to conduct nonlinear aggregation of the outputs from the component BPNs and determine the predicted feeding panel of the PCB template with a transformation. To validate the effectiveness and superiority of the proposed approach, the experiment and comparison with other approaches were conducted based on the actual records collected from a PCB template production company. The results indicated that the prediction accuracy of the proposed approach was better than those of the other methods. Besides, the proposed FCM–GABPN exhibited superiority to reduce the surplus and/or supplemental feeding in most of the case in simulation, as compared to other methods. Both contributed to the superiority of the proposed approach. Full article

► Show Figures

Figure 1

13 pages, 2225 KiB

Open AccessArticle

Improved Attribute-Based Encryption Using Chaos Synchronization and Its Application to MQTT Security

by Teh-Lu Liao, Hong-Ru Lin, Pei-Yen Wan and Jun-Juh Yan

Appl. Sci. 2019, 9(20), 4454; https://doi.org/10.3390/app9204454 - 21 Oct 2019

Cited by 15 | Viewed by 3220

Abstract

In recent years, Internet of Things (IoT) has developed rapidly and been widely used in industry, agriculture, e-health, smart cities, and families. As the total amount of data transmission will increase dramatically, security will become a very important issue in data communication in [...] Read more.

In recent years, Internet of Things (IoT) has developed rapidly and been widely used in industry, agriculture, e-health, smart cities, and families. As the total amount of data transmission will increase dramatically, security will become a very important issue in data communication in the IoT. There are many communication protocols for Device to Device (D2D) or Machine to Machine (M2M) in IoT. One of them is Message Queuing Telemetry Transport (MQTT), which is quite prevalent and easy to use. MQTT is designed for resource-constrained devices, so its security is not as strong as other communication protocols. To enhance MQTT security, it needs an additional function to overcome its weakness. However, considering the limited computational abilities of resource-constrained devices, they cannot use too powerful or complicated cryptographic algorithms. Therefore, this paper proposes novel improved attribute-based encryption (ABE) integrated with chaos synchronization to enhance the MQTT security. Finally, a small size of IoT is implemented to simulate resource-constrained devices equipped with a human–machine interface and monitoring software to show and verify the performance of MQTT communication with this improved ABE algorithm. Full article

► Show Figures

Figure 1

22 pages, 5586 KiB

Open AccessArticle

Design and Development of an Active Suspension System Using Pneumatic-Muscle Actuator and Intelligent Control

by I-Hsum Li and Lian-Wang Lee

Appl. Sci. 2019, 9(20), 4453; https://doi.org/10.3390/app9204453 - 20 Oct 2019

Cited by 5 | Viewed by 4824

Abstract

A pneumatic muscle is a cheap, clean, and high-power active actuator. However, it is difficult to control due to its inherent nonlinearity and time-varying characteristics. This paper presents a pneumatic muscle active suspension system (PM-ASS) for vehicles and uses an experimental study to [...] Read more.

A pneumatic muscle is a cheap, clean, and high-power active actuator. However, it is difficult to control due to its inherent nonlinearity and time-varying characteristics. This paper presents a pneumatic muscle active suspension system (PM-ASS) for vehicles and uses an experimental study to analyze its stability and accuracy in terms of reducing vibration. In the PM-ASS, the pneumatic muscle actuator is designed in parallel with two MacPherson struts to provide a vertical force between the chassis and the wheel. This geometric arrangement allows the PM-ASS to produce the maximum force to counter road vibration and make the MacPherson struts generate significant improvement. In terms of the controller design, this paper uses an adaptive Fourier neural network sliding-mode controller with

H_{\infty}

tracking performance for the PM-ASS, which confronts nonlinearities and time-varying characteristics. A state-predictor is used to predict the output error and to provide the predictions for the controller. Experiments with a rough concave-convex road and a two-bump excitation road use a quarter-car test rig to verify the practical feasibility of the PM-ASS, and the results show that the PM-ASS gives an improvement the ride comfort. Full article

(This article belongs to the Section Applied Industrial Technologies)

► Show Figures

Figure 1

5 pages, 189 KiB

Open AccessEditorial

Big and Deep Hype and Hope: On the Special Issue for Deep Learning and Big Data in Healthcare

by José Luis Rojo-Álvarez

Appl. Sci. 2019, 9(20), 4452; https://doi.org/10.3390/app9204452 - 20 Oct 2019

Cited by 2 | Viewed by 2654

Abstract

Deep Learning networks are revolutionizing both the academic and the industrial scenarios of information and communication technologies [...] Full article

(This article belongs to the Special Issue Deep Learning and Big Data in Healthcare)

5 pages, 178 KiB

Open AccessEditorial

Sustainable Energy Systems Planning, Integration, and Management

by Amjad Anvari-Moghaddam, Behnam Mohammadi-ivatloo, Somayeh Asadi, Kim Guldstrand Larsen and Mohammad Shahidehpour

Appl. Sci. 2019, 9(20), 4451; https://doi.org/10.3390/app9204451 - 20 Oct 2019

Cited by 5 | Viewed by 2295

Abstract

Energy systems worldwide are undergoing a major transformation as a consequence of the transition towards the widespread use of clean and sustainable energy sources [...] Full article

(This article belongs to the Special Issue Sustainable Energy Systems Planning, Integration and Management)

18 pages, 3871 KiB

Open AccessArticle

Water-Weakening Effects on the Mechanical Behavior of Different Rock Types: Phenomena and Mechanisms

by Xin Cai, Zilong Zhou, Kewei Liu, Xueming Du and Haizhi Zang

Appl. Sci. 2019, 9(20), 4450; https://doi.org/10.3390/app9204450 - 20 Oct 2019

Cited by 107 | Viewed by 7040

Abstract

The presence of water strongly affects rock properties and would be related to a series of geological disasters. To understand water saturation effects on the mechanical behavior of different rock types and interpret the underlying mechanisms of differences in water sensitivity, three kinds [...] Read more.

The presence of water strongly affects rock properties and would be related to a series of geological disasters. To understand water saturation effects on the mechanical behavior of different rock types and interpret the underlying mechanisms of differences in water sensitivity, three kinds of rocks, namely sandstone, granite and marble, were selected for tests. Uniaxial compression experiments were conducted on specimens under oven-dried and water-saturated conditions. Acoustic emission (AE) techniques were also applied to monitor and record AE signals during tests. Experimental results reveal that water weakens the mechanical parameters of the three tested rocks, such as uniaxial compressive strength (UCS), elastic modulus and critical strain. The sandstone undergoes the greatest weakening with the addition of pore water, the mechanical properties of the granite exhibit relatively minor reductions, while the marble is the least affected by water saturation. The water-weakening degree of rock properties depends on the porosity as well as the mineralogy, especially the proportion of quartz and swelling clays. Moreover, after water saturation, the failure pattern of the sandstone and the granite tends to transform into the shear-dominant mode from the tensile one in dry state, probably due to frictional reduction. However, the water presence does not change the failure mode of the marble. Full article

► Show Figures

Figure 1

12 pages, 9531 KiB

Open AccessArticle

Research on Virtual Inductive Control Strategy for Direct Current Microgrid with Constant Power Loads

by Zhiping Cheng, Meng Gong, Jinfeng Gao, Zhongwen Li and Jikai Si

Appl. Sci. 2019, 9(20), 4449; https://doi.org/10.3390/app9204449 - 20 Oct 2019

Cited by 6 | Viewed by 2507

Abstract

In order to improve the stability of direct current (DC) microgrid with constant power loads, a novel virtual inductive approach is proposed in this paper. It is known that the negative impedance characteristic of constant power loads will lead to DC bus voltage [...] Read more.

In order to improve the stability of direct current (DC) microgrid with constant power loads, a novel virtual inductive approach is proposed in this paper. It is known that the negative impedance characteristic of constant power loads will lead to DC bus voltage fluctuation, which will be more serious when they integrate into the DC microgrid though a large transmission line inductive. For the convenience of analysis, a simplified circuit model of the system is obtained by modeling the distributed resources. Unlike the existing control strategies, the proposed control strategy constructs a negative inductance link, which helps to counteract the negative effects of the line inductive between the power source and the transmission line. Detailed performance comparison of the proposed control and virtual capacitance are implemented through MATLAB/simulink simulation. Moreover, the improved performance of the proposed control method has been further validated with several detailed studies. The results demonstrate the feasibility and superiority of the proposed strategy. Full article

(This article belongs to the Special Issue DC & Hybrid Micro-Grids)

► Show Figures

Figure 1

15 pages, 1062 KiB

Open AccessArticle

Interaction-Based Behavioral Analysis of Twitter Social Network Accounts

by Hafzullah İş and Taner Tuncer

Appl. Sci. 2019, 9(20), 4448; https://doi.org/10.3390/app9204448 - 20 Oct 2019

Cited by 12 | Viewed by 3740

Abstract

This article considers methodological approaches to determine and prevent social media manipulation specific to Twitter. Behavioral analyses of Twitter users were performed by using their profile structures and interaction types, and Twitter users were classified according to their effect size values by determining [...] Read more.

This article considers methodological approaches to determine and prevent social media manipulation specific to Twitter. Behavioral analyses of Twitter users were performed by using their profile structures and interaction types, and Twitter users were classified according to their effect size values by determining their asset values. User profiles were classified into three different categories, namely popular-active, observer-passive, and spam-bot-malicious by using k-nearest neighbor (K-NN), support vector machine (SVM), and artificial neural network (ANN) algorithms. For classification, the study used the basic characteristics of users, such as density, centralization, and diameter, as well as suggested time series such as the simple moving average and cumulative moving average. The highest accuracy was obtained by the K-NN algorithm. The results obtained with K-NN for all classes were higher than the F1-Score values obtained for the other algorithms. According to the results obtained, classification accuracy values were found to reach a maximum of 96.81% and a minimum of 92.33%. Our classification results showed that the proposed method was satisfactory for popular-active, observer-passive, and spam-bot-malicious account separation. Full article

(This article belongs to the Section Computing and Artificial Intelligence)

► Show Figures

Figure 1

9 pages, 1340 KiB

Open AccessArticle

Light-Activated Zirconium(IV) Phthalocyanine Derivatives Linked to Graphite Oxide Flakes and Discussion on Their Antibacterial Activity

by Anna Lukowiak, Yuriy Gerasymchuk, Anna Wedzynska, Leili Tahershamsi, Robert Tomala, Wieslaw Strek, Dominika Piatek, Izabela Korona-Glowniak, Mateusz Speruda, Anna Kedziora and Gabriela Bugla-Ploskonska

Appl. Sci. 2019, 9(20), 4447; https://doi.org/10.3390/app9204447 - 20 Oct 2019

Cited by 6 | Viewed by 2998

Abstract

In search of an effective antibacterial agent that is useful in photodynamic therapy, new derivatives of zirconium(IV) phthalocyanine (ZrPc) complexes were obtained and linked to graphite oxide flakes. In the syntheses of ZrPc derivatives, two bis-axially substituted ligands with terminal amino group and [...] Read more.

In search of an effective antibacterial agent that is useful in photodynamic therapy, new derivatives of zirconium(IV) phthalocyanine (ZrPc) complexes were obtained and linked to graphite oxide flakes. In the syntheses of ZrPc derivatives, two bis-axially substituted ligands with terminal amino group and different lengths of linear carbon chain (C4 in 4-aminobutyric acid or C11 in 11-aminoundecanoic acid) were used. The optical properties (absorption and photoluminescence spectra) of ZrPcs and the composites were examined. Broadband red–near-infrared lamp was tested as an external stimulus to activate ZrPcs and the composites. Optical techniques were used to show generation of singlet oxygen during irradiation. Considering the application of graphite oxide-based materials as bacteriostatic photosensitive additives for endodontic treatment of periapical tissue inflammation, the antibacterial activity was determined on one Escherichia coli strain isolated directly from an infected root canal of a human tooth and one strain with silver and antibiotic resistance. Looking at the obtained results, modified levels of activity toward different bacterial strains are discussed. Full article

(This article belongs to the Special Issue Advances on Dielectric Photonic Devices and Systems beyond Visible)

► Show Figures

Figure 1

18 pages, 1758 KiB

Open AccessArticle

Kirchhoff Migration for Identifying Unknown Targets Surrounded by Random Scatterers

by Chi Young Ahn, Taeyoung Ha and Won-Kwang Park

Appl. Sci. 2019, 9(20), 4446; https://doi.org/10.3390/app9204446 - 20 Oct 2019

Cited by 2 | Viewed by 2317

Abstract

In this paper, we take into account a two-dimensional inverse scattering problem for localizing small electromagnetic anomalies when they are surrounded by small, randomly distributed electromagnetic scatterers. Generally, subspace migration is considered to be an improved version of Kirchhoff migration; however, for the [...] Read more.

In this paper, we take into account a two-dimensional inverse scattering problem for localizing small electromagnetic anomalies when they are surrounded by small, randomly distributed electromagnetic scatterers. Generally, subspace migration is considered to be an improved version of Kirchhoff migration; however, for the problem considered here, simulation results have confirmed that Kirchhoff migration is better than subspace migration, though the reasons for this have not been investigated theoretically. In order to explain theoretical reason, we explored that the imaging function of Kirchhoff migration can be expressed by the size, permittivity, permeability of anomalies and random scatterers, and the Bessel function of the first kind of order zero and one. Considered approach is based on the fact that the far-field pattern can be represented using an asymptotic expansion formula in the presence of such anomalies and random scatterers. We also present results of numerical simulations to validate the discovered imaging function structures. Full article

(This article belongs to the Section Electrical, Electronics and Communications Engineering)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Appl. Sci., Volume 9, Issue 20 (October-2 2019) – 278 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI