Next Issue
Previous Issue

Table of Contents

Appl. Sci., Volume 9, Issue 12 (June-2 2019)

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
Cover Story (view full-size image) While native aquatic plants are essential components of aquatic ecosystems, non-native invasive [...] Read more.
View options order results:
result details:
Displaying articles 1-188
Export citation of selected articles as:
Open AccessArticle
Assessment of Residual Elastic Properties of a Damaged Composite Plate with Combined Damage Index and Finite Element Methods
Appl. Sci. 2019, 9(12), 2579; https://doi.org/10.3390/app9122579
Received: 29 May 2019 / Revised: 20 June 2019 / Accepted: 21 June 2019 / Published: 25 June 2019
Viewed by 359 | PDF Full-text (5405 KB) | HTML Full-text | XML Full-text
Abstract
In structural component applications the use of composite materials is increasing thanks to their optimal mechanical characteristics. However, the complexity of the damage evolution in composite materials significantly limits their widespread diffusion. Non-destructive tests are thus becoming ever more important. The detecting Damage [...] Read more.
In structural component applications the use of composite materials is increasing thanks to their optimal mechanical characteristics. However, the complexity of the damage evolution in composite materials significantly limits their widespread diffusion. Non-destructive tests are thus becoming ever more important. The detecting Damage Index ( D I d ) technique has been recently brought in the realm of the non-destructive characterization tests for components made of composite material. In contrast to other techniques, this methodology allows to quantitatively assess local residual properties. In this paper, the D I d technique is adopted in combination with the finite element method. The mechanical response of two composite plates (an 8-layer twill fabric carbon/epoxy) subjected to four-point bending test is firstly used to tune a finite element model of the laminate. Then, an undamaged laminate of the same composite material is progressively damaged through repeated four-point bending tests. Local residual elastic properties are mapped on the plate through the D I d technique. A continuous polynomial curve has been considered to account for the variation of the elastic modulus in the finite element model. The resulting force-displacement curve of the numerical analysis is compared to experimental data of damaged plate, resulting in very good agreement. The combination of the experimental activity and the numerical finite element analysis points out the accuracy of the D I d methodology in assessing local residual elastic properties of composite materials. Full article
(This article belongs to the Special Issue Nondestructive Testing in Composite Materials)
Figures

Figure 1

Open AccessArticle
Evaluation of Sensitivity and Calibration of the Chaboche Kinematic Hardening Model Parameters for Numerical Ratcheting Simulation
Appl. Sci. 2019, 9(12), 2578; https://doi.org/10.3390/app9122578
Received: 11 April 2019 / Revised: 13 June 2019 / Accepted: 18 June 2019 / Published: 25 June 2019
Viewed by 306 | PDF Full-text (15452 KB) | HTML Full-text | XML Full-text
Abstract
Ratcheting failure of materials and structures subjected to low cycle fatigue in the presence of significant mean stress is of great interest to researchers. In this experimental and numerical study, the response of 316L stainless steel samples was observed in symmetric strain control [...] Read more.
Ratcheting failure of materials and structures subjected to low cycle fatigue in the presence of significant mean stress is of great interest to researchers. In this experimental and numerical study, the response of 316L stainless steel samples was observed in symmetric strain control uniaxial test followed by post-stabilized monotonic test, uniaxial and biaxial ratcheting tests, in order to determine the Chaboche model parameters and to evaluate ratcheting prediction using finite element analysis. The critical elastic limit was initially obtained from incremental uniaxial cyclic tests. The Chaboche parameters were subsequently extracted from experimental hysteresis and post-stabilized monotonic stress plastic-strain curves using two optimization technics, namely, the Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The two optimization methods were compared for efficiency, in terms of time and accuracy. The PSO method presented higher efficient results and was subsequently used to derive the parameters from hysteresis and post-stabilized monotonic curves. Different values (by definition) of elastic limit were also used. The Finite Element commercial software ANSYS was utilized with the Chaboche model to predict the uniaxial and biaxial ratcheting behavior of 316L stainless steel pipe. The comparison between experimental and the numerical simulation demonstrates that adopting post-stabilized monotonic curve rather than hysteresis curve and with accurate elastic limit obtained from incremental loading test improves ratcheting prediction significantly. Full article
(This article belongs to the Section Mechanical Engineering)
Figures

Graphical abstract

Open AccessReview
Clinical Applications of Optical Coherence Angiography Imaging in Ocular Vascular Diseases
Appl. Sci. 2019, 9(12), 2577; https://doi.org/10.3390/app9122577
Received: 14 May 2019 / Revised: 16 June 2019 / Accepted: 19 June 2019 / Published: 25 June 2019
Viewed by 290 | PDF Full-text (3481 KB) | HTML Full-text | XML Full-text
Abstract
Optical coherence tomography angiography (OCTA) provides us with a non-invasive and efficient means of imaging anterior and posterior segment vasculature in the eye. OCTA has been shown to be effective in imaging diseases such as diabetic retinopathy; retinal vein occlusions; retinal artery occlusions; [...] Read more.
Optical coherence tomography angiography (OCTA) provides us with a non-invasive and efficient means of imaging anterior and posterior segment vasculature in the eye. OCTA has been shown to be effective in imaging diseases such as diabetic retinopathy; retinal vein occlusions; retinal artery occlusions; ocular ischemic syndrome; and neovascularization of the iris. It is especially useful with depth-resolved imaging of the superficial, intermediate, and deep capillary plexi in the retina, which enables us to study and closely monitor disease progression and response to treatment. With further advances in technology, OCTA has the potential to become a more widely used tool in the clinical setting and may even supersede ocular angiography in some areas. Full article
(This article belongs to the Special Issue Optical Coherence Tomography and its Applications)
Figures

Graphical abstract

Open AccessArticle
Determination and Implementation of Reasonable Completion State for the Self-Anchored Suspension Bridge with Extra-Wide Concrete Girder
Appl. Sci. 2019, 9(12), 2576; https://doi.org/10.3390/app9122576
Received: 9 May 2019 / Revised: 18 June 2019 / Accepted: 21 June 2019 / Published: 25 June 2019
Viewed by 285 | PDF Full-text (5820 KB) | HTML Full-text | XML Full-text
Abstract
The present work is aimed at studying the determination method and implementation process of reasonable completion state for the Hunan Road Bridge, which is currently the widest concrete self-anchored suspension bridge in China. The global finite element model and the cable analytic program [...] Read more.
The present work is aimed at studying the determination method and implementation process of reasonable completion state for the Hunan Road Bridge, which is currently the widest concrete self-anchored suspension bridge in China. The global finite element model and the cable analytic program BNLAS were integrated. The synthesis algorithm of completion state determination was proposed. The contact relationships between the cable and saddles were captured using the refined FE discretization method. The concrete shrinkage and creep effects during the construction and operation periods were predicted using the CEB-FIP 90 model and the age-adjusted effective modulus method. The cable alignments under the free cable state, system transformation condition, and completion state were obtained. Moreover, the multiple-control method for the whole process of system transformation was proposed. The multiple parameters included the hanger tensioning force, exposed amount of hanger anchor cup, and tag line position. A detailed system transformation procedure was formulated and well preformed in the construction site. In addition, the further optimization analysis of final hanger force was conducted based on the actual completion state. The influence on the stress and geometry evolution of girder brought by the final girder alignment was investigated. The measured results of structural alignment and stress show that the target completion state was well implemented. The accuracy and efficiency of the proposed multiple-control method were verified by checking the tag line position of each step. In addition, the optimized final hanger force and girder lifting amount were obtained, which can provide feedback and reference for the construction control and service safety of the similar concrete self-anchored suspension bridges. Full article
Figures

Figure 1

Open AccessArticle
Predictive Speed-Control Algorithm Based on a Novel Extended-State Observer for PMSM Drives
Appl. Sci. 2019, 9(12), 2575; https://doi.org/10.3390/app9122575
Received: 28 April 2019 / Revised: 8 June 2019 / Accepted: 21 June 2019 / Published: 25 June 2019
Viewed by 252 | PDF Full-text (2725 KB) | HTML Full-text | XML Full-text
Abstract
To enhance the control performance of permanent-magnet synchronous motor (PMSM) drive systems, achieving high-precision motion control, a generalized predictive control (GPC) method based on a novel extended-state observer (ESO) is investigated for the speed control of PMSM. In this paper, the controller design [...] Read more.
To enhance the control performance of permanent-magnet synchronous motor (PMSM) drive systems, achieving high-precision motion control, a generalized predictive control (GPC) method based on a novel extended-state observer (ESO) is investigated for the speed control of PMSM. In this paper, the controller design consists of two steps. Firstly, according to the continuous time model of PMSM, using the Taylor series expansion, the predictive value of motor speed in finite time is derived, and the single-loop speed controller by combining the speed loop and q - axis current loop is obtained through the defined cost function. The structure of the controller is simple compared to other forms. Secondly, considering the uncertainty of the load torque and the model uncertainties, a novel extended-state observer is designed to compute the actual torque, and the observed value is introduced to the GPC controller. The simulation and experimental results show that the proposed GPC+ESO control method has superior dynamic performance and strong robustness. Full article
(This article belongs to the Section Electrical, Electronics and Communications Engineering)
Figures

Figure 1

Open AccessArticle
The Application of Adaptive Time Gain Compensation in an Improved Breast Ultrasound Tomography Algorithm
Appl. Sci. 2019, 9(12), 2574; https://doi.org/10.3390/app9122574
Received: 8 May 2019 / Revised: 19 June 2019 / Accepted: 20 June 2019 / Published: 25 June 2019
Viewed by 247 | PDF Full-text (7181 KB) | HTML Full-text | XML Full-text
Abstract
In order to better detect information about a mass in breast tissue, an ultrasound tomography algorithm based on adaptive time gain compensation (TGC) was designed. Field II was utilized to automatically evaluate the phantom attenuation coefficient and compensate for the attenuated image. The [...] Read more.
In order to better detect information about a mass in breast tissue, an ultrasound tomography algorithm based on adaptive time gain compensation (TGC) was designed. Field II was utilized to automatically evaluate the phantom attenuation coefficient and compensate for the attenuated image. The image reconstruction algorithm process is presented here. Furthermore, the experimental setup with the cylindrical motion of a piezoelectric micromachined ultrasonic transducer (PMUT) linear array was used to detect the mass in the breast model. The attenuation coefficient was evaluated by using the spectral cross-correlation method. According to the acquired attenuation coefficients, TGC compensates for the pulse-echo signal, and the horizontal slice image was reconstructed using the tomography algorithm. The experimental results show that this algorithm can evaluate the attenuation coefficient of the breast model and improve the ability to detect an internal mass. At the same time, the realization of attenuation compensation with software is beneficial to the development of portable medical equipment. Full article
(This article belongs to the Special Issue Ultrasound Technology for Clinical Diagnosis and Decisions Making)
Figures

Figure 1

Open AccessArticle
Compensating Uncertainties in Force Sensing for Robotic-Assisted Palpation
Appl. Sci. 2019, 9(12), 2573; https://doi.org/10.3390/app9122573
Received: 25 February 2019 / Revised: 13 May 2019 / Accepted: 17 May 2019 / Published: 25 June 2019
Viewed by 242 | PDF Full-text (1729 KB) | HTML Full-text | XML Full-text
Abstract
Force sensing in robotic-assisted minimally invasive surgery (RMIS) is crucial for performing dedicated surgical procedures, such as bilateral teleoperation and palpation. Due to the bio-compatibility and sterilization requirements, a specially designed surgical tool/shaft is normally attached to the sensor while contacting the organ [...] Read more.
Force sensing in robotic-assisted minimally invasive surgery (RMIS) is crucial for performing dedicated surgical procedures, such as bilateral teleoperation and palpation. Due to the bio-compatibility and sterilization requirements, a specially designed surgical tool/shaft is normally attached to the sensor while contacting the organ targets. Through this design, the measured force from the sensor usually contains uncertainties, such as noise, inertial force etc., and thus cannot reflect the actual interaction force with the tissue environment. Motivated to provide the authentic contact force between a robotic tool and soft tissue, we proposed a data-driven force compensation scheme without intricate modeling to reduce the effects of force measurement uncertainties. In this paper, a neural-network-based approach is utilized to automatically model the inertial force subject to noise during the robotic palpation procedure, then the exact contact force can be obtained through the force compensation method which cancels the noise and inertial force. Following this approach, the genuine interaction force during the palpation task can be achieved furthermore to improve the appraisal of the tumor surrounded by the soft tissue. Experiments are conducted with robotic-assisted palpation tasks on a silicone-based soft tissue phantom and the results verify the effectiveness of the suggested method. Full article
(This article belongs to the Special Issue Human Friendly Robotics)
Figures

Figure 1

Open AccessArticle
Analysis for the Vibration Mechanism of the Spillway Guide Wall Considering the Associated-Forced Coupled Vibration
Appl. Sci. 2019, 9(12), 2572; https://doi.org/10.3390/app9122572
Received: 16 March 2019 / Revised: 31 May 2019 / Accepted: 22 June 2019 / Published: 25 June 2019
Viewed by 245 | PDF Full-text (23238 KB) | HTML Full-text | XML Full-text
Abstract
During the flood discharge in large-scale hydraulic engineering projects, intense flow-induced vibrations may occur in hydraulic gates, gate piers, spillway guide walls, etc. Furthermore, the vibration mechanism is complicated. For the spillway guide wall, existing studies on the vibration mechanism usually focus on [...] Read more.
During the flood discharge in large-scale hydraulic engineering projects, intense flow-induced vibrations may occur in hydraulic gates, gate piers, spillway guide walls, etc. Furthermore, the vibration mechanism is complicated. For the spillway guide wall, existing studies on the vibration mechanism usually focus on the vibrations caused by flow excitations, without considering the influence of dam vibration. According to prototype tests, the vibrations of the spillway guide wall and the dam show synchronization. Thus, this paper presents a new vibration mechanism of associated-forced coupled vibration (AFCV) for the spillway guide wall to investigate the dynamic responses and reveal coupled vibrational properties and vibrational correlations. Different from conventional flow-induced vibration theory, this paper considers the spillway guide wall as a lightweight accessory structure connected to a large-scale primary structure. A corresponding simplified theoretical model for the AFCV system is established, with theoretical derivations given. Then, several vibrational signals measured in different structures in prototype tests are handled by the cross-wavelet transform (XWS) to reveal the vibrational correlation between the spillway guide wall and the dam. Afterwards, mutual analyses of numeral simulation, theoretical derivation, and prototype data are employed to clarify the vibration mechanism of a spillway guide wall. The proposed mechanism can give more reasonable and accurate results regarding the dynamic response and amplitude coefficient of the guide wall. Moreover, by changing the parameters in the theoretical model through practical measures, the proposed vibration mechanism can provide benefits to vibration control and structural design. Full article
(This article belongs to the Section Acoustics and Vibrations)
Figures

Figure 1

Open AccessFeature PaperReview
Review of Experimental Research on Supercritical and Transcritical Thermodynamic Cycles Designed for Heat Recovery Application
Appl. Sci. 2019, 9(12), 2571; https://doi.org/10.3390/app9122571
Received: 21 May 2019 / Revised: 14 June 2019 / Accepted: 17 June 2019 / Published: 25 June 2019
Viewed by 317 | PDF Full-text (1670 KB) | HTML Full-text | XML Full-text
Abstract
Supercritical operation is considered a main technique to achieve higher cycle efficiency in various thermodynamic systems. The present paper is a review of experimental investigations on supercritical operation considering both heat-to-upgraded heat and heat-to-power systems. Experimental works are reported and subsequently analyzed. Main [...] Read more.
Supercritical operation is considered a main technique to achieve higher cycle efficiency in various thermodynamic systems. The present paper is a review of experimental investigations on supercritical operation considering both heat-to-upgraded heat and heat-to-power systems. Experimental works are reported and subsequently analyzed. Main findings can be summarized as: steam Rankine cycles does not show much studies in the literature, transcritical organic Rankine cycles are intensely investigated and few plants are already online, carbon dioxide is considered as a promising fluid for closed Brayton and Rankine cycles but its unique properties call for a new thinking in designing cycle components. Transcritical heat pumps are extensively used in domestic and industrial applications, but supercritical heat pumps with a working fluid other than CO2 are scarce. To increase the adoption rate of supercritical thermodynamic systems further research is needed on the heat transfer behavior and the optimal design of compressors and expanders with special attention to the mechanical integrity. Full article
(This article belongs to the Special Issue Organic Rankine Cycle Systems for Waste-Heat Recovery)
Figures

Figure 1

Open AccessArticle
Sargassum muticum Hydrothermal Extract: Effects on Serum Parameters and Antioxidant Activity in Rats
Appl. Sci. 2019, 9(12), 2570; https://doi.org/10.3390/app9122570
Received: 31 March 2019 / Revised: 10 June 2019 / Accepted: 18 June 2019 / Published: 25 June 2019
Viewed by 236 | PDF Full-text (876 KB) | HTML Full-text | XML Full-text
Abstract
Sargassum muticum was processed by hydrothermal extraction under previously optimized non-isothermal conditions (up to 187 °C). The alginate free crude hydrolysate was further concentrated by ultrafiltration, operating in diafiltration mode to produce an extract (SmE) enriched in the fucoidan and the phlorotannin fractions [...] Read more.
Sargassum muticum was processed by hydrothermal extraction under previously optimized non-isothermal conditions (up to 187 °C). The alginate free crude hydrolysate was further concentrated by ultrafiltration, operating in diafiltration mode to produce an extract (SmE) enriched in the fucoidan and the phlorotannin fractions and with low mineral content and antiradical capacity equivalent to that of Trolox. In order to explore the potential of this concentrated product for food or feed additive, the in vivo antioxidant potential was assessed. Male Sprague–Dawley rats were fed SmE dissolved in distilled water at doses of 0.5, 1.0 or 2.0 g kg−1, administered via an intragastric tube daily for three weeks. The weight and organ gain was not significantly affected in the different groups in relation to the control group fed a standard diet. Serum glucose was significantly lowered in the groups receiving the higher SmE doses, liver GPx levels were reduced and liver TBARS levels decreased in rats administered the extract, but no effect on SOD activity in either liver or erythrocytes was observed. Full article
(This article belongs to the Special Issue Biomass Research and Applications)
Figures

Figure 1

Open AccessArticle
Thermo-Mechanical Investigations of Packed Beds for High Temperature Heat Storage: Continuum Modeling
Appl. Sci. 2019, 9(12), 2569; https://doi.org/10.3390/app9122569
Received: 27 May 2019 / Revised: 18 June 2019 / Accepted: 20 June 2019 / Published: 25 June 2019
Viewed by 211 | PDF Full-text (2099 KB) | HTML Full-text | XML Full-text
Abstract
Thermal energy storage (TES) systems are central elements for various types of new power plant concepts, whereat packed beds represent a promising storage inventory option. Due to thermal expansion and shrinking of the packed bed’s particles during cyclic thermal charging and discharging operation, [...] Read more.
Thermal energy storage (TES) systems are central elements for various types of new power plant concepts, whereat packed beds represent a promising storage inventory option. Due to thermal expansion and shrinking of the packed bed’s particles during cyclic thermal charging and discharging operation, high technical risks arise, and possibly lead to material failure. In order to accurately design the heat storage system, suitable tools for calculating induced forces and stresses are mandatory. Continuum models offer time efficient simulation results, but are in need of effective packed bed parameters. This paper introduces a methodology for applying a simplified continuum model and presents first results for an exemplarily large-scale application. Full article
(This article belongs to the Special Issue Thermal Energy Storage Systems)
Figures

Figure 1

Open AccessArticle
Corrosion Behavior and Conductivity of TiNb and TiNbN Coated Steel for Metallic Bipolar Plates
Appl. Sci. 2019, 9(12), 2568; https://doi.org/10.3390/app9122568
Received: 10 March 2019 / Revised: 23 May 2019 / Accepted: 30 May 2019 / Published: 24 June 2019
Viewed by 237 | PDF Full-text (3278 KB) | HTML Full-text | XML Full-text
Abstract
To improve corrosion resistance and electronic conductivity of bipolar plates for proton exchange membrane fuel cell (PEMFC), coatings of TiNb and TiNbN on 316L stainless steel (SS) were prepared by magnetron sputtering. X-ray diffraction (XRD) measurements confirmed the existence of metallic nitrides in [...] Read more.
To improve corrosion resistance and electronic conductivity of bipolar plates for proton exchange membrane fuel cell (PEMFC), coatings of TiNb and TiNbN on 316L stainless steel (SS) were prepared by magnetron sputtering. X-ray diffraction (XRD) measurements confirmed the existence of metallic nitrides in the TiNbN coating. Scanning electron microscope (SEM) tests showed that the deposited coatings provided smooth surfaces. Further electrochemical measurements indicated that the corrosion resistance of TiNb coating was significantly higher than that of substrate. At 0.19 V vs MSE, the long-term stabilized current density of TiNb/316L SS was lower than 1 μA·cm−2. The interfacial contact resistance (ICR) values between coating and carbon paper suggested that TiNb and TiNbN films had better contact conductivity than 316L SS substrate. In conclusion, TiNb coated 316L SS metallic bipolar plate material is a promising option for PEMFC. Full article
(This article belongs to the Special Issue Advances in Organic Corrosion Inhibitors and Protective Coatings)
Figures

Figure 1

Open AccessArticle
Light Harvesting and Optical-Electronic Properties of Two Quercitin and Rutin Natural Dyes
Appl. Sci. 2019, 9(12), 2567; https://doi.org/10.3390/app9122567
Received: 14 May 2019 / Revised: 9 June 2019 / Accepted: 17 June 2019 / Published: 24 June 2019
Viewed by 215 | PDF Full-text (3558 KB) | HTML Full-text | XML Full-text | Supplementary Files
Abstract
The photovoltaic properties of two dyes (quercitin (Q) and rutin (R)) were experimentally investigated. The results showed that Q had excellent photoelectric properties with Jsc of 5.480 mA·cm−2, Voc of 0.582 V, η of 2.151% larger than [...] Read more.
The photovoltaic properties of two dyes (quercitin (Q) and rutin (R)) were experimentally investigated. The results showed that Q had excellent photoelectric properties with J s c of 5.480 mA·cm−2, V o c of 0.582 V, η of 2.151% larger than R with J s c of 1.826 mA·cm−2, V o c of 0.547 V, and η of 0.713%. For a better understanding of the photoelectric properties of two molecules and illustrating why the performances of Q is better than R from the micro-level, the UV-VIs spectrum, Fourier transforms infrared (FT-IR) spectrum, and cyclic voltage current characteristics were experimentally investigated. What is more, density functional theory (DFT) and time dependent density functional theory (TD-DFT) have been implemented in theoretical calculation. Based on the calculated results, frontier molecular orbitals (FMOs), charge differential density (CDD), infrared vibration, first hyperpolarizability, projected density orbital analysis (PDOS), electrostatic potential (ESP), and natural bond orbital (NBO) were analyzed. Hole/electron reorganization energies ( λ h / λ e ), light harvesting efficiency (LHE), fluorescent lifetime (τ), absorption peak, and the vertical dipole moment ( μ n o r m a l ) were calculated, and the shift of conduction band edge of a semiconductor (ΔECB) has been analyzed, which has a close relationship with J s c and V o c . The results demonstrated that, due to the higher LHE, τ, μ n o r m a l , and red-shifted absorption peak, Q has better photoelectric properties than R as a promising sensitizer. Full article
(This article belongs to the Section Materials)
Figures

Figure 1

Open AccessArticle
Solving Nuisance Cyanobacteria Eutrophication Through Biotechnology
Appl. Sci. 2019, 9(12), 2566; https://doi.org/10.3390/app9122566
Received: 12 May 2019 / Revised: 16 June 2019 / Accepted: 20 June 2019 / Published: 24 June 2019
Viewed by 334 | PDF Full-text (1635 KB) | HTML Full-text | XML Full-text
Abstract
Management of nutrient inputs and usage of nuisance biomass as feedstock for bioenergy may be the solution of coastal lagoons eutrophication. We studied the species composition, photosynthetic pigments (Chl-a and Chl-c) and performance (OJIP-kinetics and JIP-test parameters), biochemistry (lipids and carbohydrates composition), and [...] Read more.
Management of nutrient inputs and usage of nuisance biomass as feedstock for bioenergy may be the solution of coastal lagoons eutrophication. We studied the species composition, photosynthetic pigments (Chl-a and Chl-c) and performance (OJIP-kinetics and JIP-test parameters), biochemistry (lipids and carbohydrates composition), and hydrogen production potential of Limnoraphis (Lyngbya) nuisance biomass collected from Lafri lagoon (1.24 km2) in Greece. The results showed that the removal of algal biomass from Lafri lagoon before its sedimentation, characterized by low Fν/Fm (0.42) and PItotal (2.67) values, and transfer of this in a simple, closed bioreactor, has the potential to produce hydrogen (H2), a renewable CO2-neutral energy that can directly be converted into electricity. The free carbohydrates of the lagoon water and that from the algal cells (42g glucose analogs per m3) could be also transferred to alcohols (biofuels), while the rest of the biomass could be used as organic fertilizer. The total lipid content (2.51%) of dry biomass composed primarily by palmitic acid was low. However, the presence of eicosapentaenoic (3.5%), and docosahexaenoic (1.7%), polyunsaturated fatty acids is worth mentioning. By harvesting and conversion of this coastal lagoon nuisance algal biomass to energy or other products, one could improve its water quality and, therefore, biodiversity and fish production; that is a sustainable solution of eutrophication necessary for the ongoing climatic change. Full article
(This article belongs to the Special Issue New Trends on Algal Biotechnology for a Circular Economy)
Figures

Graphical abstract

Open AccessReview
Ten Years of Gabor-Domain Optical Coherence Microscopy
Appl. Sci. 2019, 9(12), 2565; https://doi.org/10.3390/app9122565
Received: 17 April 2019 / Revised: 18 June 2019 / Accepted: 19 June 2019 / Published: 24 June 2019
Viewed by 286 | PDF Full-text (3509 KB) | HTML Full-text | XML Full-text
Abstract
Gabor-domain optical coherence microscopy (GDOCM) is a high-definition imaging technique leveraging principles of low-coherence interferometry, liquid lens technology, high-speed imaging, and precision scanning. GDOCM achieves isotropic 2 μm resolution in 3D, effectively breaking the cellular resolution limit of optical coherence tomography (OCT). In [...] Read more.
Gabor-domain optical coherence microscopy (GDOCM) is a high-definition imaging technique leveraging principles of low-coherence interferometry, liquid lens technology, high-speed imaging, and precision scanning. GDOCM achieves isotropic 2 μm resolution in 3D, effectively breaking the cellular resolution limit of optical coherence tomography (OCT). In the ten years since its introduction, GDOCM has been used for cellular imaging in 3D in a number of clinical applications, including dermatology, oncology and ophthalmology, as well as to characterize materials in industrial applications. Future developments will enhance the structural imaging capability of GDOCM by adding functional modalities, such as fluorescence and elastography, by estimating thicknesses on the nano-scale, and by incorporating machine learning techniques. Full article
(This article belongs to the Special Issue Optical Coherence Tomography and its Applications)
Figures

Figure 1

Open AccessArticle
Indium Tin Oxide Nanoparticle: TiO2: Air Layers for One-Dimensional Multilayer Photonic Structures
Appl. Sci. 2019, 9(12), 2564; https://doi.org/10.3390/app9122564
Received: 17 May 2019 / Revised: 19 June 2019 / Accepted: 20 June 2019 / Published: 24 June 2019
Viewed by 277 | PDF Full-text (2458 KB) | HTML Full-text | XML Full-text
Abstract
In this work we study the optical properties of one-dimensional photonic crystals in which layers of silica nanoparticles are alternated with layers of indium tin oxide nanoparticle (ITO)/titania nanoparticle mixture, using the transfer matrix method. The dielectric function of the mixed ITO/TiO2 [...] Read more.
In this work we study the optical properties of one-dimensional photonic crystals in which layers of silica nanoparticles are alternated with layers of indium tin oxide nanoparticle (ITO)/titania nanoparticle mixture, using the transfer matrix method. The dielectric function of the mixed ITO/TiO2 nanoparticle layer is carefully accounted for with a generalized Rayleigh equation for the ternary mixture ITO:TiO2:air. We studied the light transmission of the multilayer photonic crystal as a function of the ITO/TiO2 ratio. We observe that, by increasing the ITO content and its carrier density in the three-phase mixture, the intensity of the plasmon resonance in the near infrared (NIR) increases and the intensity of the photonic band gap (visible) decreases. Thus, our study is of major importance for the realization of electrochromic smart windows, in which separate and independent NIR and visible light control is required. Full article
(This article belongs to the Section Optics and Lasers)
Figures

Figure 1

Open AccessEditorial
Special Issue: 3D Printing of Metals
Appl. Sci. 2019, 9(12), 2563; https://doi.org/10.3390/app9122563
Received: 6 June 2019 / Accepted: 11 June 2019 / Published: 24 June 2019
Viewed by 346 | PDF Full-text (144 KB) | HTML Full-text | XML Full-text
Abstract
Additive manufacturing (AM) has emerged as one of the most enabling new manufacturing technique; the topic has been extensively researched worldwide for almost two decades [...] Full article
(This article belongs to the Special Issue 3D Printing of Metals)
Open AccessArticle
Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model
Appl. Sci. 2019, 9(12), 2562; https://doi.org/10.3390/app9122562
Received: 26 May 2019 / Revised: 19 June 2019 / Accepted: 19 June 2019 / Published: 23 June 2019
Cited by 2 | Viewed by 491 | PDF Full-text (11490 KB) | HTML Full-text | XML Full-text
Abstract
There is a large amount of useful information from past experimental tests, which are usually ignored in test-setup for the new ones. Variation of assumptions, materials, test procedures, and test objectives make it difficult to choose the right model for validation of the [...] Read more.
There is a large amount of useful information from past experimental tests, which are usually ignored in test-setup for the new ones. Variation of assumptions, materials, test procedures, and test objectives make it difficult to choose the right model for validation of the numerical models. Results from different experiments are sometimes in conflict with each other, or have minimum correlation. Furthermore, not all these information are easily accessible for researchers and engineers. Therefore, this paper presents the results of a comprehensive study on different experimental models for steel plate and reinforced concrete shear walls. A unique library of up to 13 parameters (mechanical properties and geometric characteristics) affecting the strength, stiffness and drift ratio of the shear walls are gathered including their sensitivity analysis. Next, a predictive meta-model is developed based on artificial neural network. It is capable of forecasting the responses for any desired shear wall with good accuracy. The proposed network can be used to as an alternative to the nonlinear numerical simulations or expensive experimental test. Full article
(This article belongs to the Special Issue Soft Computing Techniques in Structural Engineering and Materials)
Figures

Graphical abstract

Open AccessArticle
Energy Enhancement and Energy Spread Compression of Electron Beams in a Hybrid Laser-Plasma Wakefield Accelerator
Appl. Sci. 2019, 9(12), 2561; https://doi.org/10.3390/app9122561
Received: 12 April 2019 / Revised: 24 May 2019 / Accepted: 19 June 2019 / Published: 23 June 2019
Viewed by 353 | PDF Full-text (1757 KB) | HTML Full-text | XML Full-text
Abstract
We experimentally demonstrated the generation of narrow energy-spread electron beams with enhanced energy levels using a hybrid laser-plasma wakefield accelerator. An experiment featuring two-color electron beams showed that after the laser pump reached the depletion length, the laser-wakefield acceleration (LWFA) gradually evolved into [...] Read more.
We experimentally demonstrated the generation of narrow energy-spread electron beams with enhanced energy levels using a hybrid laser-plasma wakefield accelerator. An experiment featuring two-color electron beams showed that after the laser pump reached the depletion length, the laser-wakefield acceleration (LWFA) gradually evolved into the plasma-driven wakefield acceleration (PWFA), and thereafter, the PWFA dominated the electron acceleration. The energy spread of the electron beams was further improved by energy chirp compensation. Particle-in-cell simulations were performed to verify the experimental results. The generated monoenergetic high-energy electron beams are promising to upscale future accelerator systems and realize monoenergetic γ -ray sources. Full article
(This article belongs to the Section Optics and Lasers)
Figures

Figure 1

Open AccessArticle
EDCrammer: An Efficient Caching Rate-Control Algorithm for Streaming Data on Resource-Limited Edge Nodes
Appl. Sci. 2019, 9(12), 2560; https://doi.org/10.3390/app9122560
Received: 3 May 2019 / Revised: 14 June 2019 / Accepted: 20 June 2019 / Published: 23 June 2019
Viewed by 299 | PDF Full-text (2218 KB) | HTML Full-text | XML Full-text
Abstract
This paper explores data caching as a key factor of edge computing. State-of-the-art research of data caching on edge nodes mainly considers reactive and proactive caching, and machine learning based caching, which could be a heavy task for edge nodes. However, edge nodes [...] Read more.
This paper explores data caching as a key factor of edge computing. State-of-the-art research of data caching on edge nodes mainly considers reactive and proactive caching, and machine learning based caching, which could be a heavy task for edge nodes. However, edge nodes usually have relatively lower computing resources than cloud datacenters as those are geo-distributed from the administrator. Therefore, a caching algorithm should be lightweight for saving computing resources on edge nodes. In addition, the data caching should be agile because it has to support high-quality services on edge nodes. Accordingly, this paper proposes a lightweight, agile caching algorithm, EDCrammer (Efficient Data Crammer), which performs agile operations to control caching rate for streaming data by using the enhanced PID (Proportional-Integral-Differential) controller. Experimental results using this lightweight, agile caching algorithm show its significant value in each scenario. In four common scenarios, the desired cache utilization was reached in 1.1 s on average and then maintained within a 4–7% deviation. The cache hit ratio is about 96%, and the optimal cache capacity is around 1.5 MB. Thus, EDCrammer can help distribute the streaming data traffic to the edge nodes, mitigate the uplink load on the central cloud, and ultimately provide users with high-quality video services. We also hope that EDCrammer can improve overall service quality in 5G environment, Augmented Reality/Virtual Reality (AR/VR), Intelligent Transportation System (ITS), Internet of Things (IoT), etc. Full article
(This article belongs to the Special Issue Edge Computing Applications in IoT)
Figures

Figure 1

Open AccessArticle
Efficient Weights Quantization of Convolutional Neural Networks Using Kernel Density Estimation based Non-uniform Quantizer
Appl. Sci. 2019, 9(12), 2559; https://doi.org/10.3390/app9122559
Received: 30 April 2019 / Revised: 8 June 2019 / Accepted: 20 June 2019 / Published: 23 June 2019
Viewed by 322 | PDF Full-text (1675 KB) | HTML Full-text | XML Full-text
Abstract
Convolutional neural networks (CNN) have achieved excellent results in the field of image recognition that classifies objects in images. A typical CNN consists of a deep architecture that uses a large number of weights and layers to achieve high performance. CNN requires relatively [...] Read more.
Convolutional neural networks (CNN) have achieved excellent results in the field of image recognition that classifies objects in images. A typical CNN consists of a deep architecture that uses a large number of weights and layers to achieve high performance. CNN requires relatively large memory space and computational costs, which not only increase the time to train the model but also limit the real-time application of the trained model. For this reason, various neural network compression methodologies have been studied to efficiently use CNN in small embedded hardware such as mobile and edge devices. In this paper, we propose a kernel density estimation based non-uniform quantization methodology that can perform compression efficiently. The proposed method performs efficient weights quantization using a significantly smaller number of sampled weights than the number of original weights. Four-bit quantization experiments on the classification of the ImageNet dataset with various CNN architectures show that the proposed methodology can perform weights quantization efficiently in terms of computational costs without significant reduction in model performance. Full article
(This article belongs to the Special Issue Advances in Deep Learning)
Figures

Figure 1

Open AccessArticle
Analysis of Operations upon Entry into Intermodal Freight Terminals
Appl. Sci. 2019, 9(12), 2558; https://doi.org/10.3390/app9122558
Received: 24 May 2019 / Revised: 19 June 2019 / Accepted: 21 June 2019 / Published: 23 June 2019
Viewed by 310 | PDF Full-text (2337 KB) | HTML Full-text | XML Full-text
Abstract
The design of intermodal freight terminals requires extensive research and a thorough analysis of the technical, financial and organizational aspects. In the paper, the operation of the reposition of large cargo containers (one of the types of intermodal transport units, ITUs) on the [...] Read more.
The design of intermodal freight terminals requires extensive research and a thorough analysis of the technical, financial and organizational aspects. In the paper, the operation of the reposition of large cargo containers (one of the types of intermodal transport units, ITUs) on the dedicated places is subjected to a discussion. The analysis is carried out with the use of a vehicle equipped with a telescopic arm, such as a reach stacker. The considered storage facility is reduced to a block characterized by spatial accumulation given in the paper. The description of the procedure for the execution of the handling operation from the arrival of a tractor-trailer with a container into a terminal, followed by the ITUs being set aside in a dedicated place and, in the end, the departure of the truck without load, is given in the paper. The activities are described in detail in order to present a descriptive model of particular operations upon entry to the intermodal freight terminal. Moreover, the paper contains relevant figures illustrating the various steps of realization and the analysis of duration of activities supported by actual realizations. The durations of the individual activities described in the paper are experimental, and the results have been validated on real-world intermodal freight terminals. Therefore, the authors believe that the obtained values may be used in analytical, simulation and numerical models of intermodal freight terminals. Full article
(This article belongs to the Section Civil Engineering)
Figures

Figure 1

Open AccessArticle
Research on the Modeling, Control, and Calibration Technology of a Tracked Vehicle Load Simulation Test Bench
Appl. Sci. 2019, 9(12), 2557; https://doi.org/10.3390/app9122557
Received: 27 May 2019 / Revised: 17 June 2019 / Accepted: 20 June 2019 / Published: 22 June 2019
Viewed by 330 | PDF Full-text (14377 KB) | HTML Full-text | XML Full-text
Abstract
The load simulation test bench plays an important role in tracked vehicle development. The stability and accuracy of the system have a vital impact on the experimental results. To accurately reproduce the power performance of a tracked vehicle on the test platform, this [...] Read more.
The load simulation test bench plays an important role in tracked vehicle development. The stability and accuracy of the system have a vital impact on the experimental results. To accurately reproduce the power performance of a tracked vehicle on the test platform, this paper aims to investigate the model, control, and calibration method of the test bench. Firstly, the dynamic model of a tracked vehicle under complex driving conditions is analyzed and established, which takes driving torque as the input and driving wheel speed as the output. Then, considering the uncertainties and disturbances in the system model, a 2-degree-of-freedom (2-DOF) control method combined with a disturbance observer is proposed to solve the stability problem of the system. Furthermore, in order to investigate the accuracy of the simulation on the test bed, a method of calibrating the system by a flywheel set with standard inertia is proposed. In the calibration process, the influence of the system resistance torque and the original mechanical inertia on the results is considered, and the response time of the inertia simulation is analyzed in both a steady and dynamic state. Finally, the load simulation test is carried out with the corrected system. The test results show that the system has a high load simulation accuracy under various load simulation tests. Full article
(This article belongs to the Special Issue Experimental Mechanics, Instrumentation and Metrology)
Figures

Figure 1

Open AccessArticle
Concrete–Concrete Bond in Mode-I: A study on the Synergistic Effect of Surface Roughness and Fiber Reinforcement
Appl. Sci. 2019, 9(12), 2556; https://doi.org/10.3390/app9122556
Received: 17 April 2019 / Revised: 7 June 2019 / Accepted: 18 June 2019 / Published: 22 June 2019
Viewed by 312 | PDF Full-text (6462 KB) | HTML Full-text | XML Full-text
Abstract
Effectiveness and durability of interventions on deficient concrete structures remain a major concern, comprising the challenge of old-to-new concrete compatibility and bonding, as stress concentrations and microstructural flaws at the old-to-new concrete interface compromise structural integrity and create migration paths for harmful contaminants. [...] Read more.
Effectiveness and durability of interventions on deficient concrete structures remain a major concern, comprising the challenge of old-to-new concrete compatibility and bonding, as stress concentrations and microstructural flaws at the old-to-new concrete interface compromise structural integrity and create migration paths for harmful contaminants. Fiber reinforcement can be beneficial, but proper quantification and mastering of fundamental mechanisms is required before these are fully utilized. A study is presented on Mode-I crack growth resistance at the interface between two concretes (substrate and repair). Countered Double Cantilever Beam tests are performed, crack growth resistance curves calculated (Modified Linear Elastic Fracture Mechanics), and complemented with analysis of interfacial roughness and failure planes. Polyvinyl alcohol (8 and 12 mm length) and steel fibers (13 mm) are introduced in the repairs at 0.5% and 1% volume fractions. Results indicate that fibers improve fracture behavior of both the repair material and substrate-repair interface; correlations with interfacial roughness, crack deviation, and fracture parameters are discussed. Full article
(This article belongs to the Special Issue Fiber-Reinforced Concrete)
Figures

Figure 1

Open AccessArticle
A Method to Detect Type 1 Diabetes Based on Physical Activity Measurements Using a Mobile Device
Appl. Sci. 2019, 9(12), 2555; https://doi.org/10.3390/app9122555
Received: 28 May 2019 / Revised: 17 June 2019 / Accepted: 19 June 2019 / Published: 22 June 2019
Viewed by 1381 | PDF Full-text (800 KB) | HTML Full-text | XML Full-text
Abstract
Type 1 diabetes is a chronic disease marked by high blood glucose levels, called hyperglycemia. Diagnosis of diabetes typically requires one or more blood tests. The aim of this paper is to discuss a non-invasive method of type 1 diabetes detection, based on [...] Read more.
Type 1 diabetes is a chronic disease marked by high blood glucose levels, called hyperglycemia. Diagnosis of diabetes typically requires one or more blood tests. The aim of this paper is to discuss a non-invasive method of type 1 diabetes detection, based on physical activity measurement. We solved a binary classification problem using a variety of computational intelligence methods, including non-linear classification algorithms, which were applied and comparatively assessed. Prediction of disease presence among children and adolescents was evaluated using performance measures, such as accuracy, sensitivity, specificity, precision, the goodness index, and AUC. The most satisfying results were obtained when using the random forest method. The primary parameters in disease detection were weekly step count and the weekly number of vigorous activity minutes. The dependance between the weekly number of steps and the type 1 diabetes presence was established after an insightful analysis of data using classification and clustering algorithms. The findings have shown promising results that type 1 diabetes can be diagnosed using physical activity measurement. This is essential regarding the non-invasiveness and flexibility of the detection method, which can be tested at any time anywhere. The proposed technique can be implemented on a mobile device. Full article
(This article belongs to the Special Issue Machine Learning for Biomedical Data Analysis)
Figures

Figure 1

Open AccessArticle
Digital Shearing Speckle Pattern Interferometry Based on Rochon Prism and Its Application
Appl. Sci. 2019, 9(12), 2554; https://doi.org/10.3390/app9122554
Received: 20 May 2019 / Revised: 6 June 2019 / Accepted: 20 June 2019 / Published: 22 June 2019
Viewed by 257 | PDF Full-text (4119 KB) | HTML Full-text | XML Full-text
Abstract
This paper presents improved digital shearing speckle pattern interferometry based on Rochon Prism. The advantage of this method is that it avoids the shadow noise caused by transmission light, which improves the shearography accuracy. By reducing the angle of divergence and coordinating the [...] Read more.
This paper presents improved digital shearing speckle pattern interferometry based on Rochon Prism. The advantage of this method is that it avoids the shadow noise caused by transmission light, which improves the shearography accuracy. By reducing the angle of divergence and coordinating the measuring distance and the precision coordinate, the beam-splitting path of the interference optical path is improved. Experimental results prove that the improved method contributes to the practical and instrumental application of shearography. Full article
(This article belongs to the Section Mechanical Engineering)
Figures

Figure 1

Open AccessArticle
OntoIMM: An Ontology for Product Intelligent Master Model
Appl. Sci. 2019, 9(12), 2553; https://doi.org/10.3390/app9122553
Received: 30 May 2019 / Revised: 18 June 2019 / Accepted: 19 June 2019 / Published: 22 June 2019
Viewed by 1185 | PDF Full-text (3268 KB) | HTML Full-text | XML Full-text
Abstract
Information organizing principle is one of the key issues of intelligent master model (IMM), which is an enhancement of the master model (MM) based on KBE (knowledge-based engineering). Despite the fact that the core product model (CPM) has been confirmed to be an [...] Read more.
Information organizing principle is one of the key issues of intelligent master model (IMM), which is an enhancement of the master model (MM) based on KBE (knowledge-based engineering). Despite the fact that the core product model (CPM) has been confirmed to be an organizing mechanism for product master model, the key issue of supporting the information organizing for IMM is not yet well addressed, mainly due to the following two reasons; (1) lack of representation of complete information and knowledge with regard to product and process, including the know-why, know-how, and know-what information and knowledge, and (2) lack of semantic richness. Therefore, a multiaspect extension to CPM was first defined, and then an ontology was constructed to represent the information and design knowledge. The extension refers to adding a design process model, context model, product control structure model, and design rationale model to CPM concerning the enhancement of master model, which is to comprehensively represent the reason, process, and result information and knowledge of the product. The ontology construction refers to representing the concepts, relationships among these concepts and consistency rules of IMM information structure. Finally, an example of barrel design and analysis process is illustrated to verify the effectiveness of proposed method. Full article
(This article belongs to the Section Applied Industrial Technologies)
Figures

Figure 1

Open AccessFeature PaperArticle
Pistacia Atlantica Desf., a Source of Healthy Vegetable Oil
Appl. Sci. 2019, 9(12), 2552; https://doi.org/10.3390/app9122552
Received: 27 May 2019 / Revised: 18 June 2019 / Accepted: 20 June 2019 / Published: 21 June 2019
Viewed by 376 | PDF Full-text (691 KB) | HTML Full-text | XML Full-text
Abstract
Pistacia atlantica, which belongs to the Anacardiaceae family, is an important species for rural people in arid and semi-arid areas. The fruit, rich in oil, is used in traditional medicine for the treatment of various diseases. The oil extracted from this species [...] Read more.
Pistacia atlantica, which belongs to the Anacardiaceae family, is an important species for rural people in arid and semi-arid areas. The fruit, rich in oil, is used in traditional medicine for the treatment of various diseases. The oil extracted from this species growing in a northern area of Algeria and its fatty acid composition were previously studied. However, the largest areas where this species is present (traditional cultivation) is located in southern Algeria. Moreover, studies on oil fatty acid composition and essential oil were always conducted separately. This study was performed in order to assess the fatty acid and volatile organic compound composition of P. atlantica vegetable oil. The seeds were collected randomly from Djelfa (300 km South of Algiers, Algeria). Oil content and fatty acid composition were determined by Soxhlet extraction. The seeds contained high concentrations of oil (32–67%). The major fatty acids were oleic (39–49%), linoleic (23.6–31%), and palmitic (21.3–26.6%) acids. The ratio of polyunsaturated fatty acids (PUFA) to saturated fatty acids (SFA) indicated that the content of unsaturated fatty acids was approximately three times higher than that of SFA. This ratio is widely used in epidemiological studies and research on cardiovascular diseases, diabetes, and metabolic syndrome. The ratios of ω-acids, i.e., ω-9/ω-6 and ω-6/ω-3, were 1.3–2 and 18.5–38.3, respectively. Crushed seeds were analyzed by headspace solid-phase microextraction (SPME) coupled with gas chromatography–mass spectrometry. More than 40 compounds were identified, mainly monoterpenes (C10H16), such as α-terpinene and terpinolene, but also sesquiterpenes (C15H24) at lower levels. The value of this species as a source of healthy oil rich in ω-3 acid and its effects on cardiovascular disease risk are discussed. Full article
(This article belongs to the Special Issue Bioactive Substances: Properties, Applications and or Toxicities)
Figures

Graphical abstract

Open AccessArticle
Improving Generative and Discriminative Modelling Performance by Implementing Learning Constraints in Encapsulated Variational Autoencoders
Appl. Sci. 2019, 9(12), 2551; https://doi.org/10.3390/app9122551
Received: 17 April 2019 / Revised: 16 June 2019 / Accepted: 19 June 2019 / Published: 21 June 2019
Viewed by 1182 | PDF Full-text (1751 KB) | HTML Full-text | XML Full-text
Abstract
Learning latent representations of observed data that can favour both discriminative and generative tasks remains a challenging task in artificial-intelligence (AI) research. Previous attempts that ranged from the convex binding of discriminative and generative models to the semisupervised learning paradigm could hardly yield [...] Read more.
Learning latent representations of observed data that can favour both discriminative and generative tasks remains a challenging task in artificial-intelligence (AI) research. Previous attempts that ranged from the convex binding of discriminative and generative models to the semisupervised learning paradigm could hardly yield optimal performance on both generative and discriminative tasks. To this end, in this research, we harness the power of two neuroscience-inspired learning constraints, that is, dependence minimisation and regularisation constraints, to improve generative and discriminative modelling performance of a deep generative model. To demonstrate the usage of these learning constraints, we introduce a novel deep generative model: encapsulated variational autoencoders (EVAEs) to stack two different variational autoencoders together with their learning algorithm. Using the MNIST digits dataset as a demonstration, the generative modelling performance of EVAEs was improved with the imposed dependence-minimisation constraint, encouraging our derived deep generative model to produce various patterns of MNIST-like digits. Using CIFAR-10(4K) as an example, a semisupervised EVAE with an imposed regularisation learning constraint was able to achieve competitive discriminative performance on the classification benchmark, even in the face of state-of-the-art semisupervised learning approaches. Full article
(This article belongs to the Special Issue Advances in Deep Learning)
Figures

Figure 1

Open AccessArticle
Payload-Based Traffic Classification Using Multi-Layer LSTM in Software Defined Networks
Appl. Sci. 2019, 9(12), 2550; https://doi.org/10.3390/app9122550
Received: 8 May 2019 / Revised: 11 June 2019 / Accepted: 19 June 2019 / Published: 21 June 2019
Viewed by 382 | PDF Full-text (2479 KB) | HTML Full-text | XML Full-text
Abstract
Recently, with the advent of various Internet of Things (IoT) applications, a massive amount of network traffic is being generated. A network operator must provide different quality of service, according to the service provided by each application. Toward this end, many studies have [...] Read more.
Recently, with the advent of various Internet of Things (IoT) applications, a massive amount of network traffic is being generated. A network operator must provide different quality of service, according to the service provided by each application. Toward this end, many studies have investigated how to classify various types of application network traffic accurately. Especially, since many applications use temporary or dynamic IP or Port numbers in the IoT environment, only payload-based network traffic classification technology is more suitable than the classification using the packet header information as well as payload. Furthermore, to automatically respond to various applications, it is necessary to classify traffic using deep learning without the network operator intervention. In this study, we propose a traffic classification scheme using a deep learning model in software defined networks. We generate flow-based payload datasets through our own network traffic pre-processing, and train two deep learning models: 1) the multi-layer long short-term memory (LSTM) model and 2) the combination of convolutional neural network and single-layer LSTM models, to perform network traffic classification. We also execute a model tuning procedure to find the optimal hyper-parameters of the two deep learning models. Lastly, we analyze the network traffic classification performance on the basis of the F1-score for the two deep learning models, and show the superiority of the multi-layer LSTM model for network packet classification. Full article
Figures

Figure 1

Appl. Sci. EISSN 2076-3417 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top