Table of contents

We welcome you to the 2020 International Symposium on Automation, Mechanical and Design Engineering (SAMDE 2020), SAMDE 2020 covers a wide range of research topics, spanning both theory and practice, and both systems and the interacting and interrelated entities that form these systems. A primary objective of SAMDE 2020 is to promote multi-/interdisciplinary international research and academic, technological and industrial collaboration. Dissemination of results, discussions and collaboration in an international environment promote both personal development and scientific progress.

Due to the virulent pandemic COVID-19, SAMDE 2020 was scheduled to be held on 26-28 December as virtual event.

SAMDE 2020 is a young conference for scholars and researchers in the field of Automation, Mechanical and Design Engineering. The conference gathered great efforts of many people, we wish to express our appreciation to the members of Advisory Committee and program committee, especially thanks to paper reviewers for their hard work in reviewing submitted papers. We extend our gratitude to the three keynote speakers Prof. Francesco Bullo(University of California, Santa Barbara), Prof. Ramesh K. Agarwal (Washington University in St. Louis) and Prof. Leonid Fridman(Universidad Nacional Autonoma de Mé xico) who will share their insights with us. Finally, Our gratitude goes all authors who has contributed a paper to our conference, the conference will not be possible without their contribution.

We hope the conference will further encourage research in the common fields, and provide practitioners with better techniques. We wish you enjoy and gain something through this inspiring program.

SAMDE 2020 Organizing Committee

List of Conference Chair, Program Committee, Technical Committee are available in this pdf.

All papers published in this volume of Journal of Physics: Conference Series have been peer reviewed through processes administered by the Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.

• Type of peer review: Double-blind

• Conference submission management system: CMT Submission system

• Number of submissions received: 91

• Number of submissions sent for review: 72

• Number of submissions accepted: 43

• Acceptance Rate (Number of Submissions Accepted / Number of Submissions Received X 100): 47.2%

• Average number of reviews per paper: 2

• Total number of reviewers involved: 27

• Any additional info on review process: All submitted papers went through two process, first process is preliminary evaluation, the unqualified abstracts will be rejected directly, second process is double-blind peer review, each paper will be sent to two reviewers for evaluation.

• Contact person for queries: Anna H. M. Wong (The Hong Kong Society of Robotics and Automation) 12 FLOOR, SAN TOI BUILDING, 139 CONNAUGHT ROAD CENTRAL, HONG KONG editor@hksra.org

In order to study the aging property of nano-modified asphalt, the values of nano-modified asphalt like softening point, penetration, ductility and viscosity etc. before and after the aging test were measured by controlling the content and types of nanomaterial, and then the relevant aging property indexes were calculated, the aging property optimum of the modified asphalt was determined by scientific methods of mathematical statistics and analysis. The testing results show that nanomaterial can effectively improve the high-temperature stability, low-temperature crack resistance and viscoelasticity of nano-modified asphalt. The content and type of nanomaterial have a great influence on the aging property of modified asphalt, the anti-aging performance of nano-modified asphalt with 0.5% titanium dioxide content is better.

Timeous prevention of, and recovery from, downtimes due to in-service failure of crucial power plant components, like turbine blades, portends huge consequences in the form of operational and financial viability concerns. Intensive research and development in manufacturing, re-manufacturing and condition-based maintenance of these components have birthed a novel technique, which deploys high intensity lasers to induce compressive residual stresses to the surface of the blades. This paper presents the application of an alternate computational modelling technique in simulating this surface treatment technique on X12Cr steel, an exotic steam turbine blades material, while also investigating the economic parameters of the induced residual stresses. A numerical model is developed in this work using the commercial finite elements software ABAQUS©. The results show this computational modelling technique as being time efficient. The parametric outcomes of the simulation agreed with experimental results, lending credence to its validity. Induced compressive stresses as high as 700 MPa and depths close to 1 mm from the surface of the blade were obtained. This by indication can prospectively quell crack initiation, growth and unplanned failure of the blade while in service, with the introduced simulation technique offering a solution for timely, non-destructive mechanical integrity enhancement of engineered components.

System modelling of the surface ship, which could be regarded as a multi-variable parameter estimation problem, has attracted tremendous interests from researchers since it is of key importance to development of ships' control system. The aim of this study is to utilize the Particle Swarm Optimization (PSO) algorithm to get the optimized solution of hydrodynamic coefficients in the presence of ship's mathematical model using the space search principle. The motion equations of the ship in four degrees of freedom are formulated to clarify the scheme of the model. After expressing the theory of the PSO method, the system identification of the ship's motions is conducted to estimate the hydrodynamic coefficients. By using the identified parameters, the mathematical motion model of the free-running ship, namely 'P and O Nedlloyd Hoorn', is developed. The comparison between the experiment measurements and simulation trails and attitudes have indicated that the developed mathematical is sufficient and effective to response the ship's motions. Therefore, it is demonstrated that the PSO based system identification algorithm is capable of conducting system identification and system modelling for the surface ship through free running approach.

The rapid development of big data and artificial intelligence technology is inseparable from the acquisition of massive basic data, and the data is acquired by sensors. The Raman Distributed optical fiber Temperature Sensor (RDTS) is a kind of sensor with many advantages, such as: anti-electromagnetic interference, intrinsic safety, small size, water and high temperature resistance. It has been applied in many fields for fast and continuous temperaturemeasurement. However, due to the rapid attenuation of transmitted light and the temperature error in radiated environment, it has not been applied innuclear field. Therefore, in order to improve the temperature accuracy of RDTS in radiated environment and provide basic data for advanced control. This paper studies the radiation effect on RDTS. Analyzesthe radiation damage mechanism and radiation damage influencing factors of RDTS. Proposes measures to improve the anti-radiation performance and provides four useful calibration methodsfortemperature error. Among them, two calibration methods have been proved right by experiments.

In order to solve the control difficulties such as large dynamic delay, serious coupling between machine and furnace and strong nonlinear, the feedforward and feedback predictive control is proposed to control the coordinated system on the basis of multi-model predictive control, and the static feedforward part designs the feed line feedforward of coal quantity against coal quality disturbance on the basis of the accurate balance of energy. Thus, the reference total fuel quantity under the target load instruction is determined, and the dynamic part fully considers the dynamic compensation of the unit energy storage, gives a certain overshoot fuel quantity to the boiler regulation, speeds up its response, and ensures the rapidity of the unit. The real-time simulation results of virtual DPU (Distributed Processing Unit) show that the designed feedforward-feedback predictive control can quickly respond to load change, improve the resistance to fuel disturbance, reduce the fluctuation of main steam pressure, and better ensure the safe, economic and stable operation of the coordination system.

Mirror milling is an effective and environmentally friendly means to manufacture large thin-walled parts. The remaining wall thickness of such parts is supposed to be strictly controlled to balance strength and weight reduction. However, the clamping deformation will lead to overcut or undercut if the nominal tool path is directly utilized. To address this issue, it would be helpful to scan and reconstruct the deformed unknown workpiece surface and then adjust the nominal tool path. In this paper, an automatic profile tracking approach is proposed to adaptively sample the deformed surface and reconstruct the surface model, based on a multi-ultrasonic-probe measurement system. The adaptive sampling algorithm calculates the position and surface normal of the next sampling point simultaneously based on a curvature sphere, which utilizes the surface information of the local area covered by the multi-ultrasonic-probe system. Moreover, a boundary processing algorithm is proposed to ensure the sampling process is carried out inside the boundary. The feasibility of the proposed automatic measurement method was validated through experiment.

A gantry crane presents a control problem with ten state variables. The undamped swinging of the load has led earlier researchers to apply cumbersome control strategies. The essence of pragmatic control is gleaned from autopilot designs of half a century ago. The control is designed as a set of 'nested loops', where the innermost loop takes the form of a velocity loop wrapped around a motor to give crisp velocity control. Target values are derived from states in the outer loops, to be applied to a succession of inner loops. These target values are subjected to constraints. Thus in the case of the crane, the horizontal position of the load can be considered to be the two outermost variables. In this study, from the load position error, two target velocity components are calculated and subjected to limits. The velocity error leads in turn to a target acceleration of the load and subsequently, to the target displacement that takes place between the horizontal coordinates of the hoist and the load. In this paper, the pragmatic control technique is demonstrated with the aid of a JavaScript and MATLAB software programs using a state-space model.

In the spiral welded pipe manufacturing process, grinding is one of the production processes, this process proceeds by hand grinding and fixed machine grinding. Usually, those methods have impacts larboard intensive, long production cycle and unstable product qualification rate for the final product. To prevent those factors from this paper, present a newly-designed grinding machine for a spiral welded pipe manufacturing industry, the machine has equipped with a special grinding machine with the ability to grind the spiral welded pipe the inner and outer surface simultaneously of the pipe and equipped with 6DOF grinding robot. The kinematics model of grinding robot is derived and the robot joint trajectory is calculated. The simulation result shows that the grinding mechanism can perform the job without failures under the external torque, and also trajectory graph of the robot kinematics shows there is no vibration on the robot movement to perform the job.

While prefabrication is the process where parts are manufactured off-site, modular construction on other hand is the utilisation of parts along with their installation to form a complete structure, such as a building. The aim of this paper is to compare case studies in prefabrication including modular construction. Subsequently, this paper reviewed five case studies around the globe. The comparison of these case studies showed that China had the fastest construction rate by manufacturing steel modules off-site. This was presumably due to the significant use of Advanced Modular Technology (AMT). Such new technique can potentially be the next era of prefabrication construction in high-rise construction. Particularly, the corporations which are either exploring or are using modular prefabrication should utilise AMT to enhance the design technique and assembly of prefabricated units.

Efficiency optimization is essential in many areas of engineering and system design. This work examines the efficiency of an experimental hydraulic system from different aspects: mechanical efficiency, pumps efficiency and flow stability. In this work, the flow control system depends on two independent variables with additional four degrees of freedom in terms of working pumping stations and flow path. An optimization algorithm was developed in order to identify the optimal duty point in terms of the efficiencies and stability within all possible system configurations. The results of the model are presented on several plots covering a 3D overview plot showing the system capabilities and additional 2D plots addressing each efficiency and stability optimization results and also demonstrating the system behaviour under different working conditions. The results of this work enables the user to easily choose the amount of working pumps and the duty point in order to achieve the desired flow rate. Moreover, it enables working in the desired optimal efficiency (or stability) in the proposed complicated two variable control system.

The problem of evaluating the effectiveness of reducing the weight of the aircraft and, in particular, the use of the concept of "fuel efficiency" is considered. For the design (operational) mass analysis, the mass state equation is used, on the basis of which the method of mass growth coefficients is constructed. The most widely used short-haul and medium-haul passenger aircraft of the B737 and A320 types are considered as an example of the application of this technique. The authors suggest to reduce the weight of the aircraft structure to switch to the fuselage without portholes. In the present work, this decision is assessed from the point of view of saving fuel weight.

As a product of modern industrial cutting-edge technology, a large civil aircraft needs to undergo rigorous flight test before entering the aviation market, which fully ensures the safety of aircraft and its system. This makes the aircraft meet the airworthiness standards and requirements. The flight test of civil aircraft is a complex system project, which the top-level planning throughout the flight test period has an important influence on progress control and flight test efficiency of a new type aircraft. The core content of the top-level plan is the evaluation of flight test workload with consideration of test aircraft quantity. This paper proposes a flight test workload analysis and evaluation model based on the types of test missions through the analysis of the characteristics of civil aircraft flight test mission, which provides a feasible method for quantitative evaluation of flight test workload.

The transportation and storage of powdered bulk materials is an important part of the manufacturing process of many products and requires equally important productive resources such as time, space and capital. Accurate estimation of these materials' mechanical properties, especially those related to the above processes, such as the angle of repose provides information necessary for the design of optimized mechanical systems that minimize production costs. In the context of the present study, a mechanical device has been developed at the Machine Design Laboratory of the School of Pedagogical & Technological Education (ASPETE) for the determination of the angle of repose of bulk materials, a dimension necessary for many calculations related to machinery, such as maximum capacity e.g. of conveyor bolts, straps and lifts. This device allows studying this property very accurately under various vibration conditions, thus giving more realistic and much more useful results. Measurements were conducted on dry and wet sawdust, a raw material of many important product, and angle-of-repose diagrams were generated with respect to stimulating vibration frequency.

Analytical solution of the equilibrium configuration of an axially moving Timoshenko beam in supercritical regime is studied. Three kinds of classical boundary conditions are considered. An analytical solution of the equilibrium configuration in terms of the axial velocity in supercritical regime is determined. But most of all, for an axially moving Timoshenko beam with the fixed ends in supercritical regime, an anti-symmetric configuration is firstly detected. And, its analytical solution is solved. Besides, numerical example shows that the solution of the equilibrium configuration bifurcates with axially velocity. And the critical velocity derived from the Timoshenko beam theory is smaller than that derived from Euler-Bernoulli beam theory. The amplitude of the solution of equilibrium configuration derived from Timoshenko beam is larger.

Atmospheric environment has become the focus of global attention. Fine particulate matter has posed a serious threat to human respiratory system. In order to effectively control atmospheric environment and protect human health, pollutant prediction has become a necessary work for human survival and development. In order to improve the accuracy of PM2.5 prediction, this paper developed a new combined prediction model — SSA-LSTM. Firstly, the observed time series are decomposed into periodic component and noise component by SSA (Singular spectrum analysis). Then, LSTM (Long short-term memory) neural network was used to forecast the decomposed components. Finally, the predicted results of different components are integrated to generate the final predicted results. The results show that the proposed model has a significant improvement in the accuracy of prediction.

Knot selection for regression splines is crucial to the approximation power of splines. For univariate splines, many knot selection algorithms are available. However, extending those univariate algorithms to the multivariate case can be challenging. In this work, an estimation procedure with knot selection for multivariate regression splines is proposed, where the knot selection part is adapted from an existing univariate knot selection algorithm. Simulation results are included to demonstrate the performance of the proposed method.

The study of social tension, its causes and laws of variation, as well as establishing its level is crucial during crises, epidemics and wars. The purpose of this research is to develop the system for determining the level of tension in society on the basis of data from social networks using decision-making and computational linguistic tools. The impact of various factors on the growth of social tensions is determined with the help of knowledge bases built by means of decision support systems. To analyse the emotionality of comment on news publications the TF-IDF and Word2vec methods are used. Within the framework of the method of goal dynamic estimating of alternatives, the level of social tension is determined as the degree of achievement of the main goal, the ratings of news publications and the ratings of news events that contributed to the increase in social tension are calculated. The study presents the efficient method of determining the level of social tension and defining the main factors that have the greatest impact on the growth of social tension. Further studies are needed to improve the estimates of factors and the overall estimate of social tension.

In this paper, we address the issue of using small text datasets for learning of neural networks. We explore the method that is used with image and sound datasets to augment data for increasing the performance of models. We then leverage this data augmentation technique to expand the training set of textual data. A great challenge in our dataset is that the amount of data is insufficient for training models. For this reason, we propose a method for augmenting text data specifically for Thai language which is based on Text Similarity and using the model to determine the semantic relationship between two sentences. The experimental results indicated that our proposed method is able to improve the performance of text classification.

Often when dealing with text data, there exists valuable information that determines the relationship between the words encountered in the corpus. The type of relationship which is sought after is the "has-a" and "is-a" relationship, with which one can build a hierarchical representation of words. Since each language has its own set of rules and syntax, extraction of the relationships ultimately boils down to understanding the syntax of the particular language and using relevant features in the process.

The paper presents a machine-learning model for understanding the language syntax and deducing the relationships between the words encountered. To be specific, a sequence modeling approach if followed, where the model receives a sequence of words and makes use of the various properties of the words to build a hierarchical graph. The algorithm described will be independent of the language, and the model should be versatile enough to be trained for different languages. In addition, the paper also describes how this information can be used to build better topic models, given a corpus of text.

During the running of serial manipulator, unbalanced force produced by base with respect to the floor has a great effect on the accuracy of manipulator's end. Aiming at the above problem, we take the three-degree-of-freedom serial manipulator as an example to analysis. First, taking advantage of the methodology of Newton-Euler dynamics to derive the relative force between two joint rods and base with respect to the floor while the manipulator is at the period of working. Then, building the spring-damp vibration model to calculate the parameter formula of the base with relative to the ground. Finally, analysing the characteristics of vibration and giving measures of reducing vibration, simulating to prove the effectivity using MATLAB. The simulation results show that when choosing other values of ω_n and ξ, vibration amplitude has significant decrease compared with the conditions of ω_n = ω_i or ξ =0.414 when other parameters unchanged, which provides a certain reference for further research on vibration reduction of series manipulator.

It is a well-known thing that formaldehyde can seriously endanger human health. During decoration, some decoration materials, including furniture, will contain a large amount of formaldehyde, and some wall paint will also emit a lot of formaldehyde. Therefore, how to judge that the harmful gas in a house exceeds the standard has become a headache. In response to this problem, this article has designed an intelligent formaldehyde detection system, which can accurately detect the concentration of harmful gases in the room and then alarm. The operation is simple.The system consists of STM32F103C8T6 microcontroller circuit, LCD1602 liquid crystal display circuit, and formaldehyde detection sensor circuit. The voltage value and formaldehyde concentration value before formaldehyde conversion can be displayed in real time as the formaldehyde concentration changes. If the concentration of formaldehyde in the air is higher than the body's tolerance range, the buzzer will sound a "beep" alarm, otherwise it will not sound.

Nowadays, CNNs has delivered the state-of-the-art performance in the field of computer vision, image classification, etc. As CNNs going deeper, it becomes more difficult to implement CNNs applications based on general-purpose computing platforms. Recently, many FPGA-based CNNs accelerators have been proposed, these accelerators achieved high performance on specific CNNs models, however they are somewhat lack of reconfigurability to fit different applications. To deal with this problem, an end-to-end acceleration framework was proposed in this paper, which consists of a parameterized hardware accelerator and a fully automatic software framework. Parallel computation and pipeline optimization are deployed in the hardware design to achieve high performance. Simultaneously, runtime reconfigurability is implemented by using a global register list. By encapsulating the underlying driver, a three-layer software framework is provided for users to deploy their pre-trained models. A typical CNNs model used for handwritten digital recognition was selected to test and verify the accelerator. The experimental result shows that the accelerator can reach a recognition speed of 22.65FPS under the clock frequency of 100MHz, comparing with ARM Cortex-A9 working at 650MHz, it can achieve 25.9 times of acceleration effect, with only 1.59W power consumption.

The quad tilt rotor (QTR) has complex dynamics characteristics, especially in transition mode. It is difficult to model the QTR dynamics and the environmental factors have a great influence on it. To solve the problem of control in transition mode of QTR, this paper carries out the design of the controller based on active disturbance rejection control (ADRC). ADRC has many parameters to be tuned, and the coupling effect is more serious, so it is very difficult to tune parameters. Particle swarm optimization (PSO) algorithm has faster computing speed and better global search ability in dynamic and multi-objective optimization. So, using PSO algorithm to realize self-tuning of ADRC parameters in ADRC parameters tuning. By comparing the control performance of ADRC before and after optimization, the rationality and effectiveness of ADRC parameters tuning algorithm in QTR are verified in both time domain and frequency domain.

Two multi-exit selection models based on social force model are presented to simulate pedestrian evacuation, and the model coefficients are optimized by considering the effect of the exit distance, exit width, crowd number and distribution. The evacuation processes employing shortest distance evacuation strategy, static and dynamic exit selection model are compared. The effects of the crowd number, distribution and desired speed are investigated on the evacuation time and balance degree with the static and dynamic exit selection model. The effects of group size and group shape on the evacuation time in dynamic exit selection model is explored. The simulation results indicate that the proposed dynamic exit selection model can realistically reflect the pedestrian evacuation and help predicate the time available in building spaces with multiple exits, which can lead to a shorter evacuation time and higher evacuation efficiency. The study has some guiding significance for emergency evacuation and exits design of multi-exit buildings.

This paper introduces an arbitrary polynomial chaos expansion method for performing probabilistic power flow analysis in power systems. The proposed method is used for uncertainty analysis, expressing the uncertainty of a system as random variables with an arbitrary output distribution based on orthogonal polynomial expansion. This method is advantageous because of its calculation speed and accuracy. This study expresses probabilistic power flow in a power system with many uncertain power sources using linear combination polynomial expansion. The orthogonal polynomial system employed is generated by moment analysis from renewable energy output data, with the polynomial coefficients derived from a collocation method. Simulation of probabilistic power flow using the proposed method is applied to a 29-bus transmission network model including three renewable energies, and the calculation speed and accuracy are evaluated by changing the expansion order of the polynomial. In addition, the influence on the polynomial coefficient is assessed when the system topology is changed due to a line fault. Therefore, since the arbitrary polynomial chaos expansion method can represent complex networks by linear combination of orthogonal polynomial sets, calculation based on it is several hundred times faster than the conventional Monte Carlo method. The results demonstrate that the proposed method is very useful for analyzing the probabilistic power distribution and that third-order expansion is practically appropriate.

This paper copes with the controller design problem of a micro helicopter, which is a multivariable and strongly coupled nonlinear system. The state-space model near the hovering condition of pitch and roll channels is acquired by least-square system identification method, with flight test verification. Based on the identified model, model reference adaptive control is designed as angular rate controller, and PID controller is used to stabilize attitude loop. State-space model helps to decouple the roll and pitch channels, and model reference adaptive control can address external disturbances, model uncertainties and nonlinearities of the dynamics, which can be estimated and further eliminated online. Eventually, both simulations and actual flight tests are conducted to verify the effectiveness of the proposed control scheme.

Uncertain external disturbances either secular or oscillating make the satellite attitude be deviated or oscillating from the mission attitude. These disturbances should be detected in short and rejected with proper counter torques of actuators. Nonlinear second order sliding mode observer is one of the good algorithms that can be used for the detection of disturbances' magnitude and frequencies. With a control law of the integration and dipole rejection filters based on the identified disturbance information, the actuator torques can compensate the disturbances. The spacecraft attitude is then stabilized at the mission attitude within a tolerable error. In this paper, the performances of detection and rejection algorithms are checked respectively in computer simulations. The applicability is proved on a satellite ground simulator recently developed in Korea Aerospace University. The results show that the algorithms work properly with small error, which is due to the low grade of sensors and actuators.

The problem of car sequencing has been considered in the literature many times, but very often with the assumption of many simplifications, which meant that the discussed issue was far from the problems occurring in reality. The article presents an attempt to capture the real problem of sequencing, in particular in paint shop, because from the point of view of economic indicators, painting process is today a complex, multistage, extremely energy consuming and cost intensive operation. The main goal is therefore to minimize the number of costly changeovers of painting guns, resulting from color changes and synchronize those with periodic cleanings, forced by technological requirements. For this purpose, a buffer located in the paint shop is applied. In the paper a game-theoretic framework is presented to analyze the considered problem. Two games: Buffer Slot Assignment Game and Buffer-OutShuttle are compared with algorithms based on priority rules. Based on the performed simulations the effectivity of presented algorithms is verified using several datasets.

Computed Torque Control (CTC) is the most direct and effective way to improve the motion control performance of robot. But the computation of the joint torque is quite difficult, and because of the uncertainty of the parameters, an accurate inverse robot dynamic model for torque generation is difficult to obtain. An efficient inverse dynamic model of the industrial robot based on lie algebra is proposed and applied to the computed torque control. In order to overcome the uncertainty of parameters, the inverse robot dynamic model is linearized and an adaptive computed torque control is proposed. In order to validate the adaptive torque computed control method, a multi-domain integrated system model of 6-DOF industrial robot is established and the simulation results show that the adaptive computed torque control system has the function of parameter self-learning, the inaccurate parameters converge to the true value finally. The adaptive control shows better control performance than the traditional computed torque control.

Previous research on relation extraction has proved the effectiveness of using dependency trees, which build non-local connections between tokens. However, the existing dependency-based models treat the dependency trees as an inherently flat graph, which causes a loss of dependency information for representing sentences. Besides, they fail to consider the fact that the importance of tokens on the dependency tree varies with different relations to be extracted. In this paper, we propose a novel hierarchical graph attention network HierGAT, which can generate multi-level dependency trees and extract key information from them to improve relation extraction. Specifically, it contains multiple dependency-based graph attention layers, each of which takes a different dependency tree generated by an adaptive subtree pruning strategy as input, and distinguishes the importance of different tokens in a dependency tree. Finally, HierGAT integrates the output token representations of each layer with a multi-head attention mechanism, and learns sentence representation for relation extraction through a pooling layer. The experimental results demonstrate that our method outperforms state-of-the-art baselines on the benchmark datasets.

This paper proposes a technique for improving the localization of areas of diabetic macular edema. This study is relevant because the incidence of serious eye diseases due to diabetic macular edema is only increasing among the world's population. The proposed method is graph-based image segmentation. Comparison of optical coherence tomography (OCT) data and retinal images is based on the search and comparison of special points on the original analyzed image and OCT analysis based on these images. Segmentation accuracy is improved by using specially selected parameters. Of these, the optimal parameters obtained in the course of the study made it possible to achieve a segmentation error of 2%.

Camera motion detection is a useful functionality in video surveillance and many other areas, but with its widespread application in many areas, the compaction power has increased and needs to be addressed how to reduce it. So far, there has been a lot of research on pixel domain, but it is hard to operate with real-time and consumes very much computing power. However, since the compressed domain of block-based codec contains useful information for video analysis, this allows accurate video analysis at a low cost. The proposed method shows how to perform a motion detection accurately while significantly reducing the amount of computation compared to the pixel domain by using the DCT coefficients, motion vectors and other features in the compressed domain of the H.264 video. The proposed algorithm is designed for motion detection in video surveillance servers in the form of a cloud. The results of the experiment were shown to support validity.

The identification of persons in multi-spectral images that are not spatially aligned is a challenging process. A correct identification can improve the pedestrian detection task for machine vision applications. In this context we propose a person identification mechanism able to correctly find the same person in infrared and visible images. The main contribution of the paper is the keypoint based matcher that uses a deep learning based solution for finding relevant human pose keypoints and a local neighbour search for extracting the best candidates for person identification. For each of the two images, infrared and color we first perform pedestrian detection. Next, on each detected instance we extract the relevant keypoints for shoulders, hands and legs. A matching algorithm between the extracted keypoints is proposed in order to perform the identification of persons in the two images. We obtain an identification accuracy of 76% for pedestrians that have a medium height with respect to the image dimensions, and have a small occlusion degree.

In this paper, a new joint sparse representation method called discriminative locality-constrained sparse representation (DLSR) is proposed for robust face recognition. DLSR incorporates locality and label information of training samples into the framework of sparse representation. Locality information can distinguish dissimilarity between samples and plays an important role in image classification. Compared with the existing methods, DLSR contains more discriminative information of samples and can obtain more discriminative recognition results. Due to the use of l2-norm regularization, DLSR can obtain a closed-form solution. This makes it computationally very efficient. Experimental results based on the benchmark face databases ORL have shown that DLSR can achieve more promising performance than some state-of-the-art methods.

In the present document a processing technique is applied to identify the intention of movement in the myoelectric signals, by means of algorithms entered in a microcomputer with a software of free programming that presents a great speed when executing the instructions, with the necessary resources, to replace the PC and thus achieve low costs while maintaining the high quality standard, making the system accessible and reliable for people with low economic resources, while generating greater portability compared to the current prostheses that are handled in Peru, that are mostly made abroad, which increases the cost

In previous researches, we have proposed novel modulation methods such as the CDMA-QAM method in which Code-Division Multiple Access (CDMA) and Quadrature Amplitude Modulation (QAM) are combined, and applied these methods for improvement of railway signalling systems. Although a rail is used as a transmission medium, there are severe conditions for transmission, such as strong attenuation at frequencies above about 10 kHz. To overcome this restriction, we attempted to improve the S/N characteristics in our proposed method. Specifically, we focused on correlation characteristics of spread codes which are used in CDMA. In this paper, we show that an error correction function that does not require additional bits for such correction can be realized by using the correlation characteristics. We evaluated the effectiveness of this correction method and conducted computer simulations in which the method was employed for CDMA-based transmission.

At present, railway signalling systems in which control information is transmitted via track circuits (rails) have been deployed in many applications, such as automatic train control (ATC) systems in Japan. In these systems, it is difficult to increase the transmission speed due to the transmission characteristics of rails. To overcome this problem, we have proposed a new transmission method using orthogonal frequency division multiplexing (OFDM) and evaluated a configuration in which data judgment using majority decision was applied for improving the bit error rate (BER) characteristics. In this paper, we describe an FPGA implementation of our proposed method and the performance of the implemented devices.

As a new distributed computing paradigm, blockchain is rapidly evolving in areas such as digital finance and cryptocurrency. However, existing blockchain projects adopt different blockchain architectures and protocols, as a result it is difficult for different blockchain systems to flow value to each other or communicate information, and different blockchain systems become isolated islands. This has brought limitations to the usable range, function and scalability of blockchain technology. In order to solve this problem, and bulid trust between different blockchain networks, cross-chain technology has been proposed and received a lot of attention. In this paper we proposed a cross-chain mechanism based on verifiable random functions ( VRF ) and threshold cryptography, we name this scheme as Vger. In Vger, through VRF based cryptographic sortition to select management committee for escrow account and dynamic security setting mechanism, that optimize the security and efficiency about cross-chain transaction.

Utilizing website in business process has become essential. But lot of web designer have no respect of using methodology in developing a website cause the quality that website do not meet the needs of its users. On the other hand, usability level of the website could not attract a lot of visitation from any user. On this paper, researcher using Engineering Faculty in University of Indonesia's website to be studied. To increase the usability of this website, research conducted by redesign the website using Fuzzy Delphi Method to determine the media type to presenting each service and also to determine the services layout of each web page. In addition, this research also uses Fuzzy Cognitive Maps to models the interrelationship between each services and media type. Resulting the prototype of 12 web page for website owned by Engineering Faculty in University of Indonesia with total 36 services provided in this website to gives an optimal information for the user.

Genetic tests can provide prognostic information in breast cancer for both diagnosis and treatment planning. However, the cost of a genetic test is still high. In this study, we developed a radiogenomics method to predict genetically-evaluated responses to chemotherapy for breast cancer using our machine-learning technology coupled with model selection. Our proposed method consists of feature extraction, model selection, and prediction by the selected model. In the feature extraction, 318 morphological and texture features were extracted from a tumour region. In the model selection module, there are two major components: (1) selection of imaging biomarkers based on our original sequential forward floating selection (SFFS) feature selection and (2) building of a support vector machine (SVM) classifier including kernel function selection and hyperparameter optimization. The optimized feature set, i.e. imaging biomarkers, coupled with an SVM classifier were chosen by maximizing the area under curve (AUC) of corresponding receiver-operating-characteristic curve (ROC). After the model selection, the optimized SVM classifier operated on the selected imaging biomarkers for prediction. We applied our proposed method to 118 breast MRI studies from 118 patients for predicting genetically-evaluated responses to chemotherapy for breast cancer that evaluated by the genetic test of IRSN-23. We achieved an AUC value of 0.96 using the optimized SVM classifier model coupled with 24 selected imaging biomarkers in predicting the results of IRSN-23 in a five-fold cross-validation procedure.

Nowadays, the Chinese government usually publishes policies via social media, where everyone can respond to the messages. Exploring the interaction behaviors of millions of users can help the government collect the users' opinions and make decisions. We use the machine learning algorithm Multilayer Perceptron Network model to predict the user's interactive behaviors under their comments/replies. We found that three kinds of features are useful in predicting user interaction behaviors: the Doc2vec word vector features, the user attributes, and the user history posting information. The experiments show the effectiveness of the neural network-based model, which provides a way to optimize the formulation and implementation of public policies.