Search results for: real time acquisition
20349 Architecture for Multi-Unmanned Aerial Vehicles Based Autonomous Precision Agriculture Systems
Authors: Ebasa Girma, Nathnael Minyelshowa, Lebsework Negash
Abstract:
The use of unmanned aerial vehicles (UAVs) in precision agriculture has seen a huge increase recently. As such, systems that aim to apply various algorithms on the field need a structured framework of abstractions. This paper defines the various tasks of the UAVs in precision agriculture and models them into an architectural framework. The presented architecture is built on the context that there will be minimal physical intervention to do the tasks defined with multiple coordinated and cooperative UAVs. Various tasks such as image processing, path planning, communication, data acquisition, and field mapping are employed in the architecture to provide an efficient system. Besides, different limitation for applying Multi-UAVs in precision agriculture has been considered in designing the architecture. The architecture provides an autonomous end-to-end solution, starting from mission planning, data acquisition, and image processing framework that is highly efficient and can enable farmers to comprehensively deploy UAVs onto their lands. Simulation and field tests show that the architecture offers a number of advantages that include fault-tolerance, robustness, developer, and user-friendliness.Keywords: deep learning, multi-UAVs, precision agriculture, UAVs architecture
Procedia PDF Downloads 10720348 Development of Electroencephalograph Collection System in Language-Learning Self-Study System That Can Detect Learning State of the Learner
Authors: Katsuyuki Umezawa, Makoto Nakazawa, Manabu Kobayashi, Yutaka Ishii, Michiko Nakano, Shigeichi Hirasawa
Abstract:
This research aims to develop a self-study system equipped with an artificial teacher who gives advice to students by detecting the learners and to evaluate language learning in a unified framework. 'Detecting the learners' means that the system understands the learners' learning conditions, such as each learner’s degree of understanding, the difference in each learner’s thinking process, the degree of concentration or boredom in learning, and problem solving for each learner, which can be interpreted from learning behavior. In this paper, we propose a system to efficiently collect brain waves from learners by focusing on only the brain waves among the biological information for 'detecting the learners'. The conventional Electroencephalograph (EEG) measurement method during learning using a simple EEG has the following disadvantages. (1) The start and end of EEG measurement must be done manually by the experiment participant or staff. (2) Even when the EEG signal is weak, it may not be noticed, and the data may not be obtained. (3) Since the acquired EEG data is stored in each PC, there is a possibility that the time of data acquisition will be different in each PC. This time, we developed a system to collect brain wave data on the server side. This system overcame the above disadvantages.Keywords: artificial teacher, e-learning, self-study system, simple EEG
Procedia PDF Downloads 13620347 Deep Learning for SAR Images Restoration
Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo Ferraioli
Abstract:
In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.Keywords: SAR image, polarimetric SAR image, convolutional neural network, deep learnig, deep neural network
Procedia PDF Downloads 6420346 Multiperson Drone Control with Seamless Pilot Switching Using Onboard Camera and Openpose Real-Time Keypoint Detection
Authors: Evan Lowhorn, Rocio Alba-Flores
Abstract:
Traditional classification Convolutional Neural Networks (CNN) attempt to classify an image in its entirety. This becomes problematic when trying to perform classification with a drone’s camera in real-time due to unpredictable backgrounds. Object detectors with bounding boxes can be used to isolate individuals and other items, but the original backgrounds remain within these boxes. These basic detectors have been regularly used to determine what type of object an item is, such as “person” or “dog.” Recent advancement in computer vision, particularly with human imaging, is keypoint detection. Human keypoint detection goes beyond bounding boxes to fully isolate humans and plot points, or Regions of Interest (ROI), on their bodies within an image. ROIs can include shoulders, elbows, knees, heads, etc. These points can then be related to each other and used in deep learning methods such as pose estimation. For drone control based on human motions, poses, or signals using the onboard camera, it is important to have a simple method for pilot identification among multiple individuals while also giving the pilot fine control options for the drone. To achieve this, the OpenPose keypoint detection network was used with body and hand keypoint detection enabled. OpenPose supports the ability to combine multiple keypoint detection methods in real-time with a single network. Body keypoint detection allows simple poses to act as the pilot identifier. The hand keypoint detection with ROIs for each finger can then offer a greater variety of signal options for the pilot once identified. For this work, the individual must raise their non-control arm to be identified as the operator and send commands with the hand on their other arm. The drone ignores all other individuals in the onboard camera feed until the current operator lowers their non-control arm. When another individual wish to operate the drone, they simply raise their arm once the current operator relinquishes control, and then they can begin controlling the drone with their other hand. This is all performed mid-flight with no landing or script editing required. When using a desktop with a discrete NVIDIA GPU, the drone’s 2.4 GHz Wi-Fi connection combined with OpenPose restrictions to only body and hand allows this control method to perform as intended while maintaining the responsiveness required for practical use.Keywords: computer vision, drone control, keypoint detection, openpose
Procedia PDF Downloads 17920345 A Memetic Algorithm for an Energy-Costs-Aware Flexible Job-Shop Scheduling Problem
Authors: Christian Böning, Henrik Prinzhorn, Eric C. Hund, Malte Stonis
Abstract:
In this article, the flexible job-shop scheduling problem is extended by consideration of energy costs which arise owing to the power peak, and further decision variables such as work in process and throughput time are incorporated into the objective function. This enables a production plan to be simultaneously optimized in respect of the real arising energy and logistics costs. The energy-costs-aware flexible job-shop scheduling problem (EFJSP) which arises is described mathematically, and a memetic algorithm (MA) is presented as a solution. In the MA, the evolutionary process is supplemented with a local search. Furthermore, repair procedures are used in order to rectify any infeasible solutions that have arisen in the evolutionary process. The potential for lowering the real arising costs of a production plan through consideration of energy consumption levels is highlighted.Keywords: energy costs, flexible job-shop scheduling, memetic algorithm, power peak
Procedia PDF Downloads 34120344 Problems Arising in Visual Perception
Authors: K. A. Tharanga, K. H. H. Damayanthi
Abstract:
Perception is an epistemological concept discussed in Philosophy. Perception, in other word, vision, is one of the ways that human beings get empirical knowledge after five senses. However, we face innumerable problems when achieving knowledge from perception, and therefore the knowledge gained through perception is uncertain. what we see in the external world is not real. These are the major issues that we face when receiving knowledge through perception. Sometimes there is no physical existence of what we really see. In such cases, the perception is relative. The following frames will be taken into consideration when perception is analyzed illusions and delusions, the figure of a physical object, appearance and the reality of a physical object, time factor, and colour of a physical object.seeing and knowing become vary according to the above conceptual frames. We cannot come to a proper conclusion of what we see in the empirical world. Because the things that we see are not really there. Hence the scientific knowledge which is gained from observation is doubtful. All the factors discussed in science remain in the physical world. There is a leap from ones existence to the existence of a world outside his/her mind. Indeed, one can suppose that what he/she takes to be real is just anmassive deception. However, depending on the above facts, if someone begins to doubt about the whole world, it is unavoidable to become his/her view a scepticism or nihilism. This is a certain reality.Keywords: empirical, perception, sceptisism, nihilism
Procedia PDF Downloads 8220343 Deep Learning Based Polarimetric SAR Images Restoration
Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli
Abstract:
In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry
Procedia PDF Downloads 8320342 Optimal Portfolio of Multi-service Provision based on Stochastic Model Predictive Control
Authors: Yifu Ding, Vijay Avinash, Malcolm McCulloch
Abstract:
As the proliferation of decentralized energy systems, the UK power system allows small-scale entities such as microgrids (MGs) to tender multiple energy services including energy arbitrage and frequency responses (FRs). However, its operation requires the balance between the uncertain renewable generations and loads in real-time and has to fulfill their provision requirements of contract services continuously during the time window agreed, otherwise it will be penalized for the under-delivered provision. To hedge against risks due to uncertainties and maximize the economic benefits, we propose a stochastic model predictive control (SMPC) framework to optimize its operation for the multi-service provision. Distinguished from previous works, we include a detailed economic-degradation model of the lithium-ion battery to quantify the costs of different service provisions, as well as accurately describe the changing dynamics of the battery. Considering a branch of load and generation scenarios and the battery aging, we formulate a risk-averse cost function using conditional value at risk (CVaR). It aims to achieve the maximum expected net revenue and avoids severe losses. The framework will be performed on a case study of a PV-battery grid-tied microgrid in the UK with real-life data. To highlight its performance, the framework will be compared with the case without the degradation model and the deterministic formulation.Keywords: model predictive control (MPC), battery degradation, frequency response, microgrids
Procedia PDF Downloads 11720341 Risk Analysis in Off-Site Construction Manufacturing in Small to Medium-Sized Projects
Authors: Atousa Khodadadyan, Ali Rostami
Abstract:
The objective of off-site construction manufacturing is to utilise the workforce and machinery in a controlled environment without external interference for higher productivity and quality. The usage of prefabricated components can save up to 14% of the total energy consumption in comparison with the equivalent number of cast-in-place ones. Despite the benefits of prefabrication construction, its current project practices encompass technical and managerial issues. Building design, precast components’ production, logistics, and prefabrication installation processes are still mostly discontinued and fragmented. Furthermore, collaboration among prefabrication manufacturers, transportation parties, and on-site assemblers rely on real-time information such as the status of precast components, delivery progress, and the location of components. From the technical point of view, in this industry, geometric variability is still prevalent, which can be caused during the transportation or production of components. These issues indicate that there are still many aspects of prefabricated construction that can be developed using disruptive technologies. Practical real-time risk analysis can be used to address these issues as well as the management of safety, quality, and construction environment issues. On the other hand, the lack of research about risk assessment and the absence of standards and tools hinder risk management modeling in prefabricated construction. It is essential to note that no risk management standard has been established explicitly for prefabricated construction projects, and most software packages do not provide tailor-made functions for this type of projects.Keywords: project risk management, risk analysis, risk modelling, prefabricated construction projects
Procedia PDF Downloads 16620340 Algorithms for Fast Computation of Pan Matrix Profiles of Time Series Under Unnormalized Euclidean Distances
Authors: Jing Zhang, Daniel Nikovski
Abstract:
We propose an approximation algorithm called LINKUMP to compute the Pan Matrix Profile (PMP) under the unnormalized l∞ distance (useful for value-based similarity search) using double-ended queue and linear interpolation. The algorithm has comparable time/space complexities as the state-of-the-art algorithm for typical PMP computation under the normalized l₂ distance (useful for shape-based similarity search). We validate its efficiency and effectiveness through extensive numerical experiments and a real-world anomaly detection application.Keywords: pan matrix profile, unnormalized euclidean distance, double-ended queue, discord discovery, anomaly detection
Procedia PDF Downloads 24120339 Mathematical Modeling of Activated Sludge Process: Identification and Optimization of Key Design Parameters
Authors: Ujwal Kishor Zore, Shankar Balajirao Kausley, Aniruddha Bhalchandra Pandit
Abstract:
There are some important design parameters of activated sludge process (ASP) for wastewater treatment and they must be optimally defined to have the optimized plant working. To know them, developing a mathematical model is a way out as it is nearly commensurate the real world works. In this study, a mathematical model was developed for ASP, solved under activated sludge model no 1 (ASM 1) conditions and MATLAB tool was used to solve the mathematical equations. For its real-life validation, the developed model was tested for the inputs from the municipal wastewater treatment plant and the results were quite promising. Additionally, the most cardinal assumptions required to design the treatment plant are discussed in this paper. With the need for computerization and digitalization surging in every aspect of engineering, this mathematical model developed might prove to be a boon to many biological wastewater treatment plants as now they can in no time know the design parameters which are required for a particular type of wastewater treatment.Keywords: waste water treatment, activated sludge process, mathematical modeling, optimization
Procedia PDF Downloads 13920338 Head-Mounted Displays for HCI Validations While Driving
Abstract:
To provide reliable and valid findings when evaluating innovative in-car devices in the automotive context highly realistic driving environments are recommended. Nowadays, in-car devices are mostly evaluated due to driving simulator studies followed by real car driving experiments. Driving simulators are characterized by high internal validity, but weak regarding ecological validity. Real car driving experiments are ecologically valid, but difficult to standardize, more time-robbing and costly. One economizing suggestion is to implement more immersive driving environments when applying driving simulator studies. This paper presents research comparing non-immersive standard PC conditions with mobile and highly immersive Oculus Rift conditions while performing the Lane Change Task (LCT). Subjective data with twenty participants show advantages regarding presence and immersion experience when performing the LCT with the Oculus Rift, but affect adversely cognitive workload and simulator sickness, compared to non-immersive PC condition.Keywords: immersion, oculus rift, presence, situation awareness
Procedia PDF Downloads 18120337 Autonomous Ground Vehicle Navigation Based on a Single Camera and Image Processing Methods
Authors: Auday Al-Mayyahi, Phil Birch, William Wang
Abstract:
A vision system-based navigation for autonomous ground vehicle (AGV) equipped with a single camera in an indoor environment is presented. A proposed navigation algorithm has been utilized to detect obstacles represented by coloured mini- cones placed in different positions inside a corridor. For the recognition of the relative position and orientation of the AGV to the coloured mini cones, the features of the corridor structure are extracted using a single camera vision system. The relative position, the offset distance and steering angle of the AGV from the coloured mini-cones are derived from the simple corridor geometry to obtain a mapped environment in real world coordinates. The corridor is first captured as an image using the single camera. Hence, image processing functions are then performed to identify the existence of the cones within the environment. Using a bounding box surrounding each cone allows to identify the locations of cones in a pixel coordinate system. Thus, by matching the mapped and pixel coordinates using a projection transformation matrix, the real offset distances between the camera and obstacles are obtained. Real time experiments in an indoor environment are carried out with a wheeled AGV in order to demonstrate the validity and the effectiveness of the proposed algorithm.Keywords: autonomous ground vehicle, navigation, obstacle avoidance, vision system, single camera, image processing, ultrasonic sensor
Procedia PDF Downloads 29820336 Quantum Statistical Machine Learning and Quantum Time Series
Authors: Omar Alzeley, Sergey Utev
Abstract:
Minimizing a constrained multivariate function is the fundamental of Machine learning, and these algorithms are at the core of data mining and data visualization techniques. The decision function that maps input points to output points is based on the result of optimization. This optimization is the central of learning theory. One approach to complex systems where the dynamics of the system is inferred by a statistical analysis of the fluctuations in time of some associated observable is time series analysis. The purpose of this paper is a mathematical transition from the autoregressive model of classical time series to the matrix formalization of quantum theory. Firstly, we have proposed a quantum time series model (QTS). Although Hamiltonian technique becomes an established tool to detect a deterministic chaos, other approaches emerge. The quantum probabilistic technique is used to motivate the construction of our QTS model. The QTS model resembles the quantum dynamic model which was applied to financial data. Secondly, various statistical methods, including machine learning algorithms such as the Kalman filter algorithm, are applied to estimate and analyses the unknown parameters of the model. Finally, simulation techniques such as Markov chain Monte Carlo have been used to support our investigations. The proposed model has been examined by using real and simulated data. We establish the relation between quantum statistical machine and quantum time series via random matrix theory. It is interesting to note that the primary focus of the application of QTS in the field of quantum chaos was to find a model that explain chaotic behaviour. Maybe this model will reveal another insight into quantum chaos.Keywords: machine learning, simulation techniques, quantum probability, tensor product, time series
Procedia PDF Downloads 46520335 Real-Space Mapping of Surface Trap States in Cigse Nanocrystals Using 4D Electron Microscopy
Authors: Riya Bose, Ashok Bera, Manas R. Parida, Anirudhha Adhikari, Basamat S. Shaheen, Erkki Alarousu, Jingya Sun, Tom Wu, Osman M. Bakr, Omar F. Mohammed
Abstract:
This work reports visualization of charge carrier dynamics on the surface of copper indium gallium selenide (CIGSe) nanocrystals in real space and time using four-dimensional scanning ultrafast electron microscopy (4D S-UEM) and correlates it with the optoelectronic properties of the nanocrystals. The surface of the nanocrystals plays a key role in controlling their applicability for light emitting and light harvesting purposes. Typically for quaternary systems like CIGSe, which have many desirable attributes to be used for optoelectronic applications, relative abundance of surface trap states acting as non-radiative recombination centre for charge carriers remains as a major bottleneck preventing further advancements and commercial exploitation of these nanocrystals devices. Though ultrafast spectroscopic techniques allow determining the presence of picosecond carrier trapping channels, because of relative larger penetration depth of the laser beam, only information mainly from the bulk of the nanocrystals is obtained. Selective mapping of such ultrafast dynamical processes on the surfaces of nanocrystals remains as a key challenge, so far out of reach of purely optical probing time-resolved laser techniques. In S-UEM, the optical pulse generated from a femtosecond (fs) laser system is used to generate electron packets from the tip of the scanning electron microscope, instead of the continuous electron beam used in the conventional setup. This pulse is synchronized with another optical excitation pulse that initiates carrier dynamics in the sample. The principle of S-UEM is to detect the secondary electrons (SEs) generated in the sample, which is emitted from the first few nanometers of the top surface. Constructed at different time delays between the optical and electron pulses, these SE images give direct and precise information about the carrier dynamics on the surface of the material of interest. In this work, we report selective mapping of surface dynamics in real space and time of CIGSe nanocrystals applying 4D S-UEM. We show that the trap states can be considerably passivated by ZnS shelling of the nanocrystals, and the carrier dynamics can be significantly slowed down. We also compared and discussed the S-UEM kinetics with the carrier dynamics obtained from conventional ultrafast time-resolved techniques. Additionally, a direct effect of the state trap removal can be observed in the enhanced photoresponse of the nanocrystals after shelling. Direct observation of surface dynamics will not only provide a profound understanding of the photo-physical mechanisms on nanocrystals’ surfaces but also enable to unlock their full potential for light emitting and harvesting applications.Keywords: 4D scanning ultrafast microscopy, charge carrier dynamics, nanocrystals, optoelectronics, surface passivation, trap states
Procedia PDF Downloads 29220334 Brain-Computer Interface Based Real-Time Control of Fixed Wing and Multi-Rotor Unmanned Aerial Vehicles
Authors: Ravi Vishwanath, Saumya Kumaar, S. N. Omkar
Abstract:
Brain-computer interfacing (BCI) is a technology that is almost four decades old, and it was developed solely for the purpose of developing and enhancing the impact of neuroprosthetics. However, in the recent times, with the commercialization of non-invasive electroencephalogram (EEG) headsets, the technology has seen a wide variety of applications like home automation, wheelchair control, vehicle steering, etc. One of the latest developed applications is the mind-controlled quadrotor unmanned aerial vehicle. These applications, however, do not require a very high-speed response and give satisfactory results when standard classification methods like Support Vector Machine (SVM) and Multi-Layer Perceptron (MLPC). Issues are faced when there is a requirement for high-speed control in the case of fixed-wing unmanned aerial vehicles where such methods are rendered unreliable due to the low speed of classification. Such an application requires the system to classify data at high speeds in order to retain the controllability of the vehicle. This paper proposes a novel method of classification which uses a combination of Common Spatial Paradigm and Linear Discriminant Analysis that provides an improved classification accuracy in real time. A non-linear SVM based classification technique has also been discussed. Further, this paper discusses the implementation of the proposed method on a fixed-wing and VTOL unmanned aerial vehicles.Keywords: brain-computer interface, classification, machine learning, unmanned aerial vehicles
Procedia PDF Downloads 27520333 Dynamic Model of Heterogeneous Markets with Imperfect Information for the Optimization of Company's Long-Time Strategy
Authors: Oleg Oborin
Abstract:
This paper is dedicated to the development of the model, which can be used to evaluate the effectiveness of long-term corporate strategies and identify the best strategies. The theoretical model of the relatively homogenous product market (such as iron and steel industry, mobile services or road transport) has been developed. In the model, the market consists of a large number of companies with different internal characteristics and objectives. The companies can perform mergers and acquisitions in order to increase their market share. The model allows the simulation of long-time dynamics of the market (for a period longer than 20 years). Therefore, a large number of simulations on random input data was conducted in the framework of the model. After that, the results of the model were compared with the dynamics of real markets, such as the US steel industry from the beginning of the XX century to the present day, and the market of mobile services in Germany for the period between 1990 and 2015.Keywords: Economic Modelling, Long-Time Strategy, Mergers and Acquisitions, Simulation
Procedia PDF Downloads 35920332 Composite Approach to Extremism and Terrorism Web Content Classification
Authors: Kolade Olawande Owoeye, George Weir
Abstract:
Terrorism and extremism activities on the internet are becoming the most significant threats to national security because of their potential dangers. In response to this challenge, law enforcement and security authorities are actively implementing comprehensive measures by countering the use of the internet for terrorism. To achieve the measures, there is need for intelligence gathering via the internet. This includes real-time monitoring of potential websites that are used for recruitment and information dissemination among other operations by extremist groups. However, with billions of active webpages, real-time monitoring of all webpages become almost impossible. To narrow down the search domain, there is a need for efficient webpage classification techniques. This research proposed a new approach tagged: SentiPosit-based method. SentiPosit-based method combines features of the Posit-based method and the Sentistrenght-based method for classification of terrorism and extremism webpages. The experiment was carried out on 7500 webpages obtained through TENE-webcrawler by International Cyber Crime Research Centre (ICCRC). The webpages were manually grouped into three classes which include the ‘pro-extremist’, ‘anti-extremist’ and ‘neutral’ with 2500 webpages in each category. A supervised learning algorithm is then applied on the classified dataset in order to build the model. Results obtained was compared with existing classification method using the prediction accuracy and runtime. It was observed that our proposed hybrid approach produced a better classification accuracy compared to existing approaches within a reasonable runtime.Keywords: sentiposit, classification, extremism, terrorism
Procedia PDF Downloads 27020331 EU Integratıon Impact over the Real Convergence
Authors: Badoiu Mihaela Catalina
Abstract:
Main focus of COHESION policy was reducing social and economic disparities between member states and regions, sustainable development and equal opportunities. In this perspective, the present study intend to analyze the evolution of the European architecture and its direct impact over the real convergence in the member states.Keywords: cooperation, European union, member states, cohesion policy
Procedia PDF Downloads 45120330 Exploring a Teaching Model in Cultural Education Using Video-Focused Social Networking Apps: An Example of Chinese Language Teaching for African Students
Authors: Zhao Hong
Abstract:
When international students study Chinese as a foreign or second language, it is important for them to form constructive viewpoints and possess an open mindset on Chinese culture. This helps them to make faster progress in their language acquisition. Observations from African students at Liaoning Institute of Science and Technology show that by integrating video-focused social networking apps such as Tiktok (“Douyin”) on a controlled basis, students raise their interest not only in making an effort in learning the Chinese language, but also in the understanding of the Chinese culture. During the last twelve months, our research group explored a teaching model using selected contents in certain classroom settings, including virtual classrooms during lockdown periods due to the COVID-19 pandemic. Using interviews, a survey was conducted on international students from African countries at the Liaoning Institute of Science and Technology in Chinese language courses. Based on the results, a teaching model was built for Chinese language acquisition by entering the "mobile Chinese culture".Keywords: Chinese as a foreign language, cultural education, social networking apps, teaching model
Procedia PDF Downloads 6820329 An Investigation of Machinability of Inconel 718 in EDM Using Different Cryogenic Treated Tools
Authors: Pradeep Joshi, Prashant Dhiman, Shiv Dayal Dhakad
Abstract:
Inconel 718 is a family if Nickel-Chromium based Superalloy; it has very high oxidation and corrosion resistance. Inconel 718 is widely being used in aerospace, engine, turbine etc. due to its high mechanical strength and creep resistance. Being widely used, its machining should be easy but in real its machining is very difficult, especially by using traditional machining methods. It becomes easy to machine only by using non Traditional machining such as EDM. During EDM machining there is wear of both tool and workpiece, the tool wear is undesired because it changes tool shape, geometry. To reduce the tool wear rate (TWR) cryogenic treatment is performed on tool before the machining operation. The machining performances of the process are to be evaluated in terms of MRR, TWR which are functions of Discharge current, Pulse on-time, Pulse Off-time.Keywords: EDM, cyrogenic, TWR, MRR
Procedia PDF Downloads 44920328 Using Real Truck Tours Feedback for Address Geocoding Correction
Authors: Dalicia Bouallouche, Jean-Baptiste Vioix, Stéphane Millot, Eric Busvelle
Abstract:
When researchers or logistics software developers deal with vehicle routing optimization, they mainly focus on minimizing the total travelled distance or the total time spent in the tours by the trucks, and maximizing the number of visited customers. They assume that the upstream real data given to carry the optimization of a transporter tours is free from errors, like customers’ real constraints, customers’ addresses and their GPS-coordinates. However, in real transporter situations, upstream data is often of bad quality because of address geocoding errors and the irrelevance of received addresses from the EDI (Electronic Data Interchange). In fact, geocoders are not exempt from errors and could give impertinent GPS-coordinates. Also, even with a good geocoding, an inaccurate address can lead to a bad geocoding. For instance, when the geocoder has trouble with geocoding an address, it returns those of the center of the city. As well, an obvious geocoding issue is that the mappings used by the geocoders are not regularly updated. Thus, new buildings could not exist on maps until the next update. Even so, trying to optimize tours with impertinent customers GPS-coordinates, which are the most important and basic input data to take into account for solving a vehicle routing problem, is not really useful and will lead to a bad and incoherent solution tours because the locations of the customers used for the optimization are very different from their real positions. Our work is supported by a logistics software editor Tedies and a transport company Upsilon. We work with Upsilon's truck routes data to carry our experiments. In fact, these trucks are equipped with TOMTOM GPSs that continuously save their tours data (positions, speeds, tachograph-information, etc.). We, then, retrieve these data to extract the real truck routes to work with. The aim of this work is to use the experience of the driver and the feedback of the real truck tours to validate GPS-coordinates of well geocoded addresses, and bring a correction to the badly geocoded addresses. Thereby, when a vehicle makes its tour, for each visited customer, the vehicle might have trouble with finding this customer’s address at most once. In other words, the vehicle would be wrong at most once for each customer’s address. Our method significantly improves the quality of the geocoding. Hence, we achieve to automatically correct an average of 70% of GPS-coordinates of a tour addresses. The rest of the GPS-coordinates are corrected in a manual way by giving the user indications to help him to correct them. This study shows the importance of taking into account the feedback of the trucks to gradually correct address geocoding errors. Indeed, the accuracy of customer’s address and its GPS-coordinates play a major role in tours optimization. Unfortunately, address writing errors are very frequent. This feedback is naturally and usually taken into account by transporters (by asking drivers, calling customers…), to learn about their tours and bring corrections to the upcoming tours. Hence, we develop a method to do a big part of that automatically.Keywords: driver experience feedback, geocoding correction, real truck tours
Procedia PDF Downloads 67020327 Visual Inspection of Road Conditions Using Deep Convolutional Neural Networks
Authors: Christos Theoharatos, Dimitris Tsourounis, Spiros Oikonomou, Andreas Makedonas
Abstract:
This paper focuses on the problem of visually inspecting and recognizing the road conditions in front of moving vehicles, targeting automotive scenarios. The goal of road inspection is to identify whether the road is slippery or not, as well as to detect possible anomalies on the road surface like potholes or body bumps/humps. Our work is based on an artificial intelligence methodology for real-time monitoring of road conditions in autonomous driving scenarios, using state-of-the-art deep convolutional neural network (CNN) techniques. Initially, the road and ego lane are segmented within the field of view of the camera that is integrated into the front part of the vehicle. A novel classification CNN is utilized to identify among plain and slippery road textures (e.g., wet, snow, etc.). Simultaneously, a robust detection CNN identifies severe surface anomalies within the ego lane, such as potholes and speed bumps/humps, within a distance of 5 to 25 meters. The overall methodology is illustrated under the scope of an integrated application (or system), which can be integrated into complete Advanced Driver-Assistance Systems (ADAS) systems that provide a full range of functionalities. The outcome of the proposed techniques present state-of-the-art detection and classification results and real-time performance running on AI accelerator devices like Intel’s Myriad 2/X Vision Processing Unit (VPU).Keywords: deep learning, convolutional neural networks, road condition classification, embedded systems
Procedia PDF Downloads 12520326 Effect of Signal Acquisition Procedure on Imagined Speech Classification Accuracy
Authors: M.R Asghari Bejestani, Gh. R. Mohammad Khani, V.R. Nafisi
Abstract:
Imagined speech recognition is one of the most interesting approaches to BCI development and a lot of works have been done in this area. Many different experiments have been designed and hundreds of combinations of feature extraction methods and classifiers have been examined. Reported classification accuracies range from the chance level to more than 90%. Based on non-stationary nature of brain signals, we have introduced 3 classification modes according to time difference in inter and intra-class samples. The modes can explain the diversity of reported results and predict the range of expected classification accuracies from the brain signal accusation procedure. In this paper, a few samples are illustrated by inspecting results of some previous works.Keywords: brain computer interface, silent talk, imagined speech, classification, signal processing
Procedia PDF Downloads 14720325 Existence and Concentration of Solutions for a Class of Elliptic Partial Differential Equations Involving p-Biharmonic Operator
Authors: Debajyoti Choudhuri, Ratan Kumar Giri, Shesadev Pradhan
Abstract:
The perturbed nonlinear Schrodinger equation involving the p-biharmonic and the p-Laplacian operators involving a real valued parameter and a continuous real valued potential function defined over the N- dimensional Euclidean space has been considered. By the variational technique, an existence result pertaining to a nontrivial solution to this non-linear partial differential equation has been proposed. Further, by the Concentration lemma, the concentration of solutions to the same problem defined on the set consisting of those elements where the potential function vanishes as the real parameter approaches to infinity has been addressed.Keywords: p-Laplacian, p-biharmonic, elliptic PDEs, Concentration lemma, Sobolev space
Procedia PDF Downloads 23120324 A Picture is worth a Billion Bits: Real-Time Image Reconstruction from Dense Binary Pixels
Authors: Tal Remez, Or Litany, Alex Bronstein
Abstract:
The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots), which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.Keywords: binary pixels, maximum likelihood, neural networks, sparse coding
Procedia PDF Downloads 19720323 Distinct Patterns of Resilience Identified Using Smartphone Mobile Experience Sampling Method (M-ESM) and a Dual Model of Mental Health
Authors: Hussain-Abdulah Arjmand, Nikki S. Rickard
Abstract:
The response to stress can be highly heterogenous, and may be influenced by methodological factors. The integrity of data will be optimized by measuring both positive and negative affective responses to an event, by measuring responses in real time as close to the stressful event as possible, and by utilizing data collection methods that do not interfere with naturalistic behaviours. The aim of the current study was to explore short term prototypical responses to major stressor events on outcome measures encompassing both positive and negative indicators of psychological functioning. A novel mobile experience sampling methodology (m-ESM) was utilized to monitor both effective responses to stressors in real time. A smartphone mental health app (‘Moodprism’) which prompts users daily to report both their positive and negative mood, as well as whether any significant event had occurred in the past 24 hours, was developed for this purpose. A sample of 142 participants was recruited as part of the promotion of this app. Participants’ daily reported experience of stressor events, levels of depressive symptoms and positive affect were collected across a 30 day period as they used the app. For each participant, major stressor events were identified on the subjective severity of the event rated by the user. Depression and positive affect ratings were extracted for the three days following the event. Responses to the event were scaled relative to their general reactivity across the remainder of the 30 day period. Participants were first clustered into groups based on initial reactivity and subsequent recovery following a stressor event. This revealed distinct patterns of responding along depressive symptomatology and positive affect. Participants were then grouped based on allocations to clusters in each outcome variable. A highly individualised nature in which participants respond to stressor events, in symptoms of depression and levels of positive affect, was observed. A complete description of the novel profiles identified will be presented at the conference. These findings suggest that real-time measurement of both positive and negative functioning to stressors yields a more complex set of responses than previously observed with retrospective reporting. The use of smartphone technology to measure individualized responding also proved to shed significant insight.Keywords: depression, experience sampling methodology, positive functioning, resilience
Procedia PDF Downloads 23520322 The Design of Intelligent Passenger Organization System for Metro Stations Based on Anylogic
Authors: Cheng Zeng, Xia Luo
Abstract:
Passenger organization has always been an essential part of China's metro operation and management. Facing the massive passenger flow, stations need to improve their intelligence and automation degree by an appropriate integrated system. Based on the existing integrated supervisory control system (ISCS) and simulation software (Anylogic), this paper designs an intelligent passenger organization system (IPOS) for metro stations. Its primary function includes passenger information acquisition, data processing and computing, visualization management, decision recommendations, and decision response based on interlocking equipment. For this purpose, the logical structure and intelligent algorithms employed are particularly devised. Besides, the structure diagram of information acquisition and application module, the application of Anylogic, the case library's function process are all given by this research. Based on the secondary development of Anylogic and existing technologies like video recognition, the IPOS is supposed to improve the response speed and address capacity in the face of emergent passenger flow of metro stations.Keywords: anylogic software, decision-making support system, intellectualization, ISCS, passenger organization
Procedia PDF Downloads 16920321 Detection and Distribution Pattern of Prevelant Genotypes of Hepatitis C in a Tertiary Care Hospital of Western India
Authors: Upasana Bhumbla
Abstract:
Background: Hepatitis C virus is a major cause of chronic hepatitis, which can further lead to cirrhosis of the liver and hepatocellular carcinoma. Worldwide the burden of Hepatitis C infection has become a serious threat to the human race. Hepatitis C virus (HCV) has population-specific genotypes and provides valuable epidemiological and therapeutic information. Genotyping and assessment of viral load in HCV patients are important for planning the therapeutic strategies. The aim of the study is to study the changing trends of prevalence and genotypic distribution of hepatitis C virus in a tertiary care hospital in Western India. Methods: It is a retrospective study; blood samples were collected and tested for anti HCV antibodies by ELISA in Dept. of Microbiology. In seropositive Hepatitis C patients, quantification of HCV-RNA was done by real-time PCR and in HCV-RNA positive samples, genotyping was conducted. Results: A total of 114 patients who were seropositive for Anti HCV were recruited in the study, out of which 79 (69.29%) were HCV-RNA positive. Out of these positive samples, 54 were further subjected to genotype determination using real-time PCR. Genotype was not detected in 24 samples due to low viral load; 30 samples were positive for genotype. Conclusion: Knowledge of genotype is crucial for the management of HCV infection and prediction of prognosis. Patients infected with HCV genotype 1 and 4 will have to receive Interferon and Ribavirin for 48 weeks. Patients with these genotypes show a poor sustained viral response when tested 24 weeks after completion of therapy. On the contrary, patients infected with HCV genotype 2 and 3 are reported to have a better response to therapy.Keywords: hepatocellular, genotype, ribavarin, seropositive
Procedia PDF Downloads 12420320 Developing a Translator Career Path: Based on the Dreyfus Model of Skills Acquisition
Authors: Noha A. Alowedi
Abstract:
This paper proposes a Translator Career Path (TCP) which is based on the Dreyfus Model of Skills Acquisition as the conceptual framework. In this qualitative study, the methodology to collect and analyze the data takes an inductive approach that draws upon the literature to form the criteria for the different steps in the TCP. This path is based on descriptors of expert translator performance and best employees’ practice documented in the literature. Each translator skill will be graded as novice, advanced beginner, competent, proficient, and expert. Consequently, five levels of translator performance are identified in the TCP as five ranks. The first rank is the intern translator, which is equivalent to the novice level; the second rank is the assistant translator, which is equivalent to the advanced beginner level; the third rank is the associate translator, which is equivalent to the competent level; the fourth rank is the translator, which is equivalent to the proficient level; finally, the fifth rank is the expert translator, which is equivalent to the expert level. The main function of this career path is to guide the processes of translator development in translation organizations. Although it is designed primarily for the need of in-house translators’ supervisors, the TCP can be used in academic settings for translation trainers and teachers.Keywords: Dreyfus model, translation organization, translator career path, translator development, translator evaluation, translator promotion
Procedia PDF Downloads 368