Search results for: Projected edge descriptor

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: Deep learning, data mining, gender predication, MOOCs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1294

Authors: Ali K. M. Al-Nasrawi, Uday A. Al-Hamdany, Sarah M. Hamylton, Brian G. Jones, Yasir M. Alyazichi

Abstract:

Surface elevation dynamics have always responded to disturbance regimes. Creating Digital Elevation Models (DEMs) to detect surface dynamics has led to the development of several methods, devices and data clouds. DEMs can provide accurate and quick results with cost efficiency, in comparison to the inherited geomatics survey techniques. Nowadays, remote sensing datasets have become a primary source to create DEMs, including LiDAR point clouds with GIS analytic tools. However, these data need to be tested for error detection and correction. This paper evaluates various DEMs from different data sources over time for Apple Orchard Island, a coastal site in southeastern Australia, in order to detect surface dynamics. Subsequently, 30 chosen locations were examined in the field to test the error of the DEMs surface detection using high resolution global positioning systems (GPSs). Results show significant surface elevation changes on Apple Orchard Island. Accretion occurred on most of the island while surface elevation loss due to erosion is limited to the northern and southern parts. Concurrently, the projected differential correction and validation method aimed to identify errors in the dataset. The resultant DEMs demonstrated a small error ratio (≤ 3%) from the gathered datasets when compared with the fieldwork survey using RTK-GPS. As modern modelling approaches need to become more effective and accurate, applying several tools to create different DEMs on a multi-temporal scale would allow easy predictions in time-cost-frames with more comprehensive coverage and greater accuracy. With a DEM technique for the eco-geomorphic context, such insights about the ecosystem dynamic detection, at such a coastal intertidal system, would be valuable to assess the accuracy of the predicted eco-geomorphic risk for the conservation management sustainability. Demonstrating this framework to evaluate the historical and current anthropogenic and environmental stressors on coastal surface elevation dynamism could be profitably applied worldwide.

Keywords: DEMs, eco-geomorphic-dynamic processes, geospatial information science. Remote sensing, surface elevation changes.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1103

Authors: Ivana Scidà, Francesco Alotto, Anna Osello

Abstract:

Due to the importance given today to innovation, the education sector is evolving thanks digital technologies. Virtual Reality (VR) can be a potential teaching tool offering many advantages in the field of training and education, as it allows to acquire theoretical knowledge and practical skills using an immersive experience in less time than the traditional educational process. These assumptions allow to lay the foundations for a new educational environment, involving and stimulating for students. Starting from the objective of strengthening the innovative teaching offer and the learning processes, the case study of the research concerns the digitalization of MastrLAB, High Quality Laboratory (HQL) belonging to the Department of Structural, Building and Geotechnical Engineering (DISEG) of the Polytechnic of Turin, a center specialized in experimental mechanical tests on traditional and innovative building materials and on the structures made with them. The MastrLAB-VR has been developed, a revolutionary innovative training tool designed with the aim of educating the class in total safety on the techniques of use of machinery, thus reducing the dangers arising from the performance of potentially dangerous activities. The virtual laboratory, dedicated to the students of the Building and Civil Engineering Courses of the Polytechnic of Turin, has been projected to simulate in an absolutely realistic way the experimental approach to the structural tests foreseen in their courses of study: from the tensile tests to the relaxation tests, from the steel qualification tests to the resilience tests on elements at environmental conditions or at characterizing temperatures. The research work proposes a methodology for the virtualization of technical laboratories through the application of Building Information Modelling (BIM), starting from the creation of a digital model. The process includes the creation of an independent application, which with Oculus Rift technology will allow the user to explore the environment and interact with objects through the use of joypads. The application has been tested in prototype way on volunteers, obtaining results related to the acquisition of the educational notions exposed in the experience through a virtual quiz with multiple answers, achieving an overall evaluation report. The results have shown that MastrLAB-VR is suitable for both beginners and experts and will be adopted experimentally for other laboratories of the University departments.

Keywords: Building Information Modelling, digital learning, education, virtual laboratory, virtual reality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 763

Authors: S. V. Kasmir Raja, P. Herbert Raj

Abstract:

The overlay approach has been widely used by many service providers for Traffic Engineering (TE) in large Internet backbones. In the overlay approach, logical connections are set up between edge nodes to form a full mesh virtual network on top of the physical topology. IP routing is then run over the virtual network. Traffic engineering objectives are achieved through carefully routing logical connections over the physical links. Although the overlay approach has been implemented in many operational networks, it has a number of well-known scaling issues. This paper proposes a new approach to achieve traffic engineering without full-mesh overlaying with the help of integrated approach and equal subset split method. Traffic engineering needs to determine the optimal routing of traffic over the existing network infrastructure by efficiently allocating resource in order to optimize traffic performance on an IP network. Even though constraint-based routing [1] of Multi-Protocol Label Switching (MPLS) is developed to address this need, since it is not widely tested or debugged, Internet Service Providers (ISPs) resort to TE methods under Open Shortest Path First (OSPF), which is the most commonly used intra-domain routing protocol. Determining OSPF link weights for optimal network performance is an NP-hard problem. As it is not possible to solve this problem, we present a subset split method to improve the efficiency and performance by minimizing the maximum link utilization in the network via a small number of link weight modifications. The results of this method are compared against results of MPLS architecture [9] and other heuristic methods.

Keywords: Constraint based routing, Link Utilization, Subsetsplit method and Traffic Engineering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1349

Authors: S. M. Rifat, André L. Marchildon, Mark F. Tachie

Abstract:

Experiments were performed to investigate the effects of roughness on the reattachment and redevelopment regions over a 12 mm forward facing step (FFS) in an open channel flow. The experiments were performed over an upstream smooth wall and a smooth FFS, an upstream wall coated with sandpaper 36 grit and a smooth FFS and an upstream rough wall produced from sandpaper 36 grit and a FFS coated with sandpaper 36 grit. To investigate only the wall roughness effects, Reynolds number, Froude number, aspect ratio and blockage ratio were kept constant. Upstream profiles showed reduced streamwise mean velocities close to the rough wall compared to the smooth wall, but the turbulence level was increased by upstream wall roughness. The reattachment length for the smooth-smooth wall experiment was 1.78h; however, when it is replaced with rough-smooth wall the reattachment length decreased to 1.53h. It was observed that the upstream roughness increased the physical size of contours of maximum turbulence level; however, the downstream roughness decreased both the size and magnitude of contours in the vicinity of the leading edge of the step. Quadrant analysis was performed to investigate the dominant Reynolds shear stress contribution in the recirculation region. The Reynolds shear stress and turbulent kinetic energy profiles after the reattachment showed slower recovery compared to the streamwise mean velocity, however all the profiles fairly collapse on their corresponding upstream profiles at x/h = 60. It was concluded that to obtain a complete collapse several more streamwise distances would be required.

Keywords: Forward facing step, open channel, separated and reattached turbulent flows, wall roughness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1610

Authors: Satish Kumar, Arun Kumar Gupta, Pankaj Chandna

Abstract:

In the modern manufacturing systems, the use of thermal cutting techniques using oxyfuel, plasma and laser have become indispensable for the shape forming of high quality complex components; however, the conventional chip removal production techniques still have its widespread space in the manufacturing industry. Both these types of machining operations require the positioning of end effector tool at the edge where the cutting process commences. This repositioning of the cutting tool in every machining operation is repeated several times and is termed as non-productive time or airtime motion. Minimization of this non-productive machining time plays an important role in mass production with high speed machining. As, the tool moves from one region to the other by rapid movement and visits a meticulous region once in the whole operation, hence the non-productive time can be minimized by synchronizing the tool movements. In this work, this problem is being formulated as a general travelling salesman problem (TSP) and a genetic algorithm approach has been applied to solve the same. For improving the efficiency of the algorithm, the GA has been hybridized with a noble special heuristic and simulating annealing (SA). In the present work a novel heuristic in the combination of GA has been developed for synchronization of toolpath movements during repositioning of the tool. A comparative analysis of new Meta heuristic techniques with simple genetic algorithm has been performed. The proposed metaheuristic approach shows better performance than simple genetic algorithm for minimization of nonproductive toolpath length. Also, the results obtained with the help of hybrid simulated annealing genetic algorithm (HSAGA) are also found better than the results using simple genetic algorithm only.

Keywords: Non-productive time, Airtime, 2.5 D milling, Laser cutting, Metaheuristic, Genetic Algorithm, Simulated Annealing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2690

Authors: I. Lucas, N. Schomberg, F-A. Couturier

Abstract:

Most empirical studies have analyzed how liquidity risks faced by individual institutions turn into systemic risk. Recent banking crisis has highlighted the importance of grasping and controlling the systemic risk, and the acceptance by Central Banks to ease their monetary policies for saving default or illiquid banks. This last point shows that banks would pay less attention to liquidity risk which, in turn, can become a new important channel of loss. The financial regulation focuses on the most important and “systemic” banks in the global network. However, to quantify the expected loss associated with liquidity risk, it is worth to analyze sensitivity to this channel for the various elements of the global bank network. A small bank is not considered as potentially systemic; however the interaction of small banks all together can become a systemic element. This paper analyzes the impact of medium and small banks interaction on a set of banks which is considered as the core of the network. The proposed method uses the structure of agent-based model in a two-class environment. In first class, the data from actual balance sheets of 22 large and systemic banks (such as BNP Paribas or Barclays) are collected. In second one, to model a network as closely as possible to actual interbank market, 578 fictitious banks smaller than the ones belonging to first class have been split into two groups of small and medium ones. All banks are active on the European interbank network and have deposit and market activity. A simulation of 12 three month periods representing a midterm time interval three years is projected. In each period, there is a set of behavioral descriptions: repayment of matured loans, liquidation of deposits, income from securities, collection of new deposits, new demands of credit, and securities sale. The last two actions are part of refunding process developed in this paper. To strengthen reliability of proposed model, random parameters dynamics are managed with stochastic equations as rates the variations of which are generated by Vasicek model. The Central Bank is considered as the lender of last resort which allows banks to borrow at REPO rate and some ejection conditions of banks from the system are introduced.

Liquidity crunch due to exogenous crisis is simulated in the first class and the loss impact on other bank classes is analyzed though aggregate values representing the aggregate of loans and/or the aggregate of borrowing between classes. It is mainly shown that the three groups of European interbank network do not have the same response, and that intermediate banks are the most sensitive to liquidity risk.

Keywords: Systemic Risk, Financial Contagion, Liquidity Risk, Interbank Market, Network Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1973

Authors: Ashiquer Rahman

Abstract:

The cutting edge knowledge mediation system called ‘ePLANETe’ provides a framework for building knowledge, tools, and methods for education, research, and sustainable practices, as well as the deliberative assessment support for Higher Education, Research Institutions, and elsewhere e.g., the collaborative learning and research on sustainability and biodiversity issues of territorial development sectors. The paper is to present the analytical perspective of the ‘ePLANETe’ concept and functionalities as an experimental platform for contributing to sustainability assessment. Now the ‘ePLANETe’ can be seen as experimentation of the challenges of “ICT for Green”. The digital technologies of ‘ePLANETe’ are exploited (i) to facilitate collaborative research, learning tools, and knowledge for sustainability challenges, and (ii) as deliberation support tools in pursuing of sustainability performance and practices in territorial governance, public policy, and business strategy, as well as in the higher education sectors itself. The paper investigates the dealing capacity of qualitative and quantitative assessment of agriculture sustainability through the stakeholder-based integrated assessment. Specifically, this paper focuses on integrating system methodologies with Deliberation Support Tools (DST) and INTEGRAAL method for collective assessment and decision-making in implementing regional plans. The report aims to identify the effective knowledge and tools to enable deliberations methodologies regarding practices on the sustainability of agriculture and biodiversity issues, societal responsibilities, and regional planning, concentrating on the question: “How to effectively mobilize resources (knowledge, tools, and methods) from different sources and at different scales regarding on agriculture and biodiversity issues to address sustainability challenges” that will create the scope for qualitative and quantitative assessments of sustainability as a new landmark of the agriculture sector.

Keywords: Biodiversity, Deliberation Support Tools, INTEGRAAL, stakeholder.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 180

Authors: K. S. Sivakumaran, T. Thanga, B. Halabieh

Abstract:

The end panels of a large rectangular industrial duct, which experience significant internal pressures, also experience considerable transverse shear due to transfer of gravity loads to the supports. The current design practice of such thin plate panels for shear load is based on methods used for the design of plate girder webs. The structural arrangements, the loadings and the resulting behavior associated with the industrial duct end panels are, however, significantly different from those of the web of a plate girder. The large aspect ratio of the end panels gives rise to multiple bands of tension fields, whereas the plate girder web design is based on one tension field. In addition to shear, the industrial end panels are subjected to internal pressure which in turn produces significant membrane action. This paper reports a study which was undertaken to review the current industrial analysis and design methods and to propose a comprehensive method of designing industrial duct end panels for shear resistance. In this investigation, a nonlinear finite element model was developed to simulate the behavior of industrial duct end panel, along with the associated edge stiffeners, subjected to transverse shear and internal pressures. The model considered the geometric imperfections and constitutive relations for steels. Six scale independent dimensionless parameters that govern the behavior of such end panel were identified and were then used in a parametric study. It was concluded that the plate slenderness dominates the shear strength of stockier end panels, and whereas, both the plate slenderness and the aspect ratio influence the shear strength of slender end panels. Based on these studies, this paper proposes design aids for estimating the shear strength of rectangular duct end panels.

Keywords: Thin plate, transverse shear, tension field, finite element analysis, parametric study, design.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1921

Authors: Guillaume Mullier, Jean François Chatelain

Abstract:

Carbon Fiber Reinforced Plastics (CFRPs) are widely used for advanced applications, in particular in aerospace, automotive and wind energy industries. Once cured to near net shape, CFRP parts need several finishing operations such as trimming, milling or drilling in order to accommodate fastening hardware and meeting the final dimensions. The present research aims to study the effect of the cutting temperature in trimming on the mechanical strength of high performance CFRP laminates used for aeronautics applications. The cutting temperature is of great importance when dealing with trimming of CFRP. Temperatures higher than the glass-transition temperature (Tg) of the resin matrix are highly undesirable: they cause degradation of the matrix in the trimmed edges area, which can severely affect the mechanical performance of the entire component. In this study, a 9.50mm diameter CVD diamond coated carbide tool with six flutes was used to trim 24-plies CFRP laminates. A 300m/min cutting speed and 1140mm/min feed rate were used in the experiments. The tool was heated prior to trimming using a blowtorch, for temperatures ranging from 20°C to 300°C. The temperature at the cutting edge was measured using embedded KType thermocouples. Samples trimmed for different cutting temperatures, below and above Tg, were mechanically tested using three-points bending short-beam loading configurations. New cutting tools as well as worn cutting tools were utilized for the experiments. The experiments with the new tools could not prove any correlation between the length of cut, the cutting temperature and the mechanical performance. Thus mechanical strength was constant, regardless of the cutting temperature. However, for worn tools, producing a cutting temperature rising up to 450°C, thermal damage of the resin was observed. The mechanical tests showed a reduced mean resistance in short beam configuration, while the resistance in three point bending decreases with increase of the cutting temperature.

Keywords: Composites, Trimming, Thermal Damage, Surface Quality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1747

Authors: Murtuza Ali Lakhani, Michelle Marquard

Abstract:

From an organizational perspective, leaders are a variation of the same talent pool in that they all score a larger than average value on the bell curve that maps leadership behaviors and characteristics, namely competence, vision, communication, confidence, cultural sensibility, stewardship, empowerment, authenticity, reinforcement, and creativity. The question that remains unanswered and essentially unresolved is how to explain the irony that leaders are so much alike yet their organizations diverge so noticeably in their ability to innovate. Leadership intersects with innovation at the point where human interactions get exceedingly complex and where certain paradoxical forces cohabit: conflict with conciliation, sovereignty with interdependence, and imagination with realism. Rather than accepting that leadership is without context, we argue that leaders are specialists of their domain and that those effective at leading for innovation are distinct within the broader pool of leaders. Keeping in view the extensive literature on leadership and innovation, we carried out a quantitative study with data collected over a five-year period involving 240 participants from across five dissimilar companies based in the United States. We found that while innovation and leadership are, in general, strongly interrelated (r = .89, p = 0.0), there are five qualities that set leaders apart on innovation. These qualities include a large radius of trust, a restless curiosity with a low need for acceptance, an honest sense of self and other, a sense for knowledge and creativity as the yin and yang of innovation, and an ability to use multiple senses in the engagement with followers. When these particular behaviors and characteristics are present in leaders, organizations out-innovate their rivals by a margin of 29.3 per cent to gain an unassailable edge in a business environment that is regularly disruptive. A strategic outcome of this study is a psychometric scale named iLeadership, proposed with the underlying evidence, limitations, and potential for leadership and innovation in organizations.c

Keywords: Innovation, leadership, ileadership, stewardship, communication, empowerment, creativity, vision, influence, emotional connection, group membership, sense of community, knowledge creation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2565

Authors: C. Chahin, M. C. Hsu, Y. H. Lin, C. Y. Huang

Abstract:

Electronics Products that achieve high levels of integrated communications, computing and entertainment, multimedia features in small, stylish and robust new form factors are winning in the market place. Due to the high costs that an industry may undergo and how a high yield is directly proportional to high profits, IC (Integrated Circuit) manufacturers struggle to maximize yield, but today-s customers demand miniaturization, low costs, high performance and excellent reliability making the yield maximization a never ending research of an enhanced assembly process. With factors such as minimum tolerances, tighter parameter variations a systematic approach is needed in order to predict the assembly process. In order to evaluate the quality of upcoming circuits, yield models are used which not only predict manufacturing costs but also provide vital information in order to ease the process of correction when the yields fall below expectations. For an IC manufacturer to obtain higher assembly yields all factors such as boards, placement, components, the material from which the components are made of and processes must be taken into consideration. Effective placement yield depends heavily on machine accuracy and the vision of the system which needs the ability to recognize the features on the board and component to place the device accurately on the pads and bumps of the PCB. There are currently two methods for accurate positioning, using the edge of the package and using solder ball locations also called footprints. The only assumption that a yield model makes is that all boards and devices are completely functional. This paper will focus on the Monte Carlo method which consists in a class of computational algorithms (information processed algorithms) which depends on repeated random samplings in order to compute the results. This method utilized in order to recreate the simulation of placement and assembly processes within a production line.

Keywords: Monte Carlo simulation, placement yield, PCBcharacterization, electronics assembly

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2133

Authors: Chiung-Hui Chen

Abstract:

Traditional service channel is losing its edge due to emerging service technology. To establish interaction with the clients, the service industry is using effective mechanism to give clients direct access to services with emerging technologies. Thus, as service science receives attention, special and unique consumption pattern evolves; henceforth, leading to new market mechanism and influencing attitudes toward life and consumption patterns. The market demand for customized services is thus valued due to the emphasis of personal value, and is gradually changing the demand and supply relationship in the traditional industry. In respect of interior design service, in the process of traditional interior design, a designer converts to a concrete form the concept generated from the ideas and needs dictated by a user (client), by using his/her professional knowledge and drawing tool. The final product is generated through iterations of communication and modification, which is a very time-consuming process. Although this process has been accelerated with the help of computer graphics software today, repeated discussions and confirmations with users are still required to complete the task. In consideration of what is addressed above a space user’s life model is analyzed with visualization technique to create an interaction system modeled after interior design knowledge. The space user document intuitively personal life experience in a model requirement chart, allowing a researcher to analyze interrelation between analysis documents, identify the logic and the substance of data conversion. The repeated data which is documented are then transformed into design information for reuse and sharing. A professional interior designer may sort out the correlation among user’s preference, life pattern and design specification, thus deciding the critical design elements in the process of service design.

Keywords: Information Design, Life Model-Based, Aesthetic Computing, Communication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1676

Authors: Jasna Prester, Ivana Rašić Bakarić, Božidar Matijević

Abstract:

Innovations not only contribute to competitiveness of the company but have also positive effects on revenues. On average, product innovations account to 14 percent of companies’ sales. Innovation management has substantially changed during the last decade, because of growing reliance on external partners. As a consequence, a new task for purchasing arises, as firms need to understand which suppliers actually do have high potential contributing to the innovativeness of the firm and which do not. Proper organization of the purchasing function is important since for the majority of manufacturing companies deal with substantial material costs which pass through the purchasing function. In the past the purchasing function was largely seen as a transaction-oriented, clerical function but today purchasing is the intermediate with supply chain partners contributing to innovations, be it product or process innovations. Therefore, purchasing function has to be organized differently to enable firm innovation potential. However, innovations are inherently risky. There are behavioral risk (that some partner will take advantage of the other party), technological risk in terms of complexity of products and processes of manufacturing and incoming materials and finally market risks, which in fact judge the value of the innovation. These risks are investigated in this work. Specifically, technological risks which deal with complexity of the products, and processes will be investigated more thoroughly. Buying components or such high edge technologies necessities careful investigation of technical features and therefore is usually conducted by a team of experts. Therefore it is hypothesized that higher the technological risk, higher will be the centralization of the purchasing function as an interface with other supply chain members. Main contribution of this research lies is in the fact that analysis was performed on a large data set of 1493 companies, from 25 countries collected in the GMRG 4 survey. Most analyses of purchasing function are done by case study analysis of innovative firms. Therefore this study contributes with empirical evaluations that can be generalized.

Keywords: Purchasing function organization, innovation, technological risk, GMRG 4 survey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3682

Authors: Mathias U. Bonet, Pericles Pilidis, Georgios Doulgeris

Abstract:

A gas turbine-powered cruise Liner is scheduled to transport pilgrim passengers from Lagos-Nigeria to the Islamic port city of Jeddah in Saudi Arabia. Since the gas turbine is an air breathing machine, changes in the density and/or mass flow at the compressor inlet due to an encounter with variations in weather conditions induce negative effects on the performance of the power plant during the voyage. In practice, all deviations from the reference atmospheric conditions of 15 ^oC and 1.103 bar tend to affect the power output and other thermodynamic parameters of the gas turbine cycle. Therefore, this paper seeks to evaluate how a simple cycle marine gas turbine power plant would react under a variety of scenarios that may be encountered during a voyage as the ship sails across the Atlantic Ocean and the Mediterranean Sea before arriving at its designated port of discharge. It is also an assessment that focuses on the effect of varying aerodynamic and hydrodynamic conditions which deteriorate the efficient operation of the propulsion system due to an increase in resistance that results from some projected levels of the ship hull fouling. The investigated passenger ship is designed to run at a service speed of 22 knots and cover a distance of 5787 nautical miles. The performance evaluation consists of three separate voyages that cover a variety of weather conditions in winter, spring and summer seasons. Real-time daily temperatures and the sea states for the selected transit route were obtained and used to simulate the voyage under the aforementioned operating conditions. Changes in engine firing temperature, power output as well as the total fuel consumed per voyage including other performance variables were separately predicted under both calm and adverse weather conditions. The collated data were obtained online from the UK Meteorological Office as well as the UK Hydrographic Office websites, while adopting the Beaufort scale for determining the magnitude of sea waves resulting from rough weather situations. The simulation of the gas turbine performance and voyage analysis was effected through the use of an integrated Cranfield-University-developed computer code known as ‘Turbomatch’ and ‘Poseidon’. It is a project that is aimed at developing a method for predicting the off design behavior of the marine gas turbine when installed and operated as the main prime mover for both propulsion and powering of all other auxiliary services onboard a passenger cruise liner. Furthermore, it is a techno-economic and environmental assessment that seeks to enable the forecast of the marine gas turbine part and full load performance as it relates to the fuel requirement for a complete voyage.

Keywords:

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 809

Authors: N. N. Mosola, S. J. Molete, L. S. Masoebe, M. Letsae

Abstract:

Hand gesture recognition is a technique used to locate, detect, and recognize a hand gesture. Detection and recognition are concepts of Artificial Intelligence (AI). AI concepts are applicable in Human Computer Interaction (HCI), Expert systems (ES), etc. Hand gesture recognition can be used in sign language interpretation. Sign language is a visual communication tool. This tool is used mostly by deaf societies and those with speech disorder. Communication barriers exist when societies with speech disorder interact with others. This research aims to build a hand recognition system for Lesotho’s Sesotho and English language interpretation. The system will help to bridge the communication problems encountered by the mentioned societies. The system has various processing modules. The modules consist of a hand detection engine, image processing engine, feature extraction, and sign recognition. Detection is a process of identifying an object. The proposed system uses Canny pruning Haar and Haarcascade detection algorithms. Canny pruning implements the Canny edge detection. This is an optimal image processing algorithm. It is used to detect edges of an object. The system employs a skin detection algorithm. The skin detection performs background subtraction, computes the convex hull, and the centroid to assist in the detection process. Recognition is a process of gesture classification. Template matching classifies each hand gesture in real-time. The system was tested using various experiments. The results obtained show that time, distance, and light are factors that affect the rate of detection and ultimately recognition. Detection rate is directly proportional to the distance of the hand from the camera. Different lighting conditions were considered. The more the light intensity, the faster the detection rate. Based on the results obtained from this research, the applied methodologies are efficient and provide a plausible solution towards a light-weight, inexpensive system which can be used for sign language interpretation.

Keywords: Canny pruning, hand recognition, machine learning, skin tracking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1235

Authors: A.H.Javadi, Sh.Mirdamadi, M.A.Faghisani, S.Shakhesi

Abstract:

Nanostructured materials have attracted many researchers due to their outstanding mechanical and physical properties. For example, carbon nanotubes (CNTs) or carbon nanofibres (CNFs) are considered to be attractive reinforcement materials for light weight and high strength metal matrix composites. These composites are being projected for use in structural applications for their high specific strength as well as functional materials for their exciting thermal and electrical characteristics. The critical issues of CNT-reinforced MMCs include processing techniques, nanotube dispersion, interface, strengthening mechanisms and mechanical properties. One of the major obstacles to the effective use of carbon nanotubes as reinforcements in metal matrix composites is their agglomeration and poor distribution/dispersion within the metallic matrix. In order to tap into the advantages of the properties of CNTs (or CNFs) in composites, the high dispersion of CNTs (or CNFs) and strong interfacial bonding are the key issues which are still challenging. Processing techniques used for synthesis of the composites have been studied with an objective to achieve homogeneous distribution of carbon nanotubes in the matrix. Modified mechanical alloying (ball milling) techniques have emerged as promising routes for the fabrication of carbon nanotube (CNT) reinforced metal matrix composites. In order to obtain a homogeneous product, good control of the milling process, in particular control of the ball movement, is essential. The control of the ball motion during the milling leads to a reduction in grinding energy and a more homogeneous product. Also, the critical inner diameter of the milling container at a particular rotational speed can be calculated. In the present work, we use conventional and modified mechanical alloying to generate a homogenous distribution of 2 wt. % CNT within Al powders. 99% purity Aluminium powder (Acros, 200mesh) was used along with two different types of multiwall carbon nanotube (MWCNTs) having different aspect ratios to produce Al-CNT composites. The composite powders were processed into bulk material by compaction, and sintering using a cylindrical compaction and tube furnace. Field Emission Scanning electron microscopy (FESEM), X-Ray diffraction (XRD), Raman spectroscopy and Vickers macro hardness tester were used to evaluate CNT dispersion, powder morphology, CNT damage, phase analysis, mechanical properties and crystal size determination. Despite the success of ball milling in dispersing CNTs in Al powder, it is often accompanied with considerable strain hardening of the Al powder, which may have implications on the final properties of the composite. The results show that particle size and morphology vary with milling time. Also, by using the mixing process and sonication before mechanical alloying and modified ball mill, dispersion of the CNTs in Al matrix improves.

Keywords: multiwall carbon nanotube, Aluminum matrixcomposite, dispersion, mechanical alloying, sintering

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2282

Authors: Jay Patel

Abstract:

This research is about investigating the ‘image’ of the city, and asks whether this ‘image’ holds any significance that can be changed. Kevin Lynch in the book ‘The Image of the City’ develops a framework that breaks down the city’s image into five physical elements. These elements (Paths, Edge, Nodes, Districts, and Landmarks), according to Lynch assess the legibility of the urbanscapes, that emerged from his perception-based study in three different cities (New Jersey, Los Angeles, and Boston) in the USA. The aim of this research is to investigate whether Lynch’s framework can be applied within an Indian context or not. If so, what are the possibilities and whether the imageability of Indian cities can be depicted through the Lynch’s physical elements or it demands an extension to the framework by either adding or subtracting a physical attribute. For this research project, the walled city of Jaipur was selected, as it is considered one of the futuristic designed cities of all time in India. The other significant reason for choosing Jaipur was that it is a historically planned city with solid historical, touristic and local importance; allowing an opportunity to understand the application of Lynch's elements to the city's image. In other words, it provides an opportunity to examine how the disadvantages of a city's implicit program (its relics of bygone eras) can be converted into assets by improving the imageability of the city. To obtain data, a structured semi-open ended interview method was chosen. The reason for selecting this method explicitly was to gain qualitative data from the users rather than collecting quantitative data from closed-ended questions. This allowed in-depth understanding and applicability of Kevin Lynch’s framework while assessing what needs to be added. The interviews were conducted in Jaipur that yielded varied inferences that were different from the expected learning outcomes, highlighting the need for extension on Lynch’s physical elements to achieve city’s image. Whilst analyzing the data, there were few attributes found that defined the image of Jaipur. These were categorized into two: a Physical aspect (streets and arcade entities, natural features, temples and temporary/informal activities) and Associational aspects (History, culture and tradition, medium of help in wayfinding, and intangible aspects).

Keywords: Imageability, Kevin Lynch, People’s Perception, associational aspects, physical aspects.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 342

Authors: Alan Crowle, Philpp Thies

Abstract:

s the floating offshore wind turbine industry continues to develop and grow, the capabilities of established port facilities need to be assessed as to their ability to support the expanding construction and installation requirements. This paper assesses current infrastructure requirements and projected changes to port facilities that may be required to support the floating offshore wind industry. Understanding the infrastructure needs of the floating offshore renewable industry will help to identify the port-related requirements. Floating offshore wind turbines can be installed further out to sea and in deeper waters than traditional fixed offshore wind arrays, meaning it can take advantage of stronger winds. Separate ports are required for substructure construction, fit-out of the turbines, moorings, subsea cables and maintenance. Large areas are required for the laydown of mooring equipment, inter array cables, turbine blades and nacelles. The capabilities of established port facilities to support floating wind farms are assessed by evaluation of size of substructures, height of wind turbine with regards to the cranes for fitting of blades, distance to offshore site and offshore installation vessel characteristics. The paper will discuss the advantages and disadvantages of using large land based cranes, inshore floating crane vessels or offshore crane vessels at the fit-out port for the installation of the turbine. Water depths requirements for import of materials and export of the completed structures will be considered. There are additional costs associated with any emerging technology. However, part of the popularity of Floating Offshore Wind Turbines stems from the cost savings against permanent structures like fixed wind turbines. Floating Offshore Wind Turbine developers can benefit from lighter, more cost effective equipment which can be assembled in port and towed to site rather than relying on large, expensive installation vessels to transport and erect fixed bottom turbines. The ability to assemble Floating Offshore Wind Turbines equipment on shore means minimising highly weather dependent operations like offshore heavy lifts and assembly, saving time and costs and reducing safety risks for offshore workers. Maintenance might take place in safer onshore conditions for barges and semi submersibles. Offshore renewables, such as floating wind, can take advantage of this wealth of experience, while oil and gas operators can deploy this experience at the same time as entering the renewables space. The floating offshore wind industry is in the early stages of development and port facilities are required for substructure fabrication, turbine manufacture, turbine construction and maintenance support. The paper discusses the potential floating wind substructures as this provides a snapshot of the requirements at the present time, and potential technological developments required for commercial development. Scaling effects of demonstration-scale projects will be addressed; however the primary focus will be on commercial-scale (30+ units) device floating wind energy farms.

Keywords: Floating offshore wind turbine, port logistics, installation, construction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 423

Authors: Qing Liu, Jean-Fabien Capsal, Claude Richard

Abstract:

In this current contribution, authors are dedicated to investigate influence of the crystal lamellae orientation on electromechanical behaviors of relaxor ferroelectric Poly (vinylidene fluoride –trifluoroethylene -chlorotrifluoroethylene) (P(VDF-TrFE-CTFE)) films by control of polymer microstructure, aiming to picture the full map of structure-property relationship. In order to define their crystal orientation films, terpolymer films were fabricated by solution-casting, stretching and hot-pressing process. Differential scanning calorimetry, impedance analyzer, and tensile strength techniques were employed to characterize crystallographic parameters, dielectric permittivity, and elastic Young’s modulus respectively. In addition, large electrical induced out-of-plane electrostrictive strain was obtained by cantilever beam mode. Consequently, as-casted pristine films exhibited surprisingly high electrostrictive strain 0.1774% due to considerably small value of elastic Young’s modulus although relatively low dielectric permittivity. Such reasons contributed to large mechanical elastic energy density. Instead, due to 2 folds increase of elastic Young’s modulus and less than 50% augmentation of dielectric constant, fullycrystallized film showed weak electrostrictive behavior and mechanical energy density as well. And subjected to mechanical stretching process, Film C exhibited stronger dielectric constant and out-performed electrostrictive strain over Film B because edge-on crystal lamellae orientation induced by uniaxially mechanical stretch. Hot-press films were compared in term of cooling rate. Rather large electrostrictive strain of 0.2788% for hot-pressed Film D in quenching process was observed although its dielectric permittivity equivalent to that of pristine as-casted Film A, showing highest mechanical elastic energy density value of 359.5 J/m3. In hot-press cooling process, dielectric permittivity of Film E saw values at 48.8 concomitant with ca.100% increase of Young’s modulus. Films with intermediate mechanical energy density were obtained.

Keywords: Crystal orientation, electrostrictive strain, mechanical energy density, permittivity, relaxor ferroelectric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1624

Authors: Peter Clutterbuck, Terry Rowlands, Owen Seamons

Abstract:

In this paper we describe one critical research program within a complex, ongoing multi-year project (2010 to 2014 inclusive) with the overall goal to improve the learning outcomes for first year undergraduate commerce/business students within an Information Systems (IS) subject with very large enrolment. The single research program described in this paper is the analysis of student attitudes and decision making in relation to the availability of formative assessment feedback via Web-based real time conferencing and document exchange software (Adobe Connect). The formative assessment feedback between teaching staff and students is in respect of an authentic problem-based, team-completed assignment. The analysis of student attitudes and decision making is investigated via both qualitative (firstly) and quantitative (secondly) application of the Theory of Planned Behavior (TPB) with a two statistically-significant and separate trial samples of the enrolled students. The initial qualitative TPB investigation revealed that perceived self-efficacy, improved time-management, and lecturer-student relationship building were the major factors in shaping an overall favorable student attitude to online feedback, whilst some students expressed valid concerns with perceived control limitations identified within the online feedback protocols. The subsequent quantitative TPB investigation then confirmed that attitude towards usage, subjective norms surrounding usage, and perceived behavioral control of usage were all significant in shaping student intention to use the online feedback protocol, with these three variables explaining 63 percent of the variance in the behavioral intention to use the online feedback protocol. The identification in this research of perceived behavioral control as a significant determinant in student usage of a specific technology component within a virtual learning environment (VLE) suggests that VLEs could now be viewed not as a single, atomic entity, but as a spectrum of technology offerings ranging from the mature and simple (e.g., email, Web downloads) to the cutting-edge and challenging (e.g., Web conferencing and real-time document exchange). That is, that all VLEs should not be considered the same. The results of this research suggest that tertiary students have the technological sophistication to assess a VLE in this more selective manner.

Keywords: Formative assessment feedback, virtual learning environment, theory of planned behavior, perceived behavioral control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2043

Authors: Srinivas Bathini, Duraichelvan Raju, Simona Badilescu, Muthukumaran Packirisamy

Abstract:

A bio-sensing method, based on the plasmonic property of gold nano-islands, has been developed for detection of exosomes in a clinical setting. The position of the gold plasmon band in the UV-Visible spectrum depends on the size and shape of gold nanoparticles as well as on the surrounding environment. By adsorbing various chemical entities, or binding them, the gold plasmon band will shift toward longer wavelengths and the shift is proportional to the concentration. Exosomes transport cargoes of molecules and genetic materials to proximal and distal cells. Presently, the standard method for their isolation and quantification from body fluids is by ultracentrifugation, not a practical method to be implemented in a clinical setting. Thus, a versatile and cutting-edge platform is required to selectively detect and isolate exosomes for further analysis at clinical level. The new sensing protocol, instead of antibodies, makes use of a specially synthesized polypeptide (Vn96), to capture and quantify the exosomes from different media, by binding the heat shock proteins from exosomes. The protocol has been established and optimized by using a glass substrate, in order to facilitate the next stage, namely the transfer of the protocol to a microfluidic environment. After each step of the protocol, the UV-Vis spectrum was recorded and the position of gold Localized Surface Plasmon Resonance (LSPR) band was measured. The sensing process was modelled, taking into account the characteristics of the nano-island structure, prepared by thermal convection and annealing. The optimal molar ratios of the most important chemical entities, involved in the detection of exosomes were calculated as well. Indeed, it was found that the results of the sensing process depend on the two major steps: the molar ratios of streptavidin to biotin-PEG-Vn96 and, the final step, the capture of exosomes by the biotin-PEG-Vn96 complex. The microfluidic device designed for sensing of exosomes consists of a glass substrate, sealed by a PDMS layer that contains the channel and a collecting chamber. In the device, the solutions of linker, cross-linker, etc., are pumped over the gold nano-islands and an Ocean Optics spectrometer is used to measure the position of the Au plasmon band at each step of the sensing. The experiments have shown that the shift of the Au LSPR band is proportional to the concentration of exosomes and, thereby, exosomes can be accurately quantified. An important advantage of the method is the ability to discriminate between exosomes having different origins.

Keywords: Exosomes, gold nano-islands, microfluidics, plasmonic biosensing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1400

Authors: Jaeyoung Lee

Abstract:

Autonomous driving systems require high reliability to provide people with a safe and comfortable driving experience. However, despite the development of a number of vehicle sensors, it is difficult to always provide high perceived performance in driving environments that vary from time to season. The image segmentation method using deep learning, which has recently evolved rapidly, provides high recognition performance in various road environments stably. However, since the system controls a vehicle in real time, a highly complex deep learning network cannot be used due to time and memory constraints. Moreover, efficient networks are optimized for GPU environments, which degrade performance in embedded processor environments equipped simple hardware accelerators. In this paper, a semantic segmentation network, matrix multiplication accelerator network (MMANet), optimized for matrix multiplication accelerator (MMA) on Texas instrument digital signal processors (TI DSP) is proposed to improve the recognition performance of autonomous driving system. The proposed method is designed to maximize the number of layers that can be performed in a limited time to provide reliable driving environment information in real time. First, the number of channels in the activation map is fixed to fit the structure of MMA. By increasing the number of parallel branches, the lack of information caused by fixing the number of channels is resolved. Second, an efficient convolution is selected depending on the size of the activation. Since MMA is a fixed, it may be more efficient for normal convolution than depthwise separable convolution depending on memory access overhead. Thus, a convolution type is decided according to output stride to increase network depth. In addition, memory access time is minimized by processing operations only in L3 cache. Lastly, reliable contexts are extracted using the extended atrous spatial pyramid pooling (ASPP). The suggested method gets stable features from an extended path by increasing the kernel size and accessing consecutive data. In addition, it consists of two ASPPs to obtain high quality contexts using the restored shape without global average pooling paths since the layer uses MMA as a simple adder. To verify the proposed method, an experiment is conducted using perfsim, a timing simulator, and the Cityscapes validation sets. The proposed network can process an image with 640 x 480 resolution for 6.67 ms, so six cameras can be used to identify the surroundings of the vehicle as 20 frame per second (FPS). In addition, it achieves 73.1% mean intersection over union (mIoU) which is the highest recognition rate among embedded networks on the Cityscapes validation set.

Keywords: Edge network, embedded network, MMA, matrix multiplication accelerator and semantic segmentation network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 410

Authors: W. S. Barber, S. L. King

Abstract:

This paper is a qualitative case study analysis of the development of a fully online learning community of graduate students through arts-based community building activities. With increasing numbers and types of online learning spaces, it is incumbent upon educators to continue to push the edge of what best practices look like in digital learning environments. In digital learning spaces, instructors can no longer be seen as purveyors of content knowledge to be examined at the end of a set course by a final test or exam. The rapid and fluid dissemination of information via Web 3.0 demands that we reshape our approach to teaching and learning, from one that is content-focused to one that is process-driven. Rather than having instructors as formal leaders, today’s digital learning environments require us to share expertise, as it is the collective experiences and knowledge of all students together with the instructors that help to create a very different kind of learning community. This paper focuses on innovations pursued in a 36 hour 12 week graduate course in higher education entitled “Critical and Reflective Practice”. The authors chronicle their journey to developing a fully online learning community (FOLC) by emphasizing the elements of social, cognitive, emotional and digital spaces that form a moving interplay through the community. In this way, students embrace anywhere anytime learning and often take the learning, as well as the relationships they build and skills they acquire, beyond the digital class into real world situations. We argue that in order to increase student online engagement, pedagogical approaches need to stem from two primary elements, both creativity and critical reflection, that are essential pillars upon which instructors can co-design learning environments with students. The theoretical framework for the paper is based on the interaction and interdependence of Creativity, Intuition, Critical Reflection, Social Constructivism and FOLCs. By leveraging students’ embedded familiarity with a wide variety of technologies, this case study of a graduate level course on critical reflection in education, examines how relationships, quality of work produced, and student engagement can improve by using creative and imaginative pedagogical strategies. The authors examine their professional pedagogical strategies through the lens that the teacher acts as facilitator, guide and co-designer. In a world where students can easily search for and organize information as self-directed processes, creativity and connection can at times be lost in the digitized course environment. The paper concludes by posing further questions as to how institutions of higher education may be challenged to restructure their credit granting courses into more flexible modules, and how students need to be considered an important part of assessment and evaluation strategies. By introducing creativity and critical reflection as central features of the digital learning spaces, notions of best practices in digital teaching and learning emerge.

Keywords: Online, pedagogy, learning, communities.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1236

Authors: Sara S. Fouad, Omneya Messallam

Abstract:

Egypt has countless prestigious buildings and diversity of cultural heritage which are located in many cities. Most of the researchers, archaeologists, stakeholders and governmental bodies are paying more attention to the big cities such as Cairo and Alexandria, due to the country’s centralization nature. However, there are other historic cities that are grossly neglected and in need of emergency conservation. For instance, Port Said which is a former colonial city that was established in nineteenth century located at the edge of the northeast Egyptian coast between the Mediterranean Sea and the Suez Canal. This city is chosen because it presents one of the important Egyptian archaeological sites that archive Egyptian architecture of the 19^th and 20^th centuries. The historic urban fabric is divided into three main districts; the Arab, the European (Al-Afrang), and Port Fouad. The European district is selected to be the research case study as it has culture diversity, significant buildings, and includes the largest number of the listed heritage buildings in Port Said. Based on questionnaires and interviews, since 2003 several initiative trials have been taken by Alliance Francaise, the National Organization for Urban Harmony (NOUH), some Non-Governmental Organizations (NGOs), and few number of community residents to highlight the important city legacy and protect it from being demolished. Unfortunately, the limitation of their participation in decision-making policies is considered a crucial threat facing sustainable heritage conservation. Therefore, encouraging the local community to participate in their architecture heritage conservation would create a self-confident one, capable of making decisions for the city’s future development. This paper aims to investigate the role of the local inhabitants in protecting their buildings heritage through listing the community level of participations twice (2012 and 2018) in preserving their heritage based on the ladder citizen participation approach. Also, it is to encourage community participation in order to promote city architecture conservation, heritage management, and sustainable development. The methodology followed in this empirical research involves using several data assembly methods such as structural observations, questionnaires, interviews, and mental mapping. The questionnaire was distributed among 92 local inhabitants aged 18-60 years. However, the outset of this research at the beginning demonstrated the majority negative attitude, motivation, and confidence of the local inhabitants’ role to safeguard their architectural heritage. Over time, there was a change in the negative attitudes. Therefore, raising public awareness and encouraging community participation by providing them with a real opportunity to take part in the decision-making. This may lead to a positive relationship between the community residents and the built heritage, which is essential for promoting its preservation and sustainable development.

Keywords: Al-Afrang/Port Said, community participation, heritage conservation, ladder of citizen participation, NGOs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1417

Authors: Payam Mousavi, Andrew L. Stewart, Huiwen You, Aryeh F. G. Fayerman

Abstract:

We present a decision-support tool to assist an operator in the detection and tracking of a suspect vehicle traveling to an unknown target destination. Multiple data sources, such as traffic cameras, traffic information, weather, etc., are integrated and processed in real-time to infer a suspect’s intended destination chosen from a list of pre-determined high-value targets. Previously, we presented our work in the detection and tracking of vehicles using traffic and airborne cameras. Here, we focus on the fusion and processing of that information to predict a suspect’s behavior. The network of cameras is represented by a directional graph, where the edges correspond to direct road connections between the nodes and the edge weights are proportional to the average time it takes to travel from one node to another. For our experiments, we construct our graph based on the greater Los Angeles subset of the Caltrans’s “Performance Measurement System” (PeMS) dataset. We propose a Bayesian approach where a posterior probability for each target is continuously updated based on detections of the suspect in the live video feeds. Additionally, we introduce the concept of ‘soft interventions’, inspired by the field of Causal Inference. Soft interventions are herein defined as interventions that do not immediately interfere with the suspect’s movements; rather, a soft intervention may induce the suspect into making a new decision, ultimately making their intent more transparent. For example, a soft intervention could be temporarily closing a road a few blocks from the suspect’s current location, which may require the suspect to change their current course. The objective of these interventions is to gain the maximum amount of information about the suspect’s intent in the shortest possible time. Our system currently operates in a human-on-the-loop mode where at each step, a set of recommendations are presented to the operator to aid in decision-making. In principle, the system could operate autonomously, only prompting the operator for critical decisions, allowing the system to significantly scale up to larger areas and multiple suspects. Once the intended target is identified with sufficient confidence, the vehicle is reported to the authorities to take further action. Other recommendations include a selection of road closures, i.e., soft interventions, or to continue monitoring. We evaluate the performance of the proposed system using simulated scenarios where the suspect, starting at random locations, takes a noisy shortest path to their intended target. In all scenarios, the suspect’s intended target is unknown to our system. The decision thresholds are selected to maximize the chances of determining the suspect’s intended target in the minimum amount of time and with the smallest number of interventions. We conclude by discussing the limitations of our current approach to motivate a machine learning approach, based on reinforcement learning in order to relax some of the current limiting assumptions.

Keywords: Autonomous surveillance, Bayesian reasoning, decision-support, interventions, patterns-of-life, predictive analytics, predictive insights.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 484