Search results for: algorithmic personalization

Authors: A. Chatel, I. S. Torreguitart, T. Verstraete

Abstract:

The paper deals with a single point optimization of the LS89 turbine using an adjoint optimization and defining the design variables within a CAD system. The advantage of including the CAD model in the design system is that higher level constraints can be imposed on the shape, allowing the optimized model or component to be manufactured. However, CAD-based approaches restrict the design space compared to node-based approaches where every node is free to move. In order to preserve a rich design space, we develop a methodology to refine the CAD model during the optimization and to create the best parameterization to use at each time. This study presents a methodology to progressively refine the design space, which combines parametric effectiveness with a differential evolutionary algorithm in order to create an optimal parameterization. In this manuscript, we show that by doing the parameterization at the CAD level, we can impose higher level constraints on the shape, such as the axial chord length, the trailing edge radius and G2 geometric continuity between the suction side and pressure side at the leading edge. Additionally, the adjoint sensitivities are filtered out and only smooth shapes are produced during the optimization process. The use of algorithmic differentiation for the CAD kernel and grid generator allows computing the grid sensitivities to machine accuracy and avoid the limited arithmetic precision and the truncation error of finite differences. Then, the parametric effectiveness is computed to rate the ability of a set of CAD design parameters to produce the design shape change dictated by the adjoint sensitivities. During the optimization process, the design space is progressively enlarged using the knot insertion algorithm which allows introducing new control points whilst preserving the initial shape. The position of the inserted knots is generally assumed. However, this assumption can hinder the creation of better parameterizations that would allow producing more localized shape changes where the adjoint sensitivities dictate. To address this, we propose using a differential evolutionary algorithm to maximize the parametric effectiveness by optimizing the location of the inserted knots. This allows the optimizer to gradually explore larger design spaces and to use an optimal CAD-based parameterization during the course of the optimization. The method is tested on the LS89 turbine cascade and large aerodynamic improvements in the entropy generation are achieved whilst keeping the exit flow angle fixed. The trailing edge and axial chord length, which are kept fixed as manufacturing constraints. The optimization results show that the multilevel optimizations were more efficient than the single level optimization, even though they used the same number of design variables at the end of the multilevel optimizations. Furthermore, the multilevel optimization where the parameterization is created using the optimal knot positions results in a more efficient strategy to reach a better optimum than the multilevel optimization where the position of the knots is arbitrarily assumed.

Keywords: adjoint, CAD, knots, multilevel, optimization, parametric effectiveness

Procedia PDF Downloads 89

Authors: Mohammed Makki, Milad Showkatbakhsh, Aiman Tabony

Abstract:

Computational applications of natural evolutionary processes as problem-solving tools have been well established since the mid-20th century. However, their application within architecture and design has only gained ground in recent years, with an increasing number of academics and professionals in the field electing to utilize evolutionary computation to address problems comprised from multiple conflicting objectives with no clear optimal solution. Recent advances in computer science and its consequent constructive influence on the architectural discourse has led to the emergence of multiple algorithmic processes capable of simulating the evolutionary process in nature within an efficient timescale. Many of the developed processes of generating a population of candidate solutions to a design problem through an evolutionary based stochastic search process are often driven through the application of both environmental and architectural parameters. These methods allow for conflicting objectives to be simultaneously, independently, and objectively optimized. This is an essential approach in design problems with a final product that must address the demand of a multitude of individuals with various requirements. However, one of the main challenges encountered through the application of an evolutionary process as a design tool is the ability for the simulation to maintain variation amongst design solutions in the population while simultaneously increasing in fitness. This is most commonly known as the ‘golden rule’ of balancing exploration and exploitation over time; the difficulty of achieving this balance in the simulation is due to the tendency of either variation or optimization being favored as the simulation progresses. In such cases, the generated population of candidate solutions has either optimized very early in the simulation, or has continued to maintain high levels of variation to which an optimal set could not be discerned; thus, providing the user with a solution set that has not evolved efficiently to the objectives outlined in the problem at hand. As such, the experiments presented in this paper seek to achieve the ‘golden rule’ by incorporating a mathematical fitness criterion for the development of an urban tissue comprised from the superblock as its primary architectural element. The mathematical value investigated in the experiments is the standard deviation factor. Traditionally, the standard deviation factor has been used as an analytical value rather than a generative one, conventionally used to measure the distribution of variation within a population by calculating the degree by which the majority of the population deviates from the mean. A higher standard deviation value delineates a higher number of the population is clustered around the mean and thus limited variation within the population, while a lower standard deviation value is due to greater variation within the population and a lack of convergence towards an optimal solution. The results presented will aim to clarify the extent to which the utilization of the standard deviation factor as a fitness criterion can be advantageous to generating fitter individuals in a more efficient timeframe when compared to conventional simulations that only incorporate architectural and environmental parameters.

Keywords: architecture, computation, evolution, standard deviation, urban

Procedia PDF Downloads 109

Authors: Abdelkhalek Bouchikhi, Elyes Benmokhtar, Sebastien Saletzki

Abstract:

The aeronautical field is experiencing issues with RF spectrum congestion due to the constant increase in the number of flights, aircrafts and telecom systems on board. In addition, these systems are bulky in size, weight and energy consumption. The cognitive radio helps particularly solving the spectrum congestion issue by its capacity to detect idle frequency channels then, allowing an opportunistic exploitation of the RF spectrum. The present work aims to propose a new use case for aeronautical spectrum sharing and to study the performances of three different detection techniques: energy detector, matched filter and cyclostationary detector within the aeronautical use case. The spectrum in the proposed cognitive radio is allocated dynamically where each cognitive radio follows a cognitive cycle. The spectrum sensing is a crucial step. The goal of the sensing is gathering data about the surrounding environment. Cognitive radio can use different sensors: antennas, cameras, accelerometer, thermometer, etc. In IEEE 802.22 standard, for example, a primary user (PU) has always the priority to communicate. When a frequency channel witch used by the primary user is idle, the secondary user (SU) is allowed to transmit in this channel. The Distance Measuring Equipment (DME) is composed of a UHF transmitter/receiver (interrogator) in the aircraft and a UHF receiver/transmitter on the ground. While the future cognitive radio will be used jointly to alleviate the spectrum congestion issue in the aeronautical field. LDACS, for example, is a good candidate; it provides two isolated data-links: ground-to-air and air-to-ground data-links. The first contribution of the present work is a strategy allowing sharing the L-band. The adopted spectrum sharing strategy is as follow: the DME will play the role of PU which is the licensed user and the LDACS1 systems will be the SUs. The SUs could use the L-band channels opportunely as long as they do not causing harmful interference signals which affect the QoS of the DME system. Although the spectrum sensing is a key step, it helps detecting holes by determining whether the primary signal is present or not in a given frequency channel. A missing detection on primary user presence creates interference between PU and SU and will affect seriously the QoS of the legacy radio. In this study, first brief definitions, concepts and the state of the art of cognitive radio will be presented. Then, a study of three communication channel detection algorithms in a cognitive radio context is carried out. The study is made from the point of view of functions, material requirements and signal detection capability in the aeronautical field. Then, we presented a modeling of the detection problem by three different methods (energy, adapted filter, and cyclostationary) as well as an algorithmic description of these detectors is done. Then, we study and compare the performance of the algorithms. Simulations were carried out using MATLAB software. We analyzed the results based on ROCs curves for SNR between -10dB and 20dB. The three detectors have been tested with a synthetics and real world signals.

Keywords: aeronautic, communication, navigation, surveillance systems, cognitive radio, spectrum sensing, software defined radio

Procedia PDF Downloads 145

Authors: Michela Del Vicario, Walter Quattrociocchi, Antonio Scala, Ana Lucía Schmidt, Fabiana Zollo

Abstract:

Information, rumors, and debates may shape and impact public opinion heavily. In the latest years, several concerns have been expressed about social influence on the Internet and the outcome that online debates might have on real-world processes. Indeed, on online social networks users tend to select information that is coherent to their system of beliefs and to form groups of like-minded people –i.e., echo chambers– where they reinforce and polarize their opinions. In this way, the potential benefits coming from the exposure to different points of view may be reduced dramatically, and individuals' views may become more and more extreme. Such a context fosters misinformation spreading, which has always represented a socio-political and economic risk. The persistence of unsubstantiated rumors –e.g., the hypothetical and hazardous link between vaccines and autism– suggests that social media do have the power to misinform, manipulate, or control public opinion. As an example, current approaches such as debunking efforts or algorithmic-driven solutions based on the reputation of the source seem to prove ineffective against collective superstition. Indeed, experimental evidence shows that confirmatory information gets accepted even when containing deliberately false claims while dissenting information is mainly ignored, influences users’ emotions negatively and may even increase group polarization. Moreover, confirmation bias has been shown to play a pivotal role in information cascades, posing serious warnings about the efficacy of current debunking efforts. Nevertheless, mitigation strategies have to be adopted. To generalize the problem and to better understand social dynamics behind information spreading, in this work we rely on a tight quantitative analysis to investigate the behavior of more than 300M users w.r.t. news consumption on Facebook over a time span of six years (2010-2015). Through a massive analysis on 920 news outlets pages, we are able to characterize the anatomy of news consumption on a global and international scale. We show that users tend to focus on a limited set of pages (selective exposure) eliciting a sharp and polarized community structure among news outlets. Moreover, we find similar patterns around the Brexit –the British referendum to leave the European Union– debate, where we observe the spontaneous emergence of two well segregated and polarized groups of users around news outlets. Our findings provide interesting insights into the determinants of polarization and the evolution of core narratives on online debating. Our main aim is to understand and map the information space on online social media by identifying non-trivial proxies for the early detection of massive informational cascades. Furthermore, by combining users traces, we are finally able to draft the main concepts and beliefs of the core narrative of an echo chamber and its related perceptions.

Keywords: information spreading, misinformation, narratives, online social networks, polarization

Procedia PDF Downloads 266

Authors: Laith F. Gulli, Nicole M. Mallory

Abstract:

The undertaking to develop a psychometric instrument is monumental. Understanding the relationship between variables and events is important in structural and exploratory design of psychometric instruments. Considering this, we describe a method used to group, pair and combine multiple Philosophical Assumption statements that assisted in development of a 13 item psychometric screening instrument. We abbreviated our Philosophical Assumptions (PA)s and added parameters, which were then condensed and mathematically modeled in a specific process. This model produced clusters of combinatorics which was utilized in design and development for 1) information retrieval and categorization 2) item development and 3) estimation of interactions among variables and likelihood of events. The psychometric screening instrument measured Knowledge, Assessment (education) and Beliefs (KAB) of New Addictions Research (NAR), which we called KABNAR. We obtained an overall internal consistency for the seven Likert belief items as measured by Cronbach’s α of .81 in the final study of 40 Clinicians, calculated by SPSS 14.0.1 for Windows. We constructed the instrument to begin with demographic items (degree/addictions certifications) for identification of target populations that practiced within Outpatient Substance Abuse Counseling (OSAC) settings. We then devised education items, beliefs items (seven items) and a modifiable “barrier from learning” item that consisted of six “choose any” choices. We also conceptualized a close relationship between identifying various degrees and certifications held by Outpatient Substance Abuse Therapists (OSAT) (the demographics domain) and all aspects of their education related to EB-NAR (past and present education and desired future training). We placed a descriptive (PA)1tx in both demographic and education domains to trace relationships of therapist education within these two domains. The two perceptions domains B1/b1 and B2/b2 represented different but interrelated perceptions from the therapist perspective. The belief items measured therapist perceptions concerning EB-NAR and therapist perceptions using EB-NAR during the beginning of outpatient addictions counseling. The (PA)s were written in simple words and descriptively accurate and concise. We then devised a list of parameters and appropriately matched them to each PA and devised descriptive parametric (PA)s in a domain categorized information grid. Descriptive parametric (PA)s were reduced to simple mathematical symbols. This made it easy to utilize parametric (PA)s into algorithms, combinatorics and clusters to develop larger information grids. By using matching combinatorics we took paired demographic and education domains with a subscript of 1 and matched them to the column with each B domain with subscript 1. Our algorithmic matching formed larger information grids with organized clusters in columns and rows. We repeated the process using different demographic, education and belief domains and devised multiple information grids with different parametric clusters and geometric arrays. We found benefit combining clusters by different geometric arrays, which enabled us to trace parametric variables and concepts. We were able to understand potential differences between dependent and independent variables and trace relationships of maximum likelihoods.

Keywords: psychometric, parametric, domains, grids, therapists

Procedia PDF Downloads 247

Authors: Ennios Eros Giogos, Nefeli Katsarou, Giota Mantziorou, Elena Panou, Nikolaos Kourniatis, Socratis Giannoudis

Abstract:

In the context of the postgraduate course Productive Design, Department of Interior Architecture of the University of West Attica in Athens, under the guidance of Professors Nikolaos Koyrniatis and Socratis Giannoudis, kinetic mechanisms with parametric models were examined for their further application in the design of objects. In the first phase, the students studied a motion mechanism that they chose from daily experience and then analyzed its geometric structure in relation to the geometric transformations that exist. In the second phase, the students tried to design it through a parametric model in Grasshopper3d for Rhino algorithmic processor and plan the design of its application in an everyday object. For the project presented, our team began by studying the movement of living beings, specifically the snake. By studying the snake and the role that the environment has in its movement, four basic typologies were recognized: serpentine, concertina, sidewinding and rectilinear locomotion, as well as its ability to perform spiral formations. Most typologies are characterized by ripples, a series of sinusoidal curves. For the application of the snake movement in a polymorphic space divider, the use of a coil-type joint was studied. In the Grasshopper program, the simulation of the desired motion for the polymorphic surface was tested by applying a coil on a sinusoidal curve and a spiral curve. It was important throughout the process that the points corresponding to the nodes of the real object remain constant in number, as well as the distances between them and the elasticity of the construction had to be achieved through a modular movement of the coil and not some elastic element (material) at the nodes. Using mesh (repeating coil), the whole construction is transformed into a supporting body and combines functionality with aesthetics. The set of elements functions as a vertical spatial network, where each element participates in its coherence and stability. Depending on the positions of the elements in terms of the level of support, different perspectives are created in terms of the visual perception of the adjacent space. For the implementation of the model on the scale (1:3), (0.50m.x2.00m.), the load-bearing structure that was studied has aluminum rods for the basic pillars Φ6mm and Φ 2.50 mm, for the secondary columns. Filling elements and nodes are of similar material and were made of MDF surfaces. During the design process, four trapezoidal patterns were picketed, which function as filling elements, while in order to support their assembly, a different engraving facet was done. The nodes have holes that can be pierced by the rods, while their connection point with the patterns has a half-carved recess. The patterns have a corresponding recess. The nodes are of two different types depending on the column that passes through them. The patterns and knots were designed to be cut and engraved using a Laser Cutter and attached to the knots using glue. The parameters participate in the design as mechanisms that generate complex forms and structures through the repetition of constantly changing versions of the parts that compose the object.

Keywords: polymorphic, locomotion, sinusoidal curves, parametric

Procedia PDF Downloads 72

Authors: Maria Lazari, Lorenzo Sanavia

Abstract:

Mechanics of unsaturated soils has been an active field of research in the last decades. Efficient constitutive models that take into account the partial saturation of soil are necessary to solve a number of engineering problems e.g. instability of slopes and cuts due to heavy rainfalls. A large number of constitutive models can now be found in the literature that considers fundamental issues associated with the unsaturated soil behaviour, like the volume change and shear strength behaviour with suction or saturation changes. Partially saturated soils may either expand or collapse upon wetting depending on the stress level, and it is also possible that a soil might experience a reversal in the volumetric behaviour during wetting. Shear strength of soils also changes dramatically with changes in the degree of saturation, and a related engineering problem is slope failures caused by rainfall. There are several states of the art reviews over the last years for studying the topic, usually providing a thorough discussion of the stress state, the advantages, and disadvantages of specific constitutive models as well as the latest developments in the area of unsaturated soil modelling. However, only a few studies focused on the coupling between partial saturation states and time effects on the behaviour of geomaterials. Rate dependency is experimentally observed in the mechanical response of granular materials, and a viscoplastic constitutive model is capable of reproducing creep and relaxation processes. Therefore, in this work an elasto-viscoplastic constitutive model for unsaturated soils is proposed and validated on the basis of experimental data. The model constitutes an extension of an existing elastoplastic strain-hardening constitutive model capable of capturing the behaviour of variably saturated soils, based on energy conjugated stress variables in the framework of superposed continua. The purpose was to develop a model able to deal with possible mechanical instabilities within a consistent energy framework. The model shares the same conceptual structure of the elastoplastic laws proposed to deal with bonded geomaterials subject to weathering or diagenesis and is capable of modelling several kinds of instabilities induced by the loss of hydraulic bonding contributions. The novelty of the proposed formulation is enhanced with the incorporation of density dependent stiffness and hardening coefficients in order to allow the modeling of the pycnotropy behaviour of granular materials with a single set of material constants. The model has been implemented in the commercial FE platform PLAXIS, widely used in Europe for advanced geotechnical design. The algorithmic strategies adopted for the stress-point algorithm had to be revised to take into account the different approach adopted by PLAXIS developers in the solution of the discrete non-linear equilibrium equations. An extensive comparison between models with a series of experimental data reported by different authors is presented to validate the model and illustrate the capability of the newly developed model. After the validation, the effectiveness of the viscoplastic model is displayed by numerical simulations of a partially saturated slope failure of the laboratory scale and the effect of viscosity and degree of saturation on slope’s stability is discussed.

Keywords: PLAXIS software, slope, unsaturated soils, Viscoplasticity

Procedia PDF Downloads 194

Authors: Zachary Blanks, Solomon Sonya

Abstract:

Poaching presents a serious threat to endangered animal species, environment conservations, and human life. Additionally, some poaching activity has even been linked to supplying funds to support terrorist networks elsewhere around the world. Consequently, agencies dedicated to protecting wildlife habitats have a near intractable task of adequately patrolling an entire area (spanning several thousand kilometers) given limited resources, funds, and personnel at their disposal. Thus, agencies need predictive tools that are both high-performing and easily implementable by the user to help in learning how the significant features (e.g. animal population densities, topography, behavior patterns of the criminals within the area, etc) interact with each other in hopes of abating poaching. This research develops a classification model using machine learning algorithms to aid in forecasting future attacks that is both easy to train and performs well when compared to other models. In this research, we demonstrate how data imputation methods (specifically predictive mean matching, gradient boosting, and random forest multiple imputation) can be applied to analyze data and create significant predictions across a varied data set. Specifically, we apply these methods to improve the accuracy of adopted prediction models (Logistic Regression, Support Vector Machine, etc). Finally, we assess the performance of the model and the accuracy of our data imputation methods by learning on a real-world data set constituting four years of imputed data and testing on one year of non-imputed data. This paper provides three main contributions. First, we extend work done by the Teamcore and CREATE (Center for Risk and Economic Analysis of Terrorism Events) research group at the University of Southern California (USC) working in conjunction with the Department of Homeland Security to apply game theory and machine learning algorithms to develop more efficient ways of reducing poaching. This research introduces ensemble methods (Random Forests and Stochastic Gradient Boosting) and applies it to real-world poaching data gathered from the Ugandan rain forest park rangers. Next, we consider the effect of data imputation on both the performance of various algorithms and the general accuracy of the method itself when applied to a dependent variable where a large number of observations are missing. Third, we provide an alternate approach to predict the probability of observing poaching both by season and by month. The results from this research are very promising. We conclude that by using Stochastic Gradient Boosting to predict observations for non-commercial poaching by season, we are able to produce statistically equivalent results while being orders of magnitude faster in computation time and complexity. Additionally, when predicting potential poaching incidents by individual month vice entire seasons, boosting techniques produce a mean area under the curve increase of approximately 3% relative to previous prediction schedules by entire seasons.

Keywords: ensemble methods, imputation, machine learning, random forests, statistical analysis, stochastic gradient boosting, wildlife protection

Procedia PDF Downloads 263

Authors: Lan Cheng, Harry Qin, Yang Wang

Abstract:

Background: COVID-19 has induced the largest digital learning experiment in history. There is also emerging research evidence that students have paid a high cost of learning loss from virtual learning. University-wide survey results demonstrate that digital learning remains difficult for students who struggle with learning challenges, isolation, or a lack of resources. Large-scale efforts are therefore increasingly utilized for digital education. To better prepare students in higher education for this grand scientific and technological transformation, STEM education has been prioritized and promoted as a strategic imperative in the ongoing curriculum reform essential for unfinished learning needs and whole-person development. Building upon five key elements identified in the STEM education literature: Problem-based Learning, Community and Belonging, Technology Skills, Personalization of Learning, Connection to the External Community, this case study explores the potential of pedagogical innovation that integrates computational and experimental methodologies to support, enrich, and navigate STEM education. Objectives: The goal of this case study is to create a high-fidelity prototype design for STEM education with knowledge transfer technology that contains a Cooperative Multi-Agent System (CMAS), which has the objectives of (1) conduct assessment to reveal a virtual learning mechanism and establish strategies to facilitate scientific learning engagement, accessibility, and connection within and beyond university setting, (2) explore and validate an interactional co-creation approach embedded in project-based learning activities under the STEM learning context, which is being transformed by both digital technology and student behavior change,(3) formulate and implement the STEM-oriented campaign to guide learning network mapping, mitigate the loss of learning, enhance the learning experience, scale-up inclusive participation. Methods: This study applied a case study strategy and a methodology informed by Social Network Analysis Theory within a cross-disciplinary communication paradigm (students, peers, educators). Knowledge transfer technology is introduced to address learning challenges and to increase the efficiency of Reinforcement Learning (RL) algorithms. A co-creation learning framework was identified and investigated in a context-specific way with a learning analytic tool designed in this study. Findings: The result shows that (1) CMAS-empowered learning support reduced students’ confusion, difficulties, and gaps during problem-solving scenarios while increasing learner capacity empowerment, (2) The co-creation learning phenomenon have examined through the lens of the campaign and reveals that an interactive virtual learning environment fosters students to navigate scientific challenge independently and collaboratively, (3) The deliverables brought from the STEM educational campaign provide a methodological framework both within the context of the curriculum design and external community engagement application. Conclusion: This study brings a holistic and coherent pedagogy to cultivates students’ interest in STEM and develop them a knowledge base to integrate and apply knowledge across different STEM disciplines. Through the co-designing and cross-disciplinary educational content and campaign promotion, findings suggest factors to empower evidence-based learning practice while also piloting and tracking the impact of the scholastic value of co-creation under the dynamic learning environment. The data nested under the knowledge transfer technology situates learners’ scientific journey and could pave the way for theoretical advancement and broader scientific enervators within larger datasets, projects, and communities.

Keywords: co-creation, cross-disciplinary, knowledge transfer, STEM education, social network analysis

Procedia PDF Downloads 80