Search results for: artificial reasoning

Authors: Sultan Noman Qasem

Abstract:

This paper presents an evolutionary algorithm for solving multi-objective optimization problems-based artificial neural network (ANN). The multi-objective evolutionary algorithm used in this study is genetic algorithm while ANN used is radial basis function network (RBFN). The proposed algorithm named memetic elitist Pareto non-dominated sorting genetic algorithm-based RBFNN (MEPGAN). The proposed algorithm is implemented on medical diseases problems. The experimental results indicate that the proposed algorithm is viable, and provides an effective means to design multi-objective RBFNs with good generalization capability and compact network structure. This study shows that MEPGAN generates RBFNs coming with an appropriate balance between accuracy and simplicity, comparing to the other algorithms found in literature.

Keywords: radial basis function network, hybrid learning, multi-objective optimization, genetic algorithm

Procedia PDF Downloads 563

Authors: Gizelle K. Vianna, Gustavo S. Oliveira, Gabriel V. Cunha

Abstract:

The use of decision support systems in agriculture may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. In our work, we designed and implemented a decision support system for small tomatoes producers. This work investigates ways to recognize the late blight disease from the analysis of digital images of tomatoes, using a pair of multilayer perceptron neural networks. The networks outputs are used to generate repainted tomato images in which the injuries on the plant are highlighted, and to calculate the damage level of each plant. Those levels are then used to construct a situation map of a farm where a cellular automata simulates the outbreak evolution over the fields. The simulator can test different pesticides actions, helping in the decision on when to start the spraying and in the analysis of losses and gains of each choice of action.

Keywords: artificial neural networks, cellular automata, decision support system, pattern recognition

Procedia PDF Downloads 455

Authors: Nadia Soledad Peralta

Abstract:

Within the framework of socio-cognitive interaction, argumentation is understood as a psychological process that supports and induces reasoning and learning. Most authors emphasize the great potential of argumentation to negotiate with contradictions and complex decisions. So argumentation is a target for researchers who highlight the importance of social and cognitive processes in learning. In the context of social interaction among university students, different types of arguments are analyzed according to group size (dyads and triads) and the type of task (reading of frequency tables, causal explanation of physical phenomena, the decision regarding moral dilemma situations, and causal explanation of social phenomena). Eighty-nine first-year social sciences students of the National University of Rosario participated. Two groups were formed from the results of a pre-test that ensured the heterogeneity of points of view between participants. Group 1 consisted of 56 participants (performance in dyads, total: 28), and group 2 was formed of 33 participants (performance in triads, total: 11). A quasi-experimental design was performed in which effects of the two variables (group size and type of task) on the argumentation were analyzed. Three types of argumentation are described: authentic dialogical argumentative resolutions, individualistic argumentative resolutions, and non-argumentative resolutions. The results indicate that individualistic arguments prevail in dyads. That is, although people express their own arguments, there is no authentic argumentative interaction. Given that, there are few reciprocal evaluations and counter-arguments in dyads. By contrast, the authentically dialogical argument prevails in triads, showing constant feedback between participants’ points of view. It was observed that, in general, the type of task generates specific types of argumentative interactions. However, it is possible to emphasize that the authentically dialogic arguments predominate in the logical tasks, whereas the individualists or pseudo-dialogical are more frequent in opinion tasks. Nerveless, these relationships between task type and argumentative mode are best clarified in an interactive analysis based on group size. Finally, it is important to stress the value of dialogical argumentation in educational domains. Argumentative function not only allows a metacognitive reflection about their own point of view but also allows people to benefit from exchanging points of view in interactive contexts.

Keywords: sociocognitive interaction, argumentation, university students, size of the grup

Procedia PDF Downloads 83

Authors: Mary Moner Botros Fanawel

Abstract:

Many companies use the statistical tool named as statistical quality control, and which can have a high cost for the companies interested on these statistical tools. The evaluation of the quality of products and services is an important topic, but the reduction of the cost of the implantation of the statistical quality control also has important benefits for the companies. For this reason, it is important to implement a economic design for the various steps included into the statistical quality control. In this paper, we describe some relevant aspects related to the economic design of a quality control chart for the proportion of defective items. They are very important because the suggested issues can reduce the cost of implementing a quality control chart for the proportion of defective items. Note that the main purpose of this chart is to evaluate and control the proportion of defective items of a production process.

Keywords: model predictive control, hierarchical control structure, genetic algorithm, water quality with DBPs objectives proportion, type I error, economic plan, distribution function bootstrap control limit, p-value method, out-of-control signals, p-value, quality characteristics

Procedia PDF Downloads 62

Authors: Alena Kulikova, Tatjana Kanonire

Abstract:

Intelligence research is one of the oldest fields of psychology. Many factors have made a research on intelligence, defined as reasoning and problem solving [1, 2], a very acute and urgent problem. Thus, it has been repeatedly shown that intelligence is a predictor of academic, professional, and social achievement in adulthood (for example, [3]); Moreover, intelligence predicts these achievements better than any other trait or ability [4]. The individual level, a comprehensive assessment of intelligence is a necessary criterion for the diagnosis of various mental conditions. For example, it is a necessary condition for psychological, medical and pedagogical commissions when deciding on educational needs and the most appropriate educational programs for school children. Assessment of intelligence is crucial in clinical psychodiagnostic and needs high-quality intelligence measurement tools. Therefore, it is not surprising that the development of intelligence tests is an essential part of psychological science and practice. Many modern intelligence tests have a long history and have been used for decades, for example, the Stanford-Binet test or the Wechsler test. However, the vast majority of these tests are based on the classic linear test structure, in which all respondents receive all tasks (see, for example, a critical review by [5]). This understanding of the testing procedure is a legacy of the pre-computer era, in which blank testing was the only diagnostic procedure available [6] and has some significant limitations that affect the reliability of the data obtained [7] and increased time costs. Another problem with measuring IQ is that classical line-structured tests do not fully allow to measure respondent's intellectual progress [8], which is undoubtedly a critical limitation. Advances in modern psychometrics allow for avoiding the limitations of existing tools. However, as in any rapidly developing industry, at the moment, psychometrics does not offer ready-made and straightforward solutions and requires additional research. In our presentation we would like to discuss the strengths and weaknesses of the current approaches to intelligence measurement and highlight “points of growth” for creating a test in accordance with modern psychometrics. Whether it is possible to create the instrument that will use all achievements of modern psychometric and remain valid and practically oriented. What would be the possible limitations for such an instrument? The theoretical framework and study design to create and validate the original Russian comprehensive computer test for measuring the intellectual development in school-age children will be presented.

Keywords: Intelligence, psychometrics, psychological measurement, computerized adaptive testing, multistage testing

Procedia PDF Downloads 80

Authors: Ferinar Moaidi, Mahdi Moaidi

Abstract:

Environmental issues and the ever-increasing in demand of electrical energy make it necessary to have distributed generation (DG) resources in the power system. In this research, in order to realize the goals of reducing losses and improving the voltage profile in a microgrid, the allocation and sizing of DGs have been used. The proposed Genetic Algorithm (GA) is described from the array of artificial intelligence methods for solving the problem. The algorithm is implemented on the IEEE 33 buses network. This study is presented in two scenarios, primarily to illustrate the effect of location and determination of DGs has been done to reduce losses and improve the voltage profile. On the other hand, decisions made with the one-level assumptions of load are not universally accepted for all levels of load. Therefore, in this study, load modelling is performed and the results are presented for multi-levels load state.

Keywords: distributed generation, genetic algorithm, microgrid, load modelling, loss reduction, voltage improvement

Procedia PDF Downloads 143

Authors: Parag Bhalchandra, S. D. Khamitkar

Abstract:

Searching trees is a most interesting application of Artificial Intelligence. Over the period of time, many innovative methods have been evolved to better search trees with respect to computational complexities. Tree searches are difficult to understand due to the exponential growth of possibilities when increasing the number of nodes or levels in the tree. Usually it is understood when we traverse down in the tree, traverse down to greater depth, in the search of a solution or a goal. However, this does not happen in reality as explicit enumeration is not a very efficient method and there are many algorithmic speedups that will find the optimal solution without the burden of evaluating all possible trees. It was a common question before all researchers where they often wonder what algorithms will yield the best and fastest result The intention of this paper is two folds, one to review selected tree search algorithms and search strategies that can be applied to a problem space and the second objective is to stimulate to implement recent developments in the complexity behavior of search strategies. The algorithms discussed here apply in general to both brute force and heuristic searches.

Keywords: trees search, asymptotic complexity, brute force, heuristics algorithms

Procedia PDF Downloads 304

Authors: Rajaian Hoonejani Mohammad, Eshraghi Pegah, Zomorodian Zahra Sadat, Tahsildoost Mohammad

Abstract:

Over the past decade, energy consumption in educational buildings has steadily increased. The purpose of this research is to provide a method to quickly predict the energy consumption of buildings using separate evaluation of zones and decomposing the building to eliminate the complexity of geometry at the early design stage. To produce this framework, machine learning algorithms such as Support vector regression (SVR) and Artificial neural network (ANN) are used to predict energy consumption and thermal comfort metrics in a school as a case. The database consists of more than 55000 samples in three climates of Iran. Cross-validation evaluation and unseen data have been used for validation. In a specific label, cooling energy, it can be said the accuracy of prediction is at least 84% and 89% in SVR and ANN, respectively. The results show that the SVR performed much better than the ANN.

Keywords: early stage of design, energy, thermal comfort, validation, machine learning

Procedia PDF Downloads 73

Authors: Tian-Wei Huang, Wei-Ting Bai, Yu-Tung Cheng, Jeng-Han Tsai

Abstract:

In this paper, a 1-stage 6-section conventional distributed amplifier (CDA) structure distributed power amplifier (DPA) fabricated in a 28-nm HPC+ 1P9M CMOS process is proposed. The transistor size selection is introduced to achieve broadband power matching and thus remains a high flatness output power and power added efficiency (PAE) within the bandwidth. With the inductive peaking technique, the high-frequency pole appears and the high-frequency gain is increased; the gain flatness becomes better as well. The inductive elements used to form an artificial transmission line are built up with a floating ground coplanar waveguide plane (CPWFG) rather than a microstrip line, coplanar waveguide (CPW), or spiral inductor to get better performance. The DPA achieves 12.6 dB peak gain at 52.5 GHz with 2.9 to 64.9 GHz 3-dB bandwidth. The Psat is 11.4 dBm with PAEMAX of 10.6 % at 25 GHz. The output 1-dB compression point power is 9.8 dBm.

Keywords: distributed power amplifier (DPA), gain bandwidth (GBW), floating ground CPW, inductive peaking, 28-nm, CMOS, 5G.

Procedia PDF Downloads 81

Authors: Rose Mini Agoes Salim, Shahnaz Safitri

Abstract:

The aim of this study is to test the effectiveness of teaching kindness in preschool children by using several techniques. Kindness is a physical act or emotional support aimed to build or maintain relationships with others. Kindness is known to be essential in the development of moral reasoning to distinguish between the good and bad things. In this study, kindness is operationalized as several acts including helping friends, comforting sad friends, inviting friends to play, protecting others, sharing, saying hello, saying thank you, encouraging others, and apologizing. It is mentioned that kindness is crucial to be developed in preschool children because this is the time the children begin to interact with their social environment through play. Furthermore, preschool children's cognitive development makes them begin to represent the world with words, which then allows them to interact with others. On the other hand, preschool children egocentric thinking makes them still need to learn to consider another person's perspective. In relation to social interaction, preschool children need to be stimulated and assisted by adult to be able to pay attention to other and act with kindness toward them. On teaching kindness to children, the quality of interaction between children and their significant others is the key factor. It is known that preschool children learn about kindness by imitating adults on their two way interaction. Specifically, this study examines two types of teaching techniques that can be done by parents as a way to teach kindness, namely the picture-storybook reading and hand-puppet storytelling. These techniques were examined because both activities are easy to do and both also provide a model of behavior for the child based on the character in the story. To specifically examine those techniques effectiveness in teaching kindness, two studies were conducted. Study I involves 31 children aged 5-6 years old with picture-storybook reading technique, where the intervention is done by reading 8 picture books for 8 days. In study II, hand-puppet storytelling technique is examined to 32 children aged 3-5 years old. The treatments effectiveness are measured using an instrument in the form of nine colored cards that describe the behavior of kindness. Data analysis using Wilcoxon Signed-rank test shows a significant difference on the average score of kindness (p < 0.05) before and after the intervention has been held. For daily observation, a ‘kindness tree’ and observation sheets are used which are filled out by the teacher. Two weeks after interventions, an improvement on all kindness behaviors measured is intact. The same result is also gained from both ‘kindness tree’ and observational sheets.

Keywords: kindness, moral teaching, storytelling, hand puppet

Procedia PDF Downloads 252

Authors: Schulz Peter, Kee Kalya, Lwin May, Goh Wilson, Chia Kendrikck, Chueng Max, Lam Thomas, Sung Joseph

Abstract:

As Artificial Intelligence (AI) is progressively making inroads into clinical practice, questions have arisen as to whether acceptance of AI is skewed toward certain medical practitioner segments, even within particular specializations. This study examines distinct AI acceptance among gastroenterologists with contrasting levels of seniority/experience when interacting with AI typologies. Data from 319 gastroenterologists show the presence of four distinct clusters of clinicians based on experience levels and perceived risk typologies. Analysis of cluster-based responses further revealed that acceptance of AI was not uniform. Our findings showed that clinician experience and risk perspective have an interactive role in influencing AI acceptance. Senior clinicians with low-risk perceptions were highly accepting of AI, but those with high-risk perceptions of AI were substantially less accepting. In contrast, junior clinicians were more inclined to embrace AI when they perceived high risk, yet they hesitated to adopt AI when the perceived risk was minimal.

Keywords: risk perception, acceptance, trust, medicine

Procedia PDF Downloads 13

Authors: Oleksii Bychkov

Abstract:

The fundamental difference between randomness and vagueness is that the former requires statistical research. These issues were studied by Zadeh L, Dubois D., Prad A. The theory of possibility works with expert assessments, hypotheses, etc. gives an idea of the characteristics of the problem situation, the nature of the goals and real limitations. Possibility theory examines experiments that are not repeated. The article discusses issues related to the formalization of a fuzzy, uncertain idea of reality. The author proposes to expand the classical model of the theory of possibilities by introducing a measure of necessity. The proposed model of the theory of possibilities allows us to extend the measures of possibility and necessity onto a Boolean while preserving the properties of the measure. Thus, upper and lower estimates are obtained to describe the fact that the event will occur. Knowledge of the patterns that govern mass random, uncertain, fuzzy events allows us to predict how these events will proceed. The article proposed for publication quite fully reveals the essence of the construction and use of the theory of probability and the theory of possibility.

Keywords: possibility, artificial, modeling, axiomatics, intellectual approach

Procedia PDF Downloads 32

Authors: Venere Ferraro, Silvia Ferraris

Abstract:

We live in a world pervaded by new advanced technologies that have been changing the way we live and experience the surrounded. Besides, new technologies enable product innovation at different levels. Nevertheless, innovation does not lie just in the technological development and in its hard aspects but also in the meaningful use of it for the final user. In order to generate innovative products, a new perspective is needed: The shift from an instrument-oriented view of the technology towards a broader view that includes aspects like aesthetics, acceptance, comfort, and sociability. In many businesses, the user experience of the product is considered the key battlefield to achieve product innovation. (Holland 2011) The use of new technologies is indeed useless without paying attention to the user experience. This paper presents a workshop activity conducted at Design School of Politecnico di Milano in collaboration with Chiba University and aimed at generating innovative design concepts of high-tech mask. The students were asked to design the user experience of a new mask by exploiting emerging technologies such as wearable sensors and information communication technology (ICT) for a chosen field of application: safety or sport. When it comes to the user experience, the mask is a very challenging design product, because it covers aspects of product interaction and, most important, psychological and cultural aspects related to the impact on the facial expression. Furthermore, since the mask affects the face expression quite a lot, it could be a barrier to hide with, or it could be a mean to enhance user’s communication to others. The main request for the students was to take on a user-centered approach: To go beyond the instrumental aspects of product use and usability and focus on the user experience by shaping the technology in a desirable and meaningful way for the user reasoning on the metaphorical and cultural level of the product. During the one-week workshop students were asked to face the design process through (i) the research phase: an in-deep analysis of the user and field of application (safety or sport) to set design spaces (brief) and user scenario; (ii) the idea generation, (iii) the idea development. This text will shortly go through the meaning of the product innovation, the use and application of wearable technologies and will then focus on the user experience design in contrast with the technology-driven approach in the field of product innovation. Finally authors will describe the workshop activity and the concepts developed by the students stressing the important role of the user experience design in new product development.

Keywords: product innovation, user experience, technological exploitation, wearable technologies

Procedia PDF Downloads 345

Authors: Shady Gamal Aziz Shehata

Abstract:

Difficulty in defining construction quality arises due to perception based on the nature and requirements of the market, the different partners themselves and the results they want. Quantitative research was used in this constructivist research. A case-based study was conducted to assess the structures of positive attitudes and expectations in the context of quality improvement. A survey based on expert opinions was analyzed among construction organizations/companies operating in the construction industry in Pakistan. The financial strength, management structure and construction experience of the construction companies formed the basis of their selection. A good concept is visible at the project level and is seen as the most valuable part of the construction project. Each quality improvement technique was expected to increase the user's profits by improving the efficiency of the construction project. The Survey is useful for construction professionals to evaluate current construction concepts and expectations for the application of quality improvement techniques in construction projects.

Keywords: correlation analysis, lean construction tools, lean construction, logistic regression analysis, risk management, safety construction quality, expectation, improvement, perception

Procedia PDF Downloads 59

Authors: Daniela Tapusi, Adrian Andronic, Naomi Tufan, Ruxandra Erbașu, Ioana Teodorescu

Abstract:

The proposed theme of this article falls within the policy of reducing carbon emissions imposed by the ‘Green New Deal’ by replacing structural elements made of energy-intensive materials with ecological materials. In this sense, wood has many qualities (high strength/mass and stiffness/mass ratio, low specific gravity, recovery/recycling) that make it competitive with classic building materials. The topological optimization of the linear glulam elements, resulting from different types of analysis (Finite Element Method, simple regression on metamodels), tests on models or by Monte-Carlo simulation, leads to a material reduction of more than 10%. This article proposes a method of obtaining topologically optimized shapes for different types of glued laminated timber beams. The results obtained will constitute the database for AI training.

Keywords: timber, glued laminated timber, artificial-intelligence, environment, carbon emissions

Procedia PDF Downloads 39

Authors: Mona Mikhail Shakhloul Gadalla

Abstract:

The brand-new media revolution, which features a huge range of new media technologies like blogs, social networking, visual worlds, and wikis, has had a tremendous impact on communications, traditional media and across different disciplines. This paper gives an evaluation of the impact of recent media technology on the news, social interactions and conventional media in developing and advanced nations. The look points to the reality that there is a widespread impact of recent media technologies on the news, social interactions and the conventional media in developing and developed nations, albeit undoubtedly and negatively. Social interactions have been considerably affected, in addition to news manufacturing and reporting. It's miles reiterated that regardless of the pervasiveness of recent media technologies, it might now not carry a complete decline of conventional media. This paper contributes to the theoretical framework of the new media and will assist in assessing the extent of the effect of the new media in special places.

Keywords: court reporting, offenders in media, quantitative content analysis, victims in mediamedia literacy, ICT, internet, education communication, media, news, new media technologies, social interactions, traditional media

Procedia PDF Downloads 34

Authors: Yuanjin Liu

Abstract:

Retirement withdrawal strategies are very important to minimize the probability of ruin in retirement. The ruin probability is modeled as a function of initial withdrawal age, gender, asset allocation, inflation rate, and initial withdrawal rate. The ruin probability is obtained based on the 2019 period life table for the Social Security, IRS Required Minimum Distribution (RMD) Worksheets, US historical bond and equity returns, and inflation rates using simulation. Several popular machine learning algorithms of the generalized additive model, random forest, support vector machine, extreme gradient boosting, and artificial neural network are built. The model validation and selection are based on the test errors using hyperparameter tuning and train-test split. The optimal model is recommended for retirees to monitor the ruin probability. The optimal withdrawal strategy can be obtained based on the optimal predictive model.

Keywords: ruin probability, retirement withdrawal strategies, predictive models, optimal model

Procedia PDF Downloads 74

Authors: Khader S. Al-Aidmat, Venus W. Samawi

Abstract:

Blurred vision in the misty atmosphere is essential problem which needs to be resolved. To solve this problem, we developed a technique to restore foggy degraded image from its original version using Back-propagation neural network (BP-NN). The suggested technique is based on mapping between foggy scene and its corresponding original scene. Seven different approaches are suggested based on type of features used in image restoration. Features are extracted from spatial and spatial-frequency domain (using DCT). Each of these approaches comes with its own BP-NN architecture depending on type and number of used features. The weight matrix resulted from training each BP-NN represents a fog filter. The performance of these filters are evaluated empirically (using PSNR), and perceptually. By comparing the performance of these filters, the effective features that suits BP-NN technique for restoring foggy images is recognized. This system proved its effectiveness and success in restoring moderate foggy images.

Keywords: artificial neural network, discrete cosine transform, feed forward neural network, foggy image restoration

Procedia PDF Downloads 382

Authors: Rana I. Abdulghani, Amera I. Melhum

Abstract:

With the abnormal growth of the usage of computers over networks and under the consideration or agreement of most of the computer security experts who said that the goal of building a secure system is never achieved effectively, all these points led to the design of the intrusion detection systems(IDS). This research adopts a comparison between two techniques for network intrusion detection, The first one used the (Particles Swarm Optimization) that fall within the field (Swarm Intelligence). In this Act, the algorithm Enhanced for the purpose of obtaining the minimum error rate by amending the cluster centers when better fitness function is found through the training stages. Results show that this modification gives more efficient exploration of the original algorithm. The second algorithm used a (Back propagation NN) algorithm. Finally a comparison between the results of two methods used were based on (NSL_KDD) data sets for the construction and evaluation of intrusion detection systems. This research is only interested in clustering the two categories (Normal and Abnormal) for the given connection records. Practices experiments result in intrude detection rate (99.183818%) for EPSO and intrude detection rate (69.446416%) for BP neural network.

Keywords: IDS, SI, BP, NSL_KDD, PSO

Procedia PDF Downloads 382

Authors: Raghad A. Altowairgi

Abstract:

With the wide spread of social media platforms, young people tend to use them extensively as the first means of communication due to their ease and modernity. But these platforms often create a fertile ground for bullies to practice their aggressive behavior against their victims. Platform usage cannot be reduced, but intelligent mechanisms can be implemented to reduce the abuse. This is where machine learning comes in. Understanding and classifying text can be helpful in order to minimize the act of cyberbullying. Artificial intelligence techniques have expanded to formulate an applied tool to address the phenomenon of cyberbullying. In this research, machine learning models are built to classify text into two classes; cyberbullying and non-cyberbullying. After preprocessing the data in 4 stages; removing characters that do not provide meaningful information to the models, tokenization, removing stop words, and lowering text. BoW and TF-IDF are used as the main features for the five classifiers, which are; logistic regression, Naïve Bayes, Random Forest, XGboost, and Catboost classifiers. Each of them scores 92%, 90%, 92%, 91%, 86% respectively.

Keywords: cyberbullying, machine learning, Bag-of-Words, term frequency-inverse document frequency, natural language processing, Catboost

Procedia PDF Downloads 130

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 105

Authors: Makenzy Lee Gilbert

Abstract:

This literature review explores the role of attractor neural networks (ANNs) in modeling psychological processes in artificial and biological systems. By synthesizing research from dynamical systems theory, psychology, and computational neuroscience, the review provides an overview of the current understanding of ANN function in memory formation, reinforcement, retrieval, and forgetting. Key mathematical foundations, including dynamical systems theory and energy functions, are discussed to explain the behavior and stability of these networks. The review also examines empirical applications of ANNs in cognitive processes such as semantic memory and episodic recall, as well as highlighting the hippocampus's role in pattern separation and completion. The review addresses challenges like catastrophic forgetting and noise effects on memory retrieval. By identifying gaps between theoretical models and empirical findings, it highlights the interdisciplinary nature of ANN research and suggests future exploration areas.

Keywords: attractor neural networks, connectionism, computational modeling, cognitive neuroscience

Procedia PDF Downloads 28

Authors: Khalid Obaed Mahmod, Mesut Cevik

Abstract:

The term smart city has appeared recently and was accompanied by many definitions and concepts, but as a simplified and clear definition, it can be said that the smart city is a geographical location that has gained efficiency and flexibility in providing public services to citizens through its use of technological and communication technologies, and this is what distinguishes it from other cities. Smart cities connect the various components of the city through the main and sub-networks in addition to a set of applications and thus be able to collect data that is the basis for providing technological solutions to manage resources and provide services. The basis of the work of the smart city is the use of artificial intelligence and the technology of the Internet of Things. The work presents the concept of smart cities, the pillars, standards, and evaluation indicators on which smart cities depend, and the reasons that prompted the world to move towards its establishment. It also provides a simplified hypothetical way to measure the ideal smart city model by defining some indicators and key pillars, simulating them with logic circuits, and testing them to determine if the city can be considered an ideal smart city or not.

Keywords: factors, indicators, logic gates, pillars, smart city

Procedia PDF Downloads 150

Authors: Mohammed Nabeel Khan, C. Perisamy

Abstract:

Convective vortices are normal highlights of air that ingest lower-entropy-energy at higher temperatures than they dismiss higher-entropy-energy to space. By means of the thermodynamic proficiency, it has been anticipated that the force of convective vortices relies upon the profundity of the convective layer. The atmospheric vortex engine is proposed as a gadget for delivering mechanical energy by methods for artificially produced vortex. The task of the engine is in view of the certainties that the environment is warmed from the base and cooled from the top. By generation of the artificial vortex, it is planned to take out the physical solar updraft tower and decrease the capital of the solar chimney power plants. The study shows the essentials of the atmospheric vortex engine, furthermore, audits the cutting edge in subject. Moreover, the study talks about a thought on using the solar energy as heat source to work the framework. All in all, the framework is attainable and promising for electrical power production.

Keywords: AVE, atmospheric vortex engine, atmosphere, updraft, vortex

Procedia PDF Downloads 161

Authors: Hassam Muazzam

Abstract:

This paper devises an autonomous self-driven vehicle that is capable of taking a disabled person to his/her desired location using three different power sources (gasoline, solar, electric) without any control from the user, avoiding the obstacles in the way. The GPS co-ordinates of the desired location are sent to the main processing board via a GSM module. After the GPS co-ordinates are sent, the path to be followed by the vehicle is devised by Pythagoras theorem. The distance and angle between the present location and the desired location is calculated and then the vehicle starts moving in the desired direction. Meanwhile real-time data from ultrasonic sensors is fed to the board for obstacle avoidance mechanism. Ultrasonic sensors are used to quantify the distance of the vehicle from the object. The distance and position of the object is then used to make decisions regarding the direction of vehicle in order to avoid the obstacles using artificial neural network which is implemented using ATmega1280. Also the vehicle provides the feedback location at remote location.

Keywords: autonomous self-driven vehicle, obstacle avoidance, desired location, pythagoras theorem, neural network, remote location

Procedia PDF Downloads 409

Authors: Cláudia Pereira, Lívia Boeschenstein

Abstract:

This article aims to present an analysis of rock band t-shirts as an element that claims a certain identity in modern-contemporary culture. This work focuses on the study of t-shirts that display the name, related elements and the logo of punk band The Ramones, because of its strong presence in the collective mind along the last decades. As we shall see, it is possible to observe a phenomenon of symbolic transition from the original cultural place of that object. At first, it was a piece of cloth that had been part of a specific subculture and then it became just a generic item diluted by the mainstream. This symbolic transitional phenomenon is significant in many ways and will be discussed furthermore. For the analysis, we begin with a brief introduction to the history of the band, followed by the study about the vintage rock band T-shirts and their meanings. From there, we will turn to a historical contextualization of band T-shirts as a subcultural item and to its redefinition after the appropriation made by the mainstream. To guide this reasoning, it will be used theories about the styles, subcultures and youth culture and about material culture from an anthropological perspective. In addition, we shall see the theories and concepts of social representations in order to understand the ways of using the Ramones’s T-shirt as a representative element of a fashionable style. This T-shirt, after being resignified by the standardization and the massive consumption, no longer symbolizes the punk movement, its behavioral motivations and original policies. Also has little to do with the rage the working class suburbs of London or New York. It seems to be a mute and vague sign of a restricted rebellion, foreseen and framed establishing a stylistic contrast to the designer clothes and good behavior predicted by establishment. It's an item that composes a specific style available on the market, but at the same time is accepted by the mainstream and provides a subcultural association that has some prestige in society. Another perspective is that of resignification loop. As the same way that punk resignified the conventional goods for their own social standards, fashion resignifies what was said to be an object of a subculture and absorbs in their own mass culture standards. Therefore, outsiders to the punk phenomenon wearing Ramones’s T-shirts can be perceived negatively by subcultural members, but at the same time are well received by those who are partially unaware or completely out of subcultural context. For the general public, the stamp of the Ramones’s logo happens to be appreciated as a diffuse allusion to a punk style, since its original meaning has being entirely neutralized.

Keywords: social representations, subcultures, material culture, punk

Procedia PDF Downloads 389

Authors: Thanh Nguyen, Andrei Doncescu, Pierre Siegel

Abstract:

Classification is an important data mining technique and could be used as data filtering in artificial intelligence. The broad application of classification for all kind of data leads to be used in nearly every field of our modern life. Classification helps us to put together different items according to the feature items decided as interesting and useful. In this paper, we compare two classification methods Naïve Bayes and ADTree use to detect spam e-mail. This choice is motivated by the fact that Naive Bayes algorithm is based on probability calculus while ADTree algorithm is based on decision tree. The parameter settings of the above classifiers use the maximization of true positive rate and minimization of false positive rate. The experiment results present classification accuracy and cost analysis in view of optimal classifier choice for Spam Detection. It is point out the number of attributes to obtain a tradeoff between number of them and the classification accuracy.

Keywords: classification, data mining, spam filtering, naive bayes, decision tree

Procedia PDF Downloads 411

Authors: Shahbaz G. Hassan

Abstract:

Water quality models are very important to predict the changes in surface water quality for environmental management. The aim of this paper is to give an overview of the water qualities, and to provide directions for selecting models in specific situation. Water quality models include one kind of model based on a mechanistic approach, while other models simulate water quality without considering a mechanism. Mechanistic models can be widely applied and have capabilities for long-time simulation, with highly complexity. Therefore, more spaces are provided to explain the principle and application experience of mechanistic models. Mechanism models have certain assumptions on rivers, lakes and estuaries, which limits the application range of the model, this paper introduces the principles and applications of water quality model based on the above three scenarios. On the other hand, mechanistic models are more easily to compute, and with no limit to the geographical conditions, but they cannot be used with confidence to simulate long term changes. This paper divides the empirical models into two broad categories according to the difference of mathematical algorithm, models based on artificial intelligence and models based on statistical methods.

Keywords: empirical models, mathematical, statistical, water quality

Procedia PDF Downloads 264

Authors: Yonatan Sverdlov, Shimon Ullman

Abstract:

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to be adjusted to suit the objectives of new tasks, resulting in a phenomenon called catastrophic forgetting. Most approaches to this problem seek a balance between maximizing performance on the new tasks and minimizing the forgetting of previous tasks. In contrast, our approach attempts to maximize the performance of the new task, while ensuring zero forgetting. This is accomplished through the introduction of task-specific modulation parameters for each task, and only these parameters are learned for the new task, after a set of initial tasks have been learned. Through comprehensive experimental evaluations, our model demonstrates superior performance in acquiring and retaining novel tasks that pose difficulties for other multi-task models. This emphasizes the efficacy of our approach in preventing catastrophic forgetting while accommodating the acquisition of new tasks.

Keywords: continual learning, life-long learning, neural analogies, adaptive modulation

Procedia PDF Downloads 70

Authors: Mohamed Raouf Benmakrelouf, Joseph Rynkiewicz

Abstract:

Targeted maximum likelihood estimation (TMLE) is well-established method for causal effect estimation with desirable statistical properties. TMLE is a doubly robust maximum likelihood based approach that includes a secondary targeting step that optimizes the target statistical parameter. A causal interpretation of the statistical parameter requires assumptions of the Rubin causal framework. The causal effect of binary variable, E, on outcomes, Y, is defined in terms of comparisons between two potential outcomes as E[YE=1 − YE=0]. Our aim in this paper is to present an adaptation of TMLE methodology to estimate the causal effect of a non-binary categorical variable, providing a large application. We propose coding on the initial data in order to operate a binarization of the interest variable. For each category, we get a transformation of the non-binary interest variable into a binary variable, taking value 1 to indicate the presence of category (or group of categories) for an individual, 0 otherwise. Such a dummy variable makes it possible to have a pair of potential outcomes and oppose a category (or a group of categories) to another category (or a group of categories). Let E be a non-binary interest variable. We propose a complete disjunctive coding of our variable E. We transform the initial variable to obtain a set of binary vectors (dummy variables), E = (Ee : e ∈ {1, ..., |E|}), where each vector (variable), Ee, takes the value of 0 when its category is not present, and the value of 1 when its category is present, which allows to compute a pairwise-TMLE comparing difference in the outcome between one category and all remaining categories. In order to illustrate the application of our strategy, first, we present the implementation of TMLE to estimate the causal effect of non-binary variable on outcome using simulated data. Secondly, we apply our TMLE adaptation to survey data from the French Political Barometer (CEVIPOF), to estimate the causal effect of education level (A five-level variable) on a potential vote in favor of the French extreme right candidate Jean-Marie Le Pen. Counterfactual reasoning requires us to consider some causal questions (additional causal assumptions). Leading to different coding of E, as a set of binary vectors, E = (Ee : e ∈ {2, ..., |E|}), where each vector (variable), Ee, takes the value of 0 when the first category (reference category) is present, and the value of 1 when its category is present, which allows to apply a pairwise-TMLE comparing difference in the outcome between the first level (fixed) and each remaining level. We confirmed that the increase in the level of education decreases the voting rate for the extreme right party.

Keywords: statistical inference, causal inference, super learning, targeted maximum likelihood estimation

Procedia PDF Downloads 103