Search results for: open dataset

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: consensus, curse of correlation, imbalance classification, rank-based chain-mode ensemble

Procedia PDF Downloads 138

Authors: R Palson Kennedy, P.Kiran Sai

Abstract:

This article introduces machine learning (ML) researchers to the hurdles that geoscience problems present, as well as the opportunities for improvement in both ML and geosciences. This article presents a review from the data life cycle perspective to meet that need. Numerous facets of geosciences present unique difficulties for the study of intelligent systems. Geosciences data is notoriously difficult to analyze since it is frequently unpredictable, intermittent, sparse, multi-resolution, and multi-scale. The first half addresses data science’s essential concepts and theoretical underpinnings, while the second section contains key themes and sharing experiences from current publications focused on each stage of the data life cycle. Finally, themes such as open science, smart data, and team science are considered.

Keywords: Data science, intelligent system, machine learning, big data, data life cycle, recent development, geo science

Procedia PDF Downloads 135

Authors: Lazhar Belkhiri, Ammar Tiri, Lotfi Mouni, Fatma Elhadj Lakouas

Abstract:

This study evaluates the surface water quality in the Kebir Rhumel Basin by analyzing hydrochemical parameters. To assess spatial and temporal variations in water quality, we applied the Water Quality Index (WQI), Mann-Kendall (MK) trend analysis, and hierarchical cluster analysis (HCA). Monthly measurements of eleven hydrochemical parameters were collected across eight stations from January 2016 to December 2020. Calcium and sulfate emerged as the dominant cation and anion, respectively. WQI analysis indicated a high incidence of poor water quality at stations Ain Smara (AS), Beni Haroune (BH), Grarem (GR), and Sidi Khalifa (SK), where 89.5%, 90.6%, 78.2%, and 62.7% of samples, respectively, fell into this category. The MK trend analysis revealed a significant upward trend in WQI at Oued Boumerzoug (ON) and SK stations, signaling temporal deterioration in these areas. HCA grouped the dataset into three clusters, covering approximately 22%, 30%, and 48% of the months, respectively. Within these clusters, specific stations exhibited elevated WQI values: GR and ON in the first cluster, OB and SK in the second, and AS, BH, El Milia (EM), and Hammam Grouz (HG) in the third. Furthermore, approximately 38%, 41%, and 38% of samples in clusters one, two, and three, respectively, were classified as having poor water quality. These findings provide essential insights for policymakers in formulating strategies to restore and manage surface water quality in the region.

Keywords: surface water quality, water quality index (WQI), Mann-Kendall Trend Analysis, hierarchical cluster analysis (HCA), spatial-temporal distribution, Kebir Rhumel Basin

Procedia PDF Downloads 19

Authors: Ayça Utkan Karasu, Elif Balevi Batur, Gülçin Kaymak Karataş

Abstract:

The aim of this study was to examine the efficiency of virtual reality exercises with Nintendo Wii system on balance and independence in motor functions. This randomized controlled assessor-blinded study included 23 stroke inpatients with hemiparesis all within 12 months poststroke. Patients were randomly assigned to control group (n=11) or experimental group (n=12) via block randomization method. Control group participated in a conventional balance rehabilitation programme. Study group received a four-week balance training programme five times per week with a session duration of 20 minutes in addition to the conventional balance rehabilitation programme. Balance was assessed by the Berg’s balance scale, the functional reach test, the timed up and go test, the postural assessment scale for stroke, the static balance index. Also, displacement of centre of pressure sway and centre of pressure displacement during weight shifting was calculated by Emed-SX system. Independence in motor functions was assessed by The Functional Independence Measure (FIM) ambulation and FIM transfer subscales. The outcome measures were evaluated at baseline, 4th week (posttreatment), 8th week (follow-up). Repeated measures analysis of variance was performed for each of the outcome measure. Significant group time interaction was detected in the scores of the Berg’s balance scale, the functional reach test, eyes open anteroposterior and mediolateral center of pressure sway distance, eyes closed anteroposterior center of pressure sway distance, center of pressure displacement during weight shifting to effected side, unaffected side and total centre of pressure displacement during weight shifting (p < 0.05). Time effect was statistically significant in the scores of the Berg’s balance scale, the functional reach test, the timed up and go test, the postural assessment scale for stroke, the static balance index, eyes open anteroposterior and mediolateral center of pressure sway distance, eyes closed mediolateral center of pressure sway distance, the center of pressure displacement during weight shifting to effected side, the functional independence measure ambulation and transfer scores (p < 0.05). Virtual reality exercises with Nintendo Wii system combined with a conventional balance rehabilitation programme enhances balance performance and independence in motor functions in stroke patients.

Keywords: balance, hemiplegia, stroke rehabilitation, virtual reality

Procedia PDF Downloads 221

Authors: Larry Powell, Seth Polsley, Drew Casey, Tracy Hammond

Abstract:

Human activity recognition (HAR) systems have shown positive performance when recognizing repetitive activities like walking, running, and sleeping. Water-based activities are a reasonably new area for activity recognition. However, water-based activity recognition has largely focused on supporting the elite and competitive swimming population, which already has amazing coordination and proper form. Beginner swimmers are not perfect, and activity recognition needs to support the individual motions to help beginners. Activity recognition algorithms are traditionally built around short segments of timed sensor data. Using a time window input can cause performance issues in the machine learning model. The window’s size can be too small or large, requiring careful tuning and precise data segmentation. In this work, we present a method that uses a time window as the initial segmentation, then separates the data based on the change in the sensor value. Our system uses a multi-phase segmentation method that pulls all peaks and valleys for each axis of an accelerometer placed on the swimmer’s lower back. This results in high recognition performance using leave-one-subject-out validation on our study with 20 beginner swimmers, with our model optimized from our final dataset resulting in an F-Score of 0.95.

Keywords: time window, peak/valley segmentation, feature extraction, beginner swimming, activity recognition

Procedia PDF Downloads 123

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 183

Authors: Polina Trusova

Abstract:

The majority of young enterprises is founded and run by teams and develops new, innovative products or services. While problems within the team are considered to be an important reason for the failure of young enterprises, effective teamwork on innovation may be a key success factor. It may require special teamwork design or members’ creativity not needed during work routine. However, little is known about how young enterprises develop innovative solutions in teams, what makes their teamwork special and what influences its effectivity. Extending this knowledge is essential for understanding the success and failure factors for young enterprises. Previous research focused on working on innovation or professional teams in general. Rare studies combining these issues usually concentrate on homogenous groups like IT expert teams in innovation projects of big, well-established firms. The transferability of those studies’ findings to the entrepreneurial context is doubtful because of several reasons why teamwork should differ significantly between big, well-established firms and young enterprises. First, teamwork is conducted by team members, e.g., employees. The personality of employees in young enterprises, in contrast to that of employees in established firms, has been shown to be more similar to the personality of entrepreneurs. As entrepreneurs were found to be more open to experience and show less risk aversion, it may have a positive impact on their teamwork. Persons open to novelty are more likely to develop or accept a creative solution, which is especially important for teamwork on innovation. Secondly, young enterprises are often characterized by a flat hierarchy, so in general, teamwork should be more participative there. It encourages each member (and not only the founder) to produce and discuss innovative ideas, increasing their variety and enabling the team to select the best idea from the larger idea pool. Thirdly, teams in young enterprises are often multidisciplinary. It has some advantages but also increases the risk of internal conflicts making teamwork less effective. Despite the key role of teamwork on innovation and presented barriers for transferring existing evidence to the context of young enterprises, only a few researchers have addressed this issue. In order to close the existing research gap, to explore and understand how innovations are developed in teams of young enterprises and which factors influencing teamwork may be especially relevant for such teams, a qualitative study has been developed. The study consisting of 20 half-structured interviews with (co-)founders of young innovative enterprises in the UK and USA started in September 2017. The interview guide comprises but is not limited to teamwork dimensions discussed in literature like members’ skill or authority differentiation. Data will be evaluated following the rules of qualitative content analysis. First results indicate some factors which may be relevant especially for teamwork in young innovative enterprises. They will enrich the scientific discussion and provide the evidence needed to test a possible causality between identified factors and teamwork effectivity in future research on young innovative enterprises. Results and their discussion can be presented at the conference.

Keywords: innovation, qualitative study, teamwork, young enterprises

Procedia PDF Downloads 198

Authors: Noha Badkook, Maryam Alsubaie, Samaher Dawood, Enas Khairullah

Abstract:

Cloud computing has introduced transformative benefits in data storage and accessibility while posing unique forensic challenges. This paper explores cloud forensics, focusing on investigating and analyzing evidence from cloud environments to address issues such as unauthorized data access, manipulation, and breaches. The research highlights the practical use of open-source forensic tools like Autopsy and Bulk Extractor in real-world scenarios, including unauthorized data sharing via Google Drive and the misuse of personal cloud storage for sensitive information leaks. This work underscores the growing importance of robust forensic procedures and accessible tools in ensuring data security and accountability in cloud ecosystems.

Keywords: cloud forensic, tools, challenge, autopsy, bulk extractor

Procedia PDF Downloads 5

Authors: A. C. Vidal, D. R. Mulinari, C. F. Bandeira, S. R. Montoro

Abstract:

Due to the great effort suffered by foot during movement, is of great importance to count on a shoe that has a proper structure and excellent support tread to prevent the immediate and long-term consequences in all parts of the body. In this sense, new reinforcements of insoles with high impact absorption were developed in this work, from a polyurethane (PU) biocomposite derived from castor oil reinforced or not with palm fibers. These insoles have been obtained from the mixture with polyol prepolymer (diisocyanate) and subsequently were evaluated morphologically, mechanically and by thermal analysis. The results revealed that the biocomposites showed lower flexural strength, higher impact strength and open interconnected pores in their microstructure, but with smaller cells and degradation temperature slightly higher compared to the marketed material, showing interesting properties for a possible application as reinforcement of insoles.

Keywords: composite, polyurethane insole, palm fibers, plantar insoles reinforcement

Procedia PDF Downloads 417

Authors: Fares Hedayatit, Arnauld Joly, Panagiotis Papadimitriou

Abstract:

Many machine learning tasks such as text annotation usually require training over very big datasets, e.g., millions of web documents, that can be represented in a sparse input space. State-of the-art tree-based ensemble algorithms cannot scale to such datasets, since they include operations whose running time is a function of the input space size rather than a function of the non-zero input elements. In this paper, we propose an efficient splitting algorithm to leverage input sparsity within decision tree methods. Our algorithm improves training time over sparse datasets by more than two orders of magnitude and it has been incorporated in the current version of scikit-learn.org, the most popular open source Python machine learning library.

Keywords: big data, sparsely representable data, tree-based models, scalable learning

Procedia PDF Downloads 263

Authors: Bahloul Amel

Abstract:

This study is an attempt to raise the awareness of the stakeholders and the authorities on the sensitivity of Algerian secondary school teachers of English as a Foreign Language about the students’ loss of English language skills learned during formal schooling with effort and at expense and the supposed measures to arrest that loss. Data was collected from secondary school teachers of EFL and analyzed quantitatively using a questionnaire containing open-ended and close-ended questions. The results advocate a consensus about the need for actions to be adopted to make assessment techniques outcome-oriented. Most of the participants were in favor of including curricular activities involving contextualized learning, problem-solving learning critical self-awareness, self and peer-assisted learning, use of computers and internet so as to make learners autonomous.

Keywords: lifelong learning, EFL, contextualized learning, Algeria

Procedia PDF Downloads 348

Authors: Kishore Kumar R., Kaustav Sengupta, Shalini Sood Sehgal, Poornima Santhanam

Abstract:

Fashion is a human expression that is constantly changing. One of the prime factors that consistently influences fashion is the change in colour preferences. The role of colour in our everyday lives is very significant. It subconsciously explains a lot about one’s mindset and mood. Analyzing the colours by extracting them from the outfit images is a critical study to examine the individual’s/consumer behaviour. Several research works have been carried out on extracting colours from images, but to the best of our knowledge, there were no studies that extract colours to specific apparel and identify colour patterns geographically. This paper proposes a framework for accurately extracting colours from T-shirt images and predicting dominant colours geographically. The proposed method consists of two stages: first, a U-Net deep learning model is adopted to segment the T-shirts from the images. Second, the colours are extracted only from the T-shirt segments. The proposed method employs the iMaterialist (Fashion) 2019 dataset for the semantic segmentation task. The proposed framework also includes a mechanism for gathering data and analyzing India’s general colour preferences. From this research, it was observed that black and grey are the dominant colour in different regions of India. The proposed method can be adapted to study fashion’s evolving colour preferences.

Keywords: colour analysis in t-shirts, convolutional neural network, encoder-decoder, k-means clustering, semantic segmentation, U-Net model

Procedia PDF Downloads 111

Authors: Secil Kaya Gulen

Abstract:

Face to face and virtual classrooms that came up with different conditions and environments, but similar purposes have different characteristics. Although virtual classrooms have some similar facilities with face-to-face classes such as program, students, and administrators, they have no walls and corridors. Therefore, students can attend the courses from a distance and can control their own learning spaces. Virtual classrooms defined as simultaneous online environments where students in different places come together at the same time with the guidance of a teacher. Distance education and virtual classes require different intellectual and managerial skills and models. Therefore, for effective use of virtual classrooms, the virtual property should be taken into consideration. One of the most important factors that affect the spread and effective use of the virtual classrooms is the perceptions and opinions of students -as one the main participants-. Student opinions and recommendations are important in terms of providing information about the fulfillment of expectation. This will help to improve the applications and contribute to the more efficient implementations. In this context, ideas and perceptions of the students related to the virtual classrooms, in general, were determined in this study. Advantages and disadvantages of virtual classrooms expected contributions to the educational system and expected characteristics of virtual classrooms have examined in this study. Students of an online distance education graduate program in which all the courses offered by virtual classrooms have asked for their opinions. Online Distance Education Graduate Program has totally 19 students. The questionnaire that consists of open-ended and multiple choice questions sent to these 19 students and finally 12 of them answered the questionnaire. Analysis of the data presented as frequencies and percentages for each item. SPSS for multiple-choice questions and Nvivo for open-ended questions were used for analyses. According to the results obtained by the analysis, participants stated that they did not get any training on virtual classes before the courses; but they emphasize that newly enrolled students should be educated about the virtual classrooms. In addition, all participants mentioned that virtual classroom contribute their personal development and they want to improve their skills by gaining more experience. The participants, who mainly emphasize the advantages of virtual classrooms, express that the dissemination of virtual classrooms will contribute to the Turkish Education System. Within the advantages of virtual classrooms, ‘recordable and repeatable lessons’ and ‘eliminating the access and transportation costs’ are most common advantages according to the participants. On the other hand, they mentioned ‘technological features and keyboard usage skills affect the attendance’ is the most common disadvantage. Participants' most obvious problem during virtual lectures is ‘lack of technical support’. Finally ‘easy to use’, ‘support possibilities’, ‘communication level’ and ‘flexibility’ come to the forefront in the scope of expected features of virtual classrooms. Last of all, students' opinions about the virtual classrooms seems to be generally positive. Designing and managing virtual classrooms according to the prioritized features will increase the students’ satisfaction and will contribute to improve applications that are more effective.

Keywords: distance education, virtual classrooms, higher education, e-learning

Procedia PDF Downloads 269

Authors: B. G. C. Ahodode, S. Fekkaklouhail

Abstract:

Following the triple helix theory, this study aims to evaluate the innovation system effect on African countries’ competitiveness by taking into account external contributions; according to the extent that developing countries (especially African countries) are characterized by weak innovation systems whose synergy operates more at the foreign level than domestic and global. To do this, we used the correlation test, parsimonious regression techniques, and panel estimation between 2013 and 2016. Results show that the degree of innovation synergy has a significant effect on competitiveness in Africa. Specifically, while the opening system (OPESYS) and social system (SOCSYS) contribute respectively in importance order to 0.634 and 0.284 (at 1%) significant points of increase in the GCI, the political system (POLSYS) and educational system (EDUSYS) only increase it to 0.322 and 0.169 at 5% significance level while the effect of the economic system (ECOSYS) is not significant on Global Competitiveness Index.

Keywords: innovation system, innovation, competitiveness, Africa

Procedia PDF Downloads 69

Authors: Omair Ghori, Anton Stadler, Stefan Wilk, Wolfgang Effelsberg

Abstract:

Fire-related incidents account for extensive loss of life and material damage. Quick and reliable detection of occurring fires has high real world implications. Whereas a major research focus lies on the detection of outdoor fires, indoor camera-based fire detection is still an open issue. Cameras in combination with computer vision helps to detect flames and smoke more quickly than conventional fire detectors. In this work, we present a computer vision-based smoke detection algorithm based on contrast changes and a multi-step classification. This work accelerates computer vision-based fire detection considerably in comparison with classical indoor-fire detection.

Keywords: contrast analysis, early fire detection, video smoke detection, video surveillance

Procedia PDF Downloads 447

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 340

Authors: Suchao Donpudsa, Anchalee Tassanakajon, Vichien Rimphanitchayakit

Abstract:

A crustin gene, LV-SWD1, previously found in the hemocyte cDNA library of Litopenaeus vannamei, contains the open reading frames of 288 bp encoding a putative protein of 96 amino acid residues. The putative signal peptides of the LV-SWD1 were identified using the online SignalP 3.0 with predicted cleavage sites between Ala24-Val25, resulting in 72 residue mature protein with calculated molecular mass of 7.4 kDa and predicted pI of 8.5. This crustin contains a Arg-Pro rich region at the amino-terminus and a single whey acidic protein (WAP) domain at the carboxyl-terminus. In order to characterize their properties and biological activities, the recombinant crustin protein was produced in the Escherichia coli expression system. Antimicrobial assays showed that the growth of Bacillus subtilis was inhibited by this recombinant crustin with MIC of about 25-50 µM.

Keywords: crustin, single whey acidic protein, Litopenaeus vannamei, antimicrobial activity

Procedia PDF Downloads 244

Authors: Stephen Kirkup

Abstract:

This paper discusses the implementation of the boundary element method (BEM) on an Excel spreadsheet and how it can be used in teaching vector calculus and simulation. There are two separate spreadheets, within which Laplace equation is solved by the BEM in two dimensions (LIBEM2) and axisymmetric three dimensions (LBEMA). The main algorithms are implemented in the associated programming language within Excel, Visual Basic for Applications (VBA). The BEM only requires a boundary mesh and hence it is a relatively accessible method. The BEM in the open spreadsheet environment is demonstrated as being useful as an aid to teaching and learning. The application of the BEM implemented on a spreadsheet for educational purposes in introductory vector calculus and simulation is explored. The development of assignment work is discussed, and sample results from student work are given. The spreadsheets were found to be useful tools in developing the students’ understanding of vector calculus and in simulating heat conduction.

Keywords: boundary element method, Laplace’s equation, vector calculus, simulation, education

Procedia PDF Downloads 163

Authors: Eva Masson, Andrea Kübler

Abstract:

Anxiety disorders (AD) are the most prevalent psychological disorders. However, far from most affected individuals are diagnosed and receive treatment. This gap is probably due to the diagnosis criteria, relying on symptoms (according to the DSM-5 definition) with no objective biomarker. Approach-avoidance conflict tasks are one common approach to simulate such disorders in a lab setting, with most of the paradigms focusing on the relationships between behavior and neurophysiology. Approach-avoidance conflict tasks typically place participants in a situation where they have to make a decision that leads to both positive and negative outcomes, thereby sending conflicting signals that trigger the Behavioral Inhibition System (BIS). Furthermore, behavioral validation of such paradigms adds credibility to the tasks – with overt conflict behavior, it is safer to assume that the task actually induced a conflict. Some of those tasks have linked asymmetrical frontal brain activity to induced conflicts and the BIS. However, there is currently no consensus for the direction of the frontal activation. The authors present here a modified version of the T-Maze paradigm, a motivational conflict desktop task, in which behavior is recorded simultaneously to the recording of high-density EEG (HD-EEG). Methods: In this within-subject design, HD-EEG and behavior of 35 healthy participants was recorded. EEG data was collected with a 128 channels sponge-based system. The motivational conflict desktop task consisted of three blocks of repeated trials. Each block was designed to record a slightly different behavioral pattern, to increase the chances of eliciting conflict. This variety of behavioral patterns was however similar enough to allow comparison of the number of trials categorized as ‘overt conflict’ between the blocks. Results: Overt conflict behavior was exhibited in all blocks, but always for under 10% of the trials, in average, in each block. However, changing the order of the paradigms successfully introduced a ‘reset’ of the conflict process, therefore providing more trials for analysis. As for the EEG correlates, the authors expect a different pattern for trials categorized as conflict, compared to the other ones. More specifically, we expect an elevated alpha frequency power in the left frontal electrodes at around 200ms post-cueing, compared to the right one (relative higher right frontal activity), followed by an inversion around 600ms later. Conclusion: With this comprehensive approach of a psychological mechanism, new evidence would be brought to the frontal asymmetry discussion, and its relationship with the BIS. Furthermore, with the present task focusing on a very particular type of motivational approach-avoidance conflict, it would open the door to further variations of the paradigm to introduce different kinds of conflicts involved in AD. Even though its application as a potential biomarker sounds difficult, because of the individual reliability of both the task and peak frequency in the alpha range, we hope to open the discussion for task robustness for neuromodulation and neurofeedback future applications.

Keywords: anxiety, approach-avoidance conflict, behavioral inhibition system, EEG

Procedia PDF Downloads 40

Authors: Hong Dongchen, Chen Qiuxiao, Wu Shuang

Abstract:

Systematic science reveals the complex nonlinear mechanisms of behaviour in urban system. However, in China, when the current city planners face with the system, most of them are still taking simple linear thinking to consider the open complex giant system. This paper introduces the hyper-cycle theory, which is one of the basis theories of systematic science, based on the analysis of the reasons why the current urban planning failed, and proposals for optimization ideas that urban planning compilation should change, from controlling quantitative to the changes of relationship, from blueprint planning to progressive planning based on the nonlinear characteristics and from management control to dynamically monitor feedback.

Keywords: systematic science, hyper-cycle theory, urban planning, urban management

Procedia PDF Downloads 406

Authors: L. Yu, W. K. Li, S. K. Ong, A. Y. C. Nee

Abstract:

In this paper, a scalable augmented reality framework for handheld devices is presented. The presented framework is enabled by using a server-client data communication structure, in which the search for tracking targets among a database of images is performed on the server-side while pixel-wise 3D tracking is performed on the client-side, which, in this case, is a handheld mobile device. Image search on the server-side adopts a residual-enhanced image descriptors representation that gives the framework a scalability property. The tracking algorithm on the client-side is based on a gravity-aligned feature descriptor which takes the advantage of a sensor-equipped mobile device and an optimized intensity-based image alignment approach that ensures the accuracy of 3D tracking. Automatic content streaming is achieved by using a key-frame selection algorithm, client working phase monitoring and standardized rules for content communication between the server and client. The recognition accuracy test performed on a standard dataset shows that the method adopted in the presented framework outperforms the Bag-of-Words (BoW) method that has been used in some of the previous systems. Experimental test conducted on a set of video sequences indicated the real-time performance of the tracking system with a frame rate at 15-30 frames per second. The presented framework is exposed to be functional in practical situations with a demonstration application on a campus walk-around.

Keywords: augmented reality framework, server-client model, vision-based tracking, image search

Procedia PDF Downloads 275

Authors: Jack R. McKenzie, Peter A. Appleby, Thomas House, Neil Walton

Abstract:

Cold-start is a notoriously difficult problem which can occur in recommendation systems, and arises when there is insufficient information to draw inferences for users or items. To address this challenge, a contextual bandit algorithm – the Fast Approximate Bayesian Contextual Cold Start Learning algorithm (FAB-COST) – is proposed, which is designed to provide improved accuracy compared to the traditionally used Laplace approximation in the logistic contextual bandit, while controlling both algorithmic complexity and computational cost. To this end, FAB-COST uses a combination of two moment projection variational methods: Expectation Propagation (EP), which performs well at the cold start, but becomes slow as the amount of data increases; and Assumed Density Filtering (ADF), which has slower growth of computational cost with data size but requires more data to obtain an acceptable level of accuracy. By switching from EP to ADF when the dataset becomes large, it is able to exploit their complementary strengths. The empirical justification for FAB-COST is presented, and systematically compared to other approaches on simulated data. In a benchmark against the Laplace approximation on real data consisting of over 670, 000 impressions from autotrader.co.uk, FAB-COST demonstrates at one point increase of over 16% in user clicks. On the basis of these results, it is argued that FAB-COST is likely to be an attractive approach to cold-start recommendation systems in a variety of contexts.

Keywords: cold-start learning, expectation propagation, multi-armed bandits, Thompson Sampling, variational inference

Procedia PDF Downloads 108

Authors: Pattra Pukdeekiat, Siriluk Ruangrungrote

Abstract:

This work was originated to precisely determine direct solar radiation by using atmospheric physics models since the accurate prediction of solar radiation is necessary and useful for solar energy applications including atmospheric research. The possible models and techniques for a calculation of regional direct solar radiation were challenging and compulsory for the case of unavailable instrumental measurement. The investigation was mathematically governed by six astronomical parameters i.e. declination (δ), hour angle (ω), solar time, solar zenith angle (θz), extraterrestrial radiation (Iso) and eccentricity (E0) along with two atmospheric parameters i.e. air mass (mr) and dew point temperature at Bangna meteorological station (13.67° N, 100.61° E) in Bangkok, Thailand. Analyses of five models of solar radiation determination with the assumption of clear sky were applied accompanied by three statistical tests: Mean Bias Difference (MBD), Root Mean Square Difference (RMSD) and Coefficient of determination (R2) in order to validate the accuracy of obtainable results. The calculated direct solar radiation was in a range of 491-505 Watt/m2 with relative percentage error 8.41% for winter and 532-540 Watt/m2 with relative percentage error 4.89% for summer 2014. Additionally, dataset of seven continuous days, representing both seasons were considered with the MBD, RMSD and R2 of -0.08, 0.25, 0.86 and -0.14, 0.35, 3.29, respectively, which belong to Kumar model for winter and CSR model for summer. In summary, the determination of direct solar radiation based on atmospheric models and empirical equations could advantageously provide immediate and reliable values of the solar components for any site in the region without a constraint of actual measurement.

Keywords: atmospheric physics models, astronomical parameters, atmospheric parameters, clear sky condition

Procedia PDF Downloads 409

Authors: A. M. John-Otumu, M. M. Rahman, M. C. Onuoha, E. P. Ojonugwa

Abstract:

A Convolutional Neural Network (CNN) model for predicting Lassa fever was built using Python 3.8.0 programming language, alongside Keras 2.2.4 and TensorFlow 2.6.1 libraries as the development environment in order to reduce the current high risk of Lassa fever in West Africa, particularly in Nigeria. The study was prompted by some major flaws in existing conventional laboratory equipment for diagnosing Lassa fever (RT-PCR), as well as flaws in AI-based techniques that have been used for probing and prognosis of Lassa fever based on literature. There were 15,679 blood smear microscopic image datasets collected in total. The proposed model was trained on 70% of the dataset and tested on 30% of the microscopic images in avoid overfitting. A 3x3x3 convolution filter was also used in the proposed system to extract features from microscopic images. The proposed CNN-based model had a recall value of 96%, a precision value of 93%, an F1 score of 95%, and an accuracy of 94% in predicting and accurately classifying the images into clean or infected samples. Based on empirical evidence from the results of the literature consulted, the proposed model outperformed other existing AI-based techniques evaluated. If properly deployed, the model will assist physicians, medical laboratory scientists, and patients in making accurate diagnoses for Lassa fever cases, allowing the mortality rate due to the Lassa fever virus to be reduced through sound decision-making.

Keywords: artificial intelligence, ANN, blood smear, CNN, deep learning, Lassa fever

Procedia PDF Downloads 120

Authors: S. Ali, R. Yunus, A. Arif, Y. Ayaz, M. Baber Sial, R. Asif, N. Naseer, M. Jawad Khan

Abstract:

In this study, we have proposed a gesture to emotion recognition method using flex sensors mounted on metacarpophalangeal joints. The flex sensors are fixed in a wearable glove. The data from the glove are sent to PC using Wi-Fi. Four gestures: finger pointing, thumbs up, fist open and fist close are performed by five subjects. Each gesture is categorized into sad, happy, and excited class based on the velocity and acceleration of the hand gesture. Seventeen inspectors observed the emotions and hand gestures of the five subjects. The emotional state based on the investigators assessment and acquired movement speed data is compared. Overall, we achieved 77% accurate results. Therefore, the proposed design can be used for emotional state detection applications.

Keywords: emotion identification, emotion models, gesture recognition, user perception

Procedia PDF Downloads 285

Authors: Benkouiten Imene, Chabli Ouerdia, Boutoutaou Hamid, Kadri Nesrine, Bouledroua Omar

Abstract:

Algeria is actively enhancing gas productivity by augmenting the supply flow. However, this effort has led to increased internal pressure, posing a potential risk to the pipeline's integrity, particularly in the presence of corrosion defects. Sonatrach relies on a vast network of pipelines spanning 24,000 kilometers for the transportation of gas and oil. The aging of these pipelines raises the likelihood of corrosion both internally and externally, heightening the risk of ruptures. To address this issue, a comprehensive inspection is imperative, utilizing specialized scraping tools. These advanced tools furnish a detailed assessment of all pipeline defects. It is essential to recalculate the pressure parameters to safeguard the corroded pipeline's integrity while ensuring the continuity of production. In this context, Sonatrach employs symbolic pressure limit calculations, such as ASME B31G (2009) and the modified ASME B31G (2012). The aim of this study is to perform a comparative analysis of various limit pressure calculation methods documented in the literature, namely DNV RP F-101, SHELL, P-CORRC, NETTO, and CSA Z662. This comparative assessment will be based on a dataset comprising 329 burst tests published in the literature. Ultimately, we intend to introduce a novel approach grounded in the finite element method, employing ANSYS software.

Keywords: pipeline burst pressure, burst test, corrosion defect, corroded pipeline, finite element method

Procedia PDF Downloads 58

Authors: Vinu Elias Jacob, Manoj Kumar Kini

Abstract:

Disasters of all types are occurring more frequently and are becoming more costly than ever due to various manmade factors including climate change. A better utilisation of the concept of governance and management within disaster risk reduction is inevitable and of utmost importance. There is a need to explore the role of pre- and post-disaster public policies. The role of urban planning/design in shaping the opportunities of households, individuals and collectively the settlements for achieving recovery has to be explored. Governance strategies that can better support the integration of disaster risk reduction and management has to be examined. The main aim is to thereby build the resilience of individuals and communities and thus, the states too. Resilience is a term that is usually linked to the fields of disaster management and mitigation, but today has become an integral part of planning and design of cities. Disaster resilience broadly describes the ability of an individual or community to 'bounce back' from disaster impacts, through improved mitigation, preparedness, response, and recovery. The growing population of the world has resulted in the inflow and use of resources, creating a pressure on the various natural systems and inequity in the distribution of resources. This makes cities vulnerable to multiple attacks by both natural and man-made disasters. Each urban area needs elaborate studies and study based strategies to proceed in the discussed direction. Cochin in Kerala is the fastest and largest growing city with a population of more than 26 lakhs. The main concern that has been looked into in this paper is making cities resilient by designing a framework of strategies based on urban design principles for an immediate response system especially focussing on the city of Cochin, Kerala, India. The paper discusses, understanding the spatial transformations due to disasters and the role of spatial planning in the context of significant disasters. The paper also aims in developing a model taking into consideration of various factors such as land use, open spaces, transportation networks, physical and social infrastructure, building design, and density and ecology that can be implemented in any city of any context. Guidelines are made for the smooth evacuation of people through hassle-free transport networks, protecting vulnerable areas in the city, providing adequate open spaces for shelters and gatherings, making available basic amenities to affected population within reachable distance, etc. by using the tool of urban design. Strategies at the city level and neighbourhood level have been developed with inferences from vulnerability analysis and case studies.

Keywords: disaster management, resilience, spatial planning, spatial transformations

Procedia PDF Downloads 296

Authors: Tae-Uk Yun, Pullip Chung, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection using machine learning techniques over the past years. But, there have been no prior studies proposed an automated fake news detection method for Korean news to our best knowledge. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (topic modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as logistic regression, backpropagation network, support vector machine, and deep neural network can be applied. To validate the effectiveness of the proposed method, we collected about 200 short Korean news from Seoul National University’s FactCheck. which provides with detailed analysis reports from 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

Keywords: fake news detection, Korean news, machine learning, text mining

Procedia PDF Downloads 275

Authors: Ana Hol

Abstract:

Digital systems are in the cognitive wave of the eTransformations and are now extensively aimed at meeting the individuals’ demands, both those of customers requiring services and those of service providers. It is also apparent that successful future systems will not just simply open doors to the traditional owners/users to offer and receive services such as Uber for example does today, but will in the future require more customized and cognitively enabled infrastructures that will be responsive to the system user’s needs. To be able to identify what is required for such systems, this research reviews the historical and the current effects of the eTransformation process by studying: 1. eTransitions of company websites and mobile applications, 2. Emergence of new sheared economy business models as Uber and, 3. New requirements for demand driven, cognitive systems capable of learning and just in time decision making. Based on the analysis, this study proposes a Cognitive eTransformation Framework capable of guiding implementations of new responsive and user aware systems.

Keywords: system implementations, AI supported systems, cognitive systems, eTransformation

Procedia PDF Downloads 238

Authors: C. L. Huang, J. J. Sia

Abstract:

The interest-based social networks, also known as social bookmark sharing systems, are useful platforms for people to conveniently read and collect internet resources. These platforms also providing function of social networks, and users can share and explore internet resources from the social networks. Providing personalized internet resources to users is an important issue on these platforms. This study uses two types of relationship on the social networks—following and follower and proposes a collaborative recommender system, consisting of two main steps. First, this study calculates the relationship strength between the target user and the target user's followings and followers to find top-N similar neighbors. Second, from the top-N similar neighbors, the articles (internet resources) that may interest the target user are recommended to the target user. In this system, users can efficiently obtain recent, related and diverse internet resources (knowledge) from the interest-based social network. This study collected the experimental dataset from Diigo, which is a famous bookmark sharing system. The experimental results show that the proposed recommendation model is more accurate than two traditional baseline recommendation models but slightly lower than the cosine model in accuracy. However, in the metrics of the diversity and executing time, our proposed model outperforms the cosine model.

Keywords: recommender systems, social networks, tagging, bookmark sharing systems, collaborative recommender systems, knowledge management

Procedia PDF Downloads 173