Search results for: neural signature

Authors: Gideon C. Joseph

Abstract:

The ability to localize mobile devices is quite important, as some applications may require location information of these devices to operate or deliver better services to the users. Although there are several ways of acquiring location data of mobile devices, the WLAN fingerprinting approach has been considered in this work. This approach uses the Received Signal Strength Indicator (RSSI) measurement as a function of the position of the mobile device. RSSI is a quantitative technique of describing the radio frequency power carried by a signal. RSSI may be used to determine RF link quality and is very useful in dense traffic scenarios where interference is of major concern, for example, indoor environments. This research aims to design a system that can predict the location of a mobile device, when supplied with the mobile’s RSSIs. The developed system takes as input the RSSIs relating to the mobile device, and outputs parameters that describe the location of the device such as the longitude, latitude, floor, and building. The relationship between the Received Signal Strengths (RSSs) of mobile devices and their corresponding locations is meant to be modelled; hence, subsequent locations of mobile devices can be predicted using the developed model. It is obvious that describing mathematical relationships between the RSSIs measurements and localization parameters is one option to modelling the problem, but the complexity of such an approach is a serious turn-off. In contrast, we propose an intelligent system that can learn the mapping of such RSSIs measurements to the localization parameters to be predicted. The system is capable of upgrading its performance as more experiential knowledge is acquired. The most appealing consideration to using such a system for this task is that complicated mathematical analysis and theoretical frameworks are excluded or not needed; the intelligent system on its own learns the underlying relationship in the supplied data (RSSI levels) that corresponds to the localization parameters. These localization parameters to be predicted are of two different tasks: Longitude and latitude of mobile devices are real values (regression problem), while the floor and building of the mobile devices are of integer values or categorical (classification problem). This research work presents artificial neural network based intelligent systems to model the relationship between the RSSIs predictors and the mobile device localization parameters. The designed systems were trained and validated on the collected WLAN fingerprint database. The trained networks were then tested with another supplied database to obtain the performance of trained systems on achieved Mean Absolute Error (MAE) and error rates for the regression and classification tasks involved therein.

Keywords: indoor localization, WLAN fingerprinting, neural networks, classification, regression

Procedia PDF Downloads 311

Authors: Yeliz Ekinci, Melis Koyuncu

Abstract:

Successful planning of solid waste management systems requires successful prediction of the amount of solid waste generated in an area. Waste management planning can protect the environment and human health, hence it is tremendously important for countries. The lack of information in waste generation can cause many environmental and health problems. Turkey is a country that plans to join European Union, hence, solid waste management is one of the most significant criteria that should be handled in order to be a part of this community. Solid waste management system requires a good forecast of solid waste generation. Thus, this study aims to forecast solid waste generation in Turkey. Artificial Neural Network and Linear Regression models will be used for this aim. Many models will be run and the best one will be selected based on some predetermined performance measures.

Keywords: forecast, solid waste generation, solid waste management, Turkey

Procedia PDF Downloads 467

Authors: Farid Khosravikia, Patricia Clayton

Abstract:

The main objective of this study is to evaluate the advantages and disadvantages of various machine learning techniques in forecasting ground-motion intensity measures given source characteristics, source-to-site distance, and local site condition. Intensity measures such as peak ground acceleration and velocity (PGA and PGV, respectively) as well as 5% damped elastic pseudospectral accelerations at different periods (PSA), are indicators of the strength of shaking at the ground surface. Estimating these variables for future earthquake events is a key step in seismic hazard assessment and potentially subsequent risk assessment of different types of structures. Typically, linear regression-based models, with pre-defined equations and coefficients, are used in ground motion prediction. However, due to the restrictions of the linear regression methods, such models may not capture more complex nonlinear behaviors that exist in the data. Thus, this study comparatively investigates potential benefits from employing other machine learning techniques as a statistical method in ground motion prediction such as Artificial Neural Network, Random Forest, and Support Vector Machine. The algorithms are adjusted to quantify event-to-event and site-to-site variability of the ground motions by implementing them as random effects in the proposed models to reduce the aleatory uncertainty. All the algorithms are trained using a selected database of 4,528 ground-motions, including 376 seismic events with magnitude 3 to 5.8, recorded over the hypocentral distance range of 4 to 500 km in Oklahoma, Kansas, and Texas since 2005. The main reason of the considered database stems from the recent increase in the seismicity rate of these states attributed to petroleum production and wastewater disposal activities, which necessities further investigation in the ground motion models developed for these states. Accuracy of the models in predicting intensity measures, generalization capability of the models for future data, as well as usability of the models are discussed in the evaluation process. The results indicate the algorithms satisfy some physically sound characteristics such as magnitude scaling distance dependency without requiring pre-defined equations or coefficients. Moreover, it is shown that, when sufficient data is available, all the alternative algorithms tend to provide more accurate estimates compared to the conventional linear regression-based method, and particularly, Random Forest outperforms the other algorithms. However, the conventional method is a better tool when limited data is available.

Keywords: artificial neural network, ground-motion models, machine learning, random forest, support vector machine

Procedia PDF Downloads 91

Authors: Edgar Santoyo, Daniel Perez-Zarate, Agustin Acevedo, Lorena Diaz-Gonzalez, Mirna Guevara

Abstract:

Four new gas geothermometers have been derived from a multivariate geo chemometric analysis of a geothermal fluid chemistry database, two of which use the natural logarithm of CO₂ and H2S concentrations (mmol/mol), respectively, and the other two use the natural logarithm of the H₂S/H₂ and CO₂/H₂ ratios. As a strict compilation criterion, the database was created with gas-phase composition of fluids and bottomhole temperatures (BHTM) measured in producing wells. The calibration of the geothermometers was based on the geochemical relationship existing between the gas-phase composition of well discharges and the equilibrium temperatures measured at bottomhole conditions. Multivariate statistical analysis together with the use of artificial neural networks (ANN) was successfully applied for correlating the gas-phase compositions and the BHTM. The predicted or simulated bottomhole temperatures (BHTANN), defined as output neurons or simulation targets, were statistically compared with measured temperatures (BHTM). The coefficients of the new geothermometers were obtained from an optimized self-adjusting training algorithm applied to approximately 2,080 ANN architectures with 15,000 simulation iterations each one. The self-adjusting training algorithm used the well-known Levenberg-Marquardt model, which was used to calculate: (i) the number of neurons of the hidden layer; (ii) the training factor and the training patterns of the ANN; (iii) the linear correlation coefficient, R; (iv) the synaptic weighting coefficients; and (v) the statistical parameter, Root Mean Squared Error (RMSE) to evaluate the prediction performance between the BHTM and the simulated BHTANN. The prediction performance of the new gas geothermometers together with those predictions inferred from sixteen well-known gas geothermometers (previously developed) was statistically evaluated by using an external database for avoiding a bias problem. Statistical evaluation was performed through the analysis of the lowest RMSE values computed among the predictions of all the gas geothermometers. The new gas geothermometers developed in this work have been successfully used for predicting subsurface temperatures in high-temperature geothermal systems of Mexico (e.g., Los Azufres, Mich., Los Humeros, Pue., and Cerro Prieto, B.C.) as well as in a blind geothermal system (known as Acoculco, Puebla). The last results of the gas geothermometers (inferred from gas-phase compositions of soil-gas bubble emissions) compare well with the temperature measured in two wells of the blind geothermal system of Acoculco, Puebla (México). Details of this new development are outlined in the present research work. Acknowledgements: The authors acknowledge the funding received from CeMIE-Geo P09 project (SENER-CONACyT).

Keywords: artificial intelligence, gas geochemistry, geochemometrics, geothermal energy

Procedia PDF Downloads 307

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 95

Authors: Panda Krouse

Abstract:

This work is a marriage of the science of Applied Behavioral Analysis and an educator’s look at Neuroscience. The focus is integrating what we know about the anatomy of the brain in autism and evidence-based practices in education. It is a bold attempt to present links between neurological research and the application of evidence-based practices in education. In researching for this work, no discovery of articles making these connections was made. Consideration of the areas of structural differences in the brain are aligned with evidence-based strategies. A brief literary review identifies how identified areas affect overt behavior, which is what, as educators, is what we can see and measure. Giving further justification and validation of our practices in education from a second scientific field is significant for continued improvement in intervention for students on the autism spectrum.

Keywords: autism, evidence based practices, neurological differences, education intervention

Procedia PDF Downloads 30

Authors: Anup Anand Deshmukh, Catherine Soladie, Renaud Seguier

Abstract:

Emotion plays a key role in many applications like healthcare, to gather patients’ emotional behavior. Unlike typical ASR (Automated Speech Recognition) problems which focus on 'what was said', it is equally important to understand 'how it was said.' There are certain emotions which are given more importance due to their effectiveness in understanding human feelings. In this paper, we propose an approach that models human stress from audio signals. The research challenge in speech emotion detection is finding the appropriate set of acoustic features corresponding to an emotion. Another difficulty lies in defining the very meaning of emotion and being able to categorize it in a precise manner. Supervised Machine Learning models, including state of the art Deep Learning classification methods, rely on the availability of clean and labelled data. One of the problems in affective computation is the limited amount of annotated data. The existing labelled emotions datasets are highly subjective to the perception of the annotator. We address the first issue of feature selection by exploiting the use of traditional MFCC (Mel-Frequency Cepstral Coefficients) features in Convolutional Neural Network. Our proposed Emo-CNN (Emotion-CNN) architecture treats speech representations in a manner similar to how CNN’s treat images in a vision problem. Our experiments show that Emo-CNN consistently and significantly outperforms the popular existing methods over multiple datasets. It achieves 90.2% categorical accuracy on the Emo-DB dataset. We claim that Emo-CNN is robust to speaker variations and environmental distortions. The proposed approach achieves 85.5% speaker-dependant categorical accuracy for SAVEE (Surrey Audio-Visual Expressed Emotion) dataset, beating the existing CNN based approach by 10.2%. To tackle the second problem of subjectivity in stress labels, we use Lovheim’s cube, which is a 3-dimensional projection of emotions. Monoamine neurotransmitters are a type of chemical messengers in the brain that transmits signals on perceiving emotions. The cube aims at explaining the relationship between these neurotransmitters and the positions of emotions in 3D space. The learnt emotion representations from the Emo-CNN are mapped to the cube using three component PCA (Principal Component Analysis) which is then used to model human stress. This proposed approach not only circumvents the need for labelled stress data but also complies with the psychological theory of emotions given by Lovheim’s cube. We believe that this work is the first step towards creating a connection between Artificial Intelligence and the chemistry of human emotions.

Keywords: deep learning, brain chemistry, emotion perception, Lovheim's cube

Procedia PDF Downloads 123

Authors: Hee Sun (Sunny) Choi, Gerhard Bruyns, Wang Zhang, Sky Cheng, Saijal Sharma

Abstract:

The main focus of this paper is to propose a comprehensive framework for the cognitive measurement and modelling of the built environment. This will involve exploring and measuring neural mechanisms. The aim is to create a foundation for further studies in this field that are consistent and rigorous. Additionally, this framework will facilitate collaboration with cognitive neuroscientists by establishing a shared conceptual basis. The goal of this research is to develop a human-centric approach for urban design that is scientific and measurable, producing a set of urban design guidelines that incorporate cognitive measurement and modelling. By doing so, the broader intention is to design urban spaces that prioritize human needs and well-being, making them more liveable.

Keywords: vertical urbanism, human centric design, spatial cognition and psychology, vertical urban design guidelines

Procedia PDF Downloads 47

Authors: P. Shrivastava, A. Shukla, K. Verma, S. Rungta

Abstract:

Parkinson's disease is a chronic neurological disorder that directly affects human gait. It leads to slowness of movement, causes muscle rigidity and tremors. Gait serve as a primary outcome measure for studies aiming at early recognition of disease. Using gait techniques, this paper implements efficient binary bat algorithm for an early detection of Parkinson's disease by selecting optimal features required for classification of affected patients from others. The data of 166 people, both fit and affected is collected and optimal feature selection is done using PSO and Bat algorithm. The reduced dataset is then classified using neural network. The experiments indicate that binary bat algorithm outperforms traditional PSO and genetic algorithm and gives a fairly good recognition rate even with the reduced dataset.

Keywords: parkinson, gait, feature selection, bat algorithm

Procedia PDF Downloads 511

Authors: Thor Alexis Sazon, Alexander Guzman-Urbina, Yasuhiro Fukushima

Abstract:

This study outlines the method of how to develop a surrogate life cycle model based on fuzzy logic using three fuzzy inference methods: (1) the conventional Fuzzy Inference System (FIS), (2) the hybrid system of Data Analytics and Fuzzy Inference (DAFIS), which uses data clustering for defining the membership functions, and (3) the Adaptive-Neuro Fuzzy Inference System (ANFIS), a combination of fuzzy inference and artificial neural network. These methods were demonstrated with a case study where the Global Warming Potential (GWP) and the Levelized Cost of Energy (LCOE) of solar photovoltaic (PV) were estimated using Solar Irradiation, Module Efficiency, and Performance Ratio as inputs. The effects of using different fuzzy inference types, either Sugeno- or Mamdani-type, and of changing the number of input membership functions to the error between the calibration data and the model-generated outputs were also illustrated. The solution spaces of the three methods were consequently examined with a sensitivity analysis. ANFIS exhibited the lowest error while DAFIS gave slightly lower errors compared to FIS. Increasing the number of input membership functions helped with error reduction in some cases but, at times, resulted in the opposite. Sugeno-type models gave errors that are slightly lower than those of the Mamdani-type. While ANFIS is superior in terms of error minimization, it could generate solutions that are questionable, i.e. the negative GWP values of the Solar PV system when the inputs were all at the upper end of their range. This shows that the applicability of the ANFIS models highly depends on the range of cases at which it was calibrated. FIS and DAFIS generated more intuitive trends in the sensitivity runs. DAFIS demonstrated an optimal design point wherein increasing the input values does not improve the GWP and LCOE anymore. In the absence of data that could be used for calibration, conventional FIS presents a knowledge-based model that could be used for prediction. In the PV case study, conventional FIS generated errors that are just slightly higher than those of DAFIS. The inherent complexity of a Life Cycle study often hinders its widespread use in the industry and policy-making sectors. While the methodology does not guarantee a more accurate result compared to those generated by the Life Cycle Methodology, it does provide a relatively simpler way of generating knowledge- and data-based estimates that could be used during the initial design of a system.

Keywords: solar photovoltaic, fuzzy logic, inference system, artificial neural networks

Procedia PDF Downloads 126

Authors: M. Pilgun

Abstract:

The report presents the results of a study of the specifics of speech perception by actors of video hosting services on the material of urban planning conflicts. To analyze the content, the multimodal approach using neural network technologies is employed. Analysis of word associations and associative networks of relevant stimulus revealed the evaluative reactions of the actors. Analysis of the data identified key topics that generated negative and positive perceptions from the participants. The calculation of social stress and social well-being indices based on user-generated content made it possible to build a rating of road transport construction objects according to the degree of negative and positive perception by actors.

Keywords: social media, speech perception, video hosting, networks

Procedia PDF Downloads 118

Authors: Reza Bazargan lari, Mohammad H. Fattahi

Abstract:

Natural resources management including water resources requires reliable estimations of time variant environmental parameters. Small improvements in the estimation of environmental parameters would result in grate effects on managing decisions. Noise reduction using wavelet techniques is an effective approach for pre-processing of practical data sets. Predictability enhancement of the river flow time series are assessed using fractal approaches before and after applying wavelet based pre-processing. Time series correlation and persistency, the minimum sufficient length for training the predicting model and the maximum valid length of predictions were also investigated through a fractal assessment.

Keywords: wavelet, de-noising, predictability, time series fractal analysis, valid length, ANN

Procedia PDF Downloads 341

Authors: Su Yin Chiam, Zhipeng Ding, Guang Yang, Danny Jian Hang Tng, Peiyi Song, Geok Ing Ng, Ken-Tye Yong, Qing Xin Zhang

Abstract:

Brain-machine interfaces (BMI) is a ground rich of exploration opportunities where manipulation of neural activity are used for interconnect with myriad form of external devices. These research and intensive development were evolved into various areas from medical field, gaming and entertainment industry till safety and security field. The technology were extended for neurological disorders therapy such as obsessive compulsive disorder and Parkinson’s disease by introducing current pulses to specific region of the brain. Nonetheless, the work to develop a real-time observing, recording and altering of neural signal brain-machine interfaces system will require a significant amount of effort to overcome the obstacles in improving this system without delay in response. To date, feature size of interface devices and the density of the electrode population remain as a limitation in achieving seamless performance on BMI. Currently, the size of the BMI devices is ranging from 10 to 100 microns in terms of electrodes’ diameters. Henceforth, to accommodate the single cell level precise monitoring, smaller and denser Nano-scaled nanowire electrode arrays are vital in fabrication. In this paper, we would like to showcase the fabrication of high aspect ratio of vertical silicon nanowire electrodes arrays using microelectromechanical system (MEMS) method. Nanofabrication of the nanowire electrodes involves in deep reactive ion etching, thermal oxide thinning, electron-beam lithography patterning, sputtering of metal targets and bottom anti-reflection coating (BARC) etch. Metallization on the nanowire electrode tip is a prominent process to optimize the nanowire electrical conductivity and this step remains a challenge during fabrication. Metal electrodes were lithographically defined and yet these metal contacts outline a size scale that is larger than nanometer-scale building blocks hence further limiting potential advantages. Therefore, we present an integrated contact solution that overcomes this size constraint through self-aligned Nickel silicidation process on the tip of vertical silicon nanowire electrodes. A 4 x 4 array of vertical silicon nanowires electrodes with the diameter of 290nm and height of 3µm has been successfully fabricated.

Keywords: brain-machine interfaces, microelectromechanical systems (MEMS), nanowire, nickel silicide

Procedia PDF Downloads 402

Authors: Tim Farrelly

Abstract:

In recent years, AI-powered object detection systems have opened the doors for innovative new applications and products, especially those operating in the real world or ‘on edge’ – namely, in sport. This paper investigates the viability of an ultra-low parameter convolutional neural network specially designed for the detection of footballs on ‘on the edge’ devices. The main contribution of this paper is the exploration of integrating new design features (depth-wise separable convolutional blocks and squeezed and excitation modules) into an ultra-low parameter network and demonstrating subsequent improvements in performance. The results show that tracking the ball from Full HD images with negligibly high accu-racy is possible in real-time.

Keywords: deep learning, object detection, machine vision applications, sport, network design

Procedia PDF Downloads 116

Authors: Feng Guo

Abstract:

Human brain organoids, 3D brain tissue cultures derived from human pluripotent stem cells, hold promising potential in modeling neuroinflammation for a variety of neurological diseases. However, challenges remain in generating standardized human brain organoids that can recapitulate key physiological features of a human brain. Here, this study presents a series of organoids-on-a-chip systems to generate better human brain organoids and model neuroinflammation. By employing 3D printing and microfluidic 3D cell culture technologies, the study’s systems enable the reliable, scalable, and reproducible generation of human brain organoids. Compared with conventional protocols, this study’s method increased neural progenitor proliferation and reduced heterogeneity of human brain organoids. As a proof-of-concept application, the study applied this method to model substance use disorders.

Keywords: human brain organoids, microfluidics, organ-on-a-chip, neuroinflammation

Procedia PDF Downloads 170

Authors: Motonobu Hattori

Abstract:

In neural networks, when new patters are learned by a network, they radically interfere with previously stored patterns. This drawback is called catastrophic forgetting. We have already proposed a biologically inspired dual-network memory model which can much reduce this forgetting for static patterns. In this model, information is first stored in the hippocampal network, and thereafter, it is transferred to the neocortical network using pseudo patterns. Because, temporal sequence learning is more important than static pattern learning in the real world, in this study, we improve our conventional dual-network memory model so that it can deal with temporal sequences without catastrophic forgetting. The computer simulation results show the effectiveness of the proposed dual-network memory model.

Keywords: catastrophic forgetting, dual-network, temporal sequences, hippocampal

Procedia PDF Downloads 233

Authors: David Edgar

Abstract:

To understand how the brain’s subconscious and conscious functions, we must conquer the physics of Unity, which leads to duality’s algorithm. Where the subconscious (bottom-up) and conscious (top-down) processes function together to produce and consume intelligence, we use terms like ‘time is relative,’ but we really do understand the meaning. In the brain, there are different processes and, therefore, different observers. These different processes experience time at different rates. A sensory system such as the eyes cycles measurement around 33 milliseconds, the conscious process of the frontal lobe cycles at 300 milliseconds, and the subconscious process of the thalamus cycle at 5 milliseconds. Three different observers experience time differently. To bridge observers, the thalamus, which is the fastest of the processes, maintains a synchronous state and entangles the different components of the brain’s physical process. The entanglements form a synchronous cohesion between the brain components allowing them to share the same state and execute in the same measurement cycle. The thalamus uses the shared state to control the firing sequence of the brain’s linear subconscious process. Sharing state also allows the brain to cheat on the amount of sensory data that must be exchanged between components. Only unpredictable motion is transferred through the synchronous state because predictable motion already exists in the shared framework. The brain’s synchronous subconscious process is entirely based on energy conservation, where prediction regulates energy usage. So, the eyes every 33 milliseconds dump their sensory data into the thalamus every day. The thalamus is going to perform a motion measurement to identify the unpredictable motion in the sensory data. Here is the trick. The thalamus conducts its measurement based on the original observation time of the sensory system (33 ms), not its own process time (5 ms). This creates a data payload of synchronous motion that preserves the original sensory observation. Basically, a frozen moment in time (Flat 4D). The single moment in time can then be processed through the single state maintained by the synchronous process. Other processes, such as consciousness (300 ms), can interface with the synchronous state to generate awareness of that moment. Now, synchronous data traveling through a separate faster synchronous process creates a theoretical time tunnel where observation time is tunneled through the synchronous process and is reproduced on the other side in the original time-relativity. The synchronous process eliminates time dilation by simply removing itself from the equation so that its own process time does not alter the experience. To the original observer, the measurement appears to be instantaneous, but in the thalamus, a linear subconscious process generating sensory perception and thought production is being executed. It is all just occurring in the time available because other observation times are slower than thalamic measurement time. For life to exist in the physical universe requires a linear measurement process, it just hides by operating at a faster time relativity. What’s interesting is time dilation is not the problem; it’s the solution. Einstein said there was no universal time.

Keywords: neural synchronization, natural intelligence, 99.95% IoT data transmission savings, artificial subconscious intelligence (ASI)

Procedia PDF Downloads 96

Authors: Nidhal K. Azawi, John M. Gauch

Abstract:

Colorectal cancer is one of the leading causes of cancer death in the US and the world, which is why millions of colonoscopy examinations are performed annually. Unfortunately, noise, specular highlights, and motion artifacts corrupt many images in a typical colonoscopy exam. The goal of our research is to produce automated techniques to detect and correct or remove these noninformative images from colonoscopy videos, so physicians can focus their attention on informative images. In this research, we first automatically extract features from images. Then we use machine learning and deep neural network to classify colonoscopy images as either informative or noninformative. Our results show that we achieve image classification accuracy between 92-98%. We also show how the removal of noninformative images together with image alignment can aid in the creation of image panoramas and other visualizations of colonoscopy images.

Keywords: colonoscopy classification, feature extraction, image alignment, machine learning

Procedia PDF Downloads 218

Authors: Hans Schumann, Colin Domnauer, Louis Rosenberg

Abstract:

In this study, machine learning techniques were deployed on real-time human swarm data to forecast the likelihood of outcomes for English Premier League matches in the 2020/21 season. These techniques included ensemble models in combination with neural networks and were tested against an industry standard of Vegas Oddsmakers. Predictions made from the collective intelligence of human swarm participants managed to achieve a positive return on investment over a full season on matches, empirically proving the usefulness of a new artificial intelligence valuing human instinct and intelligence.

Keywords: artificial intelligence, data science, English Premier League, human swarming, machine learning, sports betting, swarm intelligence

Procedia PDF Downloads 177

Authors: Hossein Havaeji, Tony Wong, Thien-My Dao

Abstract:

1. Research Problems and Research Objectives: Blockchain Technology-enabled Supply Chain System (BT-enabled SCS) is the system using BT to drive SCS transparency, security, durability, and process integrity as SCS data is not always visible, available, or trusted. The costs of operating BT in the SCS are a common problem in several organizations. The costs must be estimated as they can impact existing cost control strategies. To account for system and deployment costs, it is necessary to overcome the following hurdle. The problem is that the costs of developing and running a BT in SCS are not yet clear in most cases. Many industries aiming to use BT have special attention to the importance of BT installation cost which has a direct impact on the total costs of SCS. Predicting BT installation cost in SCS may help managers decide whether BT is to be an economic advantage. The purpose of the research is to identify some main BT installation cost components in SCS needed for deeper cost analysis. We then identify and categorize the main groups of cost components in more detail to utilize them in the prediction process. The second objective is to determine the suitable Supervised Learning technique in order to predict the costs of developing and running BT in SCS in a particular case study. The last aim is to investigate how the running BT cost can be involved in the total cost of SCS. 2. Work Performed: Applied successfully in various fields, Supervised Learning is a method to set the data frame, treat the data, and train/practice the method sort. It is a learning model directed to make predictions of an outcome measurement based on a set of unforeseen input data. The following steps must be conducted to search for the objectives of our subject. The first step is to make a literature review to identify the different cost components of BT installation in SCS. Based on the literature review, we should choose some Supervised Learning methods which are suitable for BT installation cost prediction in SCS. According to the literature review, some Supervised Learning algorithms which provide us with a powerful tool to classify BT installation components and predict BT installation cost are the Support Vector Regression (SVR) algorithm, Back Propagation (BP) neural network, and Artificial Neural Network (ANN). Choosing a case study to feed data into the models comes into the third step. Finally, we will propose the best predictive performance to find the minimum BT installation costs in SCS. 3. Expected Results and Conclusion: This study tends to propose a cost prediction of BT installation in SCS with the help of Supervised Learning algorithms. At first attempt, we will select a case study in the field of BT-enabled SCS, and then use some Supervised Learning algorithms to predict BT installation cost in SCS. We continue to find the best predictive performance for developing and running BT in SCS. Finally, the paper will be presented at the conference.

Keywords: blockchain technology, blockchain technology-enabled supply chain system, installation cost, supervised learning

Procedia PDF Downloads 93

Authors: Hasna Elalaoui Elabdallaoui, Abdelaziz Elfazziki, Mohamed Sadgal

Abstract:

Outlines: The social economy is a moral approach to solidarity applied to the projects’ development. To reconcile economic activity and social equity, crowdfunding is as an alternative means of financing social projects. Several collaborative blockchain platforms exist. It eliminates the need for a central authority or an inconsiderate middleman. Also, the costs for a successful crowdfunding campaign are reduced, since there is no commission to be paid to the intermediary. It improves the transparency of record keeping and delegates authority to authorities who may be prone to corruption. Objectives: The objectives are: to define a software infrastructure for projects’ participatory financing within a social and solidarity economy, allowing transparent, secure, and fair management and to have a financial mechanism that improves financial inclusion. Methodology: The proposed methodology is: crowdfunding platforms literature review, financing mechanisms literature review, requirements analysis and project definition, a business plan, Platform development process and implementation technology, and testing an MVP. Contributions: The solution consists of proposing a new approach to crowdfunding based on Islamic financing, which is the principle of Mousharaka inspired by Islamic financing, which presents a financial innovation that integrates ethics and the social dimension into contemporary banking practices. Conclusion: Crowdfunding platforms need to secure projects and allow only quality projects but also offer a wide range of options to funders. Thus, a framework based on blockchain technology and Islamic financing is proposed to manage this arbitration between quality and quantity of options. The proposed financing system, "Musharaka", is a mode of financing that prohibits interests and uncertainties. The implementation is offered on the secure Ethereum platform as investors sign and initiate transactions for contributions using their digital signature wallet managed by a cryptography algorithm and smart contracts. Our proposal is illustrated by a crop irrigation project in the Marrakech region.

Keywords: social economy, Musharaka, blockchain, smart contract, crowdfunding

Procedia PDF Downloads 46

Authors: J. Y. Tan, L. C. Lum, M. G. Lee, S. Mansouri, K. Hapgood, X. D. Chen, M. W. Woo

Abstract:

Folic acid (FA) is known to be an important supplement to prevent neural tube defect (NTD) in pregnant women. Similar to some commercial formulations, sodium bicarbonate solution is used as a solvent for FA. This work uses the antisolvent vapor precipitation (AVP), incorporating ethanol vapor as the convective drying medium in place of air to produce branch-like micro-structure FA particles. Interestingly, the dissolution rate of the resultant particle is 2-3 times better than the particle produce from conventional air drying due to the higher surface area of particles produced. The higher dissolution rate could possibly improve the delivery and absorption of FA in human body. This application could potentially be extended to other commercial products, particularly in less soluble drugs to improve its solubility.

Keywords: absorption, antisolvent vapor precipitation, dissolution rate, folic acid

Procedia PDF Downloads 408

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 108

Authors: Yuri Boiko, Iluju Kiringa, Tet Yeap

Abstract:

Current drainage attack suggested previously is further studied in regular settings of closed-loop controlled Brushless DC (BLDC) motor with Kalman filter in the feedback loop. Modeling and simulation experiments are conducted in a Matlab environment, implementing the closed-loop control model of BLDC motor operation in position sensorless mode under Kalman filter drive. The current increase in the motor windings is caused by the controller (p-controller in our case) affected by false data injection of substitution of the angular velocity estimates with distorted values. Operation of multiplication to distortion coefficient, values of which are taken from the distortion function synchronized in its periodicity with the rotor’s position change. A saw function with a triangular tooth shape is studied herewith for the purpose of carrying out the bias injection with current drainage consequences. The specific focus here is on how the asymmetry of the tooth in the saw function affects the flow of current drainage. The purpose is two-fold: (i) to produce and collect the signature of an asymmetric saw in the attack for further pattern recognition process, and (ii) to determine conditions of improving stealthiness of such attack via regulating asymmetry in saw function used. It is found that modification of the symmetry in the saw tooth affects the periodicity of current drainage modulation. Specifically, the modulation frequency of the drained current for a fully asymmetric tooth shape coincides with the saw function modulation frequency itself. Increasing the symmetry parameter for the triangle tooth shape leads to an increase in the modulation frequency for the drained current. Moreover, such frequency reaches the switching frequency of the motor windings for fully symmetric triangular shapes, thus becoming undetectable and improving the stealthiness of the attack. Therefore, the collected signatures of the attack can serve for attack parameter identification via the pattern recognition route.

Keywords: bias injection attack, Kalman filter, BLDC motor, control system, closed loop, P-controller, PID-controller, current drainage, saw-function, asymmetry

Procedia PDF Downloads 48

Authors: K. E. Ch. Vidyasagar, M. Moghavvemi, T. S. S. T. Prabhat

Abstract:

Epilepsy is a global problem, and with seizures eluding even the smartest of diagnoses a requirement for automatic detection of the same using electroencephalogram (EEG) would have a huge impact in diagnosis of the disorder. Among a multitude of methods for automatic epilepsy detection, one should find the best method out, based on accuracy, for classification. This paper reasons out, and rationalizes, the best methods for classification. Accuracy is based on the classifier, and thus this paper discusses classifiers like quadratic discriminant analysis (QDA), classification and regression tree (CART), support vector machine (SVM), naive Bayes classifier (NBC), linear discriminant analysis (LDA), K-nearest neighbor (KNN) and artificial neural networks (ANN). Results show that ANN is the most accurate of all the above stated classifiers with 97.7% accuracy, 97.25% specificity and 98.28% sensitivity in its merit. This is followed closely by SVM with 1% variation in result. These results would certainly help researchers choose the best classifier for detection of epilepsy.

Keywords: classification, seizure, KNN, SVM, LDA, ANN, epilepsy

Procedia PDF Downloads 487

Authors: Pierre Tize Mha, Mohammad Jahazi, Amèvi Togne, Olivier Pantalé

Abstract:

Large-size forged blocks made of medium carbon high-strength steels are extensively used in the automotive industry as dies for the production of bumpers and dashboards through the plastic injection process. The manufacturing process of the large blocks starts with ingot casting, followed by open die forging and a quench and temper heat treatment process to achieve the desired mechanical properties and numerical simulation is widely used nowadays to predict these properties before the experiment. But the temperature gradient inside the specimen remains challenging in the sense that the temperature before loading inside the material is not the same, but during the simulation, constant temperature is used to simulate the experiment because it is assumed that temperature is homogenized after some holding time. Therefore to be close to the experiment, real distribution of the temperature through the specimen is needed before the mechanical loading. Thus, We present here a robust algorithm that allows the calculation of the temperature gradient within the specimen, thus representing a real temperature distribution within the specimen before deformation. Indeed, most numerical simulations consider a uniform temperature gradient which is not really the case because the surface and core temperatures of the specimen are not identical. Another feature that influences the mechanical properties of the specimen is recrystallization which strongly depends on the deformation conditions and the type of deformation like Upsetting, Cogging...etc. Indeed, Upsetting and Cogging are the stages where the greatest deformations are observed, and a lot of microstructural phenomena can be observed, like recrystallization, which requires in-depth characterization. Complete dynamic recrystallization plays an important role in the final grain size during the process and therefore helps to increase the mechanical properties of the final product. Thus, the identification of the conditions for the initiation of dynamic recrystallization is still relevant. Also, the temperature distribution within the sample and strain rate influence the recrystallization initiation. So the development of a technique allowing to predict the initiation of this recrystallization remains challenging. In this perspective, we propose here, in addition to the algorithm allowing to get the temperature distribution before the loading stage, an analytical model leading to determine the initiation of this recrystallization. These two techniques are implemented into the Abaqus finite element software via the UAMP and VUHARD subroutines for comparison with a simulation where an isothermal temperature is imposed. The Artificial Neural Network (ANN) model to describe the plastic behavior of the material is also implemented via the VUHARD subroutine. From the simulation, the temperature distribution inside the material and recrystallization initiation is properly predicted and compared to the literature models.

Keywords: dynamic recrystallization, finite element modeling, artificial neural network, numerical implementation

Procedia PDF Downloads 54

Authors: Aishrith Rao

Abstract:

Human activity recognition is an important aspect of video analytics, and many approaches have been recommended to enable action recognition. In this approach, the model is used to identify the action of the multiple people in the frame and classify them accordingly. A few approaches use RNNs and 3D CNNs, which are computationally expensive and cannot be trained with the small datasets which are currently available. Multi-person action recognition has been performed in order to understand the positions and action of people present in the video frame. The size of the video frame can be adjusted as a hyper-parameter depending on the hardware resources available. OpenPose has been used to calculate pose estimate using CNN to produce heap-maps, one of which provides skeleton features, which are basically joint features. The features are then extracted, and a classification algorithm can be applied to classify the action.

Keywords: human activity recognition, computer vision, pose estimates, convolutional neural networks

Procedia PDF Downloads 109

Authors: Tetyana Baydyk, Ernst Kussul, Sandra Bonilla Meza

Abstract:

There are many articles that attempt to establish the role of different facial fragments in face recognition. Various approaches are used to estimate this role. Frequently, authors calculate the entropy corresponding to the fragment. This approach can only give approximate estimation. In this paper, we propose to use a more direct measure of the importance of different fragments for face recognition. We propose to select a recognition method and a face database and experimentally investigate the recognition rate using different fragments of faces. We present two such experiments in the paper. We selected the PCNC neural classifier as a method for face recognition and parts of the LFW (Labeled Faces in the Wild) face database as training and testing sets. The recognition rate of the best experiment is comparable with the recognition rate obtained using the whole face.

Keywords: face recognition, labeled faces in the wild (LFW) database, random local descriptor (RLD), random features

Procedia PDF Downloads 328

Authors: Brendah Nagula, Omolo Fredrick Okalebo, Ronald Ssengendo, Ivan Bamweyana

Abstract:

The Kampala Physical Development Plan (KPDP) was developed in 2012 and projected both long term and short term developments within the City .The purpose of the plan was to not only shape the city into a spatially planned area but also to control the urban sprawl trends that had expanded with pronounced instances of informal settlements. This plan was approved by the National Physical Planning Board and a signature was appended by the Minister in 2013. Much as the KPDP plan has been implemented using different approaches such as detailed planning, development control, subdivision planning, carrying out construction inspections, greening and beautification, there is still limited knowledge on the level of conformance towards this plan. Therefore, it is yet to be determined whether it has been effective in shaping the City into an ideal spatially planned area. Attaining a clear picture of the level of conformance towards the KPDP 2012 through evaluation between the planned and the existing land use in Kampala City was performed. Methods such as Supervised Classification and Post Classification Change Detection were adopted to perform this evaluation. Scrutiny of findings revealed Central Division registered the lowest level of conformance to the planning standards specified in the KPDP 2012 followed by Nakawa, Rubaga, Kawempe, and Makindye. Furthermore, mixed-use development was identified as the land use with the highest level of non-conformity of 25.11% and institutional land use registered the highest level of conformance of 84.45 %. The results show that the aspect of location was not carefully considered while allocating uses in the KPDP whereby areas located near the Central Business District have higher land rents and hence require uses that ensure profit maximization. Also, the prominence of development towards mixed-use denotes an increased demand for land towards compact development that was not catered for in the plan. Therefore in order to transform Kampala city into a spatially planned area, there is need to carefully develop detailed plans especially for all the Central Division planning precincts indicating considerations for land use densification.

Keywords: spatial plan, post classification change detection, Kampala city, landuse

Procedia PDF Downloads 61

Authors: Bernd Kiefer, Abraham Gebru Tesfay, Dietrich Klakow

Abstract:

The motivation of our work is to detect different terrain types traversed by a robot based on acoustic data from the robot-terrain interaction. Different acoustic features and classifiers were investigated, such as Mel-frequency cepstral coefficient and Gamma-tone frequency cepstral coefficient for the feature extraction, and Gaussian mixture model and Feed forward neural network for the classification. We analyze the system’s performance by comparing our proposed techniques with some other features surveyed from distinct related works. We achieve precision and recall values between 87% and 100% per class, and an average accuracy at 95.2%. We also study the effect of varying audio chunk size in the application phase of the models and find only a mild impact on performance.

Keywords: acoustic features, autonomous robots, feature extraction, terrain classification

Procedia PDF Downloads 333