Search results for: neural network models

Authors: Shan Zhang, Peter Suechting

Abstract:

Predicting trade patterns is critical to decision-making in public and private domains, especially in the current context of trade disputes among major economies. In the past, U.S. recycling has relied heavily on strong demand for recyclable materials overseas. However, starting in 2017, a series of new recycling policies (bans and higher inspection standards) was enacted by multiple countries that were the primary importers of recyclables from the U.S. prior to that point. As the global trade flow of recycling shifts, some new importers, mostly developing countries in South and Southeast Asia, have been overwhelmed by the sheer quantities of scrap materials they have received. As the leading exporter of recyclable materials, the U.S. now has a pressing need to build its recycling industry domestically. With respect to the global trade in scrap materials used for recycling, the interest in this paper is (1) predicting how the export of recyclable materials from the U.S. might vary over time, and (2) predicting how international trade flows for recyclables might change in the future. Focusing on three major recyclable materials with a history of trade, this study uses data-driven and machine learning (ML) algorithms---supervised (shrinkage and tree methods) and unsupervised (neural network method)---to decipher the international trade pattern of recycling. Forecasting the potential trade values of recyclables in the future could help importing countries, to which those materials will shift next, to prepare related trade policies. Such policies can assist policymakers in minimizing negative environmental externalities and in finding the optimal amount of recyclables needed by each country. Such forecasts can also help exporting countries, like the U.S understand the importance of healthy domestic recycling industry. The preliminary result suggests that gravity models---in addition to particular selection macroeconomic predictor variables--are appropriate predictors of the total export value of recyclables. With the inclusion of variables measuring aspects of the political conditions (trade tariffs and bans), predictions show that recyclable materials are shifting from more policy-restricted countries to less policy-restricted countries in international recycling trade. Those countries also tend to have high manufacturing activities as a percentage of their GDP.

Keywords: environmental economics, machine learning, recycling, international trade

Procedia PDF Downloads 170

Authors: Namwinwelbere Dabire, Eugene C. Ezin, Adandedji M. Firmin

Abstract:

The prediction of hydrological flows (rainfall-depth or rainfall-discharge) is becoming increasingly important in the management of hydrological risks such as floods. In this study, the Long Short-Term Memory (LSTM) network, a state-of-the-art algorithm dedicated to time series, is applied to predict the daily water level of Nokoue Lake in Benin. This paper aims to provide an effective and reliable method enable of reproducing the future daily water level of Nokoue Lake, which is influenced by a combination of two phenomena: rainfall and river flow (runoff from the Ouémé River, the Sô River, the Porto-Novo lagoon, and the Atlantic Ocean). Performance analysis based on the forecasting horizon indicates that LSTM can predict the water level of Nokoué Lake up to a forecast horizon of t+10 days. Performance metrics such as Root Mean Square Error (RMSE), coefficient of correlation (R²), Nash-Sutcliffe Efficiency (NSE), and Mean Absolute Error (MAE) agree on a forecast horizon of up to t+3 days. The values of these metrics remain stable for forecast horizons of t+1 days, t+2 days, and t+3 days. The values of R² and NSE are greater than 0.97 during the training and testing phases in the Nokoué Lake basin. Based on the evaluation indices used to assess the model's performance for the appropriate forecast horizon of water level in the Nokoué Lake basin, the forecast horizon of t+3 days is chosen for predicting future daily water levels.

Keywords: forecasting, long short-term memory cell, recurrent artificial neural network, Nokoué lake

Procedia PDF Downloads 64

Authors: Dheyaa W. Abbood, Rafa H. AL-Suhaili, May S. Saleh

Abstract:

A model using the artificial neural networks and genetic algorithm technique is developed for obtaining optimum dimensions of the foundation length and protections of small hydraulic structures. The procedure involves optimizing an objective function comprising a weighted summation of the state variables. The decision variables considered in the optimization are the upstream and downstream cutoffs length sand their angles of inclination, the foundation length, and the length of the downstream soil protection. These were obtained for a given maximum difference in head, depth of impervious layer and degree of anisotropy.The optimization carried out subjected to constraints that ensure a safe structure against the uplift pressure force and sufficient protection length at the downstream side of the structure to overcome an excessive exit gradient. The Geo-studios oft ware, was used to analyze 1200 different cases. For each case the length of protection and volume of structure required to satisfy the safety factors mentioned previously were estimated. An ANN model was developed and verified using these cases input-output sets as its data base. A MatLAB code was written to perform a genetic algorithm optimization modeling coupled with this ANN model using a formulated optimization model. A sensitivity analysis was done for selecting the cross-over probability, the mutation probability and level ,the number of population, the position of the crossover and the weights distribution for all the terms of the objective function. Results indicate that the most factor that affects the optimum solution is the number of population required. The minimum value that gives stable global optimum solution of this parameters is (30000) while other variables have little effect on the optimum solution.

Keywords: inclined cutoff, optimization, genetic algorithm, artificial neural networks, geo-studio, uplift pressure, exit gradient, factor of safety

Procedia PDF Downloads 325

Authors: Chaudhary Muhammad Aqdus Ilyas, Matthias Rehm, Kamal Nasrollahi, Thomas B. Moeslund

Abstract:

This paper presents the investigation of data collection procedures, associated with robots when placed with traumatic brain injured (TBI) patients for rehabilitation purposes through facial expression and mood analysis. Rehabilitation after TBI is very crucial due to nature of injury and variation in recovery time. It is advantageous to analyze these emotional signals in a contactless manner, due to the non-supportive behavior of patients, limited muscle movements and increase in negative emotional expressions. This work aims at the development of framework where robots can recognize TBI emotions through facial expressions to perform rehabilitation tasks by physical, cognitive or interactive activities. The result of these studies shows that with customized data collection strategies, proposed framework identify facial and emotional expressions more accurately that can be utilized in enhancing recovery treatment and social interaction in robotic context.

Keywords: computer vision, convolution neural network- long short term memory network (CNN-LSTM), facial expression and mood recognition, multimodal (RGB-thermal) analysis, rehabilitation, robots, traumatic brain injured patients

Procedia PDF Downloads 156

Authors: Fikret Yalcinkaya, Hamza Unsal

Abstract:

To understand how neurons work, it is required to combine experimental studies on neural science with numerical simulations of neuron models in a computer environment. In this regard, the simplicity and applicability of spiking neuron modeling functions have been of great interest in computational neuron science and numerical neuroscience in recent years. Spiking neuron models can be classified by exhibiting various neuronal behaviors, such as spiking and bursting. These classifications are important for researchers working on theoretical neuroscience. In this paper, three different spiking neuron models; Izhikevich, Adaptive Exponential Integrate Fire (AEIF) and Hindmarsh Rose (HR), which are based on first order differential equations, are discussed and compared. First, the physical meanings, derivatives, and differential equations of each model are provided and simulated in the Matlab environment. Then, by selecting appropriate parameters, the models were visually examined in the Matlab environment and it was aimed to demonstrate which model can simulate well-known biological neuron behaviours such as Tonic Spiking, Tonic Bursting, Mixed Mode Firing, Spike Frequency Adaptation, Resonator and Integrator. As a result, the Izhikevich model has been shown to perform Regular Spiking, Continuous Explosion, Intrinsically Bursting, Thalmo Cortical, Low-Threshold Spiking and Resonator. The Adaptive Exponential Integrate Fire model has been able to produce firing patterns such as Regular Ignition, Adaptive Ignition, Initially Explosive Ignition, Regular Explosive Ignition, Delayed Ignition, Delayed Regular Explosive Ignition, Temporary Ignition and Irregular Ignition. The Hindmarsh Rose model showed three different dynamic neuron behaviours; Spike, Burst and Chaotic. From these results, the Izhikevich cell model may be preferred due to its ability to reflect the true behavior of the nerve cell, the ability to produce different types of spikes, and the suitability for use in larger scale brain models. The most important reason for choosing the Adaptive Exponential Integrate Fire model is that it can create rich ignition patterns with fewer parameters. The chaotic behaviours of the Hindmarsh Rose neuron model, like some chaotic systems, is thought to be used in many scientific and engineering applications such as physics, secure communication and signal processing.

Keywords: Izhikevich, adaptive exponential integrate fire, Hindmarsh Rose, biological neuron behaviours, spiking neuron models

Procedia PDF Downloads 183

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry

Procedia PDF Downloads 93

Authors: Santhosh Srinivasan, Vipul Garhiya, Shahul Hamid Khan

Abstract:

Environmental performance along with social performance is becoming vital factors for industries to achieve global standards. With a good environmental policy global industries are differentiating them from their competitors. This paper concentrates on multi stage, multi product and multi period manufacturing network. Single objective mathematical models for a total cost for the entire forward supply chain and reverse chain are considered. Here five different problems are considered by varying the number of facilities for illustration. M-MOGA, Shuffle Frog Leaping algorithm (SFLA) and CPLEX are used for finding the optimal solution for the mathematical model.

Keywords: closed loop supply chain, genetic algorithm, random search, multi period, green supply chain

Procedia PDF Downloads 393

Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Abstract:

Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.

Keywords: retail stores, faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition

Procedia PDF Downloads 157

Authors: Krishna Mohan Bathula, Fatou Bintou Loucoubar, FNU Kaleemunnisa, Christelle Scharff, Mark Anthony De Castro

Abstract:

Voice recognition algorithms such as automatic speech recognition and text-to-speech systems with African languages can play an important role in bridging the digital divide of Artificial Intelligence in Africa, contributing to the establishment of a fully inclusive information society. This paper proposes a Deep Learning model that can classify the user responses as inputs for an interactive voice response system. A dataset with Wolof language words ‘yes’ and ‘no’ is collected as audio recordings. A two stage Data Augmentation approach is adopted for enhancing the dataset size required by the deep neural network. Data preprocessing and feature engineering with Mel-Frequency Cepstral Coefficients are implemented. Convolutional Neural Networks (CNNs) have proven to be very powerful in image classification and are promising for audio processing when sounds are transformed into spectra. For performing voice response classification, the recordings are transformed into sound frequency feature spectra and then applied image classification methodology using a deep CNN model. The inference model of this trained and reusable Wolof voice response recognition system can be integrated with many applications associated with both web and mobile platforms.

Keywords: automatic speech recognition, interactive voice response, voice response recognition, wolof word classification

Procedia PDF Downloads 118

Authors: Subhash Reddy

Abstract:

Mobile communication in today’s world means a lot to the human kind, through this many deals are made and others are broken, within seconds. That is because of our sophisticated methods of transporting the data at very high speeds and to very long distances, within no time. That is also because we kept on changing the method of serving the connections as the no of connections kept on increasing, that has led to many methods like TDMA, CDMA, and FDMA, etc. in wireless communications. And also the areas, where the connections are provided are also divided into CELLS, which are the basic blocks for cellular communications. Along with the wireless network, providing a wired network in mobile phones would serve as a very good alternative and would divert the extra traffic of a cell, so that a CELL which is providing wireless network can operate more efficiently.

Keywords: CDMA, FDMA, TDMA, CELL

Procedia PDF Downloads 487

Authors: Elvira Mustikawati P.H., Iis Dewi Ratih, Dita Amelia

Abstract:

Bojonegoro has proclaimed a policy of zero malnutrition. Therefore, as an effort to solve the cases of malnutrition children in Bojonegoro, this study used the approach geographically Mixed Weighted Regression (MGWR) to determine the factors that influence the percentage of malnourished children under five in which factors can be divided into locally influential factor in each district and global factors that influence throughout the district. Based on the test of goodness of fit models, R2 and AIC values in GWR models are better than MGWR models. R2 and AIC values in MGWR models are 84.37% and 14.28, while the GWR models respectively are 91.04% and -62.04. Based on the analysis with GWR models, District Sekar, Bubulan, Gondang, and Dander is a district with three predictor variables (percentage of vitamin A, the percentage of births assisted health personnel, and the percentage of clean water) that significantly influence the percentage of malnourished children under five.

Keywords: GWR, MGWR, R2, AIC

Procedia PDF Downloads 297

Authors: Tammam A. Benmusa, Mohamed A. Shlibek, Rawad M. Swesi

Abstract:

The investigation of Buildings Penetration Loss (BPL) of radio signal is getting more and more important. It plays an important role in calculating the indoor coverage for wireless communication networks. In this paper, the theory behind BPL and its mechanisms have been reviewed. The operating frequency, coverage area type, climate condition, time of measurement, and other factors affecting the values of BPL have been discussed. The practical part of this work was conducting 4000 measurements of BPL in different areas in the Libyan capital, Tripoli, to get empirical model for this loss. The measurements were taken for 2 different types of wireless communication networks; mobile telephone network (for Almadar company), which operates at 900 MHz and WiMAX network (LTT company) which operates at 2500 MHz. The results for each network were summarized and presented in several graphs. The graphs are showing how the BPL affected by: time of measurement, morphology (type of area), and climatic environment.

Keywords: building penetration loss, wireless network, mobile network, link budget, indoor network performance

Procedia PDF Downloads 386

Authors: Joseph Uzuazomaro Oju

Abstract:

The ease at which manipulated media can be created, and the increasing difficulty in identifying fake media makes it a great threat. Most of the applications used for the creation of these high-quality fake videos and images are built with deep learning. Hence, the use of deep learning in creating a detection mechanism cannot be overemphasized. Any successful fake media that is being detected before it reached the populace will save people from the self-doubt of either a content is genuine or fake and will ensure the credibility of videos and images. The methodology introduced in this paper approaches the manipulated media detection challenge using a combo of VGG-19 and a deep capsule network. In the case of videos, they are converted into frames, which, in turn, are resized and cropped to the face region. These preprocessed images/videos are fed to the VGG-19 network to extract the latent features. The extracted latent features are inputted into a deep capsule network enhanced with a 3D -convolution dynamic routing agreement. The 3D –convolution dynamic routing agreement algorithm helps to reduce the linkages between capsules networks. Thereby limiting the poor learning shortcoming of multiple capsule network layers. The resultant output from the deep capsule network will indicate a media to be either genuine or fake.

Keywords: deep capsule network, dynamic routing, fake media detection, manipulated media

Procedia PDF Downloads 135

Authors: Esperanza Garcia-Uceda, Josefina L. Murillo-Luna, M. Pilar Latorre-Martinez, Marta Ferrer-Serrano

Abstract:

Social entrepreneurship represents an innovation of traditional business models. During the last decade, its important role in contributing to rural and regional development has been widely recognized, due to its capacity to combat the problem of depopulation through the creation of employment. However, the success of this type of innovative business initiatives depends to a large extent on the existence of an adequate ecosystem of support resources. Based on the theoretical framework of the quadruple helix (QH), which highlights the need for collaboration between different interest groups -university, industry, government and civil society- for the development of regional innovations, in this work the network analysis is applied to study the ecosystem of resources to support social entrepreneurship in the rural area of the province of Zaragoza (Spain). It is a quantitative analysis that can be used to measure the interactions between the different actors that make up the quadruple helix, as well as the networks created between the different institutions and support organizations, through the study of the complex networks they form. The results show the importance of the involvement of local governments and the university, as key elements in the development process, but also allow identifying other issues that are susceptible to improvement.

Keywords: ecosystem of support resources, network analysis, quadruple helix, social entrepreneurship

Procedia PDF Downloads 255

Authors: Dweepabiswa Bagchi, D. V. Senthilkumar

Abstract:

Numerous studies have typically demonstrated the devastation of invasions on an isolated ecosystem or, at most, a network of dispersively coupled similar ecosystem patches. Using such a simplistic 2-D network model, one can only consider dispersal coupling and inter-species trophic interactions. However, in a realistic ecosystem, numerous species co-exist and interact trophically and non-trophically in groups of 2 or more. Even different types of dispersal can introduce complexity in an ecological network. Therefore, a more accurate representation of actual ecosystems (or ecological networks) is a complex network consisting of motifs formed by two or more interacting species. Here, the apropos structure of the network should be multiplex or multi-layered. Motifs between different patches or species should be identical within the same layer and vary from one layer to another. This study investigates three distinct ecological multiplex networks facing invasion from one or more external species. This work determines and quantifies the criteria for the increased extinction risk of these networks. The dynamical states of the network with high extinction risk, i.e., the danger states, and those with low extinction risk, i.e., the resistive network states, are both subsequently identified. The analysis done in this study further quantifies the persistence of the entire network corresponding to simultaneous changes in the strength of invasive dispersal and higher-order trophic and non-trophic interactions. This study also demonstrates that the ecosystems enjoy an inherent advantage against invasions due to their multiplex network structure.

Keywords: increased ecosystem persistence, invasion on ecosystems, multiplex networks, non-trophic interactions

Procedia PDF Downloads 69

Authors: Muhammad Zubair Khan, Yugyung Lee

Abstract:

Deep learning has recently achieved enormous response in semantic image segmentation. The previously developed U-Net inspired architectures operate with continuous stride and pooling operations, leading to spatial data loss. Also, the methods lack establishing long-term pixels connection to preserve context knowledge and reduce spatial loss in prediction. This article developed encoder-decoder architecture with bi-directional LSTM embedded in long skip-connections and densely connected convolution blocks. The network non-linearly combines the feature maps across encoder-decoder paths for finding dependency and correlation between image pixels. Additionally, the densely connected convolutional blocks are kept in the final encoding layer to reuse features and prevent redundant data sharing. The method applied batch-normalization for reducing internal covariate shift in data distributions. The empirical evidence shows a promising response to our method compared with other semantic segmentation techniques.

Keywords: deep learning, semantic segmentation, image analysis, pixels connection, convolution neural network

Procedia PDF Downloads 103

Authors: Abdoullah Fath-Allah, Laila Cheikhi, Rafa E. Al-Qutaish, Ali Idri

Abstract:

Many quality models have been used to measure e-government portals quality. However, the absence of an international consensus for e-government portals quality models results in many differences in terms of quality attributes and measures. The aim of this paper is to compare and analyze the existing e-government quality models proposed in literature (those that are based on ISO standards and those that are not) in order to propose guidelines to build a good and useful e-government portals quality model. Our findings show that, there is no e-government portal quality model based on the new international standard ISO 25010. Besides that, the quality models are not based on a best practice model to allow agencies to both; measure e-government portals quality and identify missing best practices for those portals.

Keywords: e-government, portal, best practices, quality model, ISO, standard, ISO 25010, ISO 9126

Procedia PDF Downloads 561

Authors: Hamid R. Lashgarian Azad, Seyed N. Shetab Boushehri

Abstract:

Wireless sensor networks (WSN) have become progressively popular due to their wide range of applications. Wireless Sensor Network is made of numerous tiny sensor nodes that are battery-powered. It is a very significant problem to maximize the lifetime of wireless sensor networks. In this paper, we propose a two-stage protocol based on an imperialist competitive algorithm (2S-ICA) to solve a sensor network optimization problem. The energy of the sensors can be greatly reduced and the lifetime of the network reduced by long communication distances between the sensors and the sink. We can minimize the overall communication distance considerably, thereby extending the lifetime of the network lifetime through connecting sensors into a series of independent clusters using 2SICA. Comparison results of the proposed protocol and LEACH protocol, which is common to solving WSN problems, show that our protocol has a better performance in terms of improving network life and increasing the number of transmitted data.

Keywords: wireless sensor network, imperialist competitive algorithm, LEACH protocol, k-means clustering

Procedia PDF Downloads 105

Authors: Sathapath Kilaso

Abstract:

Nowadays, Today, wireless sensor networks are an important technology that works with Internet of Things. It is receiving various data from many sensor. Then sent to processing or storing. By wireless network or through the Internet. The devices around us are intelligent, can receiving/transmitting and processing data and communicating through the system. There are many applications of wireless sensor networks, such as smart city, smart farm, environmental management, weather. This article will explore the use of wireless sensor networks in Thailand and collect data from Thai Thesis database in 2012-2017. How to Implementing Wireless Sensor Network Technology. Advantage from this study To know the usage wireless technology in many fields. This will be beneficial for future research. In this study was found the most widely used wireless sensor network in agriculture field. Especially for smart farms. And the second is the adoption of the environment. Such as weather stations and water inspection.

Keywords: wireless sensor network, smart city, survey, Adhoc Network

Procedia PDF Downloads 209

Authors: Yinggang Guo, Zongchun Li

Abstract:

In order to decrease the accumulated survey error of tunnel installation control network of particle accelerator, a sectional control method is proposed. Firstly, the accumulation rule of positional error with the length of the control network is obtained by simulation calculation according to the shape of the tunnel installation-control-network. Then, the RMS of horizontal positional precision of tunnel backbone control network is taken as the threshold. When the accumulated error is bigger than the threshold, the tunnel installation control network should be divided into subsections reasonably. On each segment, the middle survey station is taken as the datum for independent adjustment calculation. Finally, by taking the backbone control points as faint datums, the weighted partial parameters adjustment is performed with the adjustment results of each segment and the coordinates of backbone control points. The subsections are jointed and unified into the global coordinate system in the adjustment process. An installation control network of the linac with a length of 1.6 km is simulated. The RMS of positional deviation of the proposed method is 2.583 mm, and the RMS of the difference of positional deviation between adjacent points reaches 0.035 mm. Experimental results show that the proposed sectional control method can not only effectively decrease the accumulated survey error but also guarantee the relative positional precision of the installation control network. So it can be applied in the data processing of tunnel installation control networks, especially for large particle accelerators.

Keywords: alignment, tunnel installation control network, accumulated survey error, sectional control method, datum

Procedia PDF Downloads 192

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 148

Authors: Subodh Chandra Shakya, Badal Shrestha, Suni Thapa, Ashutosh Chauhan, Saugat Adhikari

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: inception ResNet, convolutional neural net, deep learning, confusion matrix, data augmentation, data preprocessing

Procedia PDF Downloads 188

Authors: Teresa Azevedo PerdicoúLis, Paulo Lopes Dos Santos

Abstract:

The conceptualisation of the problem of network optimisation as a noncooperative game sets up a holistic interactive approach that brings together different network features (e.g., com-pressor stations, sources, and pipelines, in the gas context) where the optimisation objectives are different, and a single optimisation procedure becomes possible without having to feed results from diverse software packages into each other. A mathematical model of this type, where independent entities take action, offers the ideal modularity and subsequent problem decomposition in view to design a decentralised algorithm to optimise the operation and management of the network. In a game framework, compressor stations and sources are under-stood as players which communicate through network connectivity constraints–the pipeline model. That is, in a scheme similar to tatonnementˆ, the players appoint their best settings and then interact to check for network feasibility. The devolved degree of network unfeasibility informs the players about the ’quality’ of their settings, and this two-phase iterative scheme is repeated until a global optimum is obtained. Due to network transients, its optimisation needs to be assessed at different points of the control interval. For this reason, the proposed approach to optimisation has two stages: (i) the first stage computes along the period of optimisation in order to fulfil the requirement just mentioned; (ii) the second stage is initialised with the solution found by the problem computed at the first stage, and computes in the end of the period of optimisation to rectify the solution found at the first stage. The liability of the proposed scheme is proven correct on an abstract prototype and three example networks.

Keywords: connectivity matrix, gas network optimisation, large-scale, noncooperative game, system decomposition

Procedia PDF Downloads 153

Authors: Hemant Kumar, Nilendu Das

Abstract:

A study based on ANN structure gives us the information to predict the size of the future in realizing a past event. ANN, IMD (Indian meteorological department) data and remote sensing were used to enable a number of parameters for calculating the size that may occur in the future. A threshold selected specifically above the high-frequency harvest reached the area during the selected seismic activity. In the field of human and local biodiversity it remains to obtain the right parameter compared to the frequency of impact. But during the study the assumption is that predicting seismic activity is a difficult process, not because of the parameters involved here, which can be analyzed and funded in research activity.

Keywords: ANN, Bayesion class, earthquakes, IMD

Procedia PDF Downloads 126

Authors: Ksenia Volkova, Artur Petrosyan, Ignatii Dubyshkin, Alexei Ossadtchi

Abstract:

Brain-computer interfaces are a growing research field producing many implementations that find use in different fields and are used for research and practical purposes. Despite the popularity of the implementations using non-invasive neuroimaging methods, radical improvement of the state channel bandwidth and, thus, decoding accuracy is only possible by using invasive techniques. Electrocorticography (ECoG) is a minimally invasive neuroimaging method that provides highly informative brain activity signals, effective analysis of which requires the use of machine learning methods that are able to learn representations of complex patterns. Deep learning is a family of machine learning algorithms that allow learning representations of data with multiple levels of abstraction. This study explores the potential of deep learning approaches for ECoG processing, decoding movement intentions and the perception of proprioceptive information. To obtain synchronous recording of kinematic movement characteristics and corresponding electrical brain activity, a series of experiments were carried out, during which subjects performed finger movements at their own pace. Finger movements were recorded with a three-axis accelerometer, while ECoG was synchronously registered from the electrode strips that were implanted over the contralateral sensorimotor cortex. Then, multichannel ECoG signals were used to track finger movement trajectory characterized by accelerometer signal. This process was carried out both causally and non-causally, using different position of the ECoG data segment with respect to the accelerometer data stream. The recorded data was split into training and testing sets, containing continuous non-overlapping fragments of the multichannel ECoG. A deep convolutional neural network was implemented and trained, using 1-second segments of ECoG data from the training dataset as input. To assess the decoding accuracy, correlation coefficient r between the output of the model and the accelerometer readings was computed. After optimization of hyperparameters and training, the deep learning model allowed reasonably accurate causal decoding of finger movement with correlation coefficient r = 0.8. In contrast, the classical Wiener-filter like approach was able to achieve only 0.56 in the causal decoding mode. In the noncausal case, the traditional approach reached the accuracy of r = 0.69, which may be due to the presence of additional proprioceptive information. This result demonstrates that the deep neural network was able to effectively find a representation of the complex top-down information related to the actual movement rather than proprioception. The sensitivity analysis shows physiologically plausible pictures of the extent to which individual features (channel, wavelet subband) are utilized during the decoding procedure. In conclusion, the results of this study have demonstrated that a combination of a minimally invasive neuroimaging technique such as ECoG and advanced machine learning approaches allows decoding motion with high accuracy. Such setup provides means for control of devices with a large number of degrees of freedom as well as exploratory studies of the complex neural processes underlying movement execution.

Keywords: brain-computer interface, deep learning, ECoG, movement decoding, sensorimotor cortex

Procedia PDF Downloads 178

Authors: Linh Nguyen Tung, Anh Truong Viet, Nghien Nguyen Ba, Chuong Trinh Trong

Abstract:

This paper proposes a reconfiguration methodology based on a continuous genetic algorithm (CGA) and particle swarm optimization (PSO) for minimizing active power loss and minimizing voltage deviation. Both algorithms are adapted using graph theory to generate feasible individuals, and the modified crossover is used for continuous variable of CGA. To demonstrate the performance and effectiveness of the proposed methods, a comparative analysis of CGA with PSO for network reconfiguration, on 33-node and 119-bus radial distribution system is presented. The simulation results have shown that both CGA and PSO can be used in the distribution network reconfiguration and CGA outperformed PSO with significant success rate in finding optimal distribution network configuration.

Keywords: distribution network reconfiguration, particle swarm optimization, continuous genetic algorithm, power loss reduction, voltage deviation

Procedia PDF Downloads 191

Authors: Ayman Aboelkassem, Mahmoud Ali

Abstract:

Introduction: The models of soul houses have appeared in the prehistory, old kingdom and middle kingdom period. These soul houses represented the imagination of the deceased about his house in the afterlife, some of these soul houses were two floors and the study will examine five models of soul houses which were discovered near Saqqara site by an Egyptian mission. These models had been transferred to The Grand Egyptian Museum (GEM) to be ready to display at the new museum. We focus on models of soul houses (GEM Numbers, 1276, 1280, 1281, 1282, 8711) these models of soul houses were related to the old kingdom period. These models were all made of pottery, the five models have an oval shape and were decorated with relief. Methodology: The study will focus on the development of soul houses during the different periods in ancient Egypt, the function of soul houses, the kind of offerings which were put in it and the symbolism of the offerings colors in ancient Egyptian believe. Conclusion: This study is useful for the heritage and ancient civilizations especially when we talk about opening new museums like The Grand Egyptian Museum which will display a new collection of soul houses. The study of soul houses and The kinds of offerings which put in it reflect the economic situation in the Egyptian society and kinds of oils which were famous in ancient Egypt.

Keywords: archaeology study, Grand Egyptian Museum, relief, soul houses

Procedia PDF Downloads 255

Authors: Phillip Garrad, Saritha Unnikrishnan

Abstract:

The recent popularity of connected and autonomous vehicles (CAV) corresponds with an increase in the risk of cyber-attacks. These cyber-attacks have been instigated by both researchers or white-coat hackers and cyber-criminals. As Connected Vehicles move towards full autonomy, the impact of these cyber-attacks also grows. The current research details challenges faced in cybersecurity testing of CAV, including access and cost of the representative test setup. Other challenges faced are lack of experts in the field. Possible solutions to how these challenges can be overcome are reviewed and discussed. From these findings, a software simulated CAV network is established as a cost-effective representative testbed. Penetration tests are then performed on this simulation, demonstrating a cyber-attack in CAV. Studies have shown Artificial Intelligence (AI) to improve runtime, increase efficiency and comprehensively cover all the typical test aspects in penetration testing in other industries. There is an attempt to introduce similar AI models to the software simulation. The expectation from this implementation is to see similar improvements in runtime and efficiency for the CAV model. If proven to be an effective means of penetration test for CAV, this methodology may be used on a full CAV test network.

Keywords: cybersecurity, connected vehicles, software simulation, artificial intelligence, penetration testing

Procedia PDF Downloads 110

Authors: Richard Ren

Abstract:

Air pollution is a serious danger to international well-being and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.

Keywords: air quality prediction, air pollution, artificial intelligence, machine learning algorithms

Procedia PDF Downloads 130

Authors: Tao Feng, Xiaomei Ma, Xian Guo, Jing Wang

Abstract:

Named Data Network (NDN) is one of the future Internet architecture, all nodes (i.e., hosts, routers) are allowed to have a local cache, used to satisfy incoming requests for content. However, depending on caching allows an adversary to perform attacks that are very effective and relatively easy to implement, such as content pollution attack. In this paper, we use a method of secure network coding based on homomorphic signature system to solve this problem. Firstly ,we use a dynamic public key technique, our scheme for each generation authentication without updating the initial secret key used. Secondly, employing the homomorphism of hash function, intermediate node and destination node verify the signature of the received message. In addition, when the network topology of NDN is simple and fixed, the code coefficients in our scheme are generated in a pseudorandom number generator in each node, so the distribution of the coefficients is also avoided. In short, our scheme not only can efficiently prevent against Intra/Inter-GPAs, but also can against the content poisoning attack in NDN.

Keywords: named data networking, content polloution attack, network coding signature, internet architecture

Procedia PDF Downloads 338