Search results for: estimation algorithms

Authors: Sergey Kopysov, Nikita Nedozhogin, Leonid Tonkov

Abstract:

The article presents a parallel iterative solver for large sparse linear systems which can be used on a heterogeneous platform. Traditionally, the problem of solving linear systems does not scale well on multi-CPU/multi-GPUs clusters. For example, most of the attempts to implement the classical conjugate gradient method were at best counted in the same amount of time as the problem was enlarged. The paper proposes the pipelined variant of the conjugate gradient method (PCG), a formulation that is potentially better suited for hybrid CPU/GPU computing since it requires only one synchronization point per one iteration instead of two for standard CG. The standard and pipelined CG methods need the vector entries generated by the current GPU and other GPUs for matrix-vector products. So the communication between GPUs becomes a major performance bottleneck on multi GPU cluster. The article presents an approach to minimize the communications between parallel parts of algorithms. Additionally, computation and communication can be overlapped to reduce the impact of data exchange. Using the pipelined version of the CG method with one synchronization point, the possibility of asynchronous calculations and communications, load balancing between the CPU and GPU for solving the large linear systems allows for scalability. The algorithm is implemented with the combined use of technologies: MPI, OpenMP, and CUDA. We show that almost optimum speed up on 8-CPU/2GPU may be reached (relatively to a one GPU execution). The parallelized solver achieves a speedup of up to 5.49 times on 16 NVIDIA Tesla GPUs, as compared to one GPU.

Keywords: conjugate gradient, GPU, parallel programming, pipelined algorithm

Procedia PDF Downloads 165

Authors: Isaac Owusu Asante, Yushi Jiang, Hailin Tao

Abstract:

Live streaming marketing, the new electronic commerce element, became an optional marketing channel following the COVID-19 pandemic. Many sellers have leveraged the features presented by live streaming to increase sales. Studies on live streaming have focused on gaming and consumers’ loyalty to brands through live streaming, using interview questionnaires. This study, however, was conducted to measure real-time observable interactions between consumers and sellers. Based on the affordance theory, this study conceptualized constructs representing the interactive features and examined how they drive consumers’ purchase willingness during live streaming sessions using 1238 datasets from Amazon Live, following the manual observation of transaction records. Using structural equation modeling, the ordinary least square regression suggests that live viewers, new followers, live chats, and likes positively affect purchase willingness. The Sobel and Monte Carlo tests show that new followers, live chats, and likes significantly mediate the relationship between live viewers and purchase willingness. The study introduces a new way of measuring interactions in live streaming commerce and proposes a way to manually gather data on consumer behaviors in live streaming platforms when the application programming interface (API) of such platforms does not support data mining algorithms.

Keywords: livestreaming marketing, live chats, live viewers, likes, new followers, purchase willingness

Procedia PDF Downloads 81

Authors: Jiajun Lu, Yun Ma

Abstract:

As a member of the tertiary industry, tourism is an important driving factor for urban economic development. As a well-known tourist city in China, according to statistics, the added value of tourism and related industries in 2022 will reach 106.326 billion yuan, a year-on-year increase of 1.2%, accounting for 3.7% of the city's GDP. However, the overall tourism development level of Chongqing is seriously unbalanced, and the tourism strength of the main urban area is much higher than that of the southeast Chongqing, northeast Chongqing and the surrounding city tourism area, and the overall tourism strength of the other three regions is relatively balanced. Based on the estimation of tourism development level and the geographic detector method, this paper finds that the important factors affecting the tourism development level of non-main urban areas in Chongqing are A-level tourist attractions. Through GIS geospatial analysis technology and SPSS data correlation research method, the spatial distribution characteristics and influencing factors of A-level tourist attractions in Chongqing were quantitatively analyzed by using data such as geospatial data cloud, relevant documents of Chongqing Municipal Commission of Culture and Tourism Development, planning cloud, and relevant statistical yearbooks. The results show that: (1) The spatial distribution of tourist attractions in non-main urban areas of Chongqing is agglomeration and uneven. (2) The spatial distribution of A-level tourist attractions in non-main urban areas of Chongqing is affected by ecological factors, and the degree of influence is in the order of water factors> topographic factors > green space factors.

Keywords: tourist attractions, geographic detectors, quantitative research, ecological factors, GIS technology, SPSS analysis

Procedia PDF Downloads 16

Authors: Min Woo Park, Jin Do Chung, Kyu Yeol Kim, Byoung Uk Im, Jang Woo Kim, Hae Yeul Ryu

Abstract:

Nine representative species of trees among all the street trees were selected to estimate the absorption amount of carbon dioxide emitted from street trees in Seoul calculating the biomass, amount of carbon saved, and annual absorption amount of carbon dioxide in each of the species. Planting distance of street trees in Seoul was 1,851,180 m, the number of planting lines was 1,287, the number of planted trees was 284,498 and 46 species of trees were planted as of 2013. According to the result of plugging the quantity of species of street trees in Seoul on the absorption amount of each of the species, 120,097 ton of biomass, 60,049.8 ton of amount of carbon saved, and 11,294 t CO2/year of annual absorption amount of carbon dioxide were calculated. Street ratio mentioned on the road statistics in Seoul in 2022 is 23.13%. If the street trees are assumed to be increased in the same rate, the number of street trees in Seoul was calculated to be 294,823. The planting distance was estimated to be 1,918,360 m, and the annual absorption amount of carbon dioxide was measured to be 11,704 t CO2/year. Plans for improving the annual absorption amount of carbon dioxide from street trees were established based on the expected amount of absorption. First of all, it is to improve the annual absorption amount of carbon dioxide by increasing the number of planted street trees after adjusting the planting distance of street trees. If adjusting the current planting distance to 6 m, it was turned out that 12,692.7 t CO2/year was absorbed on an annual basis. Secondly, it is to change the species of trees to tulip trees that represent high absorption rate. If increasing the proportion of tulip trees to 30% up to 2022, the annual absorption rate of carbon dioxide was calculated to be 17804.4 t CO2/year.

Keywords: absorption of carbon dioxide, source of absorbing carbon dioxide, trees in city, improving species

Procedia PDF Downloads 362

Authors: Takhul Bakhtiar

Abstract:

In South Sulawesi Province, there is an active Walanae Fault causing this area to frequently experience earthquakes. This study aims to determine the level of seismicity of the earthquake in order to obtain the potential for earthquakes in the future. The estimation of the potential for earthquakes is then made a scenario model determine the estimated level of shocks as an effort to mitigate earthquake disasters in the region. The method used in this study is the Gutenberg Richter Method through the statistical likelihood approach. This study used earthquake data in the South Sulawesi region in 1972 - 2022. The research location is located at the coordinates of 3.5° – 5.5° South Latitude and 119.5° – 120.5° East Longitude and divided into two segments, namely the northern segment at the coordinates of 3.5° – 4.5° South Latitude and 119,5° – 120,5° East Longitude then the southern segment with coordinates of 4.5° – 5.5° South Latitude and 119,5° – 120.5° East Longitude. This study uses earthquake parameters with a magnitude > 1 and a depth < 50 km. The results of the analysis show that the potential for earthquakes in the next ten years with a magnitude of M = 7 in the northern segment is estimated at 98.81% with an estimated shock level of VI-VII MMI around the cities of Pare-Pare, Barru, Pinrang and Soppeng then IV - V MMI in the cities of Bulukumba, Selayar, Makassar and Gowa. In the southern segment, the potential for earthquakes in the next ten years with a magnitude of M = 7 is estimated at 32.89% with an estimated VI-VII MMI shock level in the cities of Bulukumba, Selayar, Makassar and Gowa, then III-IV MMI around the cities of Pare-Pare, Barru, Pinrang and Soppeng.

Keywords: Gutenberg Richter, likelihood method, seismicity, shakemap and MMI scale

Procedia PDF Downloads 120

Authors: Linyu Wang, Mingjun Zhu, Jianhong Xiang, Hanyu Jiang

Abstract:

Aiming at the problem that the spectral efficiency of hybrid precoding (HP) is too low in the current millimeter wave (mmWave) massive multiple input multiple output (MIMO) system, this paper proposes a digital joint equivalent channel hybrid precoding algorithm, which is based on the introduction of digital encoding matrix iteration. First, the objective function is expanded to obtain the relation equation, and the pseudo-inverse iterative function of the analog encoder is derived by using the pseudo-inverse method, which solves the problem of greatly increasing the amount of computation caused by the lack of rank of the digital encoding matrix and reduces the overall complexity of hybrid precoding. Secondly, the analog coding matrix and the millimeter-wave sparse channel matrix are combined into an equivalent channel, and then the equivalent channel is subjected to Singular Value Decomposition (SVD) to obtain a digital coding matrix, and then the derived pseudo-inverse iterative function is used to iteratively regenerate the simulated encoding matrix. The simulation results show that the proposed algorithm improves the system spectral efficiency by 10~20%compared with other algorithms and the stability is also improved.

Keywords: mmWave, massive MIMO, hybrid precoding, singular value decompositing, equivalent channel

Procedia PDF Downloads 96

Authors: Rakesh Kumar, A. K. Ghosh

Abstract:

The paper presents the modeling of linear and nonlinear longitudinal aerodynamics using real flight data of Hansa-3 aircraft gathered at low and high angles of attack. The Neural-Gauss-Newton (NGN) method has been applied to model the linear and nonlinear longitudinal dynamics and estimate parameters from flight data. Unsteady aerodynamics due to flow separation at high angles of attack near stall has been included in the aerodynamic model using Kirchhoff’s quasi-steady stall model. NGN method is an algorithm that utilizes Feed Forward Neural Network (FFNN) and Gauss-Newton optimization to estimate the parameters and it does not require any a priori postulation of mathematical model or solving of equations of motion. NGN method was validated on real flight data generated at moderate angles of attack before application to the data at high angles of attack. The estimates obtained from compatible flight data using NGN method were validated by comparing with wind tunnel values and the maximum likelihood estimates. Validation was also carried out by comparing the response of measured motion variables with the response generated by using estimates a different control input. Next, NGN method was applied to real flight data generated by executing a well-designed quasi-steady stall maneuver. The results obtained in terms of stall characteristics and aerodynamic parameters were encouraging and reasonably accurate to establish NGN as a method for modeling nonlinear aerodynamics from real flight data at high angles of attack.

Keywords: parameter estimation, NGN method, linear and nonlinear, aerodynamic modeling

Procedia PDF Downloads 446

Authors: Anwaar Ahmed, Muhammad Bilal Khurshid, Samuel Labi

Abstract:

The effect of trucks on the level of service is determined by considering passenger car equivalents (PCE) of trucks. The current version of Highway Capacity Manual (HCM) uses a single PCE value for all tucks combined. However, the composition of truck traffic varies from location to location; therefore a single PCE-value for all trucks may not correctly represent the impact of truck traffic at specific locations. Consequently, present study developed separate PCE values for single-unit and combination trucks to replace the single value provided in the HCM on different freeways. Site specific PCE values, were developed using concept of spatial lagging headways (the distance from the rear bumper of a leading vehicle to the rear bumper of the following vehicle) measured from field traffic data. The study used data from four locations on a single urban freeway and three different rural freeways in Indiana. Three-stage-least-squares (3SLS) regression techniques were used to generate models that predicted lagging headways for passenger cars, single unit trucks (SUT), and combination trucks (CT). The estimated PCE values for single-unit and combination truck for basic urban freeways (level terrain) were: 1.35 and 1.60, respectively. For rural freeways the estimated PCE values for single-unit and combination truck were: 1.30 and 1.45, respectively. As expected, traffic variables such as vehicle flow rates and speed have significant impacts on vehicle headways. Study results revealed that the use of separate PCE values for different truck classes can have significant influence on the LOS estimation.

Keywords: level of service, capacity analysis, lagging headway, trucks

Procedia PDF Downloads 356

Authors: Dongju Kim, Youngjoo Suh, Hyojin Kim, Gyeongyeong Kim

Abstract:

Acoustic Emission Testing (AET) is widely used to test the structural integrity of an operational hydrogen storage container, and clustering algorithms are frequently used in pattern recognition methods to interpret AET results. However, the interpretation of AET results can vary from user to user as the tuning of the relevant parameters relies on the user's experience and knowledge of AET. Therefore, it is necessary to use a deep learning model to identify patterns in acoustic emission (AE) signal data that can be used to classify defects instead. In this paper, a deep learning-based model for classifying the types of defects in hydrogen storage tanks, using AE sensor waveforms, is proposed. As hydrogen storage tanks are commonly constructed using carbon fiber reinforced polymer composite (CFRP), a defect classification dataset is collected through a tensile test on a specimen of CFRP with an AE sensor attached. The performance of the classification model, using one-dimensional convolutional neural network (1-D CNN) and synthetic minority oversampling technique (SMOTE) data augmentation, achieved 91.09% accuracy for each defect. It is expected that the deep learning classification model in this paper, used with AET, will help in evaluating the operational safety of hydrogen storage containers.

Keywords: acoustic emission testing, carbon fiber reinforced polymer composite, one-dimensional convolutional neural network, smote data augmentation

Procedia PDF Downloads 94

Authors: Mehrnoosh Abouzari, Shahrokh Shahraei

Abstract:

With the development of artificial intelligence in the present age, intelligent machines and systems have proven their actual and potential capabilities and are mindful of increasing their presence in various fields of human life in the fields of industry, financial transactions, marketing, manufacturing, service affairs, politics, economics and various branches of the humanities .Therefore, despite the conservatism and prudence of law enforcement, the traces of artificial intelligence can be seen in various areas of law. Including judicial robotics capability estimation, intelligent judicial decision making system, intelligent defender and attorney strategy adjustment, dissemination and regulation of different and scattered laws in each case to achieve judicial coherence and reduce opinion, reduce prolonged hearing and discontent compared to the current legal system with designing rule-based systems, case-based, knowledge-based systems, etc. are efforts to apply AI in law. In this article, we will identify the ways in which AI is applied in its laws and regulations, identify the dominant concerns in this area and outline the relationship between these two areas in order to answer the question of how artificial intelligence can be used in different areas of law and what the implications of this application will be. The authors believe that the use of artificial intelligence in the three areas of legislative, judiciary and executive power can be very effective in governments' decisions and smart governance, and helping to reach smart communities across human and geographical boundaries that humanity's long-held dream of achieving is a global village free of violence and personalization and human error. Therefore, in this article, we are going to analyze the dimensions of how to use artificial intelligence in the three legislative, judicial and executive branches of government in order to realize its application.

Keywords: artificial intelligence, law, intelligent system, judge

Procedia PDF Downloads 119

Authors: David Percy

Abstract:

Landslides are a geologic phenomenon that affects a large number of inhabited places and are constantly being monitored and studied for the prediction of future occurrences. Reconstructability analysis (RA) is a methodology for extracting informative models from large volumes of data that work exclusively with discrete data. While RA has been used in medical applications and social science extensively, we are introducing it to the spatial sciences through applications like landslide prediction. Since RA works exclusively with discrete data, such as soil classification or bedrock type, working with continuous data, such as porosity, requires that these data are binned for inclusion in the model. RA constructs models of the data which pick out the most informative elements, independent variables (IVs), from each layer that predict the dependent variable (DV), landslide occurrence. Each layer included in the model retains its classification data as a primary encoding of the data. Unlike other machine learning algorithms that force the data into one-hot encoding type of schemes, RA works directly with the data as it is encoded, with the exception of continuous data, which must be binned. The usual physical and derived layers are included in the model, and testing our results against other published methodologies, such as neural networks, yields accuracy that is similar but with the advantage of a completely transparent model. The results of an RA session with a data set are a report on every combination of variables and their probability of landslide events occurring. In this way, every combination of informative state combinations can be examined.

Keywords: reconstructability analysis, machine learning, landslides, raster analysis

Procedia PDF Downloads 66

Authors: Sushish Baral, Pratibha Joshi, Yaman Maharjan

Abstract:

Glaucoma is a chronic eye condition that causes vision loss that is irreversible. Early detection and treatment are critical to prevent vision loss because it can be asymptomatic. For the identification of glaucoma, multiple deep learning algorithms are used. Transformer-based architectures, which use the self-attention mechanism to encode long-range dependencies and acquire extremely expressive representations, have recently become popular. Convolutional architectures, on the other hand, lack knowledge of long-range dependencies in the image due to their intrinsic inductive biases. The aforementioned statements inspire this thesis to look at transformer-based solutions and investigate the viability of adopting transformer-based network designs for glaucoma detection. Using retinal fundus images of the optic nerve head to develop a viable algorithm to assess the severity of glaucoma necessitates a large number of well-curated images. Initially, data is generated by augmenting ocular pictures. After that, the ocular images are pre-processed to make them ready for further processing. The system is trained using pre-processed images, and it classifies the input images as normal or glaucoma based on the features retrieved during training. The Vision Transformer (ViT) architecture is well suited to this situation, as it allows the self-attention mechanism to utilise structural modeling. Extensive experiments are run on the common dataset, and the results are thoroughly validated and visualized.

Keywords: glaucoma, vision transformer, convolutional architectures, retinal fundus images, self-attention, deep learning

Procedia PDF Downloads 191

Authors: Renukswamy Chikkamath, Vishvapalsinhji Ramsinh Parmar, Christoph Hewel, Markus Endres

Abstract:

Given a patent document, identifying distinct semantic annotations is an interesting research aspect. Text annotation helps the patent practitioners such as examiners and patent attorneys to quickly identify the key arguments of any invention, successively providing a timely marking of a patent text. In the process of manual patent analysis, to attain better readability, recognising the semantic information by marking paragraphs is in practice. This semantic annotation process is laborious and time-consuming. To alleviate such a problem, we proposed a dataset to train machine learning algorithms to automate the highlighting process. The contributions of this work are: i) we developed a multi-class dataset of size 150k samples by traversing USPTO patents over a decade, ii) articulated statistics and distributions of data using imperative exploratory data analysis, iii) baseline Machine Learning models are developed to utilize the dataset to address patent paragraph highlighting task, and iv) future path to extend this work using Deep Learning and domain-specific pre-trained language models to develop a tool to highlight is provided. This work assists patent practitioners in highlighting semantic information automatically and aids in creating a sustainable and efficient patent analysis using the aptitude of machine learning.

Keywords: machine learning, patents, patent sentiment analysis, patent information retrieval

Procedia PDF Downloads 92

Authors: Anuradha Chug, Sunali Gandhi

Abstract:

Regression Testing is a very expensive and time-consuming process carried out to ensure the validity of modified software. Due to the availability of insufficient resources to re-execute all the test cases in time constrained environment, efforts are going on to generate test data automatically without human efforts. Many search based techniques have been proposed to generate efficient, effective as well as optimized test data, so that the overall cost of the software testing can be minimized. The generated test data should be able to uncover all potential lapses that exist in the software or product. Inspired from the natural behavior of bat for searching her food sources, current study employed a meta-heuristic, search-based bat algorithm for optimizing the test data on the basis certain parameters without compromising their effectiveness. Mathematical functions are also applied that can effectively filter out the redundant test data. As many as 50 Java programs are used to check the effectiveness of proposed test data generation and it has been found that 86% saving in testing efforts can be achieved using bat algorithm while covering 100% of the software code for testing. Bat algorithm was found to be more efficient in terms of simplicity and flexibility when the results were compared with another nature inspired algorithms such as Firefly Algorithm (FA), Hill Climbing Algorithm (HC) and Ant Colony Optimization (ACO). The output of this study would be useful to testers as they can achieve 100% path coverage for testing with minimum number of test cases.

Keywords: regression testing, test case selection, test case prioritization, genetic algorithm, bat algorithm

Procedia PDF Downloads 381

Authors: Eman M. Morgan, Hayam M. Lotfy, Yasmin M. Fayez, Mohamed Abdelkawy, Engy Shokry

Abstract:

Two simple, selective, economic, safe, accurate, precise and environmentally friendly methods were developed and validated for the quantitative determination of valaciclovir (VAL) in the presence of its related substances R1 (acyclovir), R2 (guanine) in bulk powder and in the commercial pharmaceutical product containing the drug. Method A is a colorimetric method where VAL selectively reacts with ferric hydroxamate and the developed color was measured at 490 nm over a concentration range of 0.4-2 mg/mL with percentage recovery 100.05 ± 0.58 and correlation coefficient 0.9999. Method B is a reversed phase ultra performance liquid chromatographic technique (UPLC) which is considered superior in technology to the high-performance liquid chromatography with respect to speed, resolution, solvent consumption, time, and cost of analysis. Efficient separation was achieved on Agilent Zorbax CN column using ammonium acetate (0.1%) and acetonitrile as a mobile phase in a linear gradient program. Elution time for the separation was less than 5 min and ultraviolet detection was carried out at 256 nm over a concentration range of 2-50 μg/mL with mean percentage recovery 100.11±0.55 and correlation coefficient 0.9999. The proposed methods were fully validated as per International Conference on Harmonization specifications and effectively applied for the analysis of valaciclovir in pure form and tablets dosage form. Statistical comparison of the results obtained by the proposed and official or reported methods revealed no significant difference in the performance of these methods regarding the accuracy and precision respectively.

Keywords: hydroxamic acid, related substances, UPLC, valaciclovir

Procedia PDF Downloads 247

Authors: Maxime A. J. Kuitche, Ruxandra M. Botez, Arthur Guillemin

Abstract:

As the Unmanned Aerial Systems have found diverse utilities in both military and civil aviation, the necessity to obtain an accurate aerodynamic model has shown an enormous growth of interest. Recent modeling techniques are procedures using optimization algorithms and statistics that require many flight tests and are therefore extremely demanding in terms of costs. This paper presents a procedure to estimate the aerodynamic behavior of an unmanned aerial system from a numerical approach using computational fluid dynamic analysis. The study was performed using an unstructured mesh obtained from a grid convergence analysis at a Mach number of 0.14, and at an angle of attack of 0°. The flow around the aircraft was described using a standard k-ω turbulence model. Thus, the Reynold Averaged Navier-Stokes (RANS) equations were solved using ANSYS FLUENT software. The method was applied on the UAS-S45 designed and manufactured by Hydra Technologies in Mexico. The lift, the drag, and the pitching moment coefficients were obtained at different angles of attack for several flight conditions defined in terms of altitudes and Mach numbers. The results obtained from the Computational Fluid Dynamics analysis were compared with the results obtained by using the DATCOM semi-empirical procedure. This comparison has indicated that our approach is highly accurate and that the aerodynamic model obtained could be useful to estimate the flight dynamics of the UAS-S45.

Keywords: aerodynamic modelling, CFD Analysis, ANSYS FLUENT, UAS-S45

Procedia PDF Downloads 375

Authors: Abdisalam Hassan Muse, Samuel Mwalili, Oscar Ngesa

Abstract:

A generalized log-logistic distribution with variable shapes of the hazard rate was introduced and studied, extending the log-logistic distribution by adding an extra parameter to the classical distribution, leading to greater flexibility in analysing and modeling various data types. The proposed distribution has a large number of well-known lifetime special sub-models such as; Weibull, log-logistic, exponential, and Burr XII distributions. Its basic mathematical and statistical properties were derived. The method of maximum likelihood was adopted for estimating the unknown parameters of the proposed distribution, and a Monte Carlo simulation study is carried out to assess the behavior of the estimators. The importance of this distribution is that its tendency to model both monotone (increasing and decreasing) and non-monotone (unimodal and bathtub shape) or reversed “bathtub” shape hazard rate functions which are quite common in survival and reliability data analysis. Furthermore, the flexibility and usefulness of the proposed distribution are illustrated in a real-life data set and compared to its sub-models; Weibull, log-logistic, and BurrXII distributions and other parametric survival distributions with 3-parmaeters; like the exponentiated Weibull distribution, the 3-parameter lognormal distribution, the 3- parameter gamma distribution, the 3-parameter Weibull distribution, and the 3-parameter log-logistic (also known as shifted log-logistic) distribution. The proposed distribution provided a better fit than all of the competitive distributions based on the goodness-of-fit tests, the log-likelihood, and information criterion values. Finally, Bayesian analysis and performance of Gibbs sampling for the data set are also carried out.

Keywords: hazard rate function, log-logistic distribution, maximum likelihood estimation, generalized log-logistic distribution, survival data, Monte Carlo simulation

Procedia PDF Downloads 202

Authors: Alla Levina, Sergey Taranov

Abstract:

The classical approach to the providing noise immunity and integrity of information that process in computing devices and communication channels is to use linear codes. Linear codes have fast and efficient algorithms of encoding and decoding information, but this codes concentrate their detect and correct abilities in certain error configurations. To protect against any configuration of errors at predetermined probability can robust codes. This is accomplished by the use of perfect nonlinear and almost perfect nonlinear functions to calculate the code redundancy. The paper presents the error-correcting coding scheme using biorthogonal wavelet transform. Wavelet transform applied in various fields of science. Some of the wavelet applications are cleaning of signal from noise, data compression, spectral analysis of the signal components. The article suggests methods for constructing linear codes based on wavelet decomposition. For developed constructions we build generator and check matrix that contain the scaling function coefficients of wavelet. Based on linear wavelet codes we develop robust codes that provide uniform protection against all errors. In article we propose two constructions of robust code. The first class of robust code is based on multiplicative inverse in finite field. In the second robust code construction the redundancy part is a cube of information part. Also, this paper investigates the characteristics of proposed robust and linear codes.

Keywords: robust code, linear code, wavelet decomposition, scaling function, error masking probability

Procedia PDF Downloads 489

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 447

Authors: Gen Sakoda, Hideki Takayasu, Misako Takayasu

Abstract:

Waste reduction is a fundamental problem for sustainability. Methods for waste reduction with point-of-sales (POS) data are proposed, utilizing the knowledge of a recent econophysics study on a statistical property of POS data. Concretely, the non-stationary time series analysis method based on the Particle Filter is developed, which considers abnormal fluctuation scaling known as Taylor's law. This method is extended for handling incomplete sales data because of stock-outs by introducing maximum likelihood estimation for censored data. The way for optimal stock determination with pricing the cost of waste reduction is also proposed. This study focuses on the examination of the methods for large sales numbers where Taylor's law is obvious. Numerical analysis using aggregated POS data shows the effectiveness of the methods to reduce food waste maintaining a high profit for large sales numbers. Moreover, the way of pricing the cost of waste reduction reveals that a small profit loss realizes substantial waste reduction, especially in the case that the proportionality constant  of Taylor’s law is small. Specifically, around 1% profit loss realizes half disposal at =0.12, which is the actual  value of processed food items used in this research. The methods provide practical and effective solutions for waste reduction keeping a high profit, especially with large sales numbers.

Keywords: food waste reduction, particle filter, point-of-sales, sustainable development goals, Taylor's law, time series analysis

Procedia PDF Downloads 131

Authors: Ji-Seok Koo, Hee‑Yong Kwon, Hui-Young Yun, Kyung-Hui Wang, Youn-Seo Koo

Abstract:

This paper presents a forecasting system for PM2.5 levels in Seoul, South Korea, leveraging a combination of chemical transport modeling and ConvLSTM-DNN machine learning technology. Exposure to PM2.5 has known detrimental impacts on public health, making its prediction crucial for establishing preventive measures. Existing forecasting models, like the Community Multiscale Air Quality (CMAQ) and Weather Research and Forecasting (WRF), are hindered by their reliance on uncertain input data, such as anthropogenic emissions and meteorological patterns, as well as certain intrinsic model limitations. The system we've developed specifically addresses these issues by integrating machine learning and using carefully selected input features that account for local and distant sources of PM2.5. In South Korea, the PM2.5 concentration is greatly influenced by both local emissions and long-range transport from China, and our model effectively captures these spatial and temporal dynamics. Our PM2.5 prediction system combines the strengths of advanced hybrid machine learning algorithms, convLSTM and DNN, to improve upon the limitations of the traditional CMAQ model. Data used in the system include forecasted information from CMAQ and WRF models, along with actual PM2.5 concentration and weather variable data from monitoring stations in China and South Korea. The system was implemented specifically for Seoul's PM2.5 forecasting.

Keywords: PM2.5 forecast, machine learning, convLSTM, DNN

Procedia PDF Downloads 55

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 150

Authors: Syed Toqueer Akhter, Hussain Hamid

Abstract:

Over the last few decades an upward trend has been observed in the case of labor migration from Pakistan. The emigrants are not just economically motivated and in search of a safe living environment towards more developed countries in Europe, North America and Middle East. The opportunity cost of migration comes in the form of brain drain that is the loss of qualified and skilled human capital. Throughout the history of Pakistan, situations of political instability have emerged ranging from violation of political rights, political disappearances to political assassinations. Providing security to the citizens is a major issue faced in Pakistan due to increase in crime and terrorist activities. The aim of the study is to test the impact of political instability, appearing in the form of political terror, violation of political rights and civil liberty on skilled migration of labor. Three proxies are used to measure the political instability; political terror scale (based on a scale of 1-5, the political terror and violence that a country encounters in a particular year), political rights (a rating of 1-7, that describes political rights as the ability for the people to participate without restraint in political process) and civil liberty (a rating of 1-7, civil liberty is defined as the freedom of expression and rights without government intervention). Using time series data from 1980-2011, the distributed lag models were used for estimation because migration is not a onetime process, previous events and migration can lead to more migration. Our research clearly shows that political instability appearing in the form of political terror, political rights and civil liberty all appeared significant in explaining the extent of skilled migration of Pakistan.

Keywords: skilled labor migration, political terror, political rights, civil liberty, distributed lag model

Procedia PDF Downloads 1029

Authors: Shveta Puri, Shiv Jyoti Pandey, G. M. Bhat, Neha Raina

Abstract:

TheJammu and Kashmir region of the Northwest Himalaya had witnessed many devastating earthquakes in the recent past and has remained unexplored for any kind of seismic investigations except scanty records of the earthquakes that occurred in this region in the past. In this study, we have used local seismic data of year 2013 that was recorded by the network of Broadband Seismographs in J&K. During this period, our seismic stations recorded about 207 earthquakes including two moderate events of Mw 5.7 on 1st May, 2013 and Mw 5.1 of 2nd August, 2013.We analyzed the events of Mw 3-4.6 and the main events only (for minimizing the error) for source parameters, b value and sense of movement through waveform modeling for understanding seismotectonic and seismic hazard of the region. It has been observed that most of the events are bounded between 32.9° N – 33.3° N latitude and 75.4° E – 76.1° E longitudes, Moment Magnitude (Mw) ranges from Mw 3 to 5.7, Source radius (r), from 0.21 to 3.5 km, stress drop, from 1.90 bars to 71.1 bars and Corner frequency, from 0.39 – 6.06 Hz. The b-value for this region was found to be 0.83±0 from these events which are lower than the normal value (b=1), indicating the area is under high stress. The travel time inversion and waveform inversion method suggest focal depth up to 10 km probably above the detachment depth of the Himalayan region. Moment tensor solution of the (Mw 5.1, 02:32:47 UTC) main event of 2ndAugust suggested that the source fault is striking at 295° with dip of 33° and rake value of 85°. It was found that these events form intense clustering of small to moderate events within a narrow zone between Panjal Thrust and Kishtwar Window. Moment tensor solution of the main events and their aftershocks indicating thrust type of movement is occurring in this region.

Keywords: b-value, moment tensor, seismotectonics, source parameters

Procedia PDF Downloads 313

Authors: P. Byrnes, F. A. DiazDelaO

Abstract:

The Support Vector Machine (SVM) has become widely recognised as one of the leading algorithms in machine learning for both regression and binary classification. It expresses predictions in terms of a linear combination of kernel functions, referred to as support vectors. Despite its popularity amongst practitioners, SVM has some limitations, with the most significant being the generation of point prediction as opposed to predictive distributions. Stemming from this issue, a probabilistic model namely, Probabilistic Classification Vector Machines (PCVM), has been proposed which respects the original functional form of SVM whilst also providing a predictive distribution. As physical system designs become more complex, an increasing number of classification tasks involving industrial applications consist of more than two classes. Consequently, this research proposes a framework which allows for the extension of PCVM to a multi class setting. Additionally, the original PCVM framework relies on the use of type II maximum likelihood to provide estimates for both the kernel hyperparameters and model evidence. In a high dimensional multi class setting, however, this approach has been shown to be ineffective due to bad scaling as the number of classes increases. Accordingly, we propose the application of Markov Chain Monte Carlo (MCMC) based methods to provide a posterior distribution over both parameters and hyperparameters. The proposed framework will be validated against current multi class classifiers through synthetic and real life implementations.

Keywords: probabilistic classification vector machines, multi class classification, MCMC, support vector machines

Procedia PDF Downloads 221

Authors: Seyed Saeid Tabaee, Omid Bahar

Abstract:

Nowadays, using energy dissipation devices has been commonly used in structures. A high rate of energy absorption during earthquakes is the benefit of using such devices, which results in damage reduction of structural elements specifically columns. The hysteretic damping capacity of energy dissipation devices is the key point that it may adversely complicate analysis and design of such structures. This effect may be generally represented by equivalent viscous damping. The equivalent viscous damping may be obtained from the expected hysteretic behavior under the design or maximum considered displacement of a structure. In this paper, the hysteretic damping coefficient of a steel moment resisting frame (MRF), which its performance is enhanced by a buckling restrained brace (BRB) system has been evaluated. Having the foresight of damping fraction between BRB and MRF is inevitable for seismic design procedures like Direct Displacement-Based Design (DDBD) method. This paper presents an approach to calculate the damping fraction for such systems by carrying out the dynamic nonlinear time history analysis (NTHA) under harmonic loading, which is tuned to the natural frequency of the system. Two steel moment frame structures, one equipped with BRB, and the other without BRB are simultaneously studied. The extensive analysis shows that proportion of each system damping fraction may be calculated by its shear story portion. In this way, the contribution of each BRB in the floors and their general contribution in the structural performance may be clearly recognized, in advance.

Keywords: buckling restrained brace, direct displacement based design, dual systems, hysteretic damping, moment resisting frames

Procedia PDF Downloads 434

Authors: Emad A. Mohammed

Abstract:

The concept of hydraulic flow units (HFU) has been used for decades in the petroleum industry to improve the prediction of permeability. This concept is strongly related to the flow zone indicator (FZI) which is a function of the reservoir rock quality index (RQI). Both indices are based on reservoir porosity and permeability of core samples. It is assumed that core samples with similar FZI values belong to the same HFU. Thus, after dividing the porosity-permeability data based on the HFU, transformations can be done in order to estimate the permeability from the porosity. The conventional practice is to use the power law transformation using conventional HFU where percentage of error is considerably high. In this paper, neural network technique is employed as a soft computing transformation method to predict permeability instead of power law method to avoid higher percentage of error. This technique is based on HFU identification where Amaefule et al. (1993) method is utilized. In this regard, Kozeny and Carman (K–C) model, and modified K–C model by Hasan and Hossain (2011) are employed. A comparison is made between the two transformation techniques for the two porosity-permeability models. Results show that the modified K-C model helps in getting better results with lower percentage of error in predicting permeability. The results also show that the use of artificial intelligence techniques give more accurate prediction than power law method. This study was conducted on a heterogeneous complex carbonate reservoir in Oman. Data were collected from seven wells to obtain the permeability correlations for the whole field. The findings of this study will help in getting better estimation of permeability of a complex reservoir.

Keywords: permeability, hydraulic flow units, artificial intelligence, correlation

Procedia PDF Downloads 137

Authors: Mohammad Bakhshandeh

Abstract:

Structural Health Monitoring (SHM) is a crucial and necessary practice that plays a vital role in ensuring the safety and integrity of critical structures, and in particular, bridges. The continuous monitoring of bridges for signs of damage or degradation through Bridge Health Monitoring (BHM) enables early detection of potential problems, allowing for prompt corrective action to be taken before significant damage occurs. Although all monitoring techniques aim to provide accurate and decisive information regarding the remaining useful life, safety, integrity, and serviceability of bridges, understanding the development and propagation of damage is vital for maintaining uninterrupted bridge operation. Over the years, extensive research has been conducted on BHM methods, and experts in the field have increasingly adopted new methodologies. In this article, we provide a comprehensive exploration of the various BHM approaches, including sensor-based, non-destructive testing (NDT), model-based, and artificial intelligence (AI)-based methods. We also discuss the challenges associated with BHM, including sensor placement and data acquisition, data analysis and interpretation, cost and complexity, and environmental effects, through an extensive review of relevant literature and research studies. Additionally, we examine potential solutions to these challenges and propose future research ideas to address critical gaps in BHM.

Keywords: structural health monitoring (SHM), bridge health monitoring (BHM), sensor-based methods, machine-learning algorithms, and model-based techniques, sensor placement, data acquisition, data analysis

Procedia PDF Downloads 90

Authors: Mubarek Alpkiray, Tan Nguyen, Arild Saasen

Abstract:

Geothermal drilling operations contain numerous challenges that are encountered to increase the well cost and nonproductive time. Fluid loss is one of the most undesirable troublesome that can cause well abandonment in geothermal drilling. Lost circulation can be seen due to natural fractures, high mud weight, and extremely high formation temperatures. This challenge may cause wellbore stability problems and lead to expensive drilling operations. Wellbore stability is the main domain that should be considered to mitigate or prevent fluid loss into the formation. This paper describes the causes of fluid loss in the Pamukoren geothermal field in Turkey. A geomechanics approach integration and assessment is applied to help the understanding of fluid loss problems. In geothermal drillings, geomechanics is primarily based on rock properties, in-situ stress characterization, the temperature of the rock, determination of stresses around the wellbore, and rock failure criteria. Since a high-temperature difference between the wellbore wall and drilling fluid is presented, temperature distribution through the wellbore is estimated and implemented to the wellbore stability approach. This study reviewed geothermal drilling data to analyze temperature estimation along the wellbore, the cause of fluid loss and stored electric capacity of the reservoir. Our observation demonstrates the geomechanical approach's significant role in understanding safe drilling operations on high-temperature wells. Fluid loss is encountered due to thermal stress effects around the borehole. This paper provides a wellbore stability analysis for a geothermal drilling operation to discuss the causes of lost circulation resulting in nonproductive time and cost.

Keywords: geothermal wells, drilling, wellbore stresses, drilling fluid loss, thermal stress

Procedia PDF Downloads 195

Authors: E. A. Krasikov

Abstract:

Influence of neutron irradiation on RPV steel degradation are examined with reference to the possible reasons of the substantial experimental data scatter and furthermore – nonstandard (non-monotonous) and oscillatory embrittlement behavior. In our glance, this phenomenon may be explained by presence of the wavelike component in the embrittlement kinetics. We suppose that the main factor affecting steel anomalous embrittlement is fast neutron intensity (dose rate or flux), flux effect manifestation depends on state-of-the-art fluence level. At low fluencies, radiation degradation has to exceed normative value, then approaches to normative meaning and finally became sub normative. Data on radiation damage change including through the ex-service RPVs taking into account chemical factor, fast neutron fluence and neutron flux were obtained and analyzed. In our opinion, controversy in the estimation on neutron flux on radiation degradation impact may be explained by presence of the wavelike component in the embrittlement kinetics. Therefore, flux effect manifestation depends on fluence level. At low fluencies, radiation degradation has to exceed normative value, then approaches to normative meaning and finally became sub normative. Moreover as a hypothesis we suppose that at some stages of irradiation damaged metal have to be partially restored by irradiation i.e. neutron bombardment. Nascent during irradiation structure undergo occurring once or periodically transformation in a direction both degradation and recovery of the initial properties. According to our hypothesis, at some stage(s) of metal structure degradation neutron bombardment became recovering factor. As a result, oscillation arises that in turn leads to enhanced data scatter.

Keywords: annealing, embrittlement, radiation, RPV steel

Procedia PDF Downloads 342