Search results for: strength prediction
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 5855

Search results for: strength prediction

2645 A Low-Cost Air Quality Monitoring Internet of Things Platform

Authors: Christos Spandonidis, Stefanos Tsantilas, Elias Sedikos, Nektarios Galiatsatos, Fotios Giannopoulos, Panagiotis Papadopoulos, Nikolaos Demagos, Dimitrios Reppas, Christos Giordamlis

Abstract:

In the present paper, a low cost, compact and modular Internet of Things (IoT) platform for air quality monitoring in urban areas is presented. This platform comprises of dedicated low cost, low power hardware and the associated embedded software that enable measurement of particles (PM2.5 and PM10), NO, CO, CO2 and O3 concentration in the air, along with relative temperature and humidity. This integrated platform acts as part of a greater air pollution data collecting wireless network that is able to monitor the air quality in various regions and neighborhoods of an urban area, by providing sensor measurements at a high rate that reaches up to one sample per second. It is therefore suitable for Big Data analysis applications such as air quality forecasts, weather forecasts and traffic prediction. The first real world test for the developed platform took place in Thessaloniki, Greece, where 16 devices were installed in various buildings in the city. In the near future, many more of these devices are going to be installed in the greater Thessaloniki area, giving a detailed air quality map of the city.

Keywords: distributed sensor system, environmental monitoring, Internet of Things, smart cities

Procedia PDF Downloads 146
2644 Reliable Method for Estimating Rating Curves in the Natural Rivers

Authors: Arash Ahmadi, Amirreza Kavousizadeh, Sanaz Heidarzadeh

Abstract:

Stage-discharge curve is one of the conventional methods for continuous river flow measurement. In this paper, an innovative approach is proposed for predicting the stage-discharge relationship using the application of isovel contours. Using the proposed method, it is possible to estimate the stage-discharge curve in the whole section with only using discharge information from just one arbitrary water level. For this purpose, multivariate relationships are used to determine the mean velocity in a cross-section. The unknown exponents of the proposed relationship have been obtained by using the second version of the Strength Pareto Evolutionary Algorithm (SPEA2), and the appropriate equation was selected by applying the TOPSIS (Technique for Order Preferences by Similarity to an Ideal Solution) approach. Results showed a close agreement between the estimated and observed data in the different cross-sections.

Keywords: rating curves, SPEA2, natural rivers, bed roughness distribution

Procedia PDF Downloads 159
2643 Effect of Cr2O3 on Mechanical Properties of Aluminum Produced Powder Metallurgy

Authors: Yasin Akgul, Fazil Husem, Memis Isik

Abstract:

In this study, effect of content of chromium (III) oxide on production of Al/Cr203 alloys were investigated. Experimental procedure was started with mixturing of powders in the presence of absolute ethanol, vacuum distillation technique was used for evaporation, by ultrasonic bath and mechanic stirrer. Pressing procedure was achieved by hydrolic press that has 100 tons forcing for production of 25 mm diameter compact green billets. Green bodies were sintered at 600 °C in argon atmosphere. Scanning electron microscope (SEM) analysis for characterization of microstructure, compression test for determination of strength and Vickers test for measuring of hardness of sintered billets were done. End of the study is concluded that, enhancement of physical and mechanical properties is observed by increasing content of chromium (III) oxide.

Keywords: aluminium, chromium (III) oxide, powder metallurgy, sintering

Procedia PDF Downloads 230
2642 Emotion Recognition with Occlusions Based on Facial Expression Reconstruction and Weber Local Descriptor

Authors: Jadisha Cornejo, Helio Pedrini

Abstract:

Recognition of emotions based on facial expressions has received increasing attention from the scientific community over the last years. Several fields of applications can benefit from facial emotion recognition, such as behavior prediction, interpersonal relations, human-computer interactions, recommendation systems. In this work, we develop and analyze an emotion recognition framework based on facial expressions robust to occlusions through the Weber Local Descriptor (WLD). Initially, the occluded facial expressions are reconstructed following an extension approach of Robust Principal Component Analysis (RPCA). Then, WLD features are extracted from the facial expression representation, as well as Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG). The feature vector space is reduced using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). Finally, K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) classifiers are used to recognize the expressions. Experimental results on three public datasets demonstrated that the WLD representation achieved competitive accuracy rates for occluded and non-occluded facial expressions compared to other approaches available in the literature.

Keywords: emotion recognition, facial expression, occlusion, fiducial landmarks

Procedia PDF Downloads 182
2641 Effects of Peakedness of Bimodal Waves on Overtopping of Sloping Seawalls

Authors: Stephen Orimoloye, Jose Horrillo-Caraballo, Harshinie Karunarathna, Dominic E. Reeve

Abstract:

Prediction of wave overtopping is an essential component of coastal seawall designing and management. Not only that excessive overtopping is reported for impermeable seawalls under bimodal waves, but overtopping is also showing a high sensitivity to the peakedness of the random wave propagation patterns. In the present study, we present a comprehensive analysis of the effects of peakedness of bimodal wave patterns of the overtopping of sloping seawalls. An energy-conserved bimodal spectrum with four different spectra peak periods and swell percentages was applied to estimate wave overtopping in both numerical and experimental flumes. Results of incident surface elevations and bimodal spectra were accurately captured across the flume domain using sets of well-positioned resistant-type wave gauges. Peakedness characteristics of the wave patterns were extracted to derive a relationship between the non-dimensional overtopping and the peakedness across the wave groups in the wave series. The full paper will briefly describe the development of the spectrum and present a comprehensive results analysis leading to the derivation of the relationship between dimensionless overtopping and peakedness of bimodal waves.

Keywords: wave overtopping, peakedness, bimodal waves, swell percentages

Procedia PDF Downloads 181
2640 Predictive Factors of Prognosis in Acute Stroke Patients Receiving Traditional Chinese Medicine Therapy: A Retrospective Study

Authors: Shaoyi Lu

Abstract:

Background: Traditional Chinese medicine has been used to treat stroke, which is a major cause of morbidity and mortality. There is, however, no clear agreement about the optimal timing, population, efficacy, and predictive prognosis factors of traditional Chinese medicine supplemental therapy. Method: In this study, we used a retrospective analysis with data collection from stroke patients in Stroke Registry In Chang Gung Healthcare System (SRICHS). Stroke patients who received traditional Chinese medicine consultation in neurology ward of Keelung Chang Gung Memorial Hospital from Jan 2010 to Dec 2014 were enrolled. Clinical profiles including the neurologic deficit, activities of daily living and other basic characteristics were analyzed. Through propensity score matching, we compared the NIHSS and Barthel index before and after the hospitalization, and applied with subgroup analysis, and adjusted by multivariate regression method. Results: Totally 115 stroke patients were enrolled with experiment group in 23 and control group in 92. The most important factor for prognosis prediction were the scores of National Institutes of Health Stroke Scale and Barthel index right before the hospitalization. Traditional Chinese medicine intervention had no statistically significant influence on the neurological deficit of acute stroke patients, and mild negative influence on daily activity performance of acute hemorrhagic stroke patient. Conclusion: Efficacy of traditional Chinese medicine as a supplemental therapy for acute stroke patients was controversial. The reason for this phenomenon might be complex and require more research to comprehend. Key words: traditional Chinese medicine, acupuncture, Stroke, NIH stroke scale, Barthel index, predictive factor. Method: In this study, we used a retrospective analysis with data collection from stroke patients in Stroke Registry In Chang Gung Healthcare System (SRICHS). Stroke patients who received traditional Chinese medicine consultation in neurology ward of Keelung Chang Gung Memorial Hospital from Jan 2010 to Dec 2014 were enrolled. Clinical profiles including the neurologic deficit, activities of daily living and other basic characteristics were analyzed. Through propensity score matching, we compared the NIHSS and Barthel index before and after the hospitalization, and applied with subgroup analysis, and adjusted by multivariate regression method. Results: Totally 115 stroke patients were enrolled with experiment group in 23 and control group in 92. The most important factor for prognosis prediction were the scores of National Institutes of Health Stroke Scale and Barthel index right before the hospitalization. Traditional Chinese medicine intervention had no statistically significant influence on the neurological deficit of acute stroke patients, and mild negative influence on daily activity performance of acute hemorrhagic stroke patient. Conclusion: Efficacy of traditional Chinese medicine as a supplemental therapy for acute stroke patients was controversial. The reason for this phenomenon might be complex and require more research to comprehend.

Keywords: traditional Chinese medicine, complementary and alternative medicine, stroke, acupuncture

Procedia PDF Downloads 360
2639 A Data Mining Approach for Analysing and Predicting the Bank's Asset Liability Management Based on Basel III Norms

Authors: Nidhin Dani Abraham, T. K. Sri Shilpa

Abstract:

Asset liability management is an important aspect in banking business. Moreover, the today’s banking is based on BASEL III which strictly regulates on the counterparty default. This paper focuses on prediction and analysis of counter party default risk, which is a type of risk occurs when the customers fail to repay the amount back to the lender (bank or any financial institutions). This paper proposes an approach to reduce the counterparty risk occurring in the financial institutions using an appropriate data mining technique and thus predicts the occurrence of NPA. It also helps in asset building and restructuring quality. Liability management is very important to carry out banking business. To know and analyze the depth of liability of bank, a suitable technique is required. For that a data mining technique is being used to predict the dormant behaviour of various deposit bank customers. Various models are implemented and the results are analyzed of saving bank deposit customers. All these data are cleaned using data cleansing approach from the bank data warehouse.

Keywords: data mining, asset liability management, BASEL III, banking

Procedia PDF Downloads 552
2638 Flange/Web Distortional Buckling of Cold-Formed Steel Beams with Web Holes under Pure Bending

Authors: Nan-Ting Yu, Boksun Kim, Long-Yuan Li

Abstract:

The cold-formed steel beams with web holes are widely used as the load-carrying members in structural engineering. The perforations can release the space of the building and let the pipes go through. However, the perforated cold-formed steel (PCFS) beams may fail by distortional buckling more easily than beams with plain web; this is because the rotational stiffness from the web decreases. It is well known that the distortional buckling can be described as the buckling of the compressed flange-lip system. In fact, near the ultimate failure, the flange/web corner would move laterally, which indicates the bending of the web should be taken account. The purpose of this study is to give a specific solution for the critical stress of flange/web distortional buckling of PCFS beams. The new model is deduced based on classical energy method, and the deflection of the web is represented by the shape function of the plane beam element. The finite element analyses have been performed to validate the accuracy of the proposed model. The comparison of the critical stress calculated from Hancock's model, FEA, and present model, shows that the present model can provide a splendid prediction for the flange/web distortional buckling of PCFS beams.

Keywords: cold-formed steel, beams, perforations, flange-web distortional buckling, finite element analysis

Procedia PDF Downloads 130
2637 Experimental and Numerical Analysis on Enhancing Mechanical Properties of CFRP Adhesive Joints Using Hybrid Nanofillers

Authors: Qiong Rao, Xiongqi Peng

Abstract:

In this work, multi-walled carbon nanotubes (MWCNTs) and graphene nanoplates (GNPs) were dispersed into epoxy adhesive to investigate their synergy effects on the shear properties, mode I and mode II fracture toughness of unidirectional composite bonded joints. Testing results showed that the incorporation of MWCNTs and GNPs significantly improved the shear strength, the mode I and mode II fracture toughness by 36.6%, 45% and 286%, respectively. In addition, the fracture surfaces of the bonding area as well as the toughening mechanism of nanofillers were analyzed. Finally, a nonlinear cohesive/friction coupled model for delamination analysis of adhesive layer under shear and normal compression loadings was proposed and implemented in ABAQUS/Explicit via user subroutine VUMAT.

Keywords: nanofillers, adhesive joints, fracture toughness, cohesive zone model

Procedia PDF Downloads 133
2636 Improvement of Mechanical Properties and Corrosion Resistance of AA7056 Aluminum Alloys by the Non-isothermal Aging Process

Authors: Tse-An Pan, Sheng-Long Lee

Abstract:

The effect of non-isothermal aging on the mechanical properties and corrosion resistance of Al-9Zn-2.3Mg-1.9Cu (AA7056) alloys was investigated. The results revealed that thick materials were limited to retrogression and re-aging treatment (RRA). It could not reach the retrogression temperature in the RRA treatment. Compared with the RRA treatment, the non-isothermal aging (NIA) treatment produced discontinuous precipitates at grain boundaries, while the intragranular precipitates were fine and dense. The strength was similar to that of the RRA treatment; the corrosion resistance of the alloy was significantly improved by NIA aging. NIA treatment was less affected by the thickness of the alloy. The difference between the actual temperature and the setting temperature of the alloy is minimal during the aging process. The combination of properties could overcome the fact that RRA treatment cannot handle thick materials.

Keywords: Al-Zn-Mg-Cu alloy, corrosion, retrogression, re-aging, non-isothermal aging

Procedia PDF Downloads 182
2635 Design of Geochemical Maps of Industrial City Using Gradient Boosting and Geographic Information System

Authors: Ruslan Safarov, Zhanat Shomanova, Yuri Nossenko, Zhandos Mussayev, Ayana Baltabek

Abstract:

Geochemical maps of distribution of polluting elements V, Cr, Mn, Co, Ni, Cu, Zn, Mo, Cd, Pb on the territory of the Pavlodar city (Kazakhstan), which is an industrial hub were designed. The samples of soil were taken from 100 locations. Elemental analysis has been performed using XRF. The obtained data was used for training of the computational model with gradient boosting algorithm. The optimal parameters of model as well as the loss function were selected. The computational model was used for prediction of polluting elements concentration for 1000 evenly distributed points. Based on predicted data geochemical maps were created. Additionally, the total pollution index Zc was calculated for every from 1000 point. The spatial distribution of the Zc index was visualized using GIS (QGIS). It was calculated that the maximum coverage area of the territory of the Pavlodar city belongs to the moderately hazardous category (89.7%). The visualization of the obtained data allowed us to conclude that the main source of contamination goes from the industrial zones where the strategic metallurgical and refining plants are placed.

Keywords: Pavlodar, geochemical map, gradient boosting, CatBoost, QGIS, spatial distribution, heavy metals

Procedia PDF Downloads 82
2634 Elasto-Viscoplastic Constitutive Modelling of Slow-Moving Landslides

Authors: Deepak Raj Bhat, Kazushige Hayashi, Yorihiro Tanaka, Shigeru Ogita, Akihiko Wakai

Abstract:

Slow-moving landslides are one of the major natural disasters in mountainous regions. Therefore, study of the creep displacement behaviour of a landslide and associated geological and geotechnical issues seem important. This study has addressed and evaluated the slow-moving behaviour of landslide using the 2D-FEM based Elasto-viscoplastic constitutive model. To our based knowledge, two new control constitutive parameters were incorporated in the numerical model for the first time to better understand the slow-moving behaviour of a landslide. First, the predicted time histories of horizontal displacement of the landslide are presented and discussed, which may be useful for landslide displacement prediction in the future. Then, the simulation results of deformation pattern and shear strain pattern is presented and discussed. Moreover, the possible failure mechanism along the slip surface of such landslide is discussed based on the simulation results. It is believed that this study will be useful to understand the slow-moving behaviour of landslides, and at the same time, long-term monitoring and management of the landslide disaster will be much easier.

Keywords: numerical simulation, ground water fluctuations, elasto-viscoplastic model, slow-moving behaviour

Procedia PDF Downloads 78
2633 Rice Blessing Ceremony of Thailand and Vietnam: The Relation of Southeast Asia

Authors: Patthida Bunchavalit, Saharot Kittimahacharoen

Abstract:

The objective of this article is to compare rice blessing ceremony between Thailand and Vietnam. Both countries are located in Southeast Asia where agriculture is the main occupation. As a result of the study, it is found that the rice blessing ceremony of Thai and Vietnamese societies have differences and similarities. A person leading the ceremony is a person who has the highest position in the country. For Thailand, it is the king or royal family member while for Vietnam, it is the president. In Thailand, the ceremony began in Ayutthaya period which derived from Buddhism and Brahmanism ideology. It is annually organized in the beginning of raining season. In Vietnam, it is annually organized in the beginning of spring. The first time it occurred was in Tien Le Monarchy period of Thien Phuc era deriving from Chinese ideology. The differences are ideas, believes, objectives and details of the ceremony. It is, in Thailand, to boost farmer’s morale and to predict the fertility of crops in each year. Additionally, there is a prediction using royal cows. Meanwhile, in Vietnam the purpose is to worship god of weather for seasonal rain and productive harvesting. Therefore, it is presumed that the rice blessing ceremony of Thailand and Vietnam somewhat have similarities in spite of having different origin but are on the same basis of belief.

Keywords: agriculture, ceremony, culture, Thailand, Vietnam

Procedia PDF Downloads 185
2632 Near Infrared Spectrometry to Determine the Quality of Milk, Experimental Design Setup and Chemometrics: Review

Authors: Meghana Shankara, Priyadarshini Natarajan

Abstract:

Infrared (IR) spectroscopy has revolutionized the way we look at materials around us. Unraveling the pattern in the molecular spectra of materials to analyze the composition and properties of it has been one of the most interesting challenges in modern science. Applications of the IR spectrometry are numerous in the field’s pharmaceuticals, health, food and nutrition, oils, agriculture, construction, polymers, beverage, fabrics and much more limited only by the curiosity of the people. Near Infrared (NIR) spectrometry is applied robustly in analyzing the solids and liquid substances because of its non-destructive analysis method. In this paper, we have reviewed the application of NIR spectrometry in milk quality analysis and have presented the modes of measurement applied in NIRS measurement setup, Design of Experiment (DoE), classification/quantification algorithms used in the case of milk composition prediction like Fat%, Protein%, Lactose%, Solids Not Fat (SNF%) along with different approaches for adulterant identification. We have also discussed the important NIR ranges for the chosen milk parameters. The performance metrics used in the comparison of the various Chemometric approaches include Root Mean Square Error (RMSE), R^2, slope, offset, sensitivity, specificity and accuracy

Keywords: chemometrics, design of experiment, milk quality analysis, NIRS measurement modes

Procedia PDF Downloads 271
2631 Pull-Out Behavior of Mechanical Anchor Bolts by Cyclic Loading

Authors: Yoshinori Kitsutaka, Kusumi Shingo, Matsuzawa Koichi, Kunieda Yoichiro, Yagisawa Yasuei

Abstract:

In this study, the pull-out properties of various mechanical anchor bolts embedded in concrete were investigated. Five kinds of mechanical anchor bolts were selected which were ordinarily used for concrete anchoring. Tensile tests for mechanical anchor bolts embedded in φ300mm x 100mm size concrete were conducted to measure the load - load displacement curves. The loading conditions were a monotonous loading and a repeating loading. The fracture energy for each mechanical anchor bolts was estimated by the analysis of consumed energy calculated by the load - load displacement curve. The effect of the types of mechanical anchor bolts on the pull-out properties of concrete subjected in monotonous loading and a repeating loading was cleared.

Keywords: concrete, cyclic loading, mechanical anchor bolt, pull-out strength

Procedia PDF Downloads 262
2630 Prediction of Corrosion Inhibition Using Methyl Ester Sulfonate Anionic Surfactants

Authors: A. Asselah, A. Khalfi, M. A.Toumi, A.Tazerouti

Abstract:

The study of the corrosion inhibition of a standard carbon steel "API 5L grade X70" by two biodegradable anionic surfactants derived from fatty acids by photo sulfochlorination, called sodium lauryl methyl ester sulfonates and sodium palmityl methyl ester sulfonates was carried. A solution at 2.5 g/l NaCl saturated with carbon dioxide is used as a corrosive medium. The gravimetric and electrochemical technics (stationary and transient) were used in order to quantify the rate of corrosion and to evaluate the electrochemical inhibition efficiency, thus the nature of the mode of action of the inhibitor, in addition to a surface characterization by scanning electron microscopy (MEB) coupled to energy dispersive X-ray spectroscopy (EDX). The variation of the concentration and the temperature were examined, and the mode of adsorption of these inhibitors on the surface of the metal was established by assigning it the appropriate isotherm and determining the corresponding thermodynamic parameters. The MEB-EDX allowed the visualization of good adhesion of the protective film formed by the surfactants to the surface of the steel. The corrosion inhibition was evaluated at around 93% for sodium lauryl methyl ester sulfonate surfactant at 20 ppm and 87.2% at 50 ppm for sodium palmityl methyl ester sulfonate surfactant.

Keywords: carbon steel, oilfield, corrosion, anionic surfactants

Procedia PDF Downloads 95
2629 Effect of Hydroxyl Functionalization on the Mechanical and Fracture Behaviour of Monolayer Graphene

Authors: Akarsh Verma, Avinash Parashar

Abstract:

The aim of this article is to study the effects of hydroxyl functional group on the mechanical strength and fracture toughness of graphene. This functional group forms the backbone of intrinsic atomic structure of graphene oxide (GO). Molecular dynamics-based simulations were performed in conjunction with reactive force field (ReaxFF) parameters to capture the mode-I fracture toughness of hydroxyl functionalised graphene. Moreover, these simulations helped in concluding that spatial distribution and concentration of hydroxyl functional group significantly affects the fracture morphology of graphene nanosheet. In contrast to literature investigations, atomistic simulations predicted a transition in the failure morphology of hydroxyl functionalised graphene from brittle to ductile as a function of its spatial distribution on graphene sheet.

Keywords: graphene, graphene oxide, ReaxFF, molecular dynamics

Procedia PDF Downloads 179
2628 A Particle Filter-Based Data Assimilation Method for Discrete Event Simulation

Authors: Zhi Zhu, Boquan Zhang, Tian Jing, Jingjing Li, Tao Wang

Abstract:

Data assimilation is a model and data hybrid-driven method that dynamically fuses new observation data with a numerical model to iteratively approach the real system state. It is widely used in state prediction and parameter inference of continuous systems. Because of the discrete event system’s non-linearity and non-Gaussianity, traditional Kalman Filter based on linear and Gaussian assumptions cannot perform data assimilation for such systems, so particle filter has gradually become a technical approach for discrete event simulation data assimilation. Hence, we proposed a particle filter-based discrete event simulation data assimilation method and took the unmanned aerial vehicle (UAV) maintenance service system as a proof of concept to conduct simulation experiments. The experimental results showed that the filtered state data is closer to the real state of the system, which verifies the effectiveness of the proposed method. This research can provide a reference framework for the data assimilation process of other complex nonlinear systems, such as discrete-time and agent simulation.

Keywords: discrete event simulation, data assimilation, particle filter, model and data-driven

Procedia PDF Downloads 13
2627 Forecasting the Sea Level Change in Strait of Hormuz

Authors: Hamid Goharnejad, Amir Hossein Eghbali

Abstract:

Recent investigations have demonstrated the global sea level rise due to climate change impacts. In this study climate changes study the effects of increasing water level in the strait of Hormuz. The probable changes of sea level rise should be investigated to employ the adaption strategies. The climatic output data of a GCM (General Circulation Model) named CGCM3 under climate change scenario of A1b and A2 were used. Among different variables simulated by this model, those of maximum correlation with sea level changes in the study region and least redundancy among themselves were selected for sea level rise prediction by using stepwise regression. One models of Discrete Wavelet artificial Neural Network (DWNN) was developed to explore the relationship between climatic variables and sea level changes. In these models, wavelet was used to disaggregate the time series of input and output data into different components and then ANN was used to relate the disaggregated components of predictors and predictands to each other. The results showed in the Shahid Rajae Station for scenario A1B sea level rise is among 64 to 75 cm and for the A2 Scenario sea level rise is among 90 to 105 cm. Furthermore the result showed a significant increase of sea level at the study region under climate change impacts, which should be incorporated in coastal areas management.

Keywords: climate change scenarios, sea-level rise, strait of Hormuz, forecasting

Procedia PDF Downloads 271
2626 Identification of Landslide Features Using Back-Propagation Neural Network on LiDAR Digital Elevation Model

Authors: Chia-Hao Chang, Geng-Gui Wang, Jee-Cheng Wu

Abstract:

The prediction of a landslide is a difficult task because it requires a detailed study of past activities using a complete range of investigative methods to determine the changing condition. In this research, first step, LiDAR 1-meter by 1-meter resolution of digital elevation model (DEM) was used to generate six environmental factors of landslide. Then, back-propagation neural networks (BPNN) was adopted to identify scarp, landslide areas and non-landslide areas. The BPNN uses 6 environmental factors in input layer and 1 output layer. Moreover, 6 landslide areas are used as training areas and 4 landslide areas as test areas in the BPNN. The hidden layer is set to be 1 and 2; the hidden layer neurons are set to be 4, 5, 6, 7 and 8; the learning rates are set to be 0.01, 0.1 and 0.5. When using 1 hidden layer with 7 neurons and the learning rate sets to be 0.5, the result of Network training root mean square error is 0.001388. Finally, evaluation of BPNN classification accuracy by the confusion matrix shows that the overall accuracy can reach 94.4%, and the Kappa value is 0.7464.

Keywords: digital elevation model, DEM, environmental factors, back-propagation neural network, BPNN, LiDAR

Procedia PDF Downloads 144
2625 Machine Learning in Momentum Strategies

Authors: Yi-Min Lan, Hung-Wen Cheng, Hsuan-Ling Chang, Jou-Ping Yu

Abstract:

The study applies machine learning models to construct momentum strategies and utilizes the information coefficient as an indicator for selecting stocks with strong and weak momentum characteristics. Through this approach, the study has built investment portfolios capable of generating superior returns and conducted a thorough analysis. Compared to existing research on momentum strategies, machine learning is incorporated to capture non-linear interactions. This approach enhances the conventional stock selection process, which is often impeded by difficulties associated with timeliness, accuracy, and efficiency due to market risk factors. The study finds that implementing bidirectional momentum strategies outperforms unidirectional ones, and momentum factors with longer observation periods exhibit stronger correlations with returns. Optimizing the number of stocks in the portfolio while staying within a certain threshold leads to the highest level of excess returns. The study presents a novel framework for momentum strategies that enhances and improves the operational aspects of asset management. By introducing innovative financial technology applications to traditional investment strategies, this paper can demonstrate significant effectiveness.

Keywords: information coefficient, machine learning, momentum, portfolio, return prediction

Procedia PDF Downloads 53
2624 Effect of Process Parameters on Mechanical Properties of Friction Stir Welded Aluminium Alloy Joints Using Factorial Design

Authors: Gurjinder Singh, Ankur Gill, Amardeep Singh Kang

Abstract:

In the present work an effort has been made to study the influence of the welding parameters on tensile strength of friction stir welding of aluminum. Three process parameters tool rotation speed, welding speed, and shoulder diameter were selected for the study. Two level factorial design of eight runs was selected for conducting the experiments. The mathematical model was developed from the data obtained. The significance of coefficients and adequacy of developed models were tested by ‘t’ test and ‘F’ test respectively. The effects of process parameters on mechanical properties have been represented in the form of graphs for better understanding.

Keywords: friction stir welding, aluminium alloy, mathematical model, welding speed

Procedia PDF Downloads 440
2623 Ultra High Performance Concrete Using Special Aggregates for Irregular Structures (the New Concrete Technology)

Authors: Arjun, A. D. Singh

Abstract:

Concrete the basic material using in construction across the global these days. The purpose of this special concrete is to provide extra strength and stability for irregular structure where the center of gravity is disturbed. In this paper an effort has been made to use different type of material aggregates has been discussed. We named As "STAR Aggregates" which has qualities to resist Shear, tension and compression forces. We have been divided into coarse aggregates and fine aggregates according to their sizes. Star Aggregates has interlocking behavior and cutting edge technology. Star aggregates had been draft and deign in Auto CAD and then analysis in ANSYS software. by using special aggregates we deign concrete grade of M40 for mega structures and irregular structure. This special concrete with STAR aggregates use in construction for irregular structure like Bridges, Skyscrapers or in deigned buildings.

Keywords: star aggregates, high performance concrete, material aggregates, interlocking

Procedia PDF Downloads 567
2622 Biomimetic Adhesive Pads for Precision Manufacturing Robots

Authors: Hoon Yi, Minho Sung, Hangil Ko, Moon Kyu Kwak, Hoon Eui Jeong

Abstract:

Inspired by the remarkable adhesion properties of gecko lizards, bio-inspired dry adhesives with smart adhesion properties have been developed in the last decade. Compared to earlier dry adhesives, the recently developed ones exhibit excellent adhesion strength, smart directional adhesion, and structural robustness. With these unique adhesion properties, bio-inspired dry adhesive pads have strong potential for use in precision industries such as semiconductor or display manufacturing. In this communication, we present a new manufacturing technology based on advanced dry adhesive systems that enable precise manipulation of large-area substrates over repeating cycles without any requirement for external force application. This new manufacturing technique is also highly accurate and environment-friendly, and thus has strong potential as a next-generation clean manufacturing technology.

Keywords: gecko, manufacturing robot, precision manufacturing

Procedia PDF Downloads 505
2621 Optimizing the Scanning Time with Radiation Prediction Using a Machine Learning Technique

Authors: Saeed Eskandari, Seyed Rasoul Mehdikhani

Abstract:

Radiation sources have been used in many industries, such as gamma sources in medical imaging. These waves have destructive effects on humans and the environment. It is very important to detect and find the source of these waves because these sources cannot be seen by the eye. A portable robot has been designed and built with the purpose of revealing radiation sources that are able to scan the place from 5 to 20 meters away and shows the location of the sources according to the intensity of the waves on a two-dimensional digital image. The operation of the robot is done by measuring the pixels separately. By increasing the image measurement resolution, we will have a more accurate scan of the environment, and more points will be detected. But this causes a lot of time to be spent on scanning. In this paper, to overcome this challenge, we designed a method that can optimize this time. In this method, a small number of important points of the environment are measured. Hence the remaining pixels are predicted and estimated by regression algorithms in machine learning. The research method is based on comparing the actual values of all pixels. These steps have been repeated with several other radiation sources. The obtained results of the study show that the values estimated by the regression method are very close to the real values.

Keywords: regression, machine learning, scan radiation, robot

Procedia PDF Downloads 79
2620 Pavement Roughness Prediction Systems: A Bump Integrator Approach

Authors: Manish Pal, Rumi Sutradhar

Abstract:

Pavement surface unevenness plays a pivotal role on roughness index of road which affects on riding comfort ability. Comfort ability refers to the degree of protection offered to vehicle occupants from uneven elements in the road surface. So, it is preferable to have a lower roughness index value for a better riding quality of road users. Roughness is generally defined as an expression of irregularities in the pavement surface which can be measured using different equipment like MERLIN, Bump integrator, Profilometer etc. Among them Bump Integrator is quite simple and less time consuming in case of long road sections. A case study is conducted on low volume roads in West District in Tripura to determine roughness index (RI) using Bump Integrator at the standard speed of 32 km/h. But it becomes too tough to maintain the requisite standard speed throughout the road section. The speed of Bump Integrator (BI) has to lower or higher in some distinctive situations. So, it becomes necessary to convert these roughness index values of other speeds to the standard speed of 32 km/h. This paper highlights on that roughness index conversional model. Using SPSS (Statistical Package of Social Sciences) software a generalized equation is derived among the RI value at standard speed of 32 km/h and RI value at other speed conditions.

Keywords: bump integrator, pavement distresses, roughness index, SPSS

Procedia PDF Downloads 247
2619 Neural Network Analysis Applied to Risk Prediction of Early Neonatal Death

Authors: Amanda R. R. Oliveira, Caio F. F. C. Cunha, Juan C. L. Junior, Amorim H. P. Junior

Abstract:

Children deaths are traumatic events that most often can be prevented. The technology of prevention and intervention in cases of infant deaths is available at low cost and with solid evidence and favorable results, however, with low access cover. Weight is one of the main factors related to death in the neonatal period, so the newborns of low birth weight are a population at high risk of death in the neonatal period, especially early neonatal period. This paper describes the development of a model based in neural network analysis to predict the mortality risk rating in the early neonatal period for newborns of low birth weight to identify the individuals of this population with increased risk of death. The neural network applied was trained with a set of newborns data obtained from Brazilian health system. The resulting network presented great success rate in identifying newborns with high chances of death, which demonstrates the potential for using this tool in an integrated manner to the health system, in order to direct specific actions for improving prognosis of newborns.

Keywords: low birth weight, neonatal death risk, neural network, newborn

Procedia PDF Downloads 448
2618 Effects of Sulphide Mining on AISI 304 Stainless Steel

Authors: Aguasanta Miguel Sarmiento, José Miguel Dávila, María Luisa de la Torre

Abstract:

Acid mine drainage (AMD) is an acidic leachate with high levels of metals and sulphates in solution, which seriously affects the durability and strength of metallic materials used in the construction of structural and mechanical components. This paper presents the results of the evolution over time of the reduction in tensile strength and defects in AISI 304 stainless steel in contact with acid mine drainage. For this purpose, a total of 30 bars with a diameter of 8 mm and a length of 14 cm were placed transversely in the course of a stream contaminated by AMD from the sulphide mines of the Iberian Pyritic Belt (SW Spain). This stream has average pH values of 2.6, a potential of 660 mV, and average concentrations of 12 g/L of sulphates, 1.2 g/L of Fe, 191 mg/L of Zn, etc. Every two months of exposure, 6 stainless steel bars were extracted from the acid stream. They were subjected to surface roughness analysis carried out with the help of Mitutoyo Surftest SJ-210 surface roughness tester. The analysis was carried out at three different points on 5 specimens from each series. The average reading of each parameter is calculated in order to ensure the accuracy of the measurements and the surface coverage. Arithmetic mean roughness value (Ra), mean roughness depth (Rz), and root mean square roughness (Rq) were measured. Five specimens from each series were statically tensile tested using universal equipment (Servosis ME 403 of 200kN). The specimens were clamped at their ends with two grips for cylindrical sections, and the tensile force was applied at a constant speed of 0.5 kN/s, according to the requirements of standard UNE-EN ISO 6892-1: 2020. To determine the modulus of elasticity, limits close to 15% and 55% of the maximum load were used, depending on the course of each test. Field Emission Scanning Electron Microscopy (FESEM) was used to observe corrosion products and defects generated by exposure to AMD. Energy dispersive X-ray spectrometry (EDS) was used to analyse the chemical composition of the corrosion products formed. For this purpose, small pieces were cut from the resulting specimens, cleaned, and embedded in epoxy resin. The results show that after only 5 months of exposure of AISI 304 stainless steel to the mining environment, the surface roughness increases significantly, with average depths almost 6 times greater than the initial one. Cracks are observed on the surface of the material, which increases in size with the time of exposure. A large number of grains with a composition of more than 57% Pb and 16% Sn can be observed inside these cracks. Tensile tests show a reduction in the resistance of this material after only two months of exposure. The results show the serious problems that would result from the use of this material for the use of mechanical components in a sulphide mining environment, not only because of the significant reduction in the lifetime of such components, but also because of the implications for human safety.

Keywords: acid mine drainage, corrosion, mechanical properties, stainless steel

Procedia PDF Downloads 16
2617 Hybrid Concrete Construction (HCC) for Sustainable Infrastructure Development in Nigeria

Authors: Muhammad Bello Ibrahim, M. Auwal Zakari, Aliyu Usman

Abstract:

Hybrid concrete construction (HCC) combines all the benefits of pre-casting with the advantages of cast in-situ construction. Merging the two, as a hybrid structure, results in even greater construction speed, value, and the overall economy. Its variety of uses has gained popularity in the United States and in Europe due to its distinctive benefits. However, the increase of its application in some countries (including Nigeria) has been relatively slow. Several researches have shown that hybrid construction offers an ultra-high performance concrete that offers superior strength, durability and aesthetics with design flexibility and within sustainability credentials, based on the available and economically visible technologies. This paper examines and documents the criterion that will help inform the process of deciding whether or not to adopt hybrid concrete construction (HCC) technology rather than more traditional alternatives. It also the present situation of design, construction and research on hybrid structures.

Keywords: hybrid concrete construction, Nigeria, sustainable infrastructure development, design flexibility

Procedia PDF Downloads 561
2616 Development of 3D Printed Natural Fiber Reinforced Composite Scaffolds for Maxillofacial Reconstruction

Authors: Sri Sai Ramya Bojedla, Falguni Pati

Abstract:

Nature provides the best of solutions to humans. One such incredible gift to regenerative medicine is silk. The literature has publicized a long appreciation for silk owing to its incredible physical and biological assets. Its bioactive nature, unique mechanical strength, and processing flexibility make us curious to explore further to apply it in the clinics for the welfare of mankind. In this study, Antheraea mylitta and Bombyx mori silk fibroin microfibers are developed by two economical and straightforward steps via degumming and hydrolysis for the first time, and a bioactive composite is manufactured by mixing silk fibroin microfibers at various concentrations with polycaprolactone (PCL), a biocompatible, aliphatic semi-crystalline synthetic polymer. Reconstructive surgery in any part of the body except for the maxillofacial region deals with replacing its function. But answering both the aesthetics and function is of utmost importance when it comes to facial reconstruction as it plays a critical role in the psychological and social well-being of the patient. The main concern in developing adequate bone graft substitutes or a scaffold is the noteworthy variation in each patient's bone anatomy. Additionally, the anatomical shape and size will vary based on the type of defect. The advent of additive manufacturing (AM) or 3D printing techniques to bone tissue engineering has facilitated overcoming many of the restraints of conventional fabrication techniques. The acquired patient's CT data is converted into a stereolithographic (STL)-file which is further utilized by the 3D printer to create a 3D scaffold structure in an interconnected layer-by-layer fashion. This study aims to address the limitations of currently available materials and fabrication technologies and develop a customized biomaterial implant via 3D printing technology to reconstruct complex form, function, and aesthetics of the facial anatomy. These composite scaffolds underwent structural and mechanical characterization. Atomic force microscopic (AFM) and field emission scanning electron microscopic (FESEM) images showed the uniform dispersion of the silk fibroin microfibers in the PCL matrix. With the addition of silk, there is improvement in the compressive strength of the hybrid scaffolds. The scaffolds with Antheraea mylitta silk revealed higher compressive modulus than that of Bombyx mori silk. The above results of PCL-silk scaffolds strongly recommend their utilization in bone regenerative applications. Successful completion of this research will provide a great weapon in the maxillofacial reconstructive armamentarium.

Keywords: compressive modulus, 3d printing, maxillofacial reconstruction, natural fiber reinforced composites, silk fibroin microfibers

Procedia PDF Downloads 199