Search results for: multilayer tensionless extensible geosynthetic

Authors: Sanjeev Kumar Raghuwanshi, Yadvendra Singh

Abstract:

The objective of this paper is to develop and optimize the Fiber Bragg (FBG) grating based Surface Plasmon Resonance (SPR) sensor for monitoring the hazardous toxic chemicals and gases in underground mines or any industrial area. A fully cladded telecommunication standard FBG is proposed to develop to produce surface plasmon resonance. A thin few nm gold/silver film (subject to optimization) is proposed to apply over the FBG sensing head using e-beam deposition method. Sensitivity enhancement of the sensor will be done by adding a composite nanostructured Graphene Oxide (GO) sensing layer using the spin coating method. Both sensor configurations suppose to demonstrate high responsiveness towards the changes in resonance wavelength. The GO enhanced sensor may show increased sensitivity of many fold compared to the gold coated traditional fibre optic sensor. Our work is focused on to optimize GO, multilayer structure and to develop fibre coating techniques that will serve well for sensitive and multifunctional detection of hazardous chemicals. This research proposal shows great potential towards future development of optical fiber sensors using readily available components such as Bragg gratings as highly sensitive chemical sensors in areas such as environmental sensing.

Keywords: surface plasmon resonance, fibre Bragg grating, sensitivity, toxic gases, MATRIX method

Procedia PDF Downloads 248

Authors: Ashutosh Verma, Satyendra Mittal

Abstract:

Numerous geosynthetic reinforced soil (GRS) abutment failures over the years have been attributed to the loss of strength at the facing-reinforcement interface due to seasonal thermal expansion/contraction of the bridge deck. This causes excessive settlement below the bridge seat, causing bridge bumps along the approach road which reduces the design life of any abutment. Before designers while choosing the type of facing, a broad range of facing configurations are undoubtedly available. Generally speaking, these configurations can be divided into three groups: modular (panels/block), continuous, and full height rigid (FHR). The purpose of the current study is to use 1g physical model tests under serviceable cyclic lateral displacements to experimentally investigate the behaviour of these three facing classifications. To simulate field behaviour, a field instrumented GRS abutment prototype was modeled into a N scaled down 1g physical model (N = 5) with adjustable facing arrangements to represent these three facing classifications. For cyclic lateral displacement (d/H) of top facing at loading rate of 1mm/min, the peak earth pressure coefficient (K) on the facing and vertical settlement of the footing (s/B) at 25, 50, 75 and 100 cycles have been measured. For a constant footing offset of x/H = 0.1, three forms of cyclic displacements have been performed to simulate active condition (CA), passive condition (CP), and active-passive condition (CAP). The findings showed that when reinforcements are integrated into the wall along with presence of gravel gabions i.e. FHR design, a rather substantial earth pressure occurs over the facing. Despite this, the FHR facing's continuous nature works in conjunction with the reinforcements' membrane resilience to reduce footing settlement. On the other hand, the pressure over the wall is released upon lateral excitation by the relative displacement between the panels in modular facing reducing the connection strength at the interface and leading to greater settlements below footing. On the contrary, continuous facing do not exhibit relative displacement along the depth of facing rather fails through rotation about the base, which extends the zone of active failure in the backfill leading to large depressions in the backfill region around the bridge seat. Conservatively, FHR facing shows relatively stable responses under lateral cyclic excitations as compared to modular or continuous type of abutment facing.

Keywords: GRS abutments, 1g physical model, full height rigid, cyclic lateral displacement

Procedia PDF Downloads 50

Authors: Maha M.Saber, Eitedal Daoud, Moetazza M. Alshafei, Lobna M. Abd El-Latif

Abstract:

Children in the third world consumes many food products colored red like sweets and soft drink without knowing its effect on health or the type of color used in these products Erythrosine (ER,FD & C Red No.3) is one of the most common coloring agent used in these products and in coloring cherry in compotes. The possible adverse effect of erythrosine ER on the thyroid gland function is investigated in albino rats. Forty-five adult male albino rats were divided to three groups two groups will receive ER orally in doses 68 and I36mg/kg respectively. Third group will receive distilled water for three months Sections of thyroid glands were examined for histopathological, morphometric analysis and MIB-I Ki67 (proliferative marker). Serum concentration of triiodothyronine (T3), Thyroxin (T4) and thyrotrophin (TSH) were determined, results showed histological changes in the two treatment groups versus control group in the group with 68mg/kg dose show vaculation of the cytoplasm of follicular cells and pleomorphism of their nuclei. While the other treated group {136mg /kg} showed congestion of blood vessels, hyperplasia of the interstitial cells and increased multilayer of the follicular cells. Highly significant increase in the mean area of the thyroid follicles in both treated groups compared to control group.Erythrosine treated groups showed a very highly significant decrease (P < 0.001) in serum concentration of T3 and T 4 while TSH showed a very highly significant increase versus control.

Keywords: erythrosine, thyroid, morphometrics, proliferative marker

Procedia PDF Downloads 380

Authors: Luiz Carlos Wrobel, Matjaz Hribersek, Jure Marn, Jurij Iljaz

Abstract:

Dynamic thermography has been clinically proven to be a valuable diagnostic technique for skin tumor detection as well as for other medical applications such as breast cancer diagnostics, diagnostics of vascular diseases, fever screening, dermatological and other applications. Thermography for medical screening can be done in two different ways, observing the temperature response under steady-state conditions (passive or static thermography), and by inducing thermal stresses by cooling or heating the observed tissue and measuring the thermal response during the recovery phase (active or dynamic thermography). The numerical modelling of heat transfer phenomena in biological tissue during dynamic thermography can aid the technique by improving process parameters or by estimating unknown tissue parameters based on measured data. This paper presents a nonlinear numerical model of multilayer skin tissue containing a skin tumor, together with the thermoregulation response of the tissue during the cooling-rewarming processes of dynamic thermography. The model is based on the Pennes bioheat equation and solved numerically by using a subdomain boundary element method which treats the problem as axisymmetric. The paper includes computational tests and numerical results for Clark II and Clark IV tumors, comparing the models using constant and temperature-dependent thermophysical properties, which showed noticeable differences and highlighted the importance of using a local thermoregulation model.

Keywords: boundary element method, dynamic thermography, static thermography, skin tumor diagnostic

Procedia PDF Downloads 77

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

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

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

Procedia PDF Downloads 101

Authors: Guanglin Song

Abstract:

(Objective) Situated within the context of China's tiered medical treatment system, this study aims to analyze spatial causes of urban healthcare access difficulties from the perspective of the configuration of healthcare facilities. (Methods) A social network analysis approach is employed to construct a healthcare demand and supply flow network between major residential clusters and various tiers of hospitals in the city.(Conclusion) The findings reveal that:1.there exists overall maldistribution and over-concentration of healthcare resources in Study Area, characterized by structural imbalance; 2.the low rate of primary care utilization in Study Area is a key factor contributing to congestion at higher-tier hospitals, as excessive reliance on these institutions by neighboring communities exacerbates the problem; 3.gradual optimization of the healthcare facility layout in Study Area, encompassing holistic, local, and individual institutional levels, can enhance systemic efficiency and resource balance.(Prospects) This research proposes a method for evaluating urban healthcare resource distribution structures based on service flows within hierarchical networks. It offers spatially targeted optimization suggestions for promoting the implementation of the tiered healthcare system and alleviating challenges related to accessibility and congestion in seeking medical care. Provide some new ideas for researchers and healthcare managers in countries, cities, and healthcare management around the world with similar challenges.

Keywords: flow of public services, urban networks, healthcare facilities, spatial planning, urban networks

Procedia PDF Downloads 27

Authors: Clara Shenderey, Helena Vitoshkin, Mordechai Barak, Avraham Arbel

Abstract:

Greenhouse cultivation is an energy-intensive process due to the high demands on cooling or heating according to external climatic conditions, which could be extreme in the summer or winter seasons. The thermal radiation rate inside a greenhouse depends mainly on the type of covering material and greenhouse construction. Using additional thermal screens under a greenhouse covering combined with a dehumidification system improves the insulation and could be cost-effective. Greenhouse covering material usually contains protective ultraviolet (UV) radiation additives to prevent the film wear, insect harm, and crop diseases. This paper investigates the overall heat transfer coefficient, or U-value, for greenhouse polyethylene covering contains UV-additives and glass covering with or without a thermal screen supplement. The hot-box method was employed to evaluate overall heat transfer coefficients experimentally as a function of the type and number of the thermal screens. The results show that the overall heat transfer coefficient decreases with increasing the number of thermal screens as a hyperbolic function. The overall heat transfer coefficient highly depends on the ability of the material to reflect thermal radiation. Using a greenhouse covering, i.e., polyethylene films or glass, in combination with high reflective thermal screens, i.e., containing about 98% of aluminum stripes or aluminum foil, the U-value reduces by 61%-89% in the first case, whereas by 70%-92% in the second case, depending on the number of the thermal screen. Using thermal screens made from low reflective materials may reduce the U-value by 30%-57%. The heat transfer coefficient is an indicator of the thermal insulation properties of the materials, which allows farmers to make decisions on the use of appropriate thermal screens depending on the external and internal climate conditions in a greenhouse.

Keywords: energy-saving thermal screen, greenhouse cover material, heat transfer coefficient, hot box

Procedia PDF Downloads 122

Authors: Lijuan Zhou, Mengqi Wu, Changyong Niu

Abstract:

Attributed graph clustering can utilize the graph topology and node attributes to uncover hidden community structures and patterns in complex networks, aiding in the understanding and analysis of complex systems. Utilizing contrastive learning for attributed graph clustering can effectively exploit meaningful implicit relationships between data. However, existing attributed graph clustering methods based on contrastive learning suffer from the following drawbacks: 1) Complex data augmentation increases computational cost, and inappropriate data augmentation may lead to semantic drift. 2) The selection of positive and negative samples neglects the intrinsic cluster structure learned from graph topology and node attributes. Therefore, this paper proposes a method called self-supervised Attributed Graph Clustering with Dual Contrastive Loss constraints (AGC-DCL). Firstly, Siamese Multilayer Perceptron (MLP) encoders are employed to generate two views separately to avoid complex data augmentation. Secondly, the neighborhood contrastive loss is introduced to constrain node representation using local topological structure while effectively embedding attribute information through attribute reconstruction. Additionally, clustering-oriented contrastive loss is applied to fully utilize clustering information in global semantics for discriminative node representations, regarding the cluster centers from two views as negative samples to fully leverage effective clustering information from different views. Comparative clustering results with existing attributed graph clustering algorithms on six datasets demonstrate the superiority of the proposed method.

Keywords: attributed graph clustering, contrastive learning, clustering-oriented, self-supervised learning

Procedia PDF Downloads 18

Authors: M. Abdoos, A. Amadeh, M. Adabi

Abstract:

In recent decades, the use of titanium and its alloys due to their high mechanical properties, light weight and their corrosion resistance has increased in military and industry applications. However, the poor surface properties can limit their widely usage. Many researches were carried out to improve their surface properties. The most effective technique is based on solid-state diffusion of elements that can form intermetallic compounds with the substrate. In the present work, inter-diffusion of nickel and titanium and formation of Ni-Ti intermetallic compounds in nickel-coated Ti-6Al-4V alloy have been studied. Initially, nickel was electrodeposited on the alloy using Watts bath at a current density of 20 mA/cm2 for 1 hour. The coated specimens were then heat treated in a tubular furnace under argon atmosphere at different temperatures near Ti β-transus to maximize the diffusion rate for various durations in order to improve the surface properties of the Ti-6Al-4V alloy. The effect of temperature and time on the thickness of diffusion layer and characteristics of intermetallic phases was studied by means of scanning electron microscope (SEM) equipped with energy dispersive X-ray spectrometer (EDS) and microhardness test. The results showed that a multilayer structure was formed after heat treatment: an outer layer of remaining nickel, an area of intermetallic layers with different compositions and solid solution of Ni-Ti. Three intermetallic layers was detected by EDS analysis, namely an outer layer with about 75 at.% Ni (Ni3Ti), an intermediate layer with 50 at.% Ni (NiTi) and finally an inner layer with 36 at.% Ni (NiTi2). It was also observed that the increase in time or temperature led to the formation of thicker intermetallic layers. Meanwhile, the microhardness of heat treated samples increased with formation of Ni-Ti intermetallics; however, its value depended on heat treatment parameters.

Keywords: heat treatment, microhardness, Ni coating, Ti-6Al-4V

Procedia PDF Downloads 419

Authors: Imme Petersen, Wiebke Sick, Regine Kollek

Abstract:

In systems medicine, high-throughput technologies produce large amounts of data on different biological and pathological processes, including (disturbed) gene expressions, metabolic pathways and signaling. The large volume of data of different types, stored in separate databases and often located at different geographical sites have posed new challenges regarding data handling and processing. Tools based on bioinformatics have been developed to resolve the upcoming problems of systematizing, standardizing and integrating the various data. However, the heterogeneity of data gathered at different levels of biological complexity is still a major challenge in data analysis. To build multilayer disease modules, large and heterogeneous data of disease-related information (e.g., genotype, phenotype, environmental factors) are correlated. Therefore, a great deal of attention in systems medicine has been put on data standardization, primarily to retrieve and combine large, heterogeneous datasets into standardized and incorporated forms and structures. However, this data-centred concept of standardization in systems medicine is contrary to the debate in science and technology studies (STS) on standardization that rather emphasizes the dynamics, contexts and negotiations of standard operating procedures. Based on empirical work on research consortia that explore the molecular profile of diseases to establish systems medical approaches in the clinic in Germany, we trace how standardized data are processed and shaped by bioinformatics tools, how scientists using such data in research perceive such standard operating procedures and which consequences for knowledge production (e.g. modeling) arise from it. Hence, different concepts and meanings of standardization are explored to get a deeper insight into standard operating procedures not only in systems medicine, but also beyond.

Keywords: data, science and technology studies (STS), standardization, systems medicine

Procedia PDF Downloads 313

Authors: Amani Hassan Abu Atieh

Abstract:

This study aims at examining the patterns of ideology reflected in the written discourse of women writers in the media of Jordan; Lana Mamkgh is taken as an example. This study critically analyzes the discursive, linguistic, and cognitive representations that she employs as an agent in the institutionalized discourse of the media. Grounded in van Dijk’s critical discourse analysis approach to Sociocognitive Discourse Studies, the present study builds a multilayer framework that encompasses van Dijk’s triangle: discourse, society, and cognition. Specifically, the study attempts to analyze, at both micro and macro levels, the underlying cognitive processes and structures, mainly ideology and discursive strategies, which are functional in the production of women’s discourse in terms of meaning, forms, and functions. Cognitive processes that social actors adopt are underlined by experience/context and semantic mental models on the one hand and social cognition on the other. This study is based on qualitative research and adopts purposive sampling, taking as an example a sample of an opinion article written by Lana Mamkgh in the Arabic Jordanian Daily, Al Rai. Taking her role as an agent in the public sphere, she stresses the National and feminist ideologies, demonstrating the use of assertive, evaluative, and expressive linguistic and rhetorical devices that appeal to the logic, ethics, and emotions of the addressee. Highlighting the agency of Jordanian writers in the media, the study sought to achieve the macro goal of dispensing political and social justice to the underprivileged. Further, the study seeks to prove that the voice of Jordanian women, viewed as underrepresented and invisible in the public arena, has come through clearly.

Keywords: critical discourse analysis, sociocognitive theory, ideology, women discourse, media

Procedia PDF Downloads 74

Authors: Hanjun Yun, Gun Bae, Nabin Paul, Cheolhee Moon

Abstract:

Flexible OLED is an important technology for the next generation display over various kinds of applications. However, the organic materials of OLEDs degrade rapidly under the invasion of oxygen and water moisture. The degradation causes the formation of non-emitting areas which gradually suppress the device brightness, ultimately the lifetime of the device decreasing rapidly. Until now, the most suitable sealing process of the flexible OLED devices is a thin film encapsulation (TFE). However, TFE consists of a multilayer thin-film structure with organic-inorganic materials, so the cost is expensive and the process time is long. Another problem is that the blocking characteristics from the moisture and oxygen are not perfect. Therefore, the encapsulation of the flexible OLED device is a still key technical issue for the successful market entry. In this study, we are to introduce an auxiliary sealing line between the two flexible substrates. The electrode lines were formed on the substrates which have a SiNx barrier coating layer. To induce the solid phase diffusion process between the SiNx layer and the electrode lines, the electrode materials were determined as Al-Si composition. Thermal energy was supplied for both the SiNx layer and Al-Si electrode lines within the furnace to induce the interfacial bonding through the solid phase diffusion of Si. We printed a test pattern for the edge of the flexible PET substrate of 3cm*3cm size. Experimental conditions such as heating temperature, heating time were optimized to get enough adhesion strength which was estimated through the competitive bending test. Finally, OLED devices with flexible PET substrate of 3cm*3cm size were manufactured to investigate the blocking characteristics as an encapsulation layer.

Keywords: barrier, encapsulation, OLED, solid phase diffusion

Procedia PDF Downloads 208

Authors: W. Swiderski

Abstract:

Composite materials are one answer to the growing demand for materials with better parameters of construction and exploitation. Composite materials also permit conscious shaping of desirable properties to increase the extent of reach in the case of metals, ceramics or polymers. In recent years, composite materials have been used widely in aerospace, energy, transportation, medicine, etc. Fiber-reinforced composites including carbon fiber, glass fiber and aramid fiber have become a major structural material. The typical defect during manufacture and operation is delamination damage of layered composites. When delamination damage of the composites spreads, it may lead to a composite fracture. One of the many methods used in non-destructive testing of composites is active infrared thermography. In active thermography, it is necessary to deliver energy to the examined sample in order to obtain significant temperature differences indicating the presence of subsurface anomalies. To detect possible defects in composite materials, different methods of thermal stimulation can be applied to the tested material, these include heating lamps, lasers, eddy currents, microwaves or ultrasounds. The use of a suitable source of thermal stimulation on the test material can have a decisive influence on the detection or failure to detect defects. Samples of multilayer structure carbon composites were prepared with deliberately introduced defects for comparative purposes. Very thin defects of different sizes and shapes made of Teflon or copper having a thickness of 0.1 mm were screened. Non-destructive testing was carried out using the following sources of thermal stimulation, heating lamp, flash lamp, ultrasound and eddy currents. The results are reported in the paper.

Keywords: Non-destructive testing, IR thermography, composite material, thermal stimulation

Procedia PDF Downloads 232

Authors: Fernanda M. Assef, Maria Teresinha A. Steiner

Abstract:

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.

Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines

Procedia PDF Downloads 78

Authors: Sylwia Gieraltowska, Lukasz Wachnicki, Bartlomiej S. Witkowski, Marek Godlewski

Abstract:

Oxide layers doped with rare-earth (RE) ions in optimized way can absorb short (ultraviolet light), which will be converted to visible light by so-called down-conversion. Down-conversion mechanisms are usually exploited to modify the incident solar spectrum. In down conversion, multiple low-energy photons are generated to exploit the energy of one incident high-energy photon. These RE-doped oxide materials have attracted a great deal of attention from researchers because of their potential for optical manipulation in optical devices (detectors, temperature sensors, and compact solid-state lasers, light-emitting diodes), bio-analysis, medical therapy, display technologies, and light harvesting (such as in photovoltaic cells). The zirconium dioxide (ZrO2) doped RE ions (Eu, Tb, Ce) multilayer structures were tested as active layers, which can convert short wave emission to light in the visible range (the down-conversion mechanism). For these applications original approach of deposition ZrO2 layers using the Atomic Layer Deposition (ALD) method and doping these layers with RE ions using the spin-coating technique was used. ALD films are deposited at relatively low temperature (well below 250°C). This can be an effective method to achieve the white-light emission and to improve on this way light conversion efficiency, by an extension of absorbed spectral range by a solar cell material. Photoluminescence (PL), X-ray diffraction (XRD), scanning electron microscope (SEM) and atomic force microscope (AFM) measurement are analyzed. The research was financially supported by the National Science Centre (decision No. DEC-2012/06/A/ST7/00398 and DEC- 2013/09/N/ST5/00901).

Keywords: ALD, oxide layers, photovoltaics, thin films

Procedia PDF Downloads 247

Authors: M. R. Akbari, M. Sadeghi, R. Faghihi, M. A. Mosleh-Shirazi, A. R. Khorrami-Moghadam

Abstract:

Proton radiotherapy (PRT) is becoming an established treatment modality for cancer. The localized tumors, the same as undifferentiated thyroid tumors are insufficiently handled by conventional radiotherapy, while protons would propose the prospect of increasing the tumor dose without exceeding the tolerance of the surrounding healthy tissues. In spite of relatively high advantages in giving localized radiation dose to the tumor region, in proton therapy, secondary neutron production can have significant contribution on integral dose and lessen advantages of this modality contrast to conventional radiotherapy techniques. Furthermore, neutrons have high quality factor, therefore, even a small physical dose can cause considerable biological effects. Measuring of this neutron dose is a very critical step in prediction of secondary cancer incidence. It has been found that FLUKA Monte Carlo code simulations have been used to evaluate dose due to secondaries in proton therapy. In this study, first, by validating simulated proton beam range in water phantom with CSDA range from NIST for the studied proton energy range (34-54 MeV), a proton therapy in thyroid gland cancer was simulated using FLUKA code. Secondary neutron dose equivalent of some organs and tissues after the target volume caused by 34 and 54 MeV proton interactions were calculated in order to evaluate secondary cancer incidence. A multilayer cylindrical neck phantom considering all the layers of neck tissues and a proton beam impinging normally on the phantom were also simulated. Trachea (accompanied by Larynx) had the greatest dose equivalent (1.24×10-1 and 1.45 pSv per primary 34 and 54 MeV protons, respectively) among the simulated tissues after the target volume in the neck region.

Keywords: FLUKA code, neutron dose equivalent, proton therapy, thyroid gland

Procedia PDF Downloads 393

Authors: Gholamreza Hashemitabr, Reza Valadan, Alireza Rafiei, Mohammad Reza Bassami

Abstract:

Breast cancer is the most common malignancy among women worldwide. Cancer cells use a complex multilayer network of epidermal growth factor receptors (EGFRs) signaling pathways to support their survival and growth. The overlapping networks of EGFRs signaling pathways account for the failure of most ErbB-targeted therapies. The aim of this study was to enrich a pool of recombinant antibody fragments against common epitopes of ErbB1 and ErbB2 in order to simultaneous blockade of ErbBs signaling pathways. ErbB1 and ErbB2 were expressed stably in VERO cells. Selection of recombinant antibodies was performed on live cells expressing either of ErbB1 and ErbB2 receptors using subtractive phage display approach. The results of PCR and DNA fingerprinting in the last round of panning showed that most clones contained insert (80% and 85% for ErbB1 and ErbB2 respectively) with an identical restriction pattern. The selected clones showed positive reaction to both ErbB1 and ErbB2 receptors in phage-ELISA test. Furthermore, the resulting soluble antibody fragments recognized common epitopes of both immunoprecipitated ErbB1 and ErbB2 in western blot. Additionally, the antibodies directed against the dimerization domain of ErbB1 demonstrated a significant absorbance in EGF-stimulated VERO/ErbB1 cells than non-stimulated cells (1.91 and 1.09 respectively). Moreover, the results of dimerization inhibition test showed that these antibodies blocked ErbB1 and ErbB2 dimerization on the surface of ErbB1 and ErbB2 expressing VERO cells. Regarding the importance of pan-ErbB approach to cancer therapy, the antibodies developed here might provide novel therapeutics for simultaneous blockade of ErbBs signaling pathways.

Keywords: breast cancer, single-chain antibody, ErbB1, ErbB2, epitope

Procedia PDF Downloads 615

Authors: Zahrasadat Hosseini, Jie Yuan

Abstract:

Point-of-care (POC) diagnostic devices based on lab-on-a-chip (LOC) technology have the potential to revolutionize medical diagnostics. However, the development of an ideal microfluidic system based on LOC technology for diagnostics purposes requires overcoming several obstacles, such as improving sensitivity, selectivity, portability, cost-effectiveness, and prototyping methods. While numerous studies have introduced technologies and systems that advance these criteria, existing systems still have limitations. Electrochemical enzyme-linked immunosorbent assay (e-ELISA) in a LOC device offers numerous advantages, including enhanced sensitivity, decreased turnaround time, minimized sample and analyte consumption, reduced cost, disposability, and suitability for miniaturization, integration, and multiplexing. In this study, we present a novel design and fabrication method for a microfluidic diagnostic platform that integrates screen-printed electrochemical carbon/silver chloride electrodes on flexible printed circuit boards with flexible, multilayer, polydimethylsiloxane (PDMS) microfluidic networks to accurately manipulate and pre-immobilize analytes for performing electrochemical enzyme-linked immunosorbent assay (e-ELISA) for multiplexed quantification of blood serum biomarkers. We further demonstrate fast, cost-effective prototyping, as well as accurate and reliable detection performance of this device for quantification of interleukin-6-spiked samples through electrochemical analytics methods. We anticipate that our invention represents a significant step towards the development of user-friendly, portable, medical-grade, POC diagnostic devices.

Keywords: lab-on-a-chip, point-of-care diagnostics, electrochemical ELISA, biomarker quantification, fast prototyping

Procedia PDF Downloads 55

Authors: Zahrasadat Hosseini, Jie Yuan

Abstract:

Point-of-care (POC) diagnostic devices based on lab-on-a-chip (LOC) technology have the potential to revolutionize medical diagnostics. However, the development of an ideal microfluidic system based on LOC technology for diagnostics purposes requires overcoming several obstacles, such as improving sensitivity, selectivity, portability, cost-effectiveness, and prototyping methods. While numerous studies have introduced technologies and systems that advance these criteria, existing systems still have limitations. Electrochemical enzyme-linked immunosorbent assay (e-ELISA) in a LOC device offers numerous advantages, including enhanced sensitivity, decreased turnaround time, minimized sample and analyte consumption, reduced cost, disposability, and suitability for miniaturization, integration, and multiplexing. In this study, we present a novel design and fabrication method for a microfluidic diagnostic platform that integrates screen-printed electrochemical carbon/silver chloride electrodes on flexible printed circuit boards with flexible, multilayer, polydimethylsiloxane (PDMS) microfluidic networks to accurately manipulate and pre-immobilize analytes for performing electrochemical enzyme-linked immunosorbent assay (e-ELISA) for multiplexed quantification of blood serum biomarkers. We further demonstrate fast, cost-effective prototyping, as well as accurate and reliable detection performance of this device for quantification of interleukin-6-spiked samples through electrochemical analytics methods. We anticipate that our invention represents a significant step towards the development of user-friendly, portable, medical-grade POC diagnostic devices.

Keywords: lab-on-a-chip, point-of-care diagnostics, electrochemical ELISA, biomarker quantification, fast prototyping

Procedia PDF Downloads 59

Authors: Maryam Kheirollahpour, Mahmoud Danaee, Amir Faisal Merican, Asma Ahmad Shariff

Abstract:

Background: The presence of nonlinearity among the risk factors of eating behavior causes a bias in the prediction models. The accuracy of estimation of eating behaviors risk factors in the primary prevention of obesity has been established. Objective: The aim of this study was to explore the potential of a hybrid model of structural equation modeling (SEM) and Artificial Neural Networks (ANN) to predict eating behaviors. Methods: The Partial Least Square-SEM (PLS-SEM) and a hybrid model (SEM-Artificial Neural Networks (SEM-ANN)) were applied to evaluate the factors affecting eating behavior patterns among university students. 340 university students participated in this study. The PLS-SEM analysis was used to check the effect of emotional eating scale (EES), body shape concern (BSC), and body appreciation scale (BAS) on different categories of eating behavior patterns (EBP). Then, the hybrid model was conducted using multilayer perceptron (MLP) with feedforward network topology. Moreover, Levenberg-Marquardt, which is a supervised learning model, was applied as a learning method for MLP training. The Tangent/sigmoid function was used for the input layer while the linear function applied for the output layer. The coefficient of determination (R²) and mean square error (MSE) was calculated. Results: It was proved that the hybrid model was superior to PLS-SEM methods. Using hybrid model, the optimal network happened at MPLP 3-17-8, while the R² of the model was increased by 27%, while, the MSE was decreased by 9.6%. Moreover, it was found that which one of these factors have significantly affected on healthy and unhealthy eating behavior patterns. The p-value was reported to be less than 0.01 for most of the paths. Conclusion/Importance: Thus, a hybrid approach could be suggested as a significant methodological contribution from a statistical standpoint, and it can be implemented as software to be able to predict models with the highest accuracy.

Keywords: hybrid model, structural equation modeling, artificial neural networks, eating behavior patterns

Procedia PDF Downloads 121

Authors: K. Sridhar Reddy, M. Amaranatha Reddy, Nilanjan Mitra

Abstract:

Short paneled concrete pavement (SPCP) with shorter panel size can be an alternative to the conventional jointed plain concrete pavements (JPCP) at the same cost as the asphalt pavements with all the advantages of concrete pavement with reduced thickness, less chance of mid-slab cracking and or dowel bar locking so common in JPCP. Cast-in-situ short concrete panels (short slabs) laid on a strong foundation consisting of a dry lean concrete base (DLC), and cement treated subbase (CTSB) will reduce the thickness of the concrete slab to the order of 180 mm to 220 mm, whereas JPCP was with 280 mm for the same traffic. During the construction of SPCP test sections on two Indian National Highways (NH), it was observed that the joints remain uncracked after a year of traffic. The undoweled and uncracked joints load transfer variability and joint behavior are of interest with anticipation on its long-term performance of the SPCP. To investigate the effects of undoweled and uncracked joints on short slabs, the present study was conducted. A multilayer linear elastic analysis using 3D finite element package for different panel sizes with different thicknesses resting on different types of solid elastic foundation with and without temperature gradient was developed. Surface deflections were obtained from 3D FE model and validated with measured field deflections from falling weight deflectometer (FWD) test. Stress analysis indicates that flexural stresses in short slabs are decreased with a decrease in panel size and increase in thickness. Detailed evaluation of stress analysis with the effects of curling behavior, the stiffness of the base layer and a variable degree of load transfer, is underway.

Keywords: joint behavior, short slabs, uncracked joints, undoweled joints, 3D numerical simulation

Procedia PDF Downloads 155

Authors: Hong Li, Haiyang Yu, Shiqing Cheng, Nai Cao, Zhiliang Shi

Abstract:

Unconventional resources have gradually become the main direction for oil and gas exploration and development. However, the productivity of gas wells, the level of water production, and the seepage law in tight fractured gas reservoirs are very different. These are the reasons why production prediction is so difficult. Firstly, a three-dimensional multi-scale fracture and multiphase mathematical model based on an embedded discrete fracture model (EDFM) is established. And the material balance method is used to calculate the water body multiple according to the production performance characteristics of water-producing gas well. This will help construct a 'virtual water body'. Based on these, this paper presents a numerical simulation process that can adapt to different production modes of gas wells. The research results show that fractures have a double-sided effect. The positive side is that it can increase the initial production capacity, but the negative side is that it can connect to the water body, which will lead to the gas production drop and the water production rise both rapidly, showing a 'scissor-like' characteristic. It is worth noting that fractures with different angles have different abilities to connect with the water body. The higher the angle of gas well development, the earlier the water maybe break through. When the reservoir is a single layer, there may be a stable production period without water before the fractures connect with the water body. Once connected, a 'scissors shape' will appear. If the reservoir has multiple layers, the gas and water will produce at the same time. The above gas-water relationship can be matched with the gas well production date of the Xujiahe gas reservoir in the Sichuan Basin. This method is used to predict the productivity of a well with hydraulic fractures in this gas reservoir, and the prediction results are in agreement with on-site production data by more than 90%. It shows that this research idea has great potential in the productivity prediction of water-producing gas wells. Early prediction results are of great significance to guide the design of development plans.

Keywords: EDFM, multiphase, multilayer, water body

Procedia PDF Downloads 167

Authors: Arvan Prakash Ankitha, Madasamy Arockiasamy

Abstract:

The increasing demand for adopting pile foundations in bridgeshas pointed towardsthe need to constantly improve the existing analytical techniques for better understanding of the behavior of such foundation systems. This study presents a simplistic approach using the energy-based method to assess the displacement responses of piles subjected to general loading conditions: Axial Load, Lateral Load, and a Bending Moment. The governing differential equations and the boundary conditions for a bridge pile embedded in multi-layered soil strata subjected to the general loading conditions are obtained using the Hamilton’s principle employing variational principles and minimization of energies. The soil non-linearity has been incorporated through simple constitutive relationships that account for degradation of soil moduli with increasing strain values.A simple power law based on published literature is used where the soil is assumed to be nonlinear-elastic and perfectly plastic. A Tresca yield surface is assumed to develop the soil stiffness variation with different strain levels that defines the non-linearity of the soil strata. This numerical technique has been applied to a pile foundation in a two - layered soil strata for a pier supporting the bridge and solved using the software MATLAB R2019a. The analysis yields the bridge pile displacements at any depth along the length of the pile. The results of the analysis are in good agreement with the published field data and the three-dimensional finite element analysis results performed using the software ANSYS 2019R3. The methodology can be extended to study the response of the multi-strata soil supporting group piles underneath the bridge piers.

Keywords: pile foundations, deep foundations, multilayer soil strata, energy based method

Procedia PDF Downloads 108

Authors: Maad Kamal Al-Anni

Abstract:

This study is about an algorithmic dependence of Artificial Neural Network on Multilayer Perceptron (MPL) pertaining to the classification and clustering presentations for Mobile Adhoc Network vulnerabilities. Moreover, mobile ad hoc network (MANET) is ubiquitous intelligent internetworking devices in which it has the ability to detect their environment using an autonomous system of mobile nodes that are connected via wireless links. Security affairs are the most important subject in MANET due to the easy penetrative scenarios occurred in such an auto configuration network. One of the powerful techniques used for inspecting the network packets is Intrusion Detection System (IDS); in this article, we are going to show the effectiveness of artificial neural networks used as a machine learning along with stochastic approach (information gain) to classify the malicious behaviors in simulated network with respect to different IDS techniques. The monitoring agent is responsible for detection inference engine, the audit data is collected from collecting agent by simulating the node attack and contrasted outputs with normal behaviors of the framework, whenever. In the event that there is any deviation from the ordinary behaviors then the monitoring agent is considered this event as an attack , in this article we are going to demonstrate the  signature-based IDS approach in a MANET by implementing the back propagation algorithm over ensemble-based Traffic Table (TT), thus the signature of malicious behaviors or undesirable activities are often significantly prognosticated and efficiently figured out, by increasing the parametric set-up of Back propagation algorithm during the experimental results which empirically shown its effectiveness  for the ratio of detection index up to 98.6 percentage. Consequently it is proved in empirical results in this article, the performance matrices are also being included in this article with Xgraph screen show by different through puts like Packet Delivery Ratio (PDR), Through Put(TP), and Average Delay(AD).

Keywords: Intrusion Detection System (IDS), Mobile Adhoc Networks (MANET), Back Propagation Algorithm (BPA), Neural Networks (NN)

Procedia PDF Downloads 165

Authors: Norzaliza Md. Nor, Sh-Hussain Salleh, Mahyar Hamedi, Hadrina Hussain, Wahab Abdul Rahman

Abstract:

Motivational factor is mainly the students’ desire to involve in learning process. However, it also depends on the goal towards their involvement or non-involvement in academic activity. Even though, the students’ motivation might be in the same level, but the basis of their motivation may differ. In this study, it focuses on the intrinsic motivational factor which student enjoy learning or feeling of accomplishment the activity or study for its own sake. The intrinsic motivational factor of students in learning mathematics and science has found as difficult to be achieved because it depends on students’ interest. In the Program for International Student Assessment (PISA) for mathematics and science, Malaysia is ranked as third lowest. The main problem in Malaysian educational system, students tend to have extrinsic motivation which they have to score in exam in order to achieve a good result and enrolled as university students. The use of electroencephalogram (EEG) signals has found to be scarce especially to identify the students’ intrinsic motivational factor in learning science and mathematics. In this research study, we are identifying the correlation between precursor emotion and its dynamic emotion to verify the intrinsic motivational factor of students in learning mathematics and science. The 2-D Affective Space Model (ASM) was used in this research in order to identify the relationship of precursor emotion and its dynamic emotion based on the four basic emotions, happy, calm, fear and sad. These four basic emotions are required to be used as reference stimuli. Then, in order to capture the brain waves, EEG device was used, while Mel Frequency Cepstral Coefficient (MFCC) was adopted to be used for extracting the features before it will be feed to Multilayer Perceptron (MLP) to classify the valence and arousal axes for the ASM. The results show that the precursor emotion had an influence the dynamic emotions and it identifies that most students have no interest in mathematics and science according to the negative emotion (sad and fear) appear in the EEG signals. We hope that these results can help us further relate the behavior and intrinsic motivational factor of students towards learning of mathematics and science.

Keywords: EEG, MLP, MFCC, intrinsic motivational factor

Procedia PDF Downloads 341

Authors: Deepa Kundu, Prabhakar Sharma, Sayan Bhattacharya, Jianying Shang

Abstract:

The discharge of dye-containing effluents in the water bodies has raised concern due to the potential hazards related to their toxicity in the environment. There are various treatment technologies available for the removal of dyes from wastewaters. The use of biosorbent to remove dyes from wastewater is one of the effective and inexpensive techniques. In the study, the adsorption of phenothiazine dye methylene blue onto biosorbent prepared from Lantana camara L. has been studied in aqueous solutions. The batch adsorption experiments were conducted and the effects of various parameters such as pH (3-12), contact time, adsorbent dose (100-400 mg/L), initial dye concentration (5-20 mg/L), and temperature (303, 313 and 323 K) were investigated. The prepared leaf (BCL600) and shoot (BCS600) biochar of Lantana were characterized using FTIR, SEM, elemental analysis, and zeta potential (pH~7). A comparison between the adsorption potential of both the biosorbent was also evaluated. The results indicated that the amount of methylene blue dye (mg/g) adsorbed onto the surface of biochar was highly dependent on the pH of the dye solutions as it increased with an increase in pH from 3 to 12. It was observed that the dye treated with BCS600 and BCL600 attained an equilibrium within 60 and 100 minutes, respectively. The rate of the adsorption process was determined by performing the Lagergren pseudo-first-order and pseudo-second-order kinetics. It was found that dye treated with both BCS600 and BCL600 followed pseudo-second-order kinetics implying the multi-step nature of the adsorption process involving external adsorption and diffusion of dye molecules into the interior of the adsorbents. The data obtained from batch experiments were fitted well with Langmuir and Freundlich isotherms (R² > 0.98) to indicate the multilayer adsorption of dye over the biochar surfaces. The thermodynamic studies revealed that the adsorption process is favourable, spontaneous, and endothermic in nature. Based on the results, the inexpensive and easily available Lantana camara biomass can be used to remove methylene blue dye from wastewater. It can also help in managing the growth of the notorious weed in the environment.

Keywords: adsorption kinetics, biochar, Lantana camara, methylene blue dye, possible mechanism, thermodynamics

Procedia PDF Downloads 111

Authors: Maryam Farzaneh, Seyyedeh Nafiseh Hassani, Hossein Baharvand

Abstract:

Objective: Chicken gonadal tissue has a two population such primordial germ cells (PGCs) and stromal cells (somatic cells). PGCs and embryonic germ cells (EGCs) that is a pluripotent type of PGCs in long-term culture are suitable sources for the production of chicken pluripotent stem cell lines, transgenic birds, vaccine and recombinant protein production. In general, the effect of growth factors such bFGF and mouse LIF on derivation of PGCs in vitro are important and in this study we could see the unique effect of small molecules such PD032 and SB43 as a chemical, in comparison to growth factors. Materials and Methods: After incubation of fertilized chicken egg up to 6 days and isolation of primary gonadal tissues and culture of mixed cells like PGCs and stromal cells. PGCs proliferate in the present of fetal calf serum (FCS) and small molecules and in another group bFGF, that these factors are important for PGCs culture and derivation. Somatic cells produce a multilayer feeder under the PGCs in primary culture and PGCs make a small cluster under these cells. Results: In present of small molecules and high volume of FCS (15%), the present of EGCs as a pluripotent stem cells were clear four weeks, that they had a positive immune-staining and periodic acid-Schiff staining (PAS), but in present of growth factors like bFGF without any chemicals, the present of PGCs were clear but after 7 until 10 days, there were disappear. Conclusion: Until now we have seen many researches about derivation and maintenance of chicken PGCs, in the hope of understanding the mechanisms that occur during germline development and production of a therapeutic product by transgenic birds. There are still many unknowns in this area and this project will try to have efficient conditions for identification of suitable culture medium for long-term culture of PGCs in vitro without serum and feeder cells.

Keywords: chicken gonadal primordial germ cells, pluripotent stem cells, growth factors, small molecules, transgenic birds

Procedia PDF Downloads 409

Authors: Pomozova Kseniia, Gorlachev Gennadiy, Chernyaev Aleksandr, Golanov Andrey

Abstract:

In clinical practice, and especially in stereotactic radiosurgery planning, the significance of diffusion-weighted imaging (DWI) is growing. This makes the existence of software capable of quickly processing and reliably visualizing diffusion data, as well as equipped with tools for their analysis in terms of different tasks. We are developing the «MRDiffusionImaging» software on the standard C++ language. The subject part has been moved to separate class libraries and can be used on various platforms. The user interface is Windows WPF (Windows Presentation Foundation), which is a technology for managing Windows applications with access to all components of the .NET 5 or .NET Framework platform ecosystem. One of the important features is the use of a declarative markup language, XAML (eXtensible Application Markup Language), with which you can conveniently create, initialize and set properties of objects with hierarchical relationships. Graphics are generated using the DirectX environment. The MRDiffusionImaging software package has been implemented for processing diffusion magnetic resonance imaging (dMRI), which allows loading and viewing images sorted by series. An algorithm for "masking" dMRI series based on T2-weighted images was developed using a deformable surface model to exclude tissues that are not related to the area of interest from the analysis. An algorithm of distortion correction using deformable image registration based on autocorrelation of local structure has been developed. Maximum voxel dimension was 1,03 ± 0,12 mm. In an elementary brain's volume, the diffusion tensor is geometrically interpreted using an ellipsoid, which is an isosurface of the probability density of a molecule's diffusion. For the first time, non-parametric intensity distributions, neighborhood correlations, and inhomogeneities are combined in one segmentation of white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) algorithm. A tool for calculating the coefficient of average diffusion and fractional anisotropy has been created, on the basis of which it is possible to build quantitative maps for solving various clinical problems. Functionality has been created that allows clustering and segmenting images to individualize the clinical volume of radiation treatment and further assess the response (Median Dice Score = 0.963 ± 0,137). White matter tracts of the brain were visualized using two algorithms: deterministic (fiber assignment by continuous tracking) and probabilistic using the Hough transform. The proposed algorithms test candidate curves in the voxel, assigning to each one a score computed from the diffusion data, and then selects the curves with the highest scores as the potential anatomical connections. White matter fibers were visualized using a Hough transform tractography algorithm. In the context of functional radiosurgery, it is possible to reduce the irradiation volume of the internal capsule receiving 12 Gy from 0,402 cc to 0,254 cc. The «MRDiffusionImaging» will improve the efficiency and accuracy of diagnostics and stereotactic radiotherapy of intracranial pathology. We develop software with integrated, intuitive support for processing, analysis, and inclusion in the process of radiotherapy planning and evaluating its results.

Keywords: diffusion-weighted imaging, medical imaging, stereotactic radiosurgery, tractography

Procedia PDF Downloads 52

Authors: Arjun Kumar Rath, Titus Dhanasingh

Abstract:

Embedded product development requires software to test hardware functionality during development and finding issues during manufacturing in larger quantities. As the components are getting integrated, the devices are tested for their full functionality using advanced software tools. Benchmarking tools are used to measure and compare the performance of product features. At present, these tests are based on a variety of methods involving varying hardware and software platforms. Typically, these tests are custom built for every product and remain unusable for other variants. A majority of the tests goes undocumented, not updated, unusable when the product is released. To bridge this gap, a solution accelerator in the form of a framework can address these issues for running all these tests from one place, using an off-the-shelf tests library in a continuous integration environment. There are many open-source test frameworks or tools (fuego. LAVA, AutoTest, KernelCI, etc.) designed for testing embedded system devices, with each one having several unique good features, but one single tool and framework may not satisfy all of the testing needs for embedded systems, thus an extensible framework with the multitude of tools. Embedded product testing includes board bring-up testing, test during manufacturing, firmware testing, application testing, and assembly testing. Traditional test methods include developing test libraries and support components for every new hardware platform that belongs to the same domain with identical hardware architecture. This approach will have drawbacks like non-reusability where platform-specific libraries cannot be reused, need to maintain source infrastructure for individual hardware platforms, and most importantly, time is taken to re-develop test cases for new hardware platforms. These limitations create challenges like environment set up for testing, scalability, and maintenance. A desirable strategy is certainly one that is focused on maximizing reusability, continuous integration, and leveraging artifacts across the complete development cycle during phases of testing and across family of products. To get over the stated challenges with the conventional method and offers benefits of embedded testing, an embedded test framework (ETF), a solution accelerator, is designed, which can be deployed in embedded system-related products with minimal customizations and maintenance to accelerate the hardware testing. Embedded test framework supports testing different hardwares including microprocessor and microcontroller. It offers benefits such as (1) Time-to-Market: Accelerates board brings up time with prepacked test suites supporting all necessary peripherals which can speed up the design and development stage(board bring up, manufacturing and device driver) (2) Reusability-framework components isolated from the platform-specific HW initialization and configuration makes the adaptability of test cases across various platform quick and simple (3) Effective build and test infrastructure with multiple test interface options and preintegrated with FUEGO framework (4) Continuos integration - pre-integrated with Jenkins which enabled continuous testing and automated software update feature. Applying the embedded test framework accelerator throughout the design and development phase enables to development of the well-tested systems before functional verification and improves time to market to a large extent.

Keywords: board diagnostics software, embedded system, hardware testing, test frameworks

Procedia PDF Downloads 118

Authors: Sabina-Adriana Floria, Marius Gavrilescu, Florin Leon, Silvia Curteanu, Costel Anton

Abstract:

Neuroevolution is a subfield of artificial intelligence used to solve various problems in different application areas. Specifically, neuroevolution is a technique that applies biologically inspired methods to generate neural network architectures and optimize their parameters automatically. In this paper, we use different biologically inspired optimization algorithms in an ensemble strategy with the aim of training multilayer perceptron neural networks, resulting in regression models used to simulate the industrial chemical process of obtaining bricks from silicone-based materials. Installations in the raw ceramics industry, i.e., bricks, are characterized by significant energy consumption and large quantities of emissions. In addition, the initial conditions that were taken into account during the design and commissioning of the installation can change over time, which leads to the need to add new mixes to adjust the operating conditions for the desired purpose, e.g., material properties and energy saving. The present approach follows the study by simulation of a process of obtaining bricks from silicone-based materials, i.e., the modeling and optimization of the process. Optimization aims to determine the working conditions that minimize the emissions represented by nitrogen monoxide. We first use a search procedure to find the best values for the parameters of various biologically inspired optimization algorithms. Then, we propose an adaptive ensemble strategy that uses only a subset of the best algorithms identified in the search stage. The adaptive ensemble strategy combines the results of selected algorithms and automatically assigns more processing capacity to the more efficient algorithms. Their efficiency may also vary at different stages of the optimization process. In a given ensemble iteration, the most efficient algorithms aim to maintain good convergence, while the less efficient algorithms can improve population diversity. The proposed adaptive ensemble strategy outperforms the individual optimizers and the non-adaptive ensemble strategy in convergence speed, and the obtained results provide lower error values.

Keywords: optimization, biologically inspired algorithm, neuroevolution, ensembles, bricks, emission minimization

Procedia PDF Downloads 74