Search results for: neural tube defects

Authors: Nuri Caglayan, H. Kursat Celik

Abstract:

There are many factors that influence the health and productivity of the animals in livestock production fields, including temperature, humidity, carbon dioxide (CO2), ammonia (NH3), hydrogen sulfide (H2S), physical activity and particulate matter. High NH3 concentrations reduce feed consumption and cause daily weight gain. At high concentrations, H2S causes respiratory problems and CO2 displace oxygen, which can cause suffocation or asphyxiation. Good air quality in livestock facilities can have an impact on the health and well-being of animals and humans. Air quality assessment basically depends on strictly given limits without taking into account specific local conditions between harmful gases and other meteorological factors. The stated limitations may be eliminated. using controlling systems based on neural networks and fuzzy logic. This paper describes a fuzzy logic based ventilation algorithm, which can calculate different fan speeds under pre-defined boundary conditions, for removing harmful gases from the production environment. In the paper, a fuzzy logic model has been developed based on a Mamedani’s fuzzy method. The model has been built on MATLAB software. As the result, optimum fan speeds under pre-defined boundary conditions have been presented.

Keywords: air quality, fuzzy logic model, livestock housing, fan speed

Procedia PDF Downloads 359

Authors: Chanya Inprasit, Yi-Wen Lin

Abstract:

Motion sickness (MS) is an acute disorder that occurs in healthy persons without considering gender, age or ethnicity worldwide. All signs and symptoms of MS are the results of confliction and mismatch among neural signal inputs. It is known that no singular remedy works for everybody, and electroacupuncture (EA) is one of the popular alternative therapies used for MS. Our study utilized a mouse model in order to exclude any psychological factors of MS and EA. Mice lack an emetic reflex. Therefore pica behavior, which is a normal consumption of non-nutritive substances, was found to measure the response of MS in mice. In the laboratory, Kaolin was used as a non-nutrient food substance instead of natural substances lacking nutritional value such as wood, cloth, charcoal, soil or grass. It was hypothesized that EA treatment could reduce the symptoms of MS through the TRPV1 pathways. The results of pica behavior showed a significantly increased intake of kaolin in the MS group throughout the experiment period. Moreover, the Kaolin intake of the EA group decreased to the average baseline of the control group. There was no recorded difference in the food and water intake of each group. The results indicated an increase of the TRPV1, pERK, pJNK and pmTOR protein levels in the thalamus after MS stimulation, and a significant decrease in the EA group compared with that of the control group. These findings suggest that TRPV1 pathways are associated in MS mechanisms and can be reduced by EA.

Keywords: electroacupuncture, motion sickness, Thalamus, TRPV1

Procedia PDF Downloads 241

Authors: Jay L. Fu

Abstract:

Patients with Alzheimer's disease progressively lose their memory and thinking skills and, eventually, the ability to carry out simple daily tasks. The disease is irreversible, but early detection and treatment can slow down the disease progression. In this research, publicly available MRI data and demographic data from 373 MRI imaging sessions were utilized to build models to predict dementia. Various machine learning models, including logistic regression, k-nearest neighbor, support vector machine, random forest, and neural network, were developed. Data were divided into training and testing sets, where training sets were used to build the predictive model, and testing sets were used to assess the accuracy of prediction. Key risk factors were identified, and various models were compared to come forward with the best prediction model. Among these models, the random forest model appeared to be the best model with an accuracy of 90.34%. MMSE, nWBV, and gender were the three most important contributing factors to the detection of Alzheimer’s. Among all the models used, the percent in which at least 4 of the 5 models shared the same diagnosis for a testing input was 90.42%. These machine learning models allow early detection of Alzheimer’s with good accuracy, which ultimately leads to early treatment of these patients.

Keywords: Alzheimer's disease, clinical diagnosis, magnetic resonance imaging, machine learning prediction

Procedia PDF Downloads 132

Authors: Hebah M. Musalem, Jeylan El-Mansoury, Lin M. Tuleimat, Selwa Alhazza, Abdul-Aziz A. Al Zoba

Abstract:

Background: Amblyopia is a condition that affects the visual system triggering a decrease in visual acuity without a known underlying pathology. It is due to abnormal vision development in childhood or infancy. Most importantly, vision loss is preventable or reversible with the right kind of intervention in most of the cases. Strabismus, sensory defects, and anisometropia are all well-known causes of amblyopia. However, ocular misalignment in Strabismus is considered the most common form of amblyopia worldwide. The risk of developing amblyopia increases in premature children, developmentally delayed or children who had brain lesions affecting the visual pathway. The prevalence of amblyopia varies between 2 to 5 % in the world according to the literature. Objective: To determine the different causes of Amblyopia in pediatric patients seen in ophthalmology clinic of a tertiary care center, i.e. King Faisal Specialist Hospital and Research Center (KFSH&RC). Methods: This is a hospital based, random retrospective, based on reviewing patient’s files in the Ophthalmology Department of KFSH&RC in Riyadh city, Kingdom of Saudi Arabia. Inclusion criteria: amblyopic pediatric patients who attended the clinic from 2015 to 2016, who are between 6 months and 18 years old. Exclusion Criteria: patients above 18 years of age and any patient who is uncooperative to obtain an accurate vision or a proper refraction. Detailed ocular and medical history are recorded. The examination protocol includes a full ocular exam, full cycloplegic refraction, visual acuity measurement, ocular motility and strabismus evaluation. All data were organized in tables and graphs and analyzed by statistician. Results: Our preliminary results will be discussed on spot by our corresponding author. Conclusions: We focused on this study on utilizing various examination techniques which enhanced our results and highlighted a distinguished correlation between amblyopia and its’ causes. This paper recommendation emphasizes on critical testing protocols to be followed among amblyopic patient, especially in tertiary care centers.

Keywords: amblyopia, amblyopia causes, amblyopia diagnostic criterion, amblyopia prevalence, Saudi Arabia

Procedia PDF Downloads 145

Authors: Soofiyan Atar, Adil Shaikh, Sahil Rajpurkar, Pragnesh Bhalala, Aniket Desai, Irfan Siddavatam

Abstract:

Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.

Keywords: model-based reinforcement learning, gait stability, supervised learning, pneumatic quadruped

Procedia PDF Downloads 301

Authors: Shakti S. Acharya, V. R. R. Medicherla, Rajeev Rawat, Komal Bapna, Deepnarayan Biswas, Khadija Ali, K. Maiti

Abstract:

The discovery of invar effect in 35% Ni concentration Fe1-xNix alloy has stimulated enormous experimental and theoretical research. Elemental Fe and low Ni concentration Fe1-xNix alloys which possess body centred cubic (bcc) crystal structure at ambient temperature and pressure transform to hexagonally close packed (hcp) phase at around 13 GPa. Magnetic order was found to be absent at 11K for Fe92Ni8 alloy when subjected to a high pressure of 26 GPa. The density functional theoretical calculations predicted substantial hyperfine magnetic fields, but were not observed in Mossbaur spectroscopy. The bulk modulus of fcc Fe1-xNix alloys with Ni concentration more than 35%, is found to be independent of pressure. The magnetic moment of Fe is also found be almost same in these alloys from 4 to 10 GPa pressure. Fe1-xNix alloys exhibit a complex microstructure which is formed by a series of complex phase transformations like martensitic transformation, spinodal decomposition, ordering, mono-tectoid reaction, eutectoid reaction at temperatures below 400°C. Despite the existence of several theoretical models the field is still in its infancy lacking full knowledge about the anomalous properties exhibited by these alloys. Fe1-xNix alloys have been prepared by arc melting the high purity constituent metals in argon ambient. These alloys have annealed at around 3000C in vacuum sealed quartz tube for two days to make the samples homogeneous. These alloys have been structurally characterized by x-ray diffraction and were found to exhibit a transition from bcc to fcc for x > 0.3. Ni 2p core levels of the alloys have been measured using high resolution (0.45 eV) x-ray photoelectron spectroscopy. Ni 2p core level shifts to lower binding energy with respect to that of pure Ni metal giving rise to negative core level shifts (CLSs). Measured CLSs exhibit a linear dependence in fcc region (x > 0.3) and were found to deviate slightly in bcc region (x < 0.3). ESCA potential model fails correlate CLSs with site potentials or charges in metallic alloys. CLSs in these alloys occur mainly due to shift in valence bands with composition due to intra atomic charge redistribution.

Keywords: arc melting, core level shift, ESCA potential model, valence band

Procedia PDF Downloads 368

Authors: Olarinde Olaniran, Oluyomi A. Sowemimo

Abstract:

Toxoplasmosis is frequently misdiagnosed or underdiagnosed, and it is the third most common cause of hospitalization due to food-borne infection. Intra-uterine infection with Toxoplasma gondii due to active parasitaemia during pregnancy can cause severe and often fatal cerebral damage, abortion, and stillbirth of a fetus. The aim of the study was to investigate the prevalence of T. gondii infection in women of childbearing age in selected communities of Osun State with a view to determining the risk factors which predispose to the T. gondii infection. Five (5) ml of blood was collected by venopuncture into a plain blood collection tube by a medical laboratory scientist. Serum samples were separated by centrifuging the blood samples at 3000 rpm for 5 mins. The sera were collected with Eppendorf tubes and stored at -20°C analysis for the presence of IgG and IgM antibodies against T. gondii by commercially available enzyme-linked immunosorbent assay (ELISA) kit (Demeditec Diagnostics GmbH, Germany) conducted according to the manufacturer’s instructions. The optical densities of wells were measured by a photometer at a wavelength of 450 nm. Data collected were analysed using appropriate computer software. The overall seroprevalence of T. gondii among the women of child-bearing age in selected seven communities in Osun state was 76.3%. Out of 76.3% positive for Toxoplasma gondii infection, 70.0% were positive for anti- T. gondii IgG, and 32.3% were positive for IgM, and 26.7% for both IgG and IgM. The prevalence of T. gondii was lowest (58.9%) among women from Ile Ife, a peri-urban community, and highest (100%) in women residing in Alajue, a rural community. The prevalence of infection was significantly higher (P= 0.000) among Islamic women (87.5%) than in Christian women (70.8%). The highest prevalence (86.3%) was recorded in women with primary education, while the lowest (61.2%) was recorded in women with tertiary education (p =0.016). The highest prevalence (79.7%) was recorded in women that reside in rural areas, and the lowest (70.1%) was recorded in women that reside in peri-urban area (p=0.025). The prevalence of T. gondii infection was highest (81.4%) in women with one miscarriage, while the prevalence was lowest in women with no miscarriages (75.9%). The age of the women (p=0.042), Islamic religion (p=0.001), the residence of the women (p=0.001), and water source were all positively associated with T. gondii infection. The study concluded that there was a high seroprevalence of T. gondii recorded among women of child-bearing age in the study area. Hence, there is a need for health education and create awareness of the disease and its transmission to women of reproductive age group in general and pregnant women in particular to reduce the risk of T. gondii in pregnant women.

Keywords: seroepidemiology, Toxoplasma gondii, women, child-bearing, age, communities, Ile -Ife, Nigeria

Procedia PDF Downloads 166

Authors: Bandar Alahmadi, Lethia Jackson

Abstract:

Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 327

Authors: Hamidreza Ghazvinian, Khosro Ghazvinian, Touba Khodaiean

Abstract:

The importance of evaporation estimation in water resources and agricultural studies is undeniable. Pan evaporation are used as an indicator to determine the evaporation of lakes and reservoirs around the world due to the ease of interpreting its data. In this research, intelligent models were investigated in estimating pan evaporation on a daily basis. Shahroud and Mayamey were considered as the studied cities. These two cities are located in Semnan province in Iran. The mentioned cities have dry weather conditions that are susceptible to high evaporation potential. Meteorological data of 11 years of synoptic stations of Shahrood and Mayamey cities were used. The intelligent models used in this study are Artificial Neural Network (ANN), Least Squares Support Vector Machine (LSSVM), and M5 tree models. Meteorological parameters of minimum and maximum air temperature (Tmax, Tmin), wind speed (WS), sunshine hours (SH), air pressure (PA), relative humidity (RH) as selected input data and evaporation data from pan (EP) to The output data was considered. 70% of data is used at the education level, and 30 % of the data is used at the test level. Models used with explanation coefficient evaluation (R2) Root of Mean Squares Error (RMSE) and Mean Absolute Error (MAE). The results for the two Shahroud and Mayamey stations showed that the above three models' operations are rather appropriate.

Keywords: pan evaporation, intelligent methods, shahroud, mayamey

Procedia PDF Downloads 64

Authors: Melodi Mbuyi Mata, Blessing Olamide Taiwo, Afolabi Ayodele David

Abstract:

The purpose of this research is to create empirical models for assessing the profitability of granite aggregate production in Akure, Ondo state aggregate quarries. In addition, an artificial neural network (ANN) model and multivariate predicting models for granite profitability were developed in the study. A formal survey questionnaire was used to collect data for the study. The data extracted from the case study mine for this study includes granite marketing operations, royalty, production costs, and mine production information. The following methods were used to achieve the goal of this study: descriptive statistics, MATLAB 2017, and SPSS16.0 software in analyzing and modeling the data collected from granite traders in the study areas. The ANN and Multi Variant Regression models' prediction accuracy was compared using a coefficient of determination (R²), Root mean square error (RMSE), and mean square error (MSE). Due to the high prediction error, the model evaluation indices revealed that the ANN model was suitable for predicting generated profit in a typical quarry. More quarries in Nigeria's southwest region and other geopolitical zones should be considered to improve ANN prediction accuracy.

Keywords: national development, granite, profitability assessment, ANN models

Procedia PDF Downloads 84

Authors: Norica Godja, Andreas Schindel, Luka Payrits, Zsolt Pasztor, Bálint Hegedüs, Petr Homola, Jan Horňas, Jiří Běhal, Roman Ruzek, Martin Holzleitner, Sascha Senck

Abstract:

In order to reduce fuel consumption and CO₂ emissions in the aviation sector, innovative solutions are being sought to reduce the weight of aircraft, including additive manufacturing (AM). Of particular importance are the excellent mechanical properties that are required for aircraft structures. Ti6Al4V alloys, with their high mechanical properties in relation to weight, can reduce the weight of aircraft structures compared to structures made of steel and aluminium. Currently, conventional processes such as casting and CNC machining are used to obtain the desired structures, resulting in high raw material removal, which in turn leads to higher costs and impacts the environment. Additive manufacturing (AM) offers advantages in terms of weight, lead time, design, and functionality and enables the realisation of alternative geometric shapes with high mechanical properties. However, there are currently technological shortcomings that have led to AM not being approved for structural components with high safety requirements. An assessment of damage tolerance for AM parts is required, and quality control needs to be improved. Pores and other defects cannot be completely avoided at present, but they should be kept to a minimum during manufacture. The mechanical properties of the manufactured parts can be further improved by various treatments. The influence of different treatment methods (heat treatment, CNC milling, electropolishing, chemical polishing) and operating parameters were investigated by scanning electron microscopy with energy dispersive X-ray spectroscopy (SEM/EDX), X-ray diffraction (XRD), electron backscatter diffraction (EBSD) and measurements with a focused ion beam (FIB), taking into account surface roughness, possible anomalies in the chemical composition of the surface and possible cracks. The results of the characterisation of the constructed and treated samples are discussed and presented in this paper. These results were generated within the framework of the 3TANIUM project, which is financed by EU with the contract number 101007830.

Keywords: Ti6Al4V alloys, laser powder bed fusion, damage tolerance, heat treatment, electropolishing, potential cracking

Procedia PDF Downloads 69

Authors: Seyong Oh, Jin-Hong Park

Abstract:

Recently, neuromorphic computing based on brain-inspired artificial neural networks (ANNs) has attracted huge amount of research interests due to the technological abilities to facilitate massively parallel, low-energy consuming, and event-driven computing. In particular, research on artificial synapse that imitate biological synapses responsible for human information processing and memory is in the spotlight. Here, we demonstrate a photosynaptic device, wherein a synaptic weight is governed by a mixed spike consisting of voltage and light spikes. Compared to the device operated only by the voltage spike, ∆G in the proposed photosynaptic device significantly increased from -2.32nS to 5.95nS with no degradation of nonlinearity (NL) (potentiation/depression values were changed from 4.24/8 to 5/8). Furthermore, the Modified National Institute of Standards and Technology (MNIST) digit pattern recognition rates improved from 36% and 49% to 50% and 62% in ANNs consisting of the synaptic devices with 20 and 100 weight states, respectively. We expect that the photosynaptic device technology processed by optoelectronic spike will play an important role in implementing the neuromorphic computing systems in the future.

Keywords: optoelectronic synapse, IGZO (Indium-Gallium-Zinc Oxide) photosynaptic device, optoelectronic spiking process, neuromorphic computing

Procedia PDF Downloads 160

Authors: Dalin Si, Azizan Aziz, Bertrand Lasternas

Abstract:

To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.

Keywords: building energy prediction, data mining, demand response, electricity market

Procedia PDF Downloads 307

Authors: Miho Yamashita

Abstract:

In recent years, there have been attempts to introduce Machine Translation (MT) into foreign language teaching, especially in writing instructions. This is because the performance of neural machine translation has improved dramatically since 2016, and some university instructors started to introduce MT translations to their students as a "good model" to learn from. However, MT is still not perfect, and there are many incorrect translations. In order to translate the intended text into a foreign language, it is necessary to edit the original manuscript written in the native language (pre-edit) and revise the translated foreign language text (post-edit). The latter is considered especially difficult for users without a high proficiency level of foreign language. Therefore, the author allowed her students to use MT in her writing class in one of the private universities in Japan and investigated 1) how groups of students with different English proficiency levels revised MT translations when translating Japanese manuscripts into English and 2) whether the post-edit process differed when the students revised alone or in pairs. The results showed that in 1), certain non-post-edited grammatical errors were found regardless of their proficiency levels, indicating the need for teacher intervention, and in 2), more appropriate corrections were found in pairs, and their frequent use of a dictionary was also observed. In this presentation, the author will discuss how MT writing instruction can be integrated effectively in an aim to achieve multimodal foreign language education.

Keywords: machine translation, writing instruction, pre-edit, post-edit

Procedia PDF Downloads 50

Authors: Lea Lachaud, Aida Raoult, Marion Trousselard, Francois B. Vialatte

Abstract:

This paper addresses mindfulness from a psychological and neuroscientific perspective, by studying how it modulates attention. Being mindful defines a state characterized by 1-an attention directed to the subjective experience of present moment, 2-an unconditional acceptance of this experience, and 3-the rejection of systematic rationalization in favor of plain awareness. The aim of this study is to investigate whether perceptual salience filters are lowered in a ‘mindful’ condition by exploring the role of being mindful in focused visual attention. Over the past decade, mindfulness therapies have seen a surge in popularity. While the outcomes of these therapies have been widely discussed, the mechanisms whereby meditation affects the brain remain mostly unknown. To explore the role of mindfulness in focused visual attention, we conducted a change blindness experiment on 24 subjects, 12 of them being mindful according to the Freiburg Mindfulness Inventory (FMI) scale. Our results suggest that mindful subjects are less affected by change blindness than non-mindful subjects. Furthermore, EEG measurements performed during the experiments may expose neural correlates specific to the mindful state on P300 evoked potentials. Finally, the analysis of both amplitude and latency caused by the perception of a change over 864 recordings may reveal biomarkers that are typical of this state. The paper concludes by discussing the implications of these results for further research.

Keywords: EEG, change blindness, mindfulness, p300, perception, visual attention

Procedia PDF Downloads 243

Authors: Lan Zhang, Cailing Zhang

Abstract:

In recent years, many face anti-spoofing algorithms have high detection accuracy when detecting 2D face anti-spoofing or 3D mask face anti-spoofing alone in the field of face anti-spoofing, but their detection performance is greatly reduced in multidimensional and cross-datasets tests. The rPPG method used for face anti-spoofing uses the unique vital information of real face to judge real faces and face anti-spoofing, so rPPG method has strong stability compared with other methods, but its detection rate of 2D face anti-spoofing needs to be improved. Therefore, in this paper, we improve an rPPG(Remote Photoplethysmography) method(MrPPG) for face anti-spoofing which through color space fusion, using the correlation of pulse signals between real face regions and background regions, and introducing the cyclic neural network (LSTM) method to improve accuracy in 2D face anti-spoofing. Meanwhile, the MrPPG also has high accuracy and good stability in face anti-spoofing of multi-dimensional and cross-data datasets. The improved method was validated on Replay-Attack, CASIA-FASD, Siw and HKBU_MARs_V2 datasets, the experimental results show that the performance and stability of the improved algorithm proposed in this paper is superior to many advanced algorithms.

Keywords: face anti-spoofing, face presentation attack detection, remote photoplethysmography, MrPPG

Procedia PDF Downloads 164

Authors: Sheena Christabel Pravin, M. Palanivelan

Abstract:

Speech disfluencies are common in spontaneous speech. The primary purpose of this study was to distinguish linguistic disfluencies from stuttering disfluencies in bilingual Tamil–English (TE) speaking children. The secondary purpose was to determine whether their disfluencies are mediated by native language dominance and/or on an early onset of developmental stuttering at childhood. A detailed study was carried out to identify the prosodic and acoustic features that uniquely represent the disfluent regions of speech. This paper focuses on statistical modeling of repetitions, prolongations, pauses and interjections in the speech corpus encompassing bilingual spontaneous utterances from school going children – English and Tamil. Two classifiers including Hidden Markov Models (HMM) and the Multilayer Perceptron (MLP), which is a class of feed-forward artificial neural network, were compared in the classification of disfluencies. The results of the classifiers document the patterns of disfluency in spontaneous speech samples of school-aged children to distinguish between Children Who Stutter (CWS) and Children with Language Impairment CLI). The ability of the models in classifying the disfluencies was measured in terms of F-measure, Recall, and Precision.

Keywords: bi-lingual, children who stutter, children with language impairment, hidden markov models, multi-layer perceptron, linguistic disfluencies, stuttering disfluencies

Procedia PDF Downloads 204

Authors: Bing Li, Zhi Li, Yilong Yang

Abstract:

Web classification can promote the quality of service discovery and management in the service repository. It is widely used to locate developers desired services. Although traditional classification methods based on supervised learning models can achieve classification tasks, developers need to manually mark web services, and the quality of these tags may not be enough to establish an accurate classifier for service classification. With the doubling of the number of web services, the manual tagging method has become unrealistic. In recent years, the attention mechanism has made remarkable progress in the field of deep learning, and its huge potential has been fully demonstrated in various fields. This paper designs a multi-head attention graph convolutional network (MHAGCN) service classification method, which can assign different weights to the neighborhood nodes without complicated matrix operations or relying on understanding the entire graph structure. The framework combines the advantages of the attention mechanism and graph convolutional neural network. It can classify web services through automatic feature extraction. The comprehensive experimental results on a real dataset not only show the superior performance of the proposed model over the existing models but also demonstrate its potentially good interpretability for graph analysis.

Keywords: attention mechanism, graph convolutional network, interpretability, service classification, service discovery

Procedia PDF Downloads 127

Authors: Faizul Azly Abd Dzubir, Muhammad F. Othman

Abstract:

Conventional structural health monitoring approach for mechanical equipment uses inspection data from Non-Destructive Testing (NDT) during plant shut down window and fitness for service evaluation to estimate the integrity of the equipment that is prone to crack damage. Yet, this forecast is fraught with uncertainty because it is often based on assumptions of future operational parameters, and the prediction is not continuous or online. Advanced Diagnostic and Prognostic Technology (ADaPT) uses Acoustic Emission (AE) technology and a stochastic prognostic model to provide real-time monitoring and prediction of mechanical defects or cracks. The forecast can help the plant authority handle their cracked equipment before it ruptures, causing an unscheduled shutdown of the facility. The ADaPT employs process historical data trending, finite element analysis, fitness for service, and probabilistic statistical analysis to develop a prediction model for crack initiation and growth due to mechanical damage. The prediction model is combined with live equipment operating data for real-time prediction of the remaining life span owing to fracture. ADaPT was devised at a hot combined feed exchanger (HCFE) that had suffered creep crack damage. The ADaPT tool predicts the initiation of a crack at the top weldment area by April 2019. During the shutdown window in April 2019, a crack was discovered and repaired. Furthermore, ADaPT successfully advised the plant owner to run at full capacity and improve output by up to 7% by April 2019. ADaPT was also used on a coke drum that had extensive fatigue cracking. The initial cracks are declared safe with ADaPT, with remaining crack lifetimes extended another five (5) months, just in time for another planned facility downtime to execute repair. The prediction model, when combined with plant information data, allows plant operators to continuously monitor crack propagation caused by mechanical damage for improved maintenance planning and to avoid costly shutdowns to repair immediately.

Keywords: mechanical damage, cracks, continuous monitoring tool, remaining life, acoustic emission, prognostic model

Procedia PDF Downloads 65

Authors: Jun Wang, Ge Zhang

Abstract:

Machine learning has been used in many areas today. It thrives at reviewing large volumes of data and identifying patterns and trends that might not be apparent to a human. Given the huge potential benefit and the amount of data available in the financial market, it is not surprising to see machine learning applied to various financial products. While future prices of financial securities are extremely difficult to forecast, we study them from a different angle. Instead of trying to forecast future prices, we apply machine learning algorithms to predict the direction of future price movement, in particular, whether a sector Exchange Traded Fund (ETF) would outperform or underperform the market in the next week or in the next month. We apply several machine learning algorithms for this prediction. The algorithms are Linear Discriminant Analysis (LDA), k-Nearest Neighbors (KNN), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Neural Networks (NN). We show that these machine learning algorithms, most notably GNB and NN, have some predictive power in forecasting out-performance and under-performance out of sample. We also try to explore whether it is possible to utilize the predictions from these algorithms to outperform the buy-and-hold strategy of the S&P 500 index. The trading strategy to explore out-performance predictions does not perform very well, but the trading strategy to explore under-performance predictions can earn higher returns than simply holding the S&P 500 index out of sample.

Keywords: machine learning, ETF prediction, dynamic trading, asset allocation

Procedia PDF Downloads 77

Authors: Xiang Yu, Chuntao Feng, Lu Yang, Meiyang Song, Wenhao Zhou

Abstract:

The existing two-dimensional micro-Doppler features extraction ignores the correlation information between the spatial and temporal dimension features. For the range-Doppler map, the time dimension is introduced, and a frequency modulation continuous wave (FMCW) radar human fall detection algorithm based on time-varying range-Doppler features is proposed. Firstly, the range-Doppler sequence maps are generated from the echo signals of the continuous motion of the human body collected by the radar. Then the three-dimensional data cube composed of multiple frames of range-Doppler maps is input into the three-dimensional Convolutional Neural Network (3D CNN). The spatial and temporal features of time-varying range-Doppler are extracted by the convolution layer and pool layer at the same time. Finally, the extracted spatial and temporal features are input into the fully connected layer for classification. The experimental results show that the proposed fall detection algorithm has a detection accuracy of 95.66%.

Keywords: FMCW radar, fall detection, 3D CNN, time-varying range-doppler features

Procedia PDF Downloads 106

Authors: Magdalena Smoktunowicz, Renata Wawrzyniak, Malgorzata Waleron, Krzysztof Waleron

Abstract:

Pectobacterium spp. were previously classified into the Erwinia genus founded in 1917 to unite at that time all Gram-negative, fermentative, nonsporulating and peritrichous flagellated plant pathogenic bacteria. After work of Waldee (1945), on Approved Lists of Bacterial Names and bacteriology manuals in 1980, they were described either under the species named Erwinia or Pectobacterium. The Pectobacterium genus was formally described in 1998 of 265 Pectobacterium strains. Currently, there are 21 species of Pectobacterium bacteria, including Pectobacterium betavasculorum since 2003, which caused soft rot on sugar beet tubers. Based on the biochemical experiments carried out for this, it is known that these bacteria are gram-negative, catalase-positive, oxidase-negative, facultatively anaerobic, using gelatin and causing symptoms of soft rot on potato and sugar beet tubers. The mere fact of growing on sugar beet may indicate a metabolism characteristic only for this species. Metabolomics, broadly defined as the biology of the metabolic systems, which allows to make comprehensive measurements of metabolites. Metabolomics, in combination with genomics, are complementary tools for the identification of metabolites and their reactions, and thus for the reconstruction of metabolic networks. The aim of this study was to apply the GC-MS-based untargeted metabolomics to study the metabolism of P. betavasculorum in different growing conditions. The metabolomic profiles of biomass and biomass media were determined. For sample preparation the following protocol was used: extraction with 900 µl of methanol: chloroform: water mixture (10: 3: 1, v: v) were added to 900 µl of biomass from the bottom of the tube and up to 900 µl of nutrient medium from the bacterial biomass. After centrifugation (13,000 x g, 15 min, 4oC), 300µL of the obtained supernatants were concentrated by rotary vacuum and evaporated to dryness. Afterwards, two-step derivatization procedure was performed before GC-MS analyses. The obtained results were subjected to statistical calculations with the use of both uni- and multivariate tests. The obtained results were evaluated using KEGG database, to asses which metabolic pathways are activated and which genes are responsible for it, during the metabolism of given substrates contained in the growing environment. The observed metabolic changes, combined with biochemical and physiological tests, may enable pathway discovery, regulatory inference and understanding of the homeostatic abilities of P. betavasculorum.

Keywords: GC-MS chromatograpfy, metabolomics, metabolism, pectobacterium strains, pectobacterium betavasculorum

Procedia PDF Downloads 55

Authors: Akterono Budiyati, Gita Kusumo, Teguh Putra, Fritzie Rexana, Antonius Kurniawan, Aru Sudoyo, Ahmad Utomo, Andi Utama

Abstract:

The presence of the programmed death ligand-1 (PD-L1) has been used in multiple clinical trials and approved as biomarker for selecting patients more likely to respond to immune checkpoint inhibitors. However, the expression of PD-L1 is regulated in different ways, which leads to a different significance of its presence. Positive PD-L1 within tumors may result from two mechanisms, induced PD-L1 expression by T-cell presence or genetic mechanism that lead to constitutive PD-L1 expression. Amplification of PD-L1 genes was found as one of genetic mechanism which causes an increase in PD-L1 expression. In case of colorectal cancer (CRC), targeting immune checkpoint inhibitor has been recommended for patients with microsatellite instable (MSI). Although the correlation between PD-L1 expression and MSI status has been widely studied, so far the precise mechanism of PD-L1 gene activation in CRC patients, particularly in MSI population have yet to be clarified. In this present study we have profiled 61 archived formalin fixed paraffin embedded CRC specimens of patients from Medistra Hospital, Jakarta admitted in 2010 - 2016. Immunohistochemistry was performed to measure expression of PD-L1 in tumor cells as well as MSI status using antibodies against PD-L1 and MMR (MLH1, MSH2, PMS2 and MSH6), respectively. PD-L1 expression was measured on tumor cells with cut off of 1% whereas loss of nuclear MMR protein expressions in tumor cells but not in normal or stromal cells indicated presence of MSI. Subset of PD-L1 positive patients was then assessed for copy number variations (CNVs) using single Tube TaqMan Copy Number Assays Gene CD247PD-L1. We also observed KRAS mutation to profile possible genetic mechanism leading to the presence or absence of PD-L1 expression. Analysis of 61 CRC patients revealed 15 patients (24%) expressed PD-L1 on their tumor cell membranes. The prevalence of surface membrane PD-L1 was significantly higher in patients with MSI (87%; 7/8) compared to patients with microsatellite stable (MSS) (15%; 8/53) (P=0.001). Although amplification of PD-L1 gene was not found among PD-L1 positive patients, low-level amplification of PD-L1 gene was commonly observed in MSS patients (75%; 6/8) than in MSI patients (43%; 3/7). Additionally, we found 26% of CRC patients harbored KRAS mutations (16/61), so far the distribution of KRAS status did not correlate with PD-L1 expression. Our data suggest genetic mechanism through amplification of PD-L1 seems not to be the mechanism underlying upregulation of PD-L1 expression in CRC patients. However, further studies are warranted to confirm the results.

Keywords: colorectal cancer, gene amplification, microsatellite instable, programmed death ligand-1

Procedia PDF Downloads 208

Authors: Sabrina N. Rabelo, Tiago de F. Paulino, Willian M. Duarte, Samer Sawalha, Luiz Machado

Abstract:

Energy use is one of the main indicators for the economic and social development of a country, reflecting directly in the quality of life of the population. The expansion of energy use together with the depletion of fossil resources and the poor efficiency of energy systems have led many countries in recent years to invest in renewable energy sources. In this context, solar-assisted heat pump has become very important in energy industry, since it can transfer heat energy from the sun to water or another absorbing source. The direct-expansion solar assisted heat pump (DX-SAHP) water heater system operates by receiving solar energy incident in a solar collector, which serves as an evaporator in a refrigeration cycle, and the energy reject by the condenser is used for water heating. In this paper, a DX-SAHP using carbon dioxide as refrigerant (R744) was assembled, and the influence of the variation of the water mass flow rate in the system was analyzed. The parameters such as high pressure, water outlet temperature, gas cooler outlet temperature, evaporator temperature, and the coefficient of performance were studied. The mainly components used to assemble the heat pump were a reciprocating compressor, a gas cooler which is a countercurrent concentric tube heat exchanger, a needle-valve, and an evaporator that is a copper bare flat plate solar collector designed to capture direct and diffuse radiation. Routines were developed in the LabVIEW and CoolProp through MATLAB software’s, respectively, to collect data and calculate the thermodynamics properties. The range of coefficient of performance measured was from 3.2 to 5.34. It was noticed that, with the higher water mass flow rate, the water outlet temperature decreased, and consequently, the coefficient of performance of the system increases since the heat transfer in the gas cooler is higher. In addition, the high pressure of the system and the CO₂ gas cooler outlet temperature decreased. The heat pump using carbon dioxide as a refrigerant, especially operating with solar radiation has been proven to be a renewable source in an efficient system for heating residential water compared to electrical heaters reaching temperatures between 40 °C and 80 °C.

Keywords: water mass flow rate, R-744, heat pump, solar evaporator, water heater

Procedia PDF Downloads 163

Authors: M. Abbasi Layegh, S. Haghipour, K. Athari, R. Khosravi, M. Tafkikialamdari

Abstract:

An approach to find the optimum mel-frequency cepstral coefficients (MFCCs) for the Radif of Mirzâ Ábdollâh, which is the principal emblem and the heart of Persian music, performed by most famous Iranian masters on two Iranian stringed instruments ‘Tar’ and ‘Setar’ is proposed. While investigating the variance of MFCC for each record in themusic database of 1500 gushe of the repertoire belonging to 12 modal systems (dastgâh and âvâz), we have applied the Fuzzy C-Mean clustering algorithm on each of the 12 coefficient and different combinations of those coefficients. We have applied the same experiment while increasing the number of coefficients but the clustering accuracy remained the same. Therefore, we can conclude that the first 7 MFCCs (V-7MFCC) are enough for classification of The Radif of Mirzâ Ábdollâh. Classical machine learning algorithms such as MLP neural networks, K-Nearest Neighbors (KNN), Gaussian Mixture Model (GMM), Hidden Markov Model (HMM) and Support Vector Machine (SVM) have been employed. Finally, it can be realized that SVM shows a better performance in this study.

Keywords: radif of Mirzâ Ábdollâh, Gushe, mel frequency cepstral coefficients, fuzzy c-mean clustering algorithm, k-nearest neighbors (KNN), gaussian mixture model (GMM), hidden markov model (HMM), support vector machine (SVM)

Procedia PDF Downloads 432

Authors: Mirza Mujtaba Baig

Abstract:

Artificial Intelligence (AI) is evolving rapidly, and one of the areas in which this field has influenced is automation. The automobile, healthcare, education, and robotic industries deploy AI technologies constantly, and the automation of tasks is beneficial to allow time for knowledge-based tasks and also introduce convenience to everyday human endeavors. The paper reviews the challenges faced with the current implementations of autonomous self-driving cars by exploring the machine learning, robotics, and artificial intelligence techniques employed for the development of this innovation. The controversy surrounding the development and deployment of autonomous machines, e.g., vehicles, begs the need for the exploration of the configuration of the programming modules. This paper seeks to add to the body of knowledge of research assisting researchers in decreasing the inconsistencies in current programming modules. Blockchain is a technology of which applications are mostly found within the domains of financial, pharmaceutical, manufacturing, and artificial intelligence. The registering of events in a secured manner as well as applying external algorithms required for the data analytics are especially helpful for integrating, adapting, maintaining, and extending to new domains, especially predictive analytics applications.

Keywords: artificial intelligence, automation, big data, self-driving cars, machine learning, neural networking algorithm, blockchain, business intelligence

Procedia PDF Downloads 109

Authors: Amarjit Singh, Tripatdeep Singh Dua, Vikas Attri

Abstract:

Mobile Ad-hoc Network is a combination of several nodes that create dynamically a specific network without using any base infrastructure. In this study all the mobile nodes can depended upon each other to send any data. Mobile host can pick up data and forwarding to their destination path. Basically MANET depend upon their Quality of Service which is highly constraints to the user. To give better services we need to improve the QOS. In these days MANET QOS requirement to use soft computing techniques. These techniques depend upon their specific requirement and which exists using MANET concepts. Using a soft computing techniques various protocol and algorithms may be considered. In this paper, we provide comparative study review of existing work done in MANET using various kind of soft computing techniques. Our review research is based on their specific protocol or algorithm which provide concern solution of QOS need. We discuss about various protocol through which routing in MANET. In Second section we clear the concepts of Soft Computing and their types. In third section we review the MANET using different kind of soft computing techniques work done before. In forth section we need to understand the concept of QoS requirement which exists in MANET and we done comparative study on different protocol used before and last we conclude the purpose of using MANET with soft computing techniques metrics.

Keywords: mobile ad-hoc network, fuzzy improved genetic approach, neural network, routing protocol, wireless mesh network

Procedia PDF Downloads 335

Authors: Christian Angerer, Markus Lienkamp

Abstract:

Electric vehicles offer a high variety of possible drivetrain topologies with up to 4 motors. Multi-motor-designs can have several advantages regarding traction, vehicle dynamics, safety and even efficiency. With a rising number of motors, the whole drivetrain becomes more complex. All permutations of gearings, drivetrain-layouts, motor-types and –sizes lead up in a very large solution space. Single elements of this solution space can be analyzed by simulation methods. In addition to longitudinal vehicle behavior, which most optimization-approaches are restricted to, also lateral dynamics are important for vehicle dynamics, stability and efficiency. In order to compete large solution spaces and to find an optimal result, genetic algorithm based optimization is state-of-the-art. As lateral dynamics simulation is way more CPU-intensive, optimization takes much more time than in case of longitudinal-only simulation. Therefore, this paper shows an approach how to create meta-models from a 14-degree of freedom vehicle model in order to enable a numerically efficient drivetrain-layout optimization process under consideration of lateral dynamics. Different meta-modelling approaches such as neural networks or DoE are implemented and comparatively discussed.

Keywords: driving dynamics, drivetrain layout, genetic optimization, meta-modeling, lateral dynamicx

Procedia PDF Downloads 399

Authors: Lokes Parvatha Kumaran S., Sakthi Jay Mahenthar C., Sathyaprakash P., Jayakumar V., Shobanadevi A.

Abstract:

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. But even the most powerful classical supercomputers find it difficult to execute these tasks. With the recent development of quantum computing, researchers and tech-giants strive for new quantum circuits for machine learning tasks, as present works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. But it is strenuous to simulate classical deep learning models on existing quantum computing platforms due to the inflexibility of deep quantum circuits. As a consequence, it is essential to design viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Reinforcement Learning by remodeling the experience replay and target network into a representation of VQC. In addition, to reduce the number of model parameters, quantum information encoding schemes are used to achieve better results than the classical neural networks. VQCs are employed to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and the target network.

Keywords: quantum computing, quantum machine learning, variational quantum circuit, deep reinforcement learning, quantum information encoding scheme

Procedia PDF Downloads 109

Authors: Marianna Constantinou, Hana Burianova, Ala Yankouskaya

Abstract:

Episodic memory retrieval benefits from arousal, with better performance linked to arousing to-be-remembered information. However, the enduring impact of arousal on subsequent memory processes, particularly for non-arousing stimuli, remains unclear. This functional Magnetic Resonance Imaging (fMRI) study examined the effects of arousal on episodic memory processes in young and old adults, focusing on memory of neutral information following arousal exposure. Neural activity was assessed at three distinct timepoints: during exposure to arousing and non-arousing stimuli, memory consolidation (with or without arousing stimulus exposure), and during memory retrieval (with or without arousing stimulus exposure). Behavioural results show that across both age groups, participants performed worse when retrieving episodic memories about a video preceded by a highly arousing negative image. Our fMRI findings reveal three key findings: i) the extension of the influence of negative arousal beyond encoding; ii) the presence of this influence in both young and old adults; iii) and the differential treatment of positive arousal between these age groups. Our findings emphasise valence-specific effects on memory processes and support the enduring impact of negative arousal. We further propose an age-related alteration in the old adult brain in differentiating between positive and negative arousal.

Keywords: episodic memory, ageing, fmri, arousal, valence

Procedia PDF Downloads 44