Search results for: brain machine interface (BMI)

Authors: André Augusto Ceballos Melo

Abstract:

Design to facilitate the recognition of congruent prosthetic movements, context-to-motion translations guided by image, verbal prompt, users nonverbal communication such as facial expressions, gestures, paralinguistics, scene context, and object recognition contributes to this process though it can also be applied to other tasks, such as walking, Prosthetic limbs as assistive technology through gestures, sound codes, signs, facial, body expressions, and scene context The context-to-motion model is a machine learning approach that is designed to improve the control and dexterity of prosthetic limbs. It works by using sensory input from the prosthetic limb to learn about the dynamics of the environment and then using this information to generate smooth, stable movements. This can help to improve the performance of the prosthetic limb and make it easier for the user to perform a wide range of tasks. There are several key benefits to using the context-to-motion model for prosthetic limb control. First, it can help to improve the naturalness and smoothness of prosthetic limb movements, which can make them more comfortable and easier to use for the user. Second, it can help to improve the accuracy and precision of prosthetic limb movements, which can be particularly useful for tasks that require fine motor control. Finally, the context-to-motion model can be trained using a variety of different sensory inputs, which makes it adaptable to a wide range of prosthetic limb designs and environments. Stable diffusion is a machine learning method that can be used to improve the control and stability of movements in robotic and prosthetic systems. It works by using sensory feedback to learn about the dynamics of the environment and then using this information to generate smooth, stable movements. One key aspect of stable diffusion is that it is designed to be robust to noise and uncertainty in the sensory feedback. This means that it can continue to produce stable, smooth movements even when the sensory data is noisy or unreliable. To implement stable diffusion in a robotic or prosthetic system, it is typically necessary to first collect a dataset of examples of the desired movements. This dataset can then be used to train a machine learning model to predict the appropriate control inputs for a given set of sensory observations. Once the model has been trained, it can be used to control the robotic or prosthetic system in real-time. The model receives sensory input from the system and uses it to generate control signals that drive the motors or actuators responsible for moving the system. Overall, the use of the context-to-motion model has the potential to significantly improve the dexterity and performance of prosthetic limbs, making them more useful and effective for a wide range of users Hand Gesture Body Language Influence Communication to social interaction, offering a possibility for users to maximize their quality of life, social interaction, and gesture communication.

Keywords: stable diffusion, neural interface, smart prosthetic, augmenting

Procedia PDF Downloads 87

Authors: Mina Dabirinezhad, Mohsen Bayat Pour, Amin Dabirinejad

Abstract:

This paper is intended to introduce the technology to solve some of the deficiencies of the direct digital radiology. Nowadays, digital radiology is the latest progression in dental imaging, which has become an essential part of dentistry. There are two main parts of the direct digital radiology comprised of an intraoral X-ray machine and a sensor (digital image receptor). The dentists and the dental nurses experience afflictions during the taking image process by the direct digital X-ray machine. For instance, sometimes they need to readjust the sensor in the mouth of the patient to take the X-ray image again due to the low quality of that. Another problem is, the position of the sensor may move in the mouth of the patient and it triggers off an inappropriate image for the dentists. It means that it is a time-consuming process for dentists or dental nurses. On the other hand, taking several the X-ray images brings some problems for the patient such as being harmful to their health and feeling pain in their mouth due to the pressure of the sensor to the jaw. The author provides a technology to solve the above-mentioned issues that is called “Self-Recognition Direct Digital Radiology” (SDDR). This technology is based on the principle that the intraoral X-ray machine is capable to diagnose the location of the sensor in the mouth of the patient automatically. In addition, to solve the aforementioned problems, SDDR technology brings out fewer environmental impacts in comparison to the previous version.

Keywords: Dental direct digital imaging, digital image receptor, digital x-ray machine, and environmental impacts

Procedia PDF Downloads 124

Authors: Daniel Bulanda, Janusz A. Starzyk, Adrian Horzyk

Abstract:

The electrocardiogram (ECG) is one of the most commonly used medical tests, essential for correct diagnosis and treatment of the patient. While ECG devices generate a huge amount of data, only a small part of them carries valuable medical information. To deal with this problem, many compression algorithms and filters have been developed over the past years. However, the rapid development of new machine learning techniques poses new challenges. To address this class of problems, we created the FlexPoints algorithm that searches for characteristic points on the ECG signal and ignores all other points that do not carry relevant medical information. The conducted experiments proved that the presented algorithm can significantly reduce the number of data points which represents ECG signal without losing valuable medical information. These sparse but essential characteristic points (flex points) can be a perfect input for some modern machine learning models, which works much better using flex points as an input instead of raw data or data compressed by many popular algorithms.

Keywords: characteristic points, electrocardiogram, ECG, machine learning, signal compression

Procedia PDF Downloads 149

Authors: Pouyan Jahanbin, Mahmoud Houshmand, Omid Fatahi Valilai

Abstract:

A flexible manufacturing system (FMS) is a manufacturing system having the capability of handling the variations of products features that is the result of ever-changing customer demands. The flexibility of the manufacturing systems help to utilize the resources in a more effective manner. However, the control of such systems would be complicated and challenging. FMS needs CNC machines and robots and other resources for establishing the flexibility and enhancing the efficiency of the whole system. Also it needs to integrate the resources to reach required efficiency and flexibility. In order to reach this goal, an integrator framework is proposed in which the machining data of CNC machine tools is received through a STEP-NC file. The interoperability of the system is achieved by the information system. This paper proposes an information system that its data model is designed based on object oriented approach and is implemented through a knowledge-based system. The framework is connected to a database which is filled with robot’s control commands. The framework programs the robots by rules embedded in its knowledge based system. It also controls the interactions of CNC machine tools for loading and unloading actions by robot. As a result, the proposed framework improves the integration of manufacturing resources in Flexible Manufacturing Systems.

Keywords: CNC machine tools, industrial robots, knowledge-based systems, manufacturing recourses integration, flexible manufacturing system (FMS), object-oriented data model

Procedia PDF Downloads 440

Authors: Jake Tempo, Taylor Smithurst, Jen Leah, Skye Waddingham, Amanda Catlin, Richard Cetti

Abstract:

Introduction: Percutaneous nephrolithotomy (PCNL) is the gold-standard procedure for removing large or complex renal stones. Many operating positions can be used, and the debate over the ideal position continues. PCNL can be a long procedure during which patients can sustain pressure injuries. These injuries are often underreported in the literature. Interface pressure mapping records the pressure loading between a surface and the patient. High pressures with prolonged loading result in ischaemia, muscle deformation, and reperfusion which can cause skin breakdown and muscular injury. We compared the peak pressure indexes of common PCNL positions to identify positions which may be at high risk of pressure injuries. We hope the data can be used to adapt high-risk positions so that the PPI can be lessened by either adapting the positions or by using adjuncts to lower PPI. Materials and Methods: We placed a 23-year-old male subject in fourteen different PCNL positions while performing interface pressure mapping. The subject was 179 cm with a weight of 63.3 kg, BMI 19.8kg/m². Results: Supine positions had a higher mean PPI (119mmHg (41-137)) compared to prone positions (64mmHg (32-89)) (p=0.046 two tailed t-test). The supine flexed position with a bolster under the flank produced the highest PPI (194mmHg), and this was at the sacrum. Peak pressure indexes >100mmHg were recorded in eight PCNL positions. Conclusion: Supine PCNL positions produce higher PPI than prone PCNL positions. Our study shows where ‘at risk’ bony prominences are for each PCNL position. Surgeons must ensure these areas are protected during prolonged operations.

Keywords: PCNL, pressure ulcer, interface pressure mapping, surgery

Procedia PDF Downloads 68

Authors: Nermeen El Kashef, Yasser Fouad, Khaled Mahar

Abstract:

No AI-complete system can model the human brain or behavior, without looking at the totality of the whole situation and incorporating a combination of senses. This paper proposes a Pattern Recognition model based on Simulation of Chemical Senses (SCS) for separation and classification of sign language. The model based on human taste controlling strategy. The main idea of the introduced model is motivated by the facts that the tongue cluster input substance into its basic tastes first, and then the brain recognizes its flavor. To implement this strategy, two level architecture is proposed (this is inspired from taste system). The separation-level of the architecture focuses on hand posture cluster, while the classification-level of the architecture to recognizes the sign language. The efficiency of proposed model is demonstrated experimentally by recognizing American Sign Language (ASL) data set. The recognition accuracy obtained for numbers of ASL is 92.9 percent.

Keywords: artificial intelligence, biocybernetics, gustatory system, sign language recognition, taste sense

Procedia PDF Downloads 276

Authors: Ahmed Abdulla Ashlam, Atta Badii, Frederic Stahl

Abstract:

In recent years, SQL injection attacks have been identified as being prevalent against web applications. They affect network security and user data, which leads to a considerable loss of money and data every year. This paper presents the use of classification algorithms in machine learning using a method to classify the login data filtering inputs into "SQLi" or "Non-SQLi,” thus increasing the reliability and accuracy of results in terms of deciding whether an operation is an attack or a valid operation. A method Web-App auto-generated twin data structure replication. Shielding against SQLi attacks (WebAppShield) that verifies all users and prevents attackers (SQLi attacks) from entering and or accessing the database, which the machine learning module predicts as "Non-SQLi" has been developed. A special login form has been developed with a special instance of data validation; this verification process secures the web application from its early stages. The system has been tested and validated, up to 99% of SQLi attacks have been prevented.

Keywords: SQL injection, attacks, web application, accuracy, database

Procedia PDF Downloads 131

Authors: Amhimmid Mohammed Saffour, Mustafa Mohamed Abdullah

Abstract:

The use of computers for handling image data in the healthcare is growing. However, the amount of data produced by modern image generating techniques is vast. This data might be a problem from a storage point of view or when the data is sent over a network. This paper using wavelet transform technique for medical images compression. MATLAB program, are designed to evaluate medical images storage and transmission time problem at Sebha Medical Center Libya. In this paper, three different Computed Tomography images which are abdomen, brain and chest have been selected and compressed using wavelet transform. Objective evaluation has been performed to measure the quality of the compressed images. For this evaluation, the results show that the Peak Signal to Noise Ratio (PSNR) which indicates the quality of the compressed image is ranging from (25.89db to 34.35db for abdomen images, 23.26db to 33.3db for brain images and 25.5db to 36.11db for chest images. These values shows that the compression ratio is nearly to 30:1 is acceptable.

Keywords: medical image, Matlab, image compression, wavelet's, objective evaluation

Procedia PDF Downloads 273

Authors: Razieh Teimouri

Abstract:

Electrical modelling of Cu (In,Ga)Se₂ thin film solar cells is carried out with compositionally graded absorber and CdS buffer layer. Simulation results are compared with experimental data. Surface defect layers (SDL) are located in CdS/CIGS interface for improving open circuit voltage simulated structure through the analysis of the interface is investigated with or without this layer. When SDL removed, by optimizing the conduction band offset (CBO) position of the buffer/absorber layers with its recombination mechanisms and also shallow donor density in the CdS, the open circuit voltage increased significantly. As a result of simulation, excellent performance can be obtained when the conduction band of window layer positions higher by 0.2 eV than that of CIGS and shallow donor density in the CdS was found about 1×10¹⁸ (cm⁻³).

Keywords: CIGS solar cells, thin film, SCAPS, buffer layer, conduction band offset

Procedia PDF Downloads 210

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: convolutional neural networks, coffee bean, peaberry, sorting, support vector machine

Procedia PDF Downloads 131

Authors: Natascha C. D'Amico, Enzo Grossi, Giovanni Valbusa, Ala Malasevschi, Gianpiero Cardone, Sergio Papa

Abstract:

Purpose: To characterize, through a radiomic approach, the nature of areas classified PI-RADS (Prostate Imaging Reporting and Data System) 3/5, recognized in multiparametric prostate magnetic resonance with T2-weighted (T2w), diffusion and perfusion sequences with paramagnetic contrast. Methods and Materials: 24 cases undergoing multiparametric prostate MR and biopsy were admitted to this pilot study. Clinical outcome of the PI-RADS 3/5 was found through biopsy, finding 8 malignant tumours. The analysed images were acquired with a Philips achieva 1.5T machine with a CE- T2-weighted sequence in the axial plane. Semi-automatic tumour segmentation was carried out on MR images using 3DSlicer image analysis software. 45 shape-based, intensity-based and texture-based features were extracted and represented the input for preprocessing. An evolutionary algorithm (a TWIST system based on KNN algorithm) was used to subdivide the dataset into training and testing set and select features yielding the maximal amount of information. After this pre-processing 20 input variables were selected and different machine learning systems were used to develop a predictive model based on a training testing crossover procedure. Results: The best machine learning system (three-layers feed-forward neural network) obtained a global accuracy of 90% ( 80 % sensitivity and 100% specificity ) with a ROC of 0.82. Conclusion: Machine learning systems coupled with radiomics show a promising potential in distinguishing benign from malign tumours in PI-RADS 3/5 areas.

Keywords: machine learning, MR prostate, PI-Rads 3, radiomics

Procedia PDF Downloads 174

Authors: C. G. Jinimole, A. Harsha

Abstract:

One of the key problems facing in the analysis of Computed Tomography (CT) images is the poor contrast of the images. Image enhancement can be used to improve the visual clarity and quality of the images or to provide a better transformation representation for further processing. Contrast enhancement of images is one of the acceptable methods used for image enhancement in various applications in the medical field. This will be helpful to visualize and extract details of brain infarctions, tumors, and cancers from the CT image. This paper presents a comparison study of five contrast enhancement techniques suitable for the contrast enhancement of CT images. The types of techniques include Power Law Transformation, Logarithmic Transformation, Histogram Equalization, Contrast Stretching, and Laplacian Transformation. All these techniques are compared with each other to find out which enhancement provides better contrast of CT image. For the comparison of the techniques, the parameters Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) are used. Logarithmic Transformation provided the clearer and best quality image compared to all other techniques studied and has got the highest value of PSNR. Comparison concludes with better approach for its future research especially for mapping abnormalities from CT images resulting from Brain Injuries.

Keywords: computed tomography, enhancement techniques, increasing contrast, PSNR and MSE

Procedia PDF Downloads 293

Authors: Dung Nguyen, Yu Wei, Eric Henderson

Abstract:

Analytical tools have been used for decades to assist in the development of forest plans. In 2016, a new decision support system, PRISM, was jointly developed by United States Forest Service (USFS) Northern Region and Colorado State University to support the forest planning process. Prism has a friendly user interface with functionality for database management, model development, data visualization, and sensitivity analysis. The software is tailored for USFS planning, but it is flexible enough to support planning efforts by other forestland owners and managers. Here, the core capability of PRISM and its applications in developing plans for several United States national forests are presented. The strengths of PRISM are also discussed to show its potential of being a preferable tool for managers and experts in the domain of forest management and planning.

Keywords: decision support, forest management, forest plan, graphical user interface, software

Procedia PDF Downloads 96

Authors: Willy Mbenza, Sho Kenjiro

Abstract:

Increasing efforts are directed towards a better understanding and foreknowledge of extreme precipitation likelihood, given the adverse effects associated with their occurrence. This knowledge plays a crucial role in long-term planning and the formulation of effective emergency response. However, predicting extreme events reliably presents a challenge to conventional empirical/statistics due to the involvement of numerous variables spanning different time and space scales. In the recent time, Machine Learning has emerged as a promising tool for predicting the dynamics of extreme precipitation. ML techniques enables the consideration of both local and regional physical variables that have a strong influence on the likelihood of extreme precipitation. These variables encompasses factors such as air temperature, soil moisture, specific humidity, aerosol concentration, among others. In this study, we develop an ML model that incorporates both local and regional variables while establishing a robust relationship between physical variables and precipitation during the downscaling process. Furthermore, the model provides valuable information on the frequency and duration of a given intensity of precipitation.

Keywords: machine learning (ML), predictions, rainfall events, regional variables

Procedia PDF Downloads 72

Authors: Shenghong Huang, Weirong Wang, Xisheng Luo, Xinzhu Li, Xinwen Zhao

Abstract:

Understanding of material mixing induced by Richtmyer-Meshkov instability (RMI) at extreme shock compressing conditions (high energy density environment: P >> 100GPa, T >> 10000k) is of great significance in engineering and science, such as inertial confinement fusion(ICF), supersonic combustion, etc. Turbulent mixing induced by RMI is a kind of complex fluid dynamics, which is closely related with hydrodynamic conditions, thermodynamic states, material physical properties such as compressibility, strength, surface tension and viscosity, etc. as well as initial perturbation on interface. For phenomena in ordinary thermodynamic conditions (low energy density environment), many investigations have been conducted and many progresses have been reported, while for mixing in extreme thermodynamic conditions, the evolution may be very different due to ionization as well as large difference of material physical properties, which is full of scientific problems and academic interests. In this investigation, the first principle based molecular dynamic method is applied to study metal Lithium and gas Hydrogen (Li-H2) interface mixing in micro/meso scale regime at different shock compressing loading speed ranging from 3 km/s to 30 km/s. It's found that, 1) Different from low-speed shock compressing cases, in high-speed shock compresing (>9km/s) cases, a strong acceleration of metal/gas interface after strong shock compression is observed numerically, leading to a strong phase inverse and spike growing with a relative larger linear rate. And more specially, the spike growing rate is observed to be increased with shock loading speed, presenting large discrepancy with available empirical RMI models; 2) Ionization is happened in shock font zone at high-speed loading cases(>9km/s). An additional local electric field induced by the inhomogeneous diffusion of electrons and nuclei after shock font is observed to occur near the metal/gas interface, leading to a large acceleration of nuclei in this zone; 3) In conclusion, the work of additional electric field contributes to a mechanism of RMI in micro/meso scale regime at extreme shock compressing conditions, i.e., a Rayleigh-Taylor instability(RTI) is induced by additional electric field during RMI mixing process and thus a larger linear growing rate of interface spike.

Keywords: ionization, micro/meso scale, material mixing, shock

Procedia PDF Downloads 211

Authors: Martin Alexander Eder, Sergei Semenov

Abstract:

Many glass-epoxy composite structures, such as large utility wind turbine rotor blades (WTBs), comprise of adhesive joints with typically thick bond lines used to connect the different components during assembly. Performance optimization of rotor blades to increase power output by simultaneously maintaining high stiffness-to-low-mass ratios entails intricate geometries in conjunction with complex anisotropic material behavior. Consequently, adhesive joints in WTBs are subject to multiaxial stress states with significant stress gradients depending on the local joint geometry. Moreover, the dynamic aero-elastic interaction of the WTB with the airflow generates non-proportional, variable amplitude stress histories in the material. Empiricism shows that a prominent failure type in WTBs is high cycle fatigue failure of adhesive bond line interfaces, which in fact over time developed into a design driver as WTB sizes increase rapidly. Structural optimization employed at an early design stage, therefore, sets high demands on computationally efficient interface fatigue models capable of predicting the critical locations prone for interface failure. The numerical stress-based interface fatigue model presented in this work uses the Drucker-Prager criterion to compute three different damage indices corresponding to the two interface shear tractions and the outward normal traction. The two-parameter Drucker-Prager model was chosen because of its ability to consider shear strength enhancement under compression and shear strength reduction under tension. The governing interface damage index is taken as the maximum of the triple. The damage indices are computed through the well-known linear Palmgren-Miner rule after separate rain flow-counting of the equivalent shear stress history and the equivalent pure normal stress history. The equivalent stress signals are obtained by self-similar scaling of the Drucker-Prager surface whose shape is defined by the uniaxial tensile strength and the shear strength such that it intersects with the stress point at every time step. This approach implicitly assumes that the damage caused by the prevailing multiaxial stress state is the same as the damage caused by an amplified equivalent uniaxial stress state in the three interface directions. The model was implemented as Python plug-in for the commercially available finite element code Abaqus for its use with solid elements. The model was used to predict the interface damage of an adhesively bonded, tapered glass-epoxy composite cantilever I-beam tested by LM Wind Power under constant amplitude compression-compression tip load in the high cycle fatigue regime. Results show that the model was able to predict the location of debonding in the adhesive interface between the webfoot and the cap. Moreover, with a set of two different constant life diagrams namely in shear and tension, it was possible to predict both the fatigue lifetime and the failure mode of the sub-component with reasonable accuracy. It can be concluded that the fidelity, robustness and computational efficiency of the proposed model make it especially suitable for rapid fatigue damage screening of large 3D finite element models subject to complex dynamic load histories.

Keywords: adhesive, fatigue, interface, multiaxial stress

Procedia PDF Downloads 154

Authors: Fouad. Inel, Lakhdar. Khochemane

Abstract:

This article presents a comparative response specification performance between two controllers of three and four cable based robots for various applications. The main objective of this work is: The first is to use the direct and inverse geometric model to study and simulate the end effector position of the robot with three and four cables. A graphical user interface has been implemented in order to visualizing the position of the robot. Secondly, we present the determination of static and dynamic tensions and lengths of cables required to flow different trajectories. At the end, we study the response of our systems in closed loop with a Proportional-Integrated Derivative (PID) and Proportional-Integrated (PD) controllers then this last are compared the results of the same examples using MATLAB/Simulink; we found that the PID method gives the better performance, such as rapidly speed response, settling time, compared to PD controller.

Keywords: parallel cable-based robots, geometric modeling, dynamic modeling, graphical user interface, open loop, PID/PD controllers

Procedia PDF Downloads 432

Authors: Ernesto A. Lagarda-Leyva, Manuel A. Valenzuela L., José G. Oshima C., Arnulfo A. Naranjo-Flores

Abstract:

From August to December of 2016, a diagnostic and strategic planning study was carried out on the supply chain of the company Agropecuaria GABO S.A. de C.V. The final product of the study was the development of the strategic plan and a project portfolio to meet the demands of the three links in the supply chain of the Roma tomato exported annually to the United States of America. In this project, the strategic objective of ensuring the proper handling of the product was selected and one of the goals associated with this was the employment of quantitative methods to support decision making. Considering the antecedents, the objective of this case study was to develop a model to analyze the behavioral dynamics in the distribution chain, from the logistics of storage and shipment of Roma tomato in 81-case pallets (11.5 kg per case), to the two pre-cooling rooms and eventual loading onto transports, seeking to reduce the bottleneck and the associated costs by means of a dynamic interface. The methodology used was that of system dynamics, considering four phases that were adapted to the purpose of the study: 1) the conceptualization phase; 2) the formulation phase; 3) the evaluation phase; and 4) the communication phase. The main practical conclusions lead to the possibility of reducing both the bottlenecks in the cooling rooms and the costs by simulating scenarios and modifying certain policies. Furthermore, the creation of the dynamic interface between the model and the stakeholders was achieved by generating interaction with buttons and simple instructions that allow making modifications and observing diverse behaviors.

Keywords: agrilogistics, distribution, scenarios, system dynamics

Procedia PDF Downloads 216

Authors: Vishal Das, Tianyi Mao, Zhicheng Geng, Carmen Flores, Diego Pelloso, Fang Wang

Abstract:

Accurate sell-in and sell-out forecasting is a ubiquitous problem in the retail industry. It is an important element of any demand planning activity. As a global food and beverage company, Nestlé has hundreds of products in each geographical location that they operate in. Each product has its sell-in and sell-out time series data, which are forecasted on a weekly and monthly scale for demand and financial planning. To address this challenge, Nestlé Chilein collaboration with Amazon Machine Learning Solutions Labhas developed their in-house solution of using machine learning models for forecasting. Similar products are combined together such that there is one model for each product category. In this way, the models learn from a larger set of data, and there are fewer models to maintain. The solution is scalable to all product categories and is developed to be flexible enough to include any new product or eliminate any existing product in a product category based on requirements. We show how we can use the machine learning development environment on Amazon Web Services (AWS) to explore a set of forecasting models and create business intelligence dashboards that can be used with the existing demand planning tools in Nestlé. We explored recent deep learning networks (DNN), which show promising results for a variety of time series forecasting problems. Specifically, we used a DeepAR autoregressive model that can group similar time series together and provide robust predictions. To further enhance the accuracy of the predictions and include domain-specific knowledge, we designed an ensemble approach using DeepAR and XGBoost regression model. As part of the ensemble approach, we interlinked the sell-out and sell-in information to ensure that a future sell-out influences the current sell-in predictions. Our approach outperforms the benchmark statistical models by more than 50%. The machine learning (ML) pipeline implemented in the cloud is currently being extended for other product categories and is getting adopted by other geomarkets.

Keywords: sell-in and sell-out forecasting, demand planning, DeepAR, retail, ensemble machine learning, time-series

Procedia PDF Downloads 231

Authors: M. Al Zallouha, Y. Landkocz, J. Brunet, R. Cousin, J. M. Halket, E. Genty, P. J. Martin, A. Verdin, D. Courcot, S. Siffert, P. Shirali, S. Billet

Abstract:

Toluene is one of the most used Volatile Organic Compounds (VOCs) in the industry. Amongst VOCs, Benzene, Toluene, Ethylbenzene and Xylenes (BTEX) emitted into the atmosphere have a major and direct impact on human health. It is, therefore, necessary to minimize emissions directly at source. Catalytic oxidation is an industrial technique which provides remediation efficiency in the treatment of these organic compounds. However, during operation, the catalysts can release some compounds, called byproducts, more toxic than the original VOCs. The catalytic oxidation of a gas stream containing 1000ppm of toluene on Pd/α-Al2O3 can release a few ppm of benzene, according to the operating temperature of the catalyst. The development of new catalysts must, therefore, include chemical and toxicological validation phases. In this project, A549 human lung cells were exposed in air/liquid interface (Vitrocell®) to gas mixtures derived from the oxidation of toluene with a catalyst of Pd/α-Al2O3. Both exposure concentrations (i.e. 10 and 100% of catalytic emission) resulted in increased gene expression of Xenobiotics Metabolising Enzymes (XME) (CYP2E1 CYP2S1, CYP1A1, CYP1B1, EPHX1, and NQO1). Some of these XMEs are known to be induced by polycyclic organic compounds conventionally not searched during the development of catalysts for VOCs degradation. The increase in gene expression suggests the presence of undetected compounds whose toxicity must be assessed before the adoption of new catalyst. This enhances the relevance of toxicological validation of such systems before scaling-up and marketing.

Keywords: BTEX toxicity, air/liquid interface cell exposure, Vitrocell®, catalytic oxidation

Procedia PDF Downloads 399

Authors: S. Arabnejad, D. W. C. Cheong, H. Chaobin, V. P. W. Shim

Abstract:

Debonding is the one of the fundamental damage mechanisms in particle field composites. This phenomenon gains more importance in nano composites because of the extensive interfacial region present in these materials. Understanding the debonding mechanism accurately, can help in understanding and predicting the response of nano composites as the interface deteriorates. The small length scale of the phenomenon makes the experimental characterization complicated and the results of it, far from real physical behavior. In this study the damage process in nylon-6/silica interface is examined through Molecular Dynamics (MD) modeling and simulations. The silica has been modeled with three forms of surfaces – without any surface treatment, with the surface treatment of 3-aminopropyltriethoxysilane (APTES) and with Hexamethyldisilazane (HMDZ) surface treatment. The APTES surface modification used to create functional groups on the silica surface, reacts and form covalent bonds with nylon 6 chains while the HMDZ surface treatment only interacts with both particle and polymer by non-bond interaction. The MD model in this study uses a PCFF force field. The atomic model is generated in a periodic box with a layer of vacuum on top of the polymer layer. This layer of vacuum is large enough that assures us from not having any interaction between particle and substrate after debonding. Results show that each of these three models show a different traction separation behavior. However, all of them show an almost bilinear traction separation behavior. The study also reveals a strong correlation between the length of APTES surface treatment and the cohesive strength of the interface.

Keywords: debonding, surface treatment, cohesive response, separation behaviour

Procedia PDF Downloads 443

Authors: Feng Yang

Abstract:

Machine learning (ML), especially deep learning (DL), has been extensively applied to many applications in recently years and gained great success in solving different problems, including scientific problems. However, conventional ML/DL methodologies are purely data-driven which have the limitations, such as need of ample amount of labelled training data, lack of consistency to physical principles, and lack of generalizability to new problems/domains. Recently, there is a growing consensus that ML models need to further take advantage of prior knowledge to deal with these limitations. Physics-informed machine learning, aiming at integration of physics/domain knowledge into ML, has been recognized as an emerging area of research, especially in the recent 2 to 3 years. In this work, physics-informed ML, specifically physics-informed neural network (NN), is employed and implemented to estimate the displacements at x, y, z directions in a solid mechanics problem that is controlled by equilibrium equations with boundary conditions. By incorporating the physics (i.e. the equilibrium equations) into the learning process of NN, it is showed that the NN can be trained very efficiently with a small set of labelled training data. Experiments with different settings of the NN model and the amount of labelled training data were conducted, and the results show that very high accuracy can be achieved in fulfilling the equilibrium equations as well as in predicting the displacements, e.g. in setting the overall displacement of 0.1, a root mean square error (RMSE) of 2.09 × 10−4 was achieved.

Keywords: deep learning, neural network, physics-informed machine learning, solid mechanics

Procedia PDF Downloads 135

Authors: Akshat Kumar, Vidushi

Abstract:

This paper identifies 27 KOIs, 26 of which are currently classified as candidates and one as false positives that have a high probability of being confirmed. For this purpose, 11 machine learning algorithms were implemented on the cumulative kepler dataset sourced from the NASA exoplanet archive; it was observed that the best-performing model was HistGradientBoosting and XGBoost with a test accuracy of 93.5%, and the lowest-performing model was Gaussian NB with a test accuracy of 54%, to test model performance F1, cross-validation score and RUC curve was calculated. Based on the learned models, the significant characteristics for confirm exoplanets were identified, putting emphasis on the object’s transit and stellar properties; these characteristics were namely koi_count, koi_prad, koi_period, koi_dor, koi_ror, and koi_smass, which were later considered to filter out the potential KOIs. The paper also calculates the Earth similarity index based on the planetary radius and equilibrium temperature for each KOI identified to aid in their classification.

Keywords: Kepler objects of interest, exoplanets, space exploration, machine learning, earth similarity index, transit photometry

Procedia PDF Downloads 44

Authors: Sean Paulsen, Michael Casey

Abstract:

In this work we present a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.

Keywords: transfer learning, fMRI, self-supervised, brain decoding, transformer, multitask training

Procedia PDF Downloads 72

Authors: Shaghayegh Shajari, Mehdi Mahmoodi, Mahmood Rajabian, Uttandaraman Sundararaj, Les J. Sudak

Abstract:

Although several strain sensors based on carbon nanotubes (CNTs) have been reported, the stretchability and sensitivity of these sensors have remained as a challenge. Highly stretchable and sensitive strain sensors are in great demand for human motion monitoring and human-machine interface. This paper reports the fabrication and characterization of a new type of strain sensors based on a stretchable fluoropolymer / CNT nanocomposite system made via melt-mixing technique. Electrical and mechanical characterizations were obtained. The results showed that this nanocomposite sensor has high stretchability up to 280% of strain at an optimum level of filler concentration. The piezoresistive properties and the strain sensing mechanism of the strain sensor were investigated using Electrochemical Impedance Spectroscopy (EIS). High sensitivity was obtained (gauge factor as large as 12000 under 120% applied strain) in particular at the concentrations above the percolation threshold. Due to the tunneling effect, a non- linear piezoresistivity was observed at high concentrations of CNT loading. The nanocomposites with good conductivity and lightweight could be a promising candidate for strain sensing applications.

Keywords: carbon nanotubes, fluoropolymer, piezoresistive, strain sensor

Procedia PDF Downloads 281

Authors: Aulia Fitri

Abstract:

This aims to seek which part of the linguistics with the common mistakes occurred between Instagram translation and human translation. Instagram is a social media account that is widely used by people in the world. Everyone with the Instagram account can consume the captions and pictures that are shared by their friends, celebrity, and public figures across countries. Instagram provides the machine translation under its caption space that will assist users to understand the language of their non-native. The researcher takes samples from an Indonesian public figure whereas the account is followed by many followers. The public figure tries to help her followers from other countries understand her posts by putting up the English version after the Indonesian version. However, the research on Instagram account has not been done yet even though the account is widely used by the worldwide society. There are 20 samples that will be analysed on the perspective of translation quality and linguistics tools. As the MT, Instagram tends to give a literal translation without regarding the topic meant. On the other hand, the human translation tends to exaggerate the translation which leads a different meaning in English. This is an interesting study to discuss when the human nature and robotic-system influence the translation result.

Keywords: human translation, machine translation (MT), translation quality, linguistic tool

Procedia PDF Downloads 296

Authors: Sungin Jeong

Abstract:

This paper presents a linear oscillating generator of cylindrical type for hybrid electric vehicle application. The focus of the study is the suggestion of the optimal model and the design rule of the cylindrical linear oscillating generator with permanent magnet in the back-iron translator. The cylindrical topology is achieved using equivalent magnetic circuit considering leakage elements as initial modeling. This topology with permanent magnet in the back-iron translator is described by number of phases and displacement of stroke. For more accurate analysis of an oscillating machine, it will be compared by moving just one-pole pitch forward and backward the thrust of single-phase system and three-phase system. Through the analysis and comparison, a single-phase system of cylindrical topology as the optimal topology is selected. Finally, the detailed design of the optimal topology takes the magnetic saturation effects into account by finite element analysis. Besides, the losses are examined to obtain more accurate results; copper loss in the conductors of machine windings, eddy-current loss of permanent magnet, and iron-loss of specific material of electrical steel. The considerations of thermal performances and mechanical robustness are essential, because they have an effect on the entire efficiency and the insulations of the machine due to the losses of the high temperature generated in each region of the generator. Besides electric machine with linear oscillating movement requires a support system that can resist dynamic forces and mechanical masses. As a result, the fatigue analysis of shaft is achieved by the kinetic equations. Also, the thermal characteristics are analyzed by the operating frequency in each region. The results of this study will give a very important design rule in the design of linear oscillating machines. It enables us to more accurate machine design and more accurate prediction of machine performances.

Keywords: equivalent magnetic circuit, finite element analysis, hybrid electric vehicle, linear oscillating generator

Procedia PDF Downloads 183

Authors: Sarah E. Nelson, Casey Weiner, Alexander Sigmon, Jun Hua, Haris I. Sair, Jose I. Suarez, Robert D. Stevens

Abstract:

Graph-theoretical information from structural connectomes indicated significant connectivity changes and improved acute prognostication in a Random Forest (RF) model in aneurysmal subarachnoid hemorrhage (aSAH), which can lead to significant morbidity and mortality and has traditionally been fraught by poor methods to predict outcome. This study’s hypothesis was that structural connectivity changes occur in canonical brain networks of acute aSAH patients, and that these changes are associated with functional outcome at six months. In a prospective cohort of patients admitted to a single institution for management of acute aSAH, patients underwent diffusion tensor imaging (DTI) as part of a multimodal MRI scan. A weighted undirected structural connectome was created of each patient’s images using Constant Solid Angle (CSA) tractography, with 176 regions of interest (ROIs) defined by the Johns Hopkins Eve atlas. ROIs were sorted into four networks: Default Mode Network, Executive Control Network, Salience Network, and Whole Brain. The resulting nodes and edges were characterized using graph-theoretic features, including Node Strength (NS), Betweenness Centrality (BC), Network Degree (ND), and Connectedness (C). Clinical (including demographics and World Federation of Neurologic Surgeons scale) and graph features were used separately and in combination to train RF and Logistic Regression classifiers to predict two outcomes: dichotomized modified Rankin Score (mRS) at discharge and at six months after discharge (favorable outcome mRS 0-2, unfavorable outcome mRS 3-6). A total of 56 aSAH patients underwent DTI a median (IQR) of 7 (IQR=8.5) days after admission. The best performing model (RF) combining clinical and DTI graph features had a mean Area Under the Receiver Operator Characteristic Curve (AUROC) of 0.88 ± 0.00 and Area Under the Precision Recall Curve (AUPRC) of 0.95 ± 0.00 over 500 trials. The combined model performed better than the clinical model alone (AUROC 0.81 ± 0.01, AUPRC 0.91 ± 0.00). The highest-ranked graph features for prediction were NS, BC, and ND. These results indicate reorganization of the connectome early after aSAH. The performance of clinical prognostic models was increased significantly by the inclusion of DTI-derived graph connectivity metrics. This methodology could significantly improve prognostication of aSAH.

Keywords: connectomics, diffusion tensor imaging, graph theory, machine learning, subarachnoid hemorrhage

Procedia PDF Downloads 175

Authors: Hamed Rahmani, Wim Groot

Abstract:

The term "youth not in employment, education or training (NEET)" refers to a combination of youth unemployment and school dropout. This study investigates the variables that increase the risk of becoming NEET in Iran. A selection bias-adjusted Probit model was employed using machine learning to identify these risk factors. We used cross-sectional data obtained from the Statistical Centre of Iran and the Ministry of Cooperatives Labour and Social Welfare that was taken from the labour force survey conducted in the spring of 2021. We look at years of education, work experience, housework, the number of children under the age of six in the home, family education, birthplace, and the amount of land owned by households. Results show that hours spent performing domestic chores enhance the likelihood of youth becoming NEET, and years of education and years of potential work experience decrease the chance of being NEET. The findings also show that female youth born in cities were less likely than those born in rural regions to become NEET.

Keywords: NEET youth, probit, CART, machine learning, unemployment

Procedia PDF Downloads 92

Authors: Abdulrahman Sumayli, Saad M. AlShahrani

Abstract:

For the hydrogenation process, knowing the solubility of hydrogen (H2) in hydrocarbons is critical to improve the efficiency of the process. We investigated the H2 solubility computation in four heavy crude oil feedstocks using machine learning techniques. Temperature, pressure, and feedstock type were considered as the inputs to the models, while the hydrogen solubility was the sole response. Specifically, we employed three different models: Support Vector Regression (SVR), Gaussian process regression (GPR), and Bayesian ridge regression (BRR). To achieve the best performance, the hyper-parameters of these models are optimized using the whale optimization algorithm (WOA). We evaluated the models using a dataset of solubility measurements in various feedstocks, and we compared their performance based on several metrics. Our results show that the WOA-SVR model tuned with WOA achieves the best performance overall, with an RMSE of 1.38 × 10− 2 and an R-squared of 0.991. These findings suggest that machine learning techniques can provide accurate predictions of hydrogen solubility in different feedstocks, which could be useful in the development of hydrogen-related technologies. Besides, the solubility of hydrogen in the four heavy oil fractions is estimated in different ranges of temperatures and pressures of 150 ◦C–350 ◦C and 1.2 MPa–10.8 MPa, respectively

Keywords: temperature, pressure variations, machine learning, oil treatment

Procedia PDF Downloads 54