Search results for: input–output analysis

Authors: Said Benkaciali, Mourad Haddadi, Abdallah Khellaf, Kacem Gairaa, Mawloud Guermoui

Abstract:

In this study, many experiments were carried out to assess the influence of the input parameters on the performance of multilayer perceptron which is one the configuration of the artificial neural networks. To estimate the daily global solar radiation on the horizontal surface, we have developed some models by using seven combinations of twelve meteorological and geographical input parameters collected from a radiometric station installed at Ghardaïa city (southern of Algeria). For selecting of best combination which provides a good accuracy, six statistical formulas (or statistical indicators) have been evaluated, such as the root mean square errors, mean absolute errors, correlation coefficient, and determination coefficient. We noted that multilayer perceptron techniques have the best performance, except when the sunshine duration parameter is not included in the input variables. The maximum of determination coefficient and correlation coefficient are equal to 98.20 and 99.11%. On the other hand, some empirical models were developed to compare their performances with those of multilayer perceptron neural networks. Results obtained show that the neural networks techniques give the best performance compared to the empirical models.

Keywords: empirical models, multilayer perceptron neural network, solar radiation, statistical formulas

Procedia PDF Downloads 341

Authors: Eleanor Nel

Abstract:

Research output is an indicator of institutional performance (and quality), resulting in increased pressure on academic institutions to perform in the research arena. Research output is further utilised to obtain research funding. Resultantly, academic institutions face significant pressure from governing bodies to provide evidence on the return for research investments. Research output has thus become a substantial discourse within institutions, mainly due to the processes linked to evaluating research output and the associated allocation of research funding. This focus on research outputs often surpasses the development of robust, widely accepted tools to additionally measure research impact at institutions. A publication writing programme, for enhancing research output, was launched at a South African university in 2011. Significant amounts of time, money, and energy have since been invested in the programme. Although participants provided feedback after each session, no formal review was conducted to evaluate the research output directly associated with the programme. Concerns in higher education about training costs, learning results, and the effect on society have increased the focus on value for money and the need to improve training, research performance, and productivity. Furthermore, universities rely on efficient and reliable monitoring and evaluation systems, in addition to the need to demonstrate accountability. While publishing does not occur immediately, achieving a return on investment from the intervention is critical. A multi-method study, guided by the New World Kirkpatrick Model (NWKM), was conducted to determine the impact of the publication writing programme for the period of 2011 to 2018. Quantitative results indicated a total of 314 academics participating in 72 workshops over the study period. To better understand the quantitative results, an open-ended questionnaire and semi-structured interviews were conducted with nine participants from a particular faculty as a convenience sample. The purpose of the research was to collect information to develop a comprehensive framework for impact evaluation that could be used to enhance the current design and delivery of the programme. The qualitative findings highlighted the critical role of a multi-stakeholder strategy in strengthening support before, during, and after a publication writing programme to improve the impact and research outputs. Furthermore, monitoring on-the-job learning is critical to ingrain the new skills academics have learned during the writing workshops and to encourage them to be accountable and empowered. The NWKM additionally provided essential pointers on how to link the results more effectively from publication writing programmes to institutional strategic objectives to improve research performance and quality, as well as what should be included in a comprehensive evaluation framework.

Keywords: evaluation, framework, impact, research output

Procedia PDF Downloads 74

Authors: Takuro Kida, Yuichi Kida

Abstract:

In this paper, it is shown a base of the new trend of algorithm mathematically that treats a historical reason of continuous discrimination in the world as well as its solution by introducing new concepts of parallel world that includes an invisible set of errors as its companion. With respect to a matrix operator-filter bank that the matrix operator-analysis-filter bank H and the matrix operator-sampling-filter bank S are given, firstly, we introduce the detail algorithm to derive the optimum matrix operator-synthesis-filter bank Z that minimizes all the worst-case measures of the matrix operator-error-signals E(ω) = F(ω) − Y(ω) between the matrix operator-input-signals F(ω) and the matrix operator-output-signals Y(ω) of the matrix operator-filter bank at the same time. Further, feedback is introduced to the above approximation theory, and it is indicated that introducing conversations with feedback do not superior automatically to the accumulation of existing knowledge of signal prediction. Secondly, the concept of category in the field of mathematics is applied to the above optimum signal approximation and is indicated that the category-based approximation theory is applied to the set-theoretic consideration of the recognition of humans. Based on this discussion, it is shown naturally why the narrow perception that tends to create isolation shows an apparent advantage in the short term and, often, why such narrow thinking becomes intimate with discriminatory action in a human group. Throughout these considerations, it is presented that, in order to abolish easy and intimate discriminatory behavior, it is important to create a parallel world of conception where we share the set of invisible error signals, including the words and the consciousness of both worlds.

Keywords: matrix filterbank, optimum signal approximation, category theory, simultaneous minimization

Procedia PDF Downloads 138

Authors: Jakkireddy Sravani

Abstract:

Introduction: The maintenance of hemodynamic stability is of pivotal importance in supratentorial surgeries. Anesthesia for supratentorial tumors requires an understanding of localized or generalized rising ICP, regulation, and maintenance of intracerebral perfusion, and avoidance of secondary systemic ischemic insults. We aimed to compare the effects of the combination of ketamine and propofol with propofol alone when used as an induction and maintenance anesthetic agent during supratentorial tumors. Methodology: This prospective, randomized, double-blinded controlled study was conducted at AIIMS Raipur after obtaining the institute Ethics Committee approval (1212/IEC-AIIMSRPR/2022 dated 15/10/2022), CTRI/2023/01/049298 registration and written informed consent. Fifty-two supratentorial tumor patients posted for craniotomy and excision were included in the study. The patients were randomized into two groups. One group received a combination of ketamine and propofol, and the other group received propofol for induction and maintenance of anesthesia. Intraoperative hemodynamic stability and quality of brain relaxation were studied in both groups. Statistical analysis and technique: An MS Excel spreadsheet program was used to code and record the data. Data analysis was done using IBM Corp SPSS v23. The independent sample "t" test was applied for continuously dispersed data when two groups were compared, the chi-square test for categorical data, and the Wilcoxon test for not normally distributed data. Results: The patients were comparable in terms of demographic profile, duration of the surgery, and intraoperative input-output status. The trends in BIS over time were similar between the two groups (p-value = 1.00). Intraoperative hemodynamics (SBP, DBP, MAP) were better maintained in the ketamine and propofol combination group during induction and maintenance (p-value < 0.01). The quality of brain relaxation was comparable between the two groups (p-value = 0.364). Conclusion: Ketamine and propofol combination for the induction and maintenance of anesthesia was associated with superior hemodynamic stability, required fewer vasopressors during excision of supratentorial tumors, provided adequate brain relaxation, and some degree of neuroprotection compared to propofol alone.

Keywords: supratentorial tumors, hemodynamic stability, brain relaxation, ketamine, propofol

Procedia PDF Downloads 19

Authors: Kien Vu, Jien Min Soh, Mohamed Jahangir Abubacker, Piyawut Pattamanon, Soojin Lee, Suvro Banerjee

Abstract:

Recent advances in Generative Artificial Intelligence (GenAI), in particular Large Language Models (LLMs) have shown promise to disrupt multiple industries at scale. However, LLMs also present unique challenges, notably, these so-called "hallucination" which is the generation of outputs that are not grounded in the input data that hinders its adoption into production. Common practice to mitigate hallucination problem is utilizing Retrieval Agmented Generation (RAG) system to ground LLMs'response to ground truth. RAG converts the grounding documents into embeddings, retrieve the relevant parts with vector similarity between user's query and documents, then generates a response that is not only based on its pre-trained knowledge but also on the specific information from the retrieved documents. However, the RAG system is not suitable for tabular data and subsequent data analysis tasks due to multiple reasons such as information loss, data format, and retrieval mechanism. In this study, we have explored a novel methodology that combines planning-and-execution and code generation agents to enhance LLMs' data analysis capabilities. The approach enables LLMs to autonomously dissect a complex analytical task into simpler sub-tasks and requirements, then convert them into executable segments of code. In the final step, it generates the complete response from output of the executed code. When deployed beta version on DataSense, the property insight tool of PropertyGuru, the approach yielded promising results, as it was able to provide market insights and data visualization needs with high accuracy and extensive coverage by abstracting the complexities for real-estate agents and developers from non-programming background. In essence, the methodology not only refines the analytical process but also serves as a strategic tool for real estate professionals, aiding in market understanding and enhancement without the need for programming skills. The implication extends beyond immediate analytics, paving the way for a new era in the real estate industry characterized by efficiency and advanced data utilization.

Keywords: large language model, reasoning, planning and execution, code generation, natural language processing, prompt engineering, data analysis, real estate, data sense, PropertyGuru

Procedia PDF Downloads 84

Authors: José M Martín-Moreno, Rafaela Pérez, Jesús Ruiz

Abstract:

In this paper we use a small open economy Dynamic Stochastic General Equilibrium Model (DSGE) for the Spanish economy to search for a deeper characterization of the determinants of Spain’s macroeconomic fluctuations throughout the period 1970-2008. In order to do this, we distinguish between tradable and non-tradable goods to take into account the fact that the presence of non-tradable goods in this economy is one of the largest in the world. We estimate a DSGE model with supply and demand shocks (sectorial productivity, public spending, international real interest rate and preferences) using Kalman Filter techniques. We find the following results. First of all, our variance decomposition analysis suggests that 1) the preference shock basically accounts for private consumption volatility, 2) the idiosyncratic productivity shock accounts for non-tradable output volatility, and 3) the sectorial productivity shock along with the international interest rate both greatly account for tradable output. Secondly, the model closely replicates the time path observed in the data for the Spanish economy and finally, the model captures the main cyclical qualitative features of this economy reasonably well.

Keywords: business cycle, DSGE models, Kalman filter estimation, small open economy

Procedia PDF Downloads 414

Authors: Jiawen Wang, Qijun Chen

Abstract:

The performance of most machine-learning methods for image inpainting depends on the quantity and quality of the training samples. However, it is very expensive or even impossible to obtain a great number of training samples in many scenarios. In this paper, an image inpainting model based on a generative adversary network (GAN) is constructed for the cases when the number of training samples is small. Firstly, a feature extraction network (F-net) is incorporated into the GAN network to utilize the available information of the inpainting image. The weighted sum of the extracted feature and the random noise acts as the input to the generative network (G-net). The proposed network can be trained well even when the sample size is very small. Secondly, in the phase of the completion for each damaged image, a genetic algorithm is designed to search an optimized noise input for G-net; based on this optimized input, the parameters of the G-net and F-net are further learned (Once the completion for a certain damaged image ends, the parameters restore to its original values obtained in the training phase) to generate an image patch that not only can fill the missing part of the damaged image smoothly but also has visual semantics.

Keywords: image inpainting, generative adversary nets, genetic algorithm, small-sample size

Procedia PDF Downloads 126

Authors: Edison A. Bonifaz

Abstract:

In this work, a numerical procedure is proposed to design dense multi-material structures using the Directed Energy Deposition (DED) process. A thermo-mechanical finite element model to predict thermal cycles and residual stresses is presented. A numerical layer build-up procedure coupled with a moving heat flux was constructed to minimize strains and residual stresses that result in the multi-layer deposition of an AISI 316 austenitic steel on an AISI 304 austenitic steel substrate. To simulate the DED process, the automated interface of the ABAQUS AM module was used to define element activation and heat input event data as a function of time and position. Of this manner, the construction of ABAQUS user-defined subroutines was not necessary. Thermal cycles and thermally induced stresses created during the multi-layer deposition metal AM pool crystallization were predicted and validated. Results were analyzed in three independent metal layers of three different experiments. The one-way heat and material deposition toolpath used in the analysis was created with a MatLab path script. An optimal combination of feedstock and heat input printing parameters suitable for fabricating multi-material dense structures in the directed energy deposition metal AM process was established. At constant power, it can be concluded that the lower the heat input, the lower the peak temperatures and residual stresses. It means that from a design point of view, the one-way heat and material deposition processing toolpath with the higher welding speed should be selected.

Keywords: event series, thermal cycles, residual stresses, multi-pass welding, abaqus am modeler

Procedia PDF Downloads 66

Authors: B. Manoj Kumar, C. Malavika, E. S. Kannan

Abstract:

The objective of this study is to investigate the switching behavior of two vertically aligned memristors connected by a shared top electrode, a configuration that significantly deviates from the conventional single oxide layer sandwiched between two electrodes. The device is fabricated by bridging copper electrodes with mechanically exfoliated van der Waals metal (specifically tantalum disulfide and tantalum diselenide). The device demonstrates threshold-switching behavior in its I-V characteristics. When the input voltage signal is ramped with voltages below the threshold, the output current shows spiking behavior, resembling integrated and firing actions without extra circuitry. We also investigated the self-reset behavior of the device. Using a continuous constant voltage bias, we activated the device to the firing state. After removing the bias and reapplying it shortly afterward, the current returned to its initial state. This indicates that the device can spontaneously return to its resting state. The outcome of this investigation offers a fresh perspective on memristor-based device design and an efficient method to construct hardware for neuromorphic computing systems.

Keywords: integrated and firing, memristor, spiking behavior, threshold switching

Procedia PDF Downloads 58

Authors: Sungsik Jo, Hyeonwoo Kim, Iksu Choi, Hunmo Kim

Abstract:

In the SHP, LVDT sensor is for detecting the length changes of the EHA output, and the thrust of the EHA is controlled by the pressure sensor. Sensor is possible to cause hardware fault by internal problem or external disturbance. The EHA of SHP is able to be uncontrollable due to control by feedback from uncertain information, on this paper; the sliding mode observer algorithm estimates the original sensor output information in permanent sensor fault. The proposed algorithm shows performance to recovery fault of disconnection and short circuit basically, also the algorithm detect various of sensor fault mode.

Keywords: smart hybrid powerpack (SHP), electro hydraulic actuator (EHA), permanent sensor fault tolerance, sliding mode observer (SMO), graphic user interface (GUI)

Procedia PDF Downloads 545

Authors: A. boursali, A. Guen Bouazza, M. Khaouani, Z. Kourdi, B. Bouazza

Abstract:

This paper presents the design, development and characterization of the devices simulation for X-Band Radar applications. The effect of an InAlN/GaN structure on the RF performance High Electron Mobility Transistor (HEMT) device. Systematic investigations on the small signal as well as power performance as functions of the drain biases are presented. Were improved for X-band applications. The Power Added Efficiency (PAE) was achieved over 23% for X-band. The developed devices combine two InAlN/GaN HEMTs of 30nm gate periphery and exhibited the output power of over 50W. An InAlN/GaN HEMT with 30nm gate periphery was developed and exhibited the output power of over 120W.

Keywords: InAlN/GaN, HEMT, RF analyses, PAE, X-Band, radar

Procedia PDF Downloads 554

Authors: L. Rakesh, T. Y. Heblekar

Abstract:

This study entails the development and optimization of a mathematical model for a floating drum biogas reactor from first principles using thermal and empirical considerations. The model was derived on the basis of mass conservation, lumped mass heat transfer formulations and empirical biogas formation laws. The treatment leads to a system of coupled nonlinear ordinary differential equations whose solution mapped four-time independent controllable parameters to five output variables which adequately serve to describe the reactor performance. These equations were solved numerically using fourth order Runge-Kutta method for a range of input parameter values. Using the data so obtained an Artificial Neural Network with a single hidden layer was trained using Levenberg-Marquardt Damped Least Squares (DLS) algorithm. This network was then fine-tuned for optimal mapping by varying hidden layer size. This fast forward model was then employed as a health score generator in the Bacterial Foraging Optimization code. The optimal operating state of the simplified Biogas reactor was thus obtained.

Keywords: biogas, floating drum reactor, neural network model, optimization

Procedia PDF Downloads 141

Authors: Yuri V. Kim

Abstract:

This article presents a new approach to the Functional Testing of Space Systems (SS). It can be considered as a generic test and used for a wide class of SS that from the point of view of System Dynamics and Control may be described by the ordinary differential equations. Suggested methodology is based on using semi-natural experiment- laboratory stand that doesn’t require complicated, precise and expensive technological control-verification equipment. However, it allows for testing system as a whole totally assembled unit during Assembling, Integration and Testing (AIT) activities, involving system hardware (HW) and software (SW). The test physically activates system input (sensors) and output (actuators) and requires recording their outputs in real time. The data is then inserted in laboratory PC where it is post-experiment processed by Matlab/Simulink Identification Toolbox. It allows for estimating system dynamics in form of estimation of system differential equations by the experimental way and comparing them with expected mathematical model prematurely verified by mathematical simulation during the design process.

Keywords: system dynamics, space system ground tests and space qualification, system dynamics identification, satellite attitude control, assembling, integration and testing

Procedia PDF Downloads 160

Authors: Mohammad Mojtahedpoor

Abstract:

In this paper, it has been studied the method of optimal design of the supersonic nozzle. It could make viscous axisymmetric nozzles that the quality of their outlet flow is quite desired. In this method, it is optimized the divergent nozzle, at first. The initial divergent nozzle contour is designed through the method of characteristics and adding a suitable boundary layer to the inviscid contour. After that, it is made a proper grid and then simulated flow by the numerical solution and AUSM+ method by using the operation boundary condition. At the end, solution outputs are investigated and optimized. The numerical method has been validated with experimental results. Also, in order to evaluate the effectiveness of the present method, the nozzles compared with the previous studies. The comparisons show that the nozzles obtained through this method are sufficiently better in some conditions, such as the flow uniformity, size of the boundary layer, and obtained an axial length of the nozzle. Designing the convergent nozzle part affects by flow uniformity through changing its axial length and input diameter. The results show that increasing the length of the convergent part improves the output flow uniformity.

Keywords: nozzle, supersonic, optimization, characteristic method, CFD

Procedia PDF Downloads 196

Authors: Mokrani Mohamed Amine

Abstract:

In this paper, we have implemented successive interference cancellation algorithms in the 5G downlink. We have calculated the maximum throughput in Frequency Division Duplex (FDD) mode in the downlink, where we have obtained a value equal to 836932 b/ms. The transmitter is of type Multiple Input Multiple Output (MIMO) with eight transmitting and receiving antennas. Each antenna among eight transmits simultaneously a data rate of 104616 b/ms that contains the binary messages of the three users; in this case, the Cyclic Redundancy Check CRC is negligible, and the MIMO category is the spatial diversity. The technology used for this is called Non-Orthogonal Multiple Access (NOMA) with a Quadrature Phase Shift Keying (QPSK) modulation. The transmission is done in a Rayleigh fading channel with the presence of obstacles. The MIMO Successive Interference Cancellation (SIC) receiver with two transmitting and receiving antennas recovers its binary message without errors for certain values of transmission power such as 50 dBm, with 0.054485% errors when the transmitted power is 20dBm and with 0.00286763% errors for a transmitted power of 32 dBm(in the case of user 1) as well as with 0.0114705% errors when the transmitted power is 20 dBm also with 0.00286763% errors for a power of 24 dBm(in the case of user2) by applying the steps involved in SIC.

Keywords: 5G, NOMA, QPSK, TBS, LDPC, SIC, capacity

Procedia PDF Downloads 99

Authors: Sher Muhammad, Mirza Muhammad Waqar

Abstract:

It is necessary to monitor and identify mangroves types and spatial extent near coastal areas because it plays an important role in coastal ecosystem and environmental protection. This research aims at identifying and mapping mangroves types along Karachi coast ranging from 24.79 to 24.85 degree in latitude and 66.91 to 66.97 degree in longitude using hyperspectral remote sensing data and techniques. Image acquired during February, 2012 through Hyperion sensor have been used for this research. Image preprocessing includes geometric and radiometric correction followed by Minimum Noise Fraction (MNF) and Pixel Purity Index (PPI). The output of MNF and PPI has been analyzed by visualizing it in n-dimensions for end-member extraction. Well-distributed clusters on the n-dimensional scatter plot have been selected with the region of interest (ROI) tool as end members. These end members have been used as an input for classification techniques applied to identify and map mangroves species including Spectral Angle Mapper (SAM), Spectral Feature Fitting (SFF), and Spectral Information Diversion (SID). Only two types of mangroves namely Avicennia Marina (white mangroves) and Avicennia Germinans (black mangroves) have been observed throughout the study area.

Keywords: mangrove, hyperspectral, hyperion, SAM, SFF, SID

Procedia PDF Downloads 361

Authors: S. K. Ashiquer Rahman

Abstract:

Recently, oil has become more influential in almost every economic sector as a key material. As can be seen from the news, when there are some changes in an oil price or OPEC announces a new strategy, its effect spreads to every part of the economy directly and indirectly. That’s a reason why people always observe the oil price and try to forecast the changes of it. The most important factor affecting the price is its supply which is determined by the number of wildcats drilled. Therefore, a study about the number of wellheads and other economic variables may give us some understanding of the mechanism indicated by the amount of oil supplies. In this paper, we will consider a relationship between the number of wellheads and three key factors: the price of the wellhead, domestic output, and GNP constant dollars. We also add trend variables in the models because the consumption of oil varies from time to time. Moreover, this paper will use an econometrics method to estimate parameters in the model, apply some tests to verify the result we acquire, and then conclude the model.

Keywords: price, domestic output, GNP, trend variable, wildcat activity

Procedia PDF Downloads 59

Authors: Payel Datta, Abhishek Das, Abhishek Roychoudhury, Dhiman Chattopadhyay, Tanushyam Chattopadhyay

Abstract:

Machine learning (ML) and deep learning (DL) is most predominantly used in image/video processing, natural language processing (NLP), audio and speech recognition but not that much used in system performance evaluation. In this paper, authors are going to describe the architecture of an abstraction layer constructed using ML/DL to detect the system failure. This proposed system is used to detect the system failure by evaluating the performance metrics of an IoT service deployment under constrained infrastructure environment. This system has been tested on the manually annotated data set containing different metrics of the system, like number of threads, throughput, average response time, CPU usage, memory usage, network input/output captured in different hardware environments like edge (atom based gateway) and cloud (AWS EC2). The main challenge of developing such system is that the accuracy of classification should be 100% as the error in the system has an impact on the degradation of the service performance and thus consequently affect the reliability and high availability which is mandatory for an IoT system. Proposed ML/DL classifiers work with 100% accuracy for the data set of nearly 4,000 samples captured within the organization.

Keywords: machine learning, system performance, performance metrics, IoT, edge

Procedia PDF Downloads 192

Authors: Hatem Mrad, Mohamed Bouazara, Fouad Erchiqui

Abstract:

Fatigue, is considered as one of the main cause of mechanical properties degradation of mechanical parts. Probability and reliability methods are appropriate for fatigue analysis using uncertainties that exist in fatigue material or process parameters. Current work deals with the study of the effect of the number and counting Rainflow cycle on fatigue lifetime (cumulative damage) of an upper arm of the vehicle suspension system. The major part of the fatigue damage induced in suspension arm is caused by two main classes of parameters. The first is related to the materials properties and the second is the road excitation or the applied force of the passenger’s number. Therefore, Young's modulus and road excitation are selected as input parameters to conduct repetitive simulations by Monte Carlo (MC) algorithm. Latin hypercube sampling method is used to generate these parameters. Response surface method is established according to fatigue lifetime of each combination of input parameters according to strain-life method. A PYTHON script was developed to automatize finite element simulations of the upper arm according to a design of experiments.

Keywords: fatigue, monte carlo, rainflow cycle, response surface, suspension system

Procedia PDF Downloads 253

Authors: Shreya Goyal

Abstract:

The study aims to build user-friendly software to understand patient arrival patterns and compute the number of potential patients who will visit a particular health facility for a given period by using a machine learning algorithm. The underlying machine learning algorithm used in this study is the Support Vector Machine (SVM). Accurate prediction of patient arrival allows hospitals to operate more effectively, providing timely and efficient care while optimizing resources and improving patient experience. It allows for better allocation of staff, equipment, and other resources. If there's a projected surge in patients, additional staff or resources can be allocated to handle the influx, preventing bottlenecks or delays in care. Understanding patient arrival patterns can also help streamline processes to minimize waiting times for patients and ensure timely access to care for patients in need. Another big advantage of using this software is adhering to strict data protection regulations such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States as the hospital will not have to share the data with any third party or upload it to the cloud because the software can read data locally from the machine. The data needs to be arranged in. a particular format and the software will be able to read the data and provide meaningful output. Using software that operates locally can facilitate compliance with these regulations by minimizing data exposure. Keeping patient data within the hospital's local systems reduces the risk of unauthorized access or breaches associated with transmitting data over networks or storing it in external servers. This can help maintain the confidentiality and integrity of sensitive patient information. Historical patient data is used in this study. The input variables used to train the model include patient age, time of day, day of the week, seasonal variations, and local events. The algorithm uses a Supervised learning method to optimize the objective function and find the global minima. The algorithm stores the values of the local minima after each iteration and at the end compares all the local minima to find the global minima. The strength of this study is the transfer function used to calculate the number of patients. The model has an output accuracy of >95%. The method proposed in this study could be used for better management planning of personnel and medical resources.

Keywords: machine learning, SVM, HIPAA, data

Procedia PDF Downloads 63

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

Abstract:

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

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

Procedia PDF Downloads 139

Authors: Jianyong Xue, Olivier L. Georgeon, Salima Hassas

Abstract:

During the initial phase of cognitive development, infants exhibit amazing abilities to generate novel behaviors in unfamiliar situations, and explore actively to learn the best while lacking extrinsic rewards from the environment. These abilities set them apart from even the most advanced autonomous robots. This work seeks to contribute to understand and replicate some of these abilities. We propose the Bottom-up hiErarchical sequential Learning algorithm with Constructivist pAradigm (BEL-CA) to design agents capable of learning autonomously and continuously through interactions. The algorithm implements no assumption about the semantics of input and output data. It does not rely upon a model of the world given a priori in the form of a set of states and transitions as well. Besides, we propose a toolkit to analyze the learning process at run time called GAIT (Generating and Analyzing Interaction Traces). We use GAIT to report and explain the detailed learning process and the structured behaviors that the agent has learned on each decision making. We report an experiment in which the agent learned to successfully interact with its environment and to avoid unfavorable interactions using regularities discovered through interaction.

Keywords: cognitive development, constructivist learning, hierarchical sequential learning, self-adaptation

Procedia PDF Downloads 177

Authors: Anthony John Walker, Glen Bright

Abstract:

The challenge faced by manufactures, when producing custom products, is that each product needs exact components. This can cause work-in-process instability due to component matching constraints imposed on assembly cells. Clearing type flow control policies have been used extensively in mediating server access between multiple arrival processes. Although the stability and performance of clearing policies has been well formulated and studied in the literature, the growth in arrival to departure sequence disorder for each arriving job, across a serving resource, is still an area for further analysis. In this paper, a closed form industrial model has been formulated that characterizes arrival-to-departure sequence disorder through stable manufacturing systems under clearing type flow control policy. Specifically addressed are the effects of sequence disorder imposed on a downstream assembly cell in terms of work-in-process instability induced through component matching constraints. Results from a simulated manufacturing system show that steady state average sequence disorder in parallel upstream processing cells can be balanced in order to decrease downstream assembly system instability. Simulation results also show that the closed form model accurately describes the growth and limiting behavior of average sequence disorder between parts arriving and departing from a manufacturing system flow controlled via clearing policy.

Keywords: assembly system constraint, custom products, discrete sequence disorder, flow control

Procedia PDF Downloads 174

Authors: Fawaz S. Al-Anzi, Dia AbuZeina

Abstract:

Speech recognition is of an important contribution in promoting new technologies in human computer interaction. Today, there is a growing need to employ speech technology in daily life and business activities. However, speech recognition is a challenging task that requires different stages before obtaining the desired output. Among automatic speech recognition (ASR) components is the feature extraction process, which parameterizes the speech signal to produce the corresponding feature vectors. Feature extraction process aims at approximating the linguistic content that is conveyed by the input speech signal. In speech processing field, there are several methods to extract speech features, however, Mel Frequency Cepstral Coefficients (MFCC) is the popular technique. It has been long observed that the MFCC is dominantly used in the well-known recognizers such as the Carnegie Mellon University (CMU) Sphinx and the Markov Model Toolkit (HTK). Hence, this paper focuses on the MFCC method as the standard choice to identify the different speech segments in order to obtain the language phonemes for further training and decoding steps. Due to MFCC good performance, the previous studies show that the MFCC dominates the Arabic ASR research. In this paper, we demonstrate MFCC as well as the intermediate steps that are performed to get these coefficients using the HTK toolkit.

Keywords: speech recognition, acoustic features, mel frequency, cepstral coefficients

Procedia PDF Downloads 256

Authors: Mazyar Yosofi, Olivier Kerbrat, Pascal Mognol

Abstract:

Life cycle assessment of additive manufacturing processes has evolved significantly since these past years. A lot of existing studies mainly focused on energy consumption. Nowadays, new methodologies of life cycle inventory acquisition came through the literature and help manufacturers to take into account all the input and output flows during the manufacturing step of the life cycle of products. Indeed, the environmental analysis of the phenomena that occur during the manufacturing step of additive manufacturing processes is going to be well known. Now it becomes possible to count and measure accurately all the inventory data during the manufacturing step. Optimization of the environmental performances of processes can now be considered. Environmental performance improvement can be made by varying process parameters. However, a lot of these parameters (such as manufacturing speed, the power of the energy source, quantity of support materials) affect directly the mechanical properties, surface finish and the dimensional accuracy of a functional part. This study aims to improve the environmental performance of an additive manufacturing process without deterioration of the part quality. For that purpose, the authors have developed a generic method that has been applied on multiple parts made by additive manufacturing processes. First, a complete analysis of the process parameters is made in order to identify which parameters affect only the environmental performances of the process. Then, multiple parts are manufactured by varying the identified parameters. The aim of the second step is to find the optimum value of the parameters that decrease significantly the environmental impact of the process and keep the part quality as desired. Finally, a comparison between the part made by initials parameters and changed parameters is made. In this study, the major finding claims by authors is to reduce the environmental impact of an additive manufacturing process while respecting the three quality criterion of parts, mechanical properties, dimensional accuracy and surface roughness. Now that additive manufacturing processes can be seen as mature from a technical point of view, environmental improvement of these processes can be considered while respecting the part properties. The first part of this study presents the methodology applied to multiple academic parts. Then, the validity of the methodology is demonstrated on functional parts.

Keywords: additive manufacturing, environmental impact, environmental improvement, mechanical properties

Procedia PDF Downloads 282

Authors: Aminu Yakubu Umar

Abstract:

X-ray is the major contributor to the effective dose of both the patient and the personnel. Because of the radiological risks involved, it is usually recommended that dose to patient from X-ray be kept as low as reasonably achievable (ALARA) with adequate image quality. The implementation of quality assurance in diagnostic radiology can help greatly in achieving that, as it is a technique designed to reduce X-ray doses to patients undergoing radiological examination. In this study, quality control was carried out in six hospitals, which involved KVp test, evaluation of total filtration, test for constancy of radiation output, and check for mA linearity. Equipment used include KVp meter, Rad-check meter, aluminum sheets (0.1–1.0 mm) etc. The results of this study indicate that, the age of the X-ray machines in the hospitals ranges from 3-13 years, GHI and GH2 being the oldest and FMC being the newest. In the evaluation of total filtration, the HVL of the X-ray machines in the hospitals varied, ranging from 2.3-5.2 mm. The HVL was found to be highest in AHC (5.2 mm), while it was lowest in GH3 (2.3 mm). All HVL measurements were done at 80 KVp. The variation in voltage accuracy in the hospitals ranges from 0.3%-127.5%. It was only in GH1 that the % variation was below the allowed limit. The test for constancy of radiation output showed that, the coefficient of variation ranges from 0.005–0.550. In GH3, FMC and AHC, the coefficient of linearity were less than the allowed limit, while in GH1, GH2 and GH4 the coefficient of linearity had exceeded the allowed limit. As regard to mA linearity, FMC and AHC had their coefficients of linearity as 0.12 and 0.10 respectively, which were within the accepted limit, while GH1, GH3 and GH4 had their coefficients as 0.16, 0.69 and 0.98 respectively, which exceeded the allowed limit.

Keywords: radiation, X-ray output, quality control, half-value layer, mA linearity, KVp variation

Procedia PDF Downloads 608

Authors: S. Aisyah Azizan, M. Syafiq Azmi, Yuki Harada, Yoshinobu Maeda, Takaomi Matsutani

Abstract:

We introduced an all-optical multi-casting characteristics with wavelength conversion based on a novel all-optical triode using negative feedback semiconductor optical amplifier. This study was demonstrated with a transfer speed of 10 Gb/s to a non-return zero 231-1 pseudorandom bit sequence system. This multi-wavelength converter device can simultaneously provide three channels of output signal with the support of non-inverted and inverted conversion. We studied that an all-optical multi-casting and wavelength conversion accomplishing cross gain modulation is effective in a semiconductor optical amplifier which is effective to provide an inverted conversion thus negative feedback. The relationship of received power of back to back signal and output signals with wavelength 1535 nm, 1540 nm, 1545 nm, 1550 nm, and 1555 nm with bit error rate was investigated. It was reported that the output signal wavelengths were successfully converted and modulated with a power penalty of less than 8.7 dB, which the highest is 8.6 dB while the lowest is 4.4 dB. It was proved that all-optical multi-casting and wavelength conversion using an optical triode with a negative feedback by three channels at the same time at a speed of 10 Gb/s is a promising device for the new wavelength conversion technology.

Keywords: cross gain modulation, multicasting, negative feedback optical amplifier, semiconductor optical amplifier

Procedia PDF Downloads 679

Authors: Zhaojun Wang, Zongdi Sun, Zhiyuan Liu

Abstract:

First of all, the carbon trading price and trading volume in Shanghai are transformed by Fourier transform, and the frequency response diagram is obtained. Then, the frequency response diagram is analyzed and the Blackman filter is designed. The Blackman filter is used to filter, and the carbon trading time domain and frequency response diagram are obtained. After wavelet analysis, the carbon trading data were processed; respectively, we got the average value for each 5 days, 10 days, 20 days, 30 days, and 60 days. Finally, the data are used as input of the Back Propagation Neural Network model for prediction.

Keywords: Shanghai carbon trading, carbon trading price, carbon trading volume, wavelet analysis, BP neural network model

Procedia PDF Downloads 386

Authors: Smita Pareek, Ratna Dahiya

Abstract:

The power generated by solar photovoltaic (PV) module depends on surrounding irradiance, temperature, shading conditions, and shading pattern. This paper presents a simulation of photovoltaic module using Matlab/Simulink. PV Array is also simulated by series and parallel connections of modules and their characteristics curves are given. Further PV module topology/configuration are proposed for 5.5kW inverter available in the literature. Shading of a PV array either complete or partial can have a significant impact on its power output and energy yield; therefore, the simulated model characteristics curves (I-V and P-V) are drawn for uniform shading conditions (USC) and then output power, voltage and current are calculated for variation in insolation for shading conditions. Additionally the characteristics curves are also given for a predetermined shadowing condition.

Keywords: array, series, parallel, photovoltaic, partial shading

Procedia PDF Downloads 560

Authors: Liang-Hsuan Chen, Sheng-Shing Nien

Abstract:

This study aims to develop approaches to formulate intuitionistic fuzzy regression (IFR) models for many decision-making applications in the fuzzy environments using intuitionistic fuzzy observations. Intuitionistic fuzzy numbers (IFNs) are used to characterize the fuzzy input and output variables in the IFR formulation processes. A mathematical programming problem (MPP) is built up to optimally determine the IFR parameters. Each parameter in the MPP is defined as a couple of alternative numerical variables with opposite signs, and an intuitionistic fuzzy error term is added to the MPP to characterize the uncertainty of the model. The IFR model is formulated based on the distance measure to minimize the total distance errors between estimated and observed intuitionistic fuzzy responses in the MPP resolution processes. The proposed approaches are simple/efficient in the formulation/resolution processes, in which the sign of parameters can be determined so that the problem to predetermine the sign of parameters is avoided. Furthermore, the proposed approach has the advantage that the spread of the predicted IFN response will not be over-increased, since the parameters in the established IFR model are crisp. The performance of the obtained models is evaluated and compared with the existing approaches.

Keywords: fuzzy sets, intuitionistic fuzzy number, intuitionistic fuzzy regression, mathematical programming method

Procedia PDF Downloads 136