Search results for: machine tools

Authors: N. Yogal, C. Lehrmann

Abstract:

The use of Permanent magnet (PM) is increasing in the Permanent magnet synchronous machines (PMSM) to fulfill the requirement of high efficiency machines in modern industry. PMSM is widely used in industrial application, wind power plant and automotive industry. Since the PMSM are used in different environment condition, the long-term effect of NdFeB-based magnets at high temperatures and corrosion behavior has to be studied due to irreversible loss of magnetic properties. In this paper, the effect of magnetic properties due to corrosion and increasing temperature in the climatic chamber has been presented. The magnetic moment and magnetic field of the magnet were studied experimentally.

Keywords: permanent magnet (PM), NdFeB, corrosion behavior, temperature effect, Permanent magnet synchronous machine (PMSM)

Procedia PDF Downloads 381

Authors: Maria Vueba, Tchilissila A. Simoes

Abstract:

Angola has a deficient health system characterized by reduced human and material resources. Nurses are the main actors combating different types of diseases simultaneously dealing with a lack of essentials tools and means. In this study, we aimed to assess the organizational commitment and job satisfaction of 51 health professionals from a maternity ward in Lubango, Angola. Participants completed the Organizational Commitment Questionnaire and the Job Satisfaction Scale and demonstrated a strong commitment towards the maternal facility, despite the majority of them were not satisfied with their work. Moreover, the gender and years of service seemed to not influence the level of commitment and satisfaction among the professionals. These results show the need for organizational restructuration (i.e., wages, career progression, supervision) to increase job satisfaction in this institution.

Keywords: Africa, health professionals, organizational commitment, work satisfaction

Procedia PDF Downloads 144

Authors: Santi Mutiara Asih, Sinta Kemala Asih

Abstract:

Along with the development of tourism in Indonesia, which is increasingly a lot of domestic and foreign public interest in sharia tourism, the Indonesian government is currently developing the program. It was seen that this program would have a good impact, especially for Indonesian tourism. So it is necessary to develop appropriate marketing strategies. Then to develop tourism prospects sharia government could use such a marketing strategy, for instance, marketing mix and Segmenting, Targeting, and Positioning (STP). The marketing mix is a set of marketing tools used by a state or a company to continue achieving its marketing objectives in target market. STP is the most important initial step in identifying customer value. In such away, it is expected from the use of this strategy could make sharia tourism as a market leader in the field of tourism in Indonesia, it also could attract more tourists to visit and increase economic returns.

Keywords: STP, marketing mix, market leader, sharia tourism

Procedia PDF Downloads 745

Authors: Amir Mohtarami, Hadi Kandjani

Abstract:

The amount of business-critical information in enterprises is growing at an extraordinary rate, and the ability to catalog that information and properly protect it using traditional security mechanisms is not keeping pace. Alongside the Information Technology (IT), information security needs a holistic view in enterprise. In other words, a comprehensive architectural approach is required, focusing on the information itself, understanding what the data are, who owns it, and which business and regulatory policies should be applied to the information. Enterprise Architecture Frameworks provide useful tools to grasp different dimensions of IT in organizations. Usually this is done by the layered views on IT architecture, but not requisite security attention has been held in this frameworks. In this paper, after a brief look at the Enterprise Architecture (EA), we discuss the issue of security in the overall enterprise IT architecture. Due to the increasing importance of security, a rigorous EA program in an enterprise should be able to consider security architecture as an integral part of its processes and gives a visible roadmap and blueprint for this aim.

Keywords: enterprise architecture, architecture framework, security architecture, information systems

Procedia PDF Downloads 692

Authors: Troels Bo Jørgensen, Preben Hagh Strunge Holm, Henrik Gordon Petersen, Norbert Kruger

Abstract:

This paper presents a simulation framework for using machine learning techniques to determine robust robotic motions for handling deformable objects. The main focus is on applications in the meat sector, which mainly handle three-dimensional objects. In order to optimize the robotic handling, the robot motions have been parameterized in terms of grasp points, robot trajectory and robot speed. The motions are evaluated based on a dynamic simulation environment for robotic control of deformable objects. The evaluation indicates certain parameter setups, which produce robust motions in the simulated environment, and based on a visual analysis indicate satisfactory solutions for a real world system.

Keywords: deformable objects, robotic manipulation, simulation, real world system

Procedia PDF Downloads 269

Authors: Milica Lilic, Marina Rosales Martínez

Abstract:

Academic research cannot be oblivious to social problems and needs, so projects that have the capacity for transformation and impact should have the opportunity to go beyond the University circles and bring benefit to society. Apart from patents and R&D research contracts, this opportunity can be achieved through entrepreneurship as one of the most direct tools to turn knowledge into a tangible product. Thus, as an example of good practices, it is intended to analyze the case of an institutional entrepreneurship program carried out at the University of Seville, aimed at researchers interested in assessing the business opportunity of their research and expanding their knowledge on procedures for the commercialization of technologies used at academic projects. The program is based on three pillars: training, teamwork sessions and networking. The training includes aspects such as product-client fit, technical-scientific and economic-financial feasibility of a spin-off, institutional organization and decision making, public and private fundraising, and making the spin-off visible in the business world (social networks, key contacts, corporate image and ethical principles). On the other hand, the teamwork sessions are guided by a mentor and aimed at identifying research results with potential, clarifying financial needs and procedures to obtain the necessary resources for the consolidation of the spin-off. This part of the program is considered to be crucial in order for the participants to convert their academic findings into a business model. Finally, the networking part is oriented to workshops about the digital transformation of a project, the accurate communication of the product or service a spin-off offers to society and the development of transferable skills necessary for managing a business. This blended program results in the final stage where each team, through an elevator pitch format, presents their research turned into a business model to an experienced jury. The awarded teams get a starting capital for their enterprise and enjoy the opportunity of formally consolidating their spin-off company at the University. Studying the results of the program, it has been shown that many researchers have basic or no knowledge of entrepreneurship skills and different ways to turn their research results into a business model with a direct impact on society. Therefore, the described program has been used as an example to highlight the importance of knowledge transfer at the University and the role that this institution should have in providing the tools to promote entrepreneurship within it. Keeping in mind that the University is defined by three main activities (teaching, research and knowledge transfer), it is safe to conclude that the latter, and the entrepreneurship as an expression of it, is crucial in order for the other two to comply with their purpose.

Keywords: good practice, knowledge transfer, a spin-off company, university

Procedia PDF Downloads 127

Authors: Danilo López, Nelson Vera, Luis Pedraza

Abstract:

This paper analyzes fundamental ideas and concepts related to neural networks, which provide the reader a theoretical explanation of Long Short-Term Memory (LSTM) networks operation classified as Deep Learning Systems, and to explicitly present the mathematical development of Backward Pass equations of the LSTM network model. This mathematical modeling associated with software development will provide the necessary tools to develop an intelligent system capable of predicting the behavior of licensed users in wireless cognitive radio networks.

Keywords: neural networks, multilayer perceptron, long short-term memory, recurrent neuronal network, mathematical analysis

Procedia PDF Downloads 398

Authors: Lely A. Luengas, Pedro R. Vizcaya, Giovanni Sánchez

Abstract:

In this paper, a methodology is presented to obtain the Static Alignment Model for any transtibial amputee person. The proposed methodology starts from experimental data collected on the Hospital Militar Central, Bogotá, Colombia. The effects of transtibial prosthesis malalignment on amputees were measured in terms of joint angles, center of pressure (COP) and weight distribution. Some statistical tools are used to obtain the model parameters. Mathematical predictive models of prosthetic alignment were created. The proposed models are validated in amputees and finding promising results for the prosthesis Static Alignment. Static alignment process is unique to each subject; nevertheless the proposed methodology can be used in each transtibial amputee.

Keywords: information theory, prediction model, prosthetic alignment, transtibial prosthesis

Procedia PDF Downloads 240

Authors: Taha Ahmed Özbey, Sedat Nazlıbilek, Alparslan Çağrı Yapıcı

Abstract:

Combline cavity filters have gained significant attention in recent years due to their exceptional narrowband characteristics, high unloaded Q, remarkable out-of-band rejection, and versatile post-manufacturing tuning capabilities. These filters play a vital role in various wireless communication systems, radar applications, and other advanced technologies where stringent frequency selectivity and superior performance are required. This paper represents combined cavity filter design and implementation by coupling matrix synthesis. Limited filter length, 50 dB out-of-band rejection, and agile design were aimed. To do so, CAD tools and intuitive methods were used.

Keywords: cavity, band pass filter, cavity combline filter, coupling matrix synthesis

Procedia PDF Downloads 60

Authors: Rawan K. Al-Duaij, Salem A. Al-Salem

Abstract:

Projects, the unique and temporary process of achieving a set of requirements have always been challenging; Planning the schedule and budget, managing the resources and risks are mostly driven by a similar past experience or the technical consultations of experts in the matter. With that complexity of Projects in Scope, Time, and execution environment, Adjustment Orders are tools to reflect changes to the original project parameters after Contract signature. Adjustment Orders are the official/legal amendments to the terms and conditions of a live Contract. Reasons for issuing Adjustment Orders arise from changes in Contract scope, technical requirement and specification resulting in scope addition, deletion, or alteration. It can be as well a combination of most of these parameters resulting in an increase or decrease in time and/or cost. Most business leaders (handling projects in the interest of the owner) refrain from using Adjustment Orders considering their main objectives of staying within budget and on schedule. Success in managing the changes results in uninterrupted execution and agreed project costs as well as schedule. Nevertheless, this is not always practically achievable. In this paper, a detailed study through utilizing Industrial Engineering & Systems Management tools such as Six Sigma, Data Analysis, and Quality Control were implemented on the organization’s five years records of the issued Adjustment Orders in order to investigate their prevalence, and time and cost impact. The analysis outcome revealed and helped to identify and categorize the predominant causations with the highest impacts, which were considered most in recommending the corrective measures to reach the objective of minimizing the Adjustment Orders impacts. Data analysis demonstrated no specific trend in the AO frequency in past five years; however, time impact is more than the cost impact. Although Adjustment Orders might never be avoidable; this analysis offers’ some insight to the procedural gaps, and where it is highly impacting the organization. Possible solutions are concluded such as improving project handling team’s coordination and communication, utilizing a blanket service contract, and modifying the projects gate system procedures to minimize the possibility of having similar struggles in future. Projects in the Oil and Gas sector are always evolving and demand a certain amount of flexibility to sustain the goals of the field. As it will be demonstrated, the uncertainty of project parameters, in adequate project definition, operational constraints and stringent procedures are main factors resulting in the need for Adjustment Orders and accordingly the recommendation will be to address that challenge.

Keywords: adjustment orders, data analysis, oil and gas sector, systems management

Procedia PDF Downloads 146

Authors: Qiuyu Dai, Haochong Zhang, Xiangrong Liu

Abstract:

Diagonal sparse matrix-vector multiplication is a well-studied topic in the fields of scientific computing and big data processing. However, when diagonal sparse matrices are stored in DIA format, there can be a significant number of padded zero elements and scattered points, which can lead to a degradation in the performance of the current DIA kernel. This can also lead to excessive consumption of computational and memory resources. In order to address these issues, the authors propose the DIA-Adaptive scheme and its kernel, which leverages the parallel instruction sets on MLU. The researchers analyze the effect of allocating a varying number of threads, clusters, and hardware architectures on the performance of SpMV using different formats. The experimental results indicate that the proposed DIA-Adaptive scheme performs well and offers excellent parallelism.

Keywords: adaptive method, DIA, diagonal sparse matrices, MLU, sparse matrix-vector multiplication

Procedia PDF Downloads 110

Authors: Manish Kumar Thakur, Subrata Kumar Ghosh

Abstract:

Various types of particles found in lubricant may be characterized by their fractal dimension. Some of the available methods are: yard-stick method or structured walk method, box-counting method. This paper presents a review of the developments and progress in fractal dimension computing methods as applied to characteristics the surface of wear particles. An overview of these methods, their implementation, their advantages and their limits is also present here. It has been accepted that wear particles contain major information about wear and friction of materials. Morphological analysis of wear particles from a lubricant is a very effective way for machine condition monitoring. Fractal dimension methods are used to characterize the morphology of the found particles. It is very useful in the analysis of complexity of irregular substance. The aim of this review is to bring together the fractal methods applicable for wear particles.

Keywords: fractal dimension, morphological analysis, wear, wear particles

Procedia PDF Downloads 467

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinie

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. That is why the need for automation of this task is urgent. A lot of studies have investigated the subject using different standard image processing descriptors and sometimes hand-crafted ones.In this work, we make a comparative study between classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN, Autoencoders, Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches

Keywords: pollens identification, features extraction, pollens classification, automated palynology

Procedia PDF Downloads 120

Authors: Joan Casas-Roma

Abstract:

Technology has become one of the main channels through which people engage in most of their everyday activities; from working to learning, or even when socializing, technology often acts as both an enabler and a mediator of such activities. Moreover, the affordances and interactions created by those technological tools determine the way in which the users interact with one another, as well as how they relate to the relevant environment, thus favoring certain kinds of actions and behaviors while discouraging others. In this regard, virtue ethics theories place a strong focus on a person's daily practice (understood as their decisions, actions, and behaviors) as the means to develop and enhance their habits and ethical competences --such as their awareness and sensitivity towards certain ethically-desirable principles. Under this understanding of ethics, this set of technologically-enabled affordances and interactions can be seen as the possibility space where the daily practice of their users takes place in a wide plethora of contexts and situations. At this point, the following question pops into mind: could these affordances and interactions be shaped in a way that would promote behaviors and habits basedonethically-desirable principles into their users? In the field of game design, the MDA framework (which stands for Mechanics, Dynamics, Aesthetics) explores how the interactions enabled within the possibility space of a game can lead to creating certain experiences and provoking specific reactions to the players. In this sense, these interactions can be shaped in ways thatcreate experiences to raise the players' awareness and sensitivity towards certain topics or principles. This research brings together the notions of technological affordances, the notions of practice and practical wisdom from virtue ethics, and the MDA framework from game design in order to explore how the possibility space created by technological interactions can be shaped in ways that enable and promote actions and behaviors supporting certain ethically-desirable principles. When shaped accordingly, interactions supporting certain ethically-desirable principlescould allow their users to carry out the kind of practice that, according to virtue ethics theories, provides the grounds to develop and enhance their awareness, sensitivity, and ethical reasoning capabilities. Moreover, and because ethical practice can happen collaterally in almost every context, decision, and action, this additional layer could potentially be applied in a wide variety of technological tools, contexts, and functionalities. This work explores the theoretical background, as well as the initial considerations and steps that would be needed in order to harness the potential ethically-desirable benefits that technology can bring, once it is understood as the space where most of their users' daily practice takes place.

Keywords: ethics, design methodology, human-computer interaction, philosophy of technology

Procedia PDF Downloads 142

Authors: Fahem Belkacemi, Lyes Ouali

Abstract:

Maintenance strategies and assessments continue to be a major concern for companies today. The socio-economic bets of their competitiveness are closely linked to the activities and quality of maintenance. This work deals with a study of a preventive maintenance plan to improve the availability of the production line within SAMSUNG HOME APPLIANCE “SAMHA”, Setif, Algeria. First, we applied the method of analysis of failure modes, their impact, and criticality to reduce downtime and identification of the most critical elements. Finally, to improve the availability of the production line, we carried out a study of the current preventive maintenance plan in the production line workshop at the company level and according to the history sheet of machine failures. We proposed a preventive maintenance plan to improve the availability of the production line.

Keywords: preventive maintenance, DRUM line, AMDEC, availability

Procedia PDF Downloads 47

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Generally, absorption and bioavailability increase if solubility increases; therefore, it is crucial to predict them in drug discovery applications. Molecular descriptors and Molecular properties are traditionally used for the prediction of water solubility. There are various key descriptors that are used for this purpose, namely Drogan Descriptors, Morgan Descriptors, Maccs keys, etc., and each has different prediction capabilities with differentiating successes between different data sets. Another source for the prediction of solubility is structural features; they are commonly used for the prediction of solubility. However, there are little to no studies that combine three or more properties or descriptors for prediction to produce a more powerful prediction model. Unlike available models, we used a combination of those features in a random forest machine learning model for improved solubility prediction to better predict and, therefore, contribute to drug discovery systems.

Keywords: solubility, random forest, molecular descriptors, maccs keys

Procedia PDF Downloads 23

Authors: Ron Cottam, Nils Langloh, Willy Ranson, Roger Vounckx

Abstract:

We start by formally describing the requirements for environmental-reaction survival computation in a natural temporally-demanding medium, and develop this into a more general model of the evolutionary context as a computational machine. The effect of this development is to replace deterministic logic by a modified form which exhibits a continuous range of dimensional fractal diffuseness between the isolation of perfectly ordered localization and the extended communication associated with nonlocality as represented by pure causal chaos. We investigate the appearance of life and consciousness in the derived general model, and propose a representation of Nature within which all localizations have the character of quasi-quantal entities. We compare our conclusions with Heisenberg’s uncertainty principle and nonlocal teleportation, and maintain that computability is the principal influence on evolution in the model we propose.

Keywords: computability, evolution, life, localization, modeling, nonlocality

Procedia PDF Downloads 386

Authors: Sarah O. Alhumoud, Mawaheb I. Altuwaijri, Tarfa M. Albuhairi, Wejdan M. Alohaideb

Abstract:

Large-scale data stream analysis has become one of the important business and research priorities lately. Social networks like Twitter and other micro-blogging platforms hold an enormous amount of data that is large in volume, velocity and variety. Extracting valuable information and trends out of these data would aid in a better understanding and decision-making. Multiple analysis techniques are deployed for English content. Moreover, one of the languages that produce a large amount of data over social networks and is least analyzed is the Arabic language. The proposed paper is a survey on the research efforts to analyze the Arabic content in Twitter focusing on the tools and methods used to extract the sentiments for the Arabic content on Twitter.

Keywords: big data, social networks, sentiment analysis, twitter

Procedia PDF Downloads 554

Authors: Luay Jum'a

Abstract:

Many challenges are facing third-party logistics (3PL) providers in the domestic and global markets which create a volatile decision making environment. All these challenges such as managing changes in consumer behaviour, demanding expectations from customers and time compressions have turned into complex problems for 3PL providers. Since the movement towards increased outsourcing outpaces movement towards insourcing, the need to achieve a competitive advantage over competitors in 3PL market increases. This trend continues to grow over the years and as a result, areas of strengths and improvements are highlighted through the analysis of the LSQ factors that lead to B2B customers’ satisfaction which become a priority for 3PL companies. Consequently, 3PL companies are increasingly focusing on the most important issues from the perspective of their customers and relying more on this value of information in making their managerial decisions. Therefore, this study is concerned with providing guidance for improving logistics service quality (LSQ) levels in the context of 3PL industry in Jordan. The study focused on the most important factors in LSQ and used a managerial tool that guides 3PL companies in making LSQ improvements based on a quadrant analysis of two main dimensions: LSQ declared importance and LSQ inferred importance. Although, a considerable amount of research has been conducted to investigate the relationship between logistics service quality (LSQ) and customer satisfaction, there remains a lack of developing managerial tools to aid in the process of LSQ improvement decision-making. Moreover, the main advantage for the companies to use 3PL service providers as a trend is due to the realised percentage of cost reduction on the total cost of logistics operations and the incremental improvement in customer service. In this regard, having a managerial tool that help 3PL service providers in managing the LSQ factors portfolio effectively and efficiently would be a great investment for service providers. One way of suggesting LSQ improvement actions for 3PL service providers is via the adoption of analysis tools that perform attribute categorisation such as Importance–Performance matrix. In mind of the above, it can be stated that the use of quadrant analysis will provide a valuable opportunity for 3PL service providers to identify improvement opportunities as customer service attributes or factors importance are identified in two different techniques that complete each other. Moreover, the data were collected through conducting a survey and 293 questionnaires were returned from business-to-business (B2B) customers of 3PL companies in Jordan. The results showed that the LSQ factors vary in their importance and 3PL companies should focus on some LSQ factors more than other factors. Moreover, ordering procedures, timeliness/responsiveness LSQ factors considered being crucial in 3PL businesses and therefore they need to have more focus and development by 3PL service providers in the Jordanian market.

Keywords: logistics service quality, managerial decisions, quadrant analysis, third party logistics service provider

Procedia PDF Downloads 118

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. Accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER, benefiting from deep learning, especially CNN and VGG16. First, the data is pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning

Procedia PDF Downloads 75

Authors: Yang Li, Xiaorong Guan, Cheng Xu

Abstract:

In order to design a suitable control scheme for human extremity exoskeleton, the interaction force control scheme with traditional PI controller was presented, and the simulation study of the electromechanical system of the human extremity exoskeleton was carried out by using a MATLAB/Simulink module. By analyzing the simulation calculation results, it was shown that the traditional PI controller is not very suitable for every movement speed of human body. So, at last the fuzzy self-adaptive PI controller was presented to solve this problem. Eventually, the superiority and feasibility of the fuzzy self-adaptive PI controller was proved by the simulation results and experimental results.

Keywords: human extremity exoskeleton, interaction force control scheme, simulation study, fuzzy self-adaptive pi controller, man-machine coordinated walking, bear payload

Procedia PDF Downloads 349

Authors: Richard Ren

Abstract:

Air pollution is a serious danger to international well-being and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.

Keywords: air quality prediction, air pollution, artificial intelligence, machine learning algorithms

Procedia PDF Downloads 103

Authors: Uzu-Kuei Hsu, Chang-Hsien Tai, Kai-Wun Jin

Abstract:

When sinters are filled into the cooler from the sintering machine, and the non-uniform distribution of the sinters leads to uneven cooling. This causes the temperature difference of the sinters leaving the cooler to be so large that it results in the conveyors being deformed by the heat. The present work applies CFD method to investigate the thermo flowfield phenomena in a sinter cooler by the Porous Media Model. Using the obtained experimental data to simulate porosity (Ε), permeability (κ), inertial coefficient (F), specific heat (Cp) and effective thermal conductivity (keff) of the sinter packed beds. The physical model is a similar geometry whose Darcy numbers (Da) are similar to the sinter cooler. Using the Cooling Index (CI) and Uniformity Index (UI) to analyze the thermo flowfield in the sinter packed bed obtains the cooling performance of the sinter cooler.

Keywords: porous media, sinter, cooling index (CI), uniformity index (UI), CFD

Procedia PDF Downloads 383

Authors: Angela U. Makolo

Abstract:

Protein-coding and Non-coding regions determine the biology of a sequenced transcriptome. Research advances have shown that Non-coding regions are important in disease progression and clinical diagnosis. Existing bioinformatics tools have been targeted towards Protein-coding regions alone. Therefore, there are challenges associated with gaining biological insights from transcriptome sequence data. These tools are also limited to computationally intensive sequence alignment, which is inadequate and less accurate to identify both Protein-coding and Non-coding regions. Alignment-free techniques can overcome the limitation of identifying both regions. Therefore, this study was designed to develop an efficient sequence alignment-free model for identifying both Protein-coding and Non-coding regions in sequenced transcriptomes. Feature grouping and randomization procedures were applied to the input transcriptomes (37,503 data points). Successive iterations were carried out to compute the gradient vector that converged the developed Protein-coding and Non-coding Region Identifier (PNRI) model to the approximate coefficient vector. The logistic regression algorithm was used with a sigmoid activation function. A parameter vector was estimated for every sample in 37,503 data points in a bid to reduce the generalization error and cost. Maximum Likelihood Estimation (MLE) was used for parameter estimation by taking the log-likelihood of six features and combining them into a summation function. Dynamic thresholding was used to classify the Protein-coding and Non-coding regions, and the Receiver Operating Characteristic (ROC) curve was determined. The generalization performance of PNRI was determined in terms of F1 score, accuracy, sensitivity, and specificity. The average generalization performance of PNRI was determined using a benchmark of multi-species organisms. The generalization error for identifying Protein-coding and Non-coding regions decreased from 0.514 to 0.508 and to 0.378, respectively, after three iterations. The cost (difference between the predicted and the actual outcome) also decreased from 1.446 to 0.842 and to 0.718, respectively, for the first, second and third iterations. The iterations terminated at the 390th epoch, having an error of 0.036 and a cost of 0.316. The computed elements of the parameter vector that maximized the objective function were 0.043, 0.519, 0.715, 0.878, 1.157, and 2.575. The PNRI gave an ROC of 0.97, indicating an improved predictive ability. The PNRI identified both Protein-coding and Non-coding regions with an F1 score of 0.970, accuracy (0.969), sensitivity (0.966), and specificity of 0.973. Using 13 non-human multi-species model organisms, the average generalization performance of the traditional method was 74.4%, while that of the developed model was 85.2%, thereby making the developed model better in the identification of Protein-coding and Non-coding regions in transcriptomes. The developed Protein-coding and Non-coding region identifier model efficiently identified the Protein-coding and Non-coding transcriptomic regions. It could be used in genome annotation and in the analysis of transcriptomes.

Keywords: sequence alignment-free model, dynamic thresholding classification, input randomization, genome annotation

Procedia PDF Downloads 51

Authors: Masoumeh Mofarrah, Amir NahanMoghadam

Abstract:

Higher oil prices and increasing oil demand are main reasons for great attention to Enhanced Oil Recovery (EOR). Comprehensive researches have been accomplished to develop, appraise, and improve EOR methods and their application. Recently, Artificial Intelligence (AI) gained popularity in petroleum industry that can help petroleum engineers to solve some fundamental petroleum engineering problems such as reservoir simulation, EOR project risk analysis, well log interpretation and well test model selection. This study presents a historical overview of most popular AI tools including neural networks, genetic algorithms, fuzzy logic, and expert systems in petroleum industry and discusses two case studies to represent the application of two mentioned AI methods for selecting an appropriate EOR method based on reservoir characterization infeasible and effective way.

Keywords: artificial intelligence, EOR, neural networks, expert systems

Procedia PDF Downloads 475

Authors: Murat Sarı, Emin Gundogar, Mumtaz Ipek

Abstract:

Nowadays, in a furniture sector, competition of market share (portion) and production variety and changeability enforce the firm to reengineer operations on manufacturing line to increase the productivity. In this study, spring mattress manufacturing line of the furniture manufacturing firm is analyzed analytically. It’s intended to search and find the bottlenecks of production to balance the semi-finished material flow. There are four base points required to investigate in bottleneck elimination process. These are bottlenecks of Method, Material, Machine and Man (work force) resources, respectively. Mentioned bottlenecks are investigated and varied scenarios are created for recruitment of manufacturing system. Probable near optimal alternatives are determined by system models built in Arena simulation software.

Keywords: bottleneck search, buffer stock, furniture sector, simulation

Procedia PDF Downloads 345

Authors: Nebi Gedik

Abstract:

One of the significant and continual public health problems in the world is breast cancer. Early detection is very important to fight the disease, and mammography has been one of the most common and reliable methods to detect the disease in the early stages. However, it is a difficult task, and computer-aided diagnosis (CAD) systems are needed to assist radiologists in providing both accurate and uniform evaluation for mass in mammograms. In this study, a multiresolution statistical method to classify mammograms as normal and abnormal in digitized mammograms is used to construct a CAD system. The mammogram images are represented by wave atom transform, and this representation is made by certain groups of coefficients, independently. The CAD system is designed by calculating some statistical features using each group of coefficients. The classification is performed by using support vector machine (SVM).

Keywords: wave atom transform, statistical features, multi-resolution representation, mammogram

Procedia PDF Downloads 209

Authors: Supunmali Ahangama, Danny Chiang Choon Poo

Abstract:

Health analytics (HA) is used in healthcare systems for effective decision-making, management, and planning of healthcare and related activities. However, user resistance, the unique position of medical data content, and structure (including heterogeneous and unstructured data) and impromptu HA projects have held up the progress in HA applications. Notably, the accuracy of outcomes depends on the skills and the domain knowledge of the data analyst working on the healthcare data. The success of HA depends on having a sound process model, effective project management and availability of supporting tools. Thus, to overcome these challenges through an effective process model, we propose an HA process model with features from the rational unified process (RUP) model and agile methodology.

Keywords: agile methodology, health analytics, unified process model, UML

Procedia PDF Downloads 490

Authors: Nasser S. Shebka

Abstract:

Fuzzy logic is used in complex adaptive systems where classical tools of representing knowledge are unproductive. Nevertheless, the incorporation of fuzzy logic, as it’s the case with all artificial intelligence tools, raised some inconsistencies and limitations in dealing with increased complexity systems and rules that apply to real-life situations and hinders the ability of the inference process of such systems, but it also faces some inconsistencies between inferences generated fuzzy rules of complex or imprecise knowledge-based systems. The use of fuzzy logic enhanced the capability of knowledge representation in such applications that requires fuzzy representation of truth values or similar multi-value constant parameters derived from multi-valued logic, which set the basis for the three t-norms and their based connectives which are actually continuous functions and any other continuous t-norm can be described as an ordinal sum of these three basic ones. However, some of the attempts to solve this dilemma were an alteration to fuzzy logic by means of non-monotonic logic, which is used to deal with the defeasible inference of expert systems reasoning, for example, to allow for inference retraction upon additional data. However, even the introduction of non-monotonic fuzzy reasoning faces a major issue of conflict resolution for which many principles were introduced, such as; the specificity principle and the weakest link principle. The aim of our work is to improve the logical representation and functional modelling of AI systems by presenting a method of resolving existing and potential rule conflicts by representing temporal modalities within defeasible inference rule-based systems. Our paper investigates the possibility of resolving fuzzy rules conflict in a non-monotonic fuzzy reasoning-based system by introducing temporal modalities and Kripke's general weak modal logic operators in order to expand its knowledge representation capabilities by means of flexibility in classifying newly generated rules, and hence, resolving potential conflicts between these fuzzy rules. We were able to address the aforementioned problem of our investigation by restructuring the inference process of the fuzzy rule-based system. This is achieved by using time-branching temporal logic in combination with restricted first-order logic quantifiers, as well as propositional logic to represent classical temporal modality operators. The resulting findings not only enhance the flexibility of complex rule-base systems inference process but contributes to the fundamental methods of building rule bases in such a manner that will allow for a wider range of applicable real-life situations derived from a quantitative and qualitative knowledge representational perspective.

Keywords: fuzzy rule-based systems, fuzzy tense inference, intelligent systems, temporal modalities

Procedia PDF Downloads 73

Authors: Şule Yanık, Hasan Gürgür

Abstract:

It is thought that it is important for disabled children to have the opportunity to benefit preschool education that smoothens transition process to formal education, and for the constitution of a precondition for their success. Within this context, it is important for the disabled in Turkey to be evaluated medically firstly and then educational-wise in order for them to benefit early inclusive education. Thus, disabled people are both diagnosed in hospitals and at Guidance and Research Centers (GRC) attached to Ministry of Education educational-wise. It is seen that standard evaluation tools are used and evaluations are done by special education teachers (SET) in order for educational diagnosis and evaluation (EDAE) to be realized. The literature emphasizes the importance of informal evaluation tools as well as formal ones. According to this, it is thought that another party, besides students in EDAE process and SETs, is family, because families are primary care takers for their children, and that the most correct and real information can be obtained via families beside results of educational evaluation processes (EEP). It is thought that obtaining opinions of families during EEP is important to be able to exhibit the present EDAE activities in Turkey, materialize any existing problems, and increase quality of the process. Within this context, the purpose of this study is to exhibit experiences regarding EDAE processes of 10 families having preschool children with hearing loss (CHL). The process of research is designed to be descriptive based on qualitative research paradigms. Data were collected via semi-structured interview questions, and the themes were obtained. As a result, it is seen that families, after they realize the hearing loss of their children, do not have any information regarding the subject, and that they consult to an ear-nose-throat doctor or an audiologist for support. It is seen that families go to hospitals for medical evaluation which is a pre-requisite for benefiting early education opportunities. However, during this process, as some families do not have any experience of having a CHL, it is seen that they are late for medical evaluation and hearing aids. Moreover, families stated that they were directed to GRC via audiologists for educational evaluation. Families stated that their children were evaluated regarding language, academic and psychological development in proportion with their ages in GRC after they were diagnosed medically. However, families stated that EEP realized in GRC was superficial, short and lacked detail. It is seen that many families were not included in EEP process, whereas some families stated that they were asked questions because their children are too small to answer. Regarding the benefits of EEP for themselves and their children, families stated that GRC had to give a report to them for benefiting the free support of Special Education and Rehabilitation Center, and that families had to be directed to inclusive education. As a result, it is seen that opinions of families regarding EDAE processes at GRC indicate inefficiency of the process as it is short and superficial, regardless being to the point.

Keywords: children with hearing loss, educational diagnosis and evaluation, guidance and research center, inclusion

Procedia PDF Downloads 222