Search results for: statistical machine translation

Authors: Nima Mahmoudi, Hamzeh Khazaei

Abstract:

Serving machine learning inference workloads on the cloud is still a challenging task at the production level. The optimal configuration of the inference workload to meet SLA requirements while optimizing the infrastructure costs is highly complicated due to the complex interaction between batch configuration, resource configurations, and variable arrival process. Serverless computing has emerged in recent years to automate most infrastructure management tasks. Workload batching has revealed the potential to improve the response time and cost-effectiveness of machine learning serving workloads. However, it has not yet been supported out of the box by serverless computing platforms. Our experiments have shown that for various machine learning workloads, batching can hugely improve the system’s efficiency by reducing the processing overhead per request. In this work, we present MLProxy, an adaptive reverse proxy to support efficient machine learning serving workloads on serverless computing systems. MLProxy supports adaptive batching to ensure SLA compliance while optimizing serverless costs. We performed rigorous experiments on Knative to demonstrate the effectiveness of MLProxy. We showed that MLProxy could reduce the cost of serverless deployment by up to 92% while reducing SLA violations by up to 99% that can be generalized across state-of-the-art model serving frameworks.

Keywords: serverless computing, machine learning, inference serving, Knative, google cloud run, optimization

Procedia PDF Downloads 141

Authors: S. Apprich, F. Wulle, A. Lechler, A. Pott, A. Verl

Abstract:

Large-scale machine tools for the manufacturing of large work pieces, e.g. blades, casings or gears for wind turbines, feature pose-dependent dynamic behavior. Small structural damping coefficients lead to long decay times for structural vibrations that have negative impacts on the production process. Typically, these vibrations are handled by increasing the stiffness of the structure by adding mass. That is counterproductive to the needs of sustainable manufacturing as it leads to higher resource consumption both in material and in energy. Recent research activities have led to higher resource efficiency by radical mass reduction that rely on control-integrated active vibration avoidance and damping methods. These control methods depend on information describing the dynamic behavior of the controlled machine tools in order to tune the avoidance or reduction method parameters according to the current state of the machine. The paper presents the appearance, consequences and challenges of the pose-dependent dynamic behavior of lightweight large-scale machine tool structures in production. The paper starts with the theoretical introduction of the challenges of lightweight machine tool structures resulting from reduced stiffness. The statement of the pose-dependent dynamic behavior is corroborated by the results of the experimental modal analysis of a lightweight test structure. Afterwards, the consequences of the pose-dependent dynamic behavior of lightweight machine tool structures for the use of active control and vibration reduction methods are explained. Based on the state of the art on pose-dependent dynamic machine tool models and the modal investigation of an FE-model of the lightweight test structure, the criteria for a pose-dependent model for use in vibration reduction are derived. The description of the approach for a general pose-dependent model of the dynamic behavior of large lightweight machine tools that provides the necessary input to the aforementioned vibration avoidance and reduction methods to properly tackle machine vibrations is the outlook of the paper.

Keywords: dynamic behavior, lightweight, machine tool, pose-dependency

Procedia PDF Downloads 432

Authors: Yoshio Kurosawa

Abstract:

The applications of soundproof materials for reduction of high frequency automobile interior noise have been researched. This paper presents a sound pressure prediction technique including wind noise by Hybrid Statistical Energy Analysis (HSEA) in order to reduce weight of acoustic insulations. HSEA uses both analytical SEA and experimental SEA. As a result of chassis dynamo test and road test, the validity of SEA modeling was shown, and utility of the method was confirmed.

Keywords: vibration, noise, road noise, statistical energy analysis

Procedia PDF Downloads 320

Authors: Hamidreza Akbari

Abstract:

In this paper, for detection of inclined eccentricity in an induction motor, time–frequency analysis of the stator startup current is carried out. For this purpose, the discrete wavelet transform is used. Data are obtained from simulations, using winding function approach. The results show the validity of the approach for detecting the fault and discriminating with respect to other faults.

Keywords: induction machine, fault, DWT, electric

Procedia PDF Downloads 322

Authors: Vaidehi Murarka, Sneha Mehta, Dishant Upadhyay

Abstract:

Our project topic is “Alphabet Recognition using pixel probability distribution”. The project uses techniques of Image Processing and Machine Learning in Computer Vision. Alphabet recognition is the mechanical or electronic translation of scanned images of handwritten, typewritten or printed text into machine-encoded text. It is widely used to convert books and documents into electronic files etc. Alphabet Recognition based OCR application is sometimes used in signature recognition which is used in bank and other high security buildings. One of the popular mobile applications includes reading a visiting card and directly storing it to the contacts. OCR's are known to be used in radar systems for reading speeders license plates and lots of other things. The implementation of our project has been done using Visual Studio and Open CV (Open Source Computer Vision). Our algorithm is based on Neural Networks (machine learning). The project was implemented in three modules: (1) Training: This module aims “Database Generation”. Database was generated using two methods: (a) Run-time generation included database generation at compilation time using inbuilt fonts of OpenCV library. Human intervention is not necessary for generating this database. (b) Contour–detection: ‘jpeg’ template containing different fonts of an alphabet is converted to the weighted matrix using specialized functions (contour detection and blob detection) of OpenCV. The main advantage of this type of database generation is that the algorithm becomes self-learning and the final database requires little memory to be stored (119kb precisely). (2) Preprocessing: Input image is pre-processed using image processing concepts such as adaptive thresholding, binarizing, dilating etc. and is made ready for segmentation. “Segmentation” includes extraction of lines, words, and letters from the processed text image. (3) Testing and prediction: The extracted letters are classified and predicted using the neural networks algorithm. The algorithm recognizes an alphabet based on certain mathematical parameters calculated using the database and weight matrix of the segmented image.

Keywords: contour-detection, neural networks, pre-processing, recognition coefficient, runtime-template generation, segmentation, weight matrix

Procedia PDF Downloads 359

Authors: Jeelka Ray

Abstract:

Survey of the papers revealed that there is no practical design available for packaging machine based on Embedded system, so the need arose for the development of the prototype model. In this paper, author has worked on the development of an ARM7 based Embedded Controller for controlling the sequence of packaging machine. The unit is made user friendly with TFT and Touch Screen implementing human machine interface (HMI). The different system components are briefly discussed, followed by a description of the overall design. The major functions which involve bag forming, sealing temperature control, fault detection, alarm, animated view on the home screen when the machine is working as per different parameters set makes the machine performance more successful. LPC2478 ARM 7 Embedded Microcontroller controls the coordination of individual control function modules. In back gone days, these machines were manufactured with mechanical fittings. Later on, the electronic system replaced them. With the help of ongoing technologies, these mechanical systems were controlled electronically using Microprocessors. These became the backbone of the system which became a cause for the updating technologies in which the control was handed over to the Microcontrollers with Servo drives for accurate positioning of the material. This helped to maintain the quality of the products. Including all, RS 485 MODBUS Communication technology is used for synchronizing AC Drive & Servo Drive. These all concepts are operated either manually or through a Graphical User Interface. Automatic tuning of heaters, sealers and their temperature is controlled using Proportional, Integral and Derivation loops. In the upcoming latest technological world, the practical implementation of the above mentioned concepts is really important to be in the user friendly environment. Real time model is implemented and tested on the actual machine and received fruitful results.

Keywords: packaging machine, embedded system, ARM 7, micro controller, HMI, TFT, touch screen, PID

Procedia PDF Downloads 253

Authors: Mohd Zamri Osman, Mohd Aizaini Maarof, Mohd Foad Rohani

Abstract:

Human skin detection recognized as the primary step in most of the applications such as face detection, illicit image filtering, hand recognition and video surveillance. The performance of any skin detection applications greatly relies on the two components: feature extraction and classification method. Skin color is the most vital information used for skin detection purpose. However, color feature alone sometimes could not handle images with having same color distribution with skin color. A color feature of pixel-based does not eliminate the skin-like color due to the intensity of skin and skin-like color fall under the same distribution. Hence, the statistical color analysis will be exploited such mean and standard deviation as an additional feature to increase the reliability of skin detector. In this paper, we studied the effectiveness of statistical color feature for human skin detection. Furthermore, the paper analyzed the integrated color and texture using eight classifiers with three color spaces of RGB, YCbCr, and HSV. The experimental results show that the integrating statistical feature using Random Forest classifier achieved a significant performance with an F1-score 0.969.

Keywords: color space, neural network, random forest, skin detection, statistical feature

Procedia PDF Downloads 425

Authors: Juan-Pedro Rica-Peromingo

Abstract:

Teachers constantly need to innovate and redefine materials for their lectures, especially in areas such as Language for Specific Purposes (LSP) and Translation Studies (TS). It is therefore essential for the lecturers to be technically skilled to handle the never-ending evolution in software and technology, which are necessary elements especially in certain courses at university level. This need becomes even more evident in Audiovisual Translation (AVT) Modules and Courses. AVT has undergone considerable growth in the area of teaching and learning of languages for academic purposes. We have witnessed the development of a considerable number of masters and postgraduate courses where AVT becomes a tool for L2 learning. The teaching and learning of different AVT modes are components of undergraduate and postgraduate courses. Universities, in which AVT is offered as part of their teaching programme or training, make use of professional or free software programs. This paper presents an approach in AVT withina specific university context, in which technology is used by means of professional and nonprofessional software. Students take an AVT subject as part of their English Linguistics Master’s Degree at the Complutense University (UCM) in which they are using professional (Spot) and nonprofessional (Subtitle Workshop, Aegisub, Windows Movie Maker) software packages. The students are encouraged to develop their tasks and projects simulating authentic professional experiences and contexts in the different AVT modes: subtitling for hearing and deaf and hard of hearing population, audio description and dubbing. Selected scenes from TV series such as X-Files, Gossip girl, IT Crowd; extracts from movies: Finding Nemo, Good Will Hunting, School of Rock, Harry Potter, Up; and short movies (Vincent) were used. Hence, the complexity of the audiovisual materials used in class as well as the activities for their projects were graded. The assessment of the diverse tasks carried out by all the students are expected to provide some insights into the best way to improve their linguistic accuracy and oral and written productions with the use of different AVT modes in a very specific ESP university context.

Keywords: ESP, audiovisual translation, technology, university teaching, teaching

Procedia PDF Downloads 497

Authors: Muhtasim Shafi Kader, Fizar Ahmed, Annesha Acharjee

Abstract:

Machine learning and data mining are crucial in health care, as well as medical information and detection. Machine learning approaches are now being utilized to improve awareness of a variety of critical health issues, including diabetes detection, neuron cell tumor diagnosis, COVID 19 identification, and so on. Parkinson’s disease is basically a disease for our senior citizens in Bangladesh. Parkinson's Disease indications often seem progressive and get worst with time. People got affected trouble walking and communicating with the condition advances. Patients can also have psychological and social vagaries, nap problems, hopelessness, reminiscence loss, and weariness. Parkinson's disease can happen in both men and women. Though men are affected by the illness at a proportion that is around partial of them are women. In this research, we have to get out the accurate ML algorithm to find out the disease with a predictable dataset and the model of the following machine learning classifiers. Therefore, nine ML classifiers are secondhand to portion study to use machine learning approaches like as follows, Naive Bayes, Adaptive Boosting, Bagging Classifier, Decision Tree Classifier, Random Forest classifier, XBG Classifier, K Nearest Neighbor Classifier, Support Vector Machine Classifier, and Gradient Boosting Classifier are used.

Keywords: naive bayes, adaptive boosting, bagging classifier, decision tree classifier, random forest classifier, XBG classifier, k nearest neighbor classifier, support vector classifier, gradient boosting classifier

Procedia PDF Downloads 106

Authors: Haiyan Wu, Ying Liu, Shaoyun Shi

Abstract:

Authorship attribution is to extract features to identify authors of anonymous documents. Many previous works on authorship attribution focus on statistical style features (e.g., sentence/word length), content features (e.g., frequent words, n-grams). Modeling these features by regression or some transparent machine learning methods gives a portrait of the authors' writing style. But these methods do not capture the syntactic (e.g., dependency relationship) or semantic (e.g., topics) information. In recent years, some researchers model syntactic trees or latent semantic information by neural networks. However, few works take them together. Besides, predictions by neural networks are difficult to explain, which is vital in authorship attribution tasks. In this paper, we not only utilize the statistical style and content features but also take advantage of both syntactic and semantic features. Different from an end-to-end neural model, feature selection and prediction are two steps in our method. An attentive n-gram network is utilized to select useful features, and logistic regression is applied to give prediction and understandable representation of writing style. Experiments show that our extracted features can improve the state-of-the-art methods on three benchmark datasets.

Keywords: authorship attribution, attention mechanism, syntactic feature, feature extraction

Procedia PDF Downloads 108

Authors: Wided Bakari, Patrce Bellot, Mahmoud Neji

Abstract:

With the development of electronic media and the heterogeneity of Arabic data on the Web, the idea of building a clean corpus for certain applications of natural language processing, including machine translation, information retrieval, question answer, become more and more pressing. In this manuscript, we seek to create and develop our own corpus of pair’s questions-texts. This constitution then will provide a better base for our experimentation step. Thus, we try to model this constitution by a method for Arabic insofar as it recovers texts from the web that could prove to be answers to our factual questions. To do this, we had to develop a java script that can extract from a given query a list of html pages. Then clean these pages to the extent of having a database of texts and a corpus of pair’s question-texts. In addition, we give preliminary results of our proposal method. Some investigations for the construction of Arabic corpus are also presented in this document.

Keywords: Arabic, web, corpus, search engine, URL, question, corpus building, script, Google, html, txt

Procedia PDF Downloads 299

Authors: Peli̇n Yilmaz, Gi̇zemnur Yildiz Uysal, Emi̇ne Bi̇rci̇, Berk Özcan, Burak Koca, Ehsan Tuzcuoğlu, Fati̇h Kasap

Abstract:

Development of Energy Efficient Programs (EEP) is one of the most significant trends in the wet appliance industry of the recent years. Thanks to the EEP, the energy consumption of a washing machine as one of the most energy-consuming home appliances can shrink considerably, while its washing performance and the textile hygiene should remain almost unchanged. Here in, the goal of the present study is to achieve an optimum EEP algorithm providing excellent textile hygiene results as well as cleaning performance in a domestic washing machine. In this regard, steam-pretreated cold wash approach with a combination of innovative algorithm solution in a relatively short washing cycle duration was implemented. For the parametric study, steam exposure time, washing load, total water consumption, main-washing time, and spinning rpm as the significant parameters affecting the textile hygiene and cleaning performance were investigated within a Design of Experiment study using Minitab 2021 statistical program. For the textile hygiene studies, specific loads containing the contaminated cotton carriers with Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa bacteria were washed. Then, the microbial removal performance of the designed programs was expressed as log reduction calculated as a difference of microbial count per ml of the liquids in which the cotton carriers before and after washing. For the cleaning performance studies, tests were carried out with various types of detergents and EMPA Standard Stain Strip. According to the results, the optimum EEP program provided an excellent hygiene performance of more than 2 log reduction of microorganism and a perfect Washing Efficiency Index (Iw) of 1.035, which is greater than the value specified by EU ecodesign regulation 2019/2023.

Keywords: washing machine, energy efficient programs, hygiene, washing efficiency index, microorganism, escherichia coli, staphylococcus aureus, pseudomonas aeruginosa, laundry

Procedia PDF Downloads 103

Authors: Farid Khosravikia, Patricia Clayton

Abstract:

The main objective of this study is to evaluate the advantages and disadvantages of various machine learning techniques in forecasting ground-motion intensity measures given source characteristics, source-to-site distance, and local site condition. Intensity measures such as peak ground acceleration and velocity (PGA and PGV, respectively) as well as 5% damped elastic pseudospectral accelerations at different periods (PSA), are indicators of the strength of shaking at the ground surface. Estimating these variables for future earthquake events is a key step in seismic hazard assessment and potentially subsequent risk assessment of different types of structures. Typically, linear regression-based models, with pre-defined equations and coefficients, are used in ground motion prediction. However, due to the restrictions of the linear regression methods, such models may not capture more complex nonlinear behaviors that exist in the data. Thus, this study comparatively investigates potential benefits from employing other machine learning techniques as a statistical method in ground motion prediction such as Artificial Neural Network, Random Forest, and Support Vector Machine. The algorithms are adjusted to quantify event-to-event and site-to-site variability of the ground motions by implementing them as random effects in the proposed models to reduce the aleatory uncertainty. All the algorithms are trained using a selected database of 4,528 ground-motions, including 376 seismic events with magnitude 3 to 5.8, recorded over the hypocentral distance range of 4 to 500 km in Oklahoma, Kansas, and Texas since 2005. The main reason of the considered database stems from the recent increase in the seismicity rate of these states attributed to petroleum production and wastewater disposal activities, which necessities further investigation in the ground motion models developed for these states. Accuracy of the models in predicting intensity measures, generalization capability of the models for future data, as well as usability of the models are discussed in the evaluation process. The results indicate the algorithms satisfy some physically sound characteristics such as magnitude scaling distance dependency without requiring pre-defined equations or coefficients. Moreover, it is shown that, when sufficient data is available, all the alternative algorithms tend to provide more accurate estimates compared to the conventional linear regression-based method, and particularly, Random Forest outperforms the other algorithms. However, the conventional method is a better tool when limited data is available.

Keywords: artificial neural network, ground-motion models, machine learning, random forest, support vector machine

Procedia PDF Downloads 97

Authors: Tolulope A. Olukunle

Abstract:

Plastic waste management has emerged as one of the greatest challenges facing developing countries. This paper describes the design of various components of a plastic shredder. This machine is widely used in industries and recycling plants. The introduction of plastic shredder machine will promote reduction of post-consumer plastic waste accumulation and serves as a system for wealth creation and empowerment through conversion of waste into economically viable products. In this design research, a 10 kW electric motor with a rotational speed of 500 rpm was chosen to drive the shredder. A pulley size of 400 mm is mounted on the electric motor at a distance of 1000 mm away from the shredder pulley. The shredder rotational speed is 300 rpm.

Keywords: design, machine, plastic waste, recycling

Procedia PDF Downloads 294

Authors: Saleh Elawgali

Abstract:

Current spectrums of a four pole-pair, 400 kW induction machine were calculated for the cases of full symmetry and static eccentricity. The calculations involve integration of 93 electrical plus four mechanical ordinary differential equations. Electrical equations account for variable inductances affected by slotting and eccentricities. The calculations were followed by Fourier analysis of the stator currents in steady state operation. Zooms of the current spectrums, around the 50 Hz fundamental harmonic as well as of the main slot harmonic zone, were included. The spectrums included refer to both calculated and measured currents.

Keywords: diagnostic, harmonic, induction machine, spectrum

Procedia PDF Downloads 499

Authors: G. Götz, P. Stich, J. Backhaus, G. Reinhart

Abstract:

The rising demand for format-flexible packaging machines is caused by current market changes. Increasing the formatflexibility is a new goal for the packaging machine manufacturers’ product development process. There are no methodical or designorientated tools for a comprehensive consideration of this target. This paper defines the term format-flexibility in the context of packaging machines and shows the state-of-the-art for improving the changeover of production machines. The requirements for a new approach and the concept itself will be introduced, and the method elements will be explained. Finally, the use of the concept and the result of the development of a format-flexible packaging machine will be shown.

Keywords: packaging machine, format-flexibility, changeover, design method

Procedia PDF Downloads 413

Authors: Parsa Mahdavi, M. Amin Hariri-Ardebili

Abstract:

The development of accurate machine learning and deep learning models traditionally demands hands-on expertise and a solid background to fine-tune hyperparameters. With the continuous expansion of datasets in various scientific and engineering domains, researchers increasingly turn to machine learning methods to unveil hidden insights that may elude classic regression techniques. This surge in adoption raises concerns about the adequacy of the resultant meta-models and, consequently, the interpretation of the findings. In response to these challenges, automated machine learning (AutoML) emerges as a promising solution, aiming to construct machine learning models with minimal intervention or guidance from human experts. AutoML encompasses crucial stages such as data preparation, feature engineering, hyperparameter optimization, and neural architecture search. This paper provides a comprehensive overview of the principles underpinning AutoML, surveying several widely-used AutoML platforms. Additionally, the paper offers a glimpse into the application of AutoML on various engineering datasets. By comparing these results with those obtained through classical machine learning methods, the paper quantifies the uncertainties inherent in the application of a single ML model versus the holistic approach provided by AutoML. These examples showcase the efficacy of AutoML in extracting meaningful patterns and insights, emphasizing its potential to revolutionize the way we approach and analyze complex datasets.

Keywords: automated machine learning, uncertainty, engineering dataset, regression

Procedia PDF Downloads 38

Authors: Krishang Surapaneni

Abstract:

The goal of this project is to determine how to predict important aspects of options, including the ask price. We want to compare different machine learning models to learn the best model and the best hyperparameters for that model for this purpose and data set. Option pricing is a relatively new field, and it can be very complicated and intimidating, especially to inexperienced people, so we want to create a machine learning model that can predict important aspects of an option stock, which can aid in future research. We tested multiple different models and experimented with hyperparameter tuning, trying to find some of the best parameters for a machine-learning model. We tested three different models: a Random Forest Regressor, a linear regressor, and an MLP (multi-layer perceptron) regressor. The most important feature in this experiment is the ask price; this is what we were trying to predict. In the field of stock pricing prediction, there is a large potential for error, so we are unable to determine the accuracy of the models based on if they predict the pricing perfectly. Due to this factor, we determined the accuracy of the model by finding the average percentage difference between the predicted and actual values. We tested the accuracy of the machine learning models by comparing the actual results in the testing data and the predictions made by the models. The linear regression model performed worst, with an average percentage error of 17.46%. The MLP regressor had an average percentage error of 11.45%, and the random forest regressor had an average percentage error of 7.42%

Keywords: finance, linear regression model, machine learning model, neural network, stock price

Procedia PDF Downloads 58

Authors: Dulanjali Ranasinghe, Isuru Supasan, Kaushalya Premachandra, Ranjan Dissanayake, Ajith Rajapaksha, Eustace Fernando

Abstract:

Proteomics studies of organisms are considered to be significantly information-rich compared to their genomic counterparts because proteomes of organisms represent the expressed state of all proteins of an organism at a given time. In modern top-down and bottom-up proteomics workflows, the primary analysis methods employed are gel–based methods such as two-dimensional (2D) electrophoresis and mass spectrometry based methods. Machine learning (ML) and artificial intelligence (AI) have been used increasingly in modern biological data analyses. In particular, the fields of genomics, DNA sequencing, and bioinformatics have seen an incremental trend in the usage of ML and AI techniques in recent years. The use of aforesaid techniques in the field of proteomics studies is only beginning to be materialised now. Although there is a wealth of information available in the scientific literature pertaining to proteomics workflows, no comprehensive review addresses various aspects of the combined use of proteomics and machine learning. The objective of this review is to provide a comprehensive outlook on the application of machine learning into the known proteomics workflows in order to extract more meaningful information that could be useful in a plethora of applications such as medicine, agriculture, and biotechnology.

Keywords: proteomics, machine learning, gel-based proteomics, mass spectrometry

Procedia PDF Downloads 129

Authors: Rufus Olufemi Adebayo, Sylvia Phiwani Zulu

Abstract:

Interpreting in the setting of diverse language and multicultural congregants, is often understood as integrating the content of the message. Preaching, similar to any communication, takes seriously people’s multiple contexts. The one who provides the best insight into understanding “the other”, traditionally speaking could be an interpreter in a multilingual context. Nonetheless, there are reflections in the loss of spiritual communication, translation and interpretive dialogue. No matter how eloquent the preacher is, an interpreter can make or mere the sermon (speech). The sermon that the preacher preaches is not always the one the congregation hears from the interpreter. In other occurrences, however, interpreting can lead not only to distort messages but also to dissatisfied audiences and preacher being overshadowed by the pranks of the interpreter. Using qualitative methodology, this paper explores the challenges and the conventional assumptions about preachers’ interpreter as influenced by spirituality, culture, and language in empirical and theoretical perspectives. An emphasis on the bias translation and the basis of reality that suppresses or devalues the spiritual communication is examined. The result indicates that interpretation of the declaration of guilt, history of congregation, spirituality, attitudes, morals, customs, specific practices of a preacher, education, and the environment form an entangled and misinterpretation. The article concludes by re-examining these qualities and rearticulating them into a preliminary theory for practice, as distinguished from theory, which could possibly enhance the development of more sustainable multilingual interpretation in the South African Pentecostal churches.

Keywords: congregants, divergences, interpreting/translation, language & communication, sermon/preaching

Procedia PDF Downloads 133

Authors: Maria Ezziani, Rabie Zine, Amine Amar, Ilhame Kissani

Abstract:

This paper introduces a predictive model for urban transportation engineering, which is vital for efficient traffic management. Utilizing comprehensive datasets and advanced statistical techniques, the model accurately forecasts travel times by considering temporal variations and traffic dynamics. Machine learning algorithms, including regression trees and neural networks, are employed to capture sequential dependencies. Results indicate significant improvements in predictive accuracy, particularly during peak hours and holidays, with the incorporation of traffic flow and speed variables. Future enhancements may integrate weather conditions and traffic incidents. The model's applications range from adaptive traffic management systems to route optimization algorithms, facilitating congestion reduction and enhancing journey reliability. Overall, this research extends beyond travel time estimation, offering insights into broader transportation planning and policy-making realms, empowering stakeholders to optimize infrastructure utilization and improve network efficiency.

Keywords: predictive analytics, traffic flow, travel time estimation, urban transportation, machine learning, traffic management

Procedia PDF Downloads 41

Authors: Raja Lahiani

Abstract:

'Locksley Hall' is a poem that Lord Alfred Tennyson (1809-1892) published in 1842. It is believed to be his first attempt to face as a poet some of the most painful of his experiences, as it is a study of his rising out of sickness into health, conquering his selfish sorrow by faith and hope. So far, in Victorian scholarship as in modern criticism, 'Locksley Hall' has been studied and approached as a canonical Victorian English poem. The aim of this project is to prove that some strategies of translation were used in this poem in such a way as to guarantee its assimilation into the English canon and hence efface to a large extent its Arabic roots. In its relationship with its source text, 'Locksley Hall' is at the same time mimetic and imitative. As part of the terminology used in translation studies, ‘imitation’ means almost the exact opposite of what it means in ordinary English. By adopting an imitative procedure, a translator would do something totally different from the original author, wandering far and freely from the words and sense of the original text. An imitation is thus aimed at an audience which wants the work of the particular translator rather than the work of the original poet. Hallam Tennyson, the poet’s biographer, asserts that 'Locksley Hall' is a simple invention of place, incidents, and people, though he notes that he remembers the poet claiming that Sir William Jones’ prose translation of the Mu‘allaqat (pre-Islamic poems) gave him the idea of the poem. A comparative work would prove that 'Locksley Hall' mirrors a great deal of Tennyson’s biography and hence is not a simple invention of details as asserted by his biographer. It would be challenging to prove that 'Locksley Hall' shares so many details with the Mu‘allaqat, as declared by Tennyson himself, that it needs to be studied as an imitation of the Mu‘allaqat of Imru’ al-Qays and ‘Antara in addition to its being a poem in its own right. Thus, the main aim of this work is to unveil the imitative and mimetic strategies used by Tennyson in his composition of 'Locksley Hall.' It is equally important that this project researches the acculturating assimilative tools used by the poet to root his poem in its Victorian English literary, cultural and spatiotemporal settings. This work adopts a comparative methodology. Comparison is done at different levels. The poem will be contextualized in its Victorian English literary framework. Alien details related to structure, socio-spatial setting, imagery and sound effects shall be compared to Arabic poems from the Mu‘allaqat collection. This would determine whether the poem is a translation, an adaption, an imitation or a genuine work. The ultimate objective of the project is to unveil in this canonical poem a new dimension that has for long been either marginalized or ignored. By proving that 'Locksley Hall' is an imitation of classical Arabic poetry, the project aspires to consolidate its literary value and open up new gates of accessing it.

Keywords: comparative literature, imitation, Locksley Hall, Lord Alfred Tennyson, translation, Victorian poetry

Procedia PDF Downloads 178

Authors: Hailyie Tekleselase

Abstract:

Deep learning is increasingly used as a building block of security systems. However, neural networks are hard to interpret and typically solid to the practitioner. This paper presents a detail survey of computing methods in cyber security, and analyzes the prospects of enhancing the cyber security capabilities by suggests that of accelerating the intelligence of the security systems. There are many AI-based applications used in industrial scenarios such as Internet of Things (IoT), smart grids, and edge computing. Machine learning technologies require a training process which introduces the protection problems in the training data and algorithms. We present machine learning techniques currently applied to the detection of intrusion, malware, and spam. Our conclusions are based on an extensive review of the literature as well as on experiments performed on real enterprise systems and network traffic. We conclude that problems can be solved successfully only when methods of artificial intelligence are being used besides human experts or operators.

Keywords: artificial intelligence, machine learning, deep learning, cyber security, big data

Procedia PDF Downloads 102

Authors: Chia-Chen Wei, Pack Hsieh, Jeffrey Chen

Abstract:

Surface Mount Technology (SMT) is widely used in the area of the electronic assembly in which the electronic components are mounted to the surface of the printed circuit board (PCB). Most of the defects in the SMT process are mainly related to the quality of solder paste printing. These defects lead to considerable manufacturing costs in the electronics assembly industry. Therefore, the solder paste inspection (SPI) machine for controlling and monitoring the amount of solder paste printing has become an important part of the production process. So far, the setting of the SPI threshold is based on statistical analysis and experts’ experiences to determine the appropriate threshold settings. Because the production data are not normal distribution and there are various variations in the production processes, defects related to solder paste printing still occur. In order to solve this problem, this paper proposes an online machine learning algorithm, called the automatic threshold adjustment (ATA) algorithm, and closed-loop architecture in the SMT process to determine the best threshold settings. Simulation experiments prove that our proposed threshold settings improve the accuracy from 99.85% to 100%.

Keywords: big data analytics, Industry 4.0, SPI threshold setting, surface mount technology

Procedia PDF Downloads 92

Authors: Elena Puica

Abstract:

This paper aims to investigate the impact of Supply Chain Management (SCM) on the environment by applying a Machine Learning model while pointing out the efficiency of the technology used. The Machine Learning model was used to derive the efficiency and optimization of technology used in SCM and the environmental impact of SCM processes. The model applied is a predictive classification model and was trained firstly to determine which stage of the SCM has more outputs and secondly to demonstrate the efficiency of using advanced technology in SCM instead of recuring to traditional SCM. The outputs are the emissions generated in the environment, the consumption from different steps in the life cycle, the resulting pollutants/wastes emitted, and all the releases to air, land, and water. This manuscript presents an innovative approach to applying advanced technology in SCM and simultaneously studies the efficiency of technology and the SCM's impact on the environment. Identifying the conceptual relationships between SCM practices and their impact on the environment is a new contribution to the research. The authors can take a forward step in developing recent studies in SCM and its effects on the environment by applying technology.

Keywords: machine-learning model in SCM, SCM processes, SCM and the environmental impact, technology in SCM

Procedia PDF Downloads 94

Authors: Cristina Vatamanu, Doina Cosovan, Dragos Gavrilut, Henri Luchian

Abstract:

In the past few years, the amount of malicious software increased exponentially and, therefore, machine learning algorithms became instrumental in identifying clean and malware files through semi-automated classification. When working with very large datasets, the major challenge is to reach both a very high malware detection rate and a very low false positive rate. Another challenge is to minimize the time needed for the machine learning algorithm to do so. This paper presents a comparative study between different machine learning techniques such as linear classifiers, ensembles, decision trees or various hybrids thereof. The training dataset consists of approximately 2 million clean files and 200.000 infected files, which is a realistic quantitative mixture. The paper investigates the above mentioned methods with respect to both their performance (detection rate and false positive rate) and their practicability.

Keywords: ensembles, false positives, feature selection, one side class algorithm

Procedia PDF Downloads 263

Authors: B. S. Premalatha, Kausalya Sahani

Abstract:

Background: Voice is multidimensional which convey emotion, feelings, and communication. Voice disorders have an adverse effect on the physical, emotional and functional domains of an individual. Self-rating by clients about their voice problem helps the clinicians to plan intervention strategies. Voice handicap index is one such self-rating scale contains 30 questions that quantify the functional, physical and emotional impacts of a voice disorder on a patient’s quality of life. Each subsection has 10 questions. Though adapted and validated versions of VHI are available in other Indian languages but not in Telugu, which is a Dravidian language native to India. It is mainly spoken in Andhra Pradesh and neighbouring states in southern India. Objectives: To adapt and validate the English version of Voice Handicap Index (VHI) into Telugu language and evaluate its internal consistency and clinical validate in Telugu speaking population. Materials: The study carried out in three stages. First stage was a forward translation of English version of VHI, was given to ten experts, who were well proficient in writing and reading Telugu and five speech-language pathologists to translate into Telugu. Second Stage was backward translation where translated version of Telugu was given to a different group of ten experts (who were well proficient in writing and reading Telugu) and five speech-language pathologists who were native Telugu speakers and had good proficiency in Telugu and English. The third stage was an administration of translated version on Telugu to the targeted population. Totally 40 clinical subjects and 40 normal controls served as participants, and each group had 26 males and 14 females’ age range of 20 to 60 years. Clinical group comprised of individuals with laryngectomee with the Tracheoesophageal puncture (n=18), laryngitis (n=11), vocal nodules (n=7) and vocal fold palsy (n=4). Participants were asked to mark of their each experience on a 5 point equal appearing scale (0=never, 1=almost never, 2=sometimes, 3=almost always, 4=always) with a maximum total score of 120. Results: Statistical analysis was made by using SPSS software (22.0.0 Version). Mean, standard deviation and percentage (%) were calculated all the participants for both the groups. Internal consistency of VHI in Telugu was found to be excellent with the consistency scores for all the domains such as physical, emotional and functional are 0.742, 0.934and 0.938. The validity of scores showed a significant difference between clinical population and control group for domains like physical, emotional and functional and total scores. P value found to be less than 0.001( < 0.001). Negative correlation found in age and gender among self-domains such as physical, emotional and functional total scores in dysphonic and control group. Conclusion: The present study indicated that VHI in Telugu is able to discriminate participants having voice pathology from normal populations, which make this as a valid tool to collect information about their voice from the participants.

Keywords: adaptation, Telugu Version, translation, Voice Handicap Index (VHI)

Procedia PDF Downloads 259

Authors: Alaa El-Din Rezk

Abstract:

In Egypt, management of crops still away from what is being used today by utilizing the advances of mechanical design capabilities, sensing and electronics technology. These technologies have been introduced in many places and recorm, for Straight Path, Curved Path, Sine Wave ded high accuracy in different field operations. So, an autonomous robotic platform based on machine vision has been developed and constructed to be implemented in Egyptian conditions as self-propelled mobile vehicle for carrying tools for inter/intra-row crop management based on different control modules. The experiments were carried out at plant protection research institute (PPRI) during 2014-2015 to optimize the accuracy of agricultural robotic platform control using machine vision in term of the autonomous navigation and performance of the robot’s guidance system. Results showed that the robotic platform' guidance system with machine vision was able to adequately distinguish the path and resisted image noise and did better than human operators for getting less lateral offset error. The average error of autonomous was 2.75, 19.33, 21.22, 34.18, and 16.69 mm. while the human operator was 32.70, 4.85, 7.85, 38.35 and 14.75 mm Path, Offset Discontinuity and Angle Discontinuity respectively.

Keywords: autonomous robotic, Hough transform, image processing, machine vision

Procedia PDF Downloads 286

Authors: Khalil Aryanfar, Pariya Gholipor, Elmira Hafez

Abstract:

This study examines the proportionality between the needs of industry and technical and vocational training of male and female vocational schools. The research method was descriptive that was conducted in two parts: documentary analysis and needs assessment and Delphi method was used in the need assessment. The statistical population of the study included 312 individuals from the industry sector employers and 52 of them were selected through stratified random sampling. Methods of data collection in this study, upstream documents include: document of the development of technical and vocational training, Statistical Yearbook 1393 in Tehran, the available documents in Isfahan Planning Department, the findings indicate that there is an almost proportionality between the needs of industry and Vocational training of male and female vocational schools in fields of welding, industrial electronics, electro technique, industrial drawing, auto mechanics, design, packaging, machine tool, metalworking, construction, accounting, computer graphics and the Administrative Affairs. The findings indicate that there is no proportionality between the needs of industry and Vocational training of male and female vocational schools in fields of Thermal - cooling systems, building electricity, building drawing, interior architecture, car electricity and motor repair.

Keywords: needs assessment, technical and vocational training, industry

Procedia PDF Downloads 427

Authors: Jian Wang, Lu Yang, Jiong Peng

Abstract:

Internal circulation two-platen clamping system for injection molding machine (IMM) has many potential advantages on energy-saving. In order to estimate its properties, experiments in this paper were carried out. Displacement and pressure of the components were measured. In comparison, the model of hydraulic clamping system was established by using AMESim. The related parameters as well as the energy consumption could be calculated. According to the analysis, the hydraulic system was optimized in order to reduce the energy consumption.

Keywords: AMESim, energy-saving, injection molding machine, internal circulation

Procedia PDF Downloads 520