Search results for: neural machine translation (NMT)

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 136

Authors: Jameela Ali, Hamid A. Jalab, Loay E. George, Abdul Rahim Ahmad, Azizah Suliman, Karim Al-Jashamy

Abstract:

Red blood cells (RBC) are the most common types of blood cells and are the most intensively studied in cell biology. The lack of RBCs is a condition in which the amount of hemoglobin level is lower than normal and is referred to as “anemia”. Abnormalities in RBCs will affect the exchange of oxygen. This paper presents a comparative study for various techniques for classifyig the red blood cells as normal, or abnormal (anemic) using WEKA. WEKA is an open source consists of different machine learning algorithms for data mining applications. The algorithm tested are Radial Basis Function neural network, Support vector machine, and K-Nearest Neighbors algorithm. Two sets of combined features were utilized for classification of blood cells images. The first set, exclusively consist of geometrical features, was used to identify whether the tested blood cell has a spherical shape or non-spherical cells. While the second set, consist mainly of textural features was used to recognize the types of the spherical cells. We have provided an evaluation based on applying these classification methods to our RBCs image dataset which were obtained from Serdang Hospital-Malaysia, and measuring the accuracy of test results. The best achieved classification rates are 97%, 98%, and 79% for Support vector machines, Radial Basis Function neural network, and K-Nearest Neighbors algorithm respectively

Keywords: red blood cells, classification, radial basis function neural networks, suport vector machine, k-nearest neighbors algorithm

Procedia PDF Downloads 480

Authors: Feng Yang

Abstract:

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

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

Procedia PDF Downloads 150

Authors: Ana Sofia Saldanha

Abstract:

The globalization is changing the translation world day after day, year after year. The need to know more about new technologies, clients, companies and social networks is becoming more and more demanding and competitive. The recently graduated translators usually do not know where to go, what to do or even who to contact to start their careers in translation. It is well known that there are innumerous webinars, books, blogs, webpages and even Facebook pages indicating what to do, what not to do, rates, how your CV should look like, etc. but are these pieces of advice of real translators? Translators, who work daily with clients, who understand their demands, requests, questions? As far as today`s trends, the answer is NO. Most of these pieces of advice are just theoretical and far away from the real translation world. Therefore, mentoring is becoming a very important tool to help and guide new translators starting their career. An effective and well-oriented mentoring is a powerful way to orient these translators on how to create their CVs, where to send CVs, how to approach clients, how to answer emails and how to negotiate rates in an efficient way. Mentoring is crucial when properly delivered by professional and experienced translators, to help developing careers. The advice and orientation sessions are almost a 'weapon' to destroy the barriers created by opinions, by influences or even by universities. This new trend is the future path of new translators and is the future of the translation industry and professionals, however minds and spirits need to be opened and engaged in this new way of developing skills.

Keywords: mentoring, translation, translators, orientation, professional path

Procedia PDF Downloads 179

Authors: Azene Zenebe

Abstract:

Deep learning is a subset of machine learning which incorporates techniques for the construction of artificial neural networks and found to be useful for modeling complex problems with large dataset. Deep learning requires a very high power computational and longer time for training. By aggregating computing power, high performance computer (HPC) has emerged as an approach to resolving advanced problems and performing data-driven research activities. Cyber threat intelligence (CIT) is actionable information or insight an organization or individual uses to understand the threats that have, will, or are currently targeting the organization. Results of review of literature will be presented along with results of experimental study that compares the performance of tree-based and function-base machine learning including deep learning algorithms using secondary dataset collected from darknet.

Keywords: deep-learning, cyber security, cyber threat modeling, tree-based machine learning, function-based machine learning, data science

Procedia PDF Downloads 153

Authors: Christopher Lama, Alix Rieser, Aleksandra Molchanova, Charles Thangaraj

Abstract:

New technologies like Tesla’s Dojo have made high-performance embedded computing more available. Although automobile computing has developed and benefited enormously from these more recent technologies, the costs are still high, prohibitively high in some cases for broader adaptation, particularly for the after-market and enthusiast markets. This project aims to implement a Raspberry Pi-based low-power (under one hundred Watts) highly mobile computing cluster for a neural network. The computing cluster built from off-the-shelf components is more affordable and, therefore, makes wider adoption possible. The paper describes the design of the neural network, Raspberry Pi-based cluster, and applications the cluster will run. The neural network will use input data from sensors and cameras to project a live view of the road state as the user drives. The neural network will be trained to predict traffic behavior and generate warnings when potentially dangerous situations are predicted. The significant outcomes of this study will be two folds, firstly, to implement and test the low-cost cluster, and secondly, to ascertain the effectiveness of the predictive AI implemented on the cluster.

Keywords: CS pedagogy, student research, cluster computing, machine learning

Procedia PDF Downloads 102

Authors: Mohammad Hamzah Alshehab

Abstract:

Metaphor is a substitute expression in everyday life in languages, thoughts and actions. It has an original value in language use with different conceptual, grammatical and properties. In addition, it is a central concept in literary studies. The present paper aims at investigating metaphor’s types imbedded in some Holy Verses (HV). For achieving the objectives of this paper, two English versions were chosen , the first is the Translation of the Meanings of the Noble Qura’n in the English Language by Mohammad AlHilali and Mohammad Khan, and the second version is the English Translation of the Holy Qura’n by Mohammad Ali were used. The researcher selected (20) Holy Verses include metaphors to be analyzed and investigated. Metaphor types were categorized by an assessment of the two translations followed by a discussion between the two versions of translation.

Keywords: metaphor, metaphor’s types, Holy Qura’n, Holy Verses

Procedia PDF Downloads 653

Authors: Amenador Kate Benedicta, Wang Zhiwei

Abstract:

Since the later parts of the 20th century, the notion of equivalence continues to be a central and critical concept in the development of translation theory. After decades of arguments over word-for-word and free translations methods, scholars attempting to develop more systematic and efficient translation theories began to focus on fundamental translation concepts such as equivalence. Although the concept of equivalence has piqued the interest of many scholars, its definition, scope, and applicability have sparked contentious arguments within the discipline. As a result, several distinct theories and explanations on the concept of equivalence have been put forward over the last half-century. Thus, this study explores and discusses the evolution of the critical concept of equivalence in translation studies through a bibliometric method of investigation of manual and digital books and articles by analyzing different scholars' key contributions and limitations on equivalence from various theoretical perspectives. While analyzing them, emphasis is placed on the innovations that each theory has brought to the comprehension of equivalence. In order to achieve the aim of the study, the article began by discussing the contributions of linguistically motivated theories to the notion of equivalence in translation, followed by functionalist-oriented contributions, before moving on to more recent advancements in translation studies on the concept. Because equivalence is such a broad notion, it is impossible to discuss each researcher in depth. As a result, the most well-known names and their equivalent theories are compared and contrasted in this research. The study emphasizes the developmental progression in our comprehension of the equivalence concept and equivalent effect. It concluded that the various theoretical perspective's contributions to the notion of equivalence rather complement and make up for the limitations of each other. The study also highlighted how troublesome the equivalent concept might become in terms of identifying the nature of translation and how central and unavoidable the concept is in every translation action, despite its limitations. The significance of the study lies in its synthesis of the different contributions and limitations of the various theories offered by scholars on the notion of equivalence, lending literature to both student and scholars in the field, and providing insight on future theoretical development

Keywords: equivalence, functionalist translation theories, linguistic translation approaches, translation theories, Skopos

Procedia PDF Downloads 113

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 276

Authors: Jun Wang, Ge Zhang

Abstract:

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

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

Procedia PDF Downloads 98

Authors: Sufia Maroof

Abstract:

This empirical study investigated the web-translations of five Pakistani public offices (FPSC, FIA, HEC, USB, and Ministry of Finance) offering Urdu tab as an option to access information on their official websites. Triangulation of quantitative and qualitative research design informed the researcher of the semantic, lexical and syntactic caveats in these translations. The study hypothesized that majority of the Pakistani population is oblivious of the Supreme Court’s amendments in language policy concerning national and official language; hence, Urdu web-translations of the public departments have not been accessed effectively. Firstly, the researcher conducted an online survey, comprising of two sections, close ended and short answer based questions. Secondly, the researcher compiled corpus of the five selected websites in a tabular form to compare the data. Thirdly, the administrators of the departments had been contacted regarding the methods of translation and the expertise of the personnel involved. The corpus was assessed for TQA after examining the lexical, semantic, syntactical and technical alignment inaccuracies and imperfections. The study suggests the public offices to invest in their Urdu webs by either hiring expert translators or engaging expertise of a translation agency for this project to offer quality translation to public.

Keywords: machine translations, public offices, Urdu translations, websites

Procedia PDF Downloads 126

Authors: Chinchira Bunchutrakun

Abstract:

The purposes of the study are to investigate the problems that the translators encountered when translating English idioms into Thai and study the strategies they applied in solving the problems. The original English version and the Thai translated version of each of two works of fiction were purposively selected for the study. The first was Mr. Maybe, written by Jane Green and translated by Montharat Songphao. The second was The Trials of Tiffany Trott, written by Isabel Wolff and translated by Jitraporn Notoda. Thirty idioms of two translated works of fiction were, then, analyzed. Questionnaires and interviews with the translators of each novel were conducted to obtain the best possible information. The results indicated that the only type of problem that occurred was cultural problems, and these were solved differently by the two translators.

Keywords: translation, idiom translation, fiction translation, problem-solution strategies

Procedia PDF Downloads 298

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

In the precision agriculture area, one of the main tasks is the automated detection of diseases in crops. Machine Learning algorithms have been studied in recent decades for such tasks in view of their potential for improving economic outcomes that automated disease detection may attain over crop fields. The latest generation of deep learning convolution neural networks has presented significant results in the area of image classification. In this way, this work has tested the implementation of an architecture of deep learning convolution neural network for the detection of diseases in different types of crops. A data augmentation strategy was used to meet the requirements of the algorithm implemented with a deep learning framework. Two test scenarios were deployed. The first scenario implemented a neural network under images extracted from a controlled environment while the second one took images both from the field and the controlled environment. The results evaluated the generalisation capacity of the neural networks in relation to the two types of images presented. Results yielded a general classification accuracy of 59% in scenario 1 and 96% in scenario 2.

Keywords: convolutional neural networks, deep learning, disease detection, precision agriculture

Procedia PDF Downloads 259

Authors: Linghui Meng, James Atlas, Deborah Munro

Abstract:

There is an increasing demand for prosthetics capable of mimicking natural limb movements and hand gestures, but precise movement control of prosthetics using only electrode signals continues to be challenging. This study considers the implementation of machine learning as a means of improving accuracy and presents an initial investigation into hand gesture recognition using models based on electromyographic (EMG) signals. EMG signals, which capture muscle activity, are used as inputs to machine learning algorithms to improve prosthetic control accuracy, functionality and adaptivity. Using logistic regression, a machine learning classifier, this study evaluates the accuracy of classifying two hand gestures from the publicly available Ninapro dataset using two-time series feature extraction algorithms: Time Series Feature Extraction (TSFE) and Convolutional Neural Networks (CNNs). Trials were conducted using varying numbers of EMG channels from one to eight to determine the impact of channel quantity on classification accuracy. The results suggest that although both algorithms can successfully distinguish between hand gesture EMG signals, CNNs outperform TSFE in extracting useful information for both accuracy and computational efficiency. In addition, although more channels of EMG signals provide more useful information, they also require more complex and computationally intensive feature extractors and consequently do not perform as well as lower numbers of channels. The findings also underscore the potential of machine learning techniques in developing more effective and adaptive prosthetic control systems.

Keywords: EMG, machine learning, prosthetic control, electromyographic prosthetics, hand gesture classification, CNN, computational neural networks, TSFE, time series feature extraction, channel count, logistic regression, ninapro, classifiers

Procedia PDF Downloads 28

Authors: Feride Sumbul

Abstract:

Drama is a literary genre that mirrors the people and society and transfers the human nature and life to the reader or the audience within its own social-cultural structure. Each play takes on a new reality in the time and culture of the staging, and each performance actually brings a new interpretation to the play. Similarly, each translation adds a new meaning to the source text. In other words, the translated theatrical text transcends the boundaries of its language and culture and finds a new interpretation. Thus the translation of drama takes place as a transfer from one culture to another as a cross cultural communication. In this context, translating culture specific references play a key role in terms of reflecting cultural aspects of a target society. This study aims to explore the use of Venuti's translation principles of domestication and foreignization in the transfer of culture specific references in the Turkish translation of Shakespeare's Macbeth. Macbeth is to be compared with its Turkish version in terms of the transference of culture specific references such as religious, witchcraft, and mythological, which have no equivalent in the target language and culture. To evaluate these principles of Venuti, Davies’s translation strategies are also conducted. As a method, for the most part, he predominantly uses Davies’ method of ‘addition’ through adding extra information in the notes. For instance, rather than finding the Turkish renderings of them, the translator mostly chooses to transfer witchcraft references through retaining them in the target text, but he mainly adds extra information about the references in the notes. Therefore, the translator Nutku mostly uses Venuti’s translation principle of foreignization so that he preserves the foreignness of the theatrical text.

Keywords: drama translation, theatrical texts, culture specific references, Macbeth

Procedia PDF Downloads 157

Authors: Talal Alshammari, Nasser Alshammari, Mohamed Sedky, Chris Howard

Abstract:

With the widespread adoption of the Internet-connected devices, and with the prevalence of the Internet of Things (IoT) applications, there is an increased interest in machine learning techniques that can provide useful and interesting services in the smart home domain. The areas that machine learning techniques can help advance are varied and ever-evolving. Classifying smart home inhabitants’ Activities of Daily Living (ADLs), is one prominent example. The ability of machine learning technique to find meaningful spatio-temporal relations of high-dimensional data is an important requirement as well. This paper presents a comparative evaluation of state-of-the-art machine learning techniques to classify ADLs in the smart home domain. Forty-two synthetic datasets and two real-world datasets with multiple inhabitants are used to evaluate and compare the performance of the identified machine learning techniques. Our results show significant performance differences between the evaluated techniques. Such as AdaBoost, Cortical Learning Algorithm (CLA), Decision Trees, Hidden Markov Model (HMM), Multi-layer Perceptron (MLP), Structured Perceptron and Support Vector Machines (SVM). Overall, neural network based techniques have shown superiority over the other tested techniques.

Keywords: activities of daily living, classification, internet of things, machine learning, prediction, smart home

Procedia PDF Downloads 357

Authors: Esteban Tremoco

Abstract:

This article aims to highlight some specificities of translating Science Fiction (SF literature) and, more particularly, its comic subgenre. Translating SF presupposes the translation of neologisms and gadget names of all kinds, while the translation of humor sometimes implies a need for the translator to slightly modify certain scenes or situations. In the French translation of Douglas Adams' Hitchhiker's Guide to the Galaxy by Jean Bonnefoy (Guide du routard galactique, 1982), the humorous dimension of the book is enhanced through certain choices made by the translator. One of the striking aspects of this translation is that almost all of the characters’ names have been translated, which is not the case in the German, Italian, Spanish and Portuguese translations. While there may be translations of characters’ names outside of the SF literature, there is no denying that by translating them, Jean Bonnefoy added a humorous layer to Adams' work. This work belongs to science fiction literature thanks to gadgets resulting from futuristic technological innovations, but also the presence of space travel, extra-terrestrials and mysterious worlds, which are central elements in SF. These names of planets, aliens, and other gadgets have also been translated, adapted, or at least reinvented, by Jean Bonnefoy in order to amuse the French-speaking readership.

Keywords: translation, translation studies, humour, science fiction

Procedia PDF Downloads 82

Authors: Najmeh Mohsenifar, Narjes Mohsenifar, Abbas Kargar

Abstract:

In this paper, has been presented a stable method for predicting the ECG signals through the RBF neural networks, by the PSO algorithm. In spite of quasi-periodic ECG signal from a healthy person, there are distortions in electro cardiographic data for a patient. Therefore, there is no precise mathematical model for prediction. Here, we have exploited neural networks that are capable of complicated nonlinear mapping. Although the architecture and spread of RBF networks are usually selected through trial and error, the PSO algorithm has been used for choosing the best neural network. In this way, 2 second of a recorded ECG signal is employed to predict duration of 20 second in advance. Our simulations show that PSO algorithm can find the RBF neural network with minimum MSE and the accuracy of the predicted ECG signal is 97 %.

Keywords: electrocardiogram, RBF artificial neural network, PSO algorithm, predict, accuracy

Procedia PDF Downloads 626

Authors: Christoph Linse, Thomas Martinetz

Abstract:

Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.

Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets

Procedia PDF Downloads 88

Authors: Edward Guillén, Jhordany Rodriguez, Rafael Páez

Abstract:

Anomaly detection techniques have been focused on two main components: data extraction and selection and the second one is the analysis performed over the obtained data. The goal of this paper is to analyze the influence that each of these components has over the system performance by evaluating detection over network scenarios with different setups. The independent variables are as follows: the number of system inputs, the way the inputs are codified and the complexity of the analysis techniques. For the analysis, some approaches of artificial neural networks are implemented with different number of layers. The obtained results show the influence that each of these variables has in the system performance.

Keywords: network intrusion detection, machine learning, artificial neural network, anomaly detection module

Procedia PDF Downloads 341

Authors: Diego De Almeida Pereira, Diana Borchenko

Abstract:

Artificial neural networks are used for many applications as they are able to learn complex nonlinear relationships between input and output data. As the number of neurons and layers in a neural network increases, it is possible to represent more complex behaviors. The present study proposes that artificial neural networks are a valuable tool for architecture and engineering professionals concerned with understanding how buildings influence human and social well-being based on theories of environmental psychology.

Keywords: environmental psychology, architecture, neural networks, human and social well-being

Procedia PDF Downloads 495

Authors: Yash Jain

Abstract:

The US Center for Disease Control has recommended wearing masks to slow the spread of the virus. The research uses a video feed from a camera to conduct real-time classifications of whether or not a human is correctly wearing a mask, incorrectly wearing a mask, or not wearing a mask at all. Utilizing two distinct datasets from the open-source website Kaggle, a mask detection network had been trained. The first dataset that was used to train the model was titled 'Face Mask Detection' on Kaggle, where the dataset was retrieved from and the second dataset was titled 'Face Mask Dataset, which provided the data in a (YOLO Format)' so that the TinyYoloV3 model could be trained. Based on the data from Kaggle, two machine learning models were implemented and trained: a Tiny YoloV3 Real-time model and a two-stage neural network classifier. The two-stage neural network classifier had a first step of identifying distinct faces within the image, and the second step was a classifier to detect the state of the mask on the face and whether it was worn correctly, incorrectly, or no mask at all. The TinyYoloV3 was used for the live feed as well as for a comparison standpoint against the previous two-stage classifier and was trained using the darknet neural network framework. The two-stage classifier attained a mean average precision (MAP) of 80%, while the model trained using TinyYoloV3 real-time detection had a mean average precision (MAP) of 59%. Overall, both models were able to correctly classify stages/scenarios of no mask, mask, and incorrectly worn masks.

Keywords: datasets, classifier, mask-detection, real-time, TinyYoloV3, two-stage neural network classifier

Procedia PDF Downloads 161

Authors: Boudersa Said Sami

Abstract:

This paper aims at revealing the new role of the African translator as a progressive traveler in the thoughts and minds of both Africans and others via his/her multidimensional translations, and a particular focus will be here on literary translation. The African translator, in this respect, is a great actor in Africa’s literary, intellectual and philosophical movement through his exploration of great literary books and highly-echoed intellectual masterpieces via translation. The paper’s hypothesis revolves around the importance of the African translator in moving from one thought to another as shifting from one language to another (French to English or English to French and Arabic). Unless the African translator is alert-minded, lively and animated, the African thoughts are stagnant and Africa is a big mire of rotten ideas. African thoughts are alive, providing that translation is vivid. The findings of the paper reveal the significance of the African translator’s multidimensional roles in keeping Africa in movement. As a pertinent recommendation, translation in Africa should be fostered and its tools should be enhanced as well to keep Africa’s thoughts in continuous mobility between geographic areas as languages are in a progressive move through translation.

Keywords: African, translator, literary, globetrotter, movement

Procedia PDF Downloads 156

Authors: Robert Poenaru, Mihail Pleşa

Abstract:

In this work, a solution that addresses the protection of pre-trained neural networks is developed: Singularization. This method involves applying permutations to the weight matrices of a pre-trained model, introducing a form of structured noise that obscures the original model’s architecture. These permutations make it difficult for an attacker to reconstruct the original model, even if the permuted weights are obtained. Experimental benchmarks indicate that the application of singularization has a profound impact on model performance, often degrading it to the point where retraining from scratch becomes necessary to recover functionality, which is particularly effective for securing intellectual property in neural networks. Moreover, unlike other approaches, singularization is lightweight and computationally efficient, which makes it well suited for resource-constrained environments. Our experiments also demonstrate that this technique performs efficiently in various image classification tasks, highlighting its broad applicability and practicality in real-world scenarios.

Keywords: machine learning, ANE, CNN, security

Procedia PDF Downloads 14

Authors: J. K. Alhassan, B. Attah, S. Misra

Abstract:

Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. medical dataset is a vital ingredient used in predicting patients health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. The evaluations was done using weka software and found out that DTA performed better than ANN. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. The Root Mean Squared Error (RMSE) of MLP is 0.3913,that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.

Keywords: artificial neural network, classification, decision tree algorithms, diabetes mellitus

Procedia PDF Downloads 408

Authors: Susan Diamond

Abstract:

Machine Learning workloads have traditionally been run in high-performance computing (HPC) environments, where users log in to dedicated machines and utilize the attached GPUs to run training jobs on huge datasets. Training of large neural network models is very resource intensive, and even after exploiting parallelism and accelerators such as GPUs, a single training job can still take days. Consequently, the cost of hardware is a barrier to entry. Even when upfront cost is not a concern, the lead time to set up such an HPC environment takes months from acquiring hardware to set up the hardware with the right set of firmware, software installed and configured. Furthermore, scalability is hard to achieve in a rigid traditional lab environment. Therefore, it is slow to react to the dynamic change in the artificial intelligent industry. Watson Deep Learning as a service, a cloud-based deep learning platform that mitigates the long lead time and high upfront investment in hardware. It enables robust and scalable sharing of resources among the teams in an organization. It is designed for on-demand cloud environments. Providing a similar user experience in a multi-tenant cloud environment comes with its own unique challenges regarding fault tolerance, performance, and security. Watson Deep Learning as a service tackles these challenges and present a deep learning stack for the cloud environments in a secure, scalable and fault-tolerant manner. It supports a wide range of deep-learning frameworks such as Tensorflow, PyTorch, Caffe, Torch, Theano, and MXNet etc. These frameworks reduce the effort and skillset required to design, train, and use deep learning models. Deep Learning as a service is used at IBM by AI researchers in areas including machine translation, computer vision, and healthcare. 

Keywords: deep learning, machine learning, cognitive computing, model training

Procedia PDF Downloads 208

Authors: Farina Riaz, Shahab Abdulla, Srinjoy Ganguly, Hajime Suzuki, Ravinesh C. Deo, Susan Hopkins

Abstract:

Recently, quantum machine learning has received significant attention. For various types of data, including text and images, numerous quantum machine learning (QML) models have been created and are being tested. Images are exceedingly complex data components that demand more processing power. Despite being mature, classical machine learning still has difficulties with big data applications. Furthermore, quantum technology has revolutionized how machine learning is thought of, by employing quantum features to address optimization issues. Since quantum hardware is currently extremely noisy, it is not practicable to run machine learning algorithms on it without risking the production of inaccurate results. To discover the advantages of quantum versus classical approaches, this research has concentrated on colored image data. Deep learning classification models are currently being created on Quantum platforms, but they are still in a very early stage. Black and white benchmark image datasets like MNIST and Fashion MINIST have been used in recent research. MNIST and CIFAR-10 were compared for binary classification, but the comparison showed that MNIST performed more accurately than colored CIFAR-10. This research will evaluate the performance of the QML algorithm on the colored benchmark dataset CIFAR-10 to advance QML's real-time applicability. However, deep learning classification models have not been developed to compare colored images like Quantum Convolutional Neural Network (QCNN) to determine how much it is better to classical. Only a few models, such as quantum variational circuits, take colored images. The methodology adopted in this research is a hybrid approach by using penny lane as a simulator. To process the 10 classes of CIFAR-10, the image data has been translated into grey scale and the 28 × 28-pixel image containing 10,000 test and 50,000 training images were used. The objective of this work is to determine how much the quantum approach can outperform a classical approach for a comprehensive dataset of color images. After pre-processing 50,000 images from a classical computer, the QCNN model adopted a hybrid method and encoded the images into a quantum simulator for feature extraction using quantum gate rotations. The measurements were carried out on the classical computer after the rotations were applied. According to the results, we note that the QCNN approach is ~12% more effective than the traditional classical CNN approaches and it is possible that applying data augmentation may increase the accuracy. This study has demonstrated that quantum machine and deep learning models can be relatively superior to the classical machine learning approaches in terms of their processing speed and accuracy when used to perform classification on colored classes.

Keywords: CIFAR-10, quantum convolutional neural networks, quantum deep learning, quantum machine learning

Procedia PDF Downloads 129

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 113

Authors: Gürkan Dağbaşı

Abstract:

Translation is a vitally important activity like as the expression the thought and emotions of humanbeing, providing reciprocal cultural transfer, shaping future by establishing a connection with the past, and like as being exist in an other language. Translation is also an important instrument providing cross-cultural coalescence between nations. Although the first translations from Arabic to Turkish was restricted to only religious texts, over time, the importance of translation was found out via translations of works about literature. Later on, some literature genres like novel and poems were also translated from Arabic to Turkish. Works of many men of Arabic literature were translated to Turkish, including Nejib Mahfuz, owner of Nobel Prize, Tawfiq al-Hakim, Adonis, Gibran Khalil Gibran and etc. In this study, novels and poems translated from Arabic to Turkish between 1980-2015 years are examined.

Keywords: poem, novel, Arabic, translation

Procedia PDF Downloads 374

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 150