Search results for: deep learnig

Authors: Yuta Nakano, Kozo Kajiwara, Atsushi Hori, Takeshi Fujita

Abstract:

In association with the wave of electric vehicles (EV), low energy consumption systems have become more and more important. One of the key technologies to realize low energy consumption is a dynamic vision sensor (DVS), or we can call it an event sensor, neuromorphic vision sensor and so on. This sensor has several features, such as high temporal resolution, which can achieve 1 Mframe/s, and a high dynamic range (120 DB). However, the point that can contribute to low energy consumption the most is its sparsity; to be more specific, this sensor only captures the pixels that have intensity change. In other words, there is no signal in the area that does not have any intensity change. That is to say, this sensor is more energy efficient than conventional sensors such as RGB cameras because we can remove redundant data. On the other side of the advantages, it is difficult to handle the data because the data format is completely different from RGB image; for example, acquired signals are asynchronous and sparse, and each signal is composed of x-y coordinate, polarity (two values: +1 or -1) and time stamp, it does not include intensity such as RGB values. Therefore, as we cannot use existing algorithms straightforwardly, we have to design a new processing algorithm to cope with DVS data. In order to solve difficulties caused by data format differences, most of the prior arts make a frame data and feed it to deep learning such as Convolutional Neural Networks (CNN) for object detection and recognition purposes. However, even though we can feed the data, it is still difficult to achieve good performance due to a lack of intensity information. Although polarity is often used as intensity instead of RGB pixel value, it is apparent that polarity information is not rich enough. Considering this context, we proposed to use the timestamp information as a data representation that is fed to deep learning. Concretely, at first, we also make frame data divided by a certain time period, then give intensity value in response to the timestamp in each frame; for example, a high value is given on a recent signal. We expected that this data representation could capture the features, especially of moving objects, because timestamp represents the movement direction and speed. By using this proposal method, we made our own dataset by DVS fixed on a parked car to develop an application for a surveillance system that can detect persons around the car. We think DVS is one of the ideal sensors for surveillance purposes because this sensor can run for a long time with low energy consumption in a NOT dynamic situation. For comparison purposes, we reproduced state of the art method as a benchmark, which makes frames the same as us and feeds polarity information to CNN. Then, we measured the object detection performances of the benchmark and ours on the same dataset. As a result, our method achieved a maximum of 7 points greater than the benchmark in the F1 score.

Keywords: event camera, dynamic vision sensor, deep learning, data representation, object recognition, low energy consumption

Procedia PDF Downloads 75

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 117

Authors: William C. Alexander

Abstract:

The oscillating water column (OSC) wave energy converter (WEC) with deep water reactance (DWR) consists of a large hollow sphere filled with seawater at the base, referred to as the ‘stabilizer’, a hollow cylinder at the top of the device, with a said cylinder having a bottom open to the sea and a sealed top save for an orifice which leads to an air turbine, and a long, narrow rod connecting said stabilizer with said cylinder. A small amount of ballast at the bottom of the stabilizer and a small amount of floatation in the cylinder keeps the device upright in the sea. The floatation is set such that the mean water level is nominally halfway up the cylinder. The entire device is loosely moored to the seabed to keep it from drifting away. In the presence of ocean waves, seawater will move up and down within the cylinder, producing the ‘oscillating water column’. This gives rise to air pressure within the cylinder alternating between positive and negative gauge pressure, which in turn causes air to alternately leave and enter the cylinder through said top-cover situated orifice. An air turbine situated within or immediately adjacent to said orifice converts the oscillating airflow into electric power for transport to shore or elsewhere by electric power cable. Said oscillating air pressure produces large up and down forces on the cylinder. Said large forces are opposed through the rod to the large mass of water retained within the stabilizer, which is located deep enough to be mostly free of any wave influence and which provides the deepwater reactance. The cylinder and stabilizer form a spring-mass system which has a vertical (heave) resonant frequency. The diameter of the cylinder largely determines the power rating of the device, while the size (and water mass within) of the stabilizer determines said resonant frequency. Said frequency is chosen to be on the lower end of the wave frequency spectrum to maximize the average power output of the device over a large span of time (such as a year). The upper portion of the device (the cylinder) moves laterally (surge) with the waves. This motion is accommodated with minimal loading on the said rod by having the stabilizer shaped like a sphere, allowing the entire device to rotate about the center of the stabilizer without rotating the seawater within the stabilizer. A full-scale device of this type may have the following dimensions. The cylinder may be 16 meters in diameter and 30 meters high, the stabilizer 25 meters in diameter, and the rod 55 meters long. Simulations predict that this will produce 1,400 kW in waves of 3.5-meter height and 12 second period, with a relatively flat power curve between 5 and 16 second wave periods, as will be suitable for an open-ocean location. This is nominally 10 times higher power than similar-sized WEC spar buoys as reported in the literature, and the device is projected to have only 5% of the mass per unit power of other OWC converters.

Keywords: oscillating water column, wave energy converter, spar bouy, stabilizer

Procedia PDF Downloads 86

Authors: Shraddha Jain Sharma, Ratnalata Gupta

Abstract:

Predicting stock movements in the financial market is both difficult and rewarding. Analysts and academics are increasingly using advanced approaches such as machine learning techniques to anticipate stock price patterns, thanks to the expanding capacity of computing and the recent advent of graphics processing units and tensor processing units. Stock market prediction is a type of time series prediction that is incredibly difficult to do since stock prices are influenced by a variety of financial, socioeconomic, and political factors. Furthermore, even minor mistakes in stock market price forecasts can result in significant losses for companies that employ the findings of stock market price prediction for financial analysis and investment. Soft computing techniques are increasingly being employed for stock market prediction due to their better accuracy than traditional statistical methodologies. The proposed research looks at the need for soft computing techniques in stock market prediction, the numerous soft computing approaches that are important to the field, past work in the area with their prominent features, and the significant problems or issue domain that the area involves. For constructing a predictive model, the major focus is on neural networks and fuzzy logic. The stock market is extremely unpredictable, and it is unquestionably tough to correctly predict based on certain characteristics. This study provides a complete overview of the numerous strategies investigated for high accuracy prediction, with a focus on the most important characteristics.

Keywords: stock market prediction, artificial intelligence, artificial neural networks, fuzzy logic, accuracy, deep learning, machine learning, stock price, trading volume

Procedia PDF Downloads 64

Authors: Hayriye Anıl, Görkem Kar

Abstract:

In addition to being rich in renewable energy resources, Turkey is one of the countries that promise potential in geothermal energy production with its high installed power, cheapness, and sustainability. Increasing imbalance penalties become an economic burden for organizations since geothermal generation plants cannot maintain the balance of supply and demand due to the inadequacy of the production forecasts given in the day-ahead market. A better production forecast reduces the imbalance penalties of market participants and provides a better imbalance in the day ahead market. In this study, using machine learning, deep learning, and, time series methods, the total generation of the power plants belonging to Zorlu Natural Electricity Generation, which has a high installed capacity in terms of geothermal, was estimated for the first one and two weeks of March, then the imbalance penalties were calculated with these estimates and compared with the real values. These modeling operations were carried out on two datasets, the basic dataset and the dataset created by extracting new features from this dataset with the feature engineering method. According to the results, Support Vector Regression from traditional machine learning models outperformed other models and exhibited the best performance. In addition, the estimation results in the feature engineering dataset showed lower error rates than the basic dataset. It has been concluded that the estimated imbalance penalty calculated for the selected organization is lower than the actual imbalance penalty, optimum and profitable accounts.

Keywords: machine learning, deep learning, time series models, feature engineering, geothermal energy production forecasting

Procedia PDF Downloads 87

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 154

Authors: Qingsong Xiong, Cheng Yuan, Qingzhao Kong, Haibei Xiong

Abstract:

Deep-learning-driven approaches based on vibration responses have attracted larger attention in rapid structural condition assessment while obtaining sufficient measured training data with corresponding labels is relevantly costly and even inaccessible in practical engineering. This study proposes an integrated label propagation network for structural condition assessment, which is able to diffuse the labels from continuously-generating measurements by intact structure to those of missing labels of damage scenarios. The integrated network is embedded with damage-sensitive features extraction by deep autoencoder and pseudo-labels propagation by optimized fuzzy clustering, the architecture and mechanism which are elaborated. With a sophisticated network design and specified strategies for improving performance, the present network achieves to extends the superiority of self-supervised representation learning, unsupervised fuzzy clustering and supervised classification algorithms into an integration aiming at assessing damage conditions. Both numerical simulations and full-scale laboratory shaking table tests of a two-story building structure were conducted to validate its capability of detecting post-earthquake damage. The identifying accuracy of a present network was 0.95 in numerical validations and an average 0.86 in laboratory case studies, respectively. It should be noted that the whole training procedure of all involved models in the network stringently doesn’t rely upon any labeled data of damage scenarios but only several samples of intact structure, which indicates a significant superiority in model adaptability and feasible applicability in practice.

Keywords: autoencoder, condition assessment, fuzzy clustering, label propagation

Procedia PDF Downloads 78

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.

Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning

Procedia PDF Downloads 143

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 40

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 67

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: deep neural models, natural language inference, recognizing textual entailment (RTE), sentence-to-sentence relation

Procedia PDF Downloads 327

Authors: Arina V. Tankanag, Gennady V. Krasnikov, Nikolai K. Chemeris

Abstract:

The development of respiration-dependent oscillations in the peripheral blood flow may occur by at least two mechanisms. The first mechanism is related to the change of venous pressure due to mechanical activity of lungs. This phenomenon is known as ‘respiratory pump’ and is one of the mechanisms of venous return of blood from the peripheral vessels to the heart. The second mechanism is related to the vasomotor reflexes controlled by the respiratory modulation of the activity of centers of the vegetative nervous system. Early high phase synchronization of respiration-dependent blood flow oscillations of left and right forearm skin in healthy volunteers at rest was shown. The aim of the work was to study the effect of deep controlled breathing on the phase synchronization of skin blood flow oscillations. 29 normotensive non-smoking young women (18-25 years old) of the normal constitution without diagnosed pathologies of skin, cardiovascular and respiratory systems participated in the study. For each of the participants six recording sessions were carried out: first, at the spontaneous breathing rate; and the next five, in the regimes of controlled breathing with fixed breathing depth and different rates of enforced breathing regime. The following rates of controlled breathing regime were used: 0.25, 0.16, 0.10, 0.07 and 0.05 Hz. The breathing depth amounted to 40% of the maximal chest excursion. Blood perfusion was registered by laser flowmeter LAKK-02 (LAZMA, Russia) with two identical channels (wavelength 0.63 µm; emission power, 0.5 mW). The first probe was fastened to the palmar surface of the distal phalanx of left forefinger; the second probe was attached to the external surface of the left forearm near the wrist joint. These skin zones were chosen as zones with different dominant mechanisms of vascular tonus regulation. The degree of phase synchronization of the registered signals was estimated from the value of the wavelet phase coherence. The duration of all recording was 5 min. The sampling frequency of the signals was 16 Hz. The increasing of synchronization of the respiratory-dependent skin blood flow oscillations for all controlled breathing regimes was obtained. Since the formation of respiration-dependent oscillations in the peripheral blood flow is mainly caused by the respiratory modulation of system blood pressure, the observed effects are most likely dependent on the breathing depth. It should be noted that with spontaneous breathing depth does not exceed 15% of the maximal chest excursion, while in the present study the breathing depth was 40%. Therefore it has been suggested that the observed significant increase of the phase synchronization of blood flow oscillations in our conditions is primarily due to an increase of breathing depth. This is due to the enhancement of both potential mechanisms of respiratory oscillation generation: venous pressure and sympathetic modulation of vascular tone.

Keywords: deep controlled breathing, peripheral blood flow oscillations, phase synchronization, wavelet phase coherence

Procedia PDF Downloads 192

Authors: Pius Marthin, Nihal Ata Tutkun

Abstract:

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.

Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)

Procedia PDF Downloads 69

Authors: Vyacheslav Furtak, Merja Roivainen, Olga Mirochnichenko, Majid Laassri, Bella Bidzhieva, Tatiana Zagorodnyaya, Vladimir Chizhikov, Konstantin Chumakov

Abstract:

Molecular epidemiology and environmental surveillance are parts of a rational strategy to control infectious diseases. They have been widely used in the worldwide campaign to eradicate poliomyelitis, which otherwise would be complicated by the inability to rapidly respond to outbreaks and determine sources of the infection. The conventional scheme involves isolation of viruses from patients and the environment, followed by their identification by nucleotide sequences analysis to determine phylogenetic relationships. This is a tedious and time-consuming process that yields definitive results when it may be too late to implement countermeasures. Because of the difficulty of high-throughput full-genome sequencing, most such studies are conducted by sequencing only capsid genes or their parts. Therefore the important information about the contribution of other parts of the genome and inter- and intra-species recombination to viral evolution is not captured. Here we propose a new approach based on the rapid concentration of sewage samples with tangential flow filtration followed by deep sequencing and reconstruction of nucleotide sequences of viruses present in the samples. The entire nucleic acids content of each sample is sequenced, thus preserving in digital format the complete spectrum of viruses. A set of rapid algorithms was developed to separate deep sequence reads into discrete populations corresponding to each virus and assemble them into full-length consensus contigs, as well as to generate a complete profile of sequence heterogeneities in each of them. This provides an effective approach to study molecular epidemiology and evolution of natural viral populations.

Keywords: poliovirus, eradication, environmental surveillance, laboratory diagnosis

Procedia PDF Downloads 254

Authors: F. Ghazalnaz Sharifonnasabi, Iman Makhdoom

Abstract:

Breast cancer is a serious health concern that affects many people around the world. According to a study published in the Breast journal, the global burden of breast cancer is expected to increase significantly over the next few decades. The number of deaths from breast cancer has been increasing over the years, but the age-standardized mortality rate has decreased in some countries. It’s important to be aware of the risk factors for breast cancer and to get regular check- ups to catch it early if it does occur. Machin learning techniques have been used to aid in the early detection and diagnosis of breast cancer. These techniques, that have been shown to be effective in predicting and diagnosing the disease, have become a research hotspot. In this study, we consider two deep learning approaches including: Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). We also considered the five-machine learning algorithm titled: Decision Tree (C4.5), Naïve Bayesian (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) Algorithm and XGBoost (eXtreme Gradient Boosting) on the Breast Cancer Wisconsin Diagnostic dataset. We have carried out the process of evaluating and comparing classifiers involving selecting appropriate metrics to evaluate classifier performance and selecting an appropriate tool to quantify this performance. The main purpose of the study is predicting and diagnosis breast cancer, applying the mentioned algorithms and also discovering of the most effective with respect to confusion matrix, accuracy and precision. It is realized that CNN outperformed all other classifiers and achieved the highest accuracy (0.982456). The work is implemented in the Anaconda environment based on Python programing language.

Keywords: breast cancer, multi-layer perceptron, Naïve Bayesian, SVM, decision tree, convolutional neural network, XGBoost, KNN

Procedia PDF Downloads 52

Authors: Yujiang Wu

Abstract:

As electrical machine (e-machine) power density re-querulents become more stringent in vehicle electrification, mounting a temperature sensor for e-machine stator windings becomes increasingly difficult. This can lead to higher manufacturing costs, complicated harnesses, and reduced reliability. In this paper, we propose a deep-learning method for predicting electric machine winding temperature, which can either replace the sensor entirely or serve as a backup to the existing sensor. We compare the performance of our method, the stateful long short-term memory networks (LSTM) with truncated backpropagation through time (TBTT), with that of linear regression, as well as stateless LSTM with/without residual connection. Our results demonstrate the strength of combining stateful LSTM and TBTT in tackling nonlinear time series prediction problems with long sequence lengths. Additionally, in industrial applications, high-temperature region prediction accuracy is more important because winding temperature sensing is typically used for derating machine power when the temperature is high. To evaluate the performance of our algorithm, we developed a temperature-stratified MSE. We propose a simple but effective data preprocessing trick to improve the high-temperature region prediction accuracy. Our experimental results demonstrate the effectiveness of our proposed method in accurately predicting winding temperature, particularly in high-temperature regions, while also reducing manufacturing costs and improving reliability.

Keywords: deep learning, electrical machine, functional safety, long short-term memory networks (LSTM), thermal management, time series prediction

Procedia PDF Downloads 71

Authors: Souradip Paul, Arijit Paramanick, M. Suheshkumar Singh

Abstract:

Traumatic injury is the leading worldwide health problem. Annually, millions of surgical wounds are created for the sake of routine medical care. The healing of these unintended injuries is always monitored based on visual inspection. The maximal restoration of tissue functionality remains a significant concern of clinical care. Although minor injuries heal well with proper care and medical treatment, large injuries negatively influence various factors (vasculature insufficiency, tissue coagulation) and cause poor healing. Demographically, the number of people suffering from severe wounds and impaired healing conditions is burdensome for both human health and the economy. An incomplete understanding of the functional and molecular mechanism of tissue healing often leads to a lack of proper therapies and treatment. Hence, strong and promising medical guidance is necessary for monitoring the tissue regeneration processes. Photoacoustic imaging (PAI), is a non-invasive, hybrid imaging modality that can provide a suitable solution in this regard. Light combined with sound offers structural, functional and molecular information from the higher penetration depth. Therefore, molecular and structural mechanisms of tissue repair will be readily observable in PAI from the superficial layer and in the deep tissue region. Blood vessel formation and its growth is an essential tissue-repairing components. These vessels supply nutrition and oxygen to the cell in the wound region. Angiogenesis (formation of new capillaries from existing blood vessels) contributes to new blood vessel formation during tissue repair. The betterment of tissue healing directly depends on angiogenesis. Other optical microscopy techniques can visualize angiogenesis in micron-scale penetration depth but are unable to provide deep tissue information. PAI overcomes this barrier due to its unique capability. It is ideally suited for deep tissue imaging and provides the rich optical contrast generated by hemoglobin in blood vessels. Hence, an early angiogenesis detection method provided by PAI leads to monitoring the medical treatment of the wound. Along with functional property, mechanical property also plays a key role in tissue regeneration. The wound heals through a dynamic series of physiological events like coagulation, granulation tissue formation, and extracellular matrix (ECM) remodeling. Therefore tissue elasticity changes, can be identified using non-contact photoacoustic elastography (PAE). In a nutshell, angiogenesis and biomechanical properties are both critical parameters for tissue healing and these can be characterized in a single imaging modality (PAI).

Keywords: PAT, wound healing, tissue coagulation, angiogenesis

Procedia PDF Downloads 83

Authors: Faris Tarlochan, Siva Mahesh Tangutooru

Abstract:

Lateral Geniculate Nucleus (LGN) is the relay center in the visual pathway as it receives most of the input information from retinal ganglion cells (RGC) and sends to visual cortex. Low threshold calcium currents (IT) at the membrane are the unique indicator to characterize this firing functionality of the LGN neurons gained by the RGC input. According to the LGN functional requirements such as functional mapping of RGC to LGN, the morphologies of the LGN neurons were developed. During the neurological disorders like glaucoma, the mapping between RGC and LGN is disconnected and hence stimulating LGN electrically using deep brain electrodes can restore the functionalities of LGN. A computational model was developed for simulating the LGN neurons with three predominant morphologies, each representing different functional mapping of RGC to LGN. The firings of action potentials at LGN neuron due to IT were characterized by varying the stimulation parameters, morphological parameters and orientation. A wide range of stimulation parameters (stimulus amplitude, duration and frequency) represents the various strengths of the electrical stimulation with different morphological parameters (soma size, dendrites size and structure). The orientation (0-1800) of LGN neuron with respect to the stimulating electrode represents the angle at which the extracellular deep brain stimulation towards LGN neuron is performed. A reduced dendrite structure was used in the model using Bush–Sejnowski algorithm to decrease the computational time while conserving its input resistance and total surface area. The major finding is that an input potential of 0.4 V is required to produce the action potential in the LGN neuron which is placed at 100 µm distance from the electrode. From this study, it can be concluded that the neuroprostheses under design would need to consider the capability of inducing at least 0.4V to produce action potentials in LGN.

Keywords: Lateral Geniculate Nucleus, visual cortex, finite element, glaucoma, neuroprostheses

Procedia PDF Downloads 258

Authors: Lanchi Xie, Zhihui Li, Zhigang Li, Guiqiang Wang, Lei Xu, Yuwen Yan

Abstract:

Image-based facial features can be classified into category recognition features and individual recognition features. Current automated face recognition systems extract a specific feature vector of different dimensions from a facial image according to their pre-trained neural network. However, to improve the efficiency of parameter calculation, an algorithm generally reduces the image details by pooling. The operation will overlook the details concerned much by forensic experts. In our experiment, we adopted a variety of face recognition algorithms based on deep learning, compared a large number of naturally collected face images with the known data of the same person's frontal ID photos. Downscaling and manual handling were performed on the testing images. The results supported that the facial recognition algorithms based on deep learning detected structural and morphological information and rarely focused on specific markers such as stains and moles. Overall performance, distribution of genuine scores and impostor scores, and likelihood ratios were tested to evaluate the accuracy of biometric systems and forensic experts. Experiments showed that the biometric systems were skilled in distinguishing category features, and forensic experts were better at discovering the individual features of human faces. In the proposed approach, a fusion was performed at the score level. At the specified false accept rate, the framework achieved a lower false reject rate. This paper contributes to improving the interpretability of the objective method of facial comparison and provides a novel method for human-machine collaboration in this field.

Keywords: likelihood ratio, automated facial recognition, facial comparison, biometrics

Procedia PDF Downloads 111

Authors: Arun Prasad, P. B. Ramudu, Deep Shikha, Deep Jyoti Singh

Abstract:

A number of studies have been conducted recently to investigate the influence of randomly oriented fibers on some engineering properties of cohesive soils.Freezing and thawing of soil affects the strength, durability and permeability of soil adversely. Experiments were carried out in order to investigate the effect of inclusion of randomly distributed polypropylene fibers on the strength, hydraulic conductivity and durability of local soil (CL) subjected to freeze–thaw cycles. For evaluating the change in strength of soil, a series of unconfined compression tests as well as tri-axial tests were carried out on reinforced and unreinforced soil samples. All the samples were subjected to seven cycles of freezing and thawing. Freezing was carried out at a temperature of - 15 to -18 °C; and thawing was carried out by keeping the samples at room temperature. The reinforcement of soil samples was done by mixing with polypropylene fibers, 12 mm long and with an aspect ratio of 240. The content of fibers was varied from 0.25 to 1% by dry weight of soil. The maximum strength of soil was found in samples having a fiber content of 0.75% for all the samples that were prepared at optimum moisture content (OMC), and if the OMC was increased (+2% OMC) or decreased (-2% OMC), the maximum strength observed at 0.5% fiber inclusion. The effect of fiber inclusion and freeze–thaw on the hydraulic conductivity was studied increased from around 25 times to 300 times that of the unreinforced soil, without subjected to any freeze-thaw cycles. For studying the increased durability of soil, mass loss after each freeze-thaw cycle was calculated and it was found that samples reinforced with polypropylene fibers show 50-60% less loss in weight than that of the unreinforced soil.

Keywords: fiber reinforcement, freezingand thawing, hydraulic conductivity, unconfined compressive strength

Procedia PDF Downloads 383

Authors: Prashanth Pillai, Purnaprajna Mangsuli

Abstract:

Oil exploration and production companies invest considerable time and efforts to extract essential well attributes (like well status, surface, and target coordinates, wellbore depths, event timelines, etc.) from unstructured data sources like technical reports, which are often non-standardized, multimodal, and highly domain-specific by nature. It is also important to consider the context when extracting attribute values from reports that contain information on multiple wells/wellbores. Moreover, semantically similar information may often be depicted in different data syntax representations across multiple pages and document sources. We propose a hierarchical multi-source fact extraction workflow based on a deep learning framework to extract essential well attributes at scale. An information retrieval module based on the transformer architecture was used to rank relevant pages in a document source utilizing the page image embeddings and semantic text embeddings. A question answering framework utilizingLayoutLM transformer was used to extract attribute-value pairs incorporating the text semantics and layout information from top relevant pages in a document. To better handle context while dealing with multi-well reports, we incorporate a dynamic query generation module to resolve ambiguities. The extracted attribute information from various pages and documents are standardized to a common representation using a parser module to facilitate information comparison and aggregation. Finally, we use a probabilistic approach to fuse information extracted from multiple sources into a coherent well record. The applicability of the proposed approach and related performance was studied on several real-life well technical reports.

Keywords: natural language processing, deep learning, transformers, information retrieval

Procedia PDF Downloads 177

Authors: Pengfei Meng, Shuangcheng Jia, Qian Li

Abstract:

We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.

Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling

Procedia PDF Downloads 117

Authors: Mahmoud S. Zaghloul, Mohammed M. Khalaf, Wael N. Thabet, Haidy N. Asham

Abstract:

Background. Hypertrophic scarring is a difficult problem for burn patients, and scar management is an essential aspect of outpatient burn therapy. Post-burn pathologic scars involve functional and aesthetic limitations that have a dramatic influence on the patient’s quality of life. The aim was to investigate the use of extracorporeal shock wave therapy (ESWT), which targets the fibroblasts in scar tissue, as an effective modality for scar treatment in burn patients. Subjects and methods: forty patients with post-burn scars were assigned randomly into two equal groups; their ages ranged from 20-45 years. The study group received ESWT and traditional physical therapy program (deep friction massage, stretching exercises). The control group received traditional physical therapy program (deep friction massage, stretching exercises). All groups received two sessions per week for six successful weeks. The data were collected before and after the same period of treatment for both groups. Evaluation procedures were carried out to measure scar thickness using ultrasonography and Vancouver Scar Scale (VSS) was completed before and after treatment. Results: Post-treatment results showed that there was a significant improvement difference in scar thickness in both groups in favor of the study group. Percentage of improvement in scar thickness in the study group was 42.55%, while it was 12.15% in the control group. There was also a significant improvement difference between results obtained using VSS in both groups in favor of the study group. Conclusion: ESWT is effective in management of pathologic post burn scars.

Keywords: extracorporeal shock wave therapy, post-burn scars, ultrasonography, Vancouver scar scale

Procedia PDF Downloads 236

Authors: Manaranjan Pradhan, Shailaja Grover, U. Dinesh Kumar

Abstract:

Farming community in India, as well as other parts of the world, is one of the highly stressed communities due to reasons such as increasing input costs (cost of seeds, fertilizers, pesticide), droughts, reduced revenue leading to farmer suicides. Lack of integrated farm advisory system in India adds to the farmers problems. Farmers need right information during the early stages of crop’s lifecycle to prevent damage and loss in revenue. In this paper, we use deep learning techniques to develop an early warning system for detection of crop diseases using images taken by farmers using their smart phone. The research work leads to building a smart assistant using analytics and big data which could help the farmers with early diagnosis of the crop diseases and corrective actions. The classical approach for crop disease management has been to identify diseases at crop level. Recently, ImageNet Classification using the convolutional neural network (CNN) has been successfully used to identify diseases at individual plant level. Our model uses convolution filters, max pooling, dense layers and dropouts (to avoid overfitting). The models are built for binary classification (healthy or not healthy) and multi class classification (identifying which disease). Transfer learning is used to modify the weights of parameters learnt through ImageNet dataset and apply them on crop diseases, which reduces number of epochs to learn. One shot learning is used to learn from very few images, while data augmentation techniques are used to improve accuracy with images taken from farms by using techniques such as rotation, zoom, shift and blurred images. Models built using combination of these techniques are more robust for deploying in the real world. Our model is validated using tomato crop. In India, tomato is affected by 10 different diseases. Our model achieves an accuracy of more than 95% in correctly classifying the diseases. The main contribution of our research is to create a personal assistant for farmers for managing plant disease, although the model was validated using tomato crop, it can be easily extended to other crops. The advancement of technology in computing and availability of large data has made possible the success of deep learning applications in computer vision, natural language processing, image recognition, etc. With these robust models and huge smartphone penetration, feasibility of implementation of these models is high resulting in timely advise to the farmers and thus increasing the farmers' income and reducing the input costs.

Keywords: analytics in agriculture, CNN, crop disease detection, data augmentation, image recognition, one shot learning, transfer learning

Procedia PDF Downloads 103

Authors: Hermalina Sinay, Estri L. Arumingtyas

Abstract:

The research objective was to determine the expression level of dehydration responsive element binding/DREB gene of local corn cultivars from Kisar Island Maluku. The study design was a randomized block design with single factor consist of six local corn cultivars obtained from farmers in Kisar Island and one reference varieties wich has been released by the government as a drought-tolerant varieties and obtained from Cereal Crops Research Institute (ICERI) Maros South Sulawesi. Leaf samples were taken is the second leaf after the flag leaf at the 65 days after planting. Isolation of total RNA from leaf samples was carried out according to the protocols of the R & A-BlueTM Total RNA Extraction Kit and was used as a template for cDNA synthesis. The making of cDNA from total RNA was carried out according to the protocol of One-Step Reverse Transcriptase PCR Premix Kit. Real Time-PCR was performed on cDNA from reverse transcription followed the procedures of Real MODTM Green Real-Time PCR Master Mix Kit. Data obtained from the real time-PCR results were analyzed using relative quantification method based on the critical point / Cycle Threshold (CP / CT). The results of gene expression analysis of DREB gene showed that the expression level of the gene was highest obtained at Deep Yellow local corn cultivar, and the lowest one was obtained at the Rubby Brown Cob cultivar. It can be concluded that the expression level of DREB gene of Deep Yellow local corn cultivar was highest than other local corn cultivars and Srikandi variety as a reference variety.

Keywords: expression, level, DREB gene, local corn cultivars, Kisar Island, Maluku

Procedia PDF Downloads 283

Authors: Hussein Bizimana, Osman Sönmez

Abstract:

Constructed wetlands are current the most widely recognized waste water treatment option, especially in developing countries where they have the potential for improving water quality and creating valuable wildlife habitat in ecosystem with treatment requirement relatively simple for operation and maintenance cost. Lack of grey waste water treatment facilities in Kigali İnstitute of Science and Technology in Rwanda, causes pollution in the surrounding localities of Rugunga sector, where already a problem of poor sanitation is found. In order to treat grey water produced at Kigali İnstitute of Science and Technology, with high BOD concentration, high nutrients concentration and high alkalinity; a Horizontal Sub-surface Flow pilot-scale constructed wetland was designed and can operate in Kigali İnstitute of Science and Technology. The study was carried out in a sedimentation tank of 5.5 m x 1.42 m x 1.2 m deep and a Horizontal Sub-surface constructed wetland of 4.5 m x 2.5 m x 1.42 m deep. The grey waste water flow rate of 2.5 m3/d flew through vegetated wetland and sandy pilot plant. The filter media consisted of 0.6 to 2 mm of coarse sand, 0.00003472 m/s of hydraulic conductivity and cattails (Typha latifolia spp) were used as plants species. The effluent flow rate of the plant is designed to be 1.5 m3/ day and the retention time will be 24 hrs. 72% to 79% of BOD, COD, and TSS removals are estimated to be achieved, while the nutrients (Nitrogen and Phosphate) removal is estimated to be in the range of 34% to 53%. Every effluent characteristic will meet exactly the Rwanda Utility Regulatory Agency guidelines primarily because the retention time allowed is enough to make the reduction of contaminants within effluent raw waste water. Treated water reuse system was developed where water will be used in the campus irrigation system again.

Keywords: constructed wetlands, hydraulic conductivity, grey waste water, cattails

Procedia PDF Downloads 584

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

Procedia PDF Downloads 54

Authors: Abbas Raza Ali

Abstract:

Big Data technology is gradually becoming a dire need of large enterprises. These enterprises are generating massively large amount of off-line and streaming data in both structured and unstructured formats on daily basis. It is a challenging task to effectively extract useful insights from the large scale datasets, even though sometimes it becomes a technology constraint to manage transactional data history of more than a few months. This paper presents a framework to efficiently manage massively large and complex datasets. The framework has been tested on a communication service provider producing massively large complex streaming data in binary format. The communication industry is bound by the regulators to manage history of their subscribers’ call records where every action of a subscriber generates a record. Also, managing and analyzing transactional data allows service providers to better understand their customers’ behavior, for example, deep packet inspection requires transactional internet usage data to explain internet usage behaviour of the subscribers. However, current relational database systems limit service providers to only maintain history at semantic level which is aggregated at subscriber level. The framework addresses these challenges by leveraging Big Data technology which optimally manages and allows deep analysis of complex datasets. The framework has been applied to offload existing Intelligent Network Mediation and relational Data Warehouse of the service provider on Big Data. The service provider has 50+ million subscriber-base with yearly growth of 7-10%. The end-to-end process takes not more than 10 minutes which involves binary to ASCII decoding of call detail records, stitching of all the interrogations against a call (transformations) and aggregations of all the call records of a subscriber.

Keywords: big data, communication service providers, enterprise data warehouse, stream computing, Telco IN Mediation

Procedia PDF Downloads 153

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 173

Authors: Mohammed Abu Shquier

Abstract:

This paper introduces a word segmentation method using the novel BP-LSTM-CRF architecture for processing semantic output training. The objective of web morphological analysis tools is to link a formal morpho-syntactic description to a lemma, along with morpho-syntactic information, a vocalized form, a vocalized analysis with morpho-syntactic information, and a list of paradigms. A key objective is to continuously enhance the proposed system through an inductive learning approach that considers semantic influences. The system is currently under construction and development based on data-driven learning. To evaluate the tool, an experiment on homograph analysis was conducted. The tool also encompasses the assumption of deep binary segmentation hypotheses, the arbitrary choice of trigram or n-gram continuation probabilities, language limitations, and morphology for both Modern Standard Arabic (MSA) and Dialectal Arabic (DA), which provide justification for updating this system. Most Arabic word analysis systems are based on the phonotactic morpho-syntactic analysis of a word transmitted using lexical rules, which are mainly used in MENA language technology tools, without taking into account contextual or semantic morphological implications. Therefore, it is necessary to have an automatic analysis tool taking into account the word sense and not only the morpho-syntactic category. Moreover, they are also based on statistical/stochastic models. These stochastic models, such as HMMs, have shown their effectiveness in different NLP applications: part-of-speech tagging, machine translation, speech recognition, etc. As an extension, we focus on language modeling using Recurrent Neural Network (RNN); given that morphological analysis coverage was very low in dialectal Arabic, it is significantly important to investigate deeply how the dialect data influence the accuracy of these approaches by developing dialectal morphological processing tools to show that dialectal variability can support to improve analysis.

Keywords: NLP, DL, ML, analyser, MSA, RNN, CNN

Procedia PDF Downloads 20