Search results for: deep graphical model

Authors: Airy Huang, Fuji Foo, Aries Prasetya Wibowo

Abstract:

In recent years, the focus of Natural Language Processing (NLP) development has been gradually shifting from the semantics-based approach to deep learning one, which performs faster with fewer resources. Although it performs well in many applications, the deep learning approach, due to the lack of semantics understanding, has difficulties in noticing and expressing a novel business case with a pre-defined scope. In order to meet the requirements of specific robotic services, deep learning approach is very labor-intensive and time consuming. It is very difficult to improve the capabilities of conversational AI in a short time, and it is even more difficult to self-learn from experiences to deliver the same service in a better way. In this paper, we present an adaptive conversational AI algorithm that combines both semantic knowledge and deep learning to address this issue by learning new business cases through conversations. After self-learning from experience, the robot adapts to the business cases originally out of scope. The idea is to build new or extended robotic services in a systematic and fast-training manner with self-configured programs and constructed dialog flows. For every cycle in which a chat bot (conversational AI) delivers a given set of business cases, it is trapped to self-measure its performance and rethink every unknown dialog flows to improve the service by retraining with those new business cases. If the training process reaches a bottleneck and incurs some difficulties, human personnel will be informed of further instructions. He or she may retrain the chat bot with newly configured programs, or new dialog flows for new services. One approach employs semantics analysis to learn the dialogues for new business cases and then establish the necessary ontology for the new service. With the newly learned programs, it completes the understanding of the reaction behavior and finally uses dialog flows to connect all the understanding results and programs, achieving the goal of self-learning process. We have developed a chat bot service mounted on a kiosk, with a camera for facial recognition and a directional microphone array for voice capture. The chat bot serves as a concierge with polite conversation for visitors. As a proof of concept. We have demonstrated to complete 90% of reception services with limited self-learning capability.

Keywords: conversational AI, chatbot, dialog management, semantic analysis

Procedia PDF Downloads 136

Authors: Vishal Raj, Noorhan Abbas

Abstract:

Ambiguity in NLP (Natural language processing) refers to the ability of a word, phrase, sentence, or text to have multiple meanings. This results in various kinds of ambiguities such as lexical, syntactic, semantic, anaphoric and referential am-biguities. This study is focused mainly on solving the issue of Lexical ambiguity. Word Sense Disambiguation (WSD) is an NLP technique that aims to resolve lexical ambiguity by determining the correct meaning of a word within a given context. Most WSD solutions rely on words for training and testing, but we have used lemma and Part of Speech (POS) tokens of words for training and testing. Lemma adds generality and POS adds properties of word into token. We have designed a novel method to create an affinity matrix to calculate the affinity be-tween any pair of lemma_POS (a token where lemma and POS of word are joined by underscore) of given training set. Additionally, we have devised an al-gorithm to create the sense clusters of tokens using affinity matrix under hierar-chy of POS of lemma. Furthermore, three different mechanisms to predict the sense of target word using the affinity/similarity value are devised. Each contex-tual token contributes to the sense of target word with some value and whichever sense gets higher value becomes the sense of target word. So, contextual tokens play a key role in creating sense clusters and predicting the sense of target word, hence, the model is named Contextual SenSe Model (CSM). CSM exhibits a noteworthy simplicity and explication lucidity in contrast to contemporary deep learning models characterized by intricacy, time-intensive processes, and chal-lenging explication. CSM is trained on SemCor training data and evaluated on SemEval test dataset. The results indicate that despite the naivety of the method, it achieves promising results when compared to the Most Frequent Sense (MFS) model.

Keywords: word sense disambiguation (wsd), contextual sense model (csm), most frequent sense (mfs), part of speech (pos), natural language processing (nlp), oov (out of vocabulary), lemma_pos (a token where lemma and pos of word are joined by underscore), information retrieval (ir), machine translation (mt)

Procedia PDF Downloads 108

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: classification, CNN, deep learning, prediction, SNR

Procedia PDF Downloads 134

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 63

Authors: Jaouadi Imen, Ben Djemaa Raoudha, Ben Abdallah Hanene

Abstract:

The access to relevant information that is adapted to users’ needs, preferences and environment is a challenge in many applications running. That causes an appearance of context-aware systems. To facilitate the development of this class of applications, it is necessary that these applications share a common context meta-model. In this article, we will present our context meta-model that is defined using the OMG Meta Object facility (MOF). This meta-model is based on the analysis and synthesis of context concepts proposed in literature.

Keywords: context, meta-model, MOF, awareness system

Procedia PDF Downloads 561

Authors: Wasif Mughees, Malik Al-Ahmad, Muhammad Naeem

Abstract:

This research involves the design and analysis of pinch-based water/wastewater networks to minimize water utility in the petrochemical and petroleum industries. A study has been done on Tehran Oil Refinery to analyze feasibilities of regeneration, reuse and recycling of water network. COD is considered as a single key contaminant. Amount of freshwater was reduced about 149m3/h (43.8%) regarding COD. Re-design (or retrofitting) of water allocation in the networks was undertaken. The results were analyzed through graphical method and mathematical programming technique which clearly demonstrated that amount of required water would be determined by mass transfer of COD.

Keywords: minimization, water pinch, water management, pollution prevention

Procedia PDF Downloads 448

Authors: C. Virgilio, J. Carlier, P. Campistron, M. Toubal, P. Garnier, L. Broussous, V. Thomy, B. Nongaillard

Abstract:

Wetting efficiency of microstructures or nanostructures patterned on Si wafers is a real challenge in integrated circuits manufacturing. In fact, bad or non-uniform wetting during wet processes limits chemical reactions and can lead to non-complete etching or cleaning inside the patterns and device defectivity. This issue is more and more important with the transistors size shrinkage and concerns mainly high aspect ratio structures. Deep Trench Isolation (DTI) structures enabling pixels’ isolation in imaging devices are subject to this phenomenon. While low-frequency acoustic reflectometry principle is a well-known method for Non Destructive Test applications, we have recently shown that it is also well suited for nanostructures wetting characterization in a higher frequency range. In this paper, we present a high-frequency acoustic reflectometry characterization of DTI wetting through a confrontation of both experimental and modeling results. The acoustic method proposed is based on the evaluation of the reflection of a longitudinal acoustic wave generated by a 100 µm diameter ZnO piezoelectric transducer sputtered on the silicon wafer backside using MEMS technologies. The transducers have been fabricated to work at 5 GHz corresponding to a wavelength of 1.7 µm in silicon. The DTI studied structures, manufactured on the wafer frontside, are crossing trenches of 200 nm wide and 4 µm deep (aspect ratio of 20) etched into a Si wafer frontside. In that case, the acoustic signal reflection occurs at the bottom and at the top of the DTI enabling its characterization by monitoring the electrical reflection coefficient of the transducer. A Finite Difference Time Domain (FDTD) model has been developed to predict the behavior of the emitted wave. The model shows that the separation of the reflected echoes (top and bottom of the DTI) from different acoustic modes is possible at 5 Ghz. A good correspondence between experimental and theoretical signals is observed. The model enables the identification of the different acoustic modes. The evaluation of DTI wetting is then performed by focusing on the first reflected echo obtained through the reflection at Si bottom interface, where wetting efficiency is crucial. The reflection coefficient is measured with different water / ethanol mixtures (tunable surface tension) deposited on the wafer frontside. Two cases are studied: with and without PFTS hydrophobic treatment. In the untreated surface case, acoustic reflection coefficient values with water show that liquid imbibition is partial. In the treated surface case, the acoustic reflection is total with water (no liquid in DTI). The impalement of the liquid occurs for a specific surface tension but it is still partial for pure ethanol. DTI bottom shape and local pattern collapse of the trenches can explain these incomplete wetting phenomena. This high-frequency acoustic method sensitivity coupled with a FDTD propagative model thus enables the local determination of the wetting state of a liquid on real structures. Partial wetting states for non-hydrophobic surfaces or low surface tension liquids are then detectable with this method.

Keywords: wetting, acoustic reflectometry, gigahertz, semiconductor

Procedia PDF Downloads 327

Authors: Hozaifa Zaki, Ghada Soliman

Abstract:

In this paper, we introduced an approach for Automated Dotted Arabic Expiration Date Extraction using Optimized Convolutional Autoencoder (ARABEX) with bidirectional LSTM. This approach is used for translating the Arabic dot-matrix expiration dates into their corresponding filled-in dates. A custom lightweight Convolutional Recurrent Neural Network (CRNN) model is then employed to extract the expiration dates. Due to the lack of available dataset images for the Arabic dot-matrix expiration date, we generated synthetic images by creating an Arabic dot-matrix True Type Font (TTF) matrix to address this limitation. Our model was trained on a realistic synthetic dataset of 3287 images, covering the period from 2019 to 2027, represented in the format of yyyy/mm/dd. We then trained our custom CRNN model using the generated synthetic images to assess the performance of our model (ARABEX) by extracting expiration dates from the translated images. Our proposed approach achieved an accuracy of 99.4% on the test dataset of 658 images, while also achieving a Structural Similarity Index (SSIM) of 0.46 for image translation on our dataset. The ARABEX approach demonstrates its ability to be applied to various downstream learning tasks, including image translation and reconstruction. Moreover, this pipeline (ARABEX+CRNN) can be seamlessly integrated into automated sorting systems to extract expiry dates and sort products accordingly during the manufacturing stage. By eliminating the need for manual entry of expiration dates, which can be time-consuming and inefficient for merchants, our approach offers significant results in terms of efficiency and accuracy for Arabic dot-matrix expiration date recognition.

Keywords: computer vision, deep learning, image processing, character recognition

Procedia PDF Downloads 82

Authors: Maryam Fallahpoor, Biswajeet Pradhan

Abstract:

Background: Artificial intelligence (AI) serves as a valuable tool in mitigating the scarcity of human resources required for the evaluation and categorization of vast quantities of medical imaging data. When AI operates with optimal precision, it minimizes the demand for human interpretations and, thereby, reduces the burden on radiologists. Among various AI approaches, deep learning (DL) stands out as it obviates the need for feature extraction, a process that can impede classification, especially with intricate datasets. The advent of DL models has ushered in a new era in medical imaging, particularly in the context of COVID-19 detection. Traditional 2D imaging techniques exhibit limitations when applied to volumetric data, such as Computed Tomography (CT) scans. Medical images predominantly exist in one of two formats: neuroimaging informatics technology initiative (NIfTI) and digital imaging and communications in medicine (DICOM). Purpose: This study aims to employ DL for the classification of COVID-19-infected pulmonary patients and normal cases based on 3D CT scans while investigating the impact of image format. Material and Methods: The dataset used for model training and testing consisted of 1245 patients from IranMehr Hospital. All scans shared a matrix size of 512 × 512, although they exhibited varying slice numbers. Consequently, after loading the DICOM CT scans, image resampling and interpolation were performed to standardize the slice count. All images underwent cropping and resampling, resulting in uniform dimensions of 128 × 128 × 60. Resolution uniformity was achieved through resampling to 1 mm × 1 mm × 1 mm, and image intensities were confined to the range of (−1000, 400) Hounsfield units (HU). For classification purposes, positive pulmonary COVID-19 involvement was designated as 1, while normal images were assigned a value of 0. Subsequently, a U-net-based lung segmentation module was applied to obtain 3D segmented lung regions. The pre-processing stage included normalization, zero-centering, and shuffling. Four distinct 3D CNN models (ResNet152, ResNet50, DensNet169, and DensNet201) were employed in this study. Results: The findings revealed that the segmentation technique yielded superior results for DICOM images, which could be attributed to the potential loss of information during the conversion of original DICOM images to NIFTI format. Notably, ResNet152 and ResNet50 exhibited the highest accuracy at 90.0%, and the same models achieved the best F1 score at 87%. ResNet152 also secured the highest Area under the Curve (AUC) at 0.932. Regarding sensitivity and specificity, DensNet201 achieved the highest values at 93% and 96%, respectively. Conclusion: This study underscores the capacity of deep learning to classify COVID-19 pulmonary involvement using real 3D hospital data. The results underscore the significance of employing DICOM format 3D CT images alongside appropriate pre-processing techniques when training DL models for COVID-19 detection. This approach enhances the accuracy and reliability of diagnostic systems for COVID-19 detection.

Keywords: deep learning, COVID-19 detection, NIFTI format, DICOM format

Procedia PDF Downloads 88

Authors: Lizhi Ma, Dan Liu

Abstract:

Pipeline parallelism has been widely used to accelerate distributed deep learning to alleviate GPU memory bottlenecks and to ensure that models can be trained and deployed smoothly under limited graphics memory conditions. However, in highly heterogeneous distributed clusters, traditional model partitioning methods are not able to achieve load balancing. The overlap of communication and computation is also a big challenge. In this paper, HePipe is proposed, an efficient pipeline parallel training method for highly heterogeneous clusters. According to the characteristics of the neural network model pipeline training task, oriented to the 2-level heterogeneous cluster computing topology, a training method based on the 2-level stage division of neural network modeling and partitioning is designed to improve the parallelism. Additionally, a multi-forward 1F1B scheduling strategy is designed to accelerate the training time of each stage by executing the computation units in advance to maximize the overlap between the forward propagation communication and backward propagation computation. Finally, a dynamic recomputation strategy based on task memory requirement prediction is proposed to improve the fitness ratio of task and memory, which improves the throughput of the cluster and solves the memory shortfall problem caused by memory differences in heterogeneous clusters. The empirical results show that HePipe improves the training speed by 1.6×−2.2× over the existing asynchronous pipeline baselines.

Keywords: pipeline parallelism, heterogeneous cluster, model training, 2-level stage partitioning

Procedia PDF Downloads 19

Authors: A. Rabin, G. Mazor, I. Ladizhenski, R. Shneck, Z.

Abstract:

The hardness and hardenability of AISI D2 cold work tool steel with conventional quenching (CQ), deep cryogenic quenching (DCQ) and rapid deep cryogenic quenching heat treatments caused by temporary porous coating based on magnesium sulfate was investigated. Each of the cooling processes was examined from the perspective of the full process efficiency, heat flux in the austenite-martensite transformation range followed by characterization of the temporary porous layer made of magnesium sulfate using confocal laser scanning microscopy (CLSM), surface and core hardness and hardenability using Vickr’s hardness technique. The results show that the cooling rate (CR) at the austenite-martensite transformation range have a high influence on the hardness of the studied steel.

Keywords: AISI D2, controllable cooling, magnesium sulfate coating, rapid cryogenic heat treatment, temporary porous layer

Procedia PDF Downloads 137

Authors: K. Sekulová, M. Šimon

Abstract:

This article focuses on upper-extremity musculoskeletal disorders risk assessment model at workplace. In this model are used risk factors that are responsible for musculoskeletal system damage. Based on statistic calculations the model is able to define what risk of MSD threatens workers who are under risk factors. The model is also able to say how MSD risk would decrease if these risk factors are eliminated.

Keywords: ergonomics, musculoskeletal disorders, occupational diseases, risk factors

Procedia PDF Downloads 551

Authors: Anthony Usoro

Abstract:

In this paper, two classes of bilinear time series model are obtained under certain conditions from the general bilinear autoregressive moving average model. Bilinear Autoregressive (BAR) and Bilinear Moving Average (BMA) Models have been identified. From the general bilinear model, BAR and BMA models have been proved to exist for q = Q = 0, => j = 0, and p = P = 0, => i = 0 respectively. These models are found useful in modelling most of the economic and financial data.

Keywords: autoregressive model, bilinear autoregressive model, bilinear moving average model, moving average model

Procedia PDF Downloads 407

Authors: Mihai-Ionut Firescu, Mark A. P. Carson

Abstract:

We present a case of inferior vena cava agenesis (IVCA) associated with bilateral deep venous thrombosis (DVT) in a patient with Beckwith-Wiedemann syndrome (BWS). In adult patients with BWS presenting with bilateral lower limb oedema, specific aetiological factors should be considered. These include cardiomyopathy and intraabdominal tumours. Congenital malformations of the IVC, through causing relative venous stasis, can lead to lower limb oedema either directly or indirectly by favouring lower limb venous thromboembolism; however, they are yet to be reported as an associated feature of BWS. Given its life-threatening potential, the prompt initiation of treatment for bilateral DVT is paramount. In BWS patients, however, this can prove more complicated. Due to overgrowth, the above-average birth weight can continue throughout childhood. In this case, the patient’s weight reached 170 kg, impacting on anticoagulation choice, as direct oral anticoagulants have a limited evidence base in patients with a body mass above 120 kg. Furthermore, the presence of IVCA leads to a long-term increased venous thrombosis risk. Therefore, patients with IVCA and bilateral DVT warrant specialist consideration and may benefit from multidisciplinary team management, with hematology and vascular surgery input. Conclusion: Here, we showcased a rare cause for bilateral lower limb oedema, respectively bilateral deep venous thrombosis complicating IVCA in a patient with Beckwith-Wiedemann syndrome. The importance of this case lies in its novelty, as the association between IVC agenesis and BWS has not yet been described. Furthermore, the treatment of DVT in such situations requires special consideration, taking into account the patient’s weight and the presence of a significant, predisposing vascular abnormality.

Keywords: Beckwith-Wiedemann syndrome, bilateral deep venous thrombosis, inferior vena cava agenesis, venous thromboembolism

Procedia PDF Downloads 235

Authors: Shank Kulkarni, Alireza Tabarraei

Abstract:

The fantastic properties of polyurea such as flexibility, durability, and chemical resistance have brought it a wide range of application in various industries. Effective prediction of the response of polyurea under different loading and environmental conditions necessitates the development of an accurate constitutive model. Similar to most polymers, the behavior of polyurea depends on both strain and strain rate. Therefore, the constitutive model should be able to capture both these effects on the response of polyurea. To achieve this objective, in this paper, a nonlinear hyper-viscoelastic constitutive model is developed by the superposition of a hyperelastic and a viscoelastic model. The proposed constitutive model can capture the behavior of polyurea under compressive loading conditions at various strain rates. Four parameter Ogden model and Mooney Rivlin model are used to modeling the hyperelastic behavior of polyurea. The viscoelastic behavior is modeled using both a three-parameter standard linear solid (SLS) model and a K-BKZ model. Comparison of the modeling results with experiments shows that Odgen and SLS model can more accurately predict the behavior of polyurea. The material parameters of the model are found by curve fitting of the proposed model to the uniaxial compression test data. The proposed model can closely reproduce the stress-strain behavior of polyurea for strain rates up to 6500 /s.

Keywords: constitutive modelling, ogden model, polyurea, SLS model, uniaxial compression test

Procedia PDF Downloads 244

Authors: Hussein Altartouri

Abstract:

In this paper the kinematic and kinetic models of an omnidirectional holonomic mobile robot is presented. The kinematic and kinetic models form the OmniDrive model. Therefore, a mathematical model for the robot equipped with three- omnidirectional wheels is derived. This model which takes into consideration the kinematics and kinetics of the robot, is developed to state space representation. Relative analysis of the velocities and displacements is used for the kinematics of the robot. Lagrange’s approach is considered in this study for deriving the equation of motion. The drive train and the mechanical assembly only of the Festo Robotino® is considered in this model. Mainly the model is developed for motion control. Furthermore, the model can be used for simulation purposes in different virtual environments not only Robotino® View. Further use of the model is in the mechatronics research fields with the aim of teaching and learning the advanced control theories.

Keywords: mobile robot, omni-direction wheel, mathematical model, holonomic mobile robot

Procedia PDF Downloads 609

Authors: Tahar Alimi, Rahma Boujebane, Wiem Derouich, Lamia Hadrich Belguith

Abstract:

Machine translation task of low-resourced languages such as Arabic is a challenging task. Despite the appearance of sophisticated models based on the latest deep learning techniques, namely the transfer learning and transformers, all models prove incapable of carrying out an acceptable translation, which includes Arabic Dialects (AD), because they do not have official status. In this paper, we present a machine translation model designed to translate Arabic multidialectal content into Modern Standard Arabic (MSA), leveraging both new and existing parallel resources. The latter achieved the best results for both Levantine and Maghrebi dialects with a BLEU score of 64.99.

Keywords: Arabic translation, dialect translation, fine-tune, MSA translation, transformer, translation

Procedia PDF Downloads 61

Authors: T. N. Mac, B. Shahbodaghkhan, N. Khalili

Abstract:

A new elastic-viscoplastic (EVP) constitutive model is proposed for the analysis of time-dependent behavior of clay. The proposed model is based on the bounding surface plasticity and the concept of viscoplastic consistency framework to establish continuous transition from plasticity to rate dependent viscoplasticity. Unlike the overstress based models, this model will meet the consistency condition in formulating the constitutive equation for EVP model. The procedure of deriving the constitutive relationship is also presented. Simulation results and comparisons with experimental data are then presented to demonstrate the performance of the model.

Keywords: bounding surface, consistency theory, constitutive model, viscosity

Procedia PDF Downloads 492

Authors: Sakshi V. Tantak, Vishap K. Malik, Neelanjney Pilarisetty

Abstract:

A patent is an exclusive right granted for an invention. It can be a product or a process that provides an innovative method of doing something, or offers a new technical perspective or solution to a problem. A patent can be obtained by making the technical information and details about the invention publicly available. The patent owner has exclusive rights to prevent or stop anyone from using the patented invention for commercial uses. Any commercial usage, distribution, import or export of a patented invention or product requires the patent owner’s consent. It has been observed that the central and important parts of patents are scripted in idiosyncratic and complex linguistic structures that can be difficult to read, comprehend or interpret for the masses. The abstracts of these patents tend to obfuscate the precise nature of the patent instead of clarifying it via direct and simple linguistic constructs. This makes it necessary to have an efficient access to this knowledge via concise and transparent summaries. However, as mentioned above, due to complex and repetitive linguistic constructs and extremely long sentences, common extraction-oriented automatic text summarization methods should not be expected to show a remarkable performance when applied to patent documents. Other, more content-oriented or abstractive summarization techniques are able to perform much better and generate more concise summaries. This paper proposes an efficient summarization system for patents using artificial intelligence, natural language processing and deep learning techniques to condense the knowledge and essential information from a patent document into a single summary that is easier to understand without any redundant formatting and difficult jargon.

Keywords: abstractive summarization, deep learning, natural language Processing, patent document

Procedia PDF Downloads 123

Authors: Yuanchao Sang, Zhihao Gong, Longsheng Chen, Long Chen

Abstract:

Clothing fashion represents a human’s aesthetic appreciation towards everyday outfits and appetite for fashion, and it reflects the development of status in society, humanity, and economics. However, modelling fashion by machine is extremely challenging because fashion is too abstract to be efficiently described by machines. Even human beings can hardly reach a consensus about fashion. In this paper, we are dedicated to answering a fundamental fashion-related problem: what image feature best describes clothing fashion? To address this issue, we have designed and evaluated various image features, ranging from traditional low-level hand-crafted features to mid-level style awareness features to various current popular deep neural network-based features, which have shown state-of-the-art performance in various vision tasks. In summary, we tested the following 9 feature representations: color, texture, shape, style, convolutional neural networks (CNNs), CNNs with distance metric learning (CNNs&DML), AutoEncoder, CNNs with multiple layer combination (CNNs&MLC) and CNNs with dynamic feature clustering (CNNs&DFC). Finally, we validated the performance of these features on two publicly available datasets. Quantitative and qualitative experimental results on both intra-domain and inter-domain fashion clothing image retrieval showed that deep learning based feature representations far outweigh traditional hand-crafted feature representation. Additionally, among all deep learning based methods, CNNs with explicit feature clustering performs best, which shows feature clustering is essential for discriminative fashion feature representation.

Keywords: convolutional neural network, feature representation, image processing, machine modelling

Procedia PDF Downloads 139

Authors: Golnush Masghati-Amoli, Paul Chin

Abstract:

Over the past recent years, with the rapid increases in data availability and computing power, Machine Learning (ML) techniques have been called on in a range of different industries for their strong predictive capability. However, the use of Machine Learning in commercial banking has been limited due to a special challenge imposed by numerous regulations that require lenders to be able to explain their analytic models, not only to regulators but often to consumers. In other words, although Machine Leaning techniques enable better prediction with a higher level of accuracy, in comparison with other industries, they are adopted less frequently in commercial banking especially for scoring purposes. This is due to the fact that Machine Learning techniques are often considered as a black box and fail to provide information on why a certain risk score is given to a customer. In order to bridge this gap between the explain-ability and performance of Machine Learning techniques, a Hybrid Model is developed at Dun and Bradstreet that is focused on blending Machine Learning algorithms with traditional approaches such as scorecards. The Hybrid Model maximizes efficiency of traditional scorecards by merging its practical benefits, such as explain-ability and the ability to input domain knowledge, with the deep insights of Machine Learning techniques which can uncover patterns scorecard approaches cannot. First, through development of Machine Learning models, engineered features and latent variables and feature interactions that demonstrate high information value in the prediction of customer risk are identified. Then, these features are employed to introduce observed non-linear relationships between the explanatory and dependent variables into traditional scorecards. Moreover, instead of directly computing the Weight of Evidence (WoE) from good and bad data points, the Hybrid Model tries to match the score distribution generated by a Machine Learning algorithm, which ends up providing an estimate of the WoE for each bin. This capability helps to build powerful scorecards with sparse cases that cannot be achieved with traditional approaches. The proposed Hybrid Model is tested on different portfolios where a significant gap is observed between the performance of traditional scorecards and Machine Learning models. The result of analysis shows that Hybrid Model can improve the performance of traditional scorecards by introducing non-linear relationships between explanatory and target variables from Machine Learning models into traditional scorecards. Also, it is observed that in some scenarios the Hybrid Model can be almost as predictive as the Machine Learning techniques while being as transparent as traditional scorecards. Therefore, it is concluded that, with the use of Hybrid Model, Machine Learning algorithms can be used in the commercial banking industry without being concerned with difficulties in explaining the models for regulatory purposes.

Keywords: machine learning algorithms, scorecard, commercial banking, consumer risk, feature engineering

Procedia PDF Downloads 134

Authors: Reggie Chandra

Abstract:

Trafficaccidents and traffic signal optimization are correlated. However, 70-90% of the traffic signals across the USA are not synchronized. The reason behind that is insufficient resources to create and implement timing plans. In this work, we will discuss the use of a breakthrough Artificial Intelligence (AI) technology to optimize traffic flow and collect 24/7/365 accurate traffic data using a vehicle detection system. We will discuss what are recent advances in Artificial Intelligence technology, how does AI work in vehicles, pedestrians, and bike data collection, creating timing plans, and what is the best workflow for that. Apart from that, this paper will showcase how Artificial Intelligence makes signal timing affordable. We will introduce a technology that uses Convolutional Neural Networks (CNN) and deep learning algorithms to detect, collect data, develop timing plans and deploy them in the field. Convolutional Neural Networks are a class of deep learning networks inspired by the biological processes in the visual cortex. A neural net is modeled after the human brain. It consists of millions of densely connected processing nodes. It is a form of machine learning where the neural net learns to recognize vehicles through training - which is called Deep Learning. The well-trained algorithm overcomes most of the issues faced by other detection methods and provides nearly 100% traffic data accuracy. Through this continuous learning-based method, we can constantly update traffic patterns, generate an unlimited number of timing plans and thus improve vehicle flow. Convolutional Neural Networks not only outperform other detection algorithms but also, in cases such as classifying objects into fine-grained categories, outperform humans. Safety is of primary importance to traffic professionals, but they don't have the studies or data to support their decisions. Currently, one-third of transportation agencies do not collect pedestrian and bike data. We will discuss how the use of Artificial Intelligence for data collection can help reduce pedestrian fatalities and enhance the safety of all vulnerable road users. Moreover, it provides traffic engineers with tools that allow them to unleash their potential, instead of dealing with constant complaints, a snapshot of limited handpicked data, dealing with multiple systems requiring additional work for adaptation. The methodologies used and proposed in the research contain a camera model identification method based on deep Convolutional Neural Networks. The proposed application was evaluated on our data sets acquired through a variety of daily real-world road conditions and compared with the performance of the commonly used methods requiring data collection by counting, evaluating, and adapting it, and running it through well-established algorithms, and then deploying it to the field. This work explores themes such as how technologies powered by Artificial Intelligence can benefit your community and how to translate the complex and often overwhelming benefits into a language accessible to elected officials, community leaders, and the public. Exploring such topics empowers citizens with insider knowledge about the potential of better traffic technology to save lives and improve communities. The synergies that Artificial Intelligence brings to traffic signal control and data collection are unsurpassed.

Keywords: artificial intelligence, convolutional neural networks, data collection, signal control, traffic signal

Procedia PDF Downloads 169

Authors: Charles Lee

Abstract:

The Principal Orthogonal Decomposition (POD) technique has been used as a model reduction tool for many applications in engineering and science. In principle, one begins with an ensemble of data, called snapshots, collected from an experiment or laboratory results. The beauty of the POD technique is that when applied, the entire data set can be represented by the smallest number of orthogonal basis elements. It is the such capability that allows us to reduce the complexity and dimensions of many physical applications. Mathematical formulations and numerical schemes for the POD method will be discussed along with applications in NASA’s Deep Space Large Antenna Arrays, Satellite Image Reconstruction, Cancer Detection with DNA Microarray Data, Maximizing Stock Return, and Medical Imaging.

Keywords: reduced-order methods, principal component analysis, cancer detection, image reconstruction, stock portfolios

Procedia PDF Downloads 84

Authors: A. Zecchin, E. Vallicella, I. Alberi, A. Dalle Carbonare, A. Festi, F. Galeone, S. Garzon, R. Raffaelli, P. Pomini, M. Franchi

Abstract:

Introduction: Severe endometriosis is a multiorgan disease, that involves bowel in 31% of cases. Disabling symptoms and deep infiltration can lead to bowel obstruction: surgical bowel treatment may be needed. In these cases, colorectal segment resection is usually performed by inferior mesenteric artery ligature, as radically as for oncological surgery. This study was made on surgery based on intestinal vascular axis’ preservation. It was assessed postoperative complications risks (mainly rate of dehiscence of intestinal anastomoses), and results were compared with the ones found in literature about classical colorectal resection. Materials and methods: This was a retrospective study based on 62 patients with deep infiltrating endometriosis of the bowel, which undergo segmental resection with intestinal vascular axis preservation, between 2013 and 2016. It was assessed complications related to the intervention both during hospitalization and 30-60 days after resection. Particular attention was paid to the presence of anastomotic dehiscence. 52 patients were finally telephonically interviewed in order to investigate the presence or absence of intestinal constipation. Results and Conclusion: Segmental intestinal resection performed in this study ensured a more conservative vascular approach, with lower rate of anastomotic dehiscence (1.6%) compared to classical literature data (10.0% to 11.4% ). No complications were observed regarding spontaneous recovery of intestinal motility and bladder emptying. Constipation in some patients, even after years of intervention, is not assessable in the absence of a preoperative constipation state assessment.

Keywords: anastomotic dehiscence, deep infiltrating endometriosis, colorectal resection, vascular axis preservation

Procedia PDF Downloads 204

Authors: Ying Han, Yuanxiang Chen, Yongtao Huang, Jia Fu, Kaile Li, Shangjing Lin, Jianguo Yu

Abstract:

In long-haul and high-speed optical transmission system, the orthogonal frequency division multiplexing (OFDM) signal suffers various linear and non-linear impairments. In recent years, researchers have proposed compensation schemes for specific impairment, and the effects are remarkable. However, different impairment compensation algorithms have caused an increase in transmission delay. With the widespread application of deep neural networks (DNN) in communication, multi-impairment compensation based on DNN will be a promising scheme. In this paper, we propose and apply DNN to compensate multi-impairment of 16-QAM coherent optical OFDM signal, thereby improving the performance of the transmission system. The trained DNN models are applied in the offline digital signal processing (DSP) module of the transmission system. The models can optimize the constellation mapping signals at the transmitter and compensate multi-impairment of the OFDM decoded signal at the receiver. Furthermore, the models reduce the peak to average power ratio (PAPR) of the transmitted OFDM signal and the bit error rate (BER) of the received signal. We verify the effectiveness of the proposed scheme for 16-QAM Coherent Optical OFDM signal and demonstrate and analyze transmission performance in different transmission scenarios. The experimental results show that the PAPR and BER of the transmission system are significantly reduced after using the trained DNN. It shows that the DNN with specific loss function and network structure can optimize the transmitted signal and learn the channel feature and compensate for multi-impairment in fiber transmission effectively.

Keywords: coherent optical OFDM, deep neural network, multi-impairment compensation, optical transmission

Procedia PDF Downloads 143

Authors: Seyedeh Bahar Hashemi, Alireza Rahimi, Mehdi Arjmand

Abstract:

Food is the source of energy and growth through the breakdown of its vital components and plays a vital role in human health and nutrition. Many natural compounds found in plant and animal materials play a special role in biological systems and the origin of many such compounds directly or indirectly is algae. Algae is an enormous source of polysaccharides and have gained much interest in human flourishing. In this study, algae biomass extraction is conducted using deep eutectic-based solvents (NADES) and Ultrasound-assisted extraction (UAE). The aim of this research is to extract bioactive compounds including total carotenoid, antioxidant activity, and polyphenolic contents. For this purpose, the influence of three important extraction parameters namely, biomass-to-solvent ratio, temperature, and time are studied with respect to their impact on the recovery of carotenoids, and phenolics, and on the extracts’ antioxidant activity. Here we employ the Response Surface Methodology for the process optimization. The influence of the independent parameters on each dependent is determined through Analysis of Variance. Our results show that Ultrasound-assisted extraction (UAE) for 50 min is the best extraction condition, and proline:lactic acid (1:1) and choline chloride:urea (1:2) extracts show the highest total phenolic contents (50.00 ± 0.70 mgGAE/gdw) and antioxidant activity [60.00 ± 1.70 mgTE/gdw, 70.00 ± 0.90 mgTE/gdw in 2.2-diphenyl-1-picrylhydrazyl (DPPH), and 2.2′-azino-bis (3-ethylbenzothiazoline-6-sulfonic acid) (ABTS)]. Our results confirm that the combination of UAE and NADES provides an excellent alternative to organic solvents for sustainable and green extraction and has huge potential for use in industrial applications involving the extraction of bioactive compounds from algae. This study is among the first attempts to optimize the effects of ultrasonic-assisted extraction, ultrasonic devices, and deep natural eutectic point and investigate their application in bioactive compounds extraction from algae. We also study the future perspective of ultrasound technology which helps to understand the complex mechanism of ultrasonic-assisted extraction and further guide its application in algae.

Keywords: natural deep eutectic solvents, ultrasound-assisted extraction, algae, antioxidant activity, phenolic compounds, carotenoids

Procedia PDF Downloads 179

Authors: Kingsley Nnaemeka Ogbu, Constantine Mbajiorgu

Abstract:

Vegetation has a marked effect on runoff and has become an important component in hydrologic model. The watershed Resources Management (WRM) model, a process-based, continuous, distributed parameter simulation model developed for hydrologic and soil erosion studies at the watershed scale lack a crop growth component. As such, this model assumes a constant parameter values for vegetation and hydraulic parameters throughout the duration of hydrologic simulation. Our approach is to develop a crop growth algorithm based on the original plant growth model used in the Environmental Policy Integrated Climate Model (EPIC) model. This paper describes the development of a single crop growth model which has the capability of simulating all crops using unique parameter values for each crop. Simulated crop growth processes will reflect the vegetative seasonality of the natural watershed system. An existing model was employed for evaluating vegetative resistance by hydraulic and vegetative parameters incorporated into the WRM model. The improved WRM model will have the ability to evaluate the seasonal variation of the vegetative roughness coefficient with depth of flow and further enhance the hydrologic model’s capability for accurate hydrologic studies

Keywords: crop yield, roughness coefficient, PAR, WRM model

Procedia PDF Downloads 409

Authors: Mojtaba Hakimi-Moghaddam

Abstract:

Positive real and strictly positive real transfer functions are important concepts in the control theory. In this paper, the results of researches in these areas are summarized. Definitions together with their graphical interpretations are mentioned. The equivalent conditions in the frequency domain and state space representations are reviewed. Their equivalent electrical networks are explained. Also, a comprehensive discussion about a difference between behavior of real part of positive real and strictly positive real transfer functions in high frequencies is presented. Furthermore, several illustrative examples are given.

Keywords: real rational transfer functions, positive realness property, strictly positive realness property, equivalent conditions

Procedia PDF Downloads 386

Authors: Fatema Akram, Mohammad G. Rasul, M. Masud K. Khan, M. Sharif I. I. Amir

Abstract:

Australia is a country of some 7,700 million square kilometres with a population of about 22.6 million. At present water security is a major challenge for Australia. In some areas the use of water resources is approaching and in some parts it is exceeding the limits of sustainability. A focal point of proposed national water conservation programs is the recycling of both urban storm-water and treated wastewater. But till now it is not widely practiced in Australia, and particularly storm-water is neglected. In Australia, only 4% of storm-water and rainwater is recycled, whereas less than 1% of reclaimed wastewater is reused within urban areas. Therefore, accurately monitoring, assessing and predicting the availability, quality and use of this precious resource are required for better management. As storm-water is usually of better quality than untreated sewage or industrial discharge, it has better public acceptance for recycling and reuse, particularly for non-potable use such as irrigation, watering lawns, gardens, etc. Existing storm-water recycling practice is far behind of research and no robust technologies developed for this purpose. Therefore, there is a clear need for using modern technologies for assessing feasibility of storm-water harvesting and reuse. Numerical modelling has, in recent times, become a popular tool for doing this job. It includes complex hydrological and hydraulic processes of the study area. The hydrologic model computes storm-water quantity to design the system components, and the hydraulic model helps to route the flow through storm-water infrastructures. Nowadays water quality module is incorporated with these models. Integration of Geographic Information System (GIS) with these models provides extra advantage of managing spatial information. However for the overall management of a storm-water harvesting project, Decision Support System (DSS) plays an important role incorporating database with model and GIS for the proper management of temporal information. Additionally DSS includes evaluation tools and Graphical user interface. This research aims to critically review and discuss all the aspects of storm-water harvesting and reuse such as available guidelines of storm-water harvesting and reuse, public acceptance of water reuse, the scopes and recommendation for future studies. In addition to these, this paper identifies, understand and address the importance of modern technologies capable of proper management of storm-water harvesting and reuse.

Keywords: storm-water management, storm-water harvesting and reuse, numerical modelling, geographic information system, decision support system, database

Procedia PDF Downloads 372

Authors: Anna Avramenko, Heikki Haario

Abstract:

This paper reports the development and application of a 2D depth-averaged model. The main goal of this contribution is to apply the depth averaged equations to a wind park model in which the treatment of the geometry, introduced on the mathematical model by the mass and momentum source terms. The depth-averaged model will be used in future to find the optimal position of wind turbines in the wind park. K-E and 2D LES turbulence models were consider in this article. 2D CFD simulations for one hill was done to check the depth-averaged model in practise.

Keywords: depth-averaged equations, numerical modeling, CFD, wind park model

Procedia PDF Downloads 603