Search results for: neural substrates

Authors: Tal Remez, Or Litany, Alex Bronstein

Abstract:

The pursuit of smaller pixel sizes at ever increasing resolution in digital image sensors is mainly driven by the stringent price and form-factor requirements of sensors and optics in the cellular phone market. Recently, Eric Fossum proposed a novel concept of an image sensor with dense sub-diffraction limit one-bit pixels (jots), which can be considered a digital emulation of silver halide photographic film. This idea has been recently embodied as the EPFL Gigavision camera. A major bottleneck in the design of such sensors is the image reconstruction process, producing a continuous high dynamic range image from oversampled binary measurements. The extreme quantization of the Poisson statistics is incompatible with the assumptions of most standard image processing and enhancement frameworks. The recently proposed maximum-likelihood (ML) approach addresses this difficulty, but suffers from image artifacts and has impractically high computational complexity. In this work, we study a variant of a sensor with binary threshold pixels and propose a reconstruction algorithm combining an ML data fitting term with a sparse synthesis prior. We also show an efficient hardware-friendly real-time approximation of this inverse operator. Promising results are shown on synthetic data as well as on HDR data emulated using multiple exposures of a regular CMOS sensor.

Keywords: binary pixels, maximum likelihood, neural networks, sparse coding

Procedia PDF Downloads 175

Authors: Beier Zhu, Rui Zhang, Qi Song

Abstract:

Text contained within fixed-layout documents can be of great semantic value and so requires a high localization accuracy, such as ID cards, invoices, cheques, and passports. Recently, algorithms based on deep convolutional networks achieve high performance on text detection tasks. However, for text localization in fixed-layout documents, such algorithms detect word bounding boxes individually, which ignores the layout information. This paper presents a novel architecture built on convolutional neural networks (CNNs). A global text localization network and a regional bounding-box regression network are introduced to tackle the problem in a coarse-to-fine manner. The text localization network simultaneously locates word bounding points, which takes the layout information into account. The bounding-box regression network inputs the features pooled from arbitrarily sized RoIs and refine the localizations. These two networks share their convolutional features and are trained jointly. A typical type of fixed-layout documents: ID cards, is selected to evaluate the effectiveness of the proposed system. These networks are trained on data cropped from nature scene images, and synthetic data produced by a synthetic text generation engine. Experiments show that our approach locates high accuracy word bounding boxes and achieves state-of-the-art performance.

Keywords: bounding box regression, convolutional networks, fixed-layout documents, text localization

Procedia PDF Downloads 169

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 113

Authors: Dechao Meng, Yongqi Dong, Qiyuan Feng, Zhangzhang Cui, Xiang Hu, Haoliang Huang, Genhao Liang, Huanhua Wang, Hua Zhou, Hawoong Hong, Jinghua Guo, Qingyou Lu, Xiaofang Zhai, Yalin Lu

Abstract:

Great efforts have been taken to reveal the intrinsic origins of emerging ferromagnetism (FM) in strained LaCoO₃ (LCO) films. However, some macro magnetic performances of LCO are still not well understood and even controversial, such as magnetic anisotropy. Determining and understanding magnetic anisotropy might help to find the true causes of FM in turn. Perpendicular magnetic anisotropy (PMA) was the first time to be directly observed in high-quality LCO films with different thickness. The in-plane (IP) and out of plane (OOP) remnant magnetic moment ratio of 30 unit cell (u.c.) films is as large as 20. The easy axis lays in the OOP direction with an IP/OOP coercive field ratio of 10. What's more, the PMA could be simply tuned by changing the thickness. With the thickness increases, the IP/OOP magnetic moment ratio remarkably decrease with magnetic easy axis changing from OOP to IP. Such a huge and tunable PMA performance exhibit strong potentials in fundamental researches or applications. What causes PMA is the first concern. More OOP orbitals occupation may be one of the micro reasons of PMA. A cluster-like magnetic domain pattern was found in 30 u.c. with no obvious color contrasts, similar to that of LaAlO₃/SrTiO₃ films. And the nanosize domains could not be totally switched even at a large OOP magnetic field of 23 T. It indicates strong IP characters or none OOP magnetism of some clusters. The IP magnetic domains might influence the magnetic performance and help to form PMA. Meanwhile some possible nonmagnetic clusters might be the reason why the measured moments of LCO films are smaller than the calculated values 2 μB/Co, one of the biggest confusions in LCO films.What tunes PMA seems much more interesting. Totally different magnetic domain patterns were found in 180 u.c. films with cluster magnetic domains surrounded by < 110 > cross-hatch lines. These lines were regarded as structure domain walls (DWs) determined by 3D reciprocal space mapping (RSM). Two groups of in-plane features with fourfold symmetry were observed near the film diffraction peaks in (002) 3D-RSM. One is along < 110 > directions with a larger intensity, which is well match the lines on the surfaces. The other is much weaker and along < 100 > directions, which is from the normal lattice titling of films deposited on cubic substrates. The < 110 > domain features obtained from (103) and (113) 3D-RSMs exhibit similar evolution of the DWs percentages and magnetic behavior. Structure domains and domain walls are believed to tune PMA performances by transform more IP magnetic moments to OOP. Last but not the least, thick films with lots of structure domains exhibit different electrical transport behaviors. A metal-to-insulator transition (MIT) and an angular dependent negative magnetic resistivity were observed near 150 K, higher than FM transition temperature but similar to that of spin-orbital coupling related 1/4 order diffraction peaks.

Keywords: structure domain, magnetic anisotropy, magnetic domain, domain wall, 3D-RSM, strain

Procedia PDF Downloads 130

Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Abstract:

Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.

Keywords: retail stores, faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition

Procedia PDF Downloads 121

Authors: Malihe Ahmadi

Abstract:

Nowadays, stress, tension and neural problems are among the most important concerns of the present age. The environment plays key role on improving mental health and reducing stress of citizens. Establishing balance and appropriate relationship between city and natural environment is of the most important approaches of present century. Type of approach and logical planning for urban green spaces as one of the basic sections of integration with nature, not only plays key role on quality and efficiency of comprehensive urban planning; but also it increases the system of distributing social activities and happiness and lively property of urban environments that leads to permanent urban development. The main purpose of recovering urban identity is considering culture, history and human life style in past. This is a documentary-library research that evaluates the historical properties of Iranian gardens in compliance with climate condition. Results of this research reveal that in addition to following Iranian gardens from common principles of land lot, structure of flowers and plants, water, specific buildings during different ages, the role of climate at different urban areas is among the basics of determining method of designing green spaces and different buildings located at diverse areas i.e. Iranian gardens are a space for merging natural and artificial elements that has inseparable connection with semantic principles and guarantees different functions. Some of the necessities of designing present urban gardens are including: recognition and recreation.

Keywords: historical gardens, climate, properties of Iranian gardens, Iran

Procedia PDF Downloads 377

Authors: Redouane Larbi Boufeniza, Jing-Jia Luo

Abstract:

This study assesses the suitability of deep learning (DL) for downscaling sea surface temperature (SST) over the Mediterranean Sea in the context of seasonal forecasting. We design a set of experiments that compare different DL configurations and deploy the best-performing architecture to downscale one-month lead forecasts of June–September (JJAS) SST from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0 (NUIST-CFS1.0) for the period of 1982–2020. We have also introduced predictors over a larger area to include information about the main large-scale circulations that drive SST over the Mediterranean Sea region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results showed that the convolutional neural network (CNN)-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme SST spatial patterns. Besides, the CNN-based downscaling yields a much more accurate forecast of extreme SST and spell indicators and reduces the significant relevant biases exhibited by the raw model predictions. Moreover, our results show that the CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of the Mediterranean Sea. The results demonstrate the potential usefulness of CNN in downscaling seasonal SST predictions over the Mediterranean Sea, particularly in providing improved forecast products.

Keywords: Mediterranean Sea, sea surface temperature, seasonal forecasting, downscaling, deep learning

Procedia PDF Downloads 50

Authors: Antonina Semakova, Karim Mynbaev, Nikolai Bazhenov, Anton Chernyaev, Sergei Kizhaev, Nikolai Stoyanov

Abstract:

At present, heterostructures are used for fabrication of almost all types of optoelectronic devices. Our research focuses on the optoelectronic properties of InAs(Sb) solid solutions that are widely used in fabrication of light emitting diodes (LEDs) operating in middle wavelength infrared range (MWIR). This spectral range (2-6 μm) is relevant for laser diode spectroscopy of gases and molecules, for systems for the detection of explosive substances, medical applications, and for environmental monitoring. The fabrication of MWIR LEDs that operate efficiently at room temperature is mainly hindered by the predominance of non-radiative Auger recombination of charge carriers over the process of radiative recombination, which makes practical application of LEDs difficult. However, non-radiative recombination can be partly suppressed in quantum-well structures. In this regard, studies of such structures are quite topical. In this work, electroluminescence (EL) of LED heterostructures based on InAs(Sb) epitaxial films with the molar fraction of InSb ranging from 0 to 0.09 and multi quantum-well (MQW) structures was studied in the temperature range 4.2-300 K. The growth of the heterostructures was performed by metal-organic chemical vapour deposition on InAs substrates. On top of the active layer, a wide-bandgap InAsSb(Ga,P) barrier was formed. At low temperatures (4.2-100 K) stimulated emission was observed. As the temperature increased, the emission became spontaneous. The transition from stimulated emission to spontaneous one occurred at different temperatures for structures with different InSb contents in the active region. The temperature-dependent carrier lifetime, limited by radiative recombination and the most probable Auger processes (for the materials under consideration, CHHS and CHCC), were calculated within the framework of the Kane model. The effect of various recombination processes on the carrier lifetime was studied, and the dominant role of Auger processes was established. For MQW structures quantization energies for electrons, light and heavy holes were calculated. A characteristic feature of the experimental EL spectra of these structures was the presence of peaks with energy different from that of calculated optical transitions between the first quantization levels for electrons and heavy holes. The obtained results showed strong effect of the specific electronic structure of InAsSb on the energy and intensity of optical transitions in nanostructures based on this material. For the structure with MQWs in the active layer, a very weak temperature dependence of EL peak was observed at high temperatures (>150 K), which makes it attractive for fabricating temperature-resistant gas sensors operating in the middle-infrared range.

Keywords: Electroluminescence, InAsSb, light emitting diode, quantum wells

Procedia PDF Downloads 178

Authors: L. Freeborn

Abstract:

Recent years have seen an increasing number of neuroimaging studies related to language learning as imaging techniques such as fMRI and EEG have become more widely accessible to researchers. By using a variety of structural and functional neuroimaging techniques, these studies have already made considerable progress in terms of our understanding of neural networks and processing related to first and second language acquisition. However, the methodological designs employed in neuroimaging studies to test language learning have been questioned by applied linguists working within the field of second language acquisition (SLA). One of the major criticisms is that tasks designed to measure language learning gains rarely have a communicative function, and seldom assess learners’ ability to use the language in authentic situations. This brings the validity of many neuroimaging tasks into question. The fundamental reason why people learn a language is to communicate, and it is well-known that both first and second language proficiency are developed through meaningful social interaction. With this in mind, the SLA field is in agreement that second language acquisition and proficiency should be measured through learners’ ability to communicate in authentic real-life situations. Whilst authenticity is not always possible to achieve in a classroom environment, the importance of task authenticity should be reflected in the design of language assessments, teaching materials, and curricula. Tasks that bear little relation to how language is used in real-life situations can be considered to lack construct validity. This paper first describes the typical tasks used in neuroimaging studies to measure language gains and proficiency, then analyses to what extent these tasks can validly assess these constructs.

Keywords: neuroimaging studies, research design, second language acquisition, task validity

Procedia PDF Downloads 110

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 115

Authors: Evgeniya Orlova, Dmitriy Feoktistov, Geniy Kuznetsov

Abstract:

Spreading of a droplet over a solid substrate is a key phenomenon observed in the following engineering applications: thin film coating, oil extraction, inkjet printing, and spray cooling of heated surfaces. Droplet cooling systems are known to be more effective than film or rivulet cooling systems. It is caused by the greater evaporation surface area of droplets compared with the film of the same mass and wetting surface. And the greater surface area of droplets is connected with the curvature of the interface. Location of the droplets on the cooling surface influences on the heat transfer conditions. The close distance between the droplets provides intensive heat removal, but there is a possibility of their coalescence in the liquid film. The long distance leads to overheating of the local areas of the cooling surface and the occurrence of thermal stresses. To control the location of droplets is possible by changing the roughness, structure and chemical composition of the surface. Thus, control of spreading can be implemented. The most important characteristic of spreading of droplets on solid surfaces is a dynamic contact angle, which is a function of the contact line speed or capillary number. However, there is currently no universal equation, which would describe the relationship between these parameters. This paper presents the results of the experimental studies of water droplet spreading on metal substrates with different surface roughness. The effect of the droplet growth rate and the surface roughness on spreading characteristics was studied at low capillary numbers. The shadow method using high speed video cameras recording up to 10,000 frames per seconds was implemented. A droplet profile was analyzed by Axisymmetric Drop Shape Analyses techniques. According to change of the dynamic contact angle and the contact line speed three sequential spreading stages were observed: rapid increase in the dynamic contact angle; monotonous decrease in the contact angle and the contact line speed; and form of the equilibrium contact angle at constant contact line. At low droplet growth rate, the dynamic contact angle of the droplet spreading on the surfaces with the maximum roughness is found to increase throughout the spreading time. It is due to the fact that the friction force on such surfaces is significantly greater than the inertia force; and the contact line is pinned on microasperities of a relief. At high droplet growth rate the contact angle decreases during the second stage even on the surfaces with the maximum roughness, as in this case, the liquid does not fill the microcavities, and the droplet moves over the “air cushion”, i.e. the interface is a liquid/gas/solid system. Also at such growth rates pulsation of liquid flow was detected; and the droplet oscillates during the spreading. Thus, obtained results allow to conclude that it is possible to control spreading by using the surface roughness and the growth rate of droplets on surfaces as varied factors. Also, the research findings may be used for analyzing heat transfer in rivulet and drop cooling systems of high energy equipment.

Keywords: contact line speed, droplet growth rate, dynamic contact angle, shadow system, spreading

Procedia PDF Downloads 301

Authors: N. Slepickova Kasalkova, P. Slepicka, L. Bacakova, V. Svorcik

Abstract:

Tissue engineering includes combination of materials and techniques used for the improvement, repair or replacement of the tissue. Scaffolds, permanent or temporally material, are used as support for the creation of the "new cell structures". For this important component (scaffold), a variety of materials can be used. The advantage of some polymeric materials is their cytocompatibility and possibility of biodegradation. Poly(L-lactic acid) (PLLA) is a biodegradable,  semi-crystalline thermoplastic polymer. PLLA can be fully degraded into H₂O and CO₂. In this experiment, the effect of the surface modification of biodegradable polymer (performed by plasma treatment) on the various cell types was studied. The surface parameters and changes of the physicochemical properties of modified PLLA substrates were studied by different methods. Surface wettability was determined by goniometry, surface morphology and roughness study were performed with atomic force microscopy and chemical composition was determined using photoelectron spectroscopy. The physicochemical properties were studied in relation to cytocompatibility of human osteoblast (MG 63 cells), rat vascular smooth muscle cells (VSMC), and human stem cells (ASC) of the adipose tissue in vitro. A fluorescence microscopy was chosen to study and compare cell-material interaction. Important parameters of the cytocompatibility like adhesion, proliferation, viability, shape, spreading of the cells were evaluated. It was found that the modification leads to the change of the surface wettability depending on the time of modification. Short time of exposition (10-120 s) can reduce the wettability of the aged samples, exposition longer than 150 s causes to increase of contact angle of the aged PLLA. The surface morphology is significantly influenced by duration of modification, too. The plasma treatment involves the formation of the crystallites, whose number increases with increasing time of modification. On the basis of physicochemical properties evaluation, the cells were cultivated on the selected samples. Cell-material interactions are strongly affected by material chemical structure and surface morphology. It was proved that the plasma treatment of PLLA has a positive effect on the adhesion, spreading, homogeneity of distribution and viability of all cultivated cells. This effect was even more apparent for the VSMCs and ASCs which homogeneously covered almost the whole surface of the substrate after 7 days of cultivation. The viability of these cells was high (more than 98% for VSMCs, 89-96% for ASCs). This experiment is one part of the basic research, which aims to easily create scaffolds for tissue engineering with subsequent use of stem cells and their subsequent "reorientation" towards the bone cells or smooth muscle cells.

Keywords: poly(L-lactic acid), plasma treatment, surface characterization, cytocompatibility, human osteoblast, rat vascular smooth muscle cells, human stem cells

Procedia PDF Downloads 209

Authors: Vishwanath Pethri Kamath, Jayantha Gowda Sarapanahalli, Vishal Mishra, Siddhesh Balwant Bandgar

Abstract:

Recognition of emotional information is essential in any form of communication. Growing HCI (Human-Computer Interaction) in recent times indicates the importance of understanding of emotions expressed and becomes crucial for improving the system or the interaction itself. In this research work, textual data for emotion recognition is used. The text being the least expressive amongst the multimodal resources poses various challenges such as contextual information and also sequential nature of the language construction. In this research work, the proposal is made for a neural architecture to resolve not less than 8 emotions from textual data sources derived from multiple datasets using google pre-trained word2vec word embeddings and a Multi-head attention-based bidirectional LSTM model with a one-vs-all Multi-Level Classification. The emotions targeted in this research are Anger, Disgust, Fear, Guilt, Joy, Sadness, Shame, and Surprise. Textual data from multiple datasets were used for this research work such as ISEAR, Go Emotions, Affect datasets for creating the emotions’ dataset. Data samples overlap or conflicts were considered with careful preprocessing. Our results show a significant improvement with the modeling architecture and as good as 10 points improvement in recognizing some emotions.

Keywords: text emotion recognition, bidirectional LSTM, multi-head attention, multi-level classification, google word2vec word embeddings

Procedia PDF Downloads 150

Authors: Hichem Sassi

Abstract:

Pneumonia, being a respiratory infection, has garnered global attention due to its rapid transmission and relatively high mortality rates. Timely detection and treatment play a crucial role in significantly reducing mortality associated with pneumonia. Presently, X-ray diagnosis stands out as a reasonably effective method. However, the manual scrutiny of a patient's X-ray chest radiograph by a proficient practitioner usually requires 5 to 15 minutes. In situations where cases are concentrated, this places immense pressure on clinicians for timely diagnosis. Relying solely on the visual acumen of imaging doctors proves to be inefficient, particularly given the low speed of manual analysis. Therefore, the integration of artificial intelligence into the clinical image diagnosis of pneumonia becomes imperative. Additionally, AI recognition is notably rapid, with convolutional neural networks (CNNs) demonstrating superior performance compared to human counterparts in image identification tasks. To conduct our study, we utilized a dataset comprising chest X-ray images obtained from Kaggle, encompassing a total of 5216 training images and 624 test images, categorized into two classes: normal and pneumonia. Employing five mainstream network algorithms, we undertook a comprehensive analysis to classify these diseases within the dataset, subsequently comparing the results. The integration of artificial intelligence, particularly through improved network architectures, stands as a transformative step towards more efficient and accurate clinical diagnoses across various medical domains.

Keywords: deep learning, computer vision, pneumonia, models, comparative study

Procedia PDF Downloads 28

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 7

Authors: Raymond Xu, Ashley Hua, Andrew Wang, Yuru Lin

Abstract:

During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.

Keywords: artificial intelligence, COVID-19, depression detection, psychiatric disorder

Procedia PDF Downloads 108

Authors: Trevor Malambo Simbayi, Diane Hildebrandt, Tonderayi Matambo

Abstract:

The rapid growth of population in recent decades has resulted in an increased need for energy to meet human activities. As energy demands increase, the need for other sources of energy other than fossil fuels, increases in turn. Furthermore, environmental concerns such as global warming due to the use of fossil fuels, depleting fossil fuel reserves and the rising cost of oil have contributed to an increased interest in renewables sources of energy. Biogas is a renewable source of energy produced through the process of anaerobic digestion (AD) and it offers a two-fold solution; it provides an environmentally friendly source of energy and its production helps to reduce the amount of organic waste taken to landfills. This research seeks to address the waste management problem caused by an aquatic weed called water hyacinth (Eichhornia crassipes) at the Hartbeespoort (Harties) Dam in the North West Province of South Africa, through biogas production of the weed. Water hyacinth is a category 1 invasive species and it is deemed to be the most problematic aquatic weed. This weed is said to double its size in the space of five days. Eutrophication in the Hartbeespoort Dam has manifested itself through the excessive algae bloom and water hyacinth infestation. A large amount of biomass from water hyacinth and algae are generated per annum from the two hundred hectare surface area of the dam exposed to the sun. This biomass creates a waste management problem. Water hyacinth when in full bloom can cover nearly half of the surface of Hartbeespoort Dam. The presence of water hyacinth in the dam has caused economic and environmental problems. Economic activities such as fishing, boating, and recreation, are hampered by the water hyacinth’s prolific growth. This research proposes the use of water hyacinth as a feedstock or substrate for biogas production in order to find an economic and environmentally friendly means of waste management for the communities living around the Hartbeespoort Dam. In order to achieve this objective, water hyacinth will be collected from the dam and it will be mechanically pretreated before anaerobic digestion. Pretreatment is required for lignocellulosic materials like water hyacinth because such materials are called recalcitrant solid materials. Cow manure will be employed as a source of microorganisms needed for biogas production to occur. Once the water hyacinth and the cow dung are mixed, they will be placed in laboratory anaerobic reactors. Biogas production will be monitored daily through the downward displacement of water. Characterization of the substrates (cow manure and water hyacinth) to determine the nitrogen, sulfur, carbon and hydrogen, total solids (TS) and volatile solids (VS). Liquid samples from the anaerobic digesters will be collected and analyzed for volatile fatty acids (VFAs) composition by means of a liquid gas chromatography machine.

Keywords: anaerobic digestion, biogas, waste management, water hyacinth

Procedia PDF Downloads 168

Authors: G. Shahzadi, A. Soulaimani

Abstract:

This research work aims to identify the physical parameters of the constitutive soil model in the design of a rockfill dam by inverse analysis. The best parameters of the constitutive soil model, are those that minimize the objective function, defined as the difference between the measured and numerical results. The Finite Element code (Plaxis) has been utilized for numerical simulation. Polynomial and neural network-based response surfaces have been generated to analyze the relationship between soil parameters and displacements. The performance of surrogate models has been analyzed and compared by evaluating the root mean square error. A comparative study has been done based on objective functions and optimization techniques. Objective functions are categorized by considering measured data with and without uncertainty in instruments, defined by the least square method, which estimates the norm between the predicted displacements and the measured values. Hydro Quebec provided data sets for the measured values of the Romaine-2 dam. Stochastic optimization, an approach that can overcome local minima, and solve non-convex and non-differentiable problems with ease, is used to obtain an optimum value. Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Differential Evolution (DE) are compared for the minimization problem, although all these techniques take time to converge to an optimum value; however, PSO provided the better convergence and best soil parameters. Overall, parameter identification analysis could be effectively used for the rockfill dam application and has the potential to become a valuable tool for geotechnical engineers for assessing dam performance and dam safety.

Keywords: Rockfill dam, parameter identification, stochastic analysis, regression, PLAXIS

Procedia PDF Downloads 112

Authors: Mohd Iz'aan Paiz Bin Zamri, Anis Salwa Mohd Khairuddin, Norrima Mokhtar, Rubiyah Yusof

Abstract:

Effective statistical feature extraction and classification are important in image-based automatic inspection and analysis. An automatic wood species recognition system is designed to perform wood inspection at custom checkpoints to avoid mislabeling of timber which will results to loss of income to the timber industry. The system focuses on analyzing the statistical pores properties of the wood images. This paper proposed a fuzzy-based feature extractor which mimics the experts’ knowledge on wood texture to extract the properties of pores distribution from the wood surface texture. The proposed feature extractor consists of two steps namely pores extraction and fuzzy pores management. The total number of statistical features extracted from each wood image is 38 features. Then, a backpropagation neural network is used to classify the wood species based on the statistical features. A comprehensive set of experiments on a database composed of 5200 macroscopic images from 52 tropical wood species was used to evaluate the performance of the proposed feature extractor. The advantage of the proposed feature extraction technique is that it mimics the experts’ interpretation on wood texture which allows human involvement when analyzing the wood texture. Experimental results show the efficiency of the proposed method.

Keywords: classification, feature extraction, fuzzy, inspection system, image analysis, macroscopic images

Procedia PDF Downloads 400

Authors: Arinze Ezieke, Antonio Serrano, William Clarke, Denys Villa-Gomez

Abstract:

Berry cultivation results in discharge of high organic strength putrescible solid waste which potentially contributes to environmental degradation, making it imperative to assess options for its complete management. Anaerobic digestion (AD) could be an ideal option when the target is energy generation; however, due to berry fruit characteristics high carbohydrate composition, the technology could be limited by its high alkalinity requirement which suggests dosing of additives such as buffers and trace elements supplement. Overcoming this limitation in an economically viable way could entail replacement of synthetic additives with recycled by-product waste. Consequently, ash from co-smouldering of high COD characteristic AD digestate and coco-coir could be a promising material to be used to enhance the AD of berry fruit waste, given its characteristic high pH, alkalinity and metal concentrations which is typical of synthetic additives. Therefore, the aim of the research was to evaluate the stability and process performance from the AD of BFW when ash from co-smoldered digestate and coir are supplemented as alkalinity and trace elements (TEs) source. Series of batch experiments were performed to ascertain the necessity for alkalinity addition and to see whether the alkalinity and metals in the co-smouldered digestate ash can provide the necessary buffer and TEs for AD of berry fruit waste. Triplicate assays were performed in batch systems following I/S of 2 (in VS), using serum bottles (160 mL) sealed and placed in a heated room (35±0.5 °C), after creating anaerobic conditions. Control experiment contained inoculum and substrates only, and inoculum, substrate and NaHCO3 for optimal total alkalinity concentration and TEs assays, respectively. Total alkalinity concentration refers to alkalinity of inoculum and the additives. The alkalinity and TE potential of the ash were evaluated by supplementing ash (22.574 g/kg) of equivalent total alkalinity concentration to that of the pre-determined optimal from NaHCO3, and by dosing ash (0.012 – 7.574 g/kg) of varying concentrations of specific essential TEs (Co, Fe, Ni, Se), respectively. The result showed a stable process at all examined conditions. Supplementation of 745 mg/L CaCO3 NaHCO3 resulted to an optimum TAC of 2000 mg/L CaCO3. Equivalent ash supplementation of 22.574 g/kg allowed the achievement of this pre-determined optimum total alkalinity concentration, resulting to a stable process with a 92% increase in the methane production rate (323 versus 168 mL CH4/ (gVS.d)), but a 36% reduction in the cumulative methane production (103 versus 161 mL CH4/gVS). Addition of ashes at incremental dosage as TEs source resulted to a reduction in the Cumulative methane production, with the highest dosage of 7.574 g/kg having the highest effect of -23.5%; however, the seemingly immediate bioavailability of TE at this high dosage allowed for a +15% increase in the methane production rate. With an increased methane production rate, the results demonstrated that the ash at high dosages could be an effective supplementary material for either a buffered or none buffered berry fruit waste AD system.

Keywords: anaerobic digestion, alkalinity, co-smoldered digestate ash, trace elements

Procedia PDF Downloads 100

Authors: Jacintha Menezes, Ramalingam Dharmalingam, Palaiahnakote Shivakumara

Abstract:

In the recent years, Omani acid lime cultivation and production has been affected by Citrus greening or Huanglongbing (HLB) disease. HLB disease is one of the most destructive diseases for citrus, with no remedies or countermeasures to stop the disease. Currently used Polymerase chain reaction (PCR) and enzyme-linked immunosorbent assay (ELISA) HLB detection tests require lengthy and labor-intensive laboratory procedures. Furthermore, the equipment and staff needed to carry out the laboratory procedures are frequently specialized hence making them a less optimal solution for the detection of the disease. The current research uses hyperspectral imaging technology for automatic detection of citrus trees with HLB disease. Omani citrus tree leaf images were captured through portable Specim IQ hyperspectral camera. The research considered healthy, nutrition deficient, and HLB infected leaf samples based on the Polymerase chain reaction (PCR) test. The highresolution image samples were sliced to into sub cubes. The sub cubes were further processed to obtain RGB images with spatial features. Similarly, RGB spectral slices were obtained through a moving window on the wavelength. The resized spectral-Spatial RGB images were given to Convolution Neural Networks for deep features extraction. The current research was able to classify a given sample to the appropriate class with 92.86% accuracy indicating the effectiveness of the proposed techniques. The significant bands with a difference in three types of leaves are found to be 560nm, 678nm, 726 nm and 750nm.

Keywords: huanglongbing (HLB), hyperspectral imaging (HSI), · omani citrus, CNN

Procedia PDF Downloads 50

Authors: Chul Lee, Seoae Cho, Erich D. Jarvis, Heebal Kim

Abstract:

Vocal learning, the ability to imitate vocalizations based on auditory experience, is a homoplastic character state observed in different independent lineages of animals such as songbirds, parrots, hummingbirds and human. It has now become possible to perform genome-wide molecular analyses across vocal learners and vocal non-learners with the recent expansion of avian genome data. It was analyzed the whole genomes of human and 48 avian species including those belonging to the three avian vocal learning lineages, to determine if behavior and neural convergence are associated with molecular convergence in divergent species of vocal learners. Analyses of 8295 orthologous genes across bird species revealed 141 genes with amino acid substitutions specific to vocal learners. Out of these, 25 genes have vocal learner specific genetic homoplasies, and their functions were enriched for learning. Several sites in these genes are estimated under convergent evolution and positive selection. A potential role for a subset of these genes in vocal learning was supported by associations with gene expression profiles in vocal learning brain regions of songbirds and human disease that cause language dysfunctions. The key candidate gene with multiple independent lines of the evidences specific to vocal learners was DRD5. Our findings suggest cAMP-based learning pathway in avian vocal learners, indicating molecular homoplastic changes associated with a complex behavioral trait, vocal learning.

Keywords: amino acid substitutions, convergent evolution, positive selection, vocal learning

Procedia PDF Downloads 312

Authors: Qasim Munye, Juned Islam, Haseeb Qureshi, Syed Jung

Abstract:

Lung nodules are commonly identified in computed tomography (CT) scans by experienced radiologists at a relatively late stage. Early diagnosis can greatly increase survival. We propose using a pix2pix conditional generative adversarial network to generate realistic images simulating early-stage lung nodule growth. We have applied deep images prior to 2341 slices from 895 computed tomography (CT) scans from the Lung Image Database Consortium (LIDC) dataset to generate pseudo-healthy medical images. From these images, 819 were chosen to train a pix2pix network. We observed that for most of the images, the pix2pix network was able to generate images where the nodule increased in size and intensity across epochs. To evaluate the images, 400 generated images were chosen at random and shown to a medical student beside their corresponding original image. Of these 400 generated images, 384 were defined as satisfactory - meaning they resembled a nodule and were visually similar to the corresponding image. We believe that this generated dataset could be used as training data for neural networks to detect lung nodules at an early stage or to improve the accuracy of such networks. This is particularly significant as datasets containing the growth of early-stage nodules are scarce. This project shows that the combination of deep image prior and generative models could potentially open the door to creating larger datasets than currently possible and has the potential to increase the accuracy of medical classification tasks.

Keywords: medical technology, artificial intelligence, radiology, lung cancer

Procedia PDF Downloads 44

Authors: Seung Ju Yeon, Seul Ki Min, Jun Sang Park, Yeo Seon Kwon, Hoo Cheol Lee, Hyun Jung Shim, Il-Doo Kim, Ja Kyeong Lee, Hwa Sung Shin

Abstract:

In brain injury, depleting oxidative stress is the most effective way to reduce the brain infarct size. C-phycocyanin (C-Pc) is a well-known antioxidant protein that has neuroprotective effects obtained from green microalgae. Astrocyte is glial cell that supports the nerve cell such as neuron, which account for a large portion of the brain. In brain injury, such as ischemia and reperfusion, astrocyte has an important rule that overcomes the oxidative stress and protect from brain reactive oxygen species (ROS) injury. However little is known about how C-Pc regulates the anti-oxidants effects of astrocyte. In this study, when the C-Pc was treated in oxidized astrocyte, we confirmed that inflammatory factors Interleukin-6 and Interleukin-3 were increased and antioxidants enzyme, Superoxide dismutase (SOD) and catalase was upregulated, and neurotrophic factors, brain-derived neurotrophic factor (BDNF) and nerve growth factor (NGF) was alleviated. Also, it was confirmed to reduce infarct size of the brain in ischemia and reperfusion because C-Pc has anti-oxidant effects in middle cerebral artery occlusion (MCAO) animal model. These results show that C-Pc can help astrocytes lead neuroprotective activities in the oxidative stressed environment of the brain. In summary, the C-PC protects astrocytes from oxidative stress and has anti-oxidative, anti-inflammatory, neurotrophic effects under ischemic situations.

Keywords: c-phycocyanin, astrocyte, reactive oxygen species, ischemia and reperfusion, neuroprotective effect

Procedia PDF Downloads 294

Authors: K. K. Balavenkatraman, B. Bertschi, K. Bigot, A. Grevot, A. Doelemeyer, S. D. Chibout, A. Wolf, F. Pognan, N. Manevski, O. Kretz, P. Swart, K. Litherland, J. Ashton-Chess, B. Ling, R. Wettstein, D. J. Schaefer

Abstract:

Skin toxicity is poorly detected during preclinical studies, and drug-induced side effects in humans such as rashes, hyperplasia or more serious events like bullous pemphigus or toxic epidermal necrolysis represent an important hurdle for clinical development. In vitro keratinocyte-based epidermal skin models are suitable for the detection of chemical-induced irritancy, but do not recapitulate the biological complexity of full skin and fail to detect potential serious side-effects. Normal healthy skin explants may represent a valuable complementary tool, having the advantage of retaining the full skin architecture and the resident immune cell diversity. This study investigated several conditions for the maintenance of good morphological structure after several days of culture and the retention of phase II metabolism for 24 hours in skin explants in vitro. Human skin samples were collected with informed consent from patients undergoing plastic surgery and immediately transferred and processed in our laboratory by removing the underlying dermal fat. Punch biopsies of 4 mm diameter were cultured in an air-liquid interface using transwell filters. Different cultural conditions such as the effect of calcium, temperature and cultivation media were tested for a period of 14 days and explants were histologically examined after Hematoxylin and Eosin staining. Our results demonstrated that the use of Williams E Medium at 32°C maintained the physiological integrity of the skin for approximately one week. Upon prolonged incubation, the upper layers of the epidermis become thickened and some dead cells are present. Interestingly, these effects were prevented by addition of EGFR inhibitors such as Afatinib or Erlotinib. Phase II metabolism of the skin such as glucuronidation (4-methyl umbeliferone), sulfation (minoxidil), N-acetyltransferase (p-toluidene), catechol methylation (2,3-dehydroxy naphthalene), and glutathione conjugation (chlorodinitro benzene) were analyzed by using LCMS. Our results demonstrated that the human skin explants possess metabolic activity for a period of at least 24 hours for all the substrates tested. A time course for glucuronidation with 4-methyl umbeliferone was performed and a linear correlation was obtained over a period of 24 hours. Longer-term culture studies will indicate the possible evolution of such metabolic activities. In summary, these results demonstrate that human skin explants maintain a normal structure for several days in vitro and are metabolically active for at least the first 24 hours. Hence, with further characterisation, this model may be suitable for the study of drug-induced toxicity.

Keywords: human skin explant, phase II metabolism, epidermal growth factor receptor, toxicity

Procedia PDF Downloads 260

Authors: Zubair Ahmed, Andrea Barbieri

Abstract:

The need to reduce energy consumption has prompted a considerable research effort for developing alternative energy-efficient lighting systems to replace conventional light sources (i.e., incandescent and fluorescent lamps). Organic light emitting device (OLED) technology offers the distinctive possibility to fabricate large area flat devices by vacuum or solution processing. Lanthanide β-diketonates complexes, due to unique photophysical properties of Ln(III) ions, have been explored as emitting layers in OLED displays and in solid-state lighting (SSL) in order to achieve high efficiency and color purity. For such applications, the excellent photoluminescence quantum yield (PLQY) and stability are the two key points that can be achieved simply by selecting the proper organic ligands around the Ln ion in a coordination sphere. Regarding the strategies to enhance the PLQY, the most common is the suppression of the radiationless deactivation pathways due to the presence of high-frequency oscillators (e.g., OH, –CH groups) around the Ln centre. Recently, a different approach to maximize the PLQY of Ln(β-DKs) has been proposed (named 'Escalate Coordination Anisotropy', ECA). It is based on the assumption that coordinating the Ln ion with different ligands will break the centrosymmetry of the molecule leading to less forbidden transitions (loosening the constraints of the Laporte rule). The OLEDs based on such complexes are available, but with low efficiency and stability. In order to get efficient devices, there is a need to develop some new Ln complexes with enhanced PLQYs and stabilities. For this purpose, the Ln complexes, both visible and (NIR) emitting, of variant coordination structures based on the various fluorinated/non-fluorinated β-diketones and O/N-donor neutral ligands were synthesized using a one step in situ method. In this method, the β-diketones, base, LnCl₃.nH₂O and neutral ligands were mixed in a 3:3:1:1 M ratio in ethanol that gave air and moisture stable complexes. Further, they were characterized by means of elemental analysis, NMR spectroscopy and single crystal X-ray diffraction. Thereafter, their photophysical properties were studied to select the best complexes for the fabrication of stable and efficient OLEDs. Finally, the OLEDs were fabricated and investigated using these complexes as emitting layers along with other organic layers like NPB,N,N′-Di(1-naphthyl)-N,N′-diphenyl-(1,1′-biphenyl)-4,4′-diamine (hole-transporting layer), BCP, 2,9-Dimethyl-4,7-diphenyl-1,10-phenanthroline (hole-blocker) and Alq3 (electron-transporting layer). The layers were sequentially deposited under high vacuum environment by thermal evaporation onto ITO glass substrates. Moreover, co-deposition techniques were used to improve charge transport in the devices and to avoid quenching phenomena. The devices show strong electroluminescence at 612, 998, 1064 and 1534 nm corresponding to ⁵D₀ →⁷F₂(Eu), ²F₅/₂ → ²F₇/₂ (Yb), ⁴F₃/₂→ ⁴I₉/₂ (Nd) and ⁴I1₃/₂→ ⁴I1₅/₂ (Er). All the devices fabricated show good efficiency as well as stability.

Keywords: electroluminescence, lanthanides, paramagnetic NMR, photoluminescence

Procedia PDF Downloads 97

Authors: Moustafa Osman Mohammed

Abstract:

This paper introduces topological order in descried social systems starting with the original concept of autopoiesis by biologists and scientists, including the modification of general systems based on socialized medicine. Topological order is important in describing the physical systems for exploiting optical systems and improving photonic devices. The stats of topological order have some interesting properties of topological degeneracy and fractional statistics that reveal the entanglement origin of topological order, etc. Topological ideas in photonics form exciting developments in solid-state materials, that being; insulating in the bulk, conducting electricity on their surface without dissipation or back-scattering, even in the presence of large impurities. A specific type of autopoiesis system is interrelated to the main categories amongst existing groups of the ecological phenomena interaction social and medical sciences. The hypothesis, nevertheless, has a nonlinear interaction with its natural environment 'interactional cycle' for exchange photon energy with molecules without changes in topology. The engineering topology of a biosensor is based on the excitation boundary of surface electromagnetic waves in photonic band gap multilayer films. The device operation is similar to surface Plasmonic biosensors in which a photonic band gap film replaces metal film as the medium when surface electromagnetic waves are excited. The use of photonic band gap film offers sharper surface wave resonance leading to the potential of greatly enhanced sensitivity. So, the properties of the photonic band gap material are engineered to operate a sensor at any wavelength and conduct a surface wave resonance that ranges up to 470 nm. The wavelength is not generally accessible with surface Plasmon sensing. Lastly, the photonic band gap films have robust mechanical functions that offer new substrates for surface chemistry to understand the molecular design structure and create sensing chips surface with different concentrations of DNA sequences in the solution to observe and track the surface mode resonance under the influences of processes that take place in the spectroscopic environment. These processes led to the development of several advanced analytical technologies: which are; automated, real-time, reliable, reproducible, and cost-effective. This results in faster and more accurate monitoring and detection of biomolecules on refractive index sensing, antibody-antigen reactions with a DNA or protein binding. Ultimately, the controversial aspect of molecular frictional properties is adjusted to each other in order to form unique spatial structure and dynamics of biological molecules for providing the environment mutual contribution in investigation of changes due to the pathogenic archival architecture of cell clusters.

Keywords: autopoiesis, photonics systems, quantum topology, molecular structure, biosensing

Procedia PDF Downloads 65

Authors: Yan Huang

Abstract:

Event-related potentials (ERPs) technique helps researchers to make continuous measures on the whole process of language comprehension, with an excellent temporal resolution at the level of milliseconds. The research on sentence processing has developed from the behavioral level to the neuropsychological level, which brings about a variety of sentence processing theories and models. However, the applicability of these models to L2 learners is still under debate. Therefore, the present study aims to investigate the neural mechanisms underlying English subjunctive mood processing by Chinese ESL learners. To this end, English subject clauses with subjunctive moods are used as the stimuli, all of which follow the same syntactic structure, “It is + adjective + that … + (should) do + …” Besides, in order to examine the role that language proficiency plays on L2 processing, this research deals with two groups of Chinese ESL learners (18 males and 22 females, mean age=21.68), namely, high proficiency group (Group H) and low proficiency group (Group L). Finally, the behavioral and neurophysiological data analysis reveals the following findings: 1) Syntax and semantics interact with each other on the SECOND phase (300-500ms) of sentence processing, which is partially in line with the Three-phase Sentence Model; 2) Language proficiency does affect L2 processing. Specifically, for Group H, it is the syntactic processing that plays the dominant role in sentence processing while for Group L, semantic processing also affects the syntactic parsing during the THIRD phase of sentence processing (500-700ms). Besides, Group H, compared to Group L, demonstrates a richer native-like ERPs pattern, which further demonstrates the role of language proficiency in L2 processing. Based on the research findings, this paper also provides some enlightenment for the L2 pedagogy as well as the L2 proficiency assessment.

Keywords: Chinese ESL learners, English subjunctive mood, ERPs, L2 processing

Procedia PDF Downloads 109

Authors: Chi Wu, Dean Wu, Wen-Te Liu, Cheng-Yu Tsai, Shin-Mei Hsu, Yin-Tzu Lin, Ru-Yin Yang

Abstract:

Background: The results of previous studies compared the benefits and risks of receiving insomnia medication. However, the effects between hypnotic drugs used and enhancement of sleep quality were still unclear. Objective: The aim of this study is to establish a prediction model for hypnotic drugs' dosage used for insomnia subjects and associated the relationship between sleep stage ratio change and drug types. Methodologies: According to American Academy of Sleep Medicine (AASM) guideline, sleep stages were classified and transformed to hypnogram via the polysomnography (PSG) in a hospital in New Taipei City (Taiwan). The subjects with diagnosis for insomnia without receiving hypnotic drugs treatment were be set as the comparison group. Conversely, hypnotic drugs dosage within the past three months was obtained from the clinical registration for each subject. Furthermore, the collecting subjects were divided into two groups for training and testing. After training convolution neuron network (CNN) to predict types of hypnotics used and dosages are taken, the test group was used to evaluate the accuracy of classification. Results: We recruited 76 subjects in this study, who had been done PSG for transforming hypnogram from their sleep stages. The accuracy of dosages obtained from confusion matrix on the test group by CNN is 81.94%, and accuracy of hypnotic drug types used is 74.22%. Moreover, the subjects with high ratio of wake stage were correctly classified as requiring medical treatment. Conclusion: CNN with hypnogram was potentially used for adjusting the dosage of hypnotic drugs and providing subjects to pre-screening the types of hypnotic drugs taken.

Keywords: convolution neuron network, hypnotic drugs, insomnia, polysomnography

Procedia PDF Downloads 165

Authors: Md. Mahadi Hasan Sany, Mumenunnessa Keya, Sharun Khushbu, Sheikh Abujar

Abstract:

Since the beginning of China's economic reform, trade between the U.S. and China has grown rapidly, and has increased since China's accession to the World Trade Organization in 2001. The US imports more than it exports from China, reducing the trade war between China and the U.S. for the 2019 trade deficit, but in 2020, the opposite happens. In international and U.S. trade, Washington launched a full-scale trade war against China in March 2016, which occurred a catastrophic epidemic. The main goal of our study is to measure and predict trade relations between China and the U.S., before and after the arrival of the COVID epidemic. The ML model uses different data as input but has no time dimension that is present in the time series models and is only able to predict the future from previously observed data. The LSTM (a well-known Recurrent Neural Network) model is applied as the best time series model for trading forecasting. We have been able to create a sustainable forecasting system in trade between China and the US by closely monitoring a dataset published by the State Website NZ Tatauranga Aotearoa from January 1, 2015, to April 30, 2021. Throughout the survey, we provided a 180-day forecast that outlined what would happen to trade between China and the US during COVID-19. In addition, we have illustrated that the LSTM model provides outstanding outcome in time series data analysis rather than RFR and SVR (e.g., both ML models). The study looks at how the current Covid outbreak affects China-US trade. As a comparative study, RMSE transmission rate is calculated for LSTM, RFR and SVR. From our time series analysis, it can be said that the LSTM model has given very favorable thoughts in terms of China-US trade on the future export situation.

Keywords: RFR, China-U.S. trade war, SVR, LSTM, deep learning, Covid-19, export value, forecasting, time series analysis

Procedia PDF Downloads 168