Search results for: adaptive neural controller

Authors: Pitigalage Chamath Chandira Peiris

Abstract:

A widely researched domain in the field of image processing in recent times has been single image super-resolution, which tries to restore a high-resolution image from a single low-resolution image. Many more single image super-resolution efforts have been completed utilizing equally traditional and deep learning methodologies, as well as a variety of other methodologies. Deep learning-based super-resolution methods, in particular, have received significant interest. As of now, the most advanced image restoration approaches are based on convolutional neural networks; nevertheless, only a few efforts have been performed using Transformers, which have demonstrated excellent performance on high-level vision tasks. The effectiveness of CNN-based algorithms in image super-resolution has been impressive. However, these methods cannot completely capture the non-local features of the data. Enhancer is a simple yet powerful Transformer-based approach for enhancing the resolution of images. A method for single image super-resolution was developed in this study, which utilized an efficient and effective transformer design. This proposed architecture makes use of a locally enhanced window transformer block to alleviate the enormous computational load associated with non-overlapping window-based self-attention. Additionally, it incorporates depth-wise convolution in the feed-forward network to enhance its ability to capture local context. This study is assessed by comparing the results obtained for popular datasets to those obtained by other techniques in the domain.

Keywords: single image super resolution, computer vision, vision transformers, image restoration

Procedia PDF Downloads 80

Authors: Nicola Rubino

Abstract:

This paper presents an analysis of a group of commodity exporting countries' nominal exchange rate movements in relationship to the US dollar. Using a series of Unrestricted Self-exciting Threshold Autoregressive models (SETAR), we model and evaluate sixteen national CPI price differentials relative to the US dollar CPI. Out-of-sample forecast accuracy is evaluated through calculation of mean absolute error measures on the basis of two-hundred and fifty-three months rolling window forecasts and extended to three additional models, namely a logistic smooth transition regression (LSTAR), an additive non linear autoregressive model (AAR) and a simple linear Neural Network model (NNET). Our preliminary results confirm presence of some form of TAR non linearity in the majority of the countries analyzed, with a relatively higher goodness of fit, with respect to the linear AR(1) benchmark, in five countries out of sixteen considered. Although no model appears to statistically prevail over the other, our final out-of-sample forecast exercise shows that SETAR models tend to have quite poor relative forecasting performance, especially when compared to alternative non-linear specifications. Finally, by analyzing the implied half-lives of the > coefficients, our results confirms the presence, in the spirit of arbitrage band adjustment, of band convergence with an inner unit root behaviour in five of the sixteen countries analyzed.

Keywords: transition regression model, real exchange rate, nonlinearities, price differentials, PPP, commodity points

Procedia PDF Downloads 256

Authors: Francesca Nicolosi, Teresa Cosola

Abstract:

Climate changes in Mediterranean areas, such as the increase of average seasonal temperatures, the urban heat island phenomenon, the intensification of solar radiation and the extreme weather threats, cause disruption events, so that climate adaptation has become a pressing issue. Due to the strategic role that the built heritage holds in terms of environmental impact and energy waste and its potentiality, it is necessary to assess the vulnerability and the adaptive capacity of the existing building to climate change, in order to define different mitigation scenarios. The aim of this research work is to define an optimized and integrated methodology for the assessment of resilience levels and adaptation scenarios for existing buildings in Mediterranean urban areas. Moreover, the study of resilience indicators allows us to define building environmental and energy performance in order to identify the design and technological solutions for the improvement of the building and its urban area potentialities. The methodology identifies step-by-step different phases, starting from the detailed study of characteristic elements of urban system: climatic, natural, human, typological and functional components are analyzed in their critical factors and their potential. Through the individuation of the main perturbing factors and the vulnerability degree of the system to the risks linked to climate change, it is possible to define mitigation and adaptation scenarios. They can be different, according to the typological, functional and constructive features of the analyzed system, divided into categories of intervention, and characterized by different analysis levels (from the single building to the urban area). The use of software simulations allows obtaining information on the overall behavior of the building and the urban system, to generate predictive models in the medium and long-term environmental and energy retrofit and to make a comparative study of the mitigation scenarios identified. The studied methodology is validated on a case study.

Keywords: climate impact mitigation, energy efficiency, existing building heritage, resilience

Procedia PDF Downloads 219

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 176

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: Samuel John, S. Sharanya

Abstract:

Automation has become an important part of our life. It has been used to control home entertainment systems, changing the ambience of rooms for different events etc. One of the main parameters to control in a smart home is the atmospheric comfort. Atmospheric comfort mainly includes temperature and relative humidity. In homes, the desired temperature of different rooms varies from 20 °C to 25 °C and relative humidity is around 50%. However, it varies widely. Hence, automated measurement of these parameters to ensure comfort assumes significance. To achieve this, a fuzzy logic controller using Arduino was developed using MATLAB. Arduino is an open source hardware consisting of a 24 pin ATMEGA chip (atmega328), 14 digital input /output pins and an inbuilt ADC. It runs on 5v and 3.3v power supported by a board voltage regulator. Some of the digital pins in Aruduino provide PWM (pulse width modulation) signals, which can be used in different applications. The Arduino platform provides an integrated development environment, which includes support for c, c++ and java programming languages. In the present work, soft sensor was introduced in this system that can indirectly measure temperature and humidity and can be used for processing several measurements these to ensure comfort. The Sugeno method (output variables are functions or singleton/constant, more suitable for implementing on microcontrollers) was used in the soft sensor in MATLAB and then interfaced to the Arduino, which is again interfaced to the temperature and humidity sensor DHT11. The temperature-humidity sensor DHT11 acts as the sensing element in this system. Further, a capacitive humidity sensor and a thermistor were also used to support the measurement of temperature and relative humidity of the surrounding to provide a digital signal on the data pin. The comfort sensor developed was able to measure temperature and relative humidity correctly. The comfort percentage was calculated and accordingly the temperature in the room was controlled. This system was placed in different rooms of the house to ensure that it modifies the comfort values depending on temperature and relative humidity of the environment. Compared to the existing comfort control sensors, this system was found to provide an accurate comfort percentage. Depending on the comfort percentage, the air conditioners and the coolers in the room were controlled. The main highlight of the project is its cost efficiency.

Keywords: arduino, DHT11, soft sensor, sugeno

Procedia PDF Downloads 281

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: Xiaowei Zhang, Min Xu, Saeid Habibi, Fengjun Yan, Ryan Ahmed

Abstract:

Recently, Electric Vehicles (EVs) have received extensive consideration since they offer a more sustainable and greener transportation alternative compared to fossil-fuel propelled vehicles. Lithium-Ion (Li-ion) batteries are increasingly being deployed in EVs because of their high energy density, high cell-level voltage, and low rate of self-discharge. Since Li-ion batteries represent the most expensive component in the EV powertrain, accurate monitoring and control strategies must be executed to ensure their prolonged lifespan. The Battery Management System (BMS) has to accurately estimate parameters such as the battery State-of-Charge (SOC), State-of-Health (SOH), and Remaining Useful Life (RUL). In order for the BMS to estimate these parameters, an accurate and control-oriented battery model has to work collaboratively with a robust state and parameter estimation strategy. Since battery physical parameters, such as the internal resistance and diffusion coefficient change depending on the battery state-of-life (SOL), the BMS has to be adaptive to accommodate for this change. In this paper, an extensive battery aging study has been conducted over 12-months period on 5.4 Ah, 3.7 V Lithium polymer cells. Instead of using fixed charging/discharging aging cycles at fixed C-rate, a set of real-world driving scenarios have been used to age the cells. The test has been interrupted every 5% capacity degradation by a set of reference performance tests to assess the battery degradation and track model parameters. As battery ages, the combined model parameters are optimized and tracked in an offline mode over the entire batteries lifespan. Based on the optimized model, a state and parameter estimation strategy based on the Extended Kalman Filter (EKF) and the relatively new Smooth Variable Structure Filter (SVSF) have been applied to estimate the SOC at various states of life.

Keywords: lithium-ion batteries, genetic algorithm optimization, battery aging test, parameter identification

Procedia PDF Downloads 244

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: Nafiseh Mirabdolhosseini, Jerry Zhou, Vincent Ho

Abstract:

The dramatic global rise in acid reflux has also led to oesophageal adenocarcinoma (OAC) becoming the fastest-growing cancer in developed countries. While gastroscopy with biopsy is used to diagnose OAC patients, this labour-intensive and expensive process is not suitable for population screening. This study aims to design, develop, and implement a minimally invasive system to capture optical data of the distal oesophagus for rapid screening of potential abnormalities. To develop the system and understand user requirements, a user-centric approach was employed by utilising co-design strategies. Target users’ segments were identified, and 38 patients and 14 health providers were interviewed. Next, the technical requirements were developed based on consultations with the industry. A minimally invasive optical system was designed and developed considering patient comfort. This system consists of the sensing catheter, controller unit, and analysis program. Its procedure only takes 10 minutes to perform and does not require cleaning afterward since it has a single-use catheter. A prototype system was evaluated for safety and efficacy for both laboratory and clinical performance. This prototype performed successfully when submerged in simulated gastric fluid without showing evidence of erosion after 24 hours. The system effectively recorded a video of the mid-distal oesophagus of a healthy volunteer (34-year-old male). The recorded images were used to develop an automated program to identify abnormalities in the distal oesophagus. Further data from a larger clinical study will be used to train the automated program. This system allows for quick visual assessment of the lower oesophagus in primary care settings and can serve as a screening tool for oesophageal adenocarcinoma. In addition, this system is able to be coupled with 24hr ambulatory pH monitoring to better correlate oesophageal physiological changes with reflux symptoms. It also can provide additional information on lower oesophageal sphincter functions such as opening times and bolus retention.

Keywords: endoscopy, MedTech, oesophageal adenocarcinoma, optical system, screening tool

Procedia PDF Downloads 64

Authors: Peiming Li

Abstract:

This paper presents an innovative blockchain-based approach to enhance the reliability and efficiency of federated learning systems. By integrating a decentralized oracle consensus mechanism into the federated learning framework, we address key challenges of data and model integrity. Our approach utilizes a network of redundant oracles, functioning as independent validators within an epoch-based training system in the federated learning model. In federated learning, data is decentralized, residing on various participants' devices. This scenario often leads to concerns about data integrity and model quality. Our solution employs blockchain technology to establish a transparent and tamper-proof environment, ensuring secure data sharing and aggregation. The decentralized oracles, a concept borrowed from blockchain systems, act as unbiased validators. They assess the contributions of each participant using a Hidden Markov Model (HMM), which is crucial for evaluating the consistency of participant inputs and safeguarding against model poisoning and malicious activities. Our methodology's distinct feature is its epoch-based training. An epoch here refers to a specific training phase where data is updated and assessed for quality and relevance. The redundant oracles work in concert to validate data updates during these epochs, enhancing the system's resilience to security threats and data corruption. The effectiveness of this system was tested using the Mnist dataset, a standard in machine learning for benchmarking. Results demonstrate that our blockchain-oriented federated learning approach significantly boosts system resilience, addressing the common challenges of federated environments. This paper aims to make these advanced concepts accessible, even to those with a limited background in blockchain or federated learning. We provide a foundational understanding of how blockchain technology can revolutionize data integrity in decentralized systems and explain the role of oracles in maintaining model accuracy and reliability.

Keywords: federated learning system, block chain, decentralized oracles, hidden markov model

Procedia PDF Downloads 32

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 53

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: Nurul Aliaa Idris, David A. Collings

Abstract:

Phi thickenings are specialized secondary cell wall thickenings that are found in the cortex of the roots in a wide range of plant species, including orchids. The role of phi thickenings in the root is still under debate through research have linked environmental conditions, particularly abiotic stresses such as water stress, heavy metal stress and salinity to their induction in the roots. It has also been suggested that phi thickenings may act as a barrier to regulate solute uptake, act as a physical barrier against fungal hyphal penetration due to its resemblance to the Casparian strip and play a mechanical role to support cortical cells. We have investigated phi thickening function in epiphytic orchids of the genus Miltoniopsis through induction experiment against factors such as soil compaction and water stress. The permeability of the phi thickenings in Miltoniopsis was tested through uptake experiments using the fluorescent tracer dyes Calcofluor white, Lucifer yellow and Propidium iodide then viewed with wide-field or confocal microscopy. To test whether phi thickening may prevent fungal colonization in the root cell, fungal re-infection experiment was conducted by inoculating isolated symbiotic fungus to sterile in vitro Miltoniopsis explants. As the movement of fluorescent tracers through the apoplast was not blocked by phi thickenings, and as phi thickenings developed in the roots of sterile cultures in the absence of fungus and did not prevent fungal colonization of cortical cells, the phi thickenings in Miltoniopsis do not function as a barrier. Phi thickenings were found to be absent in roots grown on agar and remained absent when plants were transplanted to moist soil. However, phi thickenings were induced when plants were transplanted to well-drained media, and by the application of water stress in all soils tested. It is likely that phi thickenings stabilize the root cortex during dehydration. Nevertheless, the varied induction responses present in different plant species suggest that the phi thickenings may play several adaptive roles, instead of just one, depending on species.

Keywords: abiotic stress, Miltoniopsis, orchid, phi thickening

Procedia PDF Downloads 122

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 120

Authors: Anna Siegler

Abstract:

Bullying among peers is not uncommon; however, adults can notice only a fragment of the cases of harassment during everyday life. The systemic approaches of bullying investigation put the whole school community in the focus of attention and propose that the solution should emerge from the culture of the school. Bystanders are essential in the prevention and intervention processes as an active agent rather than passive. For combating exclusion, stigmatization and harassment, it is important that the bystanders have to realize they have the power to take action. To prevent the escalation of violence, victims must believe that students and teachers will help them and their environment is able to provide safety. The study based on scientific narrative psychological approach, and focuses on the examination of the different perspectives of students, how peers are mentalizing with each other in case of bullying. The data collection contained responses of students (N = 138) from three schools in Hungary, and from three different area of the country (Budapest, Martfű and Barcs). The test battery include Bullying Prevalence Questionnaire, Interpersonal Reactivity Index and an instruction to get narratives about bullying, which effectiveness was tested during a pilot test. The obtained results are in line with the findings of previous bullying research: the victims are mentalizing less with their peers and experience greater personal distress when they are in identity threatening situations, thus focusing on their own difficulties rather than social signals. This isolation is an adaptive response in short-term although it seems to lead to a deficit in social skills later in life and makes it difficult for students to become socially integrated to society. In addition the results also show that students use more mental state attribution when they report verbal bullying than in case of physical abuse. Those who witness physical harassment also witness concrete answers to the problem from teachers, in contrast verbal abuse often stays without consequences. According to the results students mentalizing more in these stories because they have less normative explanation to what happened. To expanding bullying literature, this research helps to find ways to reduce school violence through community development.

Keywords: bullying, mentalization, narrative, school culture

Procedia PDF Downloads 140

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 33

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 16

Authors: S. K. Thind, Aparjot Kaur

Abstract:

Heat stress is one of the major environmental factors drastically reducing wheat production. Crop heat tolerance can be enhanced by preconditioning of plants by exogenous application of osmoprotectants. Presently, the effect of trehalose pretreatment (at 1 mM, and 1.5 nM) under heat stress of 35±2˚C (moderate) and 40±2˚ (severe) for four and eight hour was conducted in wheat (Tricticum aestivum L.) genotypes viz. HD2967, PBW 175, PBW 343, PBW 621, and PBW 590. Heat stress affects wide spectrum of physiological processes within plants that are irreversibly damaged by stress. Membrane thermal stability (MTS) and cell viability was significantly decreased under heat stress for eight hours. Pretreatment with trehalose improved MTS and cell viability under stress and this effect was more promotory with higher concentration. Thermal stability of photosynthetic apparatus differed markedly between genotypes and Hill reaction activity was recorded more in PBW621 followed by C306 as compared with others. In all genotypes photolysis of water showed decline with increase in temperature stress. Trehalose pretreatment helped in sustaining Hill reaction activity probably by stabilizing the photosynthetic apparatus against heat-induced photo inhibition. Both plant growth and development were affected by temperature in both shoot and root under heat stress. The reduction was compensated partially by trehalose (1.5 mM) application. Adaption to heat stress is associated with the metabolic adjustment which led to accumulation of soluble sugars including non-reducing and reducing for their role in adaptive mechanism. Higher acid invertase activity in shoot of tolerant genotypes appeared to be a characteristic for stress tolerance. As sucrose synthase play central role in sink strength and in studied wheat genotype was positively related to dry matter accumulation. The duration of heat stress for eight hours had more severe effect on these parameters and trehalose application at 1.5 mM ameliorated it to certain extent.

Keywords: heat stress, Triticum aestivum, trehalose, membrane thermal stability, triphenyl tetrazolium chloride, reduction test, growth, sugar metabolism

Procedia PDF Downloads 301

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: Chatrabhuti Pipop, Visessri Supattra, Charinpanitkul Tawatchai

Abstract:

Durian is one of the top agricultural products exported by Thailand. There is the massive market potential for the durian industry. While the global demand for Thai durians, especially the demand from China, is very high, Thailand's durian supply is far from satisfying strong demand. Poor agricultural practices result in low yields and poor quality of fruit. Most irrigation systems currently used by the farmers are fixed schedule or fixed rates that ignore actual weather conditions and crop water requirements. In addition, the technologies emerging are too difficult and complex and prices are too high for the farmers to adopt and afford. Many farmers leave the durian trees to grow naturally. With improper irrigation and nutrient management system, durians are vulnerable to a variety of issues, including stunted growth, not flowering, diseases, and death. Technical development or research for durian is much needed to support the wellbeing of the farmers and the economic development of the country. However, there are a limited number of studies or development projects for durian because durian is a perennial crop requiring a long time to obtain the results to report. This study, therefore, aims to address the problem of durian production by developing an autonomous and precision irrigation system. The system is designed and equipped with an industrial programmable controller, a weather station, and a digital flow meter. Daily water requirements are computed based on weather data such as rainfall and evapotranspiration for daily irrigation with variable flow rates. A prediction model is also designed as a part of the system to enhance the irrigation schedule. Before the system was installed in the field, a simulation model was built and tested in a laboratory setting to ensure its accuracy. Water consumption was measured daily before and after the experiment for further analysis. With this system, the crop water requirement is precisely estimated and optimized based on the data from the weather station. Durian will be irrigated at the right amount and at the right time, offering the opportunity for higher yield and higher income to the farmers.

Keywords: Durian, precision irrigation, precision agriculture, smart farm

Procedia PDF Downloads 90

Authors: Sakshi Chopra, Harsimarpreet Kaur, Ashima Nehra

Abstract:

Objectives: Malingering is fabricating or exaggerating the symptoms of mental or physical disorders for a variety of secondary gains or motives, which may include financial compensation; avoiding work; getting lighter criminal sentences; or simply to attract attention or sympathy. Malingering is different from somatization disorder and factitious disorder. The prevalence of malingering is unknown and difficult to determine. In an estimated study in forensic population, it can reach up to 17% cases. But the accuracy of such estimates is questionable as successful malingerers are not detected and thus, not included. Methods: The case study of a 58 years old, right handed, graduate, pre-morbidly working in a national company with reported history of stroke leading to head injury; cerebral infarction/facial palsy and dementia. He was referred for disability certification so that his job position can be transferred to his son as he could not work anymore. A series of Neuropsychological tests were administered. Results: With a mental age of < 2.5 years; social adaptive functioning was overall < 20 showing profound Mental Retardation, less than 1 year social age in abilities of self-help, eating, dressing, locomotion, occupation, communication, self-direction, and socialization; severely impaired verbal and performance ability, 96% impairment in Activities of Daily Living, with an indication of very severe depression. With inconsistent and fluctuating medical findings and problem descriptions to different health professionals forming the board for his disability, it was concluded that this patient was malingering. Conclusions: Even though it can be easily defined, malingering can be very challenging to diagnosis. Cases of malingering impose a substantial economic burden on the health care system and false attribution of malingering imposes a substantial burden of suffering on a significant proportion of the patient population. Timely, tactful diagnosis and management can help ease this patient burden on the healthcare system. Malingering can be detected by only trained mental health professionals in the clinical setting.

Keywords: disability, India, malingering, neuropsychological assessment

Procedia PDF Downloads 396

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 114

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 401

Authors: Il Ho Park, Joong Seob Lee, Sung Hun Kang, Jae-Min Shin, Il Seok Park, Seok Min Hong, Seok Jin Hong

Abstract:

Introduction: The human microbiota is the aggregate of microorganisms, and the bacterial microbiome of the human digestive tract contributes to both health and disease. In health, bacteria are key components in the development of mucosal barrier function and in innate and adaptive immune responses, and they also work to suppress the establishment of pathogens. In human upper airway, the sinonasal microbiota might play an important role in chronic rhinosinusitis (CRS). The purpose of this study is to investigate the human upper airway microbiome in CRS patients and to compare the sinonasal microbiome of adults with children. Materials and methods: A total of 19 samples from 19 patients (Group1; 9 CRS in children, aged 5 to 14 years versus Group 2; 10 CRS in adults aged 21 to 59 years) were examined. Swabs were collected from the middle meatus and/or anterior ethmoid region under general anesthesia during endoscopic sinus surgery or tonsillectomy. After DNA extraction from swab samples, we analysed bacterial microbiome consortia using 16s rRNA gene sequencing approach (the Illumina MiSeq platform). Results: In this study, relatively abundance of the six bacterial phyla and tremendous genus and species found in substantial amounts in the individual sinus swab samples, include Corynebacterium, Hemophilus, Moraxella, and Streptococcus species. Anaerobes like Fusobacterium and Bacteroides were abundantly present in the children group, Bacteroides and Propionibacterium were present in adults group. In genus, Haemophilus was the most common CRS microbiome in children and Corynebacterium was the most common CRS microbiome in adults. Conclusions: Our results show the diversity of human upper airway microbiome, and the findings will suggest that CRS is a polymicrobial infection. The Corynebacterium and Hemophilus may live as commensals on mucosal surfaces of sinus in the upper respiratory tract. The further study will be needed for analysis of microbiome-human interactions in upper airway and CRS.

Keywords: microbiome, upper airway, chronic rhinosinusitis, adult and children

Procedia PDF Downloads 98

Authors: Dylan Santos De Pinho, Arnaud Gay De Combes, Matthieu Steuhlet, Claude Jeannerat, Nabil Ouerhani

Abstract:

The Industry 4.0 initiative has been launched to address huge challenges related to ever-smaller batch sizes. The end-user need for highly customized products requires highly adaptive production systems in order to keep the same efficiency of shop floors. Most of the classical Software solutions that operate the manufacturing processes in a shop floor are based on rigid Manufacturing Execution Systems (MES), which are not capable to adapt the production order on the fly depending on changing demands and or conditions. In this paper, we present a highly modular and flexible solution to orchestrate a set of production systems composed of a micro-milling machine-tool, a polishing station, a cleaning station, a part inspection station, and a rough material store. The different stations are installed according to a novel matrix configuration of a 3x3 vertical shelf. The different cells of the shelf are connected through horizontal and vertical rails on which a set of shuttles circulate to transport the machined parts from a station to another. Our software solution for orchestrating the tasks of each station is based on a Multi-Agent System. Each station and each shuttle is operated by an autonomous agent. All agents communicate with a central agent that holds all the information about the manufacturing order. The core innovation of this paper lies in the path planning of the different shuttles with two major objectives: 1) reduce the waiting time of stations and thus reduce the cycle time of the entire part, and 2) reduce the disturbances like vibration generated by the shuttles, which highly impacts the manufacturing process and thus the quality of the final part. Simulation results show that the cycle time of the parts is reduced by up to 50% compared with MES operated linear production lines while the disturbance is systematically avoided for the critical stations like the milling machine-tool.

Keywords: multi-agent systems, micro-manufacturing, flexible manufacturing, transfer systems

Procedia PDF Downloads 112

Authors: Jaydip M. Desai, Antonio Valdevit, Arthur Ritter

Abstract:

Robotic surgery is used to enhance minimally invasive surgical procedure. It provides greater degree of freedom for surgical tools but lacks of haptic feedback system to provide sense of touch to the surgeon. Surgical robots work on master-slave operation, where user is a master and robotic arms are the slaves. Current, surgical robots provide precise control of the surgical tools, but heavily rely on visual feedback, which sometimes cause damage to the inner organs. The goal of this research was to design and develop a real-time simulink based robotic system to study force feedback mechanism during instrument-object interaction. Setup includes three Velmex XSlide assembly (XYZ Stage) for three dimensional movement, an end effector assembly for forceps, electronic circuit for four strain gages, two Novint Falcon 3D gaming controllers, microcontroller board with linear actuators, MATLAB and Simulink toolboxes. Strain gages were calibrated using Imada Digital Force Gauge device and tested with a hard-core wire to measure instrument-object interaction in the range of 0-35N. Designed simulink model successfully acquires 3D coordinates from two Novint Falcon controllers and transfer coordinates to the XYZ stage and forceps. Simulink model also reads strain gages signal through 10-bit analog to digital converter resolution of a microcontroller assembly in real time, converts voltage into force and feedback the output signals to the Novint Falcon controller for force feedback mechanism. Experimental setup allows user to change forward kinematics algorithms to achieve the best-desired movement of the XYZ stage and forceps. This project combines haptic technology with surgical robot to provide sense of touch to the user controlling forceps through machine-computer interface.

Keywords: surgical robot, haptic feedback, MATLAB, strain gage, simulink

Procedia PDF Downloads 512

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