Search results for: neural%20networks

Authors: Martin Pellon Consunji

Abstract:

Due to the rise in popularity of Bitcoin and other crypto assets as a store of wealth and speculative investment, there is an ever-growing demand for automated trading tools, such as bots, in order to gain an advantage over the market. Traditionally, trading in the stock market was done by professionals with years of training who understood patterns and exploited market opportunities in order to gain a profit. However, nowadays a larger portion of market participants are at minimum aided by market-data processing bots, which can generally generate more stable signals than the average human trader. The rise in trading bot usage can be accredited to the inherent advantages that bots have over humans in terms of processing large amounts of data, lack of emotions of fear or greed, and predicting market prices using past data and artificial intelligence, hence a growing number of approaches have been brought forward to tackle this task. However, the general limitation of these approaches can still be broken down to the fact that limited historical data doesn’t always determine the future, and that a lot of market participants are still human emotion-driven traders. Moreover, developing markets such as those of the cryptocurrency space have even less historical data to interpret than most other well-established markets. Due to this, some human traders have gone back to the tried-and-tested traditional technical analysis tools for exploiting market patterns and simplifying the broader spectrum of data that is involved in making market predictions. This paper proposes a method which uses neuro evolution techniques on both sentimental data and, the more traditionally human-consumed, technical analysis data in order to gain a more accurate forecast of future market behavior and account for the way both automated bots and human traders affect the market prices of Bitcoin and other cryptocurrencies. This study’s approach uses evolutionary algorithms to automatically develop increasingly improved populations of bots which, by using the latest inflows of market analysis and sentimental data, evolve to efficiently predict future market price movements. The effectiveness of the approach is validated by testing the system in a simulated historical trading scenario, a real Bitcoin market live trading scenario, and testing its robustness in other cryptocurrency and stock market scenarios. Experimental results during a 30-day period show that this method outperformed the buy and hold strategy by over 260% in terms of net profits, even when taking into consideration standard trading fees.

Keywords: neuro-evolution, Bitcoin, trading bots, artificial neural networks, technical analysis, evolutionary algorithms

Procedia PDF Downloads 122

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

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

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

Procedia PDF Downloads 158

Authors: A. Degale Desta, Tamirat Kebamo

Abstract:

Background: Recent advances in computer vision and pattern recognition have significantly improved activity recognition through video analysis, particularly with the application of Deep Convolutional Neural Networks (CNNs). One-stage detectors now enable efficient video-based recognition by simultaneously predicting object categories and locations. Such advancements are highly relevant in educational settings where CCTV surveillance could automatically monitor academic activities, enhancing security and classroom management. However, current datasets and recognition systems lack the specific focus on campus environments necessary for practical application in these settings.Objective: This study aims to address this gap by developing a dataset and testing an automated activity recognition system specifically tailored for educational campuses. The EthioCAD dataset was created to capture various classroom activities and teacher-student interactions, facilitating reliable recognition of academic activities using deep learning models. Method: EthioCAD, a novel video-based dataset, was created with a design science research approach to encompass teacher-student interactions across three domains and 18 distinct classroom activities. Using the Roboflow AI framework, the data was processed, with 4.224 KB of frames and 33.485 MB of images managed for frame extraction, labeling, and organization. The Ultralytics YOLOv8 model was then implemented within Google Colab to evaluate the dataset’s effectiveness, achieving high mean Average Precision (mAP) scores. Results: The YOLOv8 model demonstrated robust activity recognition within campus-like settings, achieving an mAP50 of 90.2% and an mAP50-95 of 78.6%. These results highlight the potential of EthioCAD, combined with YOLOv8, to provide reliable detection and classification of classroom activities, supporting automated surveillance needs on educational campuses. Discussion: The high performance of YOLOv8 on the EthioCAD dataset suggests that automated activity recognition for surveillance is feasible within educational environments. This system addresses current limitations in campus-specific data and tools, offering a tailored solution for academic monitoring that could enhance the effectiveness of CCTV systems in these settings. Conclusion: The EthioCAD dataset, alongside the YOLOv8 model, provides a promising framework for automated campus activity recognition. This approach lays the groundwork for future advancements in CCTV-based educational surveillance systems, enabling more refined and reliable monitoring of classroom activities.

Keywords: deep CNN, EthioCAD, deep learning, YOLOv8, activity recognition

Procedia PDF Downloads 7

Authors: Sevde Altuntas, Fatih Buyukserin

Abstract:

Alzheimer’s disease is responsible for irreversible neural damage of brain parts. One of the disease markers is Amyloid-β 1-42 protein that accumulates in the brain in the form plaques. The basic problem for detection of the protein is the low amount of protein that cannot be detected properly in body liquids such as blood, saliva or urine. To solve this problem, tests like ELISA or PCR are proposed which are expensive, require specialized personnel and can contain complex protocols. Therefore, Surface-enhanced Raman Spectroscopy (SERS) a good candidate for detection of Amyloid-β 1-42 protein. Because the spectroscopic technique can potentially allow even single molecule detection from liquid and solid surfaces. Besides SERS signal can be improved by using nanopattern surface and also is specific to molecules. In this context, our study proposes to fabricate diagnostic test models that utilize Au-coated nanopatterned polycarbonate (PC) surfaces modified with Thioflavin - T to detect low concentrations of Amyloid-β 1-42 protein in water and artificial saliva medium by the enhancement of protein SERS signal. The nanopatterned PC surface that was used to enhance SERS signal was fabricated by using Anodic Alumina Membranes (AAM) as a template. It is possible to produce AAMs with different column structures and varying thicknesses depending on voltage and anodization time. After fabrication process, the pore diameter of AAMs can be arranged with dilute acid solution treatment. In this study, two different columns structures were prepared. After a surface modification to decrease their surface energy, AAMs were treated with PC solution. Following the solvent evaporation, nanopatterned PC films with tunable pillared structures were peeled off from the membrane surface. The PC film was then modified with Au and Thioflavin-T for the detection of Amyloid-β 1-42 protein. The protein detection studies were conducted first in water via this biosensor platform. Same measurements were conducted in artificial saliva to detect the presence of Amyloid Amyloid-β 1-42 protein. SEM, SERS and contact angle measurements were carried out for the characterization of different surfaces and further demonstration of the protein attachment. SERS enhancement factor calculations were also completed via experimental results. As a result, our research group fabricated diagnostic test models that utilize Au-coated nanopatterned polycarbonate (PC) surfaces modified with Thioflavin-T to detect low concentrations of Alzheimer’s Amiloid – β protein in water and artificial saliva medium. This work was supported by The Scientific and Technological Research Council of Turkey (TUBITAK) Grant No: 214Z167.

Keywords: alzheimer, anodic aluminum oxide, nanotopography, surface enhanced Raman spectroscopy

Procedia PDF Downloads 290

Authors: Shayla He

Abstract:

Background and Purpose: According to Chamie (2017), it’s estimated that no less than 150 million people, or about 2 percent of the world’s population, are homeless. The homeless population in the United States has grown rapidly in the past four decades. In New York City, the sheltered homeless population has increased from 12,830 in 1983 to 62,679 in 2020. Knowing the trend on the homeless population is crucial at helping the states and the cities make affordable housing plans, and other community service plans ahead of time to better prepare for the situation. This study utilized the data from New York City, examined the key factors associated with the homelessness, and developed systematic modeling to predict homeless populations of the future. Using the best model developed, named HP-RNN, an analysis on the homeless population change during the months of 2020 and 2021, which were impacted by the COVID-19 pandemic, was conducted. Moreover, HP-RNN was tested on the data from Seattle. Methods: The methodology involves four phases in developing robust prediction methods. Phase 1 gathered and analyzed raw data of homeless population and demographic conditions from five urban centers. Phase 2 identified the key factors that contribute to the rate of homelessness. In Phase 3, three models were built using Linear Regression, Random Forest, and Recurrent Neural Network (RNN), respectively, to predict the future trend of society's homeless population. Each model was trained and tuned based on the dataset from New York City for its accuracy measured by Mean Squared Error (MSE). In Phase 4, the final phase, the best model from Phase 3 was evaluated using the data from Seattle that was not part of the model training and tuning process in Phase 3. Results: Compared to the Linear Regression based model used by HUD et al (2019), HP-RNN significantly improved the prediction metrics of Coefficient of Determination (R2) from -11.73 to 0.88 and MSE by 99%. HP-RNN was then validated on the data from Seattle, WA, which showed a peak %error of 14.5% between the actual and the predicted count. Finally, the modeling results were collected to predict the trend during the COVID-19 pandemic. It shows a good correlation between the actual and the predicted homeless population, with the peak %error less than 8.6%. Conclusions and Implications: This work is the first work to apply RNN to model the time series of the homeless related data. The Model shows a close correlation between the actual and the predicted homeless population. There are two major implications of this result. First, the model can be used to predict the homeless population for the next several years, and the prediction can help the states and the cities plan ahead on affordable housing allocation and other community service to better prepare for the future. Moreover, this prediction can serve as a reference to policy makers and legislators as they seek to make changes that may impact the factors closely associated with the future homeless population trend.

Keywords: homeless, prediction, model, RNN

Procedia PDF Downloads 119

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, student engagement

Procedia PDF Downloads 93

Authors: Marcos Silva Tavares, Jamile Raquel Regazzo, Edson José de Souza Sardinha, Murilo Mesquita Baesso

Abstract:

Common beans are a widely cultivated and consumed legume globally, serving as a staple food for humans, especially in developing countries, due to their nutritional characteristics. Nitrogen (N) is the most limiting nutrient for productivity, and foliar analysis is crucial to ensure balanced nitrogen fertilization. Excessive N applications can cause, either isolated or cumulatively, soil and water contamination, plant toxicity, and increase their susceptibility to diseases and pests. However, the quantification of N using conventional methods is time-consuming and costly, demanding new technologies to optimize the adequate supply of N to plants. Thus, it becomes necessary to establish constant monitoring of the foliar content of this macronutrient in plants, mainly at the V4 stage, aiming at precision management of nitrogen fertilization. In this work, the objective was to evaluate the performance of a deep learning model, Resnet-50, in the classification of foliar nitrogen in common beans using RGB images. The BRS Estilo cultivar was sown in a greenhouse in a completely randomized design with four nitrogen doses (T1 = 0 kg N ha-1, T2 = 25 kg N ha-1, T3 = 75 kg N ha-1, and T4 = 100 kg N ha-1) and 12 replications. Pots with 5L capacity were used with a substrate composed of 43% soil (Neossolo Quartzarênico), 28.5% crushed sugarcane bagasse, and 28.5% cured bovine manure. The water supply of the plants was done with 5mm of water per day. The application of urea (45% N) and the acquisition of images occurred 14 and 32 days after sowing, respectively. A code developed in Matlab© R2022b was used to cut the original images into smaller blocks, originating an image bank composed of 4 folders representing the four classes and labeled as T1, T2, T3, and T4, each containing 500 images of 224x224 pixels obtained from plants cultivated under different N doses. The Matlab© R2022b software was used for the implementation and performance analysis of the model. The evaluation of the efficiency was done by a set of metrics, including accuracy (AC), F1-score (F1), specificity (SP), area under the curve (AUC), and precision (P). The ResNet-50 showed high performance in the classification of foliar N levels in common beans, with AC values of 85.6%. The F1 for classes T1, T2, T3, and T4 was 76, 72, 74, and 77%, respectively. This study revealed that the use of RGB images combined with deep learning can be a promising alternative to slow laboratory analyses, capable of optimizing the estimation of foliar N. This can allow rapid intervention by the producer to achieve higher productivity and less fertilizer waste. Future approaches are encouraged to develop mobile devices capable of handling images using deep learning for the classification of the nutritional status of plants in situ.

Keywords: convolutional neural network, residual network 50, nutritional status, artificial intelligence

Procedia PDF Downloads 16

Authors: Fabiana Franceschi, Martha Cobo, Manuel Figueredo

Abstract:

Bogotá, the capital of Colombia, is its largest city and one of the most polluted in Latin America due to the fast economic growth over the last ten years. Bogotá has been affected by high pollution events which led to the high concentration of PM10 and NO2, exceeding the local 24-hour legal limits (100 and 150 g/m3 each). The most important pollutants in the city are PM10 and PM2.5 (which are associated with respiratory and cardiovascular problems) and it is known that their concentrations in the atmosphere depend on the local meteorological factors. Therefore, it is necessary to establish a relationship between the meteorological variables and the concentrations of the atmospheric pollutants such as PM10, PM2.5, CO, SO2, NO2 and O3. This study aims to determine the interrelations between meteorological variables and air pollutants in Bogotá, using data mining techniques. Data from 13 monitoring stations were collected from the Bogotá Air Quality Monitoring Network within the period 2010-2015. The Principal Component Analysis (PCA) algorithm was applied to obtain primary relations between all the parameters, and afterwards, the K-means clustering technique was implemented to corroborate those relations found previously and to find patterns in the data. PCA was also used on a per shift basis (morning, afternoon, night and early morning) to validate possible variation of the previous trends and a per year basis to verify that the identified trends have remained throughout the study time. Results demonstrated that wind speed, wind direction, temperature, and NO2 are the most influencing factors on PM10 concentrations. Furthermore, it was confirmed that high humidity episodes increased PM2,5 levels. It was also found that there are direct proportional relationships between O3 levels and wind speed and radiation, while there is an inverse relationship between O3 levels and humidity. Concentrations of SO2 increases with the presence of PM10 and decreases with the wind speed and wind direction. They proved as well that there is a decreasing trend of pollutant concentrations over the last five years. Also, in rainy periods (March-June and September-December) some trends regarding precipitations were stronger. Results obtained with K-means demonstrated that it was possible to find patterns on the data, and they also showed similar conditions and data distribution among Carvajal, Tunal and Puente Aranda stations, and also between Parque Simon Bolivar and las Ferias. It was verified that the aforementioned trends prevailed during the study period by applying the same technique per year. It was concluded that PCA algorithm is useful to establish preliminary relationships among variables, and K-means clustering to find patterns in the data and understanding its distribution. The discovery of patterns in the data allows using these clusters as an input to an Artificial Neural Network prediction model.

Keywords: air pollution, air quality modelling, data mining, particulate matter

Procedia PDF Downloads 258

Authors: Anirudh Lahiri

Abstract:

Neuromorphic computing, inspired by the intricate operations of biological neural networks, offers a revolutionary approach to overcoming the limitations of traditional computing architectures. This research proposes the integration of spintronics with neuromorphic systems, aiming to enhance computational performance, scalability, and energy efficiency. Traditional computing systems, based on the Von Neumann architecture, struggle with scalability and efficiency due to the segregation of memory and processing functions. In contrast, the human brain exemplifies high efficiency and adaptability, processing vast amounts of information with minimal energy consumption. This project explores the use of spintronics, which utilizes the electron's spin rather than its charge, to create more energy-efficient computing systems. Spintronic devices, such as magnetic tunnel junctions (MTJs) manipulated through spin-transfer torque (STT) and spin-orbit torque (SOT), offer a promising pathway to reducing power consumption and enhancing the speed of data processing. The integration of these devices within a neuromorphic framework aims to replicate the efficiency and adaptability of biological systems. The research is structured into three phases: an exhaustive literature review to build a theoretical foundation, laboratory experiments to test and optimize the theoretical models, and iterative refinements based on experimental results to finalize the system. The initial phase focuses on understanding the current state of neuromorphic and spintronic technologies. The second phase involves practical experimentation with spintronic devices and the development of neuromorphic systems that mimic synaptic plasticity and other biological processes. The final phase focuses on refining the systems based on feedback from the testing phase and preparing the findings for publication. The expected contributions of this research are twofold. Firstly, it aims to significantly reduce the energy consumption of computational systems while maintaining or increasing processing speed, addressing a critical need in the field of computing. Secondly, it seeks to enhance the learning capabilities of neuromorphic systems, allowing them to adapt more dynamically to changing environmental inputs, thus better mimicking the human brain's functionality. The integration of spintronics with neuromorphic computing could revolutionize how computational systems are designed, making them more efficient, faster, and more adaptable. This research aligns with the ongoing pursuit of energy-efficient and scalable computing solutions, marking a significant step forward in the field of computational technology.

Keywords: material science, biological engineering, mechanical engineering, neuromorphic computing, spintronics, energy efficiency, computational scalability, synaptic plasticity.

Procedia PDF Downloads 41

Authors: Ahmad S. Darwish, Tarek Lemaoui, Hanifa Taher, Inas M. AlNashef, Fawzi Banat

Abstract:

This research reports a systematic top-down approach for designing neoteric hydrophobic solvents –particularly, deep eutectic solvents (DES) and ionic liquids (IL)– as furfural extractants from aqueous media for the application of sustainable biomass conversion. The first stage of the framework entailed screening 32 neoteric solvents to determine their efficacy against toluene as the application’s conventional benchmark for comparison. The selection criteria for the best solvents encompassed not only their efficiency in extracting furfural but also low viscosity and minimal toxicity levels. Additionally, for the DESs, their natural origins, availability, and biodegradability were also taken into account. From the screening pool, two neoteric solvents were selected: thymol:decanoic acid 1:1 (Thy:DecA) and trihexyltetradecyl phosphonium bis(trifluoromethylsulfonyl) imide [P₁₄,₆,₆,₆][NTf₂]. These solvents outperformed the toluene benchmark, achieving efficiencies of 94.1% and 97.1% respectively, compared to toluene’s 81.2%, while also possessing the desired properties. These solvents were then characterized thoroughly in terms of their physical properties, thermal properties, critical properties, and cross-contamination solubilities. The selected neoteric solvents were then extensively tested under various operating conditions, and an exceptional stable performance was exhibited, maintaining high efficiency across a broad range of temperatures (15–100 °C), pH levels (1–13), and furfural concentrations (0.1–2.0 wt%) with a remarkable equilibrium time of only 2 minutes, and most notably, demonstrated high efficiencies even at low solvent-to-feed ratios. The durability of the neoteric solvents was also validated to be stable over multiple extraction-regeneration cycles, with limited leachability to the aqueous phase (≈0.1%). Moreover, the extraction performance of the solvents was then modeled through machine learning, specifically multiple non-linear regression (MNLR) and artificial neural networks (ANN). The models demonstrated high accuracy, indicated by their low absolute average relative deviations with values of 2.74% and 2.28% for Thy:DecA and [P₁₄,₆,₆,₆][NTf₂], respectively, using MNLR, and 0.10% for Thy:DecA and 0.41% for [P₁₄,₆,₆,₆][NTf₂] using ANN, highlighting the significantly enhanced predictive accuracy of the ANN. The neoteric solvents presented herein offer noteworthy advantages over traditional organic solvents, including their high efficiency in both extraction and regeneration processes, their stability and minimal leachability, making them particularly suitable for applications involving aqueous media. Moreover, these solvents are more environmentally friendly, incorporating renewable and sustainable components like thymol and decanoic acid. This exceptional efficacy of the newly developed neoteric solvents signifies a significant advancement, providing a green and sustainable alternative for furfural production from biowaste.

Keywords: sustainable biomass conversion, furfural extraction, ionic liquids, deep eutectic solvents

Procedia PDF Downloads 68

Authors: Skyler Kim

Abstract:

An early diagnosis of leukemia has always been a challenge to doctors and hematologists. On a worldwide basis, it was reported that there were approximately 350,000 new cases in 2012, and diagnosing leukemia was time-consuming and inefficient because of an endemic shortage of flow cytometry equipment in current clinical practice. As the number of medical diagnosis tools increased and a large volume of high-quality data was produced, there was an urgent need for more advanced data analysis methods. One of these methods was the AI approach. This approach has become a major trend in recent years, and several research groups have been working on developing these diagnostic models. However, designing and implementing a leukemia diagnostic system in real clinical environments based on a deep learning approach with larger sets remains complex. Leukemia is a major hematological malignancy that results in mortality and morbidity throughout different ages. We decided to select acute lymphocytic leukemia to develop our diagnostic system since acute lymphocytic leukemia is the most common type of leukemia, accounting for 74% of all children diagnosed with leukemia. The results from this development work can be applied to all other types of leukemia. To develop our model, the Kaggle dataset was used, which consists of 15135 total images, 8491 of these are images of abnormal cells, and 5398 images are normal. In this paper, we design and implement a leukemia diagnostic system in a real clinical environment based on deep learning approaches with larger sets. The proposed diagnostic system has the function of detecting and classifying leukemia. Different from other AI approaches, we explore hybrid architectures to improve the current performance. First, we developed two independent convolutional neural network models: VGG19 and ResNet50. Then, using both VGG19 and ResNet50, we developed a hybrid deep learning architecture employing transfer learning techniques to extract features from each input image. In our approach, fusing the features from specific abstraction layers can be deemed as auxiliary features and lead to further improvement of the classification accuracy. In this approach, features extracted from the lower levels are combined into higher dimension feature maps to help improve the discriminative capability of intermediate features and also overcome the problem of network gradient vanishing or exploding. By comparing VGG19 and ResNet50 and the proposed hybrid model, we concluded that the hybrid model had a significant advantage in accuracy. The detailed results of each model’s performance and their pros and cons will be presented in the conference.

Keywords: acute lymphoblastic leukemia, hybrid model, leukemia diagnostic system, machine learning

Procedia PDF Downloads 186

Authors: Atbin Mahabbati, Jason Beringer, Matthias Leopold

Abstract:

To address the global challenges of climate and environmental changes, there is a need for quantifying and reducing uncertainties in environmental data, including observations of carbon, water, and energy. Global eddy covariance flux tower networks (FLUXNET), and their regional counterparts (i.e., OzFlux, AmeriFlux, China Flux, etc.) were established in the late 1990s and early 2000s to address the demand. Despite the capability of eddy covariance in validating process modelling analyses, field surveys and remote sensing assessments, there are some serious concerns regarding the challenges associated with the technique, e.g. data gaps and uncertainties. To address these concerns, this research has developed an ensemble model to fill the data gaps of CO₂ flux to avoid the limitations of using a single algorithm, and therefore, provide less error and decline the uncertainties associated with the gap-filling process. In this study, the data of five towers in the OzFlux Network (Alice Springs Mulga, Calperum, Gingin, Howard Springs and Tumbarumba) during 2013 were used to develop an ensemble machine learning model, using five feedforward neural networks (FFNN) with different structures combined with an eXtreme Gradient Boosting (XGB) algorithm. The former methods, FFNN, provided the primary estimations in the first layer, while the later, XGB, used the outputs of the first layer as its input to provide the final estimations of CO₂ flux. The introduced model showed slight superiority over each single FFNN and the XGB, while each of these two methods was used individually, overall RMSE: 2.64, 2.91, and 3.54 g C m⁻² yr⁻¹ respectively (3.54 provided by the best FFNN). The most significant improvement happened to the estimation of the extreme diurnal values (during midday and sunrise), as well as nocturnal estimations, which is generally considered as one of the most challenging parts of CO₂ flux gap-filling. The towers, as well as seasonality, showed different levels of sensitivity to improvements provided by the ensemble model. For instance, Tumbarumba showed more sensitivity compared to Calperum, where the differences between the Ensemble model on the one hand and the FFNNs and XGB, on the other hand, were the least of all 5 sites. Besides, the performance difference between the ensemble model and its components individually were more significant during the warm season (Jan, Feb, Mar, Oct, Nov, and Dec) compared to the cold season (Apr, May, Jun, Jul, Aug, and Sep) due to the higher amount of photosynthesis of plants, which led to a larger range of CO₂ exchange. In conclusion, the introduced ensemble model slightly improved the accuracy of CO₂ flux gap-filling and robustness of the model. Therefore, using ensemble machine learning models is potentially capable of improving data estimation and regression outcome when it seems to be no more room for improvement while using a single algorithm.

Keywords: carbon flux, Eddy covariance, extreme gradient boosting, gap-filling comparison, hybrid model, OzFlux network

Procedia PDF Downloads 138

Authors: Mia Bahar, Özlem Bozkurt

Abstract:

Obsessive-compulsive disorder (OCD) is a typical, persistent, and long-lasting mental health condition in which a person experiences uncontrollable, recurrent thoughts (or "obsessions") and/or activities (or "compulsions") that they feel compelled to engage in repeatedly. Obsessive-compulsive disorder is both underdiagnosed and undertreated. It frequently manifests in a variety of medical settings and is persistent, expensive, and burdensome. Obsessive-compulsive neurosis was long believed to be a condition that offered valuable insight into the inner workings of the unconscious mind. Obsessive-compulsive disorder is now recognized as a prime example of a neuropsychiatric condition susceptible to particular pharmacotherapeutic and psychotherapy therapies and mediated by pathology in particular neural circuits. An obsessive-compulsive disorder which is called OCD, usually has two components, one cognitive and the other behavioral, although either can occur alone. Obsessions are often repetitive and intrusive thoughts that invade consciousness. These obsessions are incredibly hard to control or dismiss. People who have OCD often engage in rituals to reduce anxiety associated with intrusive thoughts. Once the ritual is formed, the person may feel extreme relief and be free from anxiety until the thoughts of contamination intrude once again. These thoughts are strengthened through a manifestation of negative reinforcement because they allow the person to avoid anxiety and obscurity. These thoughts are described as autogenous, meaning they most likely come from nowhere. These unwelcome thoughts are related to actions which we can describe as Thought Action Fusion. The thought becomes equated with an action, such as if they refuse to perform the ritual, something bad might happen, and so people perform the ritual to escape the intrusive thought. In almost all cases of OCD, the person's life gets extremely disturbed by compulsions and obsessions. Studies show OCD is an estimated 1.1% prevalence, making it a challenging issue with high co-morbidities with other issues like depressive episodes, panic disorders, and specific phobias. The first to reveal brain anomalies in OCD were numerous CT investigations, although the results were inconsistent. A few studies have focused on the orbitofrontal cortex (OFC), anterior cingulate gyrus (AC), and thalamus, structures also implicated in the pathophysiology of OCD by functional neuroimaging studies, but few have found consistent results. However, some studies have found abnormalities in the basal ganglion. There have also been some discussions that OCD might be genetic. OCD has been linked to families in studies of family aggregation, and findings from twin studies show that this relationship is somewhat influenced by genetic variables. Some Research has shown that OCD is a heritable, polygenic condition that can result from de novo harmful mutations as well as common and unusual variants. Numerous studies have also presented solid evidence in favor of a significant additive genetic component to OCD risk, with distinct OCD symptom dimensions showing both common and individual genetic risks.

Keywords: compulsions, obsessions, neuropsychiatric, genetic

Procedia PDF Downloads 63

Authors: Supria Sarkar, Vasit Sagan, Sourav Bhadra, Meghnath Pokharel, Felix B.Fritschi

Abstract:

Soybean and their derivatives are very important agricultural commodities around the world because of their wide applicability in human food, animal feed, biofuel, and industries. However, the significance of soybean production depends on the quality of the soybean seeds rather than the yield alone. Seed composition is widely dependent on plant physiological properties, aerobic and anaerobic environmental conditions, nutrient content, and plant phenological characteristics, which can be captured by high temporal resolution remote sensing datasets. Planet scope (PS) satellite images have high potential in sequential information of crop growth due to their frequent revisit throughout the world. In this study, we estimate soybean seed composition while the plants are in the field by utilizing PlanetScope (PS) satellite images and different machine learning algorithms. Several experimental fields were established with varying genotypes and different seed compositions were measured from the samples as ground truth data. The PS images were processed to extract 462 hand-crafted vegetative and textural features. Four machine learning algorithms, i.e., partial least squares (PLSR), random forest (RFR), gradient boosting machine (GBM), support vector machine (SVM), and two recurrent neural network architectures, i.e., long short-term memory (LSTM) and gated recurrent unit (GRU) were used in this study to predict oil, protein, sucrose, ash, starch, and fiber of soybean seed samples. The GRU and LSTM architectures had two separate branches, one for vegetative features and the other for textures features, which were later concatenated together to predict seed composition. The results show that sucrose, ash, protein, and oil yielded comparable prediction results. Machine learning algorithms that best predicted the six seed composition traits differed. GRU worked well for oil (R-Squared: of 0.53) and protein (R-Squared: 0.36), whereas SVR and PLSR showed the best result for sucrose (R-Squared: 0.74) and ash (R-Squared: 0.60), respectively. Although, the RFR and GBM provided comparable performance, the models tended to extremely overfit. Among the features, vegetative features were found as the most important variables compared to texture features. It is suggested to utilize many vegetation indices for machine learning training and select the best ones by using feature selection methods. Overall, the study reveals the feasibility and efficiency of PS images and machine learning for plot-level seed composition estimation. However, special care should be given while designing the plot size in the experiments to avoid mixed pixel issues.

Keywords: agriculture, computer vision, data science, geospatial technology

Procedia PDF Downloads 136

Authors: Rasha Waheeb, Bjorn Andersen, Rafa Shakir

Abstract:

Purpose The purpose of this study is to avoid delays that occur in emergency reconstruction projects especially in post disaster circumstances whether if they were natural or manmade due to their particular national and humanitarian importance. We presented a theoretical and practical concepts for projects management in the field of construction industry that deal with a range of global and local trails. This study aimed to identify the factors of effective delay in construction projects in Iraq that affect the time and the specific quality cost, and find the best solutions to address delays and solve the problem by setting parameters to restore balance in this study. 30 projects were selected in different areas of construction were selected as a sample for this study. Design/methodology/approach This study discusses the reconstruction strategies and delay in time and cost caused by different delay factors in some selected projects in Iraq (Baghdad as a case study).A case study approach was adopted, with thirty construction projects selected from the Baghdad region, of different types and sizes. Project participants from the case projects provided data about the projects through a data collection instrument distributed through a survey. Mixed approach and methods were applied in this study. Mathematical data analysis was used to construct models to predict delay in time and cost of projects before they started. The artificial neural networks analysis was selected as a mathematical approach. These models were mainly to help decision makers in construction project to find solutions to these delays before they cause any inefficiency in the project being implemented and to strike the obstacles thoroughly to develop this industry in Iraq. This approach was practiced using the data collected through survey and questionnaire data collection as information form. Findings The most important delay factors identified leading to schedule overruns were contractor failure, redesigning of designs/plans and change orders, security issues, selection of low-price bids, weather factors, and owner failures. Some of these are quite in line with findings from similar studies in other countries/regions, but some are unique to the Iraqi project sample, such as security issues and low-price bid selection. Originality/value we selected ANN’s analysis first because ANN’s was rarely used in project management , and never been used in Iraq to finding solutions for problems in construction industry. Also, this methodology can be used in complicated problems when there is no interpretation or solution for a problem. In some cases statistical analysis was conducted and in some cases the problem is not following a linear equation or there was a weak correlation, thus we suggested using the ANN’s because it is used for nonlinear problems to find the relationship between input and output data and that was really supportive.

Keywords: construction projects, delay factors, emergency reconstruction, innovation ANN, post disasters, project management

Procedia PDF Downloads 165

Authors: André Augusto Ceballos Melo

Abstract:

Design to facilitate the recognition of congruent prosthetic movements, context-to-motion translations guided by image, verbal prompt, users nonverbal communication such as facial expressions, gestures, paralinguistics, scene context, and object recognition contributes to this process though it can also be applied to other tasks, such as walking, Prosthetic limbs as assistive technology through gestures, sound codes, signs, facial, body expressions, and scene context The context-to-motion model is a machine learning approach that is designed to improve the control and dexterity of prosthetic limbs. It works by using sensory input from the prosthetic limb to learn about the dynamics of the environment and then using this information to generate smooth, stable movements. This can help to improve the performance of the prosthetic limb and make it easier for the user to perform a wide range of tasks. There are several key benefits to using the context-to-motion model for prosthetic limb control. First, it can help to improve the naturalness and smoothness of prosthetic limb movements, which can make them more comfortable and easier to use for the user. Second, it can help to improve the accuracy and precision of prosthetic limb movements, which can be particularly useful for tasks that require fine motor control. Finally, the context-to-motion model can be trained using a variety of different sensory inputs, which makes it adaptable to a wide range of prosthetic limb designs and environments. Stable diffusion is a machine learning method that can be used to improve the control and stability of movements in robotic and prosthetic systems. It works by using sensory feedback to learn about the dynamics of the environment and then using this information to generate smooth, stable movements. One key aspect of stable diffusion is that it is designed to be robust to noise and uncertainty in the sensory feedback. This means that it can continue to produce stable, smooth movements even when the sensory data is noisy or unreliable. To implement stable diffusion in a robotic or prosthetic system, it is typically necessary to first collect a dataset of examples of the desired movements. This dataset can then be used to train a machine learning model to predict the appropriate control inputs for a given set of sensory observations. Once the model has been trained, it can be used to control the robotic or prosthetic system in real-time. The model receives sensory input from the system and uses it to generate control signals that drive the motors or actuators responsible for moving the system. Overall, the use of the context-to-motion model has the potential to significantly improve the dexterity and performance of prosthetic limbs, making them more useful and effective for a wide range of users Hand Gesture Body Language Influence Communication to social interaction, offering a possibility for users to maximize their quality of life, social interaction, and gesture communication.

Keywords: stable diffusion, neural interface, smart prosthetic, augmenting

Procedia PDF Downloads 99

Authors: Sijie Chen, Xiaofang Chen, Juan Wang, Yingying Zhang, Yu Hong, Wanyu Zhuang, Xinxin Huang, Ping Ou, Longsheng Huang

Abstract:

Purpose: Autistic symptom improvement can be observed in children treated with acupuncture, but the mechanism is still being explored. In the present study, we used scalp acupuncture to treat autism rat model, and then their improvement in the abnormal behaviors and specific mechanisms behind were revealed by detecting animal behaviors, analyzing the RNA sequencing of the prefrontal cortex(PFC), and observing the ultrastructure of PFC neurons under the transmission electron microscope. Methods: On gestational day 12.5, Wistar rats were given valproic acid (VPA) by intraperitoneal injection, and their offspring were considered to be reliable rat models of autism. They were randomized to VPA or VPA-acupuncture group (n=8). Offspring of Wistar pregnant rats that were simultaneously injected with saline were randomly selected as the wild-type group (WT). VPA_acupuncture group rats received acupuncture intervention at 23 days of age for 4 weeks, and the other two groups followed without intervention. After the intervention, all experimental rats underwent behavioral tests. Immediately afterward, they were euthanized by cervical dislocation, and their prefrontal cortex was isolated for RNA sequencing and transmission electron microscopy. Results: The main results are as follows: 1. Animal behavioural tests: VPA group rats showed more anxiety-like behaviour and repetitive, stereotyped behaviour than WT group rats. While VPA group rats showed less spatial exploration ability, activity level, social interaction, and social novelty preference than WT group rats. It was gratifying to observe that acupuncture indeed improved these abnormal behaviors of autism rat model. 2. RNA-sequencing: The three groups of rats differed in the expression and enrichment pathways of multiple genes related to synaptic function, neural signal transduction, and circadian rhythm regulation. Our experiments indicated that acupuncture can alleviate the major symptoms of ASD by improving these neurological abnormalities. 3. Under the transmission electron microscopy, several lysosomes and mitochondrial structural abnormalities were observed in the prefrontal neurons of VPA group rats, which were manifested as atrophy of the mitochondrial membran, blurring or disappearance of the mitochondrial cristae, and even vacuolization. Moreover, the number of synapses and synaptic vesicles was relatively small. Conversely, the mitochondrial structure of rats in the WT group and VPA_acupuncture was normal, and the number of synapses and synaptic vesicles was relatively large. Conclusion: Acupuncture effectively improved the abnormal behaviors of autism rat model and the ultrastructure of the PFC neurons, which might worked by improving their abnormal synaptic function, synaptic plasticity and promoting neuronal signal transduction.

Keywords: autism spectrum disorder, acupuncture, animal behavior, RNA sequencing, transmission electron microscope

Procedia PDF Downloads 42

Authors: Noga Bregman

Abstract:

Accurate and efficient earthquake detection and phase picking are crucial for seismic hazard assessment and emergency response. This study introduces EQMamba, a deep-learning method that combines the strengths of the Earthquake Transformer and the Mamba model for simultaneous earthquake detection and phase picking. EQMamba leverages the computational efficiency of Mamba layers to process longer seismic sequences while maintaining a manageable model size. The proposed architecture integrates convolutional neural networks (CNNs), bidirectional long short-term memory (BiLSTM) networks, and Mamba blocks. The model employs an encoder composed of convolutional layers and max pooling operations, followed by residual CNN blocks for feature extraction. Mamba blocks are applied to the outputs of BiLSTM blocks, efficiently capturing long-range dependencies in seismic data. Separate decoders are used for earthquake detection, P-wave picking, and S-wave picking. We trained and evaluated EQMamba using a subset of the STEAD dataset, a comprehensive collection of labeled seismic waveforms. The model was trained using a weighted combination of binary cross-entropy loss functions for each task, with the Adam optimizer and a scheduled learning rate. Data augmentation techniques were employed to enhance the model's robustness. Performance comparisons were conducted between EQMamba and the EQTransformer over 20 epochs on this modest-sized STEAD subset. Results demonstrate that EQMamba achieves superior performance, with higher F1 scores and faster convergence compared to EQTransformer. EQMamba reached F1 scores of 0.8 by epoch 5 and maintained higher scores throughout training. The model also exhibited more stable validation performance, indicating good generalization capabilities. While both models showed lower accuracy in phase-picking tasks compared to detection, EQMamba's overall performance suggests significant potential for improving seismic data analysis. The rapid convergence and superior F1 scores of EQMamba, even on a modest-sized dataset, indicate promising scalability for larger datasets. This study contributes to the field of earthquake engineering by presenting a computationally efficient and accurate method for simultaneous earthquake detection and phase picking. Future work will focus on incorporating Mamba layers into the P and S pickers and further optimizing the architecture for seismic data specifics. The EQMamba method holds the potential for enhancing real-time earthquake monitoring systems and improving our understanding of seismic events.

Keywords: earthquake, detection, phase picking, s waves, p waves, transformer, deep learning, seismic waves

Procedia PDF Downloads 49

Authors: Brittany Richardson, Ying Wang

Abstract:

For physical therapy, exercise prescription, athlete training, and regular fitness training, it is crucial to perform health assessments or fitness assessments periodically. An accurate assessment is propitious for tracking recovery progress, preventing potential injury and making long-range training plans. Assessments include necessary measurements, height, weight, blood pressure, heart rate, body fat, etc. and advanced evaluation, muscle group strength, stability-mobility, and movement evaluation, etc. In the current standard assessment procedures, the accuracy of assessments, especially advanced evaluations, largely depends on the experience of physicians, coaches, and personal trainers. And it is challenging to track clients’ progress in the current assessment. Unlike the tradition assessment, in this paper, we present a deep learning based face recognition algorithm for accurate, comprehensive and trackable assessment. Based on the result from our assessment, physicians, coaches, and personal trainers are able to adjust the training targets and methods. The system categorizes the difficulty levels of the current activity for the client or user, furthermore make more comprehensive assessments based on tracking muscle group over time using a designed landmark detection method. The system also includes the function of grading and correcting the form of the clients during exercise. Experienced coaches and personal trainer can tell the clients' limit based on their facial expression and muscle group movements, even during the first several sessions. Similar to this, using a convolution neural network, the system is trained with people’s facial expression to differentiate challenge levels for clients. It uses landmark detection for subtle changes in muscle groups movements. It measures the proximal mobility of the hips and thoracic spine, the proximal stability of the scapulothoracic region and distal mobility of the glenohumeral joint, as well as distal mobility, and its effect on the kinetic chain. This system integrates data from other fitness assistant devices, including but not limited to Apple Watch, Fitbit, etc. for a improved training and testing performance. The system itself doesn’t require history data for an individual client, but the history data of a client can be used to create a more effective exercise plan. In order to validate the performance of the proposed work, an experimental design is presented. The results show that the proposed work contributes towards improving the quality of exercise plan, execution, progress tracking, and performance.

Keywords: exercise prescription, facial recognition, landmark detection, fitness assessments

Procedia PDF Downloads 132

Authors: Anna Slupik, Anna Mosiolek, Sebastian Wojtowicz, Dariusz Bialoszewski

Abstract:

Introduction: Whole-body vibration (WBV) uses high frequency mechanical stimuli generated by a vibration plate and transmitted through bone, muscle and connective tissues to the whole body. Research has shown that long-term vibration-plate training improves neuromuscular facilitation, especially in afferent neural pathways, responsible for the conduction of vibration and proprioceptive stimuli, muscle function, balance and proprioception. Some researchers suggest that the vibration stimulus briefly inhibits the conduction of afferent signals from proprioceptors and can interfere with the maintenance of body balance. The aim of this study was to evaluate the influence of a single set of exercises associated with whole-body vibration on the joint position sense and body balance. Material and methods: The study enrolled 55 people aged 19-24 years. These individuals were randomly divided into a test group (30 persons) and a control group (25 persons). Both groups performed the same set of exercises on a vibration plate. The following vibration parameters: frequency of 20Hz and amplitude of 3mm, were used in the test group. The control group performed exercises on the vibration plate while it was off. All participants were instructed to perform six dynamic exercises lasting 30 seconds each with a 60-second period of rest between them. The exercises involved large muscle groups of the trunk, pelvis and lower limbs. Measurements were carried out before and immediately after exercise. Joint position sense (JPS) was measured in the knee joint for the starting position at 45° in an open kinematic chain. JPS error was measured using a digital inclinometer. Balance was assessed in a standing position with both feet on the ground with the eyes open and closed (each test lasting 30 sec). Balance was assessed using Matscan with FootMat 7.0 SAM software. The surface of the ellipse of confidence and front-back as well as right-left swing were measured to assess balance. Statistical analysis was performed using Statistica 10.0 PL software. Results: There were no significant differences between the groups, both before and after the exercise (p> 0.05). JPS did not change in both the test (10.7° vs. 8.4°) and control groups (9.0° vs. 8.4°). No significant differences were shown in any of the test parameters during balance tests with the eyes open or closed in both the test and control groups (p> 0.05). Conclusions. 1. Deterioration in proprioception or balance was not observed immediately after the vibration stimulus. This suggests that vibration-induced blockage of proprioceptive stimuli conduction can have only a short-lasting effect that occurs only as long as a vibration stimulus is present. 2. Short-term use of vibration in treatment does not impair proprioception and seems to be safe for patients with proprioceptive impairment. 3. These results need to be supplemented with an assessment of proprioception during the application of vibration stimuli. Additionally, the impact of vibration parameters used in the exercises should be evaluated.

Keywords: balance, joint position sense, proprioception, whole body vibration

Procedia PDF Downloads 326

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

Abstract:

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

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

Procedia PDF Downloads 117

Authors: Kseniya Gladun

Abstract:

Tactile stimulation of a dorsal side of the wrist can have a strong impact on our attitude toward physical objects such as pleasant and unpleasant impact. This study explored different aspects of tactile perception to investigate atypical touch sensitivity in children with autism spectrum disorder (ASD). This study included 40 children with ASD and 40 healthy children aged 5 to 9 years. We recorded rsEEG (sampling rate of 250 Hz) during 20 min using EEG amplifier “Encephalan” (Medicom MTD, Taganrog, Russian Federation) with 19 AgCl electrodes placed according to the International 10–20 System. The electrodes placed on the left, and right mastoids served as joint references under unipolar montage. The registration of EEG v19 assignments was carried out: frontal (Fp1-Fp2; F3-F4), temporal anterior (T3-T4), temporal posterior (T5-T6), parietal (P3-P4), occipital (O1-O2). Subjects were passively touched by 4 types of tactile stimuli on the left wrist. Our stimuli were presented with a velocity of about 3–5 cm per sec. The stimuli materials and procedure were chosen for being the most "pleasant," "rough," "prickly" and "recognizable". Type of tactile stimulation: Soft cosmetic brush - "pleasant" , Rough shoe brush - "rough", Wartenberg pin wheel roller - "prickly", and the cognitive tactile stimulation included letters by finger (most of the patient’s name ) "recognizable". To designate the moments of the stimuli onset-offset, we marked the moment when the moment of the touch began and ended; the stimulation was manual, and synchronization was not precise enough for event-related measures. EEG epochs were cleaned from eye movements by ICA-based algorithm in EEGLAB plugin for MatLab 7.11.0 (Mathwork Inc.). Muscle artifacts were cut out by manual data inspection. The response to tactile stimuli was significantly different in the group of children with ASD and healthy children, which was also depended on type of tactile stimuli and the severity of ASD. Amplitude of Alpha rhythm increased in parietal region to response for only pleasant stimulus, for another type of stimulus ("rough," "thorny", "recognizable") distinction of amplitude was not observed. Correlation dimension D2 was higher in healthy children compared to children with ASD (main effect ANOVA). In ASD group D2 was lower for pleasant and unpleasant compared to the background in the right parietal area. Hilbert transform changes in the frequency of the theta rhythm found only for a rough tactile stimulation compared with healthy participants only in the right parietal area. Children with autism spectrum disorders and healthy children were responded to tactile stimulation differently with specific frequency distribution alpha and theta band in the right parietal area. Thus, our data supports the hypothesis that rsEEG may serve as a sensitive index of altered neural activity caused by ASD. Children with autism have difficulty in distinguishing the emotional stimuli ("pleasant," "rough," "prickly" and "recognizable").

Keywords: autism, tactile stimulation, Hilbert transform, pediatric electroencephalography

Procedia PDF Downloads 250

Authors: Robert Caulk

Abstract:

A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.

Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration

Procedia PDF Downloads 87

Authors: Yiea Funk Te, Daniel Mueller, Irena Pletikosa Cvijikj

Abstract:

Small and medium enterprises (SMEs) play an important role in the economy of many countries. When the overall world economy is considered, SMEs represent 95% of all businesses in the world, accounting for 66% of the total employment. Existing studies show that the current business environment is characterized as highly turbulent and strongly influenced by modern information and communication technologies, thus forcing SMEs to experience more severe challenges in maintaining their existence and expanding their business. To support SMEs at improving their competitiveness, researchers recently turned their focus on applying data mining techniques to build risk and growth prediction models. However, data used to assess risk and growth indicators is primarily obtained via questionnaires, which is very laborious and time-consuming, or is provided by financial institutes, thus highly sensitive to privacy issues. Recently, web mining (WM) has emerged as a new approach towards obtaining valuable insights in the business world. WM enables automatic and large scale collection and analysis of potentially valuable data from various online platforms, including companies’ websites. While WM methods have been frequently studied to anticipate growth of sales volume for e-commerce platforms, their application for assessment of SME risk and growth indicators is still scarce. Considering that a vast proportion of SMEs own a website, WM bears a great potential in revealing valuable information hidden in SME websites, which can further be used to understand SME risk and growth indicators, as well as to enhance current SME risk and growth prediction models. This study aims at developing an automated system to collect business-relevant data from the Web and predict future growth trends of SMEs by means of WM and data mining techniques. The envisioned system should serve as an 'early recognition system' for future growth opportunities. In an initial step, we examine how structured and semi-structured Web data in governmental or SME websites can be used to explain the success of SMEs. WM methods are applied to extract Web data in a form of additional input features for the growth prediction model. The data on SMEs provided by a large Swiss insurance company is used as ground truth data (i.e. growth-labeled data) to train the growth prediction model. Different machine learning classification algorithms such as the Support Vector Machine, Random Forest and Artificial Neural Network are applied and compared, with the goal to optimize the prediction performance. The results are compared to those from previous studies, in order to assess the contribution of growth indicators retrieved from the Web for increasing the predictive power of the model.

Keywords: data mining, SME growth, success factors, web mining

Procedia PDF Downloads 266

Authors: Nutcha Taneepanichskul, Helen C. Hailes, Mark Miodownik

Abstract:

Plastic waste has emerged as a critical global environmental challenge, primarily driven by the prevalent use of conventional plastics derived from petrochemical refining and manufacturing processes in modern packaging. While these plastics serve vital functions, their persistence in the environment post-disposal poses significant threats to ecosystems. Addressing this issue necessitates approaches, one of which involves the development of biodegradable plastics designed to degrade under controlled conditions, such as industrial composting facilities. It is imperative to note that compostable plastics are engineered for degradation within specific environments and are not suited for uncontrolled settings, including natural landscapes and aquatic ecosystems. The full benefits of compostable packaging are realized when subjected to industrial composting, preventing environmental contamination and waste stream pollution. Therefore, effective sorting technologies are essential to enhance composting rates for these materials and diminish the risk of contaminating recycling streams. In this study, it leverage hyperspectral imaging technology (HSI) coupled with advanced machine learning algorithms to accurately identify various types of plastics, encompassing conventional variants like Polyethylene terephthalate (PET), Polypropylene (PP), Low density polyethylene (LDPE), High density polyethylene (HDPE) and biodegradable alternatives such as Polybutylene adipate terephthalate (PBAT), Polylactic acid (PLA), and Polyhydroxyalkanoates (PHA). The dataset is partitioned into three subsets: a training dataset comprising uncontaminated conventional and biodegradable plastics, a validation dataset encompassing contaminated plastics of both types, and a testing dataset featuring real-world packaging items in both pristine and contaminated states. Five distinct machine learning algorithms, namely Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Logistic Regression, and Decision Tree Algorithm, were developed and evaluated for their classification performance. Remarkably, the Logistic Regression and CNN model exhibited the most promising outcomes, achieving a perfect accuracy rate of 100% for the training and validation datasets. Notably, the testing dataset yielded an accuracy exceeding 80%. The successful implementation of this sorting technology within recycling and composting facilities holds the potential to significantly elevate recycling and composting rates. As a result, the envisioned circular economy for plastics can be established, thereby offering a viable solution to mitigate plastic pollution.

Keywords: biodegradable plastics, sorting technology, hyperspectral imaging technology, machine learning algorithms

Procedia PDF Downloads 77

Authors: Diego Santibañez Oyarce, Fernanda Bravo Cornejo, Camilo Cerda Sarabia, Belén Díaz Díaz, Esteban Gómez Terán, Hugo Osses Prado, Raúl Caulier-Cisterna, Jorge Vergara-Quezada, Ana Moya-Beltrán

Abstract:

The advent of high-throughput sequencing technologies has revolutionized genomics, generating vast amounts of genetic data that challenge traditional bioinformatics methods. Machine learning addresses these challenges by leveraging computational power to identify patterns and extract information from large datasets. However, biological sequence data, being symbolic and non-numeric, must be converted into numerical formats for machine learning algorithms to process effectively. So far, some encoding methods, such as one-hot encoding or k-mers, have been explored. This work proposes additional approaches for encoding DNA sequences in order to compare them with existing techniques and determine if they can provide improvements or if current methods offer superior results. Data from the 16S rRNA gene, a universal marker, was used to analyze eight bacterial groups that are significant in the pulmonary environment and have clinical implications. The bacterial genes included in this analysis are Prevotella, Abiotrophia, Acidovorax, Streptococcus, Neisseria, Veillonella, Mycobacterium, and Megasphaera. These data were downloaded from the NCBI database in Genbank file format, followed by a syntactic analysis to selectively extract relevant information from each file. For data encoding, a sequence normalization process was carried out as the first step. From approximately 22,000 initial data points, a subset was generated for testing purposes. Specifically, 55 sequences from each bacterial group met the length criteria, resulting in an initial sample of approximately 440 sequences. The sequences were encoded using different methods, including one-hot encoding, k-mers, Fourier transform, and Wavelet transform. Various machine learning algorithms, such as support vector machines, random forests, and neural networks, were trained to evaluate these encoding methods. The performance of these models was assessed using multiple metrics, including the confusion matrix, ROC curve, and F1 Score, providing a comprehensive evaluation of their classification capabilities. The results show that accuracies between encoding methods vary by up to approximately 15%, with the Fourier transform obtaining the best results for the evaluated machine learning algorithms. These findings, supported by the detailed analysis using the confusion matrix, ROC curve, and F1 Score, provide valuable insights into the effectiveness of different encoding methods and machine learning algorithms for genomic data analysis, potentially improving the accuracy and efficiency of bacterial classification and related genomic studies.

Keywords: DNA encoding, machine learning, Fourier transform, Fourier transformation

Procedia PDF Downloads 22

Authors: Felice Elefant, Akanksha Bhatnaghar, Keegan Krick, Elizabeth Heller

Abstract:

Context: The severity of Alzheimer’s Disease (AD) progression involves an interplay of genetics, age, and environmental factors orchestrated by histone acetyltransferase (HAT) mediated neuroepigenetic mechanisms. While disruption of Tip60 HAT action in neural gene control is implicated in AD, alternative mechanisms underlying Tip60 function remain unexplored. Altered RNA splicing has recently been highlighted as a widespread hallmark in the AD transcriptome that is implicated in the disease. Research Aim: The aim of this study was to identify a novel RNA binding/splicing function for Tip60 in human hippocampus and impaired in brains from AD fly models and AD patients. Methodology/Analysis: The authors used RNA immunoprecipitation using RNA isolated from 200 pooled wild type Drosophila brains for each of the 3 biological replicates. To identify Tip60’s RNA targets, they performed genome sequencing (DNB-SequencingTM technology, BGI genomics) on 3 replicates for Input RNA and RNA IPs by Tip60. Findings: The authors' transcriptomic analysis of RNA bound to Tip60 by Tip60-RNA immunoprecipitation (RIP) revealed Tip60 RNA targets enriched for critical neuronal processes implicated in AD. Remarkably, 79% of Tip60’s RNA targets overlap with its chromatin gene targets, supporting a model by which Tip60 orchestrates bi-level transcriptional regulation at both the chromatin and RNA level, a function unprecedented for any HAT to date. Since RNA splicing occurs co-transcriptionally and splicing defects are implicated in AD, the authors investigated whether Tip60-RNA targeting modulates splicing decisions and if this function is altered in AD. Replicate multivariate analysis of transcript splicing (rMATS) analysis of RNA-Seq data sets from wild-type and AD fly brains revealed a multitude of mammalian-like AS defects. Strikingly, over half of these altered RNAs were bonafide Tip60-RNA targets enriched for in the AD-gene curated database, with some AS alterations prevented against by increasing Tip60 in fly brain. Importantly, human orthologs of several Tip60-modulated spliced genes in Drosophila are well characterized aberrantly spliced genes in human AD brains, implicating disruption of Tip60’s splicing function in AD pathogenesis. Theoretical Importance: The authors' findings support a novel RNA interaction and splicing regulatory function for Tip60 that may underlie AS impairments that hallmark AD etiology. Data Collection: The authors collected data from RNA immunoprecipitation experiments using RNA isolated from 200 pooled wild type Drosophila brains for each of the 3 biological replicates. They also performed genome sequencing (DNBSequencingTM technology, BGI genomics) on 3 replicates for Input RNA and RNA IPs by Tip60. Questions: The question addressed by this study was whether Tip60 has a novel RNA binding/splicing function in human hippocampus and whether this function is impaired in brains from AD fly models and AD patients. Conclusions: The authors' findings support a novel RNA interaction and splicing regulatory function for Tip60 that may underlie AS impairments that hallmark AD etiology.

Keywords: Alzheimer's disease, cognition, aging, neuroepigenetics

Procedia PDF Downloads 74

Authors: Elham Bagheri, Yalda Mohsenzadeh

Abstract:

Image memorability refers to the phenomenon where certain images are more likely to be remembered by humans than others. It is a quantifiable and intrinsic attribute of an image. Understanding how visual perception and memory interact is important in both cognitive science and artificial intelligence. It reveals the complex processes that support human cognition and helps to improve machine learning algorithms by mimicking the brain's efficient data processing and storage mechanisms. To explore the computational underpinnings of image memorability, this study examines the relationship between an image's reconstruction error, distinctiveness in latent space, and its memorability score. A trained autoencoder is used to replicate human-like memorability assessment inspired by the visual memory game employed in memorability estimations. This study leverages a VGG-based autoencoder that is pre-trained on the vast ImageNet dataset, enabling it to recognize patterns and features that are common to a wide and diverse range of images. An empirical analysis is conducted using the MemCat dataset, which includes 10,000 images from five broad categories: animals, sports, food, landscapes, and vehicles, along with their corresponding memorability scores. The memorability score assigned to each image represents the probability of that image being remembered by participants after a single exposure. The autoencoder is finetuned for one epoch with a batch size of one, attempting to create a scenario similar to human memorability experiments where memorability is quantified by the likelihood of an image being remembered after being seen only once. The reconstruction error, which is quantified as the difference between the original and reconstructed images, serves as a measure of how well the autoencoder has learned to represent the data. The reconstruction error of each image, the error reduction, and its distinctiveness in latent space are calculated and correlated with the memorability score. Distinctiveness is measured as the Euclidean distance between each image's latent representation and its nearest neighbor within the autoencoder's latent space. Different structural and perceptual loss functions are considered to quantify the reconstruction error. The results indicate that there is a strong correlation between the reconstruction error and the distinctiveness of images and their memorability scores. This suggests that images with more unique distinct features that challenge the autoencoder's compressive capacities are inherently more memorable. There is also a negative correlation between the reduction in reconstruction error compared to the autoencoder pre-trained on ImageNet, which suggests that highly memorable images are harder to reconstruct, probably due to having features that are more difficult to learn by the autoencoder. These insights suggest a new pathway for evaluating image memorability, which could potentially impact industries reliant on visual content and mark a step forward in merging the fields of artificial intelligence and cognitive science. The current research opens avenues for utilizing neural representations as instruments for understanding and predicting visual memory.

Keywords: autoencoder, computational vision, image memorability, image reconstruction, memory retention, reconstruction error, visual perception

Procedia PDF Downloads 88

Authors: Elham Koohikerade, Silvio Jose Gumiere

Abstract:

In this research, irrigation is highlighted as crucial for improving both the yield and quality of ‎potatoes due to their high sensitivity to soil moisture changes. The study presents a hybrid Long ‎Short-Term Memory (LSTM) model aimed at optimizing irrigation scheduling in potato fields in ‎Quebec City, Canada. This model integrates model-based and satellite-derived datasets to simulate ‎soil moisture content, addressing the limitations of field data. Developed under the guidance of the ‎Food and Agriculture Organization (FAO), the simulation approach compensates for the lack of direct ‎soil sensor data, enhancing the LSTM model's predictions. The model was calibrated using indices ‎like Surface Soil Moisture (SSM), Normalized Vegetation Difference Index (NDVI), Enhanced ‎Vegetation Index (EVI), and Normalized Multi-band Drought Index (NMDI) to effectively forecast ‎soil moisture reductions. Understanding soil moisture and plant development is crucial for assessing ‎drought conditions and determining irrigation needs. This study validated the spectral characteristics ‎of vegetation and soil using ECMWF Reanalysis v5 (ERA5) and Moderate Resolution Imaging ‎Spectrometer (MODIS) data from 2019 to 2023, collected from agricultural areas in Dolbeau and ‎Peribonka, Quebec. Parameters such as surface volumetric soil moisture (0-7 cm), NDVI, EVI, and ‎NMDI were extracted from these images. A regional four-year dataset of soil and vegetation moisture ‎was developed using a machine learning approach combining model-based and satellite-based ‎datasets. The LSTM model predicts soil moisture dynamics hourly across different locations and ‎times, with its accuracy verified through cross-validation and comparison with existing soil moisture ‎datasets. The model effectively captures temporal dynamics, making it valuable for applications ‎requiring soil moisture monitoring over time, such as anomaly detection and memory analysis. By ‎identifying typical peak soil moisture values and observing distribution shapes, irrigation can be ‎scheduled to maintain soil moisture within Volumetric Soil Moisture (VSM) values of 0.25 to 0.30 ‎m²/m², avoiding under and over-watering. The strong correlations between parcels suggest that a ‎uniform irrigation strategy might be effective across multiple parcels, with adjustments based on ‎specific parcel characteristics and historical data trends. The application of the LSTM model to ‎predict soil moisture and vegetation indices yielded mixed results. While the model effectively ‎captures the central tendency and temporal dynamics of soil moisture, it struggles with accurately ‎predicting EVI, NDVI, and NMDI.‎

Keywords: irrigation scheduling, LSTM neural network, remotely sensed indices, soil and vegetation ‎monitoring

Procedia PDF Downloads 40

Authors: Koteswara Rao Pagolu, Raghava Rao Tamanam

Abstract:

The present study was aimed to find out the prevalence of DD's in Visakhapatnam, one of the north coastal districts of Andhra Pradesh, India during a span of five years. A cross-sectional investigation was held at District early intervention center (DEIC), Visakhapatnam from 2016 to 2020. To identify the pattern and trend of different DD's including seasonal variations, a retrospective analysis of the health center's inpatient database for the past 5 years was done. Male and female children aged 2 months-18 years are included in the study with the prior permission of the concerned medical officer. The screening tool developed by the Ministry of health and family welfare, India, was used for the study. Among 26,423 cases, children with birth defects are 962, 2229 with deficiencies, 7516 with diseases, and 15716 with disabilities were admitted during the study period. From birth defects, congenital deafness occurred in large numbers with 22.66%, and neural tube defect observed in a small number of cases with 0.83% during the period. From the side of deficiencies, severe acute malnutrition has mostly occurred (66.80 %) and a small number of children were affected with goiter (1.70%). Among the diseases, dental carriers (67.97%) are mostly found and these cases were at peak during the years 2016 and 2019. From disabilities, children with vision impairment (20.55%) have mostly approached the center. Over the past 5 years, the admission rate of down's syndrome and congenital deafness cases showed a rising trend up to 2019 and then declined. Hearing impairment, motor delay, and learning disorder showed a steep rise and gradual decline trend, whereas severe anemia, vitamin-D deficiency, otitis media, reactive airway disease, and attention deficit hyperactivity disorder showed a declining trend. However, congenital heart diseases, dental caries, and vision impairment admission rates showed a zigzag pattern over the past 5 years. This center had inadequate diagnostic facilities related to genetic disease management. For advanced confirmation, the cases are referred to a district government hospital or private diagnostic laboratories in the city for genetic tests. Information regarding the overall burden and pattern of admissions in the health center is obtained by the review of DEIC records. Through this study, it is observed that the incidence of birth defects, as well as genetic disease burden, is high in the Visakhapatnam district. Hence there is a need for strengthening of management services for these diseases in this region.

Keywords: child health screening, developmental delays, district early intervention center, genetic disease management, infrastructural facility, Visakhapatnam district

Procedia PDF Downloads 212