Search results for: neural computing

Authors: Eyob Seife

Abstract:

Immunization is a life-saving intervention which prevents needless suffering through sickness, disability, and death. Emphasis on data quality and use will become even stronger with the development of the immunization agenda 2030 (IA2030). Quality of data is a key factor in generating reliable health information that enables monitoring progress, financial planning, vaccine forecasting capacities, and making decisions for continuous improvement of the national immunization program. However, ensuring data of sufficient quality and promoting an information-use culture at the point of the collection remains critical and challenging, especially in hard-to-reach and pastoralist areas where Degehabur district is selected based on a hypothesis of ‘there is no difference in reported and recounted immunization data consistency. Data quality is dependent on different factors where organizational, behavioral, technical, and contextual factors are the mentioned ones. A cross-sectional quantitative study was conducted on September 2022 in the Degehabur district. The study used the world health organization (WHO) recommended data quality self-assessment (DQS) tools. Immunization tally sheets, registers, and reporting documents were reviewed at 5 health facilities (2 health centers and 3 health posts) of primary health care units for one fiscal year (12 months) to determine the accuracy ratio. The data was collected by trained DQS assessors to explore the quality of monitoring systems at health posts, health centers, and the district health office. A quality index (QI) was assessed, and the accuracy ratio formulated were: the first and third doses of pentavalent vaccines, fully immunized (FI), and the first dose of measles-containing vaccines (MCV). In this study, facility-level results showed both over-reporting and under-reporting were observed at health posts when computing the accuracy ratio of the tally sheet to health post reports found at health centers for almost all antigens verified where pentavalent 1 was 88.3%, 60.4%, and 125.6% for Health posts A, B, and C respectively. For first-dose measles-containing vaccines (MCV), similarly, the accuracy ratio was found to be 126.6%, 42.6%, and 140.9% for Health posts A, B, and C, respectively. The accuracy ratio for fully immunized children also showed 0% for health posts A and B and 100% for health post-C. A relatively better accuracy ratio was seen at health centers where the first pentavalent dose was 97.4% and 103.3% for health centers A and B, while a first dose of measles-containing vaccines (MCV) was 89.2% and 100.9% for health centers A and B, respectively. A quality index (QI) of all facilities also showed results between the maximum of 33.33% and a minimum of 0%. Most of the verified immunization data accuracy ratios were found to be relatively better at the health center level. However, the quality of the monitoring system is poor at all levels, besides poor data accuracy at all health posts. So attention should be given to improving the capacity of staff and quality of monitoring system components, namely recording, reporting, archiving, data analysis, and using information for decision at all levels, especially in pastoralist areas where such kinds of study findings need to be improved beside to improving the data quality at root and health posts level.

Keywords: accuracy ratio, Degehabur District, regular childhood immunization program, quality of monitoring system, Somali Region-Ethiopia

Procedia PDF Downloads 72

Authors: Dian Zhang, Brendan Heery, Maria O’Neill, Ciprian Briciu-Burghina, Noel E. O’Connor, Fiona Regan

Abstract:

Recent developments in sensors, wireless data communication and the cloud computing have brought the sensor web to a whole new generation. The introduction of the concept of ‘Internet of Thing (IoT)’ has brought the sensor research into a new level, which involves the developing of long lasting, low cost, environment friendly and smart sensors; new wireless data communication technologies; big data analytics algorithms and cloud based solutions that are tailored to large scale smart sensor network. The next generation of smart sensor network consists of several layers: physical layer, where all the smart sensors resident and data pre-processes occur, either on the sensor itself or field gateway; data transmission layer, where data and instructions exchanges happen; the data process layer, where meaningful information is extracted and organized from the pre-process data stream. There are many definitions of smart sensor, however, to summarize all these definitions, a smart sensor must be Intelligent and Adaptable. In future large scale sensor network, collected data are far too large for traditional applications to send, store or process. The sensor unit must be intelligent that pre-processes collected data locally on board (this process may occur on field gateway depends on the sensor network structure). In this case study, three smart sensing methods, corresponding to simple thresholding, statistical model and machine learning based MoPBAS method, are introduced and their strength and weakness are discussed as an introduction to the smart sensing concept. Data fusion, the integration of data and knowledge from multiple sources, are key components of the next generation smart sensor network. For example, in the water level monitoring system, weather forecast can be extracted from external sources and if a heavy rainfall is expected, the server can send instructions to the sensor notes to, for instance, increase the sampling rate or switch on the sleeping mode vice versa. In this paper, we describe the deployment of 11 affordable water level sensors in the Dublin catchment. The objective of this paper is to use the deployed river level sensor network at the Dodder catchment in Dublin, Ireland as a case study to give a vision of the next generation of a smart sensor network for flood monitoring to assist agencies in making decisions about deploying resources in the case of a severe flood event. Some of the deployed sensors are located alongside traditional water level sensors for validation purposes. Using the 11 deployed river level sensors in a network as a case study, a vision of the next generation of smart sensor network is proposed. Each key component of the smart sensor network is discussed, which hopefully inspires the researchers who are working in the sensor research domain.

Keywords: smart sensing, internet of things, water level sensor, flooding

Procedia PDF Downloads 350

Authors: Gyu-Dong Kim, Wuk-Jae Yoo, Sang-Youl Lee

Abstract:

Composite structures offer numerous advantages over conventional structural systems in the form of higher specific stiffness and strength, lower life-cycle costs, and benefits such as easy installation and improved safety. Recently, there has been a considerable increase in the use of composites in engineering applications and as wraps for seismic upgrading and repairs. However, these composites deteriorate with time because of outdated materials, excessive use, repetitive loading, climatic conditions, manufacturing errors, and deficiencies in inspection methods. In particular, damaged fibers in a composite result in significant degradation of structural performance. In order to reduce the failure probability of composites in service, techniques to assess the condition of the composites to prevent continual growth of fiber damage are required. Condition assessment technology and nondestructive evaluation (NDE) techniques have provided various solutions for the safety of structures by means of detecting damage or defects from static or dynamic responses induced by external loading. A variety of techniques based on detecting the changes in static or dynamic behavior of isotropic structures has been developed in the last two decades. These methods, based on analytical approaches, are limited in their capabilities in dealing with complex systems, primarily because of their limitations in handling different loading and boundary conditions. Recently, investigators have introduced direct search methods based on metaheuristics techniques and artificial intelligence, such as genetic algorithms (GA), simulated annealing (SA) methods, and neural networks (NN), and have promisingly applied these methods to the field of structural identification. Among them, GAs attract our attention because they do not require a considerable amount of data in advance in dealing with complex problems and can make a global solution search possible as opposed to classical gradient-based optimization techniques. In this study, we propose an alternative damage-detection technique that can determine the degraded stiffness distribution of vibrating laminated composites made of Glass Fiber-reinforced Polymer (GFRP). The proposed method uses a modified form of the bivariate Gaussian distribution function to detect degraded stiffness characteristics. In addition, this study presents a method to detect the fiber property variation of laminated composite plates from the micromechanical point of view. The finite element model is used to study free vibrations of laminated composite plates for fiber stiffness degradation. In order to solve the inverse problem using the combined method, this study uses only first mode shapes in a structure for the measured frequency data. In particular, this study focuses on the effect of the interaction among various parameters, such as fiber angles, layup sequences, and damage distributions, on fiber-stiffness damage detection.

Keywords: stiffness detection, fiber damage, genetic algorithm, layup sequences

Procedia PDF Downloads 238

Authors: Bruno Biagianti, Angela Tseng, Kathy Wannaviroj, Allison Corlett, Megan DuBois, Kyu Lee, Suma Jacob

Abstract:

Background: ASD is characterized by pervasive Sensory Processing Abnormalities (SPA) and social cognitive deficits that persist throughout the course of the illness and have been linked to functional abnormalities in specific neural systems that underlie the perception, processing, and representation of sensory information. SPA and social cognitive deficits are associated with difficulties in interpersonal relationships, poor development of social skills, reduced social interactions and lower academic performance. Importantly, they can hamper the effects of established evidence-based psychological treatments—including PEERS (Program for the Education and Enrichment of Relationship Skills), a parent/caregiver-assisted, 16-weeks social skills intervention—which nonetheless requires a functional brain capable of assimilating and retaining information and skills. As a matter of fact, some adolescents benefit from PEERS more than others, calling for strategies to increase treatment response rates. Objective: We will present interim data on CICADAS (Care Improving Cognition for ADolescents on the Autism Spectrum)—a clinician-assisted, closed-loop technology mobile application for adolescents with ASD. Via ten mobile assessments, CICADAS captures data on sensory processing abnormalities and associated cognitive deficits. These data populate a machine learning algorithm that tailors the delivery of ten neuroplasticity-based social cognitive training (NB-SCT) exercises targeting sensory processing abnormalities. Methods: In collaboration with the Autism Spectrum and Neurodevelopmental Disorders Clinic at the University of Minnesota, we conducted a fully remote, three-arm, randomized crossover trial with adolescents with ASD to document the acceptability of CICADAS and evaluate its potential as a stand-alone treatment or as a treatment enhancer of PEERS. Twenty-four adolescents with ASD (ages 11-18) have been initially randomized to 16 weeks of PEERS + CICADAS (Arm A) vs. 16 weeks of PEERS + computer games vs. 16 weeks of CICADAS alone (Arm C). After 16 weeks, the full battery of assessments has been remotely administered. Results: We have evaluated the acceptability of CICADAS by examining adherence rates, engagement patterns, and exit survey data. We found that: 1) CICADAS is able to serve as a treatment enhancer for PEERS, inducing greater improvements in sensory processing, cognition, symptom reduction, social skills and behaviors, as well as the quality of life compared to computer games; 2) the concurrent delivery of PEERS and CICADAS induces greater improvements in study outcomes compared to CICADAS only. Conclusion: While preliminary, our results indicate that the individualized assessment and treatment approach designed in CICADAS seems effective in inducing adaptive long-term learning about social-emotional events. CICADAS-induced enhancement of processing and cognition facilitates the application of PEERS skills in the environment of adolescents with ASD, thus improving their real-world functioning.

Keywords: ASD, social skills, cognitive training, mobile app

Procedia PDF Downloads 177

Authors: Mauro Callejas-Cuervo, Andrea C. Alarcon-Aldana, Andres F. Ruiz-Olaya, Juan C. Alvarez

Abstract:

Motion capture (MC) is the construction of a precise and accurate digital representation of a real motion. Systems have been used in the last years in a wide range of applications, from films special effects and animation, interactive entertainment, medicine, to high competitive sport where a maximum performance and low injury risk during training and competition is seeking. This paper presents an inertial and magnetic sensor based technological platform, intended for particular amplitude monitoring and telerehabilitation processes considering an efficient cost/technical considerations compromise. Our platform particularities offer high social impact possibilities by making telerehabilitation accessible to large population sectors in marginal socio-economic sector, especially in underdeveloped countries that in opposition to developed countries specialist are scarce, and high technology is not available or inexistent. This platform integrates high-resolution low-cost inertial and magnetic sensors with adequate user interfaces and communication protocols to perform a web or other communication networks available diagnosis service. The amplitude information is generated by sensors then transferred to a computing device with adequate interfaces to make it accessible to inexperienced personnel, providing a high social value. Amplitude measurements of the platform virtual system presented a good fit to its respective reference system. Analyzing the robotic arm results (estimation error RMSE 1=2.12° and estimation error RMSE 2=2.28°), it can be observed that during arm motion in any sense, the estimation error is negligible; in fact, error appears only during sense inversion what can easily be explained by the nature of inertial sensors and its relation to acceleration. Inertial sensors present a time constant delay which acts as a first order filter attenuating signals at large acceleration values as is the case for a change of sense in motion. It can be seen a damped response of platform virtual in other images where error analysis show that at maximum amplitude an underestimation of amplitude is present whereas at minimum amplitude estimations an overestimation of amplitude is observed. This work presents and describes the platform virtual as a motion capture system suitable for telerehabilitation with the cost - quality and precision - accessibility relations optimized. These particular characteristics achieved by efficiently using the state of the art of accessible generic technology in sensors and hardware, and adequate software for capture, transmission analysis and visualization, provides the capacity to offer good telerehabilitation services, reaching large more or less marginal populations where technologies and specialists are not available but accessible with basic communication networks.

Keywords: inertial sensors, joint amplitude measurement, MEMS, telerehabilitation

Procedia PDF Downloads 228

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 136

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 70

Authors: G. Cunningham, E. Cantor, X. Wu, F. Shen, G. Jiang, S. Philips, C. Bales, Y. Xiao, T. R. Cummins, J. C. Fehrenbacher, B. P. Schneider

Abstract:

Background: Taxane-induced peripheral neuropathy (TIPN) is the most devastating survivorship issue for patients receiving therapy. Dose reductions due to TIPN in the curative setting lead to inferior outcomes for African American patients, as prior research has shown that this group is more susceptible to developing severe neuropathy. The mechanistic underpinnings of TIPN, however, have not been entirely elucidated. While it would be appealing to use primary tissue to study the development of TIPN, procuring nerves from patients is not realistically feasible, as nerve biopsies are painful and may result in permanent damage. Therefore, our laboratory has investigated paclitaxel-induced neuronal morphological and molecular changes using an ex vivo model of human-induced pluripotent stem cell (iPSC)-derived neurons. Methods: iPSCs are undifferentiated and endlessly dividing cells that can be generated from a patient’s somatic cells, such as peripheral blood mononuclear cells (PBMCs). We successfully reprogrammed PBMCs into iPSCs using the Erythroid Progenitor Reprograming Kit (STEMCell Technologiesᵀᴹ); pluripotency was verified by flow cytometry analysis. iPSCs were then induced into neurons using a differentiation protocol that bypasses the neural progenitor stage and uses selected small-molecule modulators of key signaling pathways (SMAD, Notch, FGFR1 inhibition, and Wnt activation). Results: Flow cytometry analysis revealed expression of core pluripotency transcription factors Nanog, Oct3/4 and Sox2 in iPSCs overlaps with commercially purchased pluripotent cell line UCSD064i-20-2. Trilineage differentiation of iPSCs was confirmed with immunofluorescent imaging with germ-layer-specific markers; Sox17 and ExoA2 for ectoderm, Nestin, and Pax6 for mesoderm, and Ncam and Brachyury for endoderm. Sensory neuron markers, β-III tubulin, and Peripherin were applied to stain the cells for the maturity of iPSC-derived neurons. Patch-clamp electrophysiology and calcitonin gene-related peptide (CGRP) release data supported the functionality of the induced neurons and provided insight into the timing for which downstream assays could be performed (week 4 post-induction). We have also performed a cell viability assay and fluorescence-activated cell sorting (FACS) using four cell-surface markers (CD184, CD44, CD15, and CD24) to select a neuronal population. At least 70% of the cells were viable in the isolated neuron population. Conclusion: We have found that these iPSC-derived neurons recapitulate mature neuronal phenotypes and demonstrate functionality. Thus, this represents a patient-derived ex vivo neuronal model to investigate the molecular mechanisms of clinical TIPN.

Keywords: chemotherapy, iPSC-derived neurons, peripheral neuropathy, taxane, paclitaxel

Procedia PDF Downloads 99

Authors: Kenneth A. Rostowsky, Alexander S. Maher, Nahian F. Chowdhury, Andrei Irimia

Abstract:

The clinical significance of cerebral microbleeds (CMBs) due to mild traumatic brain injury (mTBI) remains unclear. Here we use magnetic resonance imaging (MRI), diffusion tensor imaging (DTI) and connectomic analysis to investigate the statistical association between mTBI-related CMBs, post-TBI changes to the human connectome and neurological/cognitive deficits. This study was undertaken in agreement with US federal law (45 CFR 46) and was approved by the Institutional Review Board (IRB) of the University of Southern California (USC). Two groups, one consisting of 26 (13 females) mTBI victims and another comprising 26 (13 females) healthy control (HC) volunteers were recruited through IRB-approved procedures. The acute Glasgow Coma Scale (GCS) score was available for each mTBI victim (mean µ = 13.2; standard deviation σ = 0.4). Each HC volunteer was assigned a GCS of 15 to indicate the absence of head trauma at the time of enrollment in our study. Volunteers in the HC and mTBI groups were matched according to their sex and age (HC: µ = 67.2 years, σ = 5.62 years; mTBI: µ = 66.8 years, σ = 5.93 years). MRI [including T1- and T2-weighted volumes, gradient recalled echo (GRE)/susceptibility weighted imaging (SWI)] and gradient echo (GE) DWI volumes were acquired using the same MRI scanner type (Trio TIM, Siemens Corp.). Skull-stripping and eddy current correction were implemented. DWI volumes were processed in TrackVis (http://trackvis.org) and 3D Slicer (http://www.slicer.org). Tensors were fit to DWI data to perform DTI, and tractography streamlines were then reconstructed using deterministic tractography. A voxel classifier was used to identify image features as CMB candidates using Microbleed Anatomic Rating Scale (MARS) guidelines. For each peri-lesional DTI streamline bundle, the null hypothesis was formulated as the statement that there was no neurological or cognitive deficit associated with between-scan differences in the mean FA of DTI streamlines within each bundle. The statistical significance of each hypothesis test was calculated at the α = 0.05 level, subject to the family-wise error rate (FWER) correction for multiple comparisons. Results: In HC volunteers, the along-track analysis failed to identify statistically significant differences in the mean FA of DTI streamline bundles. In the mTBI group, significant differences in the mean FA of peri-lesional streamline bundles were found in 21 out of 26 volunteers. In those volunteers where significant differences had been found, these differences were associated with an average of ~47% of all identified CMBs (σ = 21%). In 12 out of the 21 volunteers exhibiting significant FA changes, cognitive functions (memory acquisition and retrieval, top-down control of attention, planning, judgment, cognitive aspects of decision-making) were found to have deteriorated over the six months following injury (r = -0.32, p < 0.001). Our preliminary results suggest that acute post-TBI CMBs may be associated with cognitive decline in some mTBI patients. Future research should attempt to identify mTBI patients at high risk for cognitive sequelae.

Keywords: traumatic brain injury, magnetic resonance imaging, diffusion tensor imaging, connectomics

Procedia PDF Downloads 147

Authors: S. B. R. Slagmulder

Abstract:

Monitoring inspiratory effort and dynamic lung stress in patients on pressure support ventilation in the ICU is important for protecting against self inflicted lung injury (P-SILI) and diaphragm dysfunction. Strategies to address the detrimental effects of respiratory drive and effort can lead to improved patient outcomes. Two non-invasive estimation methods, occlusion pressure (Pocc) and P0.1, have been proposed for achieving lung and diaphragm protective ventilation. However, their relationship and interpretation in neuro ICU patients is not well understood. P0.1 is the airway pressure measured during a 100-millisecond occlusion of the inspiratory port. It reflects the neural drive from the respiratory centers to the diaphragm and respiratory muscles, indicating the patient's respiratory drive during the initiation of each breath. Occlusion pressure, measured during a brief inspiratory pause against a closed airway, provides information about the inspiratory muscles' strength and the system's total resistance and compliance. Research Objective: Understanding the relationship between Pocc and P0.1 in brain-injured patients can provide insights into the interpretation of these values in pressure support ventilation. This knowledge can contribute to determining extubation readiness and optimizing ventilation strategies to improve patient outcomes. The central goal is to asses a study protocol for determining the relationship between Pocc and P0.1 in brain-injured patients on pressure support ventilation and their ability to predict successful extubation. Additionally, comparing these values between brain-damaged and non-brain-damaged patients may provide valuable insights. Key Areas of Inquiry: 1. How do Pocc and P0.1 values correlate within brain injury patients undergoing pressure support ventilation? 2. To what extent can Pocc and P0.1 values serve as predictive indicators for successful extubation in patients with brain injuries? 3. What differentiates the Pocc and P0.1 values between patients with brain injuries and those without? Methodology: P0.1 and occlusion pressures are standard measurements for pressure support ventilation patients, taken by attending doctors as per protocol. We utilize electronic patient records for existing data. Unpaired T-test will be conducted to compare P0.1 and Pocc values between both study groups. Associations between P0.1 and Pocc and other study variables, such as extubation, will be explored with simple regression and correlation analysis. Depending on how the data evolve, subgroup analysis will be performed for patients with and without extubation failure. Results: While it is anticipated that neuro patients may exhibit high respiratory drive, the linkage between such elevation, quantified by P0.1, and successful extubation remains unknown The analysis will focus on determining the ability of these values to predict successful extubation and their potential impact on ventilation strategies. Conclusion: Further research is pending to fully understand the potential of these indices and their impact on mechanical ventilation in different patient populations and clinical scenarios. Understanding these relationships can aid in determining extubation readiness and tailoring ventilation strategies to improve patient outcomes in this specific patient population. Additionally, it is vital to account for the influence of sedatives, neurological scores, and BMI on respiratory drive and occlusion pressures to ensure a comprehensive analysis.

Keywords: brain damage, diaphragm dysfunction, occlusion pressure, p0.1, respiratory drive

Procedia PDF Downloads 39

Authors: Takoua Soltani, Imen Soltani, Taoufik Aguili

Abstract:

The communications' and radar systems' demands give rise to new developments in the domain of active integrated antennas (AIA) and arrays. The main advantages of AIA arrays are the simplicity of fabrication, low cost of manufacturing, and the combination between free space power and the scanner without a phase shifter. The integrated active antenna modeling is the coupling between the electromagnetic model and the transport model that will be affected in the high frequencies. Global modeling of active circuits is important for simulating EM coupling, interaction between active devices and the EM waves, and the effects of EM radiation on active and passive components. The current review focuses on the modeling of the active element which is a MESFET transistor immersed in a rectangular waveguide. The proposed EM analysis is based on the Method of Moments combined with the Generalised Equivalent Circuit method (MOM-GEC). The Method of Moments which is the most common and powerful software as numerical techniques have been used in resolving the electromagnetic problems. In the class of numerical techniques, MOM is the dominant technique in solving of Maxwell and Transport’s integral equations for an active integrated antenna. In this situation, the equivalent circuit is introduced to the development of an integral method formulation based on the transposition of field problems in a Generalised equivalent circuit that is simpler to treat. The method of Generalised Equivalent Circuit (MGEC) was suggested in order to represent integral equations circuits that describe the unknown electromagnetic boundary conditions. The equivalent circuit presents a true electric image of the studied structures for describing the discontinuity and its environment. The aim of our developed method is to investigate the antenna parameters such as the input impedance and the current density distribution and the electric field distribution. In this work, we propose a global EM modeling of the MESFET AsGa transistor using an integral method. We will begin by describing the modeling structure that allows defining an equivalent EM scheme translating the electromagnetic equations considered. Secondly, the projection of these equations on common-type test functions leads to a linear matrix equation where the unknown variable represents the amplitudes of the current density. Solving this equation resulted in providing the input impedance, the distribution of the current density and the electric field distribution. From electromagnetic calculations, we were able to present the convergence of input impedance for different test function number as a function of the guide mode numbers. This paper presents a pilot study to find the answer to map out the variation of the existing current evaluated by the MOM-GEC. The essential improvement of our method is reducing computing time and memory requirements in order to provide a sufficient global model of the MESFET transistor.

Keywords: active integrated antenna, current density, input impedance, MESFET transistor, MOM-GEC method

Procedia PDF Downloads 170

Authors: A. Chatel, I. S. Torreguitart, T. Verstraete

Abstract:

The paper deals with a single point optimization of the LS89 turbine using an adjoint optimization and defining the design variables within a CAD system. The advantage of including the CAD model in the design system is that higher level constraints can be imposed on the shape, allowing the optimized model or component to be manufactured. However, CAD-based approaches restrict the design space compared to node-based approaches where every node is free to move. In order to preserve a rich design space, we develop a methodology to refine the CAD model during the optimization and to create the best parameterization to use at each time. This study presents a methodology to progressively refine the design space, which combines parametric effectiveness with a differential evolutionary algorithm in order to create an optimal parameterization. In this manuscript, we show that by doing the parameterization at the CAD level, we can impose higher level constraints on the shape, such as the axial chord length, the trailing edge radius and G2 geometric continuity between the suction side and pressure side at the leading edge. Additionally, the adjoint sensitivities are filtered out and only smooth shapes are produced during the optimization process. The use of algorithmic differentiation for the CAD kernel and grid generator allows computing the grid sensitivities to machine accuracy and avoid the limited arithmetic precision and the truncation error of finite differences. Then, the parametric effectiveness is computed to rate the ability of a set of CAD design parameters to produce the design shape change dictated by the adjoint sensitivities. During the optimization process, the design space is progressively enlarged using the knot insertion algorithm which allows introducing new control points whilst preserving the initial shape. The position of the inserted knots is generally assumed. However, this assumption can hinder the creation of better parameterizations that would allow producing more localized shape changes where the adjoint sensitivities dictate. To address this, we propose using a differential evolutionary algorithm to maximize the parametric effectiveness by optimizing the location of the inserted knots. This allows the optimizer to gradually explore larger design spaces and to use an optimal CAD-based parameterization during the course of the optimization. The method is tested on the LS89 turbine cascade and large aerodynamic improvements in the entropy generation are achieved whilst keeping the exit flow angle fixed. The trailing edge and axial chord length, which are kept fixed as manufacturing constraints. The optimization results show that the multilevel optimizations were more efficient than the single level optimization, even though they used the same number of design variables at the end of the multilevel optimizations. Furthermore, the multilevel optimization where the parameterization is created using the optimal knot positions results in a more efficient strategy to reach a better optimum than the multilevel optimization where the position of the knots is arbitrarily assumed.

Keywords: adjoint, CAD, knots, multilevel, optimization, parametric effectiveness

Procedia PDF Downloads 89

Authors: Tarek Saadawi, Rosario Gennaro, Jonathan Akeley

Abstract:

There is rapidly growing demand for professionals to fill positions in Cybersecurity. This is recognized as a national priority both by government agencies and the private sector. Cybersecurity is a very wide technical area which encompasses all measures that can be taken in an electronic system to prevent criminal or unauthorized use of data and resources. This requires defending computers, servers, networks, and their users from any kind of malicious attacks. The need to address this challenge has been recognized globally but is particularly acute in the New York metropolitan area, home to some of the largest financial institutions in the world, which are prime targets of cyberattacks. In New York State alone, there are currently around 57,000 jobs in the Cybersecurity industry, with more than 23,000 unfilled positions. The Cybersecurity Program at City College is a collaboration between the Departments of Computer Science and Electrical Engineering. In Fall 2020, The City College of New York matriculated its first students in theCybersecurity Master of Science program. The program was designed to fill gaps in the previous offerings and evolved out ofan established partnership with Facebook on Cybersecurity Education. City College has designed a program where courses, curricula, syllabi, materials, labs, etc., are developed in cooperation and coordination with industry whenever possible, ensuring that students graduating from the program will have the necessary background to seamlessly segue into industry jobs. The Cybersecurity Program has created multiple pathways for prospective students to obtain the necessary prerequisites to apply in order to build a more diverse student population. The program can also be pursued on a part-time basis which makes it available to working professionals. Since City College’s Cybersecurity M.S. program was established to equip students with the advanced technical skills needed to thrive in a high-demand, rapidly-evolving field, it incorporates a range of pedagogical formats. From its outset, the Cybersecurity program has sought to provide both the theoretical foundations necessary for meaningful work in the field along with labs and applied learning projects aligned with skillsets required by industry. The efforts have involved collaboration with outside organizations and with visiting professors designing new courses on topics such as Adversarial AI, Data Privacy, Secure Cloud Computing, and blockchain. Although the program was initially designed with a single asynchronous course in the curriculum with the rest of the classes designed to be offered in-person, the advent of the COVID-19 pandemic necessitated a move to fullyonline learning. The shift to online learning has provided lessons for future development by providing examples of some inherent advantages to the medium in addition to its drawbacks. This talk will address the structure of the newly-implemented Cybersecurity Master’s Program and discuss the innovations, challenges, and possible future directions.

Keywords: cybersecurity, new york, city college, graduate degree, master of science

Procedia PDF Downloads 116

Authors: Niklas Ravn-Boess, Nainita Bhowmick, Takamitsu Hattori, Shohei Koide, Christopher Park, Dimitris Placantonakis

Abstract:

Background: Glioblastoma (GBM) is the most common and deadly primary brain malignancy in adults. Tumor propagation, brain invasion, and resistance to therapy critically depend on GBM stem-like cells (GSCs); however, the mechanisms that regulate GSC self-renewal are incompletely understood. Given the aggressiveness and poor prognosis of GBM, it is imperative to find biomarkers that could also translate into novel drug targets. Along these lines, we have identified a cell surface antigen, CD97 (ADGRE5), an adhesion G protein-coupled receptor (GPCR), that is expressed on GBM cells but is absent from non-neoplastic brain tissue. CD97 has been shown to promote invasiveness, angiogenesis, and migration in several human cancers, but its frequency of expression and functional role in regulating GBM growth and survival, and its potential as a therapeutic target has not been investigated. Design: We assessed CD97 mRNA and protein expression in patient derived GBM samples and cell lines using publicly available RNA-sequencing datasets and flow cytometry, respectively. To assess CD97 function, we generated shRNA lentiviral constructs that target a sequence in the CD97 extracellular domain (ECD). A scrambled shRNA (scr) with no predicted targets in the genome was used as a control. We evaluated CD97 shRNA lentivirally transduced GBM cells for Ki67, Annexin V, and DAPI. We also tested CD97 KD cells for their ability to self-renew using clonogenic tumorsphere formation assays. Further, we utilized synthetic Abs (sAbs) generated against the ECD of CD97 to test for potential antitumor effects using patient-derived GBM cell lines. Results: CD97 mRNA expression was expressed at high levels in all GBM samples available in the TCGA cohort. We found high levels of surface CD97 protein expression in 6/6 patient-derived GBM cell cultures, but not human neural stem cells. Flow cytometry confirmed downregulation of CD97 in CD97 shRNA lentivirally transduced cells. CD97 KD induced a significant reduction in cell growth in 3 independent GBM cell lines representing mesenchymal and proneural subtypes, which was accompanied by reduced (~20%) Ki67 staining and increased (~30%) apoptosis. Incubation of GBM cells with sAbs (20 ug/ ml) against the ECD of CD97 for 3 days induced GSC differentiation, as determined by the expression of GFAP and Tubulin. Using three unique GBM patient derived cultures, we found that CD97 KD attenuated the ability of GBM cells to initiate sphere formation by over 300 fold, consistent with an impairment in GSC self-renewal. Conclusion: Loss of CD97 expression in patient-derived GBM cells markedly decreases proliferation, induces cell death, and reduces tumorsphere formation. sAbs against the ECD of CD97 reduce tumorsphere formation, recapitulating the phenotype of CD97 KD, suggesting that sAbs that inhibit CD97 function exhibit anti-tumor activity. Collectively, these findings indicate that CD97 is necessary for the proliferation and survival of human GBM cells and identify CD97 as a promising therapeutically targetable vulnerability in GBM.

Keywords: adhesion GPCR, CD97, GBM stem cell, glioblastoma

Procedia PDF Downloads 104

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

Abstract:

The detection of curvilinear structures often plays an important role in the analysis of images. In particular, it is considered as a crucial step for the diagnosis of chronic respiratory diseases to localize the fissures in chest CT imagery where the lung is divided into five lobes by the fissures that are characterized by linear features in appearance. However, the characteristic linear features for the fissures are often shown to be subtle due to the high intensity variability, pathological deformation or image noise involved in the imaging procedure, which leads to the uncertainty in the quantification of anatomical or functional properties of the lung. Thus, it is desired to enhance the linear features present in the chest CT images so that the distinctiveness in the delineation of the lobe is improved. We propose a recursive diffusion process that prefers coherent features based on the analysis of structure tensor in an anisotropic manner. The local image features associated with certain scales and directions can be characterized by the eigenanalysis of the structure tensor that is often regularized via isotropic diffusion filters. However, the isotropic diffusion filters involved in the computation of the structure tensor generally blur geometrically significant structure of the features leading to the degradation of the characteristic power in the feature space. Thus, it is required to take into consideration of local structure of the feature in scale and direction when computing the structure tensor. We apply an anisotropic diffusion in consideration of scale and direction of the features in the computation of the structure tensor that subsequently provides the geometrical structure of the features by its eigenanalysis that determines the shape of the anisotropic diffusion kernel. The recursive application of the anisotropic diffusion with the kernel the shape of which is derived from the structure tensor leading to the anisotropic scale-space where the geometrical features are preserved via the eigenanalysis of the structure tensor computed from the diffused image. The recursive interaction between the anisotropic diffusion based on the geometry-driven kernels and the computation of the structure tensor that determines the shape of the diffusion kernels yields a scale-space where geometrical properties of the image structure are effectively characterized. We apply our recursive anisotropic diffusion algorithm to the detection of curvilinear structure in the chest CT imagery where the fissures present curvilinear features and define the boundary of lobes. It is shown that our algorithm yields precise detection of the fissures while overcoming the subtlety in defining the characteristic linear features. The quantitative evaluation demonstrates the robustness and effectiveness of the proposed algorithm for the detection of fissures in the chest CT in terms of the false positive and the true positive measures. The receiver operating characteristic curves indicate the potential of our algorithm as a segmentation tool in the clinical environment. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: anisotropic diffusion, chest CT imagery, chronic respiratory disease, curvilinear structure, fissure detection, structure tensor

Procedia PDF Downloads 208

Authors: Serhat Tüzün, Tufan Demirel

Abstract:

Decision Support Systems (DSS) have been investigated by researchers and technologists for more than 35 years. This paper analyses the developments in the architecture and software of these systems, provides a systematic analysis for different Web-based DSS approaches and Intelligent Decision-making Technologies (IDT), with the suggestion for future studies. Decision Support Systems literature begins with building model-oriented DSS in the late 1960s, theory developments in the 1970s, and the implementation of financial planning systems and Group DSS in the early and mid-80s. Then it documents the origins of Executive Information Systems, online analytic processing (OLAP) and Business Intelligence. The implementation of Web-based DSS occurred in the mid-1990s. With the beginning of the new millennia, intelligence is the main focus on DSS studies. Web-based technologies are having a major impact on design, development and implementation processes for all types of DSS. Web technologies are being utilized for the development of DSS tools by leading developers of decision support technologies. Major companies are encouraging its customers to port their DSS applications, such as data mining, customer relationship management (CRM) and OLAP systems, to a web-based environment. Similarly, real-time data fed from manufacturing plants are now helping floor managers make decisions regarding production adjustment to ensure that high-quality products are produced and delivered. Web-based DSS are being employed by organizations as decision aids for employees as well as customers. A common usage of Web-based DSS has been to assist customers configure product and service according to their needs. These systems allow individual customers to design their own products by choosing from a menu of attributes, components, prices and delivery options. The Intelligent Decision-making Technologies (IDT) domain is a fast growing area of research that integrates various aspects of computer science and information systems. This includes intelligent systems, intelligent technology, intelligent agents, artificial intelligence, fuzzy logic, neural networks, machine learning, knowledge discovery, computational intelligence, data science, big data analytics, inference engines, recommender systems or engines, and a variety of related disciplines. Innovative applications that emerge using IDT often have a significant impact on decision-making processes in government, industry, business, and academia in general. This is particularly pronounced in finance, accounting, healthcare, computer networks, real-time safety monitoring and crisis response systems. Similarly, IDT is commonly used in military decision-making systems, security, marketing, stock market prediction, and robotics. Even though lots of research studies have been conducted on Decision Support Systems, a systematic analysis on the subject is still missing. Because of this necessity, this paper has been prepared to search recent articles about the DSS. The literature has been deeply reviewed and by classifying previous studies according to their preferences, taxonomy for DSS has been prepared. With the aid of the taxonomic review and the recent developments over the subject, this study aims to analyze the future trends in decision support systems.

Keywords: decision support systems, intelligent decision-making, systematic analysis, taxonomic review

Procedia PDF Downloads 246

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 51

Authors: Tuyuan Cheng

Abstract:

As we age, many things become more difficult. Among the abilities are the linguistic and cognitive ones. Competing theories have shown that these two functions could diminish together or that one is selectively affected by the other. In other words, some proposes aging affects sentence production in the same way it affects sentence comprehension and other cognitive functions, while some argues it does not.To address this question, the current investigation is conducted into the critical aspect of sentences as well as cognitive abilities – the syntactic complexity and the number of perspective shifts being contained in the elicited production. Healthy non-pathological aging is often characterized by a cognitive and neural decline in a number of cognitive abilities. Although the language is assumed to be of the more stable domain, a variety of findings in the cognitive aging literature would suggest otherwise. Older adults often show deficits in language production and multiple aspects of comprehension. Nevertheless, while some age differences likely reflect cognitive decline, others might reflect changes in communicative goals, and some even display cognitive advantages. In the domain of language processing, research efforts have been made in tests that probed a variety of communicative abilities. In general, there exists a distinction: Comprehension seems to be selectively unaffected, while production does not. The current study raises a novel question and investigates whether aging affects the production of relative clauses (RCs) under the cognitive factor of perspective shifts. Based on Perspective Hypothesis (MacWhinney, 2000, 2005), our cognitive processes build upon a fundamental system of perspective-taking, and language provides a series of cues to facilitate the construction and shifting of perspectives. These cues include a wide variety of constructions, including RCs structures. In this regard, linguistic complexity can be determined by the number of perspective shifts, and the processing difficulties of RCs can be interpreted within the theory of perspective shifting. Two experiments were conducted to study language production under controlled conditions. In Experiment 1, older healthy participants were tested on standard measures of cognitive aging, including MMSE (Mini-Mental State Examination), ToMI-2 (a simplified Theory of Mind Inventory-2), and a perspective-shifting comprehension task programmed with E-Prime. The results were analyzed to examine if/how they are correlated with aging people’s subsequent production data. In Experiment 2, the production profile of differing RCs, SRC vs. ORC, were collected with healthy aging participants who perform a picture elicitation task. Variable containing 0, 1, or 2 perspective shifts were juxtaposed respectively to the pictures and counterbalanced presented for elicitation. In parallel, a controlled group of young adults were recruited to examine the linguistic and cognitive abilities in question. The results lead us to the discussion whetheraging affects RCs production in a manner determined by its semantic structure or the number of perspective shifts it contains or the status of participants’ mental understanding. The major findingsare: (1) Elders’ production on Chinese RCtypes did not display intrinsic difficulty asymmetry. (2) RC types (the linguistic structural features) and the cognitiveperspective shifts jointly play important roles in the elders’ RCproduction. (3) The production of RC may defy the aging in the case offlexibly preserved cognitive ability.

Keywords: cognition aging, perspective hypothesis, perspective shift, relative clauses, sentence complexity

Procedia PDF Downloads 90

Authors: Tatiana G. Smirnova, Stan G. Benjamin

Abstract:

Rapid Update Cycle (RUC) land surface model (LSM) was a land-surface component in several generations of operational weather prediction models at the National Center for Environment Prediction (NCEP) at the National Oceanic and Atmospheric Administration (NOAA). It was designed for short-range weather predictions with an emphasis on severe weather and originally was intentionally simple to avoid uncertainties from poorly known parameters. Nevertheless, the RUC LSM, when coupled with the hourly-assimilating atmospheric model, can produce a realistic evolution of time-varying soil moisture and temperature, as well as the evolution of snow cover on the ground surface. This result is possible only if the soil/vegetation/snow component of the coupled weather prediction model has sufficient skill to avoid long-term drift. RUC LSM was first implemented in the operational NCEP Rapid Update Cycle (RUC) weather model in 1998 and later in the Weather Research Forecasting Model (WRF)-based Rapid Refresh (RAP) and High-resolution Rapid Refresh (HRRR). Being available to the international WRF community, it was implemented in operational weather models in Austria, New Zealand, and Switzerland. Based on the feedback from the US weather service offices and the international WRF community and also based on our own validation, RUC LSM has matured over the years. Also, a sea-ice module was added to RUC LSM for surface predictions over the Arctic sea-ice. Other modifications include refinements to the snow model and a more accurate specification of albedo, roughness length, and other surface properties. At present, RUC LSM is being tested in the regional application of the Unified Forecast System (UFS). The next generation UFS-based regional Rapid Refresh FV3 Standalone (RRFS) model will replace operational RAP and HRRR at NCEP. Over time, RUC LSM participated in several international model intercomparison projects to verify its skill using observed atmospheric forcing. The ESM-SnowMIP was the last of these experiments focused on the verification of snow models for open and forested regions. The simulations were performed for ten sites located in different climatic zones of the world forced with observed atmospheric conditions. While most of the 26 participating models have more sophisticated snow parameterizations than in RUC, RUC LSM got a high ranking in simulations of both snow water equivalent and surface temperature. However, ESM-SnowMIP experiment also revealed some issues in the RUC snow model, which will be addressed in this paper. One of them is the treatment of grid cells partially covered with snow. RUC snow module computes energy and moisture budgets of snow-covered and snow-free areas separately by aggregating the solutions at the end of each time step. Such treatment elevates the importance of computing in the model snow cover fraction. Improvements to the original simplistic threshold-based approach have been implemented and tested both offline and in the coupled weather model. The detailed description of changes to the snow cover fraction and other modifications to RUC soil and snow parameterizations will be described in this paper.

Keywords: land-surface models, weather prediction, hydrology, boundary-layer processes

Procedia PDF Downloads 58

Authors: Delphine Ribes Lemay, Valentine Bernasconi, André Andrade, Lara DéFayes, Mathieu Salzmann, FréDéRic Kaplan, Nicolas Henchoz

Abstract:

Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum für Gestaltung of Zurich holds one of the biggest poster collections of the world from which 52’000 were digitised. In the process of building a digital installation to valorize the collection, one objective was to develop an algorithm capable of predicting the next poster to show according to the ones already displayed. The work presented here describes the steps to build an algorithm able to automatically create sequences of posters reflecting associations performed by curator and professional designers. The exposed challenge finds similarities with the domain of song playlist algorithms. Recently, artificial intelligence techniques and more specifically, deep-learning algorithms have been used to facilitate their generations. Promising results were found thanks to Recurrent Neural Networks (RNN) trained on manually generated playlist and paired with clusters of extracted features from songs. We used the same principles to create the proposed algorithm but applied to a challenging medium, posters. First, a convolutional autoencoder was trained to extract features of the posters. The 52’000 digital posters were used as a training set. Poster features were then clustered. Next, an RNN learned to predict the next cluster according to the previous ones. RNN training set was composed of poster sequences extracted from a collection of books from the Gestaltung Museum of Zurich dedicated to displaying posters. Finally, within the predicted cluster, the poster with the best proximity compared to the previous poster is selected. The mean square distance between features of posters was used to compute the proximity. To validate the predictive model, we compared sequences of 15 posters produced by our model to randomly and manually generated sequences. Manual sequences were created by a professional graphic designer. We asked 21 participants working as professional graphic designers to sort the sequences from the one with the strongest graphic line to the one with the weakest and to motivate their answer with a short description. The sequences produced by the designer were ranked first 60%, second 25% and third 15% of the time. The sequences produced by our predictive model were ranked first 25%, second 45% and third 30% of the time. The sequences produced randomly were ranked first 15%, second 29%, and third 55% of the time. Compared to designer sequences, and as reported by participants, model and random sequences lacked thematic continuity. According to the results, the proposed model is able to generate better poster sequencing compared to random sampling. Eventually, our algorithm is sometimes able to outperform a professional designer. As a next step, the proposed algorithm should include a possibility to create sequences according to a selected theme. To conclude, this work shows the potentiality of artificial intelligence techniques to learn from existing content and provide a tool to curate large sets of data, with a permanent renewal of the presented content.

Keywords: Artificial Intelligence, Digital Humanities, serendipity, design research

Procedia PDF Downloads 151

Authors: Amer Ait Sidhoum

Abstract:

Interest in sustainability has gained ground among practitioners, academics and policy-makers due to growing stakeholders’ awareness of environmental and social concerns. This is particularly true for agriculture. However, relatively little research has been conducted on the quantification of social sustainability and the contribution of social issues to the agricultural production efficiency. This research's main objective is to propose a method for evaluating prices of social outputs, more precisely shadow prices, by allowing for the stochastic nature of agricultural production that is to say for production uncertainty. In this article, the assessment of social outputs’ shadow prices is conducted within the methodological framework of nonparametric Data Envelopment Analysis (DEA). An output-oriented directional distance function (DDF) is implemented to represent the technology of a sample of Catalan arable crop farms and derive the efficiency scores the overall production technology of our sample is assumed to be the intersection of two different sub-technologies. The first sub-technology models the production of random desirable agricultural outputs, while the second sub-technology reflects the social outcomes from agricultural activities. Once a nonparametric production technology has been represented, the DDF primal approach can be used for efficiency measurement, while shadow prices are drawn from the dual representation of the DDF. Computing shadow prices is a method to assign an economic value to non-marketed social outcomes. Our research uses cross sectional, farm-level data collected in 2015 from a sample of 180 Catalan arable crop farms specialized in the production of cereals, oilseeds and protein (COP) crops. Our results suggest that our sample farms show high performance scores, from 85% for the bad state of nature to 88% for the normal and ideal crop growing conditions. This suggests that farm performance is increasing with an improvement in crop growth conditions. Results also show that average shadow prices of desirable state-contingent output and social outcomes for efficient and inefficient farms are positive, suggesting that the production of desirable marketable outputs and of non-marketable outputs makes a positive contribution to the farm production efficiency. Results also indicate that social outputs’ shadow prices are contingent upon the growing conditions. The shadow prices follow an upward trend as crop-growing conditions improve. This finding suggests that these efficient farms prefer to allocate more resources in the production of desirable outputs than of social outcomes. To our knowledge, this study represents the first attempt to compute shadow prices of social outcomes while accounting for the stochastic nature of the production technology. Our findings suggest that the decision-making process of the efficient farms in dealing with social issues are stochastic and strongly dependent on the growth conditions. This implies that policy-makers should adjust their instruments according to the stochastic environmental conditions. An optimal redistribution of rural development support, by increasing the public payment with the improvement in crop growth conditions, would likely enhance the effectiveness of public policies.

Keywords: data envelopment analysis, shadow prices, social sustainability, sustainable farming

Procedia PDF Downloads 96

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations of previous approaches, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with attention mechanism. In a previous work on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: transformers, generative ai, gene expression design, classification

Procedia PDF Downloads 30

Authors: Mohammad Alipour, Ekin Esen, Riza Kizilel

Abstract:

Lithium-ion batteries are a commonly used type of rechargeable batteries because of their high specific energy and specific power. With the growing popularity of electric vehicles and hybrid electric vehicles, increasing attentions have been paid to rechargeable Lithium-ion batteries. However, safety problems, high cost and poor performance in low ambient temperatures and high current rates, are big obstacles for commercial utilization of these batteries. By proper thermal management, most of the mentioned limitations could be eliminated. Temperature profile of the Li-ion cells has a significant role in the performance, safety, and cycle life of the battery. That is why little temperature gradient can lead to great loss in the performances of the battery packs. In recent years, numerous researchers are working on new techniques to imply a better thermal management on Li-ion batteries. Keeping the battery cells within an optimum range is the main objective of battery thermal management. Commercial Li-ion cells are composed of several electrochemical layers each consisting negative-current collector, negative electrode, separator, positive electrode, and positive current collector. However, many researchers have adopted a single-layer cell to save in computing time. Their hypothesis is that thermal conductivity of the layer elements is so high and heat transfer rate is so fast. Therefore, instead of several thin layers, they model the cell as one thick layer unit. In previous work, we showed that single-layer model is insufficient to simulate the thermal behavior and temperature nonuniformity of the high-capacity Li-ion cells. We also studied the effects of the number of layers on thermal behavior of the Li-ion batteries. In this work, first thermal and electrochemical behavior of the LiFePO₄ battery is modeled with 3D multilayer cell. The model is validated with the experimental measurements at different current rates and ambient temperatures. Real time heat generation rate is also studied at different discharge rates. Results showed non-uniform temperature distribution along the cell which requires thermal management system. Therefore, aluminum plates with mini-channel system were designed to control the temperature uniformity. Design parameters such as channel number and widths, inlet flow rate, and cooling fluids are optimized. As cooling fluids, water and air are compared. Pressure drop and velocity profiles inside the channels are illustrated. Both surface and internal temperature profiles of single cell and battery packs are investigated with and without cooling systems. Our results show that using optimized Mini-channel cooling plates effectively controls the temperature rise and uniformity of the single cells and battery packs. With increasing the inlet flow rate, cooling efficiency could be reached up to 60%.

Keywords: lithium ion battery, 3D multilayer model, mini-channel cooling plates, thermal management

Procedia PDF Downloads 134

Authors: Md. Abu Sufian, Robiqul Islam, Imam Hossain Shajid, Mahesh Hanumanthu, Jarasree Varadarajan, Md. Sipon Miah, Mingbo Niu

Abstract:

Coronary Heart Disease (CHD) remains a principal cause of global morbidity and mortality, characterized by atherosclerosis—the build-up of fatty deposits inside the arteries. The study introduces an innovative methodology that leverages cloud-based platforms like AWS Live Streaming and Artificial Intelligence (AI) to early detect and prevent CHD symptoms in web applications. By employing novel simulation processes and AI algorithms, this research aims to significantly mitigate the health and societal impacts of CHD. Methodology: This study introduces a novel simulation process alongside a multi-phased model development strategy. Initially, health-related data, including heart rate variability, blood pressure, lipid profiles, and ECG readings, were collected through user interactions with web-based applications as well as API Integration. The novel simulation process involved creating synthetic datasets that mimic early-stage CHD symptoms, allowing for the refinement and training of AI algorithms under controlled conditions without compromising patient privacy. AWS Live Streaming was utilized to capture real-time health data, which was then processed and analysed using advanced AI techniques. The novel aspect of our methodology lies in the simulation of CHD symptom progression, which provides a dynamic training environment for our AI models enhancing their predictive accuracy and robustness. Model Development: it developed a machine learning model trained on both real and simulated datasets. Incorporating a variety of algorithms including neural networks and ensemble learning model to identify early signs of CHD. The model's continuous learning mechanism allows it to evolve adapting to new data inputs and improving its predictive performance over time. Results and Findings: The deployment of our model yielded promising results. In the validation phase, it achieved an accuracy of 92% in predicting early CHD symptoms surpassing existing models. The precision and recall metrics stood at 89% and 91% respectively, indicating a high level of reliability in identifying at-risk individuals. These results underscore the effectiveness of combining live data streaming with AI in the early detection of CHD. Societal Implications: The implementation of cloud-based AI for CHD symptom detection represents a significant step forward in preventive healthcare. By facilitating early intervention, this approach has the potential to reduce the incidence of CHD-related complications, decrease healthcare costs, and improve patient outcomes. Moreover, the accessibility and scalability of cloud-based solutions democratize advanced health monitoring, making it available to a broader population. This study illustrates the transformative potential of integrating technology and healthcare, setting a new standard for the early detection and management of chronic diseases.

Keywords: coronary heart disease, cloud-based ai, machine learning, novel simulation techniques, early detection, preventive healthcare

Procedia PDF Downloads 25

Authors: R. Yuan, S. Sivasankaran, N. Dutta, K. Ebrahimi

Abstract:

This paper investigates the software capability and computer-aided engineering (CAE) method of modelling transient heat transfer process occurred in the vehicle underhood region during vehicle thermal soak phase. The heat retention from the soak period will be beneficial to the cold start with reduced friction loss for the second 14°C worldwide harmonized light-duty vehicle test procedure (WLTP) cycle, therefore provides benefits on both CO₂ emission reduction and fuel economy. When vehicle undergoes soak stage, the airflow and the associated convective heat transfer around and inside the engine bay is driven by the buoyancy effect. This effect along with thermal radiation and conduction are the key factors to the thermal simulation of the engine bay to obtain the accurate fluids and metal temperature cool-down trajectories and to predict the temperatures at the end of the soak period. Method development has been investigated in this study on a light-duty passenger vehicle using coupled aerodynamic-heat transfer thermal transient modelling method for the full vehicle under 9 hours of thermal soak. The 3D underhood flow dynamics were solved inherently transient by the Lattice-Boltzmann Method (LBM) method using the PowerFlow software. This was further coupled with heat transfer modelling using the PowerTHERM software provided by Exa Corporation. The particle-based LBM method was capable of accurately handling extremely complicated transient flow behavior on complex surface geometries. The detailed thermal modelling, including heat conduction, radiation, and buoyancy-driven heat convection, were integrated solved by PowerTHERM. The 9 hours cool-down period was simulated and compared with the vehicle testing data of the key fluid (coolant, oil) and metal temperatures. The developed CAE method was able to predict the cool-down behaviour of the key fluids and components in agreement with the experimental data and also visualised the air leakage paths and thermal retention around the engine bay. The cool-down trajectories of the key components obtained for the 9 hours thermal soak period provide vital information and a basis for the further development of reduced-order modelling studies in future work. This allows a fast-running model to be developed and be further imbedded with the holistic study of vehicle energy modelling and thermal management. It is also found that the buoyancy effect plays an important part at the first stage of the 9 hours soak and the flow development during this stage is vital to accurately predict the heat transfer coefficients for the heat retention modelling. The developed method has demonstrated the software integration for simulating buoyancy-driven heat transfer in a vehicle underhood region during thermal soak with satisfying accuracy and efficient computing time. The CAE method developed will allow integration of the design of engine encapsulations for improving fuel consumption and reducing CO₂ emissions in a timely and robust manner, aiding the development of low-carbon transport technologies.

Keywords: ATCT/WLTC driving cycle, buoyancy-driven heat transfer, CAE method, heat retention, underhood modeling, vehicle thermal soak

Procedia PDF Downloads 124

Authors: Riadh Zorgati, Thomas Triboulet

Abstract:

In quite diverse application areas such as astronomy, medical imaging, geophysics or nondestructive evaluation, many problems related to calibration, fitting or estimation of a large number of input parameters of a model from a small amount of output noisy data, can be cast as inverse problems. Due to noisy data corruption, insufficient data and model errors, most inverse problems are ill-posed in a Hadamard sense, i.e. existence, uniqueness and stability of the solution are not guaranteed. A wide class of inverse problems in physics relates to the Fredholm equation of the first kind. The ill-posedness of such inverse problem results, after discretization, in a very ill-conditioned linear system of equations, the condition number of the associated matrix can typically range from 109 to 1018. This condition number plays the role of an amplifier of uncertainties on data during inversion and then, renders the inverse problem difficult to handle numerically. Similar problems appear in other areas such as numerical optimization when using interior points algorithms for solving linear programs leads to face ill-conditioned systems of linear equations. Devising efficient solution approaches for such system of equations is therefore of great practical interest. Efficient iterative algorithms are proposed for solving a system of linear equations. The approach is based on a preconditioning of the initial matrix of the system with an approximation of a generalized inverse leading to a stochastic preconditioned matrix. This approach, valid for non-negative matrices, is first extended to hermitian, semi-definite positive matrices and then generalized to any complex rectangular matrices. The main results obtained are as follows: 1) We are able to build a generalized inverse of any complex rectangular matrix which satisfies the convergence condition requested in iterative algorithms for solving a system of linear equations. This completes the (short) list of generalized inverse having this property, after Kaczmarz and Cimmino matrices. Theoretical results on both the characterization of the type of generalized inverse obtained and the convergence are derived. 2) Thanks to its properties, this matrix can be efficiently used in different solving schemes as Richardson-Tanabe or preconditioned conjugate gradients. 3) By using Lp norms, we propose generalized Kaczmarz’s type matrices. We also show how Cimmino's matrix can be considered as a particular case consisting in choosing the Euclidian norm in an asymmetrical structure. 4) Regarding numerical results obtained on some pathological well-known test-cases (Hilbert, Nakasaka, …), some of the proposed algorithms are empirically shown to be more efficient on ill-conditioned problems and more robust to error propagation than the known classical techniques we have tested (Gauss, Moore-Penrose inverse, minimum residue, conjugate gradients, Kaczmarz, Cimmino). We end on a very early prospective application of our approach based on stochastic matrices aiming at computing some parameters (such as the extreme values, the mean, the variance, …) of the solution of a linear system prior to its resolution. Such an approach, if it were to be efficient, would be a source of information on the solution of a system of linear equations.

Keywords: conditioning, generalized inverse, linear system, norms, stochastic matrix

Procedia PDF Downloads 109

Authors: Ekaterina Zvorykina

Abstract:

Nowadays, Arctic and Antarctic regions are distinguished to be one of the most important strategic resources for global development. Nonetheless, living conditions in Arctic regions still demand certain improvements. As soon as the region is rarely populated, one of the main points of interest is health accommodation of the people, who migrate to Arctic region for permanent and shift work. At Arctic and Antarctic latitudes, personnel face polar day and polar night conditions during the time of the year. It means that they are deprived of natural sunlight in winter season and have continuous daylight in summer. Firstly, the change in light intensity during 24-hours period due to migration affects circadian rhythms. Moreover, the controlled artificial light in winter is also an issue. The results of the recent studies on night shift medical professionals, who were exposed to permanent artificial light, have already demonstrated higher risks in cancer, depression, Alzheimer disease. Moreover, people exposed to frequent time zones change are also subjected to higher risks of heart attack and cancer. Thus, our main goals are to understand how high latitude work and living conditions can affect human health and how it can be prevented. In our study, we analyze molecular and cellular factors, which play important role in circadian rhythm change and distinguish main risk groups in people, migrating to high latitudes. The main well-studied index of circadian timing is melatonin or its metabolite 6-sulfatoxymelatonin. In low light intensity melatonin synthesis is disturbed and as a result human organism requires more time for sleep, which is still disregarded when it comes to working time organization. Lack of melatonin also causes shortage in serotonin production, which leads to higher depression risk. Melatonin is also known to inhibit oncogenes and increase apoptosis level in cells, the main factors for tumor growth, as well as circadian clock genes (for example Per2). Thus, people who work in high latitudes can be distinguished as a risk group for cancer diseases and demand more attention. Clock/Clock genes, known to be one of the main circadian clock regulators, decrease sensitivity of hypothalamus to estrogen and decrease glucose sensibility, which leads to premature aging and oestrous cycle disruption. Permanent light exposure also leads to accumulation superoxide dismutase and oxidative stress, which is one of the main factors for early dementia and Alzheimer disease. We propose a new screening system adjusted for people, migrating from middle to high latitudes and accommodation therapy. Screening is focused on melatonin and estrogen levels, sleep deprivation and neural disorders, depression level, cancer risks and heart and vascular disorders. Accommodation therapy includes different types artificial light exposure, additional melatonin and neuroprotectors. Preventive procedures can lead to increase of migration intensity to high latitudes and, as a result, the prosperity of Arctic region.

Keywords: circadian rhythm, high latitudes, melatonin, neuroprotectors

Procedia PDF Downloads 123

Authors: Merve Begum Terzi, Orhan Arikan, Adnan Abaci, Mustafa Candemir

Abstract:

Acute myocardial infarction is a major cause of death in the world. Therefore, its fast and reliable diagnosis is a major clinical need. ECG is the most important diagnostic methodology which is used to make decisions about the management of the cardiovascular diseases. In patients with acute myocardial ischemia, temporary chest pains together with changes in ST segment and T wave of ECG occur shortly before the start of myocardial infarction. In this study, a technique which detects changes in ST/T sections of ECG is developed for the early diagnosis of acute myocardial ischemia. For this purpose, a database of real ECG recordings that contains a set of records from 75 patients presenting symptoms of chest pain who underwent elective percutaneous coronary intervention (PCI) is constituted. 12-lead ECG’s of the patients were recorded before and during the PCI procedure. Two ECG epochs, which are the pre-inflation ECG which is acquired before any catheter insertion and the occlusion ECG which is acquired during balloon inflation, are analyzed for each patient. By using pre-inflation and occlusion recordings, ECG features that are critical in the detection of acute myocardial ischemia are identified and the most discriminative features for the detection of acute myocardial ischemia are extracted. A classification technique based on support vector machine (SVM) approach operating with linear and radial basis function (RBF) kernels to detect ischemic events by using ST-T derived joint features from non-ischemic and ischemic states of the patients is developed. The dataset is randomly divided into training and testing sets and the training set is used to optimize SVM hyperparameters by using grid-search method and 10fold cross-validation. SVMs are designed specifically for each patient by tuning the kernel parameters in order to obtain the optimal classification performance results. As a result of implementing the developed classification technique to real ECG recordings, it is shown that the proposed technique provides highly reliable detections of the anomalies in ECG signals. Furthermore, to develop a detection technique that can be used in the absence of ECG recording obtained during healthy stage, the detection of acute myocardial ischemia based on ECG recordings of the patients obtained during ischemia is also investigated. For this purpose, a Gaussian mixture model (GMM) is used to represent the joint pdf of the most discriminating ECG features of myocardial ischemia. Then, a Neyman-Pearson type of approach is developed to provide detection of outliers that would correspond to acute myocardial ischemia. Neyman – Pearson decision strategy is used by computing the average log likelihood values of ECG segments and comparing them with a range of different threshold values. For different discrimination threshold values and number of ECG segments, probability of detection and probability of false alarm values are computed, and the corresponding ROC curves are obtained. The results indicate that increasing number of ECG segments provide higher performance for GMM based classification. Moreover, the comparison between the performances of SVM and GMM based classification showed that SVM provides higher classification performance results over ECG recordings of considerable number of patients.

Keywords: ECG classification, Gaussian mixture model, Neyman–Pearson approach, support vector machine

Procedia PDF Downloads 120

Authors: Nilki Upathissa, Torin Wirasinghe

Abstract:

This solution addresses the challenges faced by traditional bookstores and the limitations of digital media, striking a balance between the tactile experience of printed books and the convenience of modern technology. The book exchange system offers a sustainable alternative, empowering users to access a diverse range of books while promoting community engagement. The user-friendly interfaces incorporated into the book exchange system ensure a seamless and enjoyable experience for users. Intuitive features for book management, search, and messaging facilitate effortless exchanges and interactions between users. By streamlining the process, the system encourages readers to explore new books aligned with their interests, enhancing the overall reading experience. Central to the system's success is the hybrid recommendation engine, which leverages advanced technologies such as Long Short-Term Memory (LSTM) models. By analyzing user input, the engine accurately predicts genre preferences, enabling personalized book recommendations. The hybrid approach integrates multiple technologies, including user interfaces, machine learning models, and recommendation algorithms, to ensure the accuracy and diversity of the recommendations. The evaluation of the book exchange system with the hybrid recommendation engine demonstrated exceptional performance across key metrics. The high accuracy score of 0.97 highlights the system's ability to provide relevant recommendations, enhancing users' chances of discovering books that resonate with their interests. The commendable precision, recall, and F1score scores further validate the system's efficacy in offering appropriate book suggestions. Additionally, the curve classifications substantiate the system's effectiveness in distinguishing positive and negative recommendations. This metric provides confidence in the system's ability to navigate the vast landscape of book choices and deliver recommendations that align with users' preferences. Furthermore, the implementation of this book exchange system with a hybrid recommendation engine has the potential to revolutionize the way readers interact with printed books. By facilitating book exchanges and providing personalized recommendations, the system encourages a sense of community and exploration within the reading community. Moreover, the emphasis on sustainability aligns with the growing global consciousness towards eco-friendly practices. With its robust technical approach and promising evaluation results, this solution paves the way for a more inclusive, accessible, and enjoyable reading experience for book lovers worldwide. In conclusion, the developed book exchange system with a hybrid recommendation engine represents a progressive solution to the challenges faced by traditional bookstores and the limitations of digital media. By promoting sustainability, widening access to printed books, and fostering engagement with reading, this system addresses the evolving needs of book enthusiasts. The integration of user-friendly interfaces, advanced machine learning models, and recommendation algorithms ensure accurate and diverse book recommendations, enriching the reading experience for users.

Keywords: recommendation systems, hybrid recommendation systems, machine learning, data science, long short-term memory, recurrent neural network

Procedia PDF Downloads 56

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of the flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on the spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts, as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with an attention mechanism. In previous works on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work, with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on the presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: machine learning, classification and regression, gene circuit design, bidirectional transformers

Procedia PDF Downloads 33