Search results for: deep eutectic systems

Authors: Achim Kampker, Peter Burggräf, Moritz Krunke, Hanno Voet

Abstract:

As a reaction to current challenges in factory planning, many companies think about introducing factory standards to lower planning times and decrease planning costs. If these factory standards are set-up with a high level of modularity, they are defined as modular factory systems. This paper deals with the main current problems in the application of modular factory systems in practice and presents a solution approach with its basic models. The methodology is based on methods from factory planning but also uses the tools of other disciplines like product development or technology management to deal with the high complexity, which the development of modular factory systems implies. The four basic models that such a methodology has to contain are introduced and pointed out.

Keywords: factory planning, modular factory systems, factory standards, cost-benefit analysis

Procedia PDF Downloads 592

Authors: Siddarth Kannan

Abstract:

Objectives: Deep Brain Stimulation (DBS) and Motor Cortex stimulation (MCS) are innovative interventions in order to treat various neuropathic pain disorders such as post-stroke pain. While each treatment has a varying degree of success in managing pain, comparative analysis has not yet been performed, and the success rates of these techniques using validated, objective pain scores have not been synthesised. The aim of this study was to compare the effect of pain relief offered by MCS and DBS on patients with post-stroke pain and to assess if either of these procedures offered better results. Methods: A systematic review and meta-analysis were conducted in accordance with PRISMA guidelines (PROSPEROID CRD42021277542). Three databases were searched, and articles published from 2000 to June 2023 were included (last search date 25 June 2023). Meta-analysis was performed using random effects models. We evaluated the performance of DBS or MCS by assessing studies that reported pain relief using the Visual Analogue Scale (VAS). Data analysis of descriptive statistics was performed using SPSS (Version 27; IBM; Armonk; NY; USA). R statistics (Rstudio Version 4.0.1) was used to perform meta-analysis. Results: Of the 478 articles identified, 27 were included in the analysis (232 patients- 117 DBS & 115 MCS). The pooled number of patients who improved after DBS was 0.68 (95% CI, 0.57-0.77, I2=36%). The pooled number of patients who improved after MCS was 0.72 (95% CI, 0.62-0.80, I2=59%). Further sensitivity analysis was done to include only studies with a minimum of 5 patients in order to assess if there was any impact on the overall results. Nine studies each for DBS and MCS met these criteria. There seemed to be no significant difference in results. Conclusions: The use of surgical interventions such as DBS and MCS is an upcoming field for the treatment of post-stroke pain, with limited studies exploring and comparing these two techniques. While our study shows that MCS might be a slightly better treatment option, further research would need to be done in order to determine the appropriate surgical intervention for post-stroke pain.

Keywords: post-stroke pain, deep brain stimulation, motor cortex stimulation, pain relief

Procedia PDF Downloads 138

Authors: Edemealem Desalegn Kingawa, Kafte Tasew Timkete, Mekashaw Girmaw Abebe, Terefe Feyisa, Abiyot Bitew Mihretie, Senait Teklemarkos Haile

Abstract:

Currently, hate speech is a growing challenge for society, individuals, policymakers, and researchers, as social media platforms make it easy to anonymously create and grow online friends and followers and provide an online forum for debate about specific issues of community life, culture, politics, and others. Despite this, research on identifying and detecting hate speech is not satisfactory performance, and this is why future research on this issue is constantly called for. This paper provides a systematic review of the literature in this field, with a focus on approaches like word embedding techniques, machine learning, deep learning technologies, hate speech terminology, and other state-of-the-art technologies with challenges. In this paper, we have made a systematic review of the last six years of literature from Research Gate and Google Scholar. Furthermore, limitations, along with algorithm selection and use challenges, data collection, and cleaning challenges, and future research directions, are discussed in detail.

Keywords: Amharic hate speech, deep learning approach, hate speech detection review, Afaan Oromo hate speech detection

Procedia PDF Downloads 174

Authors: A. Soni, D. R. Mishra, D. K. Koul

Abstract:

α-Al2O3:C has been reported to have deeper traps at 600°C and 900°C respectively. These traps have been reported to accessed at relatively earlier temperatures (122 and 322 °C respectively) using thermally assisted OSL (TA-OSL). In this work, the dose response α-Al2O3:C was studied in the dose range of 10Gy to 10kGy for its application in food irradiation in low ( upto 1kGy) and medium(1 to 10kGy) dose range. The TOL (Thermo-optically stimulated luminescence) measurements were carried out on RisØ TL/OSL, TL-DA-15 system having a blue light-emitting diodes (λ=470 ±30nm) stimulation source with power level set at the 90% of the maximum stimulation intensity for the blue LEDs (40 mW/cm2). The observations were carried on commercial α-Al2O3:C phosphor. The TOL experiments were carried out with number of active channel (300) and inactive channel (1). Using these settings, the sample is subjected to linear thermal heating and constant optical stimulation. The detection filter used in all observations was a Hoya U-340 (Ip ~ 340 nm, FWHM ~ 80 nm). Irradiation of the samples was carried out using a 90Sr/90Y β-source housed in the system. A heating rate of 2 °C/s was preferred in TL measurements so as to reduce the temperature lag between the heater plate and the samples. To study the dose response of deep traps of α-Al2O3:C, samples were irradiated with various dose ranging from 10 Gy to 10 kGy. For each set of dose, three samples were irradiated. In order to record the TA-OSL, initially TL was recorded up to a temperature of 400°C, to deplete the signal due to 185°C main dosimetry TL peak in α-Al2O3:C, which is also associated with the basic OSL traps. After taking TL readout, the sample was subsequently subjected to TOL measurement. As a result, two well-defined TA-OSL peaks at 121°C and at 232°C occur in time as well as temperature domain which are different from the main dosimetric TL peak which occurs at ~ 185°C. The linearity of the integrated TOL signal has been measured as a function of absorbed dose and found to be linear upto 10kGy. Thus, it can be used for low and intermediate dose range of for its application in food irradiation. The deep energy level defects of α-Al2O3:C phosphor can be accessed using TOL section of RisØ reader system.

Keywords: α-Al2O3:C, deep traps, food irradiation, TA-OSL

Procedia PDF Downloads 298

Authors: Hailah Alballaa, Azeddine Chikh

Abstract:

Several challenges impede the adoption of Recommender Systems for Technology Enhanced Learning (TEL): to collect and identify possible datasets; to select between different recommender approaches; to evaluate their performances. The aim is of this paper is twofold: First, it aims to introduce a survey on the most significant work in this area. Second, it aims at identifying possible research directions.

Keywords: datasets, content-based filtering, recommender systems, TEL

Procedia PDF Downloads 243

Authors: Sairoel Amertet, Girma Gebresenbet

Abstract:

Smart mechatronics systems in agriculture can be traced back to the mid-1980s, when research into automated fruit harvesting systems began in Japan, Europe, and the United States. Since then, impressive advances have been made in smart mechatronics systems. Furthermore, smart mechatronics systems are promising areas, and as a result, we were intrigued to learn more about them. Consequently, the purpose of this study was to examine the smart mechatronic systems that have been applied to agricultural areas so far, with inspiration from the smart mechatronic system in other sectors. To get an overview of the current state of the art, benefits and drawbacks of smart mechatronics systems, various approaches were investigated. Moreover, smart mechatronic modules and various networks applied in agriculture processing were examined. Finally, we explored how the data retrieved using the one-way analysis of variance related to each other. The result showed that there were strongly related keywords for different journals. With the virtually limited use of sophisticated mechatronics in the agricultural industry and, at the same time, the low production rate, the demand for food security has fallen dramatically. Therefore, the application of smart mechatronics systems in agricultural sectors would be taken into consideration in order to overcome these issues.

Keywords: mechatronics, robotic, robotic system, automation, agriculture mechanism

Procedia PDF Downloads 79

Authors: Monty Vacura

Abstract:

Hamilton’s Rule is a universal law of biology expressed in protists, plants and animals. When applied to human populations, this model explains: 1) Origin of religion in society as a biopsychological need naturally selected to increase population size; 2) Instincts of racism expressed through intergroup competition; 3) Simultaneous selection for human cooperation and conflict, love and hate; 4) Places Dawkins’s selfish gene as the r, relationship variable; 5) Flipping the equation variable themes (close relationship to distant relationship, and benefit to threat) the new equation can now be used to identify the offensive and defensive sides of conflict; 6) Connection between sporting events and instinctive social messaging for stimulating offensive and defensive responses; 6) Pathway to reduce human sacrifice through manipulation of variables. This paper discusses the deep psychological influences of Hamilton’s Rule. Suggestions are provided to reduce human deaths via our instinctive sacrificial behavior, by consciously monitoring Hamilton’s Rule variables highlighted throughout our media outlets.

Keywords: psychology, Hamilton’s rule, evolution, human instincts

Procedia PDF Downloads 49

Authors: Gao Youtao, Zhao Tanran, Jin Bingyu, Xu Bo

Abstract:

Global navigation satellite system(GNSS) can deliver navigation information for spacecraft orbiting on low-Earth orbits and medium Earth orbits. However, the GNSS cannot navigate the spacecraft on high-Earth orbit or deep space probes effectively. With the deep space exploration becoming a hot spot of aerospace, the demand for a deep space satellite navigation system is becoming increasingly prominent. Many researchers discussed the feasibility and performance of a satellite navigation system on periodic orbits around the Earth-Moon libration points which can be called Lagrangian point satellite navigation system. Autonomous orbit determination (AOD) is an important performance for the Lagrangian point satellite navigation system. With this ability, the Lagrangian point satellite navigation system can reduce the dependency on ground stations. AOD also can greatly reduce total system cost and assure mission continuity. As the elliptical restricted three-body problem can describe the Earth-Moon system more accurately than the circular restricted three-body problem, we study the autonomous orbit determination of Lagrangian navigation constellation using only crosslink range based on elliptical restricted three body problem. Extended Kalman filter is used in the autonomous orbit determination. In order to compare the autonomous orbit determination results based on elliptical restricted three-body problem to the results of autonomous orbit determination based on circular restricted three-body problem, we give the autonomous orbit determination position errors of a navigation constellation include four satellites based on the circular restricted three-body problem. The simulation result shows that the Lagrangian navigation constellation can achieve long-term precise autonomous orbit determination using only crosslink range. In addition, the type of the libration point orbit will influence the autonomous orbit determination accuracy.

Keywords: extended Kalman filter, autonomous orbit determination, quasi-periodic orbit, navigation constellation

Procedia PDF Downloads 280

Authors: Şakir Bingöl, Abdullah Emre Aydemir, Abdullah Saado, Ahmet Akıl, Elif Canbaz, Feyza Nur Bulgurcu, Gizem Uzun, Günsu Bilge Dal, Muhammedcan Pirinççi

Abstract:

Smart contracts, which can be applied in many different areas, from financial applications to the internet of things, come to the fore with their security, low cost, and self-executing features. In this paper, it is focused on peer-to-peer (P2P) energy trading and the implementation of the smart contract on the Ethereum blockchain. It is assumed a microgrid consists of consumers and prosumers that can produce solar and wind energy. The proposed architecture is a system where the prosumer makes the purchase or sale request in the smart contract and the maximum price obtained through the distribution system operator (DSO) by forecasting. It is aimed to forecast the hourly maximum unit price of energy by using deep learning instead of a fixed pricing. In this way, it will make the system more reliable as there will be more dynamic and accurate pricing. For this purpose, Istanbul's energy generation, energy consumption and market clearing price data were used. The consistency of the available data and forecasting results is observed and discussed with graphs.

Keywords: energy trading smart contract, deep learning, microgrid, forecasting, Ethereum, peer to peer

Procedia PDF Downloads 136

Authors: Slah Alsaleh

Abstract:

In the recent years and with popularity of internet and technology, e-learning became a major part of majority of education systems. One of the advantages the e-learning systems provide is the large amount of information available about the students' behavior while communicating with the e-learning system. Such information is very rich and it can be used to improve the capability and efficiency of e-learning systems. This paper discusses how e-learning can benefit from implicit data in different ways including; creating homogeneous groups of student, evaluating students' learning, creating behavior profiles for students and identifying the students through their behaviors.

Keywords: e-learning, implicit data, user behavior, data mining

Procedia PDF Downloads 305

Authors: Jay Xiong, Li Lin

Abstract:

Existing software modeling and visualization approaches using UML are outdated, which are outcomes of reductionism and the superposition principle that the whole of a system is the sum of its parts, so that with them all tasks of software modeling and visualization are performed linearly, partially, and locally. This paper introduces revolutionary solutions for modeling and visualization of complex software systems, which make complex software systems much easy to understand, test, and maintain. The solutions are based on complexity science, offering holistic, automatic, dynamic, virtual, and executable approaches about thousand times more efficient than the traditional ones.

Keywords: complex systems, software maintenance, software modeling, software visualization

Procedia PDF Downloads 399

Authors: Romisaa Ali

Abstract:

This paper presents a comparison between twin-delayed Deep Deterministic Policy Gradient (TD3) and Soft Actor-Critic (SAC) reinforcement learning algorithms in the context of training robust navigation policies for Jackal robots. By leveraging an open-source framework and custom motion control environments, the study evaluates the performance, robustness, and transferability of the trained policies across a range of scenarios. The primary focus of the experiments is to assess the training process, the adaptability of the algorithms, and the robot’s ability to navigate in previously unseen environments. Moreover, the paper examines the influence of varying environmental complexities on the learning process and the generalization capabilities of the resulting policies. The results of this study aim to inform and guide the development of more efficient and practical reinforcement learning-based navigation policies for Jackal robots in real-world scenarios.

Keywords: Jackal robot environments, reinforcement learning, TD3, SAC, robust navigation, transferability, custom environment

Procedia PDF Downloads 100

Authors: Omer Cahana, Ofer Levi, Maya Herman

Abstract:

Magnetic Resonance Imaging (MRI) is a lengthy medical scan that stems from a long acquisition time. Its length is mainly due to the traditional sampling theorem, which defines a lower boundary for sampling. However, it is still possible to accelerate the scan by using a different approach such as Compress Sensing (CS) or Parallel Imaging (PI). These two complementary methods can be combined to achieve a faster scan with high-fidelity imaging. To achieve that, two conditions must be satisfied: i) the signal must be sparse under a known transform domain, and ii) the sampling method must be incoherent. In addition, a nonlinear reconstruction algorithm must be applied to recover the signal. While the rapid advances in Deep Learning (DL) have had tremendous successes in various computer vision tasks, the field of MRI reconstruction is still in its early stages. In this paper, we present an end-to-end method for MRI reconstruction from k-space to image. Our method contains two parts. The first is sensitivity map estimation (SME), which is a small yet effective network that can easily be extended to a variable number of coils. The second is reconstruction, which is a top-down architecture with lateral connections developed for building high-level refinement at all scales. Our method holds the state-of-art fastMRI benchmark, which is the largest, most diverse benchmark for MRI reconstruction.

Keywords: magnetic resonance imaging, image reconstruction, pyramid network, deep learning

Procedia PDF Downloads 90

Authors: Shubham Bhonde, Nekzad Doctor, Shashwat Gawande

Abstract:

For the use and the import of Keys and ID Transmitter as well as Body Control Modules with radio transmission in a lot of countries, homologation is required. Final deliverables in homologation of the product are certificates. In considering the world of homologation, there are approximately 200 certificates per product, with most of the certificates in local languages. It is challenging to manually investigate each certificate and extract relevant data from the certificate, such as expiry date, approval date, etc. It is most important to get accurate data from the certificate as inaccuracy may lead to missing re-homologation of certificates that will result in an incompliance situation. There is a scope of automation in reading the certificate data in the field of homologation. We are using deep learning as a tool for automation. We have first trained a model using machine learning by providing all country's basic data. We have trained this model only once. We trained the model by feeding pdf and jpg files using the ETL process. Eventually, that trained model will give more accurate results later. As an outcome, we will get the expiry date and approval date of the certificate with a single click. This will eventually help to implement automation features on a broader level in the database where certificates are stored. This automation will help to minimize human error to almost negligible.

Keywords: homologation, re-homologation, data science, deep learning, machine learning, ETL (extract transform loading)

Procedia PDF Downloads 160

Authors: Irtaza M. Syed, Kaameran Raahemifar

Abstract:

This paper presents comparative analysis of photovoltaic systems (PVS) and proposes practical techniques to improve operational efficiency of the PVS. The best engineering and construction practices for PVS are identified and field oriented recommendation are made. Comparative analysis of central and string inverter based, as well as 600 and 1000 VDC PVS are performed. In addition, direct current (DC) and alternating current (AC) photovoltaic (PV) module based systems are compared. Comparison shows that 1000 V DC String Inverters based PVS is the best choice.

Keywords: photovoltaic module, photovoltaic systems, operational efficiency improvement, comparative analysis

Procedia PDF Downloads 483

Authors: Omer Cahana, Maya Herman, Ofer Levi

Abstract:

Magnetic resonance imaging (MRI) is a long medical scan that stems from a long acquisition time. This length is mainly due to the traditional sampling theorem, which defines a lower boundary for sampling. However, it is still possible to accelerate the scan by using a different approach, such as compress sensing (CS) or parallel imaging (PI). These two complementary methods can be combined to achieve a faster scan with high-fidelity imaging. In order to achieve that, two properties have to exist: i) the signal must be sparse under a known transform domain, ii) the sampling method must be incoherent. In addition, a nonlinear reconstruction algorithm needs to be applied to recover the signal. While the rapid advance in the deep learning (DL) field, which has demonstrated tremendous successes in various computer vision task’s, the field of MRI reconstruction is still in an early stage. In this paper, we present an extension of the state-of-the-art model in MRI reconstruction -VarNet. We utilize VarNet by using dilated convolution in different scales, which extends the receptive field to capture more contextual information. Moreover, we simplified the sensitivity map estimation (SME), for it holds many unnecessary layers for this task. Those improvements have shown significant decreases in computation costs as well as higher accuracy.

Keywords: MRI, deep learning, variational network, computer vision, compress sensing

Procedia PDF Downloads 158

Authors: A. Javorova, M. Matusova, K. Velisek

Abstract:

The article summarizes the experience of laboratory technical subjects teaching methodologies using a number of software products. The main aim is to modernize the teaching process in accordance with the requirements of today - based on information technology. Increasing of the study attractiveness and effectiveness is due to the introduction of CA technologies in the learning process. This paper discussed the areas where individual CA system used. Environment using CA systems are briefly presented in each chapter.

Keywords: education, CA systems, simulation, technology

Procedia PDF Downloads 395

Authors: Nicole Virgili, Marco Utili

Abstract:

The design of the Breeding Blanket in Tokamak fusion energy systems has to guarantee sufficient availability in addition to its functions, that are, tritium breeding self-sufficiency, power extraction and shielding (the magnets and the VV). All these function in the presence of extremely harsh operating conditions in terms of heat flux and neutron dose as well as chemical environment of the coolant and breeder that challenge structural materials (structural resistance and corrosion resistance). The movement and activation of fluids from the BB to the Ex-vessel components in a fusion power plant have an important radiological consideration because flowing material can carry radioactivity to safety-critical areas. This includes gamma-ray emission from activated fluid and activated corrosion products, and secondary activation resulting from neutron emission, with implication for the safety of maintenance personnel and damage to electrical and electronic equipment. In addition to the PbLi breeder activation, it is important to evaluate the contribution due to the activated corrosion products (ACPs) dissolved in the lead-lithium eutectic alloy, at different concentration levels. Therefore, the purpose of the study project is to evaluate the PbLi activity utilizing the FISPACT II inventory code. Emphasis is given on how the design of the EU-DEMO WCLL, and potential recycling of the breeder material will be impacted by the activation of PbLi and the associated active corrosion products (ACPs). For this scope the following Computational Tools, Data and Geometry have been considered: • Neutron source: EU-DEMO neutron flux < 1014/cm2/s • Neutron flux distribution in equatorial breeding blanket module (BBM) #13 in the WCLL BB outboard central zone, which is the most activated zone, with the aim to introduce a conservative component utilizing MNCP6. • The recommended geometry model: 2017 EU DEMO CAD model. • Blanket Module Material Specifications (Composition) • Activation calculations for different ACP concentration levels in the PbLi breeder, with a given chemistry in stationary equilibrium conditions, using FISPACT II code. Results suggest that there should be a waiting time of about 10 years from the shut-down (SD) to be able to safely manipulate the PbLi for recycling operations with simple shielding requirements. The dose rate is mainly given by the PbLi and the ACP concentration (x1 or x 100) does not shift the result. In conclusion, the results show that there is no impact on PbLi activation due to ACPs levels.

Keywords: activation, corrosion products, recycling, WCLL BB., PbLi

Procedia PDF Downloads 129

Authors: Uvais Qidwai, Amor Moursi, Mohamed Tahar, Malek Hamad, Hamad Alansi

Abstract:

This paper focuses on the development and implementation of an advanced plant health monitoring system with an AI backbone and IoT sensory network. Our approach involves addressing the critical environmental factors essential for preserving a plant’s well-being, including air temperature, soil moisture, soil temperature, soil conductivity, pH, water levels, and humidity, as well as the presence of essential nutrients like nitrogen, phosphorus, and potassium. Central to our methodology is the utilization of computer vision technology, particularly a night vision camera. The captured data is then compared against a reference database containing different health statuses. This comparative analysis is implemented using an AI deep learning model, which enables us to generate accurate assessments of plant health status. By combining the AI-based decision-making approach, our system aims to provide precise and timely insights into the overall health and well-being of plants, offering a valuable tool for effective plant care and management.

Keywords: deep learning image model, IoT sensing, cloud-based analysis, remote monitoring app, computer vision, fuzzy control

Procedia PDF Downloads 53

Authors: Anton Hristozov, Eric Matson, Eric Dietz, Marcus Rogers

Abstract:

Components are heavily used in many software systems, including robotics systems. The growth of sophistication and diversity of new capabilities for robotic systems presents new challenges to their architectures. Their complexity is growing exponentially with the advent of AI, smart sensors, and the complex tasks they have to accomplish. Such complexity requires a more rigorous approach to the creation, use, and interoperability of software components. The issue is exacerbated because robotic systems are becoming more and more reliant on third-party components for certain functions. In order to achieve this kind of interoperability, including dynamic component replacement, we need a way to standardize their interfaces. A formal approach is desperately needed to specify what an interface of a robotic software component should contain. This study performs an analysis of the issue and presents a universal and generic approach to standardizing component interfaces for robotic systems. Our approach is inspired by well-established robotic architectures such as ROS, PX4, and Ardupilot. The study is also applicable to other software systems that share similar characteristics with robotic systems. We consider the use of JSON or Domain Specific Languages (DSL) development with tools such as Antlr and automatic code and configuration file generation for frameworks such as ROS and PX4. A case study with ROS2 is presented as a proof of concept for the proposed methodology.

Keywords: CPS, robots, software architecture, interface, ROS, autopilot

Procedia PDF Downloads 90

Authors: Bliss Singhal

Abstract:

Epilepsy is a prevalent neurological disorder affecting approximately 50 million individuals worldwide and 1.2 million Americans. There exist millions of pediatric patients with intractable epilepsy, a condition in which seizures fail to come under control. The occurrence of seizures can result in physical injury, disorientation, unconsciousness, and additional symptoms that could impede children's ability to participate in everyday tasks. Predicting seizures can help parents and healthcare providers take precautions, prevent risky situations, and mentally prepare children to minimize anxiety and nervousness associated with the uncertainty of a seizure. This research proposes a comprehensive framework to predict seizures in pediatric patients by evaluating machine learning algorithms on unimodal neuroimaging data consisting of electroencephalogram signals. The bandpass filtering and independent component analysis proved to be effective in reducing the noise and artifacts from the dataset. Various machine learning algorithms’ performance is evaluated on important metrics such as accuracy, precision, specificity, sensitivity, F1 score and MCC. The results show that the deep learning algorithms are more successful in predicting seizures than logistic Regression, and k nearest neighbors. The recurrent neural network (RNN) gave the highest precision and F1 Score, long short-term memory (LSTM) outperformed RNN in accuracy and convolutional neural network (CNN) resulted in the highest Specificity. This research has significant implications for healthcare providers in proactively managing seizure occurrence in pediatric patients, potentially transforming clinical practices, and improving pediatric care.

Keywords: intractable epilepsy, seizure, deep learning, prediction, electroencephalogram channels

Procedia PDF Downloads 83

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 197

Authors: C. Pislaru, A. Shebani

Abstract:

This paper uses the radial basis function neural network (RBFNN) for system identification of nonlinear systems. Five nonlinear systems are used to examine the activity of RBFNN in system modeling of nonlinear systems; the five nonlinear systems are dual tank system, single tank system, DC motor system, and two academic models. The feed forward method is considered in this work for modelling the non-linear dynamic models, where the K-Means clustering algorithm used in this paper to select the centers of radial basis function network, because it is reliable, offers fast convergence and can handle large data sets. The least mean square method is used to adjust the weights to the output layer, and Euclidean distance method used to measure the width of the Gaussian function.

Keywords: system identification, nonlinear systems, neural networks, radial basis function, K-means clustering algorithm

Procedia PDF Downloads 469

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 77

Authors: Min Jin Kwon, Seung Won Kim, Eui Yeon Kim, Haeyoung Lee

Abstract:

Numerous anonymous chat apps that help people to connect with random strangers have been released in South Korea. However, they become a serious problem for young people since young people often use them for channels of prostitution or sexual violence. Although ISPs in South Korea are responsible for making inappropriate content inaccessible on their networks, they do not block traffic of random chat apps since 1) the use of random chat apps is entirely legal. 2) it is reported that they use HTTP proxy blocking so that non-HTTP traffic cannot be blocked. In this paper, we propose a service model that can block random chat apps at home routers. A service provider manages a blacklist that contains blocked apps’ information. Home routers that subscribe the service filter the traffic of the apps out using deep packet inspection. We have implemented a prototype of the proposed model, including a centralized server providing the blacklist, a Raspberry Pi-based home router that can filter traffic of the apps out, and an Android app used by the router’s administrator to locally customize the blacklist.

Keywords: deep packet inspection, internet filtering, juvenile protection, technical blocking

Procedia PDF Downloads 348

Authors: Lubowa Samuel

Abstract:

Health information systems, often known as HIS, are critical components of the healthcare system to improve health policies and promote global health development. In a broader sense, HIS as a system integrates data collecting, processing, reporting, and making use of various types of data to improve healthcare efficacy and efficiency through better management at all levels of healthcare delivery. The aim of this study is to assess the adoption of health information systems (HIS) in a resource-constrained country drawing from the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model. The results indicate that the user's perception of the technology and the poor information technology infrastructures contribute a lot to the low adoption of HIS in resource-constrained countries.

Keywords: health information systems, resource-constrained countries, health information systems

Procedia PDF Downloads 118

Authors: Shubham Gogri, Lucia Florescu

Abstract:

Medical diagnosis and radiotherapy treatment planning using Computed Tomography (CT) rely on the quantitative accuracy and quality of the CT images. At the same time, requirements for CT imaging include reducing the radiation dose exposure to patients and minimizing scanning time. A solution to this is the sparse-view CT technique, based on a reduced number of projection views. This, however, introduces a new problem— the incomplete projection data results in lower quality of the reconstructed images. To tackle this issue, deep learning methods have been applied to enhance the quality of the sparse-view CT images. A first approach involved employing Mir-Net, a dedicated deep neural network designed for image enhancement. This showed promise, utilizing an intricate architecture comprising encoder and decoder networks, along with the incorporation of the Charbonnier Loss. However, this approach was computationally demanding. Subsequently, a specialized Generative Adversarial Network (GAN) architecture, rooted in the Pix2Pix framework, was implemented. This GAN framework involves a U-Net-based Generator and a Discriminator based on Convolutional Neural Networks. To bolster the GAN's performance, both Charbonnier and Wasserstein loss functions were introduced, collectively focusing on capturing minute details while ensuring training stability. The integration of the perceptual loss, calculated based on feature vectors extracted from the VGG16 network pretrained on the ImageNet dataset, further enhanced the network's ability to synthesize relevant images. A series of comprehensive experiments with clinical CT data were conducted, exploring various GAN loss functions, including Wasserstein, Charbonnier, and perceptual loss. The outcomes demonstrated significant image quality improvements, confirmed through pertinent metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) between the corrected images and the ground truth. Furthermore, learning curves and qualitative comparisons added evidence of the enhanced image quality and the network's increased stability, while preserving pixel value intensity. The experiments underscored the potential of deep learning frameworks in enhancing the visual interpretation of CT scans, achieving outcomes with SSIM values close to one and PSNR values reaching up to 76.

Keywords: generative adversarial networks, sparse view computed tomography, CT image correction, Mir-Net

Procedia PDF Downloads 159

Authors: Nasser Almonawer

Abstract:

Timely reaction to an evolving global business environment and volatile market conditions necessitates system and process flexibility, which in turn demands agile and adaptable architecture and a steady infusion of affordable new technologies. On the contrary, a large number of organizations utilize systems characterized by inflexible and obsolete legacy architectures. To effectively respond to the dynamic contemporary business environments, such architectures must be migrated to robust and modular open architectures. To this end, this paper proposes an integrated decision support system for a seamless migration to open systems. The proposed decision support system (DSS) integrates three well-established quantitative and qualitative decision-making models—namely, the Delphi method, Analytic Hierarchy Process (AHP) and Goal Programming (GP) to (1) assess risks and establish evaluation criteria; (2) formulate migration strategy and rank candidate systems; and (3) allocate resources among the selected systems.

Keywords: decision support systems, open systems architecture, analytic hierarchy process (AHP), goal programming (GP), delphi method

Procedia PDF Downloads 45

Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Sachi Nandan Mohanty, J. V. R. Ravindra

Abstract:

In the rapidly evolving landscape of medical diagnostics, the early detection and accurate classification of skin cancer remain paramount for effective treatment outcomes. This research delves into the transformative potential of Artificial Intelligence (AI), specifically Deep Learning (DL), as a tool for discerning and categorizing various skin conditions. Utilizing a diverse dataset of 3,000 images representing nine distinct skin conditions, we confront the inherent challenge of class imbalance. This imbalance, where conditions like melanomas are over-represented, is addressed by incorporating class weights during the model training phase, ensuring an equitable representation of all conditions in the learning process. Our pioneering approach introduces a hybrid model, amalgamating the strengths of two renowned Convolutional Neural Networks (CNNs), VGG16 and ResNet50. These networks, pre-trained on the ImageNet dataset, are adept at extracting intricate features from images. By synergizing these models, our research aims to capture a holistic set of features, thereby bolstering classification performance. Preliminary findings underscore the hybrid model's superiority over individual models, showcasing its prowess in feature extraction and classification. Moreover, the research emphasizes the significance of rigorous data pre-processing, including image resizing, color normalization, and segmentation, in ensuring data quality and model reliability. In essence, this study illuminates the promising role of AI and DL in revolutionizing skin cancer diagnostics, offering insights into its potential applications in broader medical domains.

Keywords: artificial intelligence, machine learning, deep learning, skin cancer, dermatology, convolutional neural networks, image classification, computer vision, healthcare technology, cancer detection, medical imaging

Procedia PDF Downloads 85

Authors: Yaolin Tian, Shanxiong Chen, Fujia Zhao, Xiaoyu Lin, Hailing Xiong

Abstract:

Ancient books are significant culture inheritors and their background textures convey the potential history information. However, multi-style texture recovery of ancient books has received little attention. Restricted by insufficient ancient textures and complex handling process, the generation of ancient textures confronts with new challenges. For instance, training without sufficient data usually brings about overfitting or mode collapse, so some of the outputs are prone to be fake. Recently, image generation and style transfer based on deep learning are widely applied in computer vision. Breakthroughs within the field make it possible to conduct research upon multi-style texture recovery of ancient books. Under the circumstances, we proposed a network of layout analysis and image fusion system. Firstly, we trained models by using Deep Convolution Generative against Networks (DCGAN) to synthesize multi-style ancient textures; then, we analyzed layouts based on the Position Rearrangement (PR) algorithm that we proposed to adjust the layout structure of foreground content; at last, we realized our goal by fusing rearranged foreground texts and generated background. In experiments, diversified samples such as ancient Yi, Jurchen, Seal were selected as our training sets. Then, the performances of different fine-turning models were gradually improved by adjusting DCGAN model in parameters as well as structures. In order to evaluate the results scientifically, cross entropy loss function and Fréchet Inception Distance (FID) are selected to be our assessment criteria. Eventually, we got model M8 with lowest FID score. Compared with DCGAN model proposed by Radford at el., the FID score of M8 improved by 19.26%, enhancing the quality of the synthetic images profoundly.

Keywords: deep learning, image fusion, image generation, layout analysis

Procedia PDF Downloads 156