Search results for: algorithms and data structure

Authors: Pirom Thangchitpianpol, Suttipong Jumroonrut

Abstract:

This research investigates the distribution of food demand for animal food and the optimum amount of that food production at minimum cost. The data consist of customer purchase orders for the food of laying hens, price of food for laying hens, cost per unit for the food inventory, cost related to food of laying hens in which the food is out of stock, such as fine, overtime, urgent purchase for material. They were collected from January, 1990 to December, 2013 from a factory in Nakhonratchasima province. The collected data are analyzed in order to explore the distribution of the monthly food demand for the laying hens and to see the rate of inventory per unit. The results are used in a stochastic linear programming model for aggregate planning in which the optimum production or minimum cost could be obtained. Programming algorithms in MATLAB and tools in Linprog software are used to get the solution. The distribution of the food demand for laying hens and the random numbers are used in the model. The study shows that the distribution of monthly food demand for laying has a normal distribution, the monthly average amount (unit: 30 kg) of production from January to December. The minimum total cost average for 12 months is Baht 62,329,181.77. Therefore, the production planning can reduce the cost by 14.64% from real cost.

Keywords: animal food, stochastic linear programming, aggregate planning, production planning, demand uncertainty

Procedia PDF Downloads 384

Authors: Kazeem Adesina Dauda, Waheed Babatunde Yahya

Abstract:

To design a tree that maximizes within-node homogeneity, there is a need for a homogeneity measure that is appropriate for event history data with multiple risks. We consider the use of Deviance and Modified Cox-Snell residuals as a measure of impurity in Classification Regression Tree (CART) and compare our results with the results of Fiona (2008) in which homogeneity measures were based on Martingale Residual. Data structure approach was used to validate the performance of our proposed techniques via simulation and real life data. The results of univariate competing risk revealed that: using Deviance and Cox-Snell residuals as a response in within node homogeneity classification tree perform better than using other residuals irrespective of performance techniques. Bone marrow transplant data and double-blinded randomized clinical trial, conducted in other to compare two treatments for patients with prostate cancer were used to demonstrate the efficiency of our proposed method vis-à-vis the existing ones. Results from empirical studies of the bone marrow transplant data showed that the proposed model with Cox-Snell residual (Deviance=16.6498) performs better than both the Martingale residual (deviance=160.3592) and Deviance residual (Deviance=556.8822) in both event of interest and competing risks. Additionally, results from prostate cancer also reveal the performance of proposed model over the existing one in both causes, interestingly, Cox-Snell residual (MSE=0.01783563) outfit both the Martingale residual (MSE=0.1853148) and Deviance residual (MSE=0.8043366). Moreover, these results validate those obtained from the Monte-Carlo studies.

Keywords: within-node homogeneity, Martingale residual, modified Cox-Snell residual, classification and regression tree

Procedia PDF Downloads 275

Authors: Goran Begović

Abstract:

In recent years, many researchers are focusing on non-intrusive measuring methods when it comes to human biosignals. These methods provide solutions for everyday use, whether it’s health monitoring or finessing the workout routine. One of the biggest issues with these solutions is that the sensors’ accuracy is highly variable due to many factors, such as ambiental light, skin color diversity, etc. That is why we wanted to explore different outcomes under those kinds of circumstances in order to find the most optimal algorithm(s) for extracting heart rate (HR) information. The optimization of such algorithms can benefit the wider, cheaper, and safer application of home health monitoring, without having to visit medical professionals as often when it comes to observing heart irregularities. In this study, we explored the accuracy of infrared (IR), red, and green LED sensorics in a controlled environment and compared the results with a medically accurate ECG monitoring device.

Keywords: data science, ECG, heart rate, holter monitor, LED sensors

Procedia PDF Downloads 133

Authors: Vera Varazashvili, Murman Tsarakhov, Tamar Mirianashvili, Teimuraz Pavlenishvili, Tengiz Machaladze, Mzia Khundadze

Abstract:

Standard Gibbs energy of formation ΔGfor(298.15) of lanthanide-iron double oxides of garnet-type crystal structure R3Fe5O12 - RIG (R – are rare earth ions) from initial oxides are evaluated. The calculation is based on the data of standard entropies S298.15 and standard enthalpies ΔH298.15 of formation of compounds which are involved in the process of garnets synthesis. Gibbs energy of formation is presented as temperature function ΔGfor(T) for the range 300-1600K. The necessary starting thermodynamic data were obtained from calorimetric study of heat capacity – temperature functions and by using the semi-empirical method for calculation of ΔH298.15 of formation. Thermodynamic functions for standard temperature – enthalpy, entropy and Gibbs energy - are recommended as reference data for technological evaluations. Through the isostructural series of rare earth-iron garnets the correlation between thermodynamic properties and characteristics of lanthanide ions are elucidated.

Keywords: calorimetry, entropy, enthalpy, heat capacity, gibbs energy of formation, rare earth iron garnets

Procedia PDF Downloads 385

Authors: Siyuan Cai

Abstract:

This paper takes community segregation during major infectious diseases as the background, based on the physiological needs and safety needs of citizens during home segregation, and based on the selection of convenient facilities and medical facilities as the main research objects. Based on the POI data of public facilities in Chongqing, the spatial distribution characteristics of the convenience and medical facilities in the 15-minute living circle centered on three neighborhoods in Shapingba, namely Shengwei Community, Anju Commmunity and Fengtian Garden Community, were explored by means of GIS spatial analysis. The results show that the spatial distribution of convenience and medical facilities in this area has significant clustering characteristics, with a point-like distribution pattern of "dense in the west and sparse in the east", and a grouped and multi-polar spatial structure. The spatial structure is multi-polar and has an obvious tendency to the intersections and residential areas with dense pedestrian flow. This study provides a preliminary exploration of the distribution of medical and convenience facilities within the 15-minute living circle of a segregated community, which makes up for the lack of spatial research in this area.

Keywords: ArcGIS, community segregation, convenient facilities; distribution pattern, medical facilities, POI, 15-minute community life circle

Procedia PDF Downloads 127

Authors: Rimmy Yadav, Anmol Preet Kaur

Abstract:

Big Data has demonstrated the vast potential in streamlining, deciding, spotting business drifts in different fields, for example, producing, fund, Information Technology. This paper gives a multi-disciplinary diagram of the research issues in enormous information and its procedures, instruments, and system identified with the privacy, data storage management, network and energy utilization, adaptation to non-critical failure and information representations. Other than this, result difficulties and openings accessible in this Big Data platform have made.

Keywords: big data, privacy, data management, network and energy consumption

Procedia PDF Downloads 315

Authors: Brennan Lodge

Abstract:

Amidst a complex regulatory landscape, Retrieval Augmented Generation (RAG) emerges as a transformative tool for Governance Risk and Compliance (GRC) officers. This paper details the application of RAG in synthesizing Large Language Models (LLMs) with external knowledge bases, offering GRC professionals an advanced means to adapt to rapid changes in compliance requirements. While the development for standalone LLM’s (Large Language Models) is exciting, such models do have their downsides. LLM’s cannot easily expand or revise their memory, and they can’t straightforwardly provide insight into their predictions, and may produce “hallucinations.” Leveraging a pre-trained seq2seq transformer and a dense vector index of domain-specific data, this approach integrates real-time data retrieval into the generative process, enabling gap analysis and the dynamic generation of compliance and risk management content. We delve into the mechanics of RAG, focusing on its dual structure that pairs parametric knowledge contained within the transformer model with non-parametric data extracted from an updatable corpus. This hybrid model enhances decision-making through context-rich insights, drawing from the most current and relevant information, thereby enabling GRC officers to maintain a proactive compliance stance. Our methodology aligns with the latest advances in neural network fine-tuning, providing a granular, token-level application of retrieved information to inform and generate compliance narratives. By employing RAG, we exhibit a scalable solution that can adapt to novel regulatory challenges and cybersecurity threats, offering GRC officers a robust, predictive tool that augments their expertise. The granular application of RAG’s dual structure not only improves compliance and risk management protocols but also informs the development of compliance narratives with pinpoint accuracy. It underscores AI’s emerging role in strategic risk mitigation and proactive policy formation, positioning GRC officers to anticipate and navigate the complexities of regulatory evolution confidently.

Keywords: cybersecurity, gen AI, retrieval augmented generation, cybersecurity defense strategies

Procedia PDF Downloads 101

Authors: Abdelkader Hocine, Abdelhakim Maizia

Abstract:

The exponential growth of reinforced fibers composite materials use has prompted researchers to step up their work on the prediction of their reliability. Owing to differences between the properties of the materials used for the composite, the manufacturing processes, the load combinations and types of environment, the prediction of the reliability of composite materials has become a primary task. Through failure criteria, TSAI-WU and the maximum stress, the reliability of multilayer tubular structures under pressure is the subject of this paper, where the failure probability of is estimated by the method of Monte Carlo.

Keywords: composite, design, monte carlo, tubular structure, reliability

Procedia PDF Downloads 469

Authors: Dasom Kim, William Xiu Shun Wong, Yoonjin Hyun, Donghoon Lee, Minji Paek, Sungho Byun, Namgyu Kim

Abstract:

There have been many researches on document classification for classifying voluminous documents automatically. Through document classification, we can assign a specific category to each unlabeled document on the basis of various machine learning algorithms. However, providing labeled documents manually requires considerable time and effort. To overcome the limitations, the semi-supervised learning which uses unlabeled document as well as labeled documents has been invented. However, traditional document classifiers, regardless of supervised or semi-supervised ones, cannot sufficiently explain the reason or the process of the classification. Thus, in this paper, we proposed a methodology to visualize major topics and class components of each document. We believe that our methodology for visualizing topics and classes of each document can enhance the reliability and explanatory power of document classifiers.

Keywords: data mining, document classifier, text mining, topic modeling

Procedia PDF Downloads 406

Authors: Maciej Życki, Anna Kowalik-klimczak, Monika Łożyńska, Wioletta Barszcz, Jolanta Drabik Anna Kowalik-klimczak

Abstract:

The rapidly changing fashion trends generate huge amounts of leather and textile waste globally. The complexity of these types of waste makes recycling difficult in economic terms. Pyrolysis is suggested for this purpose, which transforms heterogeneous and complex waste into added-value products e.g. active carbons and soil fertilizer. The possibility of using pyrolysis for the valorization of leather and textile waste has been analyzed in this paper. In the first stage, leather and textile waste were subjected to TG/DTG thermogravimetric and DSC calorimetric analysis. These analyses provided basic information about thermochemical transformations and degradation rates during the pyrolysis of these types of waste and enabled the selection of the pyrolysis temperature. In the next stage, the effect of gas type using pyrolysis was investigated on the physicochemical properties, composition, structure, and formation of the specific surfaces of carbonized materials produced by means of a thermal treatment without oxygen access to the reaction chamber. These studies contribute some data about the thermal management and pyrolytic processing of leather and textile waste into useful carbonized materials, according to the circular economy model.

Keywords: pyrolysis, leather and textiles waste, composition and structure of carbonized materials, valorisation of waste, circular economy model

Procedia PDF Downloads 14

Authors: Mansoureh Ghiasabadi Farahani, Samira Kalantary, Sara Taghi-Pour, Mahboubeh Shamsi

Abstract:

Nowadays, the development of computers technology and its recent applications provide access to new types of data, which have not been considered by the traditional data analysts. Two particularly interesting characteristics of such data sets include their huge size and streaming nature .Incremental learning techniques have been used extensively to address the data stream classification problem. This paper presents a concise survey on the obstacles and the requirements issues classifying data streams with using decision tree. The most important issue is to maintain a balance between accuracy and efficiency, the algorithm should provide good classification performance with a reasonable time response.

Keywords: big data, data streams, classification, decision tree

Procedia PDF Downloads 525

Authors: Polo G. Yohn Edison, Rocha F. Pedricto

Abstract:

This work presents a study about a retaining structure designed for the duplication of the rail FEPASA on the 74th km between Santos and São Paulo. This structure, an anchored retaining wall, was instrumented in the anchors heads with strain gauges in order to monitor its loads. The load measurements occurred during the performance test, locking and also after the works were concluded. A decrease on anchors loads is noticed at the moment immediately after the locking, during construction and after the works finished. It was observed that a loss of load in the anchors occurred to a maximum of 54%.

Keywords: instrumentation, strain gauges, retaining wall, anchors

Procedia PDF Downloads 500

Authors: Aishwarya Shekhar, Himanshu Sharma

Abstract:

Data deduplication is one of important data compression techniques for eliminating duplicate copies of repeating data, and has been widely used in cloud storage to reduce the amount of storage space and save bandwidth. In this process, duplicate data is expunged, leaving only one copy means single instance of the data to be accumulated. Though, indexing of each and every data is still maintained. Data deduplication is an approach for minimizing the part of storage space an organization required to retain its data. In most of the company, the storage systems carry identical copies of numerous pieces of data. Deduplication terminates these additional copies by saving just one copy of the data and exchanging the other copies with pointers that assist back to the primary copy. To ignore this duplication of the data and to preserve the confidentiality in the cloud here we are applying the concept of hybrid nature of cloud. A hybrid cloud is a fusion of minimally one public and private cloud. As a proof of concept, we implement a java code which provides security as well as removes all types of duplicated data from the cloud.

Keywords: confidentiality, deduplication, data compression, hybridity of cloud

Procedia PDF Downloads 386

Authors: Zahara Abdulhussan Al-Awadai

Abstract:

Currently, serious games play a significant role in education, sparking an increasing interest in using games for purposes beyond mere entertainment. In this research, we investigate the main requirements and aspects of designing and developing effective serious games for learning and developing a conceptual model to describe the structure of serious games with a focus on both aspects of serious games. The main contributions of this approach are to facilitate the design and development of serious games in a flexible and easy-to-use way and also to support the cooperative work between the multidisciplinary developer team.

Keywords: game development, game design, requirements, serious games, serious game model.

Procedia PDF Downloads 68

Authors: Elham Koohi, Silvio Jose Gumiere, Hossein Bonakdari, Saeid Homayouni

Abstract:

Water used in agricultural crops can be managed by irrigation scheduling based on soil moisture levels and plant water stress thresholds. Automated irrigation scheduling limits crop physiological damage and yield reduction. Knowledge of crop water stress monitoring approaches can be effective in optimizing the use of agricultural water. Understanding the physiological mechanisms of crop responding and adapting to water deficit ensures sustainable agricultural management and food supply. This aim could be achieved by analyzing and diagnosing crop characteristics and their interlinkage with the surrounding environment. Assessments of plant functional types (e.g., leaf area and structure, tree height, rate of evapotranspiration, rate of photosynthesis), controlling changes, and irrigated areas mapping. Calculating thresholds of soil water content parameters, crop water use efficiency, and Nitrogen status make irrigation scheduling decisions more accurate by preventing water limitations between irrigations. Combining Remote Sensing (RS), the Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning Algorithms (MLAs) can improve measurement accuracies and automate irrigation scheduling. This paper is a review structured by surveying about 100 recent research studies to analyze varied approaches in terms of providing high spatial and temporal resolution mapping, sensor-based Variable Rate Application (VRA) mapping, the relation between spectral and thermal reflectance and different features of crop and soil. The other objective is to assess RS indices formed by choosing specific reflectance bands and identifying the correct spectral band to optimize classification techniques and analyze Proximal Optical Sensors (POSs) to control changes. The innovation of this paper can be defined as categorizing evaluation methodologies of precision irrigation (applying the right practice, at the right place, at the right time, with the right quantity) controlled by soil moisture levels and sensitiveness of crops to water stress, into pre-processing, processing (retrieval algorithms), and post-processing parts. Then, the main idea of this research is to analyze the error reasons and/or values in employing different approaches in three proposed parts reported by recent studies. Additionally, as an overview conclusion tried to decompose different approaches to optimizing indices, calibration methods for the sensors, thresholding and prediction models prone to errors, and improvements in classification accuracy for mapping changes.

Keywords: agricultural crops, crop water stress detection, irrigation scheduling, precision agriculture, remote sensing

Procedia PDF Downloads 73

Authors: Wooseok Song, Sunjung Park, Jongkwon Lee, Jaye Koo

Abstract:

The objective of this paper is to observe the effects of injection conditions on flame structures in gas-centered swirl coaxial injector. Gaseous oxygen and liquid kerosene were used as propellants. For different injection conditions, two types of injector, which only differ in the diameter of the tangential inlet, were used in this study. In addition, oxidizer injection pressure was varied to control the combustion chamber pressure in different types of injector. In order to analyze the combustion instability intensity, the dynamic pressure was measured in both the combustion chamber and propellants lines. With the increase in differential pressure between the propellant injection pressure and the combustion chamber pressure, the combustion instability intensity increased. In addition, the flame structure was recorded using a high-speed camera to detect CH* chemiluminescence intensity. With the change in the injection conditions in the gas-centered swirl coaxial injector, the flame structure changed.

Keywords: liquid rocket engine, flame structure, combustion instability, dynamic pressure

Procedia PDF Downloads 237

Authors: Karina Zaccari, Ernesto Cordeiro Marujo

Abstract:

This paper presents a Machine Learning (ML) approach to support Meningitis diagnosis in patients at a children’s hospital in Sao Paulo, Brazil. The aim is to use ML techniques to reduce the use of invasive procedures, such as cerebrospinal fluid (CSF) collection, as much as possible. In this study, we focus on predicting the probability of Meningitis given the results of a blood and urine laboratory tests, together with the analysis of pain or other complaints from the patient. We tested a number of different ML algorithms, including: Adaptative Boosting (AdaBoost), Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Random Forest and Support Vector Machines (SVM). Decision Tree algorithm performed best, with 94.56% and 96.18% accuracy for training and testing data, respectively. These results represent a significant aid to doctors in diagnosing Meningitis as early as possible and in preventing expensive and painful procedures on some children.

Keywords: machine learning, medical diagnosis, meningitis detection, pediatric research

Procedia PDF Downloads 152

Authors: Devatha Kalyan Kumar, Aravindraj D., Sadathulla A.

Abstract:

Big data are now rapidly expanding in all engineering and science and many other domains. The potential of large or massive data is undoubtedly significant, make sense to require new ways of thinking and learning techniques to address the various big data challenges. Machine learning is continuously unleashing its power in a wide range of applications. In this paper, the latest advances and advancements in the researches on machine learning for big data processing. First, the machine learning techniques methods in recent studies, such as deep learning, representation learning, transfer learning, active learning and distributed and parallel learning. Then focus on the challenges and possible solutions of machine learning for big data.

Keywords: active learning, big data, deep learning, machine learning

Procedia PDF Downloads 449

Authors: Arshia Aflaki, Hadis Karimipour, Anik Islam

Abstract:

Generative Adversarial Attacks (GAAs) threaten critical sectors, ranging from fingerprint recognition to industrial control systems. Existing Deep Learning (DL) algorithms are not robust enough against this kind of cyber-attack. As one of the most critical industries in the world, the power grid is not an exception. In this study, a Deep Reinforcement Learning-based (DRL) framework assisting the DL model to improve the robustness of the model against generative adversarial attacks is proposed. Real-world smart grid stability data, as an IIoT dataset, test our method and improves the classification accuracy of a deep learning model from around 57 percent to 96 percent.

Keywords: generative adversarial attack, deep reinforcement learning, deep learning, IIoT, generative adversarial networks, power system

Procedia PDF Downloads 50

Authors: Tomy Prihananto, Damar Apri Sudarmadi

Abstract:

Indonesia recognizes the right to privacy as a human right. Indonesia provides legal protection against data management activities because the protection of personal data is a part of human rights. This paper aims to describe the arrangement of data management and data management in Indonesia. This paper is a descriptive research with qualitative approach and collecting data from literature study. Results of this paper are comprehensive arrangement of data that have been set up as a technical requirement of data protection by encryption methods. Arrangements on encryption and protection of personal data are mutually reinforcing arrangements in the protection of personal data. Indonesia has two important and immediately enacted laws that provide protection for the privacy of information that is part of human rights.

Keywords: Indonesia, protection, personal data, privacy, human rights, encryption

Procedia PDF Downloads 187

Authors: Zhaoxin Luo, Michael Zhu

Abstract:

In natural languages, there are always complex semantic hierarchies. Obtaining the feature representation based on these complex semantic hierarchies becomes the key to the success of the model. Several RNN models have recently been proposed to use latent indicators to obtain the hierarchical structure of documents. However, the model that only uses a single-layer latent indicator cannot achieve the true hierarchical structure of the language, especially a complex language like Chinese. In this paper, we propose a deep layered model that stacks arbitrarily many RNN layers equipped with latent indicators. After using EM and training it hierarchically, our model solves the computational problem of stacking RNN layers and makes it possible to stack arbitrarily many RNN layers. Our deep hierarchical model not only achieves comparable results to large pre-trained models on the Chinese short text classification problem but also achieves state of art results on the Chinese long text classification problem.

Keywords: nature language processing, recurrent neural network, hierarchical structure, document classification, Chinese

Procedia PDF Downloads 72

Authors: Semih Sözer

Abstract:

One of the most common issues in economic systems is understanding characteristics of economic activities in cities and regions. Although there are critics to economic base models in conceptual and empirical aspects, these models are useful tools to examining the economic structure of a nation, regions or cities. This paper uses one of the methodologies of economic base models namely the location quotients model. Data for this model includes employment numbers of provinces and NUTS II regions in Turkey. Time series of data covers the years of 1990, 2000, 2003, and 2009. Aim of this study is finding which sectors are export-base and which sectors are import-base in provinces and regions. Model results show that big provinces or powerful regions (population, size etc.) mostly have basic sectors in their economic system. However, interesting facts came from different sectors in different provinces and regions in the model results.

Keywords: economic base, location quotients model, regional economics, regional development

Procedia PDF Downloads 428

Authors: Nairy Kechichian

Abstract:

The original Leclerc Bridge is a covered wooden bridge that is considered a Quebec heritage structure with an index of 60, making it a very important provincial bridge from a historical point of view. It was constructed in 1927 and is in the rural area of Abitibi-Temiscamingue. It is a “town Québécois” type of structure, which is generally rare but common for covered bridges in Abitibi-Temiscamingue. This type of structure is composed of two trusses on both sides formed with diagonals, internal bracings, uprights and top and bottom chords to allow the transmission of loads. This structure is mostly known for its solidity, lightweightness, and ease of construction. It is a single-span bridge with a length of 25.3 meters and allows the passage of one vehicle at a time with a 4.22-meter driving lane. The structure is composed of 2 trusses located at each end of the deck, two gabion foundations at both ends, uprights and top and bottom chords. WSP (Williams Sale Partnership) Canada inc. was mandated by the Transport Minister of Quebec in 2019 to increase the capacity of the bridge from 5 tons to 30.6 tons and rehabilitate it, as it has deteriorated quite significantly over the years. The bridge was damaged due to material deterioration over time, exposure to humidity, high load effects and insect infestation. To allow the passage of 3 axle trucks, as well as to keep the integrity of this heritage structure, the final design chosen to rehabilitate the bridge involved adding a new deck independent from the roof structure of the bridge. Essentially, new steel beams support the deck loads and the desired vehicle loads. The roof of the bridge is linked to the steel deck for lateral support, but it is isolated from the wooden deck. The roof is preserved for aesthetic reasons and remains intact as it is a heritage piece. Due to strict traffic management obstacles, an efficient construction method was put into place, which consisted of building a temporary bridge and moving the existing roof onto it to allow the circulation of vehicles on one side of the temporary bridge while providing a working space for the repairs of the roof on the other side to take place simultaneously. In parallel, this method allowed the demolition and reconstruction of the existing foundation, building a new steel deck, and transporting back the roof on the new bridge. One of the main criteria for the rehabilitation of the wooden bridge was to preserve, as much as possible, the existing patrimonial architectural design of the bridge. The project was completed successfully by the end of 2021.

Keywords: covered bridge, wood-steel, short span, town Québécois structure

Procedia PDF Downloads 71

Authors: Ambali Alade Odebowale, Andargachew Mekonnen Berhe, Haroldo T. Hattori, Andrey E. Miroshnichenko

Abstract:

Solar thermophotovoltaic systems (STPV) have emerged as a promising solution to overcome the Shockley-Queisser limit, a significant impediment in the direct conversion of solar radiation into electricity using conventional solar cells. The STPV system comprises essential components such as an optical concentrator, selective emitter, and a thermophotovoltaic (TPV) cell. The pivotal element in achieving high efficiency in an STPV system lies in the design of a spectrally selective emitter or absorber. Traditional methods for designing and optimizing selective emitters are often time-consuming and may not yield highly selective emitters, posing a challenge to the overall system performance. In recent years, the application of machine learning techniques in various scientific disciplines has demonstrated significant advantages. This paper proposes a novel nanostructure composed of four-layered materials (SiC/W/SiO2/W) to function as a selective emitter in the energy conversion process of an STPV system. Unlike conventional approaches widely adopted by researchers, this study employs a machine learning-based approach for the design and optimization of the selective emitter. Specifically, a random forest algorithm (RFA) is employed for the design of the selective emitter, while the optimization process is executed using genetic algorithms. This innovative methodology holds promise in addressing the challenges posed by traditional methods, offering a more efficient and streamlined approach to selective emitter design. The utilization of a machine learning approach brings several advantages to the design and optimization of a selective emitter within the STPV system. Machine learning algorithms, such as the random forest algorithm, have the capability to analyze complex datasets and identify intricate patterns that may not be apparent through traditional methods. This allows for a more comprehensive exploration of the design space, potentially leading to highly efficient emitter configurations. Moreover, the application of genetic algorithms in the optimization process enhances the adaptability and efficiency of the overall system. Genetic algorithms mimic the principles of natural selection, enabling the exploration of a diverse range of emitter configurations and facilitating the identification of optimal solutions. This not only accelerates the design and optimization process but also increases the likelihood of discovering configurations that exhibit superior performance compared to traditional methods. In conclusion, the integration of machine learning techniques in the design and optimization of a selective emitter for solar thermophotovoltaic systems represents a groundbreaking approach. This innovative methodology not only addresses the limitations of traditional methods but also holds the potential to significantly improve the overall performance of STPV systems, paving the way for enhanced solar energy conversion efficiency.

Keywords: emitter, genetic algorithm, radiation, random forest, thermophotovoltaic

Procedia PDF Downloads 66

Authors: Ali Nabavi, Farimah Safari, Mohammad Kashkooli, Sara Sadat Nabavizadeh, Hossein Molavi Vardanjani

Abstract:

Cognitive impairment presents a significant and increasing health concern as populations age. Environmental risk factors such as heavy metal exposure are suspected contributors, but their specific roles remain incompletely understood. Machine learning offers a promising approach to integrate multi-factorial data and improve the prediction of cognitive outcomes. This study aimed to develop and validate machine learning models to predict early risk of cognitive impairment by incorporating demographic, clinical, and biomarker data, including measures of heavy metal exposure. A retrospective analysis was conducted using 2011-2014 National Health and Nutrition Examination Survey (NHANES) data. The dataset included participants aged 20 years and older who underwent cognitive testing. Variables encompassed demographic information, medical history, lifestyle factors, and biomarkers such as blood and urine levels of lead, cadmium, manganese, and other metals. Machine learning algorithms were trained on 90% of the data and evaluated on the remaining 10%, with performance assessed through metrics such as accuracy, area under curve (AUC), and sensitivity. Analysis included 2,933 participants. The stacking ensemble model demonstrated the highest predictive performance, achieving an AUC of 0.778 and a sensitivity of 0.879 on the test dataset. Key predictors included age, gender, hypertension, education level, urinary cadmium, and blood manganese levels. The findings indicate that machine learning can effectively predict the risk of cognitive impairment using a comprehensive set of clinical and environmental exposure data. Incorporating biomarkers of heavy metal exposure improved prediction accuracy and highlighted the role of environmental factors in cognitive decline. Further prospective studies are recommended to validate the models and assess their utility over time.

Keywords: cognitive impairment, heavy metal exposure, predictive models, aging

Procedia PDF Downloads 8

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feed-forward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on self organizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: classification, SOFM algorithm, neural network, neighborhood, RGB image

Procedia PDF Downloads 487

Authors: Liuhui Zhu, Peng Zeng

Abstract:

With the rapid development in China, the urbanization has entered the transformation and promotion stage, and its direction of development has shifted to overall regional synergy. China has a large number of towns and villages, with comparative small scale and scattered distribution, which always support and provide resources to cities leading to urban-rural opposition, so it is difficult to achieve common development in a single town or village. In this context, the regional development should focus more on towns and villages to form a synergetic system, joining the regional association with cities. Thus, the paper raises the question about how to effectively organize towns and villages system to regulate the resource allocation and improve the comprehensive value of the regional area. To answer the question, it is necessary to find a suitable research unit and analysis of its present situation of towns and villages system for optimal development. By combing relevant researches and theoretical models, the county is the most basic administrative unit in China, which can directly guide and regulate the development of towns and villages, so the paper takes county as the research unit. Following the theoretical concept of ‘three structures and one network’, the paper concludes the research framework to analyse the present situation of towns and villages system, including scale structure, functional structure, spatial structure, and organization network. The analytical methods refer to the fractal theory and gravity model, using statistics and spatial data. The scale structure analyzes rank-size dimensions and uses the principal component method to calculate the comprehensive scale of towns and villages. The functional structure analyzes the functional types and industrial development of towns and villages. The spatial structure analyzes the aggregation dimension, network dimension, and correlation dimension of spatial elements to represent the overall spatial relationships. In terms of organization network, from the perspective of entity and ono-entity, the paper analyzes the transportation network and gravitational network. Based on the present situation analysis, the optimization strategies are proposed in order to achieve a synergetic relationship between towns and villages in the county area. The paper uses Suning county in the Beijing-Tianjin-Hebei region as a case study to apply the research framework and methods and then proposes the optimization orientations. The analysis results indicate that: (1) The Suning county is lack of medium-scale towns to transfer effect from towns to villages. (2) The distribution of gravitational centers is uneven, and the effect of gravity is limited only for nearby towns and villages. The gravitational network is not complete, leading to economic activities scattered and isolated. (3) The overall development of towns and villages system is immature, staying at ‘single heart and multi-core’ stage, and some specific optimization strategies are proposed. This study provides a regional view for the development of towns and villages and concludes the research framework and methods of towns and villages system for forming an effective synergetic relationship between them, contributing to organize resources and stimulate endogenous motivation, and form counter magnets to join the urban-rural integration.

Keywords: towns and villages system, organization structure, county area, fractal theory, gravity model

Procedia PDF Downloads 143

Authors: Shidrokh Goudarzi, Wan Haslina Hassan

Abstract:

Heterogeneous wireless networks are converging towards an all-IP network as part of the so-called next-generation network. In this paradigm, different access technologies need to be interconnected; thus, vertical handovers or vertical handoffs are necessary for seamless mobility. In this paper, we conduct a review of existing vertical handover decision-making mechanisms that aim to provide ubiquitous connectivity to mobile users. To offer a systematic comparison, we categorize these vertical handover measurement and decision structures based on their respective methodology and parameters. Subsequently, we analyze several vertical handover approaches in the literature and compare them according to their advantages and weaknesses. The paper compares the algorithms based on the network selection methods, complexity of the technologies used and efficiency in order to introduce our vertical handover decision framework. We find that vertical handovers on heterogeneous wireless networks suffer from the lack of a standard and efficient method to satisfy both user and network quality of service requirements at different levels including architectural, decision-making and protocols. Also, the consolidation of network terminal, cross-layer information, multi packet casting and intelligent network selection algorithm appears to be an optimum solution for achieving seamless service continuity in order to facilitate seamless connectivity.

Keywords: heterogeneous wireless networks, vertical handovers, vertical handover metric, decision-making algorithms

Procedia PDF Downloads 398

Authors: Hyungoo Kang, Jinkoo Kim

Abstract:

This study investigated the determination of the optimal location and friction force of friction dampers to effectively reduce the seismic response of a reinforced concrete structure designed without considering seismic load. To this end, the genetic algorithm process was applied and the results were compared with those obtained by simplified methods such as distribution of dampers based on the story shear or the inter-story drift ratio. The seismic performance of the model structure with optimally positioned friction dampers was evaluated by nonlinear static and dynamic analyses. The analysis results showed that compared with the system without friction dampers, the maximum roof displacement and the inter-story drift ratio were reduced by about 30% and 40%, respectively. After installation of the dampers about 70% of the earthquake input energy was dissipated by the dampers and the energy dissipated in the structural elements was reduced by about 50%. In comparison with the simplified methods of installation, the genetic algorithm provided more efficient solutions for seismic retrofit of the model structure.

Keywords: friction dampers, genetic algorithm, optimal design, RC buildings

Procedia PDF Downloads 246

Authors: Pengfei Meng, Shuangcheng Jia, Qian Li

Abstract:

We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.

Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling

Procedia PDF Downloads 158