Search results for: decision tree algorithm

Authors: K. Hema Shankari, R. Thirumalaiselvi, N. V. Balasubramanian

Abstract:

The present paper addresses to the research in the area of regression testing with emphasis on automated tools as well as prioritization of test cases. The uniqueness of regression testing and its cyclic nature is pointed out. The difference in approach between industry, with business model as basis, and academia, with focus on data mining, is highlighted. Test Metrics are discussed as a prelude to our formula for prioritization; a case study is further discussed to illustrate this methodology. An industrial case study is also described in the paper, where the number of test cases is so large that they have to be grouped as Test Suites. In such situations, a genetic algorithm proposed by us can be used to reconfigure these Test Suites in each cycle of regression testing. The comparison is made between a proprietary tool and an open source tool using the above-mentioned metrics. Our approach is clarified through several tables.

Keywords: APFD metric, genetic algorithm, regression testing, RFT tool, test case prioritization, selenium tool

Procedia PDF Downloads 434

Authors: Pascal François Faye, Baye Mor Sall, Bineta Dembele, Jeanne Ana Awa Faye

Abstract:

In agriculture, estimating crop yields is key to improving productivity and decision-making processes such as financial market forecasting and addressing food security issues. The main objective of this paper is to have tools to predict and improve the accuracy of crop yield forecasts using machine learning (ML) algorithms such as CART , KNN and SVM . We developed a mobile app and a web app that uses these algorithms for practical use by farmers. The tests show that our system (collection and deployment architecture, web application and mobile application) is operational and validates empirical knowledge on agro-climatic parameters in addition to proactive decision-making support. The experimental results obtained on the agricultural data, the performance of the ML algorithms are compared using cross-validation in order to identify the most effective ones following the agricultural data. The proposed applications demonstrate that the proposed approach is effective in predicting crop yields and provides timely and accurate responses to farmers for decision support.

Keywords: prediction, machine learning, artificial intelligence, digital agriculture

Procedia PDF Downloads 79

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

The design of adaptive systems that take advantage of financial markets while reducing the risk can bring more stagnant wealth into the global market. However, most efforts made to generate successful deals in trading financial assets rely on Supervised Learning (SL), which suffered from various limitations. Deep Reinforcement Learning (DRL) offers to solve these drawbacks of SL approaches by combining the financial assets price "prediction" step and the "allocation" step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. In this paper, a continuous action space approach is adopted to give the trading agent the ability to gradually adjust the portfolio's positions with each time step (dynamically re-allocate investments), resulting in better agent-environment interaction and faster convergence of the learning process. In addition, the approach supports the managing of a portfolio with several assets instead of a single one. This work represents a novel DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem, or what is referred to as The Agent Environment as Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. More specifically, we design an environment that simulates the real-world trading process by augmenting the state representation with ten different technical indicators and sentiment analysis of news articles for each stock. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, which can learn policies in high-dimensional and continuous action spaces like those typically found in the stock market environment. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of deep reinforcement learning in financial markets over other types of machine learning such as supervised learning and proves its credibility and advantages of strategic decision-making.

Keywords: the stock market, deep reinforcement learning, MDP, twin delayed deep deterministic policy gradient, sentiment analysis, technical indicators, autonomous agent

Procedia PDF Downloads 176

Authors: Yao-Hong Tsai

Abstract:

This paper presents an efficient fusion algorithm for iris images to generate stable feature for recognition in unconstrained environment. Recently, iris recognition systems are focused on real scenarios in our daily life without the subject’s cooperation. Under large variation in the environment, the objective of this paper is to combine information from multiple images of the same iris. The result of image fusion is a new image which is more stable for further iris recognition than each original noise iris image. A wavelet-based approach for multi-resolution image fusion is applied in the fusion process. The detection of the iris image is based on Adaboost algorithm and then local binary pattern (LBP) histogram is then applied to texture classification with the weighting scheme. Experiment showed that the generated features from the proposed fusion algorithm can improve the performance for verification system through iris recognition.

Keywords: image fusion, iris recognition, local binary pattern, wavelet

Procedia PDF Downloads 366

Authors: Dimitris Varsamis, Christos Talagkozis, Alkiviadis Tsimpiris, Paris Mastorocostas

Abstract:

The aim of this work is the parallel implementation of k-means in MATLAB, in order to reduce the execution time. Specifically, a new function in MATLAB for serial k-means algorithm is developed, which meets all the requirements for the conversion to a function in MATLAB with parallel computations. Additionally, two different variants for the definition of initial values are presented. In the sequel, the parallel approach is presented. Finally, the performance tests for the computation times respect to the numbers of features and classes are illustrated.

Keywords: K-means algorithm, clustering, parallel computations, Matlab

Procedia PDF Downloads 383

Authors: Deepak Singh, Rail Kuliev

Abstract:

This research article explores the significance of advanced data visualization techniques in enhancing decision-making processes within the oil and gas exploration and production domain. With the oil and gas industry facing numerous challenges, effective interpretation and analysis of vast and diverse datasets are crucial for optimizing exploration strategies, production operations, and risk assessment. The article highlights the importance of data visualization in managing big data, aiding the decision-making process, and facilitating communication with stakeholders. Various advanced data visualization techniques, including 3D visualization, augmented reality (AR), virtual reality (VR), interactive dashboards, and geospatial visualization, are discussed in detail, showcasing their applications and benefits in the oil and gas sector. The article presents case studies demonstrating the successful use of these techniques in optimizing well placement, real-time operations monitoring, and virtual reality training. Additionally, the article addresses the challenges of data integration and scalability, emphasizing the need for future developments in AI-driven visualization. In conclusion, this research emphasizes the immense potential of advanced data visualization in revolutionizing decision-making processes, fostering data-driven strategies, and promoting sustainable growth and improved operational efficiency within the oil and gas exploration and production industry.

Keywords: augmented reality (AR), virtual reality (VR), interactive dashboards, real-time operations monitoring

Procedia PDF Downloads 84

Authors: Onyedikachi Ulelu, Andrew P. Longstaff, Simon Fletcher, Simon Parkinson

Abstract:

The widespread interest in 'Industry 4.0' or 'digital manufacturing' has led to significant research requiring the acquisition of data from sensors, instruments, and machine signals. In-depth research then identifies methods of analysis of the massive amounts of data generated before and during manufacture to solve a particular problem. The ultimate goal is for industrial Internet of Things (IIoT) data to be processed automatically to assist with either visualisation or autonomous system decision-making. However, the collection and processing of data in an industrial environment come with a cost. Little research has been undertaken on how to specify optimally what data to capture, transmit, process, and store at various levels of an edge-cloud network. The first step in this specification is to categorise IIoT data for efficient and effective use. This paper proposes the required attributes and classification to take manufacturing digital data from various sources to determine the most suitable location for data processing on the edge-cloud network. The proposed classification framework will minimise overhead in terms of network bandwidth/cost and processing time of machine tool data via efficient decision making on which dataset should be processed at the ‘edge’ and what to send to a remote server (cloud). A fast-and-frugal heuristic method is implemented for this decision-making. The framework is tested using case studies from industrial machine tools for machine productivity and maintenance.

Keywords: data classification, decision making, edge computing, industrial IoT, industry 4.0

Procedia PDF Downloads 176

Authors: Juan Heredia, Naci Dilekli

Abstract:

The Ecuadorian Rainforest has been polluted for almost 60 years with little to no regard to oversight, law, or regulations. The consequences have been vast environmental damage such as pollution and deforestation, as well as sickness and the death of many people and animals. The aim of this paper is to quantify and localize the polluted zones, which something that has not been conducted and is the first step for remediation. To approach this problem, multi-spectral Remote Sensing imagery was utilized using a novel algorithm developed for this study, based on four normalized indices available in the literature. The algorithm classifies the pixels in polluted or healthy ones. The results of this study include a new algorithm for pixel classification and quantification of the polluted area in the selected image. Those results were finally validated by ground control points found in the literature. The main conclusion of this work is that using hyperspectral images, it is possible to identify polluted vegetation. The future work is environmental remediation, in-situ tests, and more extensive results that would inform new policymaking.

Keywords: remote sensing, oil pollution quatification, amazon forest, hyperspectral remote sensing

Procedia PDF Downloads 161

Authors: Trapti Sharma, Devesh Kumar Srivastava

Abstract:

This paper is basically a analysis study of above MapReduce implementation and also to verify and validate the MapReduce solution model for Parallel K-Mediod algorithm on Hadoop Cluster. MapReduce is a programming model which authorize the managing of huge amounts of data in parallel, on a large number of devices. It is specially well suited to constant or moderate changing set of data since the implementation point of a position is usually high. MapReduce has slowly become the framework of choice for “big data”. The MapReduce model authorizes for systematic and instant organizing of large scale data with a cluster of evaluate nodes. One of the primary affect in Hadoop is how to minimize the completion length (i.e. makespan) of a set of MapReduce duty. In this paper, we have verified and validated various MapReduce applications like wordcount, grep, terasort and parallel K-Mediod clustering algorithm. We have found that as the amount of nodes increases the completion time decreases.

Keywords: hadoop, mapreduce, k-mediod, validation, verification

Procedia PDF Downloads 365

Authors: D. M. S. Bandara, Yunqi Lei, Ye Luo

Abstract:

Fingerprints are suitable as long-term markers of human identity since they provide detailed and unique individual features which are difficult to alter and durable over life time. In this paper, we propose an algorithm to encrypt and decrypt fingerprint images by using a specially designed Elliptic Curve Cryptography (ECC) procedure based on block ciphers. In addition, to increase the confusing effect of fingerprint encryption, we also utilize a chaotic-behaved method called Arnold Cat Map (ACM) for a 2D scrambling of pixel locations in our method. Experimental results are carried out with various types of efficiency and security analyses. As a result, we demonstrate that the proposed fingerprint encryption/decryption algorithm is advantageous in several different aspects including efficiency, security and flexibility. In particular, using this algorithm, we achieve a margin of about 0.1% in the test of Number of Pixel Changing Rate (NPCR) values comparing to the-state-of-the-art performances.

Keywords: arnold cat map, biometric encryption, block cipher, elliptic curve cryptography, fingerprint encryption, Koblitz’s encoding

Procedia PDF Downloads 203

Authors: Krzysztof Malczewski

Abstract:

Magnetic Resonance Imaging (MRI) reconstruction algorithm using compressed sensing is presented in this paper. It is exhibited that the offered approach improves MR images spatial resolution in circumstances when highly undersampled k-space trajectories are applied. Compressed Sensing (CS) aims at signal and images reconstructing from significantly fewer measurements than were conventionally assumed necessary. Magnetic Resonance Imaging (MRI) is a fundamental medical imaging method struggles with an inherently slow data acquisition process. The use of CS to MRI has the potential for significant scan time reductions, with visible benefits for patients and health care economics. In this study the objective is to combine super-resolution image enhancement algorithm with CS framework benefits to achieve high resolution MR output image. Both methods emphasize on maximizing image sparsity on known sparse transform domain and minimizing fidelity. The presented algorithm considers the cardiac and respiratory movements.

Keywords: super-resolution, MRI, compressed sensing, sparse-sense, image enhancement

Procedia PDF Downloads 428

Authors: Fahad Suleiman

Abstract:

Queuing, in medical system is the process of moving patients in a specific sequence to a specific service according to the patients’ nature of illness. The term scheduling stands for the process of computing a schedule. This may be done by a queuing based scheduler. This paper focuses on the medical consultancy system, the different queuing algorithms that are used in healthcare system to serve the patients, and the average waiting time. The aim of this paper is to build automatic queuing system for organizing the medical queuing system that can analyses the queue status and take decision which patient to serve. The new queuing architecture model can switch between different scheduling algorithms according to the testing results and the factor of the average waiting time. The main innovation of this work concerns the modeling of the average waiting time is taken into processing, in addition with the process of switching to the scheduling algorithm that gives the best average waiting time.

Keywords: queuing systems, queuing system models, scheduling algorithms, patients

Procedia PDF Downloads 352

Authors: Yeonjune Kang

Abstract:

A triangulation of a planar region is a partition of that region into triangles. In the finite element method, triangulations are often used as the grid underlying a computation. In order to be suitable as a finite element mesh, a triangulation must have well-shaped triangles, according to criteria that depend on the details of the particular problem. For instance, most methods require that all triangles be small and as close to the equilateral shape as possible. Stated differently, one wants to avoid having either thin or flat triangles in the triangulation. There are many triangulation procedures, a particular one being the one known as the longest edge bisection algorithm described below. Starting with a given triangle, locate the midpoint of the longest edge and join it to the opposite vertex of the triangle. Two smaller triangles are formed; apply the same bisection procedure to each of these triangles. Continuing in this manner after n steps one obtains a triangulation of the initial triangle into 2n smaller triangles. The longest edge algorithm was first considered in the late 70’s. It was shown by various authors that this triangulation has the desirable properties for the finite element method: independently of the number of iterations the angles of these triangles cannot get too small; moreover, the size of the triangles decays exponentially. In the present paper we consider a related triangulation algorithm we refer to as the largest angle bisection procedure. As the name suggests, rather than bisecting the longest edge, at each step we bisect the largest angle. We study the properties of the resulting triangulation and prove that, while the general behavior resembles the one in the longest edge bisection algorithm, there are several notable differences as well.

Keywords: angle bisectors, geometry, triangulation, applied mathematics

Procedia PDF Downloads 400

Authors: Maryam Kalkatechi

Abstract:

Nowadays, parametric design, scientific analysis, and digital fabrication are dominant. Many architectural practices are increasingly seeking to incorporate advanced digital software and fabrication in their projects. Proposing an erudite design process that combines digital and practical aspects in a strong frame within the method was resulted from the dissertation research. The digital aspects are the progressive advancements in algorithm design and simulation software. These aspects have assisted the firms to develop more holistic concepts at the early stage and maintain collaboration among disciplines during the design process. The erudite design process enhances the current design processes by encouraging the designer to implement the construction and architecture knowledge within the algorithm to make successful design processes. The erudite design process also involves the ongoing improvements of applying the new method of 3D printing in construction. This is achieved through the ‘data-sketches’. The term ‘data-sketch’ was developed by the author in the dissertation that was recently completed. It accommodates the decisions of the architect on the algorithm. This paper introduces the erudite design process and its components. It will summarize the application of this process in development of the ‘3D printed construction unit’. This paper contributes to overlaying the academic and practice with advanced technology by presenting a design process that transfers the dominance of tool to the learned architect and encourages innovation in design processes.

Keywords: erudite, data-sketch, algorithm design in architecture, design process

Procedia PDF Downloads 273

Authors: Devika Tanna

Abstract:

'Biometrics' means 'life measurement' but the term is usually associated with the use of unique physiological characteristics to identify an individual. It is important to secure the privacy of digital face image that is stored in central database. To impart privacy to such biometric face images, first, the digital face image is split into two host face images such that, each of it gives no idea of existence of the original face image and, then each cover image is stored in two different databases geographically apart. When both the cover images are simultaneously available then only we can access that original image. This can be achieved by using the XM2VTS and IMM face database, an adaptive algorithm for spatial greyscale. The algorithm helps to select the appropriate host images which are most likely to be compatible with the secret image stored in the central database based on its geometry and appearance. The encryption is done using GEVCS which results in a reconstructed image identical to the original private image.

Keywords: adaptive algorithm, database, host images, privacy, visual cryptography

Procedia PDF Downloads 129

Authors: Analise Borg, Paul Micallef

Abstract:

Over the past few years, the online multimedia collection has grown at a fast pace. Several companies showed interest to study the different ways to organize the amount of audio information without the need of human intervention to generate metadata. In the past few years, many applications have emerged on the market which are capable of identifying a piece of music in a short time. Different audio effects and degradation make it much harder to identify the unknown piece. In this paper, an audio fingerprinting system which makes use of a non-parametric based algorithm is presented. Parametric analysis is also performed using Gaussian Mixture Models (GMMs). The feature extraction methods employed are the Mel Spectrum Coefficients and the MPEG-7 basic descriptors. Bin numbers replaced the extracted feature coefficients during the non-parametric modelling. The results show that non-parametric analysis offer potential results as the ones mentioned in the literature.

Keywords: audio fingerprinting, mapping algorithm, Gaussian Mixture Models, MFCC, MPEG-7

Procedia PDF Downloads 419

Authors: Wan Noorul Hafilah Binti Wan Ariffin

Abstract:

Dam safety management is the crucial infrastructure as dam failure has a catastrophic effect on the community. Dam safety management is the effective framework of key actions and activities for the dam owner to manage the safety of the dam for its entire life cycle. However, maintaining dam safety is a challenging task as there are changes in current dam states. These changes introduce new risks to the dam's safety, which had not been considered when the dam was designed. A new framework has to be developed to adapt to the changes in the dam risk and make the dams resilient. This study proposes a risk-based decision-making adaptation framework for dam safety management. The research focuses on climate change's impact on hydrological situations as it causes floods and damages the dam structure. The risk analysis framework is adopted to improve the dam management strategies. The proposed study encompasses four phases. To start with, measuring the effect by assessing the impact of climate change on embankment dam, the second phase is to analyze the potential embankment dam failures. The third is analyzing the different components of risks related to the dam and, finally, developing a robust decision-making framework.

Keywords: climate change, embankment dam, failure, risk-informed decision making

Procedia PDF Downloads 163

Authors: Mohamed Khallaf, Hossein M Rizeei

Abstract:

Simulating wind pattern behavior over proposed urban features is critical in the early stage of the conceptual design of both architectural and urban disciplines. However, it is typically not possible for designers to explore the impact of wind flow profiles across new urban developments due to a lack of real data and inaccurate estimation of building parameters. Modeling the details of existing and proposed urban features and testing them against wind flows is the missing part of the conceptual design puzzle where architectural and urban discipline can focus. This research aims to develop a spatial decision-support design method utilizing LiDAR, GIS, and performance-based wind simulation technology to mitigate wind-related hazards on a design by simulating alternative design scenarios at the pedestrian level prior to its implementation in Sydney, Australia. The result of the experiment demonstrates the capability of the proposed framework to improve pedestrian comfort in relation to wind profile.

Keywords: spatial decision-support design, performance-based wind simulation, LiDAR, GIS

Procedia PDF Downloads 121

Authors: Nattachote Rugthaicharoencheep

Abstract:

This paper presents a feeder reconfiguration problem in distribution systems. The objective is to minimize the system power loss and to improve bus voltage profile. The optimization problem is subjected to system constraints consisting of load-point voltage limits, radial configuration format, no load-point interruption, and feeder capability limits. A method based on genetic algorithm, a search algorithm based on the mechanics of natural selection and natural genetics, is proposed to determine the optimal pattern of configuration. The developed methodology is demonstrated by a 33-bus radial distribution system with distributed generations and feeder capacitors. The study results show that the optimal on/off patterns of the switches can be identified to give the minimum power loss while respecting all the constraints.

Keywords: network reconfiguration, distributed generation capacitor placement, loss reduction, genetic algorithm

Procedia PDF Downloads 174

Authors: Nima Khosravi

Abstract:

This paper describes an integrated optimization technique with concurrent use of sequential quadratic programming, genetic algorithm, and simulated annealing particle swarm optimization for the design and optimization of a beam column. In this research, the comparison between 4 different types of optimization methods. The comparison is done and it is found out that all the methods meet the required constraints and the lowest value of the objective function is achieved by SQP, which was also the fastest optimizer to produce the results. SQP is a gradient based optimizer hence its results are usually the same after every run. The only thing which affects the results is the initial conditions given. The initial conditions given in the various test run were very large as compared. Hence, the value converged at a different point. Rest of the methods is a heuristic method which provides different values for different runs even if every parameter is kept constant.

Keywords: beam column, genetic algorithm, particle swarm optimization, sequential quadratic programming, simulated annealing

Procedia PDF Downloads 384

Authors: Soheila Sadeghi

Abstract:

In the dynamic landscape of project management, scope changes are an inevitable reality that can significantly impact project performance. These changes, whether initiated by stakeholders, external factors, or internal project dynamics, can lead to cost overruns and schedule delays. Accurately predicting the consequences of these changes is crucial for effective project control and informed decision-making. This study aims to develop predictive models to estimate the impact of scope changes on project cost and schedule using machine learning techniques. The research utilizes a comprehensive dataset containing detailed information on project tasks, including the Work Breakdown Structure (WBS), task type, productivity rate, estimated cost, actual cost, duration, task dependencies, scope change magnitude, and scope change timing. Multiple machine learning models are developed and evaluated to predict the impact of scope changes on project cost and schedule. These models include Linear Regression, Decision Tree, Ridge Regression, Random Forest, Gradient Boosting, and XGBoost. The dataset is split into training and testing sets, and the models are trained using the preprocessed data. Cross-validation techniques are employed to assess the robustness and generalization ability of the models. The performance of the models is evaluated using metrics such as Mean Squared Error (MSE) and R-squared. Residual plots are generated to assess the goodness of fit and identify any patterns or outliers. Hyperparameter tuning is performed to optimize the XGBoost model and improve its predictive accuracy. The feature importance analysis reveals the relative significance of different project attributes in predicting the impact on cost and schedule. Key factors such as productivity rate, scope change magnitude, task dependencies, estimated cost, actual cost, duration, and specific WBS elements are identified as influential predictors. The study highlights the importance of considering both cost and schedule implications when managing scope changes. The developed predictive models provide project managers with a data-driven tool to proactively assess the potential impact of scope changes on project cost and schedule. By leveraging these insights, project managers can make informed decisions, optimize resource allocation, and develop effective mitigation strategies. The findings of this research contribute to improved project planning, risk management, and overall project success.

Keywords: cost impact, machine learning, predictive modeling, schedule impact, scope changes

Procedia PDF Downloads 38

Authors: Aicha Majda, Abdelhamid El Hassani

Abstract:

Lung CT image segmentation is a prerequisite in lung CT image analysis. Most of the conventional methods need a post-processing to deal with the abnormal lung CT scans such as lung nodules or other lesions. The simplest similarity measure in the standard Graph Cuts Algorithm consists of directly comparing the pixel values of the two neighboring regions, which is not accurate because this kind of metrics is extremely sensitive to minor transformations such as noise or other artifacts problems. In this work, we propose an improved version of the standard graph cuts algorithm based on the Patch-Based similarity metric. The boundary penalty term in the graph cut algorithm is defined Based on Patch-Based similarity measurement instead of the simple intensity measurement in the standard method. The weights between each pixel and its neighboring pixels are Based on the obtained new term. The graph is then created using theses weights between its nodes. Finally, the segmentation is completed with the minimum cut/Max-Flow algorithm. Experimental results show that the proposed method is very accurate and efficient, and can directly provide explicit lung regions without any post-processing operations compared to the standard method.

Keywords: graph cuts, lung CT scan, lung parenchyma segmentation, patch-based similarity metric

Procedia PDF Downloads 167

Authors: Irum Matloob, Shoab Ahmad Khan, Fahim Arif

Abstract:

As Indo-Pak has been the victim of heart diseases since many decades. Many surveys showed that percentage of cardiac patients is increasing in Pakistan day by day, and special attention is needed to pay on this issue. The framework is proposed for performing detailed analysis of ECG survey data which is conducted for measuring prevalence of heart diseases statistics in Pakistan. The ECG survey data is evaluated or filtered by using automated Minnesota codes and only those ECGs are used for further analysis which is fulfilling the standardized conditions mentioned in the Minnesota codes. Then feature selection is performed by applying proposed algorithm based on discernibility matrix, for selecting relevant features from the database. Clustering is performed for exposing natural clusters from the ECG survey data by applying spectral clustering algorithm using fuzzy c means algorithm. The hidden patterns and interesting relationships which have been exposed after this analysis are useful for further detailed analysis and for many other multiple purposes.

Keywords: arrhythmias, centroids, ECG, clustering, discernibility matrix

Procedia PDF Downloads 469

Authors: Suparman

Abstract:

Piecewise linear regression models are very flexible models for modeling the data. If the piecewise linear regression models are matched against the data, then the parameters are generally not known. This paper studies the problem of parameter estimation of piecewise linear regression models. The method used to estimate the parameters of picewise linear regression models is Bayesian method. But the Bayes estimator can not be found analytically. To overcome these problems, the reversible jump MCMC algorithm is proposed. Reversible jump MCMC algorithm generates the Markov chain converges to the limit distribution of the posterior distribution of the parameters of picewise linear regression models. The resulting Markov chain is used to calculate the Bayes estimator for the parameters of picewise linear regression models.

Keywords: regression, piecewise, Bayesian, reversible Jump MCMC

Procedia PDF Downloads 519

Authors: M. Johnson, R. Faggian, V. Sposito

Abstract:

A participatory and engaged approach is key in connecting agricultural managers to sustainable agricultural systems to support and optimize production in Victoria’s food bowl. A sustainable intensification (SI) approach is well documented globally, but participation rates amongst Victorian farmers is fragmentary, and key outcomes and implementation strategies are poorly understood. Improvement in decision-support management tools and a greater understanding of the productivity gains available upon implementation of SI is necessary. This paper reviews the current understanding and uptake of SI practices amongst farmers in one of Victoria’s premier food producing regions, the Goulburn Broken; and it spatially analyses the potential for this region to adapt to climate change and optimize food production. A Geographical Information Systems (GIS) approach is taken to develop an interactive decision-support tool that can be accessible to on-ground agricultural managers. The tool encompasses multiple criteria analysis (MCA) that identifies factors during the construction phase of the tool, using expert witnesses and regional knowledge, framed within an Analytical Hierarchy Process. Given the complexities of the interrelations between each of the key outcomes, this participatory approach, in which local realities and factors inform the key outcomes and help to strategies for a particular region, results in a robust strategy for sustainably intensifying production in key food producing regions. The creation of an interactive, locally embedded, decision-support management and education tool can help to close the gap between farmer knowledge and production, increase on-farm adoption of sustainable farming strategies and techniques, and optimize farm productivity.

Keywords: agriculture, decision-support management tool, Geographic Information System, GIS, sustainable intensification

Procedia PDF Downloads 165

Authors: Shuge Lei, Haonan Hu, Dasheng Sun, Huabin Zhang, Kehong Yuan, Jian Dai, Yan Tong

Abstract:

It remains challenging to measure reliability from classification results from different machine learning models. This paper proposes a reliable soup optimization algorithm based on the model weight fusion algorithm Model Soup, aiming to improve reliability by using dual-channel reliability as the objective function to fuse a series of weights in the breast ultrasound classification models. Experimental results on breast ultrasound clinical datasets demonstrate that reliable soup significantly enhances the reliability of breast ultrasound image classification tasks. The effectiveness of the proposed approach was verified via multicenter trials. The results from five centers indicate that the reliability optimization algorithm can enhance the reliability of the breast ultrasound image classification model and exhibit low multicenter correlation.

Keywords: breast ultrasound image classification, feature attribution, reliability assessment, reliability optimization

Procedia PDF Downloads 83

Authors: Guldana Zhigerbayeva, Ming Yang

Abstract:

Transportation of hazardous materials (HAZMAT) is inevitable in the process industries. The statistics show a significant number of accidents has occurred during the transportation of HAZMAT. This makes risk management of HAZMAT transportation an important topic. The tree-based methods including fault-trees, event-trees and cause-consequence analysis, and Bayesian network, have been applied to risk management of HAZMAT transportation. However, there is limited work on the development of a systematic approach. The existing approaches fail to build up the linkages between the regulatory requirements and the safety measures development. The analysis of historical data from the past accidents’ report databases would limit our focus on the specific incidents and their specific causes. Thus, we may overlook some essential elements in risk management, including regulatory compliance, field expert opinions, and suggestions. A systematic approach is needed to translate the regulatory requirements of HAZMAT transportation into specified safety measures (both technical and administrative) to support the risk management process. This study aims to first adapt the House of Quality (HoQ) to House of Safety (HoS) and proposes a new approach- Safety Function Deployment (SFD). The results of SFD will be used in a multi-criteria decision-support system to develop find an optimal route for HazMats transportation. The proposed approach will be demonstrated through a hypothetical transportation case in Kazakhstan.

Keywords: hazardous materials, risk assessment, risk management, quality function deployment

Procedia PDF Downloads 140

Authors: G. Tamulevičius, A. Serackis, T. Sledevič, D. Navakauskas

Abstract:

We consider the biggest challenge in speech recognition – noise reduction. Traditionally detected transient noise pulses are removed with the corrupted speech using pulse models. In this paper we propose to cope with the problem directly in Dynamic Time Warping domain. Bidirectional Dynamic Time Warping algorithm for the recognition of isolated words impacted by transient noise pulses is proposed. It uses simple transient noise pulse detector, employs bidirectional computation of dynamic time warping and directly manipulates with warping results. Experimental investigation with several alternative solutions confirms effectiveness of the proposed algorithm in the reduction of impact of noise on recognition process – 3.9% increase of the noisy speech recognition is achieved.

Keywords: transient noise pulses, noise reduction, dynamic time warping, speech recognition

Procedia PDF Downloads 556

Authors: Aaditya U. Jhamb

Abstract:

Due to the current energy crisis that many countries are battling, energy-efficient buildings are the subject of extensive research in the modern technological era because of growing worries about energy consumption and its effects on the environment. The paper explores 8 factors that help determine energy efficiency for a building: (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution), with Tsanas and Xifara providing a dataset. The data set employed 768 different residential building models to anticipate heating and cooling loads with a low mean squared error. By optimizing these characteristics, machine learning algorithms may assess and properly forecast a building's heating and cooling loads, lowering energy usage while increasing the quality of people's lives. As a result, the paper studied the magnitude of the correlation between these input factors and the two output variables using various statistical methods of analysis after determining which input variable was most closely associated with the output loads. The most conclusive model was the Decision Tree Regressor, which had a mean squared error of 0.258, whilst the least definitive model was the Isotonic Regressor, which had a mean squared error of 21.68. This paper also investigated the KNN Regressor and the Linear Regression, which had to mean squared errors of 3.349 and 18.141, respectively. In conclusion, the model, given the 8 input variables, was able to predict the heating and cooling loads of a residential building accurately and precisely.

Keywords: energy efficient buildings, heating load, cooling load, machine learning models

Procedia PDF Downloads 92

Authors: Malika Yaici, Assia Arab, Betitra Yakouben, Samia Zermani

Abstract:

Ubiquitous computing is nowadays a reality through the networking of a growing number of computing devices. It allows providing users with context aware information and services in a heterogeneous environment, anywhere and anytime. Selection of the best context-aware service, between many available services and providers, is a tedious problem. In this paper, a service selection method based on Constraint Satisfaction Problem (CSP) formalism is proposed. The services are considered as variables and domains; and the user context, preferences and providers characteristics are considered as constraints. The Backtrack algorithm is used to solve the problem to find the best service and provider which matches the user requirements. Even though this algorithm has an exponential complexity, but its use guarantees that the service, that best matches the user requirements, will be found. A comparison of the proposed method with the existing solutions finishes the paper.

Keywords: ubiquitous computing, services selection, constraint satisfaction problem, backtrack algorithm

Procedia PDF Downloads 243