Search results for: evaluation metrics

Authors: Seyed-Ali Sadegh-Zadeh, Kaveh Kavianpour, Hamed Atashbar, Elham Heidari, Saeed Shiry Ghidary, Amir M. Hajiyavand

Abstract:

Evaluation metrics play a critical role in assessing the performance of machine learning models. In this review paper, we provide a comprehensive overview of performance measurement approaches for machine learning models. For each category, we discuss the most widely used metrics, including their mathematical formulations and interpretation. Additionally, we provide a comparative analysis of performance measurement approaches for metric combinations. Our review paper aims to provide researchers and practitioners with a better understanding of performance measurement approaches and to aid in the selection of appropriate evaluation metrics for their specific applications.

Keywords: evaluation metrics, performance measurement, supervised learning, unsupervised learning, reinforcement learning, model robustness and stability, comparative analysis

Procedia PDF Downloads 76

Authors: C. Rana, S. K. Jain

Abstract:

The enormous amount of Web data has challenged its usage in efficient manner in the past few years. As such, a range of techniques are applied to tackle this problem; prominent among them is personalization and recommender system. In fact, these are the tools that assist user in finding relevant information of web. Most of the e-commerce websites are applying such tools in one way or the other. In the past decade, a large number of recommendation algorithms have been proposed to tackle such problems. However, there have not been much research in the evaluation criteria for these algorithms. As such, the traditional accuracy and classification metrics are still used for the evaluation purpose that provides a static view. This paper studies how the evolution of user preference over a period of time can be mapped in a recommender system using a new evaluation methodology that explicitly using time dimension. We have also presented different types of experimental set up that are generally used for recommender system evaluation. Furthermore, an overview of major accuracy metrics and metrics that go beyond the scope of accuracy as researched in the past few years is also discussed in detail.

Keywords: collaborative filtering, data mining, evolutionary, clustering, algorithm, recommender systems

Procedia PDF Downloads 415

Authors: Pratik Dhabal Deo, Manoj P.

Abstract:

With the increasing number of social media users, the amount of video content available has also significantly increased. Currently, the number of smartphone users is at its peak, and many are increasingly using their smartphones as their main photography and recording devices. There have been a lot of developments in the field of Video Quality Assessment (VQA) and metrics like VMAF, SSIM etc. are said to be some of the best performing metrics, but the evaluation of these metrics is dominantly done on professionally taken video contents using professional tools, lighting conditions etc. No study particularly pinpointing the performance of the metrics on the contents taken by users on very commonly available devices has been done. Datasets that contain a huge number of videos from different high-end devices make it difficult to analyze the performance of the metrics on the content from most used devices even if they contain contents taken in poor lighting conditions using lower-end devices. These devices face a lot of distortions due to various factors since the spectrum of contents recorded on these devices is huge. In this paper, we have presented an analysis of the objective VQA metrics on contents taken only from most used devices and their performance on them, focusing on full-reference metrics. To carry out this research, we created a custom dataset containing a total of 90 videos that have been taken from three most commonly used devices, and android smartphone, an IOS smartphone and a DSLR. On the videos taken on each of these devices, the six most common types of distortions that users face have been applied on addition to already existing H.264 compression based on four reference videos. These six applied distortions have three levels of degradation each. A total of the five most popular VQA metrics have been evaluated on this dataset and the highest values and the lowest values of each of the metrics on the distortions have been recorded. Finally, it is found that blur is the artifact on which most of the metrics didn’t perform well. Thus, in order to understand the results better the amount of blur in the data set has been calculated and an additional evaluation of the metrics was done using HEVC codec, which is the next version of H.264 compression, on the camera that proved to be the sharpest among the devices. The results have shown that as the resolution increases, the performance of the metrics tends to become more accurate and the best performing metric among them is VQM with very few inconsistencies and inaccurate results when the compression applied is H.264, but when the compression is applied is HEVC, SSIM and VMAF have performed significantly better.

Keywords: distortion, metrics, performance, resolution, video quality assessment

Procedia PDF Downloads 204

Authors: Pradeep Singh, Shrish Verma

Abstract:

Software fault prediction models are created by using the source code, processed metrics from the same or previous version of code and related fault data. Some company do not store and keep track of all artifacts which are required for software fault prediction. To construct fault prediction model for such company, the training data from the other projects can be one potential solution. The earlier we predict the fault the less cost it requires to correct. The training data consists of metrics data and related fault data at function/module level. This paper investigates fault predictions at early stage using the cross-project data focusing on the design metrics. In this study, empirical analysis is carried out to validate design metrics for cross project fault prediction. The machine learning techniques used for evaluation is Naïve Bayes. The design phase metrics of other projects can be used as initial guideline for the projects where no previous fault data is available. We analyze seven data sets from NASA Metrics Data Program which offer design as well as code metrics. Overall, the results of cross project is comparable to the within company data learning.

Keywords: software metrics, fault prediction, cross project, within project.

Procedia PDF Downloads 344

Authors: Tareq Aljaber

Abstract:

The number of mobile health apps is growing at a fast frequency as it's nearly doubled in a year between 2015 and 2016. Though, there is a lack of an effective evaluation framework to verify the usability and reliability of mobile phone health education applications which would help saving time and effort for the numerous user groups. This abstract describing a framework for evaluating mobile applications in specifically mobile health education applications, along with a guidance select tool to assist different users to select the most suitable mobile health education apps. The effective framework outcome is intended to meet the requirements and needs of the different stakeholder groups additionally to enhancing the development of mobile health education applications with software engineering approaches, by producing new and more effective techniques to evaluate such software. This abstract highlights the significance and consequences of mobile health education apps, before focusing the light on the required to create an effective evaluation framework for these apps. An explanation of the effective evaluation framework is going to be delivered in the abstract, beside with some specific evaluation metrics: an efficient hybrid of selected heuristic evaluation (HE) and usability evaluation (UE) metrics to enable the determination of the usefulness and usability of health education mobile apps. Moreover, an explanation of the qualitative and quantitative outcomes for the effective evaluation framework was accomplished using Epocrates mobile phone app in addition to some other mobile phone apps. This proposed framework-An Evaluation Framework for Mobile Health Education Apps-consists of a hybrid of 5 metrics designated from a larger set in usability evaluation and heuristic evaluation, illuminated grounded on 15 unstructured interviews from software developers (SD), health professionals (HP) and patients (P). These five metrics corresponding to explicit facets of usability recognised through a requirements analysis of typical stakeholders of mobile health apps. These five hybrid selected metrics were scattered across 24 specific questionnaire questions, which are available on request from first author. This questionnaire has been sent to 81 participants distributed in three sets of stakeholders from software developers (SD), health professionals (HP) and patients/general users (P/GU) on the purpose of ranking three sets of mobile health education applications. Finally, the outcomes from the questionnaire data helped us to approach our aims which are finding the profile for different stakeholders, finding the profile for different mobile health educations application packages, ranking different mobile health education application and guide us to build the select guidance too which is apart from the Evaluation Framework for Mobile Health Education Apps.

Keywords: evaluation framework, heuristic evaluation, usability evaluation, metrics

Procedia PDF Downloads 404

Authors: Johanna Renny Octavia, Meliana Nurdin, Ignatius Kevin Kurniawan, Ricca Aksara

Abstract:

It is widely believed that usability evaluation is necessary to evaluate a website design for further improvement. Traditional methods of usability evaluation have given sufficient insights to reveal usability problems of websites. Eye-tracking analysis has been considered as a useful method that adds a powerful dimension to web usability evaluation. It allows web designers and usability researchers to understand exactly what users do and do not see on a web page, thus disclose more information on web usability and provide a more complete insights on a website design. This paper elaborates on moving beyond traditional methods of web usability evaluation by integrating eye-tracking analysis to enhance the evaluation of website design, and presents three case studies to support this approach. In these case studies, eye movement metrics such as gaze plots and fixation-derived metrics, and user performance data such as task completion times and number of errors were recorded as objective measurements that can inform the necessity for website design improvements.

Keywords: design, eye-tracking, usability evaluation, website

Procedia PDF Downloads 303

Authors: Mohamed Boubekri, Jaewook Lee

Abstract:

The assessment of the daylighting performance of a design solution is a complex task due to the changing nature of daylight. A few quantitative metrics are available to designers to assess such a performance, among them are the mean hourly illuminance (MHI), the daylight factor (DF), the daylight autonomy (DA) and the useful daylight illuminance (UDI). Each of these metrics has criteria and limitations that affect the outcome of the evaluation. When to use one metric instead of another depends largely on the design goals to be achieved. Using Design Iterate Validate Adapt (DIVA) daylighting simulation program we set out to examine the performance behavior of these four metrics with the changing dimensions of three shading devices: a horizontal overhang, a horizontal louver system, and a vertical louver system, and compare their performance behavior as the orientation of the window changes. The context is a classroom of a prototypical elementary school in South Korea. Our results indicate that not all four metrics behave similarly as we vary the size of each shading device and as orientations changes. The UDI is the metric that leads to outcome most different than the other three metrics. Our conclusion is that not all daylighting metrics lead to the same conclusions and that it is important to use the metric that corresponds to the specific goals and objectives of the daylighting solution.

Keywords: daylight factor, hourly daylight illuminance, daylight autonomy, useful daylight illuminance

Procedia PDF Downloads 285

Authors: Aviv Yaniv, Ron Ben Arosh, Nadav Gasner, Michael Konviser, Arbel Yaniv

Abstract:

This paper introduces two methods for the evaluation of Question Decomposition Meaning Representation (QDMR) as predicted by sequence-to-sequence model and COPYNET parser for natural language questions processing, motivated by the fact that previous evaluation metrics used for this task do not take into account some characteristics of the representation, such as partial ordering structure. To this end, several heuristics to extract such partial dependencies are formulated, followed by the hereby proposed evaluation methods denoted as Proportional Graph Matcher (PGM) and Conversion to Normal String Representation (Nor-Str), designed to better capture the accuracy level of QDMR predictions. Experiments are conducted to demonstrate the efficacy of the proposed evaluation methods and show the added value suggested by one of them- the Nor-Str, for better distinguishing between high and low-quality QDMR when predicted by models such as COPYNET. This work represents an important step forward in the development of better evaluation methods for QDMR predictions, which will be critical for improving the accuracy and reliability of natural language question-answering systems.

Keywords: NLP, question answering, question decomposition meaning representation, QDMR evaluation metrics

Procedia PDF Downloads 78

Authors: Qasim Zafar, Matthew Anderson, Esteban Garcia, Steven Drager

Abstract:

Software failures can present an enormous detriment to people's lives and cost millions of dollars to repair when they are unexpectedly encountered in the wild. Despite a significant portion of the software development lifecycle and resources are dedicated to testing, software failures are a relatively frequent occurrence. Nevertheless, the evaluation of testing effectiveness remains at the forefront of ensuring high-quality software and software metrics play a critical role in providing valuable insights into quantifiable objectives to assess the level of assurance and confidence in the system. As the selection of appropriate metrics can be an arduous process, the goal of this paper is to shed light on the significance of software metrics by examining a range of testing techniques and metrics as well as identifying key areas for improvement. Additionally, through this investigation, readers will gain a deeper understanding of how metrics can help to drive informed decision-making on delivering high-quality software and facilitate continuous improvement in testing practices.

Keywords: software testing, software metrics, testing effectiveness, black box testing, random testing, adaptive random testing, combinatorial testing, fuzz testing, equivalence partition, boundary value analysis, white box testing

Procedia PDF Downloads 89

Authors: Arvinder Kaur, Deepti Chopra

Abstract:

Software Entropy Metrics for bug prediction have been validated on various software systems by different researchers. In our previous research, we have validated that Software Entropy Metrics calculated for Mozilla subsystem’s predict the future bugs reasonably well. In this study, the Software Entropy metrics are calculated for a subsystem of Android and it is noticed that these metrics are not suitable for bug prediction. The results are compared with a subsystem of Mozilla and a comparison is made between the two software systems to determine the reasons why Software Entropy metrics are not applicable for Android.

Keywords: android, bug prediction, mining software repositories, software entropy

Procedia PDF Downloads 578

Authors: Maryam Azimi, Amin Banitalebi-Dehkordi, Yuanyuan Dong, Mahsa T. Pourazad, Panos Nasiopoulos

Abstract:

While there exists a wide variety of Low Dynamic Range (LDR) quality metrics, only a limited number of metrics are designed specifically for the High Dynamic Range (HDR) content. With the introduction of HDR video compression standardization effort by international standardization bodies, the need for an efficient video quality metric for HDR applications has become more pronounced. The objective of this study is to compare the performance of the existing full-reference LDR and HDR video quality metrics on HDR content and identify the most effective one for HDR applications. To this end, a new HDR video data set is created, which consists of representative indoor and outdoor video sequences with different brightness, motion levels and different representing types of distortions. The quality of each distorted video in this data set is evaluated both subjectively and objectively. The correlation between the subjective and objective results confirm that VIF quality metric outperforms all to their tested metrics in the presence of the tested types of distortions.

Keywords: HDR, dynamic range, LDR, subjective evaluation, video compression, HEVC, video quality metrics

Procedia PDF Downloads 525

Authors: Mariayee Doraisamy, Suhaimi bin Ibrahim, Mohd Naz’ri Mahrin

Abstract:

There are several methods to monitor software projects and the objective for monitoring is to ensure that the software projects are developed and delivered successfully. A performance measurement is a method that is closely associated with monitoring and it can be scrutinized by looking at two important attributes which are efficiency and effectiveness both of which are factors that are important for the success of a software project. Consequently, a successful steering is achieved by monitoring and controlling a software project via the performance measurement criteria and metrics. Hence, this paper is aimed at identifying the performance measurement criteria and the metrics for monitoring the performance of a software project by using the Goal Question Metrics (GQM) approach. The GQM approach is utilized to ensure that the identified metrics are reliable and useful. These identified metrics are useful guidelines for project managers to monitor the performance of their software projects.

Keywords: component, software project performance, goal question metrics, performance measurement criteria, metrics

Procedia PDF Downloads 356

Authors: Samira Kalantary, Zohre Saatzade

Abstract:

Wireless Mesh Networks (WMNs) are low-cost access networks built on cooperative routing over a backbone composed of stationary wireless routers. WMNs must deal with the highly unstable wireless medium. Thus, routing metrics and protocols are evolving by designing algorithms that consider link quality to choose the best routes. In this work, we analyse the state of the art in WMN metrics and propose taxonomy for WMN routing protocols. Performance measurements of a wireless mesh network deployed using various routing metrics are presented and corroborate our analysis.

Keywords: wireless mesh networks, routing protocols, routing metrics, bioinformatics

Procedia PDF Downloads 455

Authors: Nasrin Sadeghzadeh

Abstract:

In this paper we study projective invariants of spherically symmetric Finsler metrics in Rn. We find the necessary and sufficient conditions for the metrics to be Douglas and Generalized Douglas-Weyl (GDW) types. Also we show that two classes of GDW and Douglas spherically symmetric Finsler metrics coincide.

Keywords: spherically symmetric finsler metrics in Rn, finsler metrics, douglas metric, generalized Douglas-Weyl (GDW) metric

Procedia PDF Downloads 360

Authors: Ahmad Mohsin, Irfan Raza Naqvi, Syda Fatima Usamn

Abstract:

Applications with higher fault tolerance index are considered more reliable and trustworthy to drive quality. In recent years application development has been shifted from traditional desktop and web to native and hybrid application(s) for the web and mobile platforms. With the emergence of Internet of things IOTs, cloud and big data trends, the need for measuring Fault Tolerance for these complex nature applications has increased to evaluate their performance. There is a phenomenal gap between fault tolerance metrics development and measurement. Classic quality metric models focused on metrics for traditional systems ignoring the essence of today’s applications software, hardware & deployment characteristics. In this paper, we have proposed simple metrics to measure fault tolerance considering general requirements for Web and Mobile Applications. We have aligned factors – subfactors, using GQM for metrics development considering the nature of mobile we apps. Systematic Mathematical formulation is done to measure metrics quantitatively. Three web mobile applications are selected to measure Fault Tolerance factors using formulated metrics. Applications are then analysed on the basis of results from observations in a controlled environment on different mobile devices. Quantitative results are presented depicting Fault tolerance in respective applications.

Keywords: web and mobile applications, reliability, fault tolerance metric, quality metrics, GQM based metrics

Procedia PDF Downloads 344

Authors: Satya Pradhan, Venky Nanniyur

Abstract:

As the software industry transitions from a license-based model to a subscription-based Software-as-a-Service (SaaS) model, many software development groups are using a hybrid development model that incorporates Agile and Waterfall methodologies in different parts of the organization. The traditional metrics used for measuring software quality in Waterfall or Agile paradigms do not apply to this new hybrid methodology. In addition, to respond to higher quality demands from customers and to gain a competitive advantage in the market, many companies are starting to prioritize quality as a strategic differentiator. As a result, quality metrics are included in the decision-making activities all the way up to the executive level, including board of director reviews. This paper presents key challenges associated with measuring software quality in organizations using the hybrid development model. We introduce a framework called Prevention-Inspection-Evaluation-Removal (PIER) to provide a comprehensive metric definition for hybrid organizations. The framework includes quality measurements, quality enforcement, and quality decision points at different organizational levels and project milestones. The metrics framework defined in this paper is being used for all Cisco systems products used in customer premises. We present several field metrics for one product portfolio (enterprise networking) to show the effectiveness of the proposed measurement system. As the results show, this metrics framework has significantly improved in-process defect management as well as field quality.

Keywords: quality management system, quality metrics framework, quality metrics, agile, waterfall, hybrid development system

Procedia PDF Downloads 174

Authors: Kumar Kanudkuri, A. Sandhya

Abstract:

Typically, in a MRI clinical setting, there are several protocols run, each indicated for a specific anatomy and disease condition. However, these protocols or parameters within them can change over time due to changes to the recommendations by the physician groups or updates in the software or by the availability of new technologies. Most of the time, the changes are performed by the MRI technologist to account for either time, coverage, physiological, or Specific Absorbtion Rate (SAR ) reasons. However, giving properly guidelines to MRI technologist is important so that they do not change the parameters that negatively impact the image quality. Typically a standard American College of Radiology (ACR) MRI phantom is used for Quality Control (QC) in order to guarantee that the primary objectives of MRI are met. The visual evaluation of quality depends on the operator/reviewer and might change amongst operators as well as for the same operator at various times. Therefore, overcoming these constraints is essential for a more impartial evaluation of quality. This makes quantitative estimation of image quality (IQ) metrics for MRI quality control is very important. So in order to solve this problem, we proposed that there is a need for a robust, open-source, and automated MRI image control tool. The Designed and developed an automatic analysis tool for measuring MRI image quality (IQ) metrics like Signal to Noise Ratio (SNR), Signal to Noise Ratio Uniformity (SNRU), Visual Information Fidelity (VIF), Feature Similarity (FSIM), Gray level co-occurrence matrix (GLCM), slice thickness accuracy, slice position accuracy, High contrast spatial resolution) provided good accuracy assessment. A standardized quality report has generated that incorporates metrics that impact diagnostic quality.

Keywords: ACR MRI phantom, MRI image quality metrics, SNRU, VIF, FSIM, GLCM, slice thickness accuracy, slice position accuracy

Procedia PDF Downloads 171

Authors: Silvio Ricardo Rodrigues Sanches, Bianca Cogo Barbosa, Beatriz Regina Brum, Cléber Gimenez Corrêa

Abstract:

To evaluate the quality of a segmentation algorithm, the authors use subjective or objective metrics. Although subjective metrics are more accurate than objective ones, objective metrics do not require user feedback to test an algorithm. Objective metrics require subjective experiments only during their development. Subjective experiments typically display to users some videos (generated from frames with segmentation errors) that simulate the environment of an application domain. This user feedback is crucial information for metric definition. In the subjective experiments applied to develop some state-of-the-art metrics used to test segmentation algorithms, the videos displayed during the experiments did not contain audio. Audio is an essential component in applications such as videoconference and augmented reality. If the audio influences the user’s perception, using only videos without audio in subjective experiments can compromise the efficiency of an objective metric generated using data from these experiments. This work aims to identify if the audio influences the user’s perception of segmentation quality in background substitution applications with audio. The proposed approach used a subjective method based on formal video quality assessment methods. The results showed that audio influences the quality of segmentation perceived by a user.

Keywords: background substitution, influence of audio, segmentation evaluation, segmentation quality

Procedia PDF Downloads 117

Authors: Maria Grazia Albanesi, Riccardo Amadeo

Abstract:

This study presents a new model of the human image quality assessment process: the aim is to highlight the foundations of the image quality metrics proposed in literature, by identifying the cognitive/physiological or mathematical principles of their development and the relation with the actual human quality assessment process. The model allows to create a novel categorization of objective and subjective image quality metrics. Our work includes an overview of the most used or effective objective metrics in literature, and, for each of them, we underline its main characteristics, with reference to the rationale of the proposed model and categorization. From the results of this operation, we underline a problem that affects all the presented metrics: the fact that many aspects of human biases are not taken in account at all. We then propose a possible methodology to address this issue.

Keywords: eye-tracking, image quality assessment metric, MOS, quality of user experience, visual perception

Procedia PDF Downloads 412

Authors: Kenny Raharjo, Ramon Lawrence

Abstract:

Game designers have the challenging task of building games that engage players to spend their time and money on the game. There are an infinite number of game variations and design choices, and it is hard to systematically determine game design choices that will have positive experiences for players. In this work, we demonstrate how multi-arm bandits can be used to automatically explore game design variations to achieve improved player metrics. The advantage of multi-arm bandits is that they allow for continuous experimentation and variation, intrinsically converge to the best solution, and require no special infrastructure to use beyond allowing minor game variations to be deployed to users for evaluation. A user study confirms that applying multi-arm bandits was successful in determining the preferred game variation with highest play time metrics and can be a useful technique in a game designer's toolkit.

Keywords: game design, multi-arm bandit, design exploration and data mining, player metric optimization and analytics

Procedia PDF Downloads 511

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 277

Authors: Manel Brichni, Abdelhak-Djamel Seriai

Abstract:

Systems are increasingly complex. To reduce their complexity, an abstract view of the system can simplify its development. To overcome this problem, we propose a method to decompose systems into subsystems while reducing their coupling. These subsystems represent components. Consisting of an existing object-oriented systems, the main idea of our approach is based on modelling as graphs all entities of an oriented object source code. Such modelling is easy to handle, so we can apply restructuring algorithms based on graph metrics. The particularity of our approach consists in integrating in addition to standard metrics, such as coupling and cohesion, some graph metrics giving more precision during the components identication. To treat this problem, we relied on the ROMANTIC approach that proposed a component-based software architecture recovery from an object oriented system.

Keywords: software reengineering, software component and interfaces, metrics, graphs

Procedia PDF Downloads 501

Authors: Berhanu Terfa, Nengcheng C.

Abstract:

The study deals with the analysis of urban expansion and land transformation of Hawass City using remote sensing data and landscape metrics during last three decades (1987–2017). Remote sensing data from Various multi-temporal satellite images viz., TM (1987), TM (1995), ETM+ (2005) and OLI (2017) were used to examine the urban expansion, growth types, and spatial isolation within the urban landscape to develop an understanding the trends of built-up growth in Hawassa City, Ethiopia. Landscape metrics and built-up density were employed to analyze the pattern, process and overall growth status. The area under investigation was divided into concentric circles with a consecutive circle of 1 km incremental radius from the central pixel (Central Business District) for analysis. The result exhibited that the built-up area had increased by 541.32% between 1987 and 2017and an extension growth types (more than 67 %) was observed. The major growth took place in north-west direction followed by north direction in haphazard manner during 1987–1995 period, whereas predominant built-up development was observed in south and southwest direction during 1995–2017 period. Land scape metrics result revealed that the of urban patches density, total edge and edge density increased, while mean nearest neighbors’ distance decreased showing the tendency of sprawl.

Keywords: landscape metrics, spatial patterns, remote sensing, multi-temporal, urban sprawl

Procedia PDF Downloads 286

Authors: M. C. Akay, A. Aybakan, H. Temeltas

Abstract:

Aerial and ground robots have various advantages of usage in different missions. Aerial robots can move quickly and get a different sight of view of the area, but those vehicles cannot carry heavy payloads. On the other hand, unmanned ground vehicles (UGVs) are slow moving vehicles, since those can carry heavier payloads than unmanned aerial vehicles (UAVs). In this context, we investigate the performances of various Similarity Metrics to provide a common map for Heterogeneous Robot Team (HRT) in complex environments. Within the usage of Lidar Odometry and Octree Mapping technique, the local 3D maps of the environment are gathered.  In order to obtain a common map for HRT, informative theoretic similarity metrics are exploited. All types of these similarity metrics gave adequate as allowable simulation time and accurate results that can be used in different types of applications. For the heterogeneous multi robot team, those methods can be used to match different types of maps.

Keywords: common maps, heterogeneous robot team, map matching, informative theoretic similarity metrics

Procedia PDF Downloads 168

Authors: Daniel F. Bohorquez, Luis M. Agudelo, Henry H. León

Abstract:

Heart rate variability (HRV) is defined as the temporary variation between heartbeats or RR intervals (distance between R waves in an electrocardiographic signal). This distance is currently a recognized biomarker. With the analysis of the distance, it is possible to assess the sympathetic and parasympathetic nervous systems. These systems are responsible for the regulation of the cardiac muscle. The analysis allows health specialists and researchers to diagnose various pathologies based on this variation. For the acquisition and analysis of HRV taken from a cardiac electrical signal, electronic equipment and analysis software that work independently are currently used. This complicates and delays the process of interpretation and diagnosis. With this delay, the health condition of patients can be put at greater risk. This can lead to an untimely treatment. This document presents a single portable device capable of acquiring electrocardiographic signals and calculating a total of 19 HRV metrics. This reduces the time required, resulting in a timelier intervention. The device has an electrocardiographic signal acquisition card attached to a microcontroller capable of transmitting the cardiac signal wirelessly to a mobile device. In addition, a mobile application was designed to analyze the cardiac waveform. The device calculates the RR and different metrics. The application allows a user to visualize in real-time the cardiac signal and the 19 metrics. The information is exported to a cloud database for remote analysis. The study was performed under controlled conditions in the simulated hospital of the Universidad de la Sabana, Colombia. A total of 60 signals were acquired and analyzed. The device was compared against two reference systems. The results show a strong level of correlation (r > 0.95, p < 0.05) between the 19 metrics compared. Therefore, the use of the portable system evaluated in clinical scenarios controlled by medical specialists and researchers is recommended for the evaluation of the condition of the cardiac system.

Keywords: biological signal análisis, heart rate variability (HRV), HRV metrics, mobile app, portable device.

Procedia PDF Downloads 184

Authors: Peter Tabatt, Christian Siemers

Abstract:

Using FPGA devices to improve the behavior of time-critical parts of embedded systems is a proven concept for years. With reconfigurable FPGA devices, the logical blocks can be partitioned and grouped into static and dynamic parts. The dynamic parts can be reloaded 'on demand' at runtime. This work uses cellular automata, which are constructed through compilation from (partially restricted) ANSI-C sources, to determine the suitability of various metrics for optimal partitioning. Significant metrics, in this case, are for example the area on the FPGA device for the partition, the pass count for loop constructs and communication characteristics to other partitions. With successful partitioning, it is possible to use smaller FPGA devices for the same requirements as with not reconfigurable FPGA devices or – vice versa – to use the same FPGAs for larger programs.

Keywords: reconfigurable FPGA, cellular automata, partitioning, metrics, parallel computing

Procedia PDF Downloads 272

Authors: Payel Datta, Abhishek Das, Abhishek Roychoudhury, Dhiman Chattopadhyay, Tanushyam Chattopadhyay

Abstract:

Machine learning (ML) and deep learning (DL) is most predominantly used in image/video processing, natural language processing (NLP), audio and speech recognition but not that much used in system performance evaluation. In this paper, authors are going to describe the architecture of an abstraction layer constructed using ML/DL to detect the system failure. This proposed system is used to detect the system failure by evaluating the performance metrics of an IoT service deployment under constrained infrastructure environment. This system has been tested on the manually annotated data set containing different metrics of the system, like number of threads, throughput, average response time, CPU usage, memory usage, network input/output captured in different hardware environments like edge (atom based gateway) and cloud (AWS EC2). The main challenge of developing such system is that the accuracy of classification should be 100% as the error in the system has an impact on the degradation of the service performance and thus consequently affect the reliability and high availability which is mandatory for an IoT system. Proposed ML/DL classifiers work with 100% accuracy for the data set of nearly 4,000 samples captured within the organization.

Keywords: machine learning, system performance, performance metrics, IoT, edge

Procedia PDF Downloads 195

Authors: Martin H¨ausl, Maximilian Auch, Johannes Forster, Peter Mandl, Alexander Schill

Abstract:

In order to survive on the market, companies must constantly develop improved and new products. These products are designed to serve the needs of their customers in the best possible way. The creation of new products is also called innovation and is primarily driven by a company’s internal research and development department. However, a new approach has been taking place for some years now, involving external knowledge in the innovation process. This approach is called open innovation and identifies customer knowledge as the most important source in the innovation process. This paper presents a concept of using social media posts as an external source to support the open innovation approach in its initial phase, the Ideation phase. For this purpose, the social media posts are semantically structured with the help of an ontology and the authors are evaluated using graph-theoretical metrics such as density. For the structuring and evaluation of relevant social media posts, we also use the findings of Natural Language Processing, e. g. Named Entity Recognition, specific dictionaries, Triple Tagger and Part-of-Speech-Tagger. The selection and evaluation of the tools used are discussed in this paper. Using our ontology and metrics to structure social media posts enables users to semantically search these posts for new product ideas and thus gain an improved insight into the external sources such as customer needs.

Keywords: idea ontology, innovation management, semantic search, open information extraction

Procedia PDF Downloads 188

Authors: Ahlad Neti, Elisa Arch, Martha Hall

Abstract:

Studies have shown that individuals who use Ankle-Foot-Orthoses (AFOs) have a high level of dissatisfaction regarding their current AFOs. Studies point to the focus on technical design with little attention given to the user perspective as a source of AFO designs that leave users dissatisfied. To design a new AFO that satisfies users and thereby improves their quality of life, the reasons for their dissatisfaction and their wants and needs for an improved AFO design must be identified. There has been little research into the user perspective on AFO use and desired improvements, so the relationship between AFO design and satisfaction in daily use must be assessed to develop appropriate metrics and constraints prior to designing a novel AFO. To assess the user perspective on AFO design, structured interviews were conducted with 7 individuals (average age of 64.29±8.81 years) who use AFOs. All interviews were transcribed and coded to identify common themes using Grounded Theory Method in NVivo 12. Qualitative analysis of these results identified sources of user dissatisfaction such as heaviness, bulk, and uncomfortable material and overall needs and wants for an AFO. Beyond the user perspective, certain objective factors must be considered in the construction of metrics and constraints to ensure that the AFO fulfills its medical purpose. These more objective metrics are rooted in a common medical device market and technical standards. Given the large body of research concerning these standards, these objective metrics and constraints were derived through a literature review. Through these two methods, a comprehensive list of metrics and constraints accounting for both the user perspective on AFO design and the AFO’s medical purpose was compiled. These metrics and constraints will establish the framework for designing a new AFO that carries out its medical purpose while also improving the user experience. The metrics can be categorized into several overarching areas for AFO improvement. Categories of user perspective related metrics include comfort, discreteness, aesthetics, ease of use, and compatibility with clothing. Categories of medical purpose related metrics include biomechanical functionality, durability, and affordability. These metrics were used to guide an iterative prototyping process. Six concepts were ideated and compared using system-level analysis. From these six concepts, two concepts – the piano wire model and the segmented model – were selected to move forward into prototyping. Evaluation of non-functional prototypes of the piano wire and segmented models determined that the piano wire model better fulfilled the metrics by offering increased stability, longer durability, fewer points for failure, and a strong enough core component to allow a sock to cover over the AFO while maintaining the overall structure. As such, the piano wire AFO has moved forward into the functional prototyping phase, and healthy subject testing is being designed and recruited to conduct design validation and verification.

Keywords: ankle-foot orthotic, assistive technology, human centered design, medical devices

Procedia PDF Downloads 156

Authors: Prajwal Prakash Vasisht, Sharath Rajamurthy, Nishanth Dara

Abstract:

In a supervised machine learning approach, metrics such as precision, accuracy, and coverage can be calculated using ground truth labels to help in model tuning, evaluation, and selection. In an unsupervised setting, however, where the data has no ground truth, there are few interpretable metrics that can guide us to do the same. Our approach creates a framework to adapt the Intersection over Union metric, referred to as Adapted IoU, usually used to evaluate supervised learning models, into the unsupervised domain, which solves the problem by factoring in subject matter expertise and intuition about the ideal output from the model. This metric essentially provides a scale that allows us to compare the performance across numerous unsupervised models or tune hyper-parameters and compare different versions of the same model.

Keywords: general metric, unsupervised learning, classification, intersection over union

Procedia PDF Downloads 49