Search results for: data acquisition

Authors: Evisa Mitrou, Nicholas Tsitsianis, Supriya Shinde

Abstract:

In the age of digitisation and globalisation, businesses have shifted online and are investing in big data analytics (BDA) to respond to changing market conditions and sustain their performance. Our study shifts the focus from the adoption of BDA to the impact of BDA on financial performance. We explore the financial performance of both BDA-vendors (business-to-business) and BDA-clients (business-to-customer). We distinguish between the five BDA-technologies (big-data-as-a-service (BDaaS), descriptive, diagnostic, predictive, and prescriptive analytics) and discuss them individually. Further, we use four perspectives (internal business process, learning and growth, customer, and finance) and discuss the significance of how each of the five BDA-technologies affects the performance measures of these four perspectives. We also present the analysis of employee engagement, average turnover, average net income, and average net assets for BDA-clients and BDA-vendors. Our study also explores the effect of the COVID-19 pandemic on business continuity for both BDA-vendors and BDA-clients.

Keywords: BDA-clients, BDA-vendors, big data analytics, financial performance

Procedia PDF Downloads 109

Authors: Saeid Gharechelou, Ryutaro Tateishi

Abstract:

Earthquake is an inevitable catastrophic natural disaster. The damages of buildings and man-made structures, where most of the human activities occur are the major cause of casualties from earthquakes. A comparison of optical and SAR data is presented in the case of Kathmandu valley which was hardly shaken by 2015-Nepal Earthquake. Though many existing researchers have conducted optical data based estimated or suggested combined use of optical and SAR data for improved accuracy, however finding cloud-free optical images when urgently needed are not assured. Therefore, this research is specializd in developing SAR based technique with the target of rapid and accurate geospatial reporting. Should considers that limited time available in post-disaster situation offering quick computation exclusively based on two pairs of pre-seismic and co-seismic single look complex (SLC) images. The InSAR coherence pre-seismic, co-seismic and post-seismic was used to detect the change in damaged area. In addition, the ground truth data from field applied to optical data by random forest classification for detection of damaged area. The ground truth data collected in the field were used to assess the accuracy of supervised classification approach. Though a higher accuracy obtained from the optical data then integration by optical-SAR data. Limitation of cloud-free images when urgently needed for earthquak evevent are and is not assured, thus further research on improving the SAR based damage detection is suggested. Availability of very accurate damage information is expected for channelling the rescue and emergency operations. It is expected that the quick reporting of the post-disaster damage situation quantified by the rapid earthquake assessment should assist in channeling the rescue and emergency operations, and in informing the public about the scale of damage.

Keywords: Sentinel-1A data, Landsat-8, earthquake damage, InSAR, rapid damage monitoring, 2015-Nepal earthquake

Procedia PDF Downloads 157

Authors: AmirHossein Mohajerzadeh, Mohammad Alishahi, Saeed Aslishahi, Mohsen Zabihi

Abstract:

In this paper, we consider sensor nodes with the capability of measuring the bearings (relative angle to the target). We use geometric methods to select a set of observer nodes which are responsible for collecting data from the target. Considering the characteristics of target tracking applications, it is clear that significant numbers of sensor nodes are usually inactive. Therefore, in order to minimize the total network energy consumption, a set of sensor nodes, called sentinel, is periodically selected for monitoring, controlling the environment and transmitting data through the network. The other nodes are inactive. Furthermore, the proposed algorithm provides a joint scheduling and routing algorithm to transmit data between network nodes and the fusion center (FC) in which not only provides an efficient way to estimate the target position but also provides an efficient target tracking. Performance evaluation confirms the superiority of the proposed algorithm.

Keywords: coverage, routing, scheduling, target tracking, wireless sensor networks

Procedia PDF Downloads 365

Authors: Sun-Young Jang, Sung-Ah Kim, Dongyoun Shin

Abstract:

Current real-estate value estimation, difficult for laymen, usually is performed by specialists. This paper presents an automated estimation process based on big data and machine-learning technology that calculates influences of building conditions on real-estate price measurement. The present study analyzed actual building sales sample data for Nonhyeon-dong, Gangnam-gu, Seoul, Korea, measuring the major influencing factors among the various building conditions. Further to that analysis, a prediction model was established and applied using RapidMiner Studio, a graphical user interface (GUI)-based tool for derivation of machine-learning prototypes. The prediction model is formulated by reference to previous examples. When new examples are applied, it analyses and predicts accordingly. The analysis process discerns the crucial factors effecting price increases by calculation of weighted values. The model was verified, and its accuracy determined, by comparing its predicted values with actual price increases.

Keywords: apartment complex, big data, life-cycle building value analysis, machine learning

Procedia PDF Downloads 359

Authors: Omid Amini

Abstract:

Nowadays, technology plays the most important role in the life of human beings because people use technology to share data and to communicate with each other, but the challenge is the security of this data. For instance, as more people turn to technology in the world, more data is generated, and more hackers try to steal or infiltrate data. In addition, the data is under the control of the central authority, which can trigger the challenge of losing information and changing information; this can create widespread anxiety for different people in different communities. In this paper, we sought to investigate Blockchain technology that can guarantee information security and eliminate the challenge of central authority access to information. Now a day, people are suffering from the current voting system. This means that the lack of transparency in the voting system is a big problem for society and the government in most countries, but blockchain technology can be the best alternative to the previous voting system methods because it removes the most important challenge for voting. According to the results, this research can be a good start to getting acquainted with this new technology, especially on the security part and familiarity with how to use a voting system based on blockchain in the world. At the end of this research, it is concluded that the use of blockchain technology can solve the major security problem and lead to a secure and transparent election.

Keywords: blockchain, technology, security, information, voting system, transparency

Procedia PDF Downloads 111

Authors: Mpho Mokoatle, Darlington Mapiye, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on $k$-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0%, 80.5%, 80.5%, 63.6%, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms.

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 150

Authors: Darlington Mapiye, Mpho Mokoatle, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on k-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0 %, 80.5 %, 80.5 %, 63.6 %, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 138

Authors: Bernice Badal

Abstract:

The South African English curriculum emphasizes the adoption of the Communicative Approach (CA) using Communicative Language Teaching (CLT) methodologies to develop English as a second language (ESL) learners’ communicative competence in contexts such as township schools in South Africa. However, studies indicate that the adoption of the approach largely remains a rhetoric. Poor English language proficiency among learners and poor student performance, which continues from the secondary to the tertiary phase, is widely attributed to a lack of English language proficiency in South Africa. Consequently, this qualitative study, using a mix of classroom observations and interviews, sought to investigate teacher knowledge of Communicative Competence and the methods and strategies ESL teachers used to develop their learners’ communicative competence. The success of learners’ ability to develop communicative competence in contexts such as township schools in South Africa is inseparable from materials, tasks, teacher knowledge and how they implement the approach in the classrooms. Accordingly, teacher knowledge of the theory and practical implications of the CLT approach is imperative for the negotiation of meaning and appropriate use of language in context in resource-impoverished areas like the township. Using a mix of interviews and observations as data sources, this qualitative study examined teachers’ definitions and knowledge of Communicative competence with a focus on how it influenced their classroom practices. The findings revealed that teachers were not familiar with the notion of communicative competence, the communication process, and the underpinnings of CLT. Teachers’ narratives indicated an awareness that there should be interactions and communication in the classroom, but a lack of theoretical understanding of the types of communication necessary scuttled their initiatives. Thus, conceptual deficiency influences teachers’ practices as they engage in classroom activities in a superficial manner or focus on stipulated learner activities prescribed by the CAPS document. This study, therefore, concluded that partial or limited conceptual and coherent understandings with ‘teacher-proof’ stipulations for classroom practice do not inspire teacher efficacy and mastery of prescribed approaches; thus, more efforts should be made by the Department of Basic Education to strengthen the existing Professional Development workshops to support teachers in improving their understandings and application of CLT for the development of Communicative competence in their learners. The findings of the study contribute to the field of teacher knowledge acquisition, teacher beliefs and practices and professional development in the context of second language teaching and learning with a recommendation that frameworks for the development of communicative competence with wider applicability in resource-poor environments be developed to support teacher understanding and application in classrooms.

Keywords: communicative competence, CLT, conceptual understanding of reforms, professional development

Procedia PDF Downloads 41

Authors: K. W. Nam, B. J. Kim, S. J. Lee

Abstract:

Along with the development of network infrastructures, such as high-speed Internet and mobile environment, the explosion of multimedia data is expanding the range of multimedia services beyond voice and data services. Amid this flow, research is actively being done on the creation, management, and transmission of metadata on digital content to provide different services to users. This paper proposes a system for the insertion, storage, and retrieval of metadata about digital content. The metadata server with Binary XML was implemented for efficient storage space and retrieval speeds, and the transport data size required for metadata retrieval was simplified. With the proposed system, the metadata could be inserted into the moving objects in the video, and the unnecessary overlap could be minimized by improving the storage structure of the metadata. The proposed system can assemble metadata into one relevant topic, even if it is expressed in different media or in different forms. It is expected that the proposed system will handle complex network types of data.

Keywords: video, multimedia, metadata, editing tool, XML

Procedia PDF Downloads 155

Authors: Luís Pina

Abstract:

The conservation of marine biodiversity keeps ecosystems in balance and ensures the sustainable use of resources. In this context, technological resources have been used for monitoring marine species to allow biologists to obtain data in real-time. There are different mobile applications developed for data collection for monitoring purposes, but these systems are designed to be utilized only on third-generation (3G) phones or smartphones with Internet access and in rural parts of the developing countries, Internet services and smartphones are scarce. Thus, the objective of this work is to develop a system to monitor marine turtles using Unstructured Supplementary Service Data (USSD), which users can access through basic mobile phones. The system aims to improve the data collection mechanism and enhance the effectiveness of current systems in monitoring sea turtles using any type of mobile device without Internet access. The system will be able to report information related to the biological activities of marine turtles. Also, it will be used as a platform to assist marine conservation entities to receive reports of illegal sales of sea turtles. The system can also be utilized as an educational tool for communities, providing knowledge and allowing the inclusion of communities in the process of monitoring marine turtles. Therefore, this work may contribute with information to decision-making and implementation of contingency plans for marine conservation programs.

Keywords: GSM, marine biology, marine turtles, unstructured supplementary service data (USSD)

Procedia PDF Downloads 192

Authors: Oussama Hafferssas, Hiba Benyahia, Amina Madani, Nassima Zeriri

Abstract:

Although data nowadays has multiple forms; from text to images, and from audio to videos, yet text is still the most used one at a public level. At an academical and research level, and unlike other forms, text can be considered as the easiest form to process. Therefore, a brunch of Data Mining researches has been always under its shadow, called "Text Mining". Its concept is just like data mining’s, finding valuable patterns in data, from large collections and tremendous volumes of data, in this case: Text. Named entity recognition (NER) is one of Text Mining’s disciplines, it aims to extract and classify references such as proper names, locations, expressions of time and dates, organizations and more in a given text. Our approach "Octopub" does not aim to find new ways to improve named entity recognition process, rather than that it’s about finding a new, and yet smart way, to use NER in a way that we can extract sentiments of millions of people using Social Networks as a limitless information source, and Marketing for product promotion as the main domain of application.

Keywords: textmining, named entity recognition(NER), sentiment analysis, social media networks (SN, SMN), business intelligence(BI), marketing

Procedia PDF Downloads 569

Authors: Mohammadreza Ashouri, Majid Bayatian

Abstract:

Analysis of fire data is a way for the implementation of any plan to improve the level of safety in cities. Such an analysis is able to reveal signs of changes in a given period and can be used as a measure of safety. The information of about 66,341 fires (from 2002 to 2012) released by Tehran Safety Services and Fire-Fighting Organization and data on the population and the number of households provided by Tehran Municipality and the Statistical Yearbook of Iran were extracted. Using the data, the fire changes, the rate of injuries, and mortality rate were determined and analyzed. The rate of injuries and mortality rate of fires per one million population of Tehran were 59.58% and 86.12%, respectively. During the study period, the number of fires and fire stations increased by 104.38% and 102.63%, respectively. Most fires (9.21%) happened in the 4th District of Tehran. The results showed that the recorded fire data have not been systematically planned for fire prevention since one of the ways to reduce injuries caused by fires is to develop a systematic plan for necessary actions in emergency situations. To determine a reliable source for fire prevention, the stages, definitions of working processes and the cause and effect chains should be considered. Therefore, a comprehensive statistical system should be developed for reported and recorded fire data.

Keywords: fire statistics, fire analysis, accident prevention, Tehran

Procedia PDF Downloads 169

Authors: Sebastian Leal-Arenas

Abstract:

TikTok’s influence on contemporary society is undeniable. The impact of the mobile app transcends entertainment, as shown by the growing presence of specialized accounts dedicated to providing educational content, particularly as it pertains to language learning. However, the prevailing trend on the platform is vocabulary and grammar acquisition, neglecting a critical component: pronunciation. This study examines English pronunciation materials available on TikTok by taking a comprehensive approach that incorporates established assessment tools, such as the Learning Object Review Instrument and the Framework for Language Learning App Evaluation. Furthermore, novel evaluation categories are introduced to provide a more holistic assessment of these educational resources. 60 English pronunciation videos were part of the analysis. The findings reveal that these audio-visual materials present clear audio bolstered by high-quality video content and automatically generated closed captions. These three components enhance the comprehensibility of the input, making these concise videos valuable assets for language learners. Nevertheless, certain deficiencies are observed, such as the lack of emphasis on specific segments and their relationship with articulators. Improvements and refinements are discussed, as well as their potential utility within the language classroom. This study contributes to the ongoing investigation of multimedia materials used for language teaching and emphasizes the need to adapt pronunciation instruction methods to today’s technology.

Keywords: pronunciation, segments, teaching materials, technology

Procedia PDF Downloads 63

Authors: Nam Don Kim, Jungho Moon, Tae Yun Chung

Abstract:

This paper proposes an Internet of Things (IoT) based virtualization platform for providing smart tourism services. The virtualization platform provides a consistent access interface to various types of data by naming IoT devices and legacy information systems as pathnames in a virtual file system. In the other words, the IoT virtualization platform functions as a middleware which uses the metadata for underlying collected data. The proposed platform makes it easy to provide customized tourism information by using tourist locations collected by IoT devices and additionally enables to create new interactive smart tourism services focused on the tourist locations. The proposed platform is very efficient so that the provided tourism services are isolated from changes in raw data and the services can be modified or expanded without changing the underlying data structure.

Keywords: internet of things (IoT), IoT platform, serviceplatform, virtual file system (VSF)

Procedia PDF Downloads 487

Authors: Slim Namouchi, Bruno Vallet, Imed Riadh Farah

Abstract:

3D urban models provide powerful tools for decision making, urban planning, and smart city services. The accuracy of this 3D based systems is directly related to the quality of these models. Since manual large-scale modeling, such as cities or countries is highly time intensive and very expensive process, a fully automatic 3D building generation is needed. However, 3D modeling process result depends on the input data, the proprieties of the captured objects, and the required characteristics of the reconstructed 3D model. Nowadays, producing 3D real-world model is no longer a problem. Remotely sensed data had experienced a remarkable increase in the recent years, especially data acquired using unmanned aerial vehicles (UAV). While the scanning techniques are developing, the captured data amount and the resolution are getting bigger and more precise. This paper presents a literature review, which aims to identify different methods of automatic 3D buildings extractions either from LiDAR or the combination of LiDAR and satellite or aerial images. Then, we present open source technologies, and data models (e.g., CityGML, PostGIS, Cesiumjs) used to integrate these models in geospatial base layers for smart city services.

Keywords: CityGML, LiDAR, remote sensing, SIG, Smart City, 3D urban modeling

Procedia PDF Downloads 116

Authors: Ahmed Noor Al-qayyim, Barlas Özden Çağlayan

Abstract:

Structural failure is caused mainly by damage that often occurs on structures. Many researchers focus on obtaining very efficient tools to detect the damage in structures in the early state. In the past decades, a subject that has received considerable attention in literature is the damage detection as determined by variations in the dynamic characteristics or response of structures. This study presents a new damage identification technique. The technique detects the damage location for the incomplete structure system using output data only. The method indicates the damage based on the free vibration test data by using “Two Points - Condensation (TPC) technique”. This method creates a set of matrices by reducing the structural system to two degrees of freedom systems. The current stiffness matrices are obtained from optimization of the equation of motion using the measured test data. The current stiffness matrices are compared with original (undamaged) stiffness matrices. High percentage changes in matrices’ coefficients lead to the location of the damage. TPC technique is applied to the experimental data of a simply supported steel beam model structure after inducing thickness change in one element. Where two cases are considered, the method detects the damage and determines its location accurately in both cases. In addition, the results illustrate that these changes in stiffness matrix can be a useful tool for continuous monitoring of structural safety using ambient vibration data. Furthermore, its efficiency proves that this technique can also be used for big structures.

Keywords: damage detection, optimization, signals processing, structural health monitoring, two points–condensation

Procedia PDF Downloads 347

Authors: P. Senthil Kumari

Abstract:

Main concerns in data mining investigation are social controls of data mining for handling ambiguity, noise, or incompleteness on text data. We describe an innovative approach for unplanned text data detection of community networks achieved by classification mechanism. In a tangible domain claim with humble secrecy backgrounds provided by community network for evading annoying content is presented on consumer message partition. To avoid this, mining methodology provides the capability to unswervingly switch the messages and similarly recover the superiority of ordering. Here we designated learning-centered mining approaches with pre-processing technique to complete this effort. Our involvement of work compact with rule-based personalization for automatic text categorization which was appropriate in many dissimilar frameworks and offers tolerance value for permits the background of comments conferring to a variety of conditions associated with the policy or rule arrangements processed by learning algorithm. Remarkably, we find that the choice of classifier has predicted the class labels for control of the inadequate documents on community network with great value of effect.

Keywords: text mining, data classification, community network, learning algorithm

Procedia PDF Downloads 487

Authors: Tien-Li Chang, Huang-Chi Huang, Zhao-Chi Chen, Wun-Yi Chen

Abstract:

The droplet-based microfluidic are used as micro-reactors for chemical and biological assays. Hence, the precise addition of reagents into the droplets is essential for this function in the scope of lab-on-a-chip applications. To obtain the characteristics (size, velocity, pressure, and frequency of production) of droplets, this study describes an integrated on-chip method of real-time signal detection. By controlling and manipulating the fluids, the flow behavior can be obtained in the droplet-based microfluidics. The detection method is used a type of infrared sensor. Through the varieties of droplets in the microfluidic devices, the real-time conditions of velocity and pressure are gained from the sensors. Here the microfluidic devices are fabricated by polydimethylsiloxane (PDMS). To measure the droplets, the signal acquisition of sensor and LabVIEW program control must be established in the microchannel devices. The devices can generate the different size droplets where the flow rate of oil phase is fixed 30 μl/hr and the flow rates of water phase range are from 20 μl/hr to 80 μl/hr. The experimental results demonstrate that the sensors are able to measure the time difference of droplets under the different velocity at the voltage from 0 V to 2 V. Consequently, the droplets are measured the fastest speed of 1.6 mm/s and related flow behaviors that can be helpful to develop and integrate the practical microfluidic applications.

Keywords: microfluidic, droplets, sensors, single detection

Procedia PDF Downloads 474

Authors: Ivan Balachin, Geanette Polanco, Jiang Xingliang, Hu Qin

Abstract:

The problem of global warming raised up interest towards renewable energy sources. To reduce cost of wind energy is a challenge. Before building of wind park conditions such as: average wind speed, direction, time for each wind, probability of icing, must be considered in the design phase. Operation values used on the setting of control systems also will depend on mentioned variables. Here it is proposed a procedure to be include in the evaluation of the performance of a wind turbine, based on the amplitude of wind changes, the number of changes and their duration. A generic study case based on actual data is presented. Data analysing techniques were applied to model the power required for yaw system based on amplitude and data amount of wind changes. A theoretical model between time, amplitude of wind changes and angular speed of nacelle rotation was identified.

Keywords: field data processing, regression determination, wind turbine performance, wind turbine placing, yaw system losses

Procedia PDF Downloads 369

Authors: Masoud Charkhabi

Abstract:

We examine trade theory with this motivation. The full set of World Trade Organization data are organized into country-year pairs, each treated as a different entity. Topological Data Analysis reveals that among the 16 region and 240 region-year pairs there exists in fact a distinguishable group of region-period pairs. The generally accepted periods of shifts from dissimilar-dissimilar to similar-similar trade in goods among regions are examined from this new perspective. The period breaks are treated as cumulative and are flexible. This type of all-subsets analysis is motivated from computer science and is made possible with Lossy Compression and Graph Theory. The results question many patterns in similar-similar to dissimilar-dissimilar trade. They also show indications of economic shifts that only later become evident in other economic metrics.

Keywords: econometrics, globalization, network science, topological data, analysis, trade theory, visualization, world trade

Procedia PDF Downloads 356

Authors: Mumtaz Begum Mustafa, Siti Salwah Salim, Feizal Dani Rahman

Abstract:

Recently, Automatic Speech Recognition (ASR) systems were used to assist children in language acquisition as it has the ability to detect human speech signal. Despite the benefits offered by the ASR system, there is a lack of ASR systems for Malay-speaking children. One of the contributing factors for this is the lack of continuous speech database for the target users. Though cross-lingual adaptation is a common solution for developing ASR systems for under-resourced language, it is not viable for children as there are very limited speech databases as a source model. In this research, we propose a two-stage adaptation for the development of ASR system for Malay-speaking children using a very limited database. The two stage adaptation comprises the cross-lingual adaptation (first stage) and cross-age adaptation. For the first stage, a well-known speech database that is phonetically rich and balanced, is adapted to the medium-sized Malay adults using supervised MLLR. The second stage adaptation uses the speech acoustic model generated from the first adaptation, and the target database is a small-sized database of the target users. We have measured the performance of the proposed technique using word error rate, and then compare them with the conventional benchmark adaptation. The two stage adaptation proposed in this research has better recognition accuracy as compared to the benchmark adaptation in recognizing children’s speech.

Keywords: Automatic Speech Recognition System, children speech, adaptation, Malay

Procedia PDF Downloads 376

Authors: Muhammad Awais Shafique, Eiji Hato, Hideki Yaginuma

Abstract:

Recently GPS data is used in a lot of studies to automatically reconstruct travel patterns for trip survey. The aim is to minimize the use of questionnaire surveys and travel diaries so as to reduce their negative effects. In this paper data acquired from GPS and accelerometer embedded in smart phones is utilized to predict the mode of transportation used by the phone carrier. For prediction, Support Vector Machine (SVM) and Adaptive boosting (AdaBoost) are employed. Moreover a unique method to improve the prediction results from these algorithms is also proposed. Results suggest that the prediction accuracy of AdaBoost after improvement is relatively better than the rest.

Keywords: accelerometer, AdaBoost, GPS, mode prediction, support vector machine

Procedia PDF Downloads 339

Authors: Eric Kumar, Erica Cochran, Zhiang Zhang, Wei Liang, Ronak Mody

Abstract:

The objective of this article was to create a modelling framework that exposes the marginal costs of shifting workloads across geographically distributed data-centers. Geographical distribution of internet services helps to optimize their performance for localized end users with lowered communications times and increased availability. However, due to the geographical and temporal effects, the physical embodiments of a service's data center infrastructure can vary greatly. In this work, we first identify that the sources of variances in the physical infrastructure primarily stem from local weather conditions, specific user traffic profiles, energy sources, and the types of IT hardware available at the time of deployment. Second, we create a traffic simulator that indicates the IT load at each data-center in the set as an approximator for user traffic profiles. Third, we implement a framework that quantifies the global level energy demands using building energy models and the traffic profiles. The results of the model provide a time series of energy demands that can be used for further life cycle analysis of internet services.

Keywords: data-centers, energy, life cycle, network simulation

Procedia PDF Downloads 130

Authors: Marcho Setiawan Handok, Samuel S. Lemma, Abdoulaye Fofana, Naseef Mansoor

Abstract:

This paper is proposing a method to predict the outcome of the National Football League match with data from 2019 to 2022 and compare it with other popular models. The model uses open-source statistical data of each team, such as passing yards, rushing yards, fumbles lost, and scoring. Each statistical data has offensive and defensive. For instance, a data set of anticipated values for a specific matchup is created by comparing the offensive passing yards obtained by one team to the defensive passing yards given by the opposition. We evaluated the model’s performance by contrasting its result with those of established prediction algorithms. This research is using a neural network to predict the score of a National Football League match and then predict the winner of the game.

Keywords: game prediction, NFL, football, artificial neural network

Procedia PDF Downloads 65

Authors: Mehdi Khaki, Ehsan Forootan, Joseph Awange, Michael Kuhn

Abstract:

Terrestrial water storage, as a source of freshwater, plays an important role in human lives. Hydrological models offer important tools for simulating and predicting water storages at global and regional scales. However, their comparisons with 'reality' are imperfect mainly due to a high level of uncertainty in input data and limitations in accounting for all complex water cycle processes, uncertainties of (unknown) empirical model parameters, as well as the absence of high resolution (both spatially and temporally) data. Data assimilation can mitigate this drawback by incorporating new sets of observations into models. In this effort, we use multi-mission satellite-derived remotely sensed observations to improve the performance of World-Wide Water Resources Assessment system (W3RA) hydrological model for estimating terrestrial water storages. For this purpose, we assimilate total water storage (TWS) data from the Gravity Recovery And Climate Experiment (GRACE) and surface soil moisture data from the Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) into W3RA. This is done to (i) improve model estimations of water stored in ground and soil moisture, and (ii) assess the impacts of each satellite of data (from GRACE and AMSR-E) and their combination on the final terrestrial water storage estimations. These data are assimilated into W3RA using the Ensemble Square-Root Filter (EnSRF) filtering technique over Mississippi Basin (the United States) and Murray-Darling Basin (Australia) between 2002 and 2013. In order to evaluate the results, independent ground-based groundwater and soil moisture measurements within each basin are used.

Keywords: data assimilation, GRACE, AMSR-E, hydrological model, EnSRF

Procedia PDF Downloads 271

Authors: Jacob Wahl, Jane Zhang

Abstract:

This paper describes the development and characterization of a prototype IoT network for use with agricultural imaging and monitoring applications. The sensor and gateway nodes are designed using the ESP32 SoC with integrated Bluetooth Low Energy 4.2 and Wi-Fi. A development board, the Arducam IoTai ESP32, is used for prototyping, testing, and power measurements. Google’s Firebase is used as the cloud storage site for image data collected by the sensor. The sensor node captures images using the OV2640 2MP camera module and transmits the image data to the gateway via Bluetooth Low Energy. The gateway then uploads the collected images to Firebase via a known nearby Wi-Fi network connection. This image data can then be processed and analyzed by computer vision and machine learning pipelines to assess crop growth or other needs. The sensor node achieves a wireless transmission data throughput of 220kbps while consuming 150mA of current; the sensor sleeps at 162µA. The sensor node device lifetime is estimated to be 682 days on a 6600mAh LiPo battery while acquiring five images per day based on the development board power measurements. This network can be utilized by any application that requires high data rates, low power consumption, short-range communication, and large amounts of data to be transmitted at low-frequency intervals.

Keywords: Bluetooth low energy, ESP32, firebase cloud, IoT, smart farming

Procedia PDF Downloads 128

Authors: Lauren C. Porter, Andrew Curtis, Eric Jefferis, Susanne Mitchell

Abstract:

A wealth of research has been generated examining the variation in crime across neighborhoods. However, there is also a striking degree of crime concentration within neighborhoods. A number of studies show that a small percentage of street segments, intersections, or addresses account for a large portion of crime. Not surprisingly, a focus on these crime hot spots can be an effective strategy for reducing community level crime and related ills, such as health problems. However, research is also limited in an important respect. Studies tend to use official data to identify hot spots, such as 911 calls or calls for service. While the use of call data may be more representative of the actual level and distribution of crime than some other official measures (e.g. arrest data), call data still suffer from the 'dark figure of crime.' That is, there is most certainly a degree of error between crimes that occur versus crimes that are reported to the police. In this study, we present an alternative method of identifying crime hot spots, that does not rely on official data. In doing so, we highlight the potential utility of neighborhood-insiders to identify and understand crime dynamics within geographic spaces. Specifically, we use spatial video and geo-narratives to record the crime insights of 36 police, ex-offenders, and residents of a high crime neighborhood in northeast Ohio. Spatial mentions of crime are mapped to identify participant-identified hot spots, and these are juxtaposed with calls for service (CFS) data. While there are bound to be differences between these two sources of data, we find that one location, in particular, a corner store, emerges as a hot spot for all three groups of participants. Yet it does not emerge when we examine CFS data. A closer examination of the space around this corner store and a qualitative analysis of narrative data reveal important clues as to why this store may indeed be a hot spot, but not generate disproportionate calls to the police. In short, our results suggest that researchers who rely solely on official data to study crime hot spots may risk missing some of the most dangerous places.

Keywords: crime, narrative, video, neighborhood

Procedia PDF Downloads 224

Authors: Nasim Eslamirad, Mahdi Rasoulinezhad, Francesco De Luca, Sadok Ben Yahia, Kimmo Sakari Lylykangas, Francesco Pilla

Abstract:

With the ongoing urbanization, cities face increasing environmental challenges impacting human well-being. To tackle these issues, data-driven approaches in urban analysis have gained prominence, leveraging urban data to promote sustainability. Integrating Machine Learning techniques enables researchers to analyze and predict complex environmental phenomena like Urban Heat Island occurrences in urban areas. This paper demonstrates the implementation of data-driven approach and interpretable Machine Learning algorithms with interpretability techniques to conduct comprehensive data analyses for sustainable urban design. The developed framework and algorithms are demonstrated for Tallinn, Estonia to develop sustainable urban strategies to mitigate urban heat waves. Geospatial data, preprocessed and labeled with UHI levels, are used to train various ML models, with Logistic Regression emerging as the best-performing model based on evaluation metrics to derive a mathematical equation representing the area with UHI or without UHI effects, providing insights into UHI occurrences based on buildings and urban features. The derived formula highlights the importance of building volume, height, area, and shape length to create an urban environment with UHI impact. The data-driven approach and derived equation inform mitigation strategies and sustainable urban development in Tallinn and offer valuable guidance for other locations with varying climates.

Keywords: data-driven approach, machine learning transparent models, interpretable machine learning models, urban heat island effect

Procedia PDF Downloads 15

Authors: Ibrahim A. Adeniran, Rui F. Zhu, Man S. Wong

Abstract:

Owing to the insufficiency in the spatial representativeness and continuity of in situ temperature measurements from weather stations (WS), the use of temperature measurement from WS for large-range diurnal analysis in heterogenous landscapes has been limited. This has made the accurate estimation of land surface temperature (LST) from remotely sensed data more crucial. Moreover, the study of dynamic interaction between the atmosphere and the physical surface of the Earth could be enhanced at both annual and diurnal scales by using optimal LST data derived from satellite sensors. The tradeoff between the spatial and temporal resolution of LSTs from satellite’s thermal infrared sensors (TIRS) has, however, been a major challenge, especially when high spatiotemporal LST data are recommended. It is well-known from existing literature that polar satellites have the advantage of high spatial resolution, while geostationary satellites have a high temporal resolution. Hence, this study is aimed at designing a framework for the cross-comparison of LST data from polar and geostationary satellites in a heterogeneous landscape. This could help to understand the relationship between the LST estimates from the two satellites and, consequently, their integration in diurnal LST analysis. Landsat-8 satellite data will be used as the representative of the polar satellite due to the availability of its long-term series, while the Himawari-8 satellite will be used as the data source for the geostationary satellite because of its improved TIRS. For the study area, Hong Kong Special Administrative Region (HK SAR) will be selected; this is due to the heterogeneity in the landscape of the region. LST data will be retrieved from both satellites using the Split window algorithm (SWA), and the resulting data will be validated by comparing satellite-derived LST data with temperature data from automatic WS in HK SAR. The LST data from the satellite data will then be separated based on the land use classification in HK SAR using the Global Land Cover by National Mapping Organization version3 (GLCNMO 2013) data. The relationship between LST data from Landsat-8 and Himawari-8 will then be investigated based on the land-use class and over different seasons of the year in order to account for seasonal variation in their relationship. The resulting relationship will be spatially and statistically analyzed and graphically visualized for detailed interpretation. Findings from this study will reveal the relationship between the two satellite data based on the land use classification within the study area and the seasons of the year. While the information provided by this study will help in the optimal combination of LST data from Polar (Landsat-8) and geostationary (Himawari-8) satellites, it will also serve as a roadmap in the annual and diurnal urban heat (UHI) analysis in Hong Kong SAR.

Keywords: automatic weather station, Himawari-8, Landsat-8, land surface temperature, land use classification, split window algorithm, urban heat island

Procedia PDF Downloads 57

Authors: Najrullah Khan, Athar Ali Khan

Abstract:

The Topp-Leone distribution was introduced by Topp- Leone in 1955. In this paper, an attempt has been made to fit Topp-Leone Generalized exponential (TPGE) distribution. A real survival data set is used for illustrations. Implementation is done using R and JAGS and appropriate illustrations are made. R and JAGS codes have been provided to implement censoring mechanism using both optimization and simulation tools. The main aim of this paper is to describe and illustrate the Bayesian modelling approach to the analysis of survival data. Emphasis is placed on the modeling of data and the interpretation of the results. Crucial to this is an understanding of the nature of the incomplete or 'censored' data encountered. Analytic approximation and simulation tools are covered here, but most of the emphasis is on Markov chain based Monte Carlo method including independent Metropolis algorithm, which is currently the most popular technique. For analytic approximation, among various optimization algorithms and trust region method is found to be the best. In this paper, TPGE model is also used to analyze the lifetime data in Bayesian paradigm. Results are evaluated from the above mentioned real survival data set. The analytic approximation and simulation methods are implemented using some software packages. It is clear from our findings that simulation tools provide better results as compared to those obtained by asymptotic approximation.

Keywords: Bayesian Inference, JAGS, Laplace Approximation, LaplacesDemon, posterior, R Software, simulation

Procedia PDF Downloads 510