Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360595
Islam Obaidat, Rami Mohawesh, M. Al-Ayyoub, Mohammad Al-Smadi, Y. Jararweh
Sentiment Analysis (SA) is the process of determining the sentiment of a text written in a natural language to be positive, negative or neutral. It is one of the most interesting subfields of natural language processing (NLP) and Web mining due to its diverse applications and the challenges associated with applying it on the massive amounts of textual data available online (especially, on social networks). Most of the current works on SA focus on the English language and work on the sentence-level or the document-level. This work focuses on the less studied version of SA, which is aspect-based SA (ABSA) for the Arabic language. Specifically, this work considers two ABSA tasks: aspect category determination and aspect category polarity determination, and makes use of the publicly available human annotated Arabic dataset (HAAD) along with its baseline experiments conducted by HAAD providers. In this work, several lexicon-based approaches are presented for the two tasks at hand and show that some of the presented approaches significantly outperforms the best known result on the given dataset.
{"title":"Enhancing the determination of aspect categories and their polarities in Arabic reviews using lexicon-based approaches","authors":"Islam Obaidat, Rami Mohawesh, M. Al-Ayyoub, Mohammad Al-Smadi, Y. Jararweh","doi":"10.1109/AEECT.2015.7360595","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360595","url":null,"abstract":"Sentiment Analysis (SA) is the process of determining the sentiment of a text written in a natural language to be positive, negative or neutral. It is one of the most interesting subfields of natural language processing (NLP) and Web mining due to its diverse applications and the challenges associated with applying it on the massive amounts of textual data available online (especially, on social networks). Most of the current works on SA focus on the English language and work on the sentence-level or the document-level. This work focuses on the less studied version of SA, which is aspect-based SA (ABSA) for the Arabic language. Specifically, this work considers two ABSA tasks: aspect category determination and aspect category polarity determination, and makes use of the publicly available human annotated Arabic dataset (HAAD) along with its baseline experiments conducted by HAAD providers. In this work, several lexicon-based approaches are presented for the two tasks at hand and show that some of the presented approaches significantly outperforms the best known result on the given dataset.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127173509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360567
Hamzah S. AlZu'bi, W. Al-Nuaimy, Jonathan Buckley, L. Sneddon, Iain S. Young
Over half a million fish are used in scientific procedures annually in the UK alone. Most fish are subject to invasive procedures which may cause pain distress or death. A range of procedures such as fin clipping, tagging and exposure to chemicals of low pH have been associated with change in behaviour. Abnormal behaviour after common procedures may influence and confuse experiment output.
{"title":"Real-time 3D fish tracking and behaviour analysis","authors":"Hamzah S. AlZu'bi, W. Al-Nuaimy, Jonathan Buckley, L. Sneddon, Iain S. Young","doi":"10.1109/AEECT.2015.7360567","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360567","url":null,"abstract":"Over half a million fish are used in scientific procedures annually in the UK alone. Most fish are subject to invasive procedures which may cause pain distress or death. A range of procedures such as fin clipping, tagging and exposure to chemicals of low pH have been associated with change in behaviour. Abnormal behaviour after common procedures may influence and confuse experiment output.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125177240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360558
Mario Reis, F. Perdigoto, Antonio Pires, Fernando Henriques, S. Faria, T. Fernandes
This paper proposes an advanced industrial controller prepared for hazardous industrial environments, namely natural gas odorisation. Its design and conception is focused on robustness and reliability, with high flexibility to allow local and remote monitoring and control. Instead of a centralized approach, where the computational load relies on a unique processor, we propose a distributed architecture, where the various control tasks are distributed among the existing microprocessors, like in a DCS system, but yet exhibiting a fast response time between inputs and outputs, like a PLC.The proposed architecture presents a high degree of flexibility and scalability, in order to allow an easy addition of new modules. By resorting to a script language interpreter installed in each I/O board, they may be reconfigured to a different functionally, thus increasing the system reliability and safety. An efficient and synchronized communication between boards ensures that all memory boards share the system status information, thus allowing each board to process individually. With the same performance and flexibility of a high-end PLC controller with full extras, like tactile HMI and TCP/IP remote control, we present an affordable gas odorizing system, which can be easily adapted for other industrial applications.
{"title":"Distributed processing system for gas odorization","authors":"Mario Reis, F. Perdigoto, Antonio Pires, Fernando Henriques, S. Faria, T. Fernandes","doi":"10.1109/AEECT.2015.7360558","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360558","url":null,"abstract":"This paper proposes an advanced industrial controller prepared for hazardous industrial environments, namely natural gas odorisation. Its design and conception is focused on robustness and reliability, with high flexibility to allow local and remote monitoring and control. Instead of a centralized approach, where the computational load relies on a unique processor, we propose a distributed architecture, where the various control tasks are distributed among the existing microprocessors, like in a DCS system, but yet exhibiting a fast response time between inputs and outputs, like a PLC.The proposed architecture presents a high degree of flexibility and scalability, in order to allow an easy addition of new modules. By resorting to a script language interpreter installed in each I/O board, they may be reconfigured to a different functionally, thus increasing the system reliability and safety. An efficient and synchronized communication between boards ensures that all memory boards share the system status information, thus allowing each board to process individually. With the same performance and flexibility of a high-end PLC controller with full extras, like tactile HMI and TCP/IP remote control, we present an affordable gas odorizing system, which can be easily adapted for other industrial applications.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125909790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360586
A. Ghaempanah, J. Faiz
Impact of the rotor end-winding on the force distribution of the stator end-winding using equivalent current sheets or a concentrated coil in each rotor slot has been so far considered in the literatures. However, the impact of the stator stepped end core on the force has not been studied yet. In this paper calculation methods for magnetic force exerted on the stator end-winding are first reviewed comprehensively; then the impact of some parameters on the magnetic force distribution on the stator end-winding of a 2-pole, 200 MVA turbo-generator under sudden three-phase short-circuit are studied. Three-dimensional finite element method (FEM) based on the reduced magnetic scalar potential formulation is used. The stator and rotor end-windings actual geometry is taken into account, except their cross section areas which are approximated by combination of straight line segments. To simplify the meshing process, stator stepped end core geometry is replaced by equivalent ramp geometry. Short-circuit currents of the generator windings are computed using two-dimensional transient FEM. It is shown that these parameters affect the stator end-winding magnetic force, particularly in the involutes part of the stator end-coils.
{"title":"Impact of rotor winding and stator stepped end core on magnetic force distribution on stator end-winding of turbogenerators","authors":"A. Ghaempanah, J. Faiz","doi":"10.1109/AEECT.2015.7360586","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360586","url":null,"abstract":"Impact of the rotor end-winding on the force distribution of the stator end-winding using equivalent current sheets or a concentrated coil in each rotor slot has been so far considered in the literatures. However, the impact of the stator stepped end core on the force has not been studied yet. In this paper calculation methods for magnetic force exerted on the stator end-winding are first reviewed comprehensively; then the impact of some parameters on the magnetic force distribution on the stator end-winding of a 2-pole, 200 MVA turbo-generator under sudden three-phase short-circuit are studied. Three-dimensional finite element method (FEM) based on the reduced magnetic scalar potential formulation is used. The stator and rotor end-windings actual geometry is taken into account, except their cross section areas which are approximated by combination of straight line segments. To simplify the meshing process, stator stepped end core geometry is replaced by equivalent ramp geometry. Short-circuit currents of the generator windings are computed using two-dimensional transient FEM. It is shown that these parameters affect the stator end-winding magnetic force, particularly in the involutes part of the stator end-coils.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129880608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360583
I. Al Ridhawi, M. Aloqaily
Autonomous service adaptation in cloud environments requires both location-awareness and the acquisition and utilization of contextual information. Statically configured service adaptation frameworks lack the ability to adapt to changing network conditions and geographical locations. This paper presents a framework that continuously derives updated configuration policies with respect to service selection and handover to third party cloud service providers. Location tracking and prediction empower the system to provide ongoing robust services for cloud service subscribers. To achieve this goal, the proposed work relies on a policy-based real-time simulator to evaluate possible new service provider handover configurations before actually applying them to the real network. Preliminary performance evaluation results demonstrate the significant enhancement of the outcome of the proposed framework in terms of continuous services for subscribers and load balancing for service providers.
{"title":"A policy-based location-aware framework for personalized services in cloud computing systems","authors":"I. Al Ridhawi, M. Aloqaily","doi":"10.1109/AEECT.2015.7360583","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360583","url":null,"abstract":"Autonomous service adaptation in cloud environments requires both location-awareness and the acquisition and utilization of contextual information. Statically configured service adaptation frameworks lack the ability to adapt to changing network conditions and geographical locations. This paper presents a framework that continuously derives updated configuration policies with respect to service selection and handover to third party cloud service providers. Location tracking and prediction empower the system to provide ongoing robust services for cloud service subscribers. To achieve this goal, the proposed work relies on a policy-based real-time simulator to evaluate possible new service provider handover configurations before actually applying them to the real network. Preliminary performance evaluation results demonstrate the significant enhancement of the outcome of the proposed framework in terms of continuous services for subscribers and load balancing for service providers.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129842367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360576
Hossam Faris, Ibrahim Aljarah, Ja'far Alqatawna
Krill Herd is a new optimization technique that was inspired by the herding behavior of real small crustaceans called Krills. The method was developed for continuous optimization problems and has recently been successfully applied to different complex problems. Feedforward neural network has a number of characteristics which make it suitable for solving complex classification problems. The training of the this type of neural networks is considered the most challenging operation. Training neural networks aims to find a nearly global optimal set of connection weights in a relatively short time. In this paper we propose an application of Krill Herd algorithm for training the Feedforward neural network and optimizing its connection weights. The developed neural network will be applied for an E-mail spam detection model. The model will be evaluated and compared to other two popular training algorithms; the Back-propagation algorithm and the Genetic Algorithm. Evaluation results show that the developed training approach using Krill Herd algorithm outperforms the other two algorithms.
{"title":"Optimizing Feedforward neural networks using Krill Herd algorithm for E-mail spam detection","authors":"Hossam Faris, Ibrahim Aljarah, Ja'far Alqatawna","doi":"10.1109/AEECT.2015.7360576","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360576","url":null,"abstract":"Krill Herd is a new optimization technique that was inspired by the herding behavior of real small crustaceans called Krills. The method was developed for continuous optimization problems and has recently been successfully applied to different complex problems. Feedforward neural network has a number of characteristics which make it suitable for solving complex classification problems. The training of the this type of neural networks is considered the most challenging operation. Training neural networks aims to find a nearly global optimal set of connection weights in a relatively short time. In this paper we propose an application of Krill Herd algorithm for training the Feedforward neural network and optimizing its connection weights. The developed neural network will be applied for an E-mail spam detection model. The model will be evaluated and compared to other two popular training algorithms; the Back-propagation algorithm and the Genetic Algorithm. Evaluation results show that the developed training approach using Krill Herd algorithm outperforms the other two algorithms.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131587038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360548
W. Almobaideen, Dimah A. Z. AlKhateeb
Mobile Ad-hoc NETworks (MANET) consists of mobile nodes that can move randomly resulting in a very dynamic network topology. MANET could use single or multipath routing protocols. Multipath routing protocols usually select more than one path between any source and destination. Stability based partially disjoint AOMDV (SPDA), is a multipath routing protocols that selects partially disjoint paths that are stable based on the history of these multiple paths kept by each node. In this paper a new protocol which is based on SPDA is presented and evaluated. The proposed protocol gets multiple loop-free partially link disjoint paths based on links stability and extends SPDA by tacking wireless carrier perceived contention level into consideration. The proposed protocol is called Contention and Stability-based Partially Disjoint AOMDV (CSPDA) protocol. Results show an obvious improvement of CSPDA over SPDA regarding the throughput and end to end delay performance metrics. Experiments have been conducted using Glomosim simulator package while varying different performance parameters such as the mobility speed of wireless nodes as well as the number of connections initiated by various nodes in the ad hoc network.
{"title":"CSPDA: Contention and stability aware partially disjoint AOMDV routing protocol","authors":"W. Almobaideen, Dimah A. Z. AlKhateeb","doi":"10.1109/AEECT.2015.7360548","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360548","url":null,"abstract":"Mobile Ad-hoc NETworks (MANET) consists of mobile nodes that can move randomly resulting in a very dynamic network topology. MANET could use single or multipath routing protocols. Multipath routing protocols usually select more than one path between any source and destination. Stability based partially disjoint AOMDV (SPDA), is a multipath routing protocols that selects partially disjoint paths that are stable based on the history of these multiple paths kept by each node. In this paper a new protocol which is based on SPDA is presented and evaluated. The proposed protocol gets multiple loop-free partially link disjoint paths based on links stability and extends SPDA by tacking wireless carrier perceived contention level into consideration. The proposed protocol is called Contention and Stability-based Partially Disjoint AOMDV (CSPDA) protocol. Results show an obvious improvement of CSPDA over SPDA regarding the throughput and end to end delay performance metrics. Experiments have been conducted using Glomosim simulator package while varying different performance parameters such as the mobility speed of wireless nodes as well as the number of connections initiated by various nodes in the ad hoc network.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114196016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360534
A. Ababneh
Aluminium nitride (AlN) is a promising material for high temperature applications in harsh environments. Reactively sputter-deposited AlN from an aluminium target is an interesting piezoelectric thin film material with high CMOS compatibility. The properties of thin films differ from bulk material, especially at high temperatures. Therefore, the influence of different annealing temperatures up to 1000°C on the microstructure of AlN thin films with a typical thickness of about 500 nm was investigated. The degree of c-axis orientation is unaffected for temperature between room temperature and 400°C. By further increasing the annealing temperature up to 800°C, the intensity of the (0 0 2) peak decreases slightly. At 1000°C, the peak intensity decreased by a factor of about 1.5. The grain size increased with increased annealing temperature, where the grain size was about 40 nm in “as deposited” state and increased to 50 nm at 800°C and to 100 nm at 1000°C. At 1000°C annealing temperature the columnar growth is disturbed by the formation of pinholes inside the film. Finally, the piezoelectric coefficients d33 and d31 were determined experimentally by laser scanning vibrometry. Effective values for temperatures between room temperature and 400°C were 3.0 and -1.0 pm/V, respectively. By further increase of the annealing temperature, the piezoelectric coefficients decreased. The effective d33 and d31 values for films annealed at 800°C were 1.8 pm/V and -0.77 pm/V, respectively. As for films annealed at 1000°C, no displacement profile was detected by the laser vibrometer, which indicates poor film structure.
{"title":"Impact of annealing temperature on piezoelectric and morphological properties of aluminium nitride thin films","authors":"A. Ababneh","doi":"10.1109/AEECT.2015.7360534","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360534","url":null,"abstract":"Aluminium nitride (AlN) is a promising material for high temperature applications in harsh environments. Reactively sputter-deposited AlN from an aluminium target is an interesting piezoelectric thin film material with high CMOS compatibility. The properties of thin films differ from bulk material, especially at high temperatures. Therefore, the influence of different annealing temperatures up to 1000°C on the microstructure of AlN thin films with a typical thickness of about 500 nm was investigated. The degree of c-axis orientation is unaffected for temperature between room temperature and 400°C. By further increasing the annealing temperature up to 800°C, the intensity of the (0 0 2) peak decreases slightly. At 1000°C, the peak intensity decreased by a factor of about 1.5. The grain size increased with increased annealing temperature, where the grain size was about 40 nm in “as deposited” state and increased to 50 nm at 800°C and to 100 nm at 1000°C. At 1000°C annealing temperature the columnar growth is disturbed by the formation of pinholes inside the film. Finally, the piezoelectric coefficients d33 and d31 were determined experimentally by laser scanning vibrometry. Effective values for temperatures between room temperature and 400°C were 3.0 and -1.0 pm/V, respectively. By further increase of the annealing temperature, the piezoelectric coefficients decreased. The effective d33 and d31 values for films annealed at 800°C were 1.8 pm/V and -0.77 pm/V, respectively. As for films annealed at 1000°C, no displacement profile was detected by the laser vibrometer, which indicates poor film structure.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115953068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360581
Elaf Abu Amrieh, Thair M. Hamtini, Ibrahim Aljarah
Educational data mining concerns of developing methods to discover hidden patterns from educational data. The quality of data mining techniques depends on the collected data and features. In this paper, we proposed a new student performance model with a new category of features, which called behavioral features. This type of features is related to the learner interactivity with e-learning system. We collect the data from an e-Learning system called Kalboard 360 using Experience API Web service (XAPI). After that, we use some data mining techniques such as Artificial Neural Network, Naïve Bayesian, and Decision Tree classifiers to evaluate the impact of such features on student's academic performance. The results reveal that there is a strong relationship between learner behaviors and its academic achievement. Results with different classification methods using behavioral features achieved up to 29% improvement in the classification accuracy compared to the same data set when removing such features.
{"title":"Preprocessing and analyzing educational data set using X-API for improving student's performance","authors":"Elaf Abu Amrieh, Thair M. Hamtini, Ibrahim Aljarah","doi":"10.1109/AEECT.2015.7360581","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360581","url":null,"abstract":"Educational data mining concerns of developing methods to discover hidden patterns from educational data. The quality of data mining techniques depends on the collected data and features. In this paper, we proposed a new student performance model with a new category of features, which called behavioral features. This type of features is related to the learner interactivity with e-learning system. We collect the data from an e-Learning system called Kalboard 360 using Experience API Web service (XAPI). After that, we use some data mining techniques such as Artificial Neural Network, Naïve Bayesian, and Decision Tree classifiers to evaluate the impact of such features on student's academic performance. The results reveal that there is a strong relationship between learner behaviors and its academic achievement. Results with different classification methods using behavioral features achieved up to 29% improvement in the classification accuracy compared to the same data set when removing such features.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121117227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-12-21DOI: 10.1109/AEECT.2015.7360560
G. Hassapis
In this article a brief introduction to the IEC61499 standard is made. This standard proposes reference architecture and language constructs for developing event-based software models for distributed control and automation systems. Based on this standard, a methodology is presented addressing a systematic stepwise software development for automation applications. The first step considers a high level abstract design of the software by the use of the Composite Function Block concept of the standard and the subsequent steps address the fine grained development of models for the components of the first step abstract design. At the final step the executable code is generated. Available software engineering tools that can be utilized to support the design steps are also presented.
{"title":"Component-based engineering of distributed control and automation software","authors":"G. Hassapis","doi":"10.1109/AEECT.2015.7360560","DOIUrl":"https://doi.org/10.1109/AEECT.2015.7360560","url":null,"abstract":"In this article a brief introduction to the IEC61499 standard is made. This standard proposes reference architecture and language constructs for developing event-based software models for distributed control and automation systems. Based on this standard, a methodology is presented addressing a systematic stepwise software development for automation applications. The first step considers a high level abstract design of the software by the use of the Composite Function Block concept of the standard and the subsequent steps address the fine grained development of models for the components of the first step abstract design. At the final step the executable code is generated. Available software engineering tools that can be utilized to support the design steps are also presented.","PeriodicalId":227019,"journal":{"name":"2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116486179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：