Pub Date : 2016-12-01DOI: 10.1109/ICENCO.2016.7856471
M. F. Hassanin, Abdullah M. Shoeb, A. Hassanien
For many decades, artificial neural network (ANN) proves successful results in thousands of problems in many disciplines. Back-propagation (BP) is one of the candidate algorithms to train ANN. Due to the way of BP to find the solution for the underlying problem, there is an important drawback of it, namely the stuck in local minima rather than the global one. Recent studies introduce meta-heuristic techniques to train ANN. The current work proposes a framework in which grey wolf optimizer (GWO) provides the initial solution to a BP ANN. Five datasets are used to benchmark GWO BP performance with other competitors. The first competitor is an optimized BP ANN based on genetic algorithm. The second is a BP ANN powered by particle swarm optimizer. The third is the BP algorithm itself and lastly a feedforward ANN enhanced by GWO. The carried experiments show that GWOBP outperforms the compared algorithms.
{"title":"Grey wolf optimizer-based back-propagation neural network algorithm","authors":"M. F. Hassanin, Abdullah M. Shoeb, A. Hassanien","doi":"10.1109/ICENCO.2016.7856471","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856471","url":null,"abstract":"For many decades, artificial neural network (ANN) proves successful results in thousands of problems in many disciplines. Back-propagation (BP) is one of the candidate algorithms to train ANN. Due to the way of BP to find the solution for the underlying problem, there is an important drawback of it, namely the stuck in local minima rather than the global one. Recent studies introduce meta-heuristic techniques to train ANN. The current work proposes a framework in which grey wolf optimizer (GWO) provides the initial solution to a BP ANN. Five datasets are used to benchmark GWO BP performance with other competitors. The first competitor is an optimized BP ANN based on genetic algorithm. The second is a BP ANN powered by particle swarm optimizer. The third is the BP algorithm itself and lastly a feedforward ANN enhanced by GWO. The carried experiments show that GWOBP outperforms the compared algorithms.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115262206","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856437
Walaa Abdellatief, Osama S. Youness, H. Abdelkader, Mohee Hadhoud
Wireless sensor network applications are composed of a vast number of inexpensive battery-powered sensors. One of its primary applications is environmental monitoring for physical phenomena in rigid areas such as forests and volcanoes. In such applications, a large number of sensors are randomly scattered by aircraft over the area of monitoring. These applications mainly depend on clustering to arrange nodes into groups to facilitate their communication. Previously proposed clustering techniques are classified into two types, which are distributed or centralized techniques. Each of these types has advantages as well as some flaws. In this paper, we propose a globally distributed clustering technique. This technique depends on some global information about the network to allow each node to decide its role in the produced clusters locally. This information is assumed to be known by default by the BS for any communication or topological control activities. Simulation results show that the proposed technique achieves less power consumption and therefore longer network lifetime when compared with other clustering techniques.
{"title":"Global distributed clustering technique for randomly deployed wireless sensor networks","authors":"Walaa Abdellatief, Osama S. Youness, H. Abdelkader, Mohee Hadhoud","doi":"10.1109/ICENCO.2016.7856437","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856437","url":null,"abstract":"Wireless sensor network applications are composed of a vast number of inexpensive battery-powered sensors. One of its primary applications is environmental monitoring for physical phenomena in rigid areas such as forests and volcanoes. In such applications, a large number of sensors are randomly scattered by aircraft over the area of monitoring. These applications mainly depend on clustering to arrange nodes into groups to facilitate their communication. Previously proposed clustering techniques are classified into two types, which are distributed or centralized techniques. Each of these types has advantages as well as some flaws. In this paper, we propose a globally distributed clustering technique. This technique depends on some global information about the network to allow each node to decide its role in the produced clusters locally. This information is assumed to be known by default by the BS for any communication or topological control activities. Simulation results show that the proposed technique achieves less power consumption and therefore longer network lifetime when compared with other clustering techniques.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114282842","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856466
H. A. Elkader, G. Abdel-Hamid, A. S. T. El-dien, Asmaa A. Nassif
Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) system has been implemented to achieve a good service and boost the data rate in wireless communication system. Space Time Frequency (STF) is used to enhance the diversity gain. This paper aims at a performance analysis of MIMO-OFDM system using two different STF codes with a random beamforming. The two proposed codes give better bit error rates (BER) performance as compared to the BER performance of STF of Alamouti code for MIMO-OFDM system. We have applied STF with random beamforming to improve the performance of the whole system for different diversity. The performance of the second STFC is better than the performance of the first STFC at high signal to noise ratio (SNR). It is also observed that the BER performance of the two proposed schemes with beamforming is better than the BER performance of space-time block codes (STBC) with beamforming.
{"title":"Combined Space-time-frequency codes for four time slots with beamforming","authors":"H. A. Elkader, G. Abdel-Hamid, A. S. T. El-dien, Asmaa A. Nassif","doi":"10.1109/ICENCO.2016.7856466","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856466","url":null,"abstract":"Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) system has been implemented to achieve a good service and boost the data rate in wireless communication system. Space Time Frequency (STF) is used to enhance the diversity gain. This paper aims at a performance analysis of MIMO-OFDM system using two different STF codes with a random beamforming. The two proposed codes give better bit error rates (BER) performance as compared to the BER performance of STF of Alamouti code for MIMO-OFDM system. We have applied STF with random beamforming to improve the performance of the whole system for different diversity. The performance of the second STFC is better than the performance of the first STFC at high signal to noise ratio (SNR). It is also observed that the BER performance of the two proposed schemes with beamforming is better than the BER performance of space-time block codes (STBC) with beamforming.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121852121","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856451
R. Gharieb, G. Gendy, A. Abdelfattah
This paper presents a technique for incorporating local data and membership information into the standard fuzzy C-means (FCM) algorithm. The objective function associated with the technique consists of a modified version of the standard FCM function plus a weighted regularized FCM-like one. In the first function, the Euclidian pixel-to-cluster distances are computed using the original data. However, in the second one, they are computed by replacing the original data by locally smoothed one to reduce additive noise. Both distances are also modified to account for the distances in the pixel neighborhood. In both functions, to incorporate the local membership information, the resultant pixel-to-cluster distance is weighted by the reciprocal of the average of the membership to this cluster in the pixel vicinity. Results clustering synthetic and medical images are presented. The performance of the proposed robust local data and membership information FCM (RFCM) is compared with the standard FCM, local spatial information based FCM (SFCM), and data and local data and membership weighted FCM (LDMWFCM).
{"title":"A robust local data and membership information based FCM algorithm for noisy image segmentation","authors":"R. Gharieb, G. Gendy, A. Abdelfattah","doi":"10.1109/ICENCO.2016.7856451","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856451","url":null,"abstract":"This paper presents a technique for incorporating local data and membership information into the standard fuzzy C-means (FCM) algorithm. The objective function associated with the technique consists of a modified version of the standard FCM function plus a weighted regularized FCM-like one. In the first function, the Euclidian pixel-to-cluster distances are computed using the original data. However, in the second one, they are computed by replacing the original data by locally smoothed one to reduce additive noise. Both distances are also modified to account for the distances in the pixel neighborhood. In both functions, to incorporate the local membership information, the resultant pixel-to-cluster distance is weighted by the reciprocal of the average of the membership to this cluster in the pixel vicinity. Results clustering synthetic and medical images are presented. The performance of the proposed robust local data and membership information FCM (RFCM) is compared with the standard FCM, local spatial information based FCM (SFCM), and data and local data and membership weighted FCM (LDMWFCM).","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"39 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114086214","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856465
Ibrahim Salah, W. Saad, M. Shokair, M. Elkordy
Cooperative spectrum sensing assumes an essential part in cognitive radio network due to having the capacity to enhance spectrum sensing performance and reduce probability of error in fading and shadowing channels. In fact, clustering scheme and cooperative spectrum sensing are combined to reduce Jostle of reporting channel, improve performance of sensing and reduce the computational cost. Many methods of cooperative spectrum sensing have been proposed based on clustering technique. In this paper, proposed approach will be suggested based on clustering to minimize the total power consumed by CRN in order to perform spectrum sensing, transmit decision to cluster head, and transmit the final decision to the fusion center. This is done by using multi objective genetic algorithm. Simulation results show that our proposed algorithm can achieve better energy gain which is less than conventional cluster based cooperative spectrum sensing scheme. Moreover, it increases performance of CRN.
{"title":"Minimizing energy of cluster-based Cooperative Spectrum Sensing in CRN using Multi Objective Genetic Algorithm","authors":"Ibrahim Salah, W. Saad, M. Shokair, M. Elkordy","doi":"10.1109/ICENCO.2016.7856465","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856465","url":null,"abstract":"Cooperative spectrum sensing assumes an essential part in cognitive radio network due to having the capacity to enhance spectrum sensing performance and reduce probability of error in fading and shadowing channels. In fact, clustering scheme and cooperative spectrum sensing are combined to reduce Jostle of reporting channel, improve performance of sensing and reduce the computational cost. Many methods of cooperative spectrum sensing have been proposed based on clustering technique. In this paper, proposed approach will be suggested based on clustering to minimize the total power consumed by CRN in order to perform spectrum sensing, transmit decision to cluster head, and transmit the final decision to the fusion center. This is done by using multi objective genetic algorithm. Simulation results show that our proposed algorithm can achieve better energy gain which is less than conventional cluster based cooperative spectrum sensing scheme. Moreover, it increases performance of CRN.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127978050","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856453
Mai Mohamed Mahmoud Farag, T. Elghazaly, H. Hefny
In this paper we apply particle swarm optimization (PSO) feature selection to enhance Hidden Markov Model (HMM) states and parameters for face recognition systems. Ideal Feature selection for face images based on the idea of collaborative behavior of bird flocking to reduce the feature size and hence recognition time complicity. The framework has been inspected on 400 face pictures of the Olivetti Research Laboratory face database. The experiments demonstrated an acknowledgment rate of 98.5%, using half of the images for training.
{"title":"Face recognition system using HMM-PSO for feature selection","authors":"Mai Mohamed Mahmoud Farag, T. Elghazaly, H. Hefny","doi":"10.1109/ICENCO.2016.7856453","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856453","url":null,"abstract":"In this paper we apply particle swarm optimization (PSO) feature selection to enhance Hidden Markov Model (HMM) states and parameters for face recognition systems. Ideal Feature selection for face images based on the idea of collaborative behavior of bird flocking to reduce the feature size and hence recognition time complicity. The framework has been inspected on 400 face pictures of the Olivetti Research Laboratory face database. The experiments demonstrated an acknowledgment rate of 98.5%, using half of the images for training.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132729136","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856458
Mohamed Ali, Eman S. Nasr, Mervat H. Geith
A Feature Model (FM) is a powerful tool used to model requirements in any domain on a high abstract level. A FM is applied to model variable and common assets of Software Product Lines (SPLs). The industrial importance of a FM has been increasing rapidly in the last years. FM is built with a set of notations to maintain the relations between the modeled requirements. Day after day feature modeling has proved its ability to represent and manage requirements of SPLs in different domains. In addition, FM could also be extended and modified to support the nature of various domains. In this paper, we extend the FM to provide a technique for representing functional requirements of a SPL for an ERP. This technique takes the advantages of the hierarchical structure of ERP systems and merges them with the FM. The modeled requirements on the FM will be transformed into a conceptual model, to increase the stakeholders' involvement in the requirements engineering process. The technique used the principles of the form-based model to represent the requirements in a conceptual model.
{"title":"Mapping functional requirements of ERP SPL on an extended form of Feature Model","authors":"Mohamed Ali, Eman S. Nasr, Mervat H. Geith","doi":"10.1109/ICENCO.2016.7856458","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856458","url":null,"abstract":"A Feature Model (FM) is a powerful tool used to model requirements in any domain on a high abstract level. A FM is applied to model variable and common assets of Software Product Lines (SPLs). The industrial importance of a FM has been increasing rapidly in the last years. FM is built with a set of notations to maintain the relations between the modeled requirements. Day after day feature modeling has proved its ability to represent and manage requirements of SPLs in different domains. In addition, FM could also be extended and modified to support the nature of various domains. In this paper, we extend the FM to provide a technique for representing functional requirements of a SPL for an ERP. This technique takes the advantages of the hierarchical structure of ERP systems and merges them with the FM. The modeled requirements on the FM will be transformed into a conceptual model, to increase the stakeholders' involvement in the requirements engineering process. The technique used the principles of the form-based model to represent the requirements in a conceptual model.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125665490","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856436
M. Torky, A. Meligy, H. Ibrahim
Online Social Networks (OSNs) are a great venue for scammers to impersonate the identities of users via creating fake profiles. Fake profiles are a popular tool for the intruders which can be used to carry out malicious activities such as impersonation attacks and harming persons' reputation and privacy in (OSN). Hence, recognizing the identities of fake profiles is one of the critical security problems in OSNs. In this paper, we proposed a detection mechanism called Fake Profiles Recognizer (FPR) for recognizing and detecting Fake Profiles in OSNs. The detection methodology in FPR is based on the functionality of Regular Expression and Deterministic Finite Automaton (DFA) approaches for recognizing the identity of profiles. We evaluated our detection system on three popular types of Online Social Networks: Facebook, Google+, and Twitter. The results explored high accuracy, efficiency, and low False Positive Rate of FPR mechanism in detecting the identities of Fake Profiles. In addition, our proposed detection mechanism achieved strong competitive results compared with other detection mechanisms in the literature.
{"title":"Recognizing Fake identities in Online Social Networks based on a Finite Automaton approach","authors":"M. Torky, A. Meligy, H. Ibrahim","doi":"10.1109/ICENCO.2016.7856436","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856436","url":null,"abstract":"Online Social Networks (OSNs) are a great venue for scammers to impersonate the identities of users via creating fake profiles. Fake profiles are a popular tool for the intruders which can be used to carry out malicious activities such as impersonation attacks and harming persons' reputation and privacy in (OSN). Hence, recognizing the identities of fake profiles is one of the critical security problems in OSNs. In this paper, we proposed a detection mechanism called Fake Profiles Recognizer (FPR) for recognizing and detecting Fake Profiles in OSNs. The detection methodology in FPR is based on the functionality of Regular Expression and Deterministic Finite Automaton (DFA) approaches for recognizing the identity of profiles. We evaluated our detection system on three popular types of Online Social Networks: Facebook, Google+, and Twitter. The results explored high accuracy, efficiency, and low False Positive Rate of FPR mechanism in detecting the identities of Fake Profiles. In addition, our proposed detection mechanism achieved strong competitive results compared with other detection mechanisms in the literature.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132417828","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856460
Asmaa Elbamby, E. Hemayed, D. Helal, M. Rehan
Despite License Plate Recognition is mainly regarded as a solved problem; most of the techniques have been mainly developed for specific country or special formats which can strictly limits their applicability. There have been extensive studies of license plate detection since the 70s. The suggested approaches have difficulties in processing high-resolution imagery in real-time. This paper presents a novel algorithm for real-time automatic multi-style license plate detection in videos. The proposed algorithm can detect in a real time multiple license plates with various sizes in unfamiliar and complex environment. In this system, candidate plate regions are extracted using a preprocessing function to increase accuracy while decreasing computational time. Then a tree of LBP-based cascade classifiers is used to classify the candidate plate regions into one of the learned style. The proposed approach has been applied to Egyptian license plates with four different plate styles. The proposed approach achieved a success rate of 94% at 25 frames/sec using a moderate laptop.
{"title":"Real-time automatic multi-style license plate detection in videos","authors":"Asmaa Elbamby, E. Hemayed, D. Helal, M. Rehan","doi":"10.1109/ICENCO.2016.7856460","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856460","url":null,"abstract":"Despite License Plate Recognition is mainly regarded as a solved problem; most of the techniques have been mainly developed for specific country or special formats which can strictly limits their applicability. There have been extensive studies of license plate detection since the 70s. The suggested approaches have difficulties in processing high-resolution imagery in real-time. This paper presents a novel algorithm for real-time automatic multi-style license plate detection in videos. The proposed algorithm can detect in a real time multiple license plates with various sizes in unfamiliar and complex environment. In this system, candidate plate regions are extracted using a preprocessing function to increase accuracy while decreasing computational time. Then a tree of LBP-based cascade classifiers is used to classify the candidate plate regions into one of the learned style. The proposed approach has been applied to Egyptian license plates with four different plate styles. The proposed approach achieved a success rate of 94% at 25 frames/sec using a moderate laptop.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122190441","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 : 2016-12-01DOI: 10.1109/ICENCO.2016.7856442
A. Sahlol, A. Ewees, Ahmed Monem Hemdan, A. Hassanien
Analytical prediction of oxidative stress biomarkers in ecosystem provides an expressive result for many stressors. These oxidative stress biomarkers including superoxide dismutase, glutathione peroxidase and catalase activity in fish liver tissue were analyzed within feeding different levels of selenium nanoparticles. Se-nanoparticles represent a salient defense mechanism in oxidative stress within certain limits; however, stress can be engendered from toxic levels of these nanoparticles. For instance, prediction of the level of pollution and/or stressors was elucidated to be improved with different levels of selenium nanoparticles using the bio-inspired Sine-Cosine algorithm (SCA). In this paper, we improved the prediction accuracy of liver enzymes of fish fed by nano-selenite by developing a neural network model based on SCA, that can train and update the weights and the biases of the network until reaching the optimum value. The performance of the proposed model is better and achieved more efficient than other models.
{"title":"Training feedforward neural networks using Sine-Cosine algorithm to improve the prediction of liver enzymes on fish farmed on nano-selenite","authors":"A. Sahlol, A. Ewees, Ahmed Monem Hemdan, A. Hassanien","doi":"10.1109/ICENCO.2016.7856442","DOIUrl":"https://doi.org/10.1109/ICENCO.2016.7856442","url":null,"abstract":"Analytical prediction of oxidative stress biomarkers in ecosystem provides an expressive result for many stressors. These oxidative stress biomarkers including superoxide dismutase, glutathione peroxidase and catalase activity in fish liver tissue were analyzed within feeding different levels of selenium nanoparticles. Se-nanoparticles represent a salient defense mechanism in oxidative stress within certain limits; however, stress can be engendered from toxic levels of these nanoparticles. For instance, prediction of the level of pollution and/or stressors was elucidated to be improved with different levels of selenium nanoparticles using the bio-inspired Sine-Cosine algorithm (SCA). In this paper, we improved the prediction accuracy of liver enzymes of fish fed by nano-selenite by developing a neural network model based on SCA, that can train and update the weights and the biases of the network until reaching the optimum value. The performance of the proposed model is better and achieved more efficient than other models.","PeriodicalId":332360,"journal":{"name":"2016 12th International Computer Engineering Conference (ICENCO)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127773219","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：