Pub Date : 2018-07-01DOI: 10.1109/IWOBI.2018.8464134
Carlos Gomez, G. González, Esteban Meneses
An accurate understanding of the evolutionary history of virus species could help in the development of prevention measures or new treatments. Most current tools offer phylogenetic analysis focused on mutations as the main evolutionary mechanism and ignore inconsistencies caused by recombination events. This work intends to describe an algorithm for history reconstruction of recombination events detected from a set of viral genomic sequences. Preliminary results are provided from the analysis of some sequences of Human Adenovirus D with the proposed algorithm.
{"title":"Algorithm for History Reconstruction of Viral Recombination Events: Preliminary Results","authors":"Carlos Gomez, G. González, Esteban Meneses","doi":"10.1109/IWOBI.2018.8464134","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464134","url":null,"abstract":"An accurate understanding of the evolutionary history of virus species could help in the development of prevention measures or new treatments. Most current tools offer phylogenetic analysis focused on mutations as the main evolutionary mechanism and ignore inconsistencies caused by recombination events. This work intends to describe an algorithm for history reconstruction of recombination events detected from a set of viral genomic sequences. Preliminary results are provided from the analysis of some sequences of Human Adenovirus D with the proposed algorithm.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131147454","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 : 2018-07-01DOI: 10.1109/IWOBI.2018.8464130
J. Molina-Mora, Rebeca Campos-Sánchez, Fernando Quiles García
Pseudomonas aeruginosa is an opportunistic pathogen that causes a variety of infections in humans and frequently develops mechanisms of resistance to antibiotics, which makes its treatment difficult. In this study we applied gene expression analysis using data mining techniques and network analysis to evaluate the temporal effects of exposure to ciprofloxacin and the changes caused by the loss of function of LexA, a regulator of the SOS response to the cellular stress. Initially, global differential expression profiles using clustering algorithms suggested that the effects of antibiotic exposure were determined primarily by time and not by loss of LexA function. This was verified by performing attribute selection and differential expression analysis among conditions, where less than 3.3% of maximum difference between strains but up to 21% of differences were observed over time. Together with network analysis, a significant increase in topological metrics was determined when evaluating temporal changes. Functional annotation showed metabolic pathways enriched over time but not when comparing strains. Overall, the results obtained revealed that the response to ciprofloxacin tends to be exacerbated over time and that it remains stable in the face of the loss of function of LexA activity.
{"title":"Gene Expression Dynamics Induced by Ciprofloxacin and Loss of Lexa Function in Pseudomonas Aeruginosa PAO1 Using Data Mining and Network Analysis","authors":"J. Molina-Mora, Rebeca Campos-Sánchez, Fernando Quiles García","doi":"10.1109/IWOBI.2018.8464130","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464130","url":null,"abstract":"Pseudomonas aeruginosa is an opportunistic pathogen that causes a variety of infections in humans and frequently develops mechanisms of resistance to antibiotics, which makes its treatment difficult. In this study we applied gene expression analysis using data mining techniques and network analysis to evaluate the temporal effects of exposure to ciprofloxacin and the changes caused by the loss of function of LexA, a regulator of the SOS response to the cellular stress. Initially, global differential expression profiles using clustering algorithms suggested that the effects of antibiotic exposure were determined primarily by time and not by loss of LexA function. This was verified by performing attribute selection and differential expression analysis among conditions, where less than 3.3% of maximum difference between strains but up to 21% of differences were observed over time. Together with network analysis, a significant increase in topological metrics was determined when evaluating temporal changes. Functional annotation showed metabolic pathways enriched over time but not when comparing strains. Overall, the results obtained revealed that the response to ciprofloxacin tends to be exacerbated over time and that it remains stable in the face of the loss of function of LexA activity.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127597660","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 : 2018-07-01DOI: 10.1109/IWOBI.2018.8464199
I. Quiros-Fernandez, J. Molina-Mora, M. Kop-Montero, E. Salas-Hidalgo, R. Mora-Rodríguez
Cancer is a group of heterogeneous and complex diseases, with limited therapeutic options due to the recurrent emergence of drug resistance. Sphingolipids are bioactive molecules that participate in signaling of cell death or proliferation. Because there is no laboratory test to rapidly predict a tumor chemosensitivity, we propose the use of a sphingomyelin fluorescent analogue as a chemotherapy response sensor. Through kinetic live cell imaging experiments, we extracted 1611 fluorescence features with single cell time resolved resolution. After comparing the variations in this reporter, induced by different chemotherapies, it was possible to reduce the system complexity to elaborate a decision tree algorithm based in only 3 fluorescence features capable of predicting chemosensitivity with a 73% of accuracy. This approach serves as a proof of principle for the possible future implementation of a chemosensitivity test that could be used with patient primary tumors, and thus contribute to personalized therapy against cancer.
{"title":"Predicting Cancer Chemosensitivity Based on Intensity/Distribution Profiles of Cells Loaded with a Fluorescent Sphingolipid Analogue","authors":"I. Quiros-Fernandez, J. Molina-Mora, M. Kop-Montero, E. Salas-Hidalgo, R. Mora-Rodríguez","doi":"10.1109/IWOBI.2018.8464199","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464199","url":null,"abstract":"Cancer is a group of heterogeneous and complex diseases, with limited therapeutic options due to the recurrent emergence of drug resistance. Sphingolipids are bioactive molecules that participate in signaling of cell death or proliferation. Because there is no laboratory test to rapidly predict a tumor chemosensitivity, we propose the use of a sphingomyelin fluorescent analogue as a chemotherapy response sensor. Through kinetic live cell imaging experiments, we extracted 1611 fluorescence features with single cell time resolved resolution. After comparing the variations in this reporter, induced by different chemotherapies, it was possible to reduce the system complexity to elaborate a decision tree algorithm based in only 3 fluorescence features capable of predicting chemosensitivity with a 73% of accuracy. This approach serves as a proof of principle for the possible future implementation of a chemosensitivity test that could be used with patient primary tumors, and thus contribute to personalized therapy against cancer.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131656491","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 : 2018-07-01DOI: 10.1109/IWOBI.2018.8464214
Blaž Meden, P. Peer, V. Štruc
Privacy is a highly debatable topic in the modern technological era. With the advent of massive video and image data (which in a lot of cases contains personal information on the recorded subjects), there is an imminent need for efficient privacy protection mechanisms. To this end, we develop in this work a novel Face Deidentification Network (FaDeNet) that is able to alter the input faces in such a way that automated recognition fail to recognize the subjects in the images, while this is still possible for human observers. FaDeNet is based an encoder-decoder architecture that is trained to auto-encode the input image, while (at the same time) minimizing the recognition performance of a secondary network that is used as an socalled identity critic in FaDeNet. We present experiments on the Radbound Faces Dataset and observe encouraging results.
{"title":"Selective Face Deidentification with End-to-End Perceptual Loss Learning","authors":"Blaž Meden, P. Peer, V. Štruc","doi":"10.1109/IWOBI.2018.8464214","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464214","url":null,"abstract":"Privacy is a highly debatable topic in the modern technological era. With the advent of massive video and image data (which in a lot of cases contains personal information on the recorded subjects), there is an imminent need for efficient privacy protection mechanisms. To this end, we develop in this work a novel Face Deidentification Network (FaDeNet) that is able to alter the input faces in such a way that automated recognition fail to recognize the subjects in the images, while this is still possible for human observers. FaDeNet is based an encoder-decoder architecture that is trained to auto-encode the input image, while (at the same time) minimizing the recognition performance of a secondary network that is used as an socalled identity critic in FaDeNet. We present experiments on the Radbound Faces Dataset and observe encouraging results.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128237509","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 : 2018-07-01DOI: 10.1109/IWOBI.2018.8464136
M. L.Nunez, D. Dajles, Francisco Siles
Given the resemblance between the human body and that of a humanoid robot, a very intuitive control system might use motion capture; the system would track the motion of different key joints along the body of the human operator and the robot should mimic the action. To mimic the human's actions, a structure that supports and solves the issues related to motion tracking, human-robot figure relation, motion stability, and other issues is needed. This project consist of the development of a teleoperation system, which would allow a NAO humanoid robot to behave as a human motion imitator, using an optical motion capture system.
{"title":"Teleoperation of a Humanoid Robot Using an Optical Motion Capture System","authors":"M. L.Nunez, D. Dajles, Francisco Siles","doi":"10.1109/IWOBI.2018.8464136","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464136","url":null,"abstract":"Given the resemblance between the human body and that of a humanoid robot, a very intuitive control system might use motion capture; the system would track the motion of different key joints along the body of the human operator and the robot should mimic the action. To mimic the human's actions, a structure that supports and solves the issues related to motion tracking, human-robot figure relation, motion stability, and other issues is needed. This project consist of the development of a teleoperation system, which would allow a NAO humanoid robot to behave as a human motion imitator, using an optical motion capture system.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132183066","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 : 2018-07-01DOI: 10.1109/IWOBI.2018.8464180
Saúl Calderón Ramírez, Jorge Castro, Manuel Zurnbado
This paper presents a novel computational optimization of the deceived non local means filter using moving average and symmetric weighting. The proposed optimization is compared with different approaches that reduce the computational cost of the deceived non local means filter. Furthermore, the impact of parallelizing different optimization approaches is assessed by evaluating the execution time and scalability in Xeon Phi KNL architecture. The proposed optimization for the sequential implementation achieved a 90x speedup, while its parallelized implementation yielded a speedup of up to 1662x.
{"title":"DNLM-MA-P: A Parallelization of the Deceived Non Local Means Filter with Moving Average and Symmetric Weighting","authors":"Saúl Calderón Ramírez, Jorge Castro, Manuel Zurnbado","doi":"10.1109/IWOBI.2018.8464180","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464180","url":null,"abstract":"This paper presents a novel computational optimization of the deceived non local means filter using moving average and symmetric weighting. The proposed optimization is compared with different approaches that reduce the computational cost of the deceived non local means filter. Furthermore, the impact of parallelizing different optimization approaches is assessed by evaluating the execution time and scalability in Xeon Phi KNL architecture. The proposed optimization for the sequential implementation achieved a 90x speedup, while its parallelized implementation yielded a speedup of up to 1662x.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129507126","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 : 2018-07-01DOI: 10.1109/IWOBI.2018.8464195
Pablo Soto-Quiros, A. Torokhti
New multi-objective operators of random signals are presented in this paper. The new operators improve, under a unrestrictive condition, the performance of known techniques: the generalized Karhunen-Loéve transform, the transform considered by Brillinger and the generalized Brillinger-like transform. This is obtained by particular design of new operators which have more parameters to optimize than that of other operators described in literature.
{"title":"Multi-Objective Operator for Optimal Compression and De-compression of Random Signals","authors":"Pablo Soto-Quiros, A. Torokhti","doi":"10.1109/IWOBI.2018.8464195","DOIUrl":"https://doi.org/10.1109/IWOBI.2018.8464195","url":null,"abstract":"New multi-objective operators of random signals are presented in this paper. The new operators improve, under a unrestrictive condition, the performance of known techniques: the generalized Karhunen-Loéve transform, the transform considered by Brillinger and the generalized Brillinger-like transform. This is obtained by particular design of new operators which have more parameters to optimize than that of other operators described in literature.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"32 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131433474","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 : 2018-07-01DOI: 10.1109/iwobi.2018.8464196
Juan Carlos Laurencio-Molina, C. Salazar-García
Tankless water heaters (TWHs) have been become more popular day-by-day in special because of the low-power consumption that characterizes these devices in comparison with the tank water heaters. Nonetheless, it is desirable that these systems have a rapid response to disturbances such as changes in water flow or the inlet temperature. Different methods of classic control have been used for solving this problem for decades. These techniques provide a good solution although not necessarily the optimal one. With the recent boom in automatic control techniques based on Artificial Neural Networks (ANNs) [1]–[3] and the scaling in terms of computational power of embedded systems, this has led to the use of ANNs in low-profile embedded systems. In this work, we present an implementation of an ANN for a commercial application of a TWH running on a low-profile embedded system where we demonstrated that the stabilization time is reduced by up to 25% whilst the overshoot by up to 50%, both in comparison with a classic methods of automatic control using a low-performance microcontroller.
{"title":"Design of an Artificial Neural Network Controller for a Tankless Water Heater By Using a Low-Profile Embedded System","authors":"Juan Carlos Laurencio-Molina, C. Salazar-García","doi":"10.1109/iwobi.2018.8464196","DOIUrl":"https://doi.org/10.1109/iwobi.2018.8464196","url":null,"abstract":"Tankless water heaters (TWHs) have been become more popular day-by-day in special because of the low-power consumption that characterizes these devices in comparison with the tank water heaters. Nonetheless, it is desirable that these systems have a rapid response to disturbances such as changes in water flow or the inlet temperature. Different methods of classic control have been used for solving this problem for decades. These techniques provide a good solution although not necessarily the optimal one. With the recent boom in automatic control techniques based on Artificial Neural Networks (ANNs) [1]–[3] and the scaling in terms of computational power of embedded systems, this has led to the use of ANNs in low-profile embedded systems. In this work, we present an implementation of an ANN for a commercial application of a TWH running on a low-profile embedded system where we demonstrated that the stabilization time is reduced by up to 25% whilst the overshoot by up to 50%, both in comparison with a classic methods of automatic control using a low-performance microcontroller.","PeriodicalId":127078,"journal":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123484496","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：