Jesus Silva - Academia.edu (original) (raw)

Papers by Jesus Silva

Procedia Computer Science, 2020

External cause injuries are defined as intentionally or unintentionally harm or injury to a perso... more External cause injuries are defined as intentionally or unintentionally harm or injury to a person, which may be caused by trauma, poisoning, assault, accidents, etc., being fatal (fatal injury) or not leading to death (non-fatal injury). External injuries have been considered a global health problem for two decades. This work aims to determine criminal patterns using data mining techniques to a sample of patients from Mumbai city in India.

Procedia Computer Science, 2019

Today, as technologies mature and people are encouraged to contribute data to organizations' data... more Today, as technologies mature and people are encouraged to contribute data to organizations' databases, more transactions are being captured than ever before. Meanwhile, improvements in data storage technologies have made the cost of evaluating, selecting, and destroying legacy data considerably greater than simply letting it accumulate. On the one hand, the excess of stored data has considerably increased the opportunities to interrelate and analyze them, while the moderate enthusiasm generated by data warehousing and data mining in the 1990s has been replaced by a rampant euphoria about big data and data analytics. But, is this as wonderful as seems? This paper presents a risk analysis of Big Data and Big Data Analytics based on a review of quality factors.

In the last few decades, the constant growth of digital images, as the main source of information... more In the last few decades, the constant growth of digital images, as the main source of information representation for scientific applications, has made image classification a challenging task. To achieve high classification yields, different pattern recognition techniques have been proposed, among which are the deep learning methods that today focus their study on image processing and computer vision. In this approach, the most popular architecture for the image classification task is the convolutional neural network (CNN), a network constructed of multiple layers and where each layer models a receptive field of the visual cortex making it much more effective in artificial vision tasks [1]. This paper proposes a convolutional network architecture with a performance-enhancing approach, a hierarchical structure that is easy to build, adaptive, and easy to train with good performance in image classification tasks.

Marketing and Smart Technologies, 2019

In Colombia, small and medium-sized enterprises (SMEs) are the most powerful engines of economic ... more In Colombia, small and medium-sized enterprises (SMEs) are the most powerful engines of economic development, since they generate a high volume of jobs in the national territory, while diversifying productive, commercial, and service activities. In order to propose a model for logistics management as a component for the competitiveness of SMEs, a qualitative study is proposed that will allow us to collect from a structured review of recent literature, identifying the elements to be taken into account for logistics management in order to provide timely support and open space for continuous improvement. The proposed model is structured in six main blocks: characterization of processes according to the activity of the SME, external factors of influence, internal factors of influence, feeding of information, monitoring and control of operations, and feedback between support areas. The above elements have been analyzed and suggested taking into account the specific aspects of SMEs in the country, and taking into account the peculiarities of these small productive cells.

Beekeeping has suffered a serious deterioration in the regions of the world. The possibility of n... more Beekeeping has suffered a serious deterioration in the regions of the world. The possibility of nectar-polliniferous resources has decreased and, therefore, the feeding of bees, with the consequent decrease in production. There is, therefore, a need to improve marketing and diversification systems and to update production techniques and the management of the production process by beekeepers to obtain the quality of honey required by the market [1]. This work proposes the use of spectral information to identify the different pollen-producing plants using remote vision, image processing, and artificial neural networks.

Procedia Computer Science, 2019

In this era of technology, data of business organizations are growing with acceleration. Mining h... more In this era of technology, data of business organizations are growing with acceleration. Mining hidden patterns from this huge database would benefit many industries improving their decision-making processes. Along with the non-sensitive information, these databases also contain some sensitive information about customers. During the mining process, sensitive information about a person can get leaked, resulting in a misuse of the data and causing loss to an individual. The privacy preserving data mining can bring a solution to this problem, helping provide the benefits of mined data along with maintaining the privacy of the sensitive information. Hence, there is a growing interest in the scientific community for developing new approaches to hide the mined sensitive information. In this research, a bibliometric review is carried out during the period 2010 to 2018 to analyze the growth of studies regarding the confidential information privacy preservation through approaches addressed to the hiding of association rules of data.

Procedia Computer Science, 2019

Making strategic decisions is a complex process that requires reliable and up-to-date information... more Making strategic decisions is a complex process that requires reliable and up-to-date information. It is therefore necessary to have tools that facilitate the information management. Technology Surveillance (TS) and Competitive Intelligence (CI) are two disciplines that seek to obtain accurate and up-to-date information. Clearly, the web is the largest and most important source of information, but their destructuring and disorganization requires tools that help to manage it. This work presents a model for TS and CI using Web Mining techniques such as ranking algorithm of web pages based on machine learning, i.e. the Advanced Cluster Vector Page Ranking (ACVPR) algorithm.

Procedia Computer Science, 2019

Applications based on Artificial Neural Networks (ANN) have been developed thanks to the advance ... more Applications based on Artificial Neural Networks (ANN) have been developed thanks to the advance of the technological progress which has permitted the development of sales forecasting on consumer products, improving the accuracy of traditional forecasting systems. The present study compares the performance of traditional models against other more developed systems such as ANN, and Support Vector Machines or Support Vector Regression (SVM-SVR) machines. It demonstrates the importance of considering external factors such as macroeconomic and microeconomic indicators, like the prices of related products, which affect the level of sales in an organization. The data was collected from a group of supermarkets belonging to the SMEs sector in Colombia. At first, a pre-processing was carried out to clean, adapt and standardize data bases. Then, since there was no labeled information about the pairs of substitute or complementary products, it was necessary to implement a cross-elasticity analysis. In addition, a harmonic average (f1-score) was considered at several points to establish priorities in some products and obtained results. The model proposed in this study shows its potential application in the product sales forecasting with high rotation in SMEs supermarkets since their results are more accurate than those obtained using traditional procedures.

Procedia Computer Science, 2019

Big Data promises great socially accepted and desirable benefits. However, in general terms, the ... more Big Data promises great socially accepted and desirable benefits. However, in general terms, the datification of life has made people to lose some awareness of the risks involved in the massive analysis of data regarding their fundamental rights. This fact is used by the companies involved in the data value chain to maximize their benefits although this implies the proliferation of negative externalities assumed by the information holders. The Colombian State has made great efforts regarding the protection of data and privacy, as demonstrated by Law 1266 of 2008 and Law 1581 of 2012, nevertheless, a deep literary review leads to conclude the need to adapt to the international context.

Procedia Computer Science, 2019

Data Mining applied to the field of commercialization allows, among other aspects, to discover pa... more Data Mining applied to the field of commercialization allows, among other aspects, to discover patterns of behavior in clients, which companies can use to create marketing strategies addressed to their different types of clients. This research focused on a database, the CRISP-DM methodology was applied for the Data Mining process. The database used was that corresponding to the sector of SMEs and referring to customers and sales, the analysis was made based on the PFM model (Presence, Frequency, Monetary Value), and on this model the grouping algorithms were applied: k-means, k-medoids, and SelfOrganizing Maps (SOM). To validate the result of the grouping algorithms and select the one that provides the best quality groups, the cascade evaluation technique has been used applying a classification algorithm. Finally, the Apriori algorithm was used to find associations between products for each group of customers.

Journal of Chemotherapy, 1998

The activities of several β-lactam antimicrobial agents, aminoglycosides and ciprofloxacin, were ... more The activities of several β-lactam antimicrobial agents, aminoglycosides and ciprofloxacin, were determined against 62 clinical isolates of enterobacteria resistant to oxyimino cephalosporins (extended-spectrum β-lactamase producers), collected during 1991 to 1993, and 16 penicillin-resistant invasive isolates of Streptococcus pneumoniae collected during 1994-1996. The numbers and percentages of susceptible enterobacterial strains to tested antibiotics were: imipenem 60 (97%), ciprofloxacin 57 (92%), cefepime 56 (90%), cefpirome 34 (55%), aztreonam 13 (21%), cefotaxime 7 (11%), ceftazidime 0 (0%), amikacin 11 (18%) and gentamicin 16 (26%). Despite the fact that these strains had never been exposed previously to cefepime or cefpirome, the susceptibility was 90% and 55%, respectively. No penicillin-resistant strains of S. pneumoniae were susceptible to cefotaxime, imipenem or cefepime. Only one strain was susceptible to ceftazidime and 4 (25%) were susceptible to cefpirome. Erythromycin showed the greatest activity with 12 (75%) susceptible strains.

common to class A b-lactamases: 70 SXXK, 130 SDN, and 234 KTG. The amino acid sequence of TLA-1 s... more common to class A b-lactamases: 70 SXXK, 130 SDN, and 234 KTG. The amino acid sequence of TLA-1 shared 50% identity with the CME-1 chromosomal class A b-lactamase from Chryseobacterium (Flavobacterium) me- ningosepticum; 48.8% identity with the VEB-1 class A b-lactamase from E. coli; 40 to 42% identity with CblA of Bacteroides uniformis, PER-1 of Pseudomonas aeruginosa, and PER-2 of

Journal of Clinical Microbiology, 2004

One hundred eighty-four clinical isolates of Klebsiella pneumoniae were recovered from August 199... more One hundred eighty-four clinical isolates of Klebsiella pneumoniae were recovered from August 1996 to October 1997 at the Pediatric Hospital of the Instituto Mexicano del Seguro Social in Mexico City, Mexico. Most of the isolates were collected from the neonatal intensive care unit and infant wards, which are located on the same floor of the hospital. Isolates were genotypically compared by pulsed-field gel electrophoresis with Xba I restriction of chromosomal DNA. Of 184 clinical isolates, 91 belonged to cluster A and comprised three subtypes (A1, A2, and A3), while 93 isolates, comprising two minor clones, B (10 isolates) and C (7 isolates), and 76 unique patterns, were considered unrelated isolates (URI). Susceptibility patterns were indistinguishable in both groups. Fifty extended-spectrum β-lactamase-producing isolates, including 34 from clone A and 16 from URI, were examined for further studies. Molecular and genetic analysis showed that 47 of 50 clinical isolates expressed th...

Journal of Clinical Microbiology, 2001

Thirty-one strains of Klebsiella pneumoniae (including 10 duplicates) from 21 septicemic pediatri... more Thirty-one strains of Klebsiella pneumoniae (including 10 duplicates) from 21 septicemic pediatric patients (age, <2 months) were studied during a 4-month period (June to October 1996) in which the fatality rate was 62% (13 of 21). These isolates identified by the API 20E system yielded the same biotype. Pulsed-field gel electrophoresis experiments revealed the same clone in 31 strains. The isolates were multidrug-resistant but were still susceptible to ciprofloxacin, imipenem, and cefoxitin. A 135-kb plasmid was harbored in all of the isolates. No transconjugants were obtained that were resistant to ampicillin, cefotaxime, tetracycline, or gentamicin. Isoelectric focusing for β-lactamases was performed on all strains, and three bands with pIs of 5.4, 7.6, and 8.2 were obtained. Of these, the pI 8.2 β-lactamase had an extended-spectrum β-lactamase phenotype. PCR amplification of both TEM- and SHV-type genes was obtained. The sequence analysis of the SHV PCR product indicated a mu...

Procedia Computer Science, 2020

External cause injuries are defined as intentionally or unintentionally harm or injury to a perso... more External cause injuries are defined as intentionally or unintentionally harm or injury to a person, which may be caused by trauma, poisoning, assault, accidents, etc., being fatal (fatal injury) or not leading to death (non-fatal injury). External injuries have been considered a global health problem for two decades. This work aims to determine criminal patterns using data mining techniques to a sample of patients from Mumbai city in India.

Procedia Computer Science, 2019

Today, as technologies mature and people are encouraged to contribute data to organizations' data... more Today, as technologies mature and people are encouraged to contribute data to organizations' databases, more transactions are being captured than ever before. Meanwhile, improvements in data storage technologies have made the cost of evaluating, selecting, and destroying legacy data considerably greater than simply letting it accumulate. On the one hand, the excess of stored data has considerably increased the opportunities to interrelate and analyze them, while the moderate enthusiasm generated by data warehousing and data mining in the 1990s has been replaced by a rampant euphoria about big data and data analytics. But, is this as wonderful as seems? This paper presents a risk analysis of Big Data and Big Data Analytics based on a review of quality factors.

In the last few decades, the constant growth of digital images, as the main source of information... more In the last few decades, the constant growth of digital images, as the main source of information representation for scientific applications, has made image classification a challenging task. To achieve high classification yields, different pattern recognition techniques have been proposed, among which are the deep learning methods that today focus their study on image processing and computer vision. In this approach, the most popular architecture for the image classification task is the convolutional neural network (CNN), a network constructed of multiple layers and where each layer models a receptive field of the visual cortex making it much more effective in artificial vision tasks [1]. This paper proposes a convolutional network architecture with a performance-enhancing approach, a hierarchical structure that is easy to build, adaptive, and easy to train with good performance in image classification tasks.

Marketing and Smart Technologies, 2019

In Colombia, small and medium-sized enterprises (SMEs) are the most powerful engines of economic ... more In Colombia, small and medium-sized enterprises (SMEs) are the most powerful engines of economic development, since they generate a high volume of jobs in the national territory, while diversifying productive, commercial, and service activities. In order to propose a model for logistics management as a component for the competitiveness of SMEs, a qualitative study is proposed that will allow us to collect from a structured review of recent literature, identifying the elements to be taken into account for logistics management in order to provide timely support and open space for continuous improvement. The proposed model is structured in six main blocks: characterization of processes according to the activity of the SME, external factors of influence, internal factors of influence, feeding of information, monitoring and control of operations, and feedback between support areas. The above elements have been analyzed and suggested taking into account the specific aspects of SMEs in the country, and taking into account the peculiarities of these small productive cells.

Beekeeping has suffered a serious deterioration in the regions of the world. The possibility of n... more Beekeeping has suffered a serious deterioration in the regions of the world. The possibility of nectar-polliniferous resources has decreased and, therefore, the feeding of bees, with the consequent decrease in production. There is, therefore, a need to improve marketing and diversification systems and to update production techniques and the management of the production process by beekeepers to obtain the quality of honey required by the market [1]. This work proposes the use of spectral information to identify the different pollen-producing plants using remote vision, image processing, and artificial neural networks.

Procedia Computer Science, 2019

In this era of technology, data of business organizations are growing with acceleration. Mining h... more In this era of technology, data of business organizations are growing with acceleration. Mining hidden patterns from this huge database would benefit many industries improving their decision-making processes. Along with the non-sensitive information, these databases also contain some sensitive information about customers. During the mining process, sensitive information about a person can get leaked, resulting in a misuse of the data and causing loss to an individual. The privacy preserving data mining can bring a solution to this problem, helping provide the benefits of mined data along with maintaining the privacy of the sensitive information. Hence, there is a growing interest in the scientific community for developing new approaches to hide the mined sensitive information. In this research, a bibliometric review is carried out during the period 2010 to 2018 to analyze the growth of studies regarding the confidential information privacy preservation through approaches addressed to the hiding of association rules of data.

Procedia Computer Science, 2019

Making strategic decisions is a complex process that requires reliable and up-to-date information... more Making strategic decisions is a complex process that requires reliable and up-to-date information. It is therefore necessary to have tools that facilitate the information management. Technology Surveillance (TS) and Competitive Intelligence (CI) are two disciplines that seek to obtain accurate and up-to-date information. Clearly, the web is the largest and most important source of information, but their destructuring and disorganization requires tools that help to manage it. This work presents a model for TS and CI using Web Mining techniques such as ranking algorithm of web pages based on machine learning, i.e. the Advanced Cluster Vector Page Ranking (ACVPR) algorithm.

Procedia Computer Science, 2019

Applications based on Artificial Neural Networks (ANN) have been developed thanks to the advance ... more Applications based on Artificial Neural Networks (ANN) have been developed thanks to the advance of the technological progress which has permitted the development of sales forecasting on consumer products, improving the accuracy of traditional forecasting systems. The present study compares the performance of traditional models against other more developed systems such as ANN, and Support Vector Machines or Support Vector Regression (SVM-SVR) machines. It demonstrates the importance of considering external factors such as macroeconomic and microeconomic indicators, like the prices of related products, which affect the level of sales in an organization. The data was collected from a group of supermarkets belonging to the SMEs sector in Colombia. At first, a pre-processing was carried out to clean, adapt and standardize data bases. Then, since there was no labeled information about the pairs of substitute or complementary products, it was necessary to implement a cross-elasticity analysis. In addition, a harmonic average (f1-score) was considered at several points to establish priorities in some products and obtained results. The model proposed in this study shows its potential application in the product sales forecasting with high rotation in SMEs supermarkets since their results are more accurate than those obtained using traditional procedures.

Procedia Computer Science, 2019

Big Data promises great socially accepted and desirable benefits. However, in general terms, the ... more Big Data promises great socially accepted and desirable benefits. However, in general terms, the datification of life has made people to lose some awareness of the risks involved in the massive analysis of data regarding their fundamental rights. This fact is used by the companies involved in the data value chain to maximize their benefits although this implies the proliferation of negative externalities assumed by the information holders. The Colombian State has made great efforts regarding the protection of data and privacy, as demonstrated by Law 1266 of 2008 and Law 1581 of 2012, nevertheless, a deep literary review leads to conclude the need to adapt to the international context.

Procedia Computer Science, 2019

Data Mining applied to the field of commercialization allows, among other aspects, to discover pa... more Data Mining applied to the field of commercialization allows, among other aspects, to discover patterns of behavior in clients, which companies can use to create marketing strategies addressed to their different types of clients. This research focused on a database, the CRISP-DM methodology was applied for the Data Mining process. The database used was that corresponding to the sector of SMEs and referring to customers and sales, the analysis was made based on the PFM model (Presence, Frequency, Monetary Value), and on this model the grouping algorithms were applied: k-means, k-medoids, and SelfOrganizing Maps (SOM). To validate the result of the grouping algorithms and select the one that provides the best quality groups, the cascade evaluation technique has been used applying a classification algorithm. Finally, the Apriori algorithm was used to find associations between products for each group of customers.

Journal of Chemotherapy, 1998

The activities of several β-lactam antimicrobial agents, aminoglycosides and ciprofloxacin, were ... more The activities of several β-lactam antimicrobial agents, aminoglycosides and ciprofloxacin, were determined against 62 clinical isolates of enterobacteria resistant to oxyimino cephalosporins (extended-spectrum β-lactamase producers), collected during 1991 to 1993, and 16 penicillin-resistant invasive isolates of Streptococcus pneumoniae collected during 1994-1996. The numbers and percentages of susceptible enterobacterial strains to tested antibiotics were: imipenem 60 (97%), ciprofloxacin 57 (92%), cefepime 56 (90%), cefpirome 34 (55%), aztreonam 13 (21%), cefotaxime 7 (11%), ceftazidime 0 (0%), amikacin 11 (18%) and gentamicin 16 (26%). Despite the fact that these strains had never been exposed previously to cefepime or cefpirome, the susceptibility was 90% and 55%, respectively. No penicillin-resistant strains of S. pneumoniae were susceptible to cefotaxime, imipenem or cefepime. Only one strain was susceptible to ceftazidime and 4 (25%) were susceptible to cefpirome. Erythromycin showed the greatest activity with 12 (75%) susceptible strains.

common to class A b-lactamases: 70 SXXK, 130 SDN, and 234 KTG. The amino acid sequence of TLA-1 s... more common to class A b-lactamases: 70 SXXK, 130 SDN, and 234 KTG. The amino acid sequence of TLA-1 shared 50% identity with the CME-1 chromosomal class A b-lactamase from Chryseobacterium (Flavobacterium) me- ningosepticum; 48.8% identity with the VEB-1 class A b-lactamase from E. coli; 40 to 42% identity with CblA of Bacteroides uniformis, PER-1 of Pseudomonas aeruginosa, and PER-2 of

Journal of Clinical Microbiology, 2004

One hundred eighty-four clinical isolates of Klebsiella pneumoniae were recovered from August 199... more One hundred eighty-four clinical isolates of Klebsiella pneumoniae were recovered from August 1996 to October 1997 at the Pediatric Hospital of the Instituto Mexicano del Seguro Social in Mexico City, Mexico. Most of the isolates were collected from the neonatal intensive care unit and infant wards, which are located on the same floor of the hospital. Isolates were genotypically compared by pulsed-field gel electrophoresis with Xba I restriction of chromosomal DNA. Of 184 clinical isolates, 91 belonged to cluster A and comprised three subtypes (A1, A2, and A3), while 93 isolates, comprising two minor clones, B (10 isolates) and C (7 isolates), and 76 unique patterns, were considered unrelated isolates (URI). Susceptibility patterns were indistinguishable in both groups. Fifty extended-spectrum β-lactamase-producing isolates, including 34 from clone A and 16 from URI, were examined for further studies. Molecular and genetic analysis showed that 47 of 50 clinical isolates expressed th...

Journal of Clinical Microbiology, 2001

Thirty-one strains of Klebsiella pneumoniae (including 10 duplicates) from 21 septicemic pediatri... more Thirty-one strains of Klebsiella pneumoniae (including 10 duplicates) from 21 septicemic pediatric patients (age, <2 months) were studied during a 4-month period (June to October 1996) in which the fatality rate was 62% (13 of 21). These isolates identified by the API 20E system yielded the same biotype. Pulsed-field gel electrophoresis experiments revealed the same clone in 31 strains. The isolates were multidrug-resistant but were still susceptible to ciprofloxacin, imipenem, and cefoxitin. A 135-kb plasmid was harbored in all of the isolates. No transconjugants were obtained that were resistant to ampicillin, cefotaxime, tetracycline, or gentamicin. Isoelectric focusing for β-lactamases was performed on all strains, and three bands with pIs of 5.4, 7.6, and 8.2 were obtained. Of these, the pI 8.2 β-lactamase had an extended-spectrum β-lactamase phenotype. PCR amplification of both TEM- and SHV-type genes was obtained. The sequence analysis of the SHV PCR product indicated a mu...