Juan Carlos Olivares Rojas | Tecnologico Nacional De Mexico (original) (raw)
Papers by Juan Carlos Olivares Rojas
International Journal of Combinatorial Optimization Problems and Informatics, 2024
Soil moisture is crucial in various fields and monitoring it to guide irrigation is challenging. ... more Soil moisture is crucial in various fields and monitoring it to guide irrigation is challenging. Machine learning has emerged as a promising tool to predict soil moisture levels accurately. This study evaluates machine learning techniques for this task, training models with meteorological variables and direct soil moisture measurements. Four machine learning algorithms were implemented, highlighting the Gradient Boosting Regressor as the most effective. In addition, a processed data set that combines meteorological and soil moisture measurements is presented, hoping it will be helpful for future research. This approach seeks to improve the compression and predictability of soil moisture, which is crucial for agricultural planning and water management in agriculture
Global Journal of Engineering and Technology Advances, 2024
Lung cancer is one of the leading causes of cancer-related deaths methods for lung nodules in com... more Lung cancer is one of the leading causes of cancer-related deaths methods for lung nodules in computed tomography (CT) images rely on manual interpretation by radiologist, which can be time-consuming and prone to human error. This paper presents BreathSafe.AI a deep learning system for the automatic detection and segmentation of lung nodules in CT images using an enhanced U-Net architecture combined with dense network techniques. Our model is trained on the LUNA16 dataset, utilizing advanced image preprocessing and segmentation methods to optimize nodule detection. This system achieves a diagnostic accuracy of over 90%, significantly improving detection speed and consistency compared to existing methods. The results highlight the system's potential to enhance lung cancer screening by reducing diagnosis time and variability, making it valuable tool for clinical use. Our approach demonstrates superior performance compared to state-of-art techniques, offering a scalable and efficient solution for early detection of lung cancer.
Lecture notes in computer science, 2024
Global Journal of Engineering and Technology Advances, Jun 30, 2024
The integration of smart electrical networks aims to better respond to faults, and distribute and... more The integration of smart electrical networks aims to better respond to faults, and distribute and control energy consumption, all of this would be difficult to achieve without the functions of smart meters that allow the sending of information between electricity companies’ services and the consumer, which is why it is important to guarantee the reliability of the information that is shared. In this work, the validation of the EVM430-F6736 meter and the PZEM-004T sensor is carried out concerning conventional devices for measuring electrical variables such as multimeters and wattmeters. The results show the error percentages between the measurements of the different devices.
Zenodo (CERN European Organization for Nuclear Research), Jul 19, 2023
Journal of intelligent & fuzzy systems, Mar 23, 2024
Efficient medical information management is essential in today’s healthcare, significantly to aut... more Efficient medical information management is essential in today’s healthcare, significantly to automate diagnoses of chronic diseases. This study focuses on the automated identification of diabetic patients through a clinical note classification system. This innovative approach combines rules, information extraction, and machine learning algorithms to promise greater accuracy and adaptability. Initially, the four algorithms evaluated showed similar performance, with Gradient Boosting standing out with an accuracy of 0.999. They were tested on our clinical and oncology notes, where SVM excelled in correctly labeling non-oncology notes with a 0.99. Gradient Boosting had the best average with 0.966. The combination of rules, information extraction, and Random Forest provided the best average performance, significantly improving the classification of clinical notes and reducing the margin of error in identifying diabetic patients. The principal contribution of this research lies in the pioneering integration of rule-based methods, information extraction techniques, and machine learning algorithms for enhanced accuracy in diabetic patient identification. For future work, we consider implementing these algorithms in natural clinical settings to evaluate their practical performance. Additionally, additional approaches will be explored to improve the accuracy and applicability of clinical note-grading systems in healthcare.
Lecture notes in networks and systems, 2024
Surface electromyography (sEMG) is the de-facto biopotential medical instrumentation solution for... more Surface electromyography (sEMG) is the de-facto biopotential medical instrumentation solution for non-invasive detection of limb motion EMG activation signals, which in turn provides important information regarding intentional and reactive muscle activity. However, sEMG delivers information of electrical activity mainly due to superficial muscles over a wide sensing field. Additional physiological processes may be elucidated by combining sEMG data with other measurements, such as Electrical Impedance Tomography (EIT) imaging, to assess muscular activity due to increased vascularization. In any case, the choice of the electrode material and shape influences the quality of measured data; "wet" electrodes (Ag/AgCl) are typically used for non-invasive sEMG measurements, whereas "dry" electrodes (i.e. stainless steel, copper-nickel) are preferred for electrical impedance measurements. Here, the authors explore the use of different types of electrode materials to measure sEMG upper limb motion signals, in comparison with Ag/AgCl electrodes, to determine a suitable electrode array that can accommodate both sEMG and EIT measurements. sEMG data was obtained from 10 healthy volunteers and processed using Short Time Fourier Transform (STFT) and Principal Component Spectral Analysis (PCSA) for Principal Component Regression (PCR) and Partial Least Squares Regression (PLSR). The results suggest that steel electrodes perform closer to commonly used Ag/AgCl electrodes, offering the potential for a developing a multimodal sEMG/EIT wearable measurement system for upper limb motion evaluation.
Detecting disturbances using digital signal processing methods and techniques that allow the corr... more Detecting disturbances using digital signal processing methods and techniques that allow the correct extraction of their distinctive characteristics to make the classification more effective is necessary for Power Quality monitoring. But developing an automatic detection system to be applied in smart measurement devices is not a trivial task, especially in obtaining a low computational cost method that can be integrated into hardware, due to the need to coordinate the functions of data acquisition, preprocessing, detection, and data exchange in real-time. It has been demonstrated that FPGA is a sufficiently fast hardware platform that allows the detection of disturbances of transient nature. In this work, a methodology for detection and extraction of the distinctive features of seven simple power quality disturbances based on Discrete Wavelet Transform and methods of energy and RMS values extraction, implemented in real-time using the Artix-7 FPGA from Xilinx, is proposed. From implementing the proposed methodology on the hardware platform, the result obtained is an algorithm that allows extracting the distinctive features of the analyzed disturbances, making optimal use of memory and processing resources, which makes this procedure efficient for its implementation in real time.
Monitoring disturbances in power quality (PQD) has gained importance in recent decades. This inte... more Monitoring disturbances in power quality (PQD) has gained importance in recent decades. This interest arises from the fact that disturbances associated with power quality directly affect the equipment connected to the grid, leading to malfunctions or complete equipment failure. For this reason, efforts have been made to optimize the methods for detecting these disturbances occurring in the electrical network.In this study, a Python algorithm is proposed to improve the detection and classification of seven types of simple electrical disturbances (sag, swell, flicker, oscillatory transient, interruption, harmonics, and notch). The algorithm varies the combination of characteristic vectors extracted (energy, mean, standard deviation, skewness, Shannon entropy, RMS, kurtosis, and logEnergy entropy) obtained from the Discrete Wavelet Transform (DWT) through Multiresolution Analysis (MRA) with 6 levels of detail. A database was generated by sampling three thousand five hundred electrical disturbances at 10 kHz. The experiment involved connecting a Beagle Bone Black (BBB) development board to a BK Precision 4064 arbitrary waveform generator.Combinations of two characteristic vectors were extracted from each signal in the database to evaluate them using the Random Forest classifier and determine which one is most suitable for this type of analysis based on their accuracy percentages.
In this work, a comparative evaluation of embedded devices for Natural Language Processing (NLP) ... more In this work, a comparative evaluation of embedded devices for Natural Language Processing (NLP) in biomedical applications in Spanish is carried out, specifically in text-to-speech and speech-to-text algorithms. Several embedded devices have been selected to achieve this, including Jetson Nano, Raspberry Pi (4B, 400, and 3B+), and Latte Panda. This analysis focuses on key aspects such as execution time, CPU usage percentage, and RAM usage percentage. These criteria will allow us to compare the evaluated devices' performance and determine the most suitable NLP in biomedical applications in Spanish. This benchmarking is expected to provide valuable information to facilitate the selection of devices in future projects and applications within the NLP. This work will allow professionals and developers to make informed decisions and optimize their resources when implementing NLP solutions in the biomedical field in Spanish.
Global Journal of Engineering and Technology Advances, Dec 29, 2023
IEEE Latin America Transactions, Dec 31, 2023
6th International Conference on Water, Waste, and Energy Management (WWEM22), 2022
Soil moisture influences geomorphological, atmospheric, hydrological, and agricultural biological... more Soil moisture influences geomorphological, atmospheric, hydrological, and agricultural biological processes, and intersects multiple areas of scientific research. Moreover, soil moisture measurements play an essential role in sustainable development since they allow elucidating information about the synergistic relationship between the processes involved in agricultural production [1]. One of the factors that influence the correct use of water resources for irrigation is the correct characterization of soil hydraulic conductivity properties [2]. Therefore, planning and allocation of water resources requires accurate knowledge of soil hydraulic conductivity properties. Electromagnetic soil humidity sensors (i. e. capacitive, Time Domain Reflectometry (TDR)) allow rapid on-site qualification; however, they produce a point-wise or volume-wise which may be insufficient to correctly characterize soils. Here, the authors
present the development and test of an IoT Electronic Wetting Front Detector for measuring the dynamics of water propagation in soils, dividing the soils depth in discrete regions.
Algorithms, 2024
Cervical cancer ranks among the leading causes of mortality in women worldwide, underscoring the ... more Cervical cancer ranks among the leading causes of mortality in women worldwide, underscoring the critical need for early detection to ensure patient survival. While the Pap smear test is widely used, its effectiveness is hampered by the inherent subjectivity of cytological analysis, impacting its sensitivity and specificity. This study introduces an innovative methodology for detecting and tracking precursor cervical cancer cells using SIFT descriptors in video sequences captured with mobile devices. More than one hundred digital images were analyzed from Papanicolaou smears provided by the State Public Health Laboratory of Michoacán, Mexico, along with over 1800 unique examples of cervical cancer precursor cells. SIFT descriptors enabled real-time correspondence of precursor cells, yielding results demonstrating 98.34% accuracy, 98.3% precision, 98.2% recovery rate, and an F-measure of 98.05%. These methods were meticulously optimized for real-time analysis, showcasing significant potential to enhance the accuracy and efficiency of the Pap smear test in early cervical cancer detection.
Global Journal of Engineering and Technology Advances, 2024
The integration of smart electrical networks aims to better respond to faults, and distribute and... more The integration of smart electrical networks aims to better respond to faults, and distribute and control energy
consumption, all of this would be difficult to achieve without the functions of smart meters that allow the sending of
information between electricity companies’ services and the consumer, which is why it is important to guarantee the
reliability of the information that is shared. In this work, the validation of the EVM430-F6736 meter and the PZEM-004T
sensor is carried out concerning conventional devices for measuring electrical variables such as multimeters and
wattmeters. The results show the error percentages between the measurements of the different devices.
MCPR, 2024
The development of natural language processing is popularizing the use of voice interfaces in cur... more The development of natural language processing is popularizing the use of voice interfaces in current applications. However, many of the interfaces currently developed are graphical interfaces that have been surpassed for the new needs of users. Hence, the use of multimodal interfaces, both visual and voice, is necessary to be more friendly and easy to use by final users. To do this, it would be necessary to redesign current graphic systems to integrate voice interfaces. This work shows that it is possible to develop multimodal interfaces starting from existing graphical interfaces by adding voice interfaces through previously designed dialogue and interactions. Tests were carried out through Web forms using feature extraction techniques, where satisfactory results were obtained.
Energies, 2024
Power quality improvement and Power quality disturbance (PQD) detection are two significant conce... more Power quality improvement and Power quality disturbance (PQD) detection are two significant concerns that must be addressed to ensure an efficient power distribution within the utility grid. When the process to analyze PQD is migrated to real-time platforms, the possible occurrence of a phase mismatch can affect the algorithm’s accuracy; this paper evaluates phase shifting as an additional stage in signal acquisition for detecting and classifying eight types of single power quality disturbances. According to their mathematical models, a set of disturbances was generated using an arbitrary waveform generator BK Precision 4064. The acquisition, detection, and classification stages were embedded into a BeagleBone Black. The detection stage was performed using multiresolution analysis. The feature vectors of the acquired signals were obtained from the combination of Shannon entropy and log-energy entropy. For classification purposes, four types of classifiers were trained: multilayer perceptron, K-nearest neighbors, probabilistic neural network, and decision tree. The results show that incorporating a phase-shifting stage as a preprocessing stage significantly improves the classification accuracy in all cases.
ENC, 2023
Since traditional agricultural traceability systems are largely centralized, traceability results... more Since traditional agricultural traceability systems are largely centralized, traceability results are not always accurate, there is a risk of privacy data leakage. A trustworthy agricultural traceability system built on the Ethereum Blockchain was suggested to solve these issues. On the other hand, the use of Blockchain and IPFS (Interplanetary File System) dual storage architecture was created to lessen the blockchain’s storage demands for effective information queries and prevent data explosion. To stop the leakage of sensitive and other critical data, a method for data privacy protection is suggested based on cryptographic primitives. Using the Ethereum blockchain platform, a portion of the planned system was implemented, and a cost, performance, and security analysis were conducted in addition to a comparison with conventional agricultural traceability systems. The outcomes demonstrated that the proposed system could be effective and practical and satisfy future suitable application needs.
Journal of Intelligent & Fuzzy Systems, 2024
Efficient medical information management is essential in today’s healthcare, significantly to aut... more Efficient medical information management is essential in today’s healthcare, significantly to automate diagnoses of chronic diseases. This study focuses on the automated identification of diabetic patients through a clinical note classification system. This innovative approach combines rules, information extraction, and machine learning algorithms to promise greater accuracy and adaptability. Initially, the four algorithms evaluated showed similar performance, with Gradient Boosting standing out with an accuracy of 0.999. They were tested on our clinical and oncology notes, where SVM excelled in correctly labeling non-oncology notes with a 0.99. Gradient Boosting had the best average with 0.966. The combination of rules, information extraction, and Random Forest provided the best average performance, significantly improving the classification of clinical notes and reducing the margin of error in identifying diabetic patients. The principal contribution of this research lies in the pioneering integration of rule-based methods, information extraction techniques, and machine learning algorithms for enhanced accuracy in diabetic patient identification. For future work, we consider implementing these algorithms in natural clinical settings to evaluate their practical performance. Additionally, additional approaches will be explored to improve the accuracy and applicability of clinical note-grading systems in healthcare.
International Journal of Combinatorial Optimization Problems and Informatics, 2024
Soil moisture is crucial in various fields and monitoring it to guide irrigation is challenging. ... more Soil moisture is crucial in various fields and monitoring it to guide irrigation is challenging. Machine learning has emerged as a promising tool to predict soil moisture levels accurately. This study evaluates machine learning techniques for this task, training models with meteorological variables and direct soil moisture measurements. Four machine learning algorithms were implemented, highlighting the Gradient Boosting Regressor as the most effective. In addition, a processed data set that combines meteorological and soil moisture measurements is presented, hoping it will be helpful for future research. This approach seeks to improve the compression and predictability of soil moisture, which is crucial for agricultural planning and water management in agriculture
Global Journal of Engineering and Technology Advances, 2024
Lung cancer is one of the leading causes of cancer-related deaths methods for lung nodules in com... more Lung cancer is one of the leading causes of cancer-related deaths methods for lung nodules in computed tomography (CT) images rely on manual interpretation by radiologist, which can be time-consuming and prone to human error. This paper presents BreathSafe.AI a deep learning system for the automatic detection and segmentation of lung nodules in CT images using an enhanced U-Net architecture combined with dense network techniques. Our model is trained on the LUNA16 dataset, utilizing advanced image preprocessing and segmentation methods to optimize nodule detection. This system achieves a diagnostic accuracy of over 90%, significantly improving detection speed and consistency compared to existing methods. The results highlight the system's potential to enhance lung cancer screening by reducing diagnosis time and variability, making it valuable tool for clinical use. Our approach demonstrates superior performance compared to state-of-art techniques, offering a scalable and efficient solution for early detection of lung cancer.
Lecture notes in computer science, 2024
Global Journal of Engineering and Technology Advances, Jun 30, 2024
The integration of smart electrical networks aims to better respond to faults, and distribute and... more The integration of smart electrical networks aims to better respond to faults, and distribute and control energy consumption, all of this would be difficult to achieve without the functions of smart meters that allow the sending of information between electricity companies’ services and the consumer, which is why it is important to guarantee the reliability of the information that is shared. In this work, the validation of the EVM430-F6736 meter and the PZEM-004T sensor is carried out concerning conventional devices for measuring electrical variables such as multimeters and wattmeters. The results show the error percentages between the measurements of the different devices.
Zenodo (CERN European Organization for Nuclear Research), Jul 19, 2023
Journal of intelligent & fuzzy systems, Mar 23, 2024
Efficient medical information management is essential in today’s healthcare, significantly to aut... more Efficient medical information management is essential in today’s healthcare, significantly to automate diagnoses of chronic diseases. This study focuses on the automated identification of diabetic patients through a clinical note classification system. This innovative approach combines rules, information extraction, and machine learning algorithms to promise greater accuracy and adaptability. Initially, the four algorithms evaluated showed similar performance, with Gradient Boosting standing out with an accuracy of 0.999. They were tested on our clinical and oncology notes, where SVM excelled in correctly labeling non-oncology notes with a 0.99. Gradient Boosting had the best average with 0.966. The combination of rules, information extraction, and Random Forest provided the best average performance, significantly improving the classification of clinical notes and reducing the margin of error in identifying diabetic patients. The principal contribution of this research lies in the pioneering integration of rule-based methods, information extraction techniques, and machine learning algorithms for enhanced accuracy in diabetic patient identification. For future work, we consider implementing these algorithms in natural clinical settings to evaluate their practical performance. Additionally, additional approaches will be explored to improve the accuracy and applicability of clinical note-grading systems in healthcare.
Lecture notes in networks and systems, 2024
Surface electromyography (sEMG) is the de-facto biopotential medical instrumentation solution for... more Surface electromyography (sEMG) is the de-facto biopotential medical instrumentation solution for non-invasive detection of limb motion EMG activation signals, which in turn provides important information regarding intentional and reactive muscle activity. However, sEMG delivers information of electrical activity mainly due to superficial muscles over a wide sensing field. Additional physiological processes may be elucidated by combining sEMG data with other measurements, such as Electrical Impedance Tomography (EIT) imaging, to assess muscular activity due to increased vascularization. In any case, the choice of the electrode material and shape influences the quality of measured data; "wet" electrodes (Ag/AgCl) are typically used for non-invasive sEMG measurements, whereas "dry" electrodes (i.e. stainless steel, copper-nickel) are preferred for electrical impedance measurements. Here, the authors explore the use of different types of electrode materials to measure sEMG upper limb motion signals, in comparison with Ag/AgCl electrodes, to determine a suitable electrode array that can accommodate both sEMG and EIT measurements. sEMG data was obtained from 10 healthy volunteers and processed using Short Time Fourier Transform (STFT) and Principal Component Spectral Analysis (PCSA) for Principal Component Regression (PCR) and Partial Least Squares Regression (PLSR). The results suggest that steel electrodes perform closer to commonly used Ag/AgCl electrodes, offering the potential for a developing a multimodal sEMG/EIT wearable measurement system for upper limb motion evaluation.
Detecting disturbances using digital signal processing methods and techniques that allow the corr... more Detecting disturbances using digital signal processing methods and techniques that allow the correct extraction of their distinctive characteristics to make the classification more effective is necessary for Power Quality monitoring. But developing an automatic detection system to be applied in smart measurement devices is not a trivial task, especially in obtaining a low computational cost method that can be integrated into hardware, due to the need to coordinate the functions of data acquisition, preprocessing, detection, and data exchange in real-time. It has been demonstrated that FPGA is a sufficiently fast hardware platform that allows the detection of disturbances of transient nature. In this work, a methodology for detection and extraction of the distinctive features of seven simple power quality disturbances based on Discrete Wavelet Transform and methods of energy and RMS values extraction, implemented in real-time using the Artix-7 FPGA from Xilinx, is proposed. From implementing the proposed methodology on the hardware platform, the result obtained is an algorithm that allows extracting the distinctive features of the analyzed disturbances, making optimal use of memory and processing resources, which makes this procedure efficient for its implementation in real time.
Monitoring disturbances in power quality (PQD) has gained importance in recent decades. This inte... more Monitoring disturbances in power quality (PQD) has gained importance in recent decades. This interest arises from the fact that disturbances associated with power quality directly affect the equipment connected to the grid, leading to malfunctions or complete equipment failure. For this reason, efforts have been made to optimize the methods for detecting these disturbances occurring in the electrical network.In this study, a Python algorithm is proposed to improve the detection and classification of seven types of simple electrical disturbances (sag, swell, flicker, oscillatory transient, interruption, harmonics, and notch). The algorithm varies the combination of characteristic vectors extracted (energy, mean, standard deviation, skewness, Shannon entropy, RMS, kurtosis, and logEnergy entropy) obtained from the Discrete Wavelet Transform (DWT) through Multiresolution Analysis (MRA) with 6 levels of detail. A database was generated by sampling three thousand five hundred electrical disturbances at 10 kHz. The experiment involved connecting a Beagle Bone Black (BBB) development board to a BK Precision 4064 arbitrary waveform generator.Combinations of two characteristic vectors were extracted from each signal in the database to evaluate them using the Random Forest classifier and determine which one is most suitable for this type of analysis based on their accuracy percentages.
In this work, a comparative evaluation of embedded devices for Natural Language Processing (NLP) ... more In this work, a comparative evaluation of embedded devices for Natural Language Processing (NLP) in biomedical applications in Spanish is carried out, specifically in text-to-speech and speech-to-text algorithms. Several embedded devices have been selected to achieve this, including Jetson Nano, Raspberry Pi (4B, 400, and 3B+), and Latte Panda. This analysis focuses on key aspects such as execution time, CPU usage percentage, and RAM usage percentage. These criteria will allow us to compare the evaluated devices' performance and determine the most suitable NLP in biomedical applications in Spanish. This benchmarking is expected to provide valuable information to facilitate the selection of devices in future projects and applications within the NLP. This work will allow professionals and developers to make informed decisions and optimize their resources when implementing NLP solutions in the biomedical field in Spanish.
Global Journal of Engineering and Technology Advances, Dec 29, 2023
IEEE Latin America Transactions, Dec 31, 2023
6th International Conference on Water, Waste, and Energy Management (WWEM22), 2022
Soil moisture influences geomorphological, atmospheric, hydrological, and agricultural biological... more Soil moisture influences geomorphological, atmospheric, hydrological, and agricultural biological processes, and intersects multiple areas of scientific research. Moreover, soil moisture measurements play an essential role in sustainable development since they allow elucidating information about the synergistic relationship between the processes involved in agricultural production [1]. One of the factors that influence the correct use of water resources for irrigation is the correct characterization of soil hydraulic conductivity properties [2]. Therefore, planning and allocation of water resources requires accurate knowledge of soil hydraulic conductivity properties. Electromagnetic soil humidity sensors (i. e. capacitive, Time Domain Reflectometry (TDR)) allow rapid on-site qualification; however, they produce a point-wise or volume-wise which may be insufficient to correctly characterize soils. Here, the authors
present the development and test of an IoT Electronic Wetting Front Detector for measuring the dynamics of water propagation in soils, dividing the soils depth in discrete regions.
Algorithms, 2024
Cervical cancer ranks among the leading causes of mortality in women worldwide, underscoring the ... more Cervical cancer ranks among the leading causes of mortality in women worldwide, underscoring the critical need for early detection to ensure patient survival. While the Pap smear test is widely used, its effectiveness is hampered by the inherent subjectivity of cytological analysis, impacting its sensitivity and specificity. This study introduces an innovative methodology for detecting and tracking precursor cervical cancer cells using SIFT descriptors in video sequences captured with mobile devices. More than one hundred digital images were analyzed from Papanicolaou smears provided by the State Public Health Laboratory of Michoacán, Mexico, along with over 1800 unique examples of cervical cancer precursor cells. SIFT descriptors enabled real-time correspondence of precursor cells, yielding results demonstrating 98.34% accuracy, 98.3% precision, 98.2% recovery rate, and an F-measure of 98.05%. These methods were meticulously optimized for real-time analysis, showcasing significant potential to enhance the accuracy and efficiency of the Pap smear test in early cervical cancer detection.
Global Journal of Engineering and Technology Advances, 2024
The integration of smart electrical networks aims to better respond to faults, and distribute and... more The integration of smart electrical networks aims to better respond to faults, and distribute and control energy
consumption, all of this would be difficult to achieve without the functions of smart meters that allow the sending of
information between electricity companies’ services and the consumer, which is why it is important to guarantee the
reliability of the information that is shared. In this work, the validation of the EVM430-F6736 meter and the PZEM-004T
sensor is carried out concerning conventional devices for measuring electrical variables such as multimeters and
wattmeters. The results show the error percentages between the measurements of the different devices.
MCPR, 2024
The development of natural language processing is popularizing the use of voice interfaces in cur... more The development of natural language processing is popularizing the use of voice interfaces in current applications. However, many of the interfaces currently developed are graphical interfaces that have been surpassed for the new needs of users. Hence, the use of multimodal interfaces, both visual and voice, is necessary to be more friendly and easy to use by final users. To do this, it would be necessary to redesign current graphic systems to integrate voice interfaces. This work shows that it is possible to develop multimodal interfaces starting from existing graphical interfaces by adding voice interfaces through previously designed dialogue and interactions. Tests were carried out through Web forms using feature extraction techniques, where satisfactory results were obtained.
Energies, 2024
Power quality improvement and Power quality disturbance (PQD) detection are two significant conce... more Power quality improvement and Power quality disturbance (PQD) detection are two significant concerns that must be addressed to ensure an efficient power distribution within the utility grid. When the process to analyze PQD is migrated to real-time platforms, the possible occurrence of a phase mismatch can affect the algorithm’s accuracy; this paper evaluates phase shifting as an additional stage in signal acquisition for detecting and classifying eight types of single power quality disturbances. According to their mathematical models, a set of disturbances was generated using an arbitrary waveform generator BK Precision 4064. The acquisition, detection, and classification stages were embedded into a BeagleBone Black. The detection stage was performed using multiresolution analysis. The feature vectors of the acquired signals were obtained from the combination of Shannon entropy and log-energy entropy. For classification purposes, four types of classifiers were trained: multilayer perceptron, K-nearest neighbors, probabilistic neural network, and decision tree. The results show that incorporating a phase-shifting stage as a preprocessing stage significantly improves the classification accuracy in all cases.
ENC, 2023
Since traditional agricultural traceability systems are largely centralized, traceability results... more Since traditional agricultural traceability systems are largely centralized, traceability results are not always accurate, there is a risk of privacy data leakage. A trustworthy agricultural traceability system built on the Ethereum Blockchain was suggested to solve these issues. On the other hand, the use of Blockchain and IPFS (Interplanetary File System) dual storage architecture was created to lessen the blockchain’s storage demands for effective information queries and prevent data explosion. To stop the leakage of sensitive and other critical data, a method for data privacy protection is suggested based on cryptographic primitives. Using the Ethereum blockchain platform, a portion of the planned system was implemented, and a cost, performance, and security analysis were conducted in addition to a comparison with conventional agricultural traceability systems. The outcomes demonstrated that the proposed system could be effective and practical and satisfy future suitable application needs.
Journal of Intelligent & Fuzzy Systems, 2024
Efficient medical information management is essential in today’s healthcare, significantly to aut... more Efficient medical information management is essential in today’s healthcare, significantly to automate diagnoses of chronic diseases. This study focuses on the automated identification of diabetic patients through a clinical note classification system. This innovative approach combines rules, information extraction, and machine learning algorithms to promise greater accuracy and adaptability. Initially, the four algorithms evaluated showed similar performance, with Gradient Boosting standing out with an accuracy of 0.999. They were tested on our clinical and oncology notes, where SVM excelled in correctly labeling non-oncology notes with a 0.99. Gradient Boosting had the best average with 0.966. The combination of rules, information extraction, and Random Forest provided the best average performance, significantly improving the classification of clinical notes and reducing the margin of error in identifying diabetic patients. The principal contribution of this research lies in the pioneering integration of rule-based methods, information extraction techniques, and machine learning algorithms for enhanced accuracy in diabetic patient identification. For future work, we consider implementing these algorithms in natural clinical settings to evaluate their practical performance. Additionally, additional approaches will be explored to improve the accuracy and applicability of clinical note-grading systems in healthcare.
2022 International Conference on Green Energy and Environmental Technology (GEET-22), 2022
In spite of the great popularity which the mobile devices have in our days, the access to Interne... more In spite of the great popularity which the mobile devices have in our days, the access to Internet through this type of devices is extremely limited. This due because Web sites have not been developed taking into account the characteristics and constrains from these devices in view of making the Web resources more accessible. Thus for example, the screen-restrictions, the low capacity of memory and storage, the communications
through no persistent connections, the high costs and the deficient bandwidth of connection, among others, these characteristics have restrained the visualization of Web
sites through mobile devices.
The present work tries “to put the Web in the users’ pockets”. In order to guarantee that the users can visualize correctly the Web resources, two things are needed: a mechanism that control disconnections and allow to visualize Web content without concerning the connection state of the device (hoarding), and a mechanism that adapts the Web content to the own characteristics of the specific mobile device (transcoding). In this work a tool that integrates these two mechanisms and allows improving the navigation experience of the users in the mobile Web is presented.
The goal of this thesis consists of which the Web resources are accessible independent of the device, when, where and how the users need. In addition, with this work it is possible to reduce the size of the Web resources when transcoding and hoarding them
on the mobile device, energy save of the batteries, as well as speed up access times to the resources, which with takes to diminish costs of accessing to the Web or per time air
or by volumen of information This aid to increase the access levels to the Web through mobile devices.
Academia Journals Tepic, 2019
Aplicacion de Tecnicas de UX en el Desarrollo de un Portal de un Sistema de Medición Inteligente
Mejoramiento del proceso de enseñanza-aprendizaje
Presentacion Congreso CIIDET 2016
Presentación en el Congreso 2012 del Instituto Tecnológico Superior de Zongolica, Veracruz
Presentación en la Semana Académica del Instituto Tecnológico Superior de Coalcomán 2013
Instituto Tecnologico de la Costa Grande, Congreso 2013
Presentación en el Congreso UVA, 2013
PResentación en el 9no Congreso CECTI, Morelia 2014
Presentación en el 9no. Congreso CECTI, Morelia 2014
Presentación en el IEEE Day, Instituto Tecnológico de Morelia, 2014
Presentación en el Festival de Software Libre 2014 del Instituto Tecnológico Superior de Pátzcuaro
Congreso Instituto Tecnológico de Ciudad Guzmán, 2014
Presentación del Congreo Tekhne 2013, Instituto Tecnológico de Morelia
Presentación en el Congreso Tékhne 2013, Instituto Tecnológico de Morelia
Semana Académica del Instituto Tecnológico de Huetamo, 2011
Presentación en el Congreso de la UNID 2011
Presentación en la Semana Académica del Instituto Tecnológico Superior del Occidente de Zacatecas... more Presentación en la Semana Académica del Instituto Tecnológico Superior del Occidente de Zacatecas, en Sombrerete
Presentación de Semana Académica del CECyTEM 2010
Universidad Michoacana 2010
Instituto Tecnológico de Zitácuaro, 2009
2020 KGSWC Winter School Book, 2021
This paper shows the proposal of the use of linked data for smart metering systems. The aim of li... more This paper shows the proposal of the use of linked data for smart metering systems. The aim of linked data in smart grid applications such as smart metering systems is to give semantic knowledge of the energy transactions between all participators in the power markets. In combination with other technologies like blockchain, the linked data could improve decentralization and security in the world's energetic future.
Eficiencia Energética en los hogares utilizando Medidores Inteligentes
A pesar del gran auge que han tenido los dispositivos móviles en nuestros días, el acceso a Inter... more A pesar del gran auge que han tenido los dispositivos móviles en nuestros días, el acceso a Internet a través de esta clase de dispositivos es sumamente limitado. Esto se debe a que los sitios Web no han sido desarrollados tomando en cuenta las características y limitantes de estos dispositivos en vista de hacer los recursos Web más accesible. Así por ejemplo, las restricciones de pantalla, la poca capacidad de memoria y de almacenamiento, los enlaces de comunicaciones no persistentes, los altos costos de
conexión y el deficiente ancho de banda, han frenado la visualización de sitios Web a través de dispositivos móviles.
El presente trabajo pretende “poner la Web en los bolsillos de los usuarios”.
Para garantizar que los usuarios puedan visualizar correctamente los recursos de Web, se necesitan dos cosas: un mecanismo que controle desconexiones y permita visualizar contenido Web sin importar el estado de conexión del dispositivo (acaparamiento), y un mecanismo que adapte el contenido de la Web a las características propias del dispositivo móvil específico (transcodificación). MoviWeb es una herramienta que
integra estos dos mecanismos y permite mejorar la experiencia de navegación de los usuarios en la Web móvil.
La meta de Moviware consiste en que los recursos de la Web sean accesibles independientes del dispositivo, cuando, en donde y como los necesiten los usuarios.
Además, con este trabajo se ahorra en espacio de almacenamiento, energía de las baterías, así como tiempos de acceso a los recursos, lo que con lleva a disminuir costos por acceder a la Web ya sea por tiempo aire o por volumen de información Esto ayuda a incrementar los niveles de acceso a la Web a través de dispositivos móviles. .
Presentación del Concurso Nacional de Creatividad 2006 Fase Regional Instituto Tencológico de Tux... more Presentación del Concurso Nacional de Creatividad 2006 Fase Regional Instituto Tencológico de Tuxtepec
Internet de las Cosas en Redes Eléctricas Inteligentes
Evaluación de mecanismos de cadenas de bloques y criptomonedas para garantizar confiabilidad en t... more Evaluación de mecanismos de cadenas de bloques y criptomonedas para garantizar confiabilidad en transacciones en mercados eléctricos
Presentación sobre aspectos básicos de CyberSeguridad
Presentación de propuesta para entrar al doctorado
Smart cities: IoT and Big Data for Susitanailable Development
Desarrollar un prototipo didáctico con objetos de aprendizaje diversos para dispositivos móviles ... more Desarrollar un prototipo didáctico con objetos de aprendizaje diversos para dispositivos móviles que faciliten el aprendizaje de fundamentos de programación orientada a objetos a través de la creación de videojuegos para computadoras personales.
Algunas Estrategias Didácticas del TecNM
Sistemas de Medición Inteligente
Como realizar simulaciones de Internet de Todas las Cosas en Cisco Packet Tracer
Introducción a las Redes Eléctricas Inteligentes
Internet de las Cosas (Parte I)
Introducción a los medidores eléctricos inteligentes
Guía Examen Programación Maestría en Ciencias Ingeniería Electronica
Introducción a los Sistemas Embebidos
Programa de Asignatura de la Maestría en Ciencias en Ingeniería Electrónica
Redes PLC (Power Line Communication)
Seguridad en Medidores Inteligentes (Smart Meter)
In spite of the great popularity which the mobile devices have in our days, the access to Interne... more In spite of the great popularity which the mobile devices have in our days, the access to Internet through this type of devices is extremely limited. This due because Web sites have not been developed taking into account the characteristics and constrains from these devices in view of making the Web resources more accessible. Thus for example, the screen-restrictions, the low capacity of memory and storage, the communications through no persistent connections, the high costs and the deficient bandwidth of connection, among others, these characteristics have restrained the visualization of Web sites through mobile devices.
The present work tries “to put the Web in the users’ pockets”. In order to guarantee that the users can visualize correctly the Web resources, two things are needed: a mechanism that control disconnections and allow to visualize Web content without concerning the connection state of the device (hoarding), and a mechanism that adapts the Web content to the own characteristics of the specific mobile device (transcoding). In this work a tool that integrates these two mechanisms and allows improving the navigation experience of the users in the mobile Web is presented.
The goal of this thesis consists of which the Web resources are accessible independent of the device, when, where and how the users need. In addition, with this work it is possible to reduce the size of the Web resources when transcoding and hoarding them on the mobile device, energy save of the batteries, as well as speed up access times to the resources, which with takes to diminish costs of accessing to the Web or per time air or by volumen of information This aid to increase the access levels to the Web through mobile devices.