Researcher in the Department of Computer Science, National Institute of Astrophysics, Optics and Electronics (INAOE), holds a PhD in Electrical Engineering from the Center for Research and Advanced Studies of the National Polytechnic Institute (CINVESTAV-IPN); a Master of Science in Electrical Engineering from CINVESTAV-IPN; and a Bachelor of Science in Electronics from the Technological Institute of Tuxtla Gutiérrez (ITT). His research interests include signal processing, road safety, cybersecurity, IoT, Industry 4.0, integrated circuit design, and intelligent systems design.
Research Areas: Signal Processing
Internet of Things (IoT)
Cybersecurity
Integrated Circuit Development
Laboratories: Reconfigurable and High-Performance Computing
Cybersecurity
Currently, the temperature and humidity are important factors for the correct operation and security of electronic devices in a data center. According to the specifications of the International Computer Room Experts Association (ICREA) and the American Society of Heating, Refrigerating and Air Conditioning Engineers (ASHRAE), the temperature must oscillate between 64.4°F and 80°F equal to 18°C and 27°C. The humidity and non-condensing range must oscillate between 40% Relative Humidity (RH), 5.5°C (41.9°F) of Dew Point (DP) to 60% RH, 15°C (59°F) of DP. Considering the mentioned data, a technique, and a method, was developed for real-time measurements based on the fusion of embedded sensors and systems; with connectivity to the communication network in generation of a dedicated database, for information processing; with open software and hardware resources for temperature and humidity monitoring in a data center; located in a region of humid tropical climate, in the south-southeast of Mexico, specifically in the TECNM-Villahermosa. Presents itself the sensor fusion and embedded systems integrate the Internet of Things, to acquire and analyze data in real-time; as well as its communication system, mobile application and web Page developed for a boss of the data center to have in real-time the data generated from the analysis of the sensor network implemented. Graphs of the behavior of the information and the analysis of the data are presented; complying with the cited standards and associations.
This paper presents the development and implementation of neural control systems in mobile robots in obstacleavoidance in real time using ultrasonic sensors with complex strategies of decision-making in development (Matlab andProcessing). An Arduino embedded platform is used to implement the neural control for field results.
The fast pace of development of the Internet and the Coronavirus Disease (COVID-19) pandemic have considerably impacted the educative sector, encouraging the constant transformation of the teaching/learning strategies and more in technological areas as Educational Software Engineering. Web programming, a fundamental topic in Software Engineering and Cloud-based applications, deals with various critical challenges in education, such as learning continuous emerging technological tools, plagiarism detection, generating innovative learning environments, among others. Continual change and even more change with the current digitization becomes a challenge for teachers and students who cannot depend on traditional educational methods. The article presents a sustainable teaching/learning methodology for web programming courses in Engineering Education using project-based learning adaptable to the continuous web technological advances. The methodology has been developed and improved during 9 years, 15 groups, and 3 different universities. Our results demonstrate that the methodology is adaptable with new technologies that might arise; it also presents the advantages of avoiding plagiarism in students and a personalized induction for every specific student in the learning process.
This study presents the design and implementation of an electronic system aimed at capturing vibrations produced during truck operation. The system employs a graphical interface to display vibration levels, ensuring the necessary comfort and offering indicators as a solution to mitigate the damage caused by these vibrations. Additionally, the system alerts the driver when a mechanical vibration that could potentially impact their health is detected. The field of health is rigorously regulated by various international standards and guidelines. The case of mechanical vibrations, particularly those transmitted to the entire body of a seated individual, is no exception. Internationally, ISO 2631-1:1997/Amd 1:2010 oversees this study. The system was designed and implemented using a blend of hardware and software. The hardware components comprise a vibration sensor, a data acquisition card, and a graphical user interface (GUI). The software components consist of a data acquisition and processing library, along with a GUI development framework. The system underwent testing in a controlled environment and demonstrated stability and robustness. The GUI proved to be intuitive and could be integrated into modern vehicles with built-in displays. The findings of this study suggest that the proposed system is a viable and effective method for capturing vibrations in trucks and informing drivers about vibration levels. This system has the potential to enhance the comfort and safety of truck drivers.
Mobile robots represent one of the most relevant areas of study within robotics due to their potential for designing and developing new nonlinear control structures that can be implemented in simulations and applications in specific environments. In this work, a fuzzy steering controller with a symmetric distribution of fuzzy numbers is proposed and designed for implementation in the kinematic model of a non-holonomic mobile robot. The symmetry in the distribution of triangular fuzzy numbers contributes to a balanced response to disturbances and minimizes systematic errors in direction estimation. Additionally, it improves the system’s adaptability to various reference paths, ensuring accurate tracking and optimized performance in robot navigation. Furthermore, this fuzzy logic-based controller emulates the behavior of a classic PID controller by offering a robust and flexible alternative to traditional methods. A virtual environment was also developed using the UNITY platform to evaluate the performance of the fuzzy controller. The results were evaluated by considering the average tracking error, maximum error, steady-state error, settling time, and total distance traveled, emphasizing the trajectory error. The circular trajectory showed high accuracy with an average error of 0.0089 m, while the cross trajectory presented 0.01814 m, reflecting slight deviations in the turns. The point-to-point trajectory registered a more significant error of 0.9531 m due to abrupt transitions, although with effective corrections in a steady state. The simulation results validate the robustness of the proposed fuzzy controller, providing quantitative insights into its precision and efficiency in a virtual environment, and demonstrating the effectiveness of the proposal.
In recent years, there is a trend towards the development of reconfigurable circuits where devices using them offer flexibility and performance. Different technologies are explored, such as threshold logic gates (TLGs), which are one of the most promising future technologies, and researchers are examining and improving different characteristics such as density, performance and power dissipation. This research presents a 4‐bit arithmetic logic unit (ALU), which was designed using TLGs through reconfigurable logic blocks with a universal circuit configured with three stages based on a floating‐gate metal oxide semiconductor transistor with more than one control gate, which was named neu‐complementary metal oxide semiconductor ( ν ‐CMOS). The main contribution is that this device is configured as a ν ‐CMOS inverter and has the ability to program the threshold voltage of its transfer curve by applying an external voltage to the additional control gates. The number of input bits and the magnitude of the weighted input capacitances related to control gates of the ν ‐CMOS inverters is obtained and analyzed by using the graphical method (floating‐gate potential diagram). Finally, the proposed 4‐bit ALU shows similar results as those measured from the ALUs implemented in the field programmable gate array evaluation kit and the Motorola chip MC14581B.
In emergent technologies, data integrity is critical for message-passing communications, where security measures and validations must be considered to prevent the entrance of invalid data, detect errors in transmissions, and prevent data loss. The SHA-256 algorithm is used to tackle these requirements. Current hardware architecture works present issues regarding real-time balance among processing, efficiency and cost, because some of them introduce significant critical paths. Besides, the SHA-256 algorithm itself considers no verification mechanisms for internal calculations and failure prevention. Hardware implementations can be affected by diverse problems, ranging from physical phenomena to interference or faults inherent to data spectra. Previous works have mainly addressed this problem through three kinds of redundancy: information, hardware, or time. To the best of our knowledge, pipelining has not been previously used to perform different hash calculations with a redundancy topic. Therefore, in this work, we present a novel hybrid architecture, implemented on a 3-stage pipeline structure, which is traditionally used to improve performance by simultaneously processing several blocks; instead, we propose using a pipeline technique for implementing hardware and time redundancies, analyzing hardware resources and performance to balance the critical path. We have improved performance at a certain clock speed, defining a data flow transformation in several sequential phases. Our architecture reported a throughput of 441.72 Mbps and 2255 LUTs, and presented an efficiency of 195.8 Kbps/LUT.
This paper presents the development of a multilayer feed-forward neural network for the diagnosis of hypertension, based on a population-based study. For the development of this architecture, several physiological factors have been considered, which are vital to determining the risk of being hypertensive; a diagnostic system can offer a solution which is not easy to determine by conventional means. The results obtained demonstrate the sustainability of health conditions affecting humanity today as a consequence of the social environment in which we live, e.g., economics, stress, smoking, alcoholism, drug addiction, obesity, diabetes, physical inactivity, etc., which leads to hypertension. The results of the neural network-based diagnostic system show an effectiveness of 90%, thus generating a high expectation in diagnosing the risk of hypertension from the analyzed physiological data.
Obstacle–Avoidance robots have become an essential field of study in recent years. This paper analyzes two cases that extend reactive systems focused on obstacle detection and its avoidance. The scenarios explored get data from their environments through sensors and generate information for the models based on artificial intelligence to obtain a reactive decision. The main contribution is focused on the discussion of aspects that allow for comparing both approaches, such as the heuristic approach implemented, requirements, restrictions, response time, and performance. The first case presents a mobile robot that applies a fuzzy inference system (FIS) to achieve soft turning basing its decision on depth image information. The second case introduces a mobile robot based on a multilayer perceptron (MLP) architecture, which is a class of feedforward artificial neural network (ANN), and ultrasonic sensors to decide how to move in an uncontrolled environment. The analysis of both options offers perspectives to choose between reactive Obstacle–Avoidance systems based on ultrasonic or Kinect sensors, models that infer optimal decisions applying fuzzy logic or artificial neural networks, with key elements and methods to design mobile robots with wheels. Therefore, we show how AI or Fuzzy Logic techniques allow us to design mobile robots that learn from their “experience” by making them safe and adjustable for new tasks, unlike traditional robots that use large programs to perform a specific task.
This paper presents a fault diagnosis (FDD) approach based on a Takagi-Sugeno Unknown Input Observer (TS-UIO) that allows for the estimation of the states of an active pitch system for a studied wind turbine even in the presence of unknown interference factors. A scheme for FDD is proposed based on the residual evaluation between the non-linear model of the active pitch system and the Takagi-Sugeno unknown input observer proposed for the detection and isolation of faults in sensors with measurable premise variables. The proposed TS-UIO State Observer is resilient to disturbances and measurement noise due to its unique feature of decoupling unknown inputs, interruptions, or undefined factors that affect the behavior of the system under study. This study investigates the effect of load-induced stress on the mechanical blades of a wind turbine, caused by the wind force considered as an unknown disturbance or input to the system given its dependence on weather conditions. The proposed FDD algorithm includes Linear Matrix Inequalities (LMI) ensuring the estimation error dynamics approximates to zero. Successful implementation tests are demonstrated in an active pitch system with reference parameters based on a wind turbine model. The review outlines traditional FDD approaches, including those based on nonlinear models, as well as relatively new methods based on linear sector conditions. Special attention is given to Takagi-Sugeno (TS) methods.
This study examines high school student dropout and proposes a support tool that utilizes a neuro-fuzzy system to mitigate this issue. The system analyzes a student’s economic and social information through a human-machine interface, registering data to evaluate dropout risk levels. It is proposed as an innovative alternative and considered a development project that seeks to perform diagnostics without compromising current support mechanisms. The successful implementation of this proposal will result in tangible benefits, particularly when considering the student community in various regions of the State of Chiapas, specifically in vulnerable areas. The system yielded positive results, manifesting its stability and robustness in both design and implementation. This endeavor not only tackles the identified issue, but also functions as an efficacious and dependable mechanism for assessing and averting student attrition, thereby fortifying the education system in these locales.
The great increase of the digital communications, where the technological society depends on applications, devices and networks, the security problems motivate different researches for providing algorithms and systems resistant to attacks, and these lasts need of services of confidentiality, authentication, integrity, etc. This paper proposes the hardware implementation of an steganographic/cryptographic algorithm, which is based on the DWT (Discrete Wavelet Transform) and the AES (Advanced Encryption Standard) cipher algorithm in CBC mode. The proposed scheme takes advantage of a double-security ciphertext, which makes difficult to identify and decipher it. The hardware architecture reports a high efficiency (182.2 bps/slice and 85.2 bps/LUT) and low hardware resources consumption (867 slices and 1853 LUTs), where several parallel implementations can improve the throughout (0.162 Mbps) for processing large amounts of data.
A methodology is proposed for the design of a 4-Bit Arithmetic Logic Unit (ALU) based on Soft-Hardware-Logic (SHL). The core of the implementation is based on the device known as neu-MOS (ν-MOS), a floating-gate MOS transistor with more than one control gate used for the digital signal processing. This configuration is reconfigurable modifying only the external voltages applied to an intermediate stage of programmable CMOS inverters, without any circuitry change, in contrast with conventional digital implementations. Here it is demonstrated that using a universal circuit, basic Boolean functions like AND, NAND, OR, NOR, Exclusive-OR and Exclusive-NOR can be configured using Multiple-Input Floating-Gate (MIFG) Transistors or neu-MOS. Based on a graphical method called Floating-gate Potential Diagram (FPD), a very basic 4-Bit ALU was designed and simulated for a couple of arithmetic and logic functions taking advantage of the weighted sum performed at the floating gate of the neu-MOS. Weighted inputs can be obtained from the FPD and then converted to effective capacitances choosing a given CMOS technology, OnSemi's 0.5 μm technology, for instance. Results obtained from simulations of the proposed design are compared with experimental results of ALUs configured with a FPGA evaluation kit and Motorola's MC14581B ALU chip.
This paper proposes a geometrical criterion for denoising a single-lead ECG signal. It was designed to ease the use of heuristic procedures for removing the most common types of noises from ANSI/AAMI-compliant ECG signals. However, in this paper, only the system-noise was considered to illustrate how this geometrical criterion is applied to the signal. The proposal here presented relies on a voltage-level slope detector that marks where the signal starts to increase, decrease or remain at the same level in order to perform an abstract segmentation of the ECG signal. The resulting segments are quantitatively classified as significant segments or noisy segments by analyzing their amplitude and time duration according to a previously defined threshold-level with the intention of helping the algorithm to decide its own operational parameters. The system-noise filter proposed here has five different operation modes. The main one is based on the arithmetic mean operation to smooth out short-term fluctuations; additionally, it is complemented with geometrical estimations for preserving the physiological characteristics of the ECG signal. The other operation modes are purely based on geometric estimations to calculate the filter output. The geometrical criterion described here differs from many other approaches presented until now owing to its low mathematical complexity and low computational consumption since all calculations can be performed with raw ADC readings and arithmetical operations, characteristics that make this filter easy to implement on embedded systems. This denoising approach was designed for online processing applications but it also works well with previously recorded signals.
The optimization is essential in the engineering area and, in conjunction with use of meta-heuristics, has had a great impact in recent years; this is because of its great precision in search of optimal parameters for the solution of problems. In this work, the use of the Artificial Bee Colony Algorithm (ABC) is presented to optimize the values for the variables of a proportional integral controller (PI) to observe the behavior of the controller with the optimized Ti and Kp values. It is proposed using a robot built using the MINDSTORMS version EV3 kit. The objective of this work is to demonstrate the improvement and efficiency of the controllers in conjunction with optimization meta-heuristics. In the results section, we observe that the results improve considerably compared to traditional methods. In this work, the main contribution is the implementation of an optimization algorithm (ABC) applied to a controller (PI), and the results are tested to control the movement of a robot. There are many papers where the kit is used in various domains such as education as well as research for science and technology tasks and some real-world problems by engineering scholars, showing the acceptable result.
The design of neural network architectures is carried out using methods that optimize a particular objective function, in which a point that minimizes the function is sought. In reported works, they only focused on software simulations or commercial complementary metal-oxide-semiconductor (CMOS), neither of which guarantees the quality of the solution. In this work, we designed a hardware architecture using individual neurons as building blocks based on the optimization of n-dimensional objective functions, such as obtaining the bias and synaptic weight parameters of an artificial neural network (ANN) model using the gradient descent method. The ANN-based architecture has a 5-3-1 configuration and is implemented on a 1.2 μm technology integrated circuit, with a total power consumption of 46.08 mW, using nine neurons and 36 CMOS operational amplifiers (op-amps). We show the results obtained from the application of integrated circuits for ANNs simulated in PSpice applied to the classification of digital data, demonstrating that the optimization method successfully obtains the synaptic weights and bias values generated by the learning algorithm (Steepest-Descent), for the design of the neural architecture.
Obstacle-avoidance robots have become an essential field of study in recent years. This paper analyzes two cases that extend reactive systems focused on obstacle detection and its avoidance. The scenarios explored get data from their environments through sensors and generate information for the models based on artificial intelligence to obtain a reactive decision. The main contribution is focused on the discussion of aspects that allow comparing both approaches, such as the heuristic approach implemented, requirements, restrictions, response time, and performance. The first case presents a mobile robot that applies fuzzy logic to achieve soft turning basing its decision on depth image information. The second case introduces a mobile robot based on multi-layer perceptron and ultrasonic sensors to decide how to move in an uncontrolled environment. The analysis of both options offers perspectives to choose between reactive obstacle-avoidance systems based on ultrasonic or Kinect sensors, models that infer optimal decisions applying fuzzy logic or artificial neural networks, with key elements and methods to design mobile robots with wheels. Therefore, we show how AI or Fuzzy Logic techniques allow us to design mobile robots that learn from their “ experience ” by making them safe and adjustable for new tasks, unlike traditional robots that use large programs to perform a specific task.
Road event detection is critical for tasks such as monitoring, anomaly detection, and optimization. Traditional approaches often require complex feature engineering or the use of machine learning models, which can be computationally intensive, especially when dealing with real-time data from high-frequency vibration and acceleration sensors. In this work, we propose a Random Forest-based event classification algorithm designed to handle the unique patterns of vibration and acceleration data in road event detection for an urban traffic scenario. Our method utilizes vibration and acceleration data in three axes (x, y, z) to classify events in a robust and scalable manner. The Random Forest model is trained to identify patterns in the sensor data and assign them to predefined event categories, providing an efficient and accurate classification mechanism. Experimental results prove the effectiveness of our approach: it reaches an accuracy of 91.99%, with a precision of 80% and a recall of 75%, demonstrating reliable event classification. Additionally, the Area Under the Curve (AUC) score of 0.9468 confirms the model’s strong discriminative capability. Further, compared to a rule-based approach, our method offers greater generalization and adaptability, reducing the need for manual parameter tuning. While the rule-based approach attains a higher precision of 92%, it requires frequent adjustments for each dataset and lacks robustness across different road conditions.
As soft-hardware-logic circuits had been proposed in the literature as an alternative for digital circuits taking advantage the fact that any Boolean function could be implemented with the same cell, just configuring external signals, this work shows a methodology that could be followed particularly for the design of a four bits logic gate, using the so-called neuron MOS transistor (ν-MOS). Simulation results show the feasibility of the design for performing as XNOR, NOR, OR, XOR, AND or NAND logic gates, for instance. In order to extrapolate the design to a higher number of bits, the key issue is to properly consider the weight of the input capacitances in correlation with the number of input bits. A D/A converter can be used as the input stage of the configuration. This design considers the D/A converter-less version, since it helps to increase device integration as the number of transistors used is reduced with no difference in its performance. The design should be based on the theoretical floating potential diagram (FPD) of the desired logic gate.
This item presents the real-time programming of a prototype robot to control its movement from one moment toanother without showing response delays. Contributing to this is the communication protocol developed in ourlaboratories and feasibility of being implemented in the future with wireless control via radio frequency, and to presentthe progress to date have been obtained.
This paper presents the development of a nutritional system using Backpropagation neural network, that is able to provide a clear and simple prediction problems of obesity in children up to twelve years, based on your eating habits during the day. For the development of this project has taken into account various factors, which are vital for the proper development of infants. A prediction system can offer a solution to several factors, which are not easily determined by convectional means.
The present research work is about the simulation in real time to control the movement of an arm, through the acquisition of myoelectric data. The system can help the development and perfection of upper limb prostheses through the use of the tools LabVIEW, SolidWorks, Arduino and Muscle Sensor v3.
This article presents the development of a support system for the physician in the diagnosis of mental illness; the system is based on an Adaline neural network for the processing of biomedical signals from 4 types of ocular movements in order to extract their information and interpret the action potential of each eye movement under study.
<p>This study explores the efficacy of software simulation in refining control system design, focusing on the implementation of a fuzzy controller within a Ball & Beam system. The proposed fuzzy controller, validated through SIMULINK simulation experiments, demonstrated robust performance in handling disturbances, inaccuracies, and noise. Employing a cascade structure for dual control, managing both beam angle and ball position, enhanced disturbance rejection and overall system performance.</p>
<p>This study explores the efficacy of software simulation in refining control system design, focusing on the implementation of a fuzzy controller within a Ball & Beam system. The proposed fuzzy controller, validated through SIMULINK simulation experiments, demonstrated robust performance in handling disturbances, inaccuracies, and noise. Employing a cascade structure for dual control, managing both beam angle and ball position, enhanced disturbance rejection and overall system performance.</p>
<title>Abstract</title> Detecting objects in images is crucial across a wide range of applications, including surveillance, autonomous navigation, augmented reality, and more. While AI-based approaches such as Convolutional Neural Networks (CNNs) have proven highly effective in object detection, in some industrial applications where the objects being recognized are confidential, it is difficult to train an AI for such tasks. On the other hand, feature-based approaches like SIFT, SURF, and ORB offer the capability to search any template but may struggle with complex visual variations. In this work, we introduce a novel edge-based object/scene recognition method. We propose that utilizing feature edges, instead of feature points, offers high performance under complex visual variations. Our primary contribution is a directional pixel voting descriptor based on image segments. Experimental results are promising; compared to previous approaches, ours demonstrates superior performance under complex visual variations, enabling real-time processing with embedded capabilities.
Methotrexate is an antimetabolic agent with proliferative and immunosuppressive activity. It has been demonstrated to be an effective treatment for acute lymphoblastic leukemia (ALL) in children. However, there is evidence of an association between methotrexate and toxicity risks, which influences the personalization of treatment, particularly in the case of childhood ALL. This article presents the development and implementation of an algorithm based on artificial neural networks to detect methotrexate toxicity in pediatric patients with acute lymphoblastic leukemia. The algorithm utilizes historical clinical and laboratory data, with an effectiveness of 99% in the tests performed with the patients dataset. The use of neural networks in medicine is often linked to disease diagnosis systems. However, neural networks are not only capable of recognizing examples, but also hold very important information. For this reason, one of the main areas of application of neural networks is the interpretation of medical data. In this article we diagnose with the application of neural networks in medicine with a concrete example: Detecting Methotrexate in Pediatric Patient in its early stages.
Detecting objects in images is crucial for several applications, including surveillance, autonomous navigation, augmented reality, and so on. Although AI-based approaches such as Convolutional Neural Networks (CNNs) have proven highly effective in object detection, in scenarios where the objects being recognized are unknow, it is difficult to generalize an AI model for such tasks. In another trend, feature-based approaches like SIFT, SURF, and ORB offer the capability to search any object but have limitations under complex visual variations. In this work, we introduce a novel edge-based object/scene recognition method. We propose that utilizing feature edges, instead of feature points, offers high performance under complex visual variations. Our primary contribution is a directional pixel voting descriptor based on image segments. Experimental results are promising; compared to previous approaches, ours demonstrates superior performance under complex visual variations and high processing speed.
Superpixel segmentation aims to produce a consistent grouping of pixels. In recent years, the importance of superpixel segmentation has increased in computer vision since it offers useful primitives for extracting image features and simplifies the complexity of other image processing steps. In this work, we propose the TurboPixels algorithm, whose main contribution is a hardware architecture for superpixel segmentation. Compared with previous approaches, our superpixels are computed without the need for iterative loops. This makes it possible to reduce algorithmic complexity and increases processing speed. The experimental results indicate that our approach enables a small-scale FPGA-based implementation suitable for embedded applications. In addition, the results demonstrate that robust superpixel segmentation can be achieved with processing speeds up to 86 times faster than in previous works in the current literature.
Methotrexate is an antimetabolic agent with proliferative and immunosuppressive activity. It has been demonstrated to be an effective treatment for acute lymphoblastic leukemia (ALL) in children. However, there is evidence of an association between methotrexate and toxicity risks, which influences the personalization of treatment, particularly in the case of childhood ALL. This article presents the development and implementation of an algorithm based on artificial neural networks to detect methotrexate toxicity in pediatric patients with acute lymphoblastic leukemia. The algorithm utilizes historical clinical and laboratory data, with an effectiveness of 99% in the tests performed with the patient dataset. The use of neural networks in medicine is often linked to disease diagnosis systems. However, neural networks are not only capable of recognizing examples but also hold very important information. For this reason, one of the main areas of application of neural networks is the interpretation of medical data. In this article, we diagnose, with the application of neural networks in medicine, a concrete example: detecting methotrexate in its early stages in pediatric patients.
Estimating ego-motion in autonomous vehicles is critical for tasks such as localization, navigation, obstacle avoidance, and so on. While traditional methods often rely on direct pose estimation or AI-based approaches, these can be computationally intensive, especially for small, incremental movements typically observed between consecutive frames. In this work, we propose a brute-force-based ego-motion estimation algorithm that takes advantage of the constraints of autonomous vehicles, which are assumed to have only three degrees of freedom (x, y, and yaw). Our approach is based on a genetic algorithm to efficiently explore potential vehicle movements. By generating an initial seed of random motion candidates and iteratively mutating and selecting the best-performing individuals, we minimize the cost function that measures image similarity between frames. Furthermore, we implement the algorithm using CUDA to exploit parallel processing, significantly improving computational speed. Experimental results demonstrate that our approach achieves accurate ego-motion estimation with high efficiency, making it suitable for real-time autonomous vehicle applications.
Background: In the current context of increasing competitiveness and complexity in markets, accurate demand forecasting has become a key element for efficient production planning. Methods: This study implements recurrent neural networks (RNNs) to predict raw material demand using historical sales data, leveraging their ability to identify complex temporal patterns by analyzing 156 historical records. Results: The findings reveal that the RNN-based model significantly outperforms traditional methods in predictive accuracy when sufficient data is available. Conclusions: Although integration with MRP systems is not explored, the results demonstrate the potential of this deep learning approach to improve decision-making in production management, offering an innovative solution for increasingly dynamic and demanding industrial environments.
Vehicular Ad Hoc Networks (VANETs) enable critical communication for Intelligent Transportation Systems (ITS) but are vulnerable to cybersecurity threats, such as Gray Hole attacks, where malicious nodes selectively drop packets, compromising network integrity. Traditional detection methods struggle with the intermittent nature of these attacks, necessitating advanced solutions. This study proposes a machine learning-based Intrusion Detection System (IDS) to detect Gray Hole attacks in VANETs. Methods: This study proposes a machine learning-based Intrusion Detection System (IDS) to detect Gray Hole attacks in VANETs. Features were extracted from network traffic simulations on NS-3 and categorized into time-, packet-, and protocol-based attributes, where NS-3 is defined as a discrete event network simulator widely used in communication protocol research. Multiple classifiers, including Random Forest, Support Vector Machine (SVM), Logistic Regression, and Naive Bayes, were evaluated using precision, recall, and F1-score metrics. The Random Forest classifier outperformed others, achieving an F1-score of 0.9927 with 15 estimators and a depth of 15. In contrast, SVM variants exhibited limitations due to overfitting, with precision and recall below 0.76. Feature analysis highlighted transmission rate and packet/byte counts as the most influential for detection. The Random Forest-based IDS effectively identifies Gray Hole attacks, offering high accuracy and robustness. This approach addresses a critical gap in VANET security, enhancing resilience against sophisticated threats. Future work could explore hybrid models or real-world deployment to further validate the system’s efficacy.
Road event detection plays a key role in tasks such as monitoring, anomaly identification, and urban traffic optimization. Conventional methods often rely on feature extraction and classification or classical machine learning models, which may struggle when processing high-frequency signals in real time. In this work, we propose a CNN-based classification approach designed to handle multi-axial acceleration and vibration signals captured from road scenarios. Instead of relying on static feature sets, our method leverages a convolutional neural network architecture capable of automatically learning discriminative patterns from raw sensor data. We structure the time-series input into temporal windows and use it to train models that can identify different event categories, including “Speed Bumps”, “Potholes”, and “Sudden Braking” events. The experimental results show that our approach achieves an accuracy of 93.51%, with a precision of 93.56% and a recall of 93.51%. Further, the average AUC score of 0.9855 confirms the strong discriminative power of our proposal. In contrast to rule-based methods, which require frequent tuning to adapt to new datasets, our approach generalizes better across different road conditions and offers a practical alternative for real-time deployment in dynamic environments, outperforming rule-based approaches by over 10% in F1-score, while preserving deployment efficiency on embedded hardware.
The product delivery process is a set of steps to transport a product of an origin to a delivery point. Nowadays, there are different platforms or software based on classical algorithms for network optimization that help develop routes. Although these informatics systems provide vehicle routes, their prediction time has low accuracy compared to real times in the product distribution, since these systems do not consider the elements that affect route planning, i.e., despite providing vehicle routes, these software systems have low prediction accuracy. To address this problem, an alternative is to use artificial intelligence systems that consider the knowledge of the product delivery planning into route optimization models, thus increasing the time accuracy, but adding the challenge of having to interpret correctly the vehicle route ambiguities. Motivated by the latter, we propose a new fuzzy linear programming formulation to predict delivery times for products. Unlike previous studies, our methodology considers various parameters in the distribution process and offers an effective way to identify which parameters should be used. Our strategy combines the abstraction power of fuzzy logic and the result that provides a route optimization analysis, i.e., this work brings the best of the two worlds to address the difficult problem of shortest-route in product delivery. For that, our methodology has three steps. First, we introduce our formulation that incorporates a Fuzzy Inference System (FIS) into linear programming to achieve accurate time predictions in product delivery. Second, we propose a fuzzy adjustment coefficient to consider the uncertain factors in product distribution and the expertise of the delivery staff. Finally, we develop a Geographic Information System (GIS) to visualize the distribution route and its time. On the other hand, we evaluate this methodology in the routes of a soft drink company using statistical analyses. Experimental results are feasible and promising. For example, in real-world scenarios, our approach reduced the Mean Absolute Percentage Error (MAPE) by 56% compared to methods that utilize artificial intelligence.
I invite you to collaborate with the signal processing group for road safety using AI techniques with OBD2 data for the development of algo…
I invite you to collaborate with the signal processing group for road safety using AI techniques with OBD2 data for the development of algo…