Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Efficient analysis and compression of urban green areas in RGB drone imagery using the OSAVI index(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025-06-12) Hernández Animas, Edwin; Camacho León, Sergio; emipsanchez; Mendoza Montoya,Omar; Barrios Piña, Héctor Alfonso; School of Engineering and Sciences; Campus MonterreyGreen urban area detection is essential for environmental planning; traditional field surveys are laborintensive and time-consuming, making remote sensing (drone and satellite imagery) a powerful alternative. Three main problems are detected by working with these technologies: i) While enabling detailed analysis of lawns and individual trees due to their high spatial resolution, this results in data storage demands. ii) Moreover, the Normalized Difference Vegetation Index (NDVI), the most widely used for analyzing general vegetation, is highly sensitive to soil brightness, making it less suitable for examining urban greenery where bare soil, artificial surfaces, and mixed land covers are common. iii) Additionally, existing tree inventory algorithms in urban or heterogeneous environments remain labor-intensive, as they require annotated training samples to effectively distinguish trees from surrounding features. This study presents high-resolution multispectral and RGB imagery captured by an Unmanned Aerial Vehicle (UAV), the DJI MAVIC 3M, used to measure general vegetation. A masking process based on morphological operations was applied to segment green urban areas in the RGB image, to optimize both image storage size with lossless compression (Deflate & LZW) and traditional tree inventory based on crown detection (DeepForest). The segmentation based on Optimized Soil-Adjusted Index (OSAVI) mask applied in urban areas presents multiple advantages in terms of reduction of storage size due to the increase in homogeneous regions with pixel values sharing identical color characteristics. By using the OSAVI vegetation index as the masking criterion, the dense vegetation (trees) is not affected during the process, preserving its location and color (pixel values) of the original image, excelling current tree inventory algorithms (DeepForest) based on orthoimages without the need to prepare additional training data. Using the OSAVI instead of NDVI outperformed traditional green urban area segmentation, demonstrating 25% more robustness in avoiding saturation caused by Near-Infrared (NIR) reflecting areas. The segmentation performance achieved by OSAVI and morphological operations resulted in: IoU = 0.85 | Dice = 0.91 | Precision = 0.89 | Recall = 0.94 | Accuracy = 0.96. The final storage sizes of the masked RGB images were equal to the percentage of vegetation multiplied by the storage size of the non-masked (original) compressed images, with a Pearson Correlation of 0.98, being the Deflate method superior (bpp = 9) to the LZW method (bpp = 11.40) in terms of storage efficiency. The comparison between the tree inventory on the original RGB scenarios presented a Mean Absolute Error (MAE) = 193.25, and the RGB images masked by OSAVI index MAE = 98.25, 49% better and closer to the real tree inventory, with a Friedman test p-value = 0.046 rejecting the null hypothesis that all methods (Baseline: Precision = 0.33 | Recall = 0.45 | F1 = 0.38 and Proposed: Precision = 0.54 | Recall = 0.53 | F1 = 0.53 ) perform equally.
- Effect of different agricultural ecosystems of the north-eastern Mexican territory on power degradation of radio frequency waves on LoRa-based communication applications(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024) Assad Santos, Alan; Camacho León, Sergio; emimmayorquin; Vidal Rosas, Alejandro; School of Engineering and Sciences; Campus Monterrey; Rodriguez Corbo, FidelThe increasing demand for crop production driven by human overpopulation, high meat and dairy consumption, and biofuel demands imposes a substantial increase in agricultural productivity by 2050. Rather than expanding agricultural land, enhancing crop yields emerges as a sustainable solution. Smart farming, an evolved form of Precision Agriculture, integrates Internet-of-Things (IoT) technologies to facilitate strategic decision-making in agriculture. This study focuses on evaluating the performance of the LilyGo LoRa T3S3 on diverse agricultural environments of the north-eastern Mexican territory, varying parameters such as distance from gateway to transmitter, transmitter height, transmitter output power, and spreading factors. Insights gained emphasize the significance of environmental considerations in communication architecture design for smart farming applications. Measurement of energy consumption across spreading factors determines optimal sensor deployment strategies, which are vital for sustainable farming practices. The coverage maps derived from experiments provide actionable guidance for sensor placement in agricultural landscapes, facilitating effective monitoring of soil properties, moisture levels, crop health, and environmental conditions. This research advances efficient and sustainable sensor deployment in smart farming, empowering farmers to optimize crop yields and foster sustainable agricultural practices for the future.
- Development of algorithm and architecture design of camera-radar perception system for agriculture & construction machinery(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-11-27) De la Fuente Bustos, Juan Francisco David; Camacho León, Sergio; emipsanchez; Escobedo Cabello, Jesús Arturo; School of Engineering and Sciences; Campus Monterrey; Vidal Rosas, AlejandroIn a smart farming & construction automated working scenario, the machinery needs accurate perception resources to autonomously perform the tasks and even stop them when an object is frontal, or rear detected. Automotive devices like lidars, radars, cameras and other vision systems are being integrated into road vehicles over the last years. There is profound literature available only on on-road area; there exist many other challenges when dealing with off-road vehicles such as agriculture & construction machinery. The understanding of sensor fusion levels to develop an advanced, cheap, robust, and reliable Camera-Radar perception system output is proposed. Radar provides speed with great precision, and it has good performance vs poor weather conditions. Camera delivers high resolution images, color, and depth information. The architecture design is driven by a low-level fusion, it means that relies on the choice of simple mmWave radar and stereo camera together with a smart ECU (Electronic Control Unit). As a result, real-time colored 3D cloud point information is obtained with high resolution from the camera and radar. Object range is also given by the radar. The proposed objective is to carry out testing through real experiments, understand camera+radar object detection capabilities along different conditions. Also, the aim of this investigation is to increase repertory of heavy machinery environmental expectations aligned to most common scenarios and how they would affect perception system output.
- Design and validation of an IoT platform with adaptive data logging for remote real time monitoring of rapid changing variables in indoors and outdoors environments(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2020-05-14) López Hernández, José Yael; CAMACHO LEON, SERGIO; 213140; LOPEZ HERNANDEZ, JOSE YAEL; 888357; VAZQUEZ PIÑON, MATIAS; 299241; MENDOZA BUENROSTRO, CHRISTIAN CARLOS; 295935; Camacho León, Sergio; Vázquez Piñón, Matias; Mendoza Buenrostro, Christian Carlos; School of Engineering and Sciences; Campus MonterreyThis thesis addresses the impact of Internet of Things (IoT) development as well as its growing importance in the industry of big economies like China and shows the development of an IoT platform for real-time data acquisition and display on a web page. From the beginning of this decade, the Chinese government has been focusing on the development of new technologies like IoT devices and services by investing in fast-growing cities through the implementation of the so-called "Science Cities". A research carried out in China, that had as scope the use of IoT technologies, resulting in the knowledge that there is a need of the development of IoT devices to fulfill the industry requirements, thus a prototype for remote data monitoring using a microcontroller capable to connect to Wi-Fi networks is proposed. The system prototype that was developed is based on a client-server architecture following a Device-To- Gateway communication model using on-the-shelf components for the measurement of humidity and temperature as well as acquiring Global Position System (GPS) information. For this system, a web page interface was designed to display the collected readings. The maintenance, accuracy, and consistency of data, referring to the data integrity, was obtained in every test performed using the system prototype. This prototype was tested in static indoor environments, where the devices did not change their location during the test, and dynamic outdoor environments, where the devices were shifting locations during the test. The obtaining _findings of the prototype performance show 94.76% of data integrity on the indoor static test and 76.76% using the web page in the same conditions. On the other hand, the outdoor dynamic test achieved a maximum of 44.66% of data integrity, which dropped to 17.24% by using the web page. It is observed how the use of the web page results in a decrease of the data integrity mostly because of the network compatibility between the Wi-Fi device and frequency bands that the network vendor uses to connect to the internet. A test performed using an adaptive method, where the temperature was constantly being modified, resulted in an increase in the efficiency of how the data is saved in the storage device achieving a data reduction of 74% and a final Comma-Separated Values (CSV) _le size decrease of 75%. The data acquired is then used for further processing by calculating the position based on the GPS latitude and longitude, the velocity using an approach with backward differences and acceleration using an approach with centered differences. The experimental results show that the IoT system prototype can be used for the measurements of environmental variables on indoor and outdoor applications.
- Comparative analysis of power consumption between MQTT and HTTP protocols for an IoT platform designed and implemented for remote real-time monitoring of long-term cold chain transport operations.(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2020) Jara Ochoa, Heriberto Javier; CAMACHO LEON, SERGIO; 213140; JARA OCHOA, HERIBERTO JAVIER; 852655; VAZQUEZ PIÑON, MATIAS; 299241; CESPEDES MOTA, ARMANDO; 53083; Camacho León, Sergio; RR; Vázquez Piñón, Matias; Céspedes Mota, Armando; School of Engineering and Sciences; Campus MonterreyIn the actual world, huge technological advances in the IoT area have been developed in the course of the last few years. IoT systems have had an exponential growth and have contributed to the development of novel applications in industries, health, wearables, domotics, smart supply chains, logistics, among many others. Nowadays, IoT technological solutions have been invented and developed for the transport industry to monitor vehicles speed, avoid accidents, choose better routes, track supply chains, monitor load conditions, among others. The development and production of IoT devices in portable systems brings with it an increase in the importance of power consumption. For this, as alternatives to reduce power wastage, many communication protocols have been tested such as HTTP with the client-server model and MQTT with the publisher-subscriber model. In this thesis project, the prototype is intended to work on ground cargo transport to monitor temperature and humidity values of the load, and vehicle's location. Temperature, humidity and location variables are sent in real-time via Wi-Fi to a MySQL database and either to a web server created by the NodeMCU microcontroller or to a cloud-based broker. The experimentation is done in both HTTP and MQTT communication protocols in order to make a comparison and demonstrate the differences in power consumption. First, in this thesis project, research was made in the city of Hangzhou, considered as the capital of e-commerce in China, having as main scope the use of IoT technology and services in a first world country such as China. China has had an important growth in the number of IoT connections over the last 5 years, and in this thesis is pretended to make an analysis of the IoT technology in industries either because IoT solutions are used to be sold or to be implemented in manufacturing processes. In order to locate the area where IoT technology abounds, according to the results of the field investigation, most of the IoT companies which were analyzed in Hangzhou, are focused on mechanical and industrial engineering areas which have been inaugurated between the years 2000 - 2011. Most of these companies have between 51 and 200 employees and earn around 1 to 2.5 millions of dollars in a year. In the prototype developed in this thesis, a design and validation of an electronic platform system for remote real-time monitoring is proposed using the ESP8266 microcontroller. ESP8266 is a very complete wireless microcontroller, which can be used for many purposes and can work with Wi-Fi technology. Besides, its low-cost and its easy of working make it a good solution in IoT problems. The system is able to detect the humidity and temperature of the environment with a DHT11 sensor, and detect the actual location with a NEO-6M GPS sensor. The collected information is saved in a MicroSD Card, displayed in a LCD and sent through HTTP or MQTT protocol to a web server where the data can be visualized in real-time with respective indicators and a dynamic map. Also, the information of the sensor readings are sent to a MySQL database. The server in HTTP protocol is built by the ESP8266 microcontroller, while in the MQTT protocol, ESP8266 is used to communicate with the specialized cloud-based broker Adafruit IO. A device-to-gateway model was used in the MQTT protocol where the Adafruit IO cloud-based broker acts as a cloud-based gateway. Since MQTT protocol is associated as the main communication protocol in IoT, it is imperative to explore and analyze the power consumption of this protocol with different conditions. The experimentation is done in HTTP protocol and in MQTT protocol with different QoS levels in order to make a comparison and demonstrate the differences in power consumption. The experimentation in MQTT protocol with QoS 0 and 1 was successful resulting in power savings of 6.03% and 8.33% respectively, compared with HTTP protocol, representing many hours more in the duration of the battery, which can be very useful in technological solutions for the transport industry.
- Optical flow sensor for droplet-based Lab-on-PCB devices(Instituto Tecnológico y de Estudios Superiores de Monterrey) Solano Teran, Daniel Hugo; CAMACHO LEON, SERGIO; 213140; Camacho León, Sergio; puelquio, emipsanchez; Luque Estepa, Antonio; Vázquez Piñón, Matías; Escuela de Ingeniería y Ciencias; Campus MonterreyAdvancements on Lab-on-a-PCB devices nowadays focus on design goals such as Affordable, Sensitive, Specific, User-friendly, Rapid and robust, Equipment-free, Deliverable to end-users (ASSURED) devices. However, most of these new systems present external equipment dependencies, complex set-up processes, low reproducibility factors, and intricate manufacturing processes. For many industries (medical, pharmaceutical, cosmetics), Lab-on-a-PCB devices are capable of characterizing multiphase systems such as cell-in-droplets identification, flow-phase characterization, and micromixing detection. Thus, this work presents a new optical droplet detector, employing common and cost-effective electronics components. The device consists of a fluid channel between a light-emitting diode (LED) and a photo-resistor (LDR), whose voltage variation is measured and then processed with an ARDUINO microcontroller. This new sensor can determine different multiphase flow properties such as velocity, flow, droplet lengths, and volume with high-speed throughput up to 1000 droplets per second. Furthermore, this sensor presents a modular electronic design that provides a simple calibration, high adaptability, and a standardized fabrication process. Therefore, it creates a cost-effective, portable, easy-to-fabricate, and plug-and-play environment for the alignment with the ASSURED criteria. Droplet detection and characterization showed MRE values ranging from 2.4% up to 17%. The lowest MRE value was obtained using a two-phase flow system with water-in-air droplets at a sampling rate of 2.3 kHz for flow rates starting at 20 up to 425 μL/min. In contrast, the highest MRE value reported was under a three-phase flow system for dyed and pure water-in-air droplets at a 5 kHz sampling rate at a 250 µL/min flow rate.