https://hdl.handle.net/20.500.12724/20620 Wed, 13 May 2026 05:23:45 GMT 2026-05-13T05:23:45Z https://hdl.handle.net/20.500.12724/17607 Semantic Segmentation of Underwater Environments Using DeepLabv3+ and Transfer Learning Chicchón Apaza, Miguel Ángel; Bedón Monzón, Héctor Manuel The semantic segmentation approach is essential in automated scene analysis, but its application in underwater environments is still limited. Datasets generally have insufficient labeled data, unbalanced data classes, and different lighting conditions, making it difficult to obtain optimal results. Currently, deep convolutional neural networks allow very good results in machine vision tasks, and one of the network architectures with good performance in semantic segmentation is DeepLabv3 +. This paper evaluates the performance of DeepLabv3 + and transfer learning based on pre-trained backend networks in ImageNet to study underwater scenes. The experimentation is carried out on a dataset available on the Internet with labels of eight classes. Experimental results show that DeepLabv3 + and transfer learning are effective for semantic segmentation of multiple underwater scene objects with insufficient tagged data and unbalanced classes. Sat, 01 Jan 2022 00:00:00 GMT https://hdl.handle.net/20.500.12724/17607 2022-01-01T00:00:00Z https://hdl.handle.net/20.500.12724/17591 Influencia de la Autonomía Laboral en el Balance Vida-Trabajo del Personal de Atención Médica Campoverde, Ronald; Paredes Aguirre, Milton; Barriga Medina, Holger; Carpio Freire, Carlos Raúl; Bastidas Lucín, Ammy Los trabajadores pueden alcanzar el bienestar laboral a partir de la autonomía y el balance vida-trabajo. Este bienestar, reduce la exposición a factores negativos que afectan su salud física y psicológica. Por ello, esta investigación determina la relación que existe entre autonomía y balance vida-trabajo en los profesionales de salud del área de emergencia. Se realizó un estudio de corte transversal de enero a junio del 2021 en un hospital público de Guayaquil. Para determinarla relación se utilizó el cuestionario de autonomía propuesto por Kuratko y de balance vida-trabajo propuesto por Tasdelen y Bakalim. Los resultados muestran una relación significativa entre autonomía y balance vida-trabajo. En conclusión, promover la autonomía laboral afecta positivamente el balance vida-trabajo, lo cual mejora la calidad de vida del personal.; Workers can get labour well-being based on autonomy and work-life balance. This well-bieng reduces exposure to negative factors that affect their physical and psychological health. Therefore, this research determines the relationship between autonomy and work-life balance in emergency area’s professionals. A cross-sectional study was carried out from January to June 2021 in a public hospital in Guayaquil. To determine the relationship, autonomy questionna ire proposed by Kuratko and the work-life balance questionnaire proposed by Tasdelen y Bakalim were used. The results show a significant relationship between autonomy and work-life balance. In conclusion, promoting work autonomy positively affects the work-life balance, which improves the quality of life of the staff. Sat, 01 Jan 2022 00:00:00 GMT https://hdl.handle.net/20.500.12724/17591 2022-01-01T00:00:00Z https://hdl.handle.net/20.500.12724/13906 Nonlinear waves in pantographic beams induced by transverse impulses Chicchón Apaza, Miguel Ángel; Huerta, Ronny Peru is one of the main producers of a wide variety of native potatoes in the world. Nevertheless, to achieve a competitive export of derived products is necessary to implement automation tasks in the production process. Nowadays, volume measurements of native potatoes are done manually, increasing production costs. To reduce these costs, a deep approach based on convolutional neural networks have been developed, tested, and evaluated, using a portable machine vision system to improve high-speed native potato volume estimations. The system was tested under different conditions and was able to detect volume with up to 90% of accuracy. Fri, 01 Jan 2021 00:00:00 GMT https://hdl.handle.net/20.500.12724/13906 2021-01-01T00:00:00Z https://hdl.handle.net/20.500.12724/13427 Marine Delay and Disruption Tolerant Networks (MaDTN): Application for Artisanal Fisheries Bedón Monzón, Héctor Manuel; López Pastor, Jaime; Cedeño Herrera, Edwin; Nieto, C.M. The artisanal fishing activity carried out on the coasts where the production of fish can be exploited is affected by a lack of communication between the vessels in order to provide relevant information related to multiple marine sensor parameters. It is mainly due to the rugged geographic area that causes highly disruptive communication links and in which traditional IP-based communications with transport protocols such as TCP or UDP do not work properly. This paper presents and evaluates a new communications architecture to provide services to marine sensor networks using a disruption tolerant networking (DTN) based solution. We propose a new architecture that takes into account the different vessels densities. We assume a finite sensor population model and a saturated traffic condition where every sensor always has frames to transmit. The performance was evaluated in terms of delivery probabilities, delay and a DTN scenario indicator (DSI) proposed. Through simulations, this paper reveals that Low Density scenery yield greater latency, and more density of nodes has better results. We achieved a successful delivery rate of 74% and a latency of 2 h approximately. Finally indicators shows that high density of nodes is strongly recommended for fishery scenery models. Fri, 01 Jan 2021 00:00:00 GMT https://hdl.handle.net/20.500.12724/13427 2021-01-01T00:00:00Z