42 research outputs found
Superresolution recurrent convolutional neural networks for learning with multi-resolution whole slide images
No full textThis file was last viewed in Microsoft Edge.A recurrent convolutional neural network is supervised machine learning way to process images that has both properties of convolutional and recurrent networks. We propose Convolutional Neural Network (CNN) based approach and its advanced recurrent version (RCNN) to solve the problem of enhancing the resolution of images obtained from a low magnification scanner, also known as the image super-resolution (SR) problem. The given class of scanner produces microscopic images relatively fast and storage efficiently. However, those scanners generate comparatively low quality images than images from complex and sophisticated scanners and do not have the necessary resolution for diagnostic or clinical researches, therefore low resolutions scanners are not in demand. The motivation of this study is to determine whether an image with low resolution could be enhanced by applying deep learning framework such that it would serve the same diagnostic purpose as a high resolution image from expensive scanners or microscopes. We presented novel network design and complex loss function. We validate these resolution improvements with computational analysis to show an enhanced image give the same quantitative results. In summary, our extensive experiments demonstrate that this method indeed produces images which are same quality to images from high resolution scanners. This approach opens up new application possibilities for using low-resolution scanners not only in terms of cost but also in access and speed of scanning for both research and possible clinical use
Project Play: An exploration of how to combine architecture and play
No full textEverything started with my fascination of Pokémon-Go; the cultural moment when the building environment was used differently than intended; massive groups gathered around in public parks and kids invading your backyard. I wanted to understand the behavior of people and the new ways of interaction between space and humans. Literature research helped defining different fields of game-theory and architectural space, and most importantly the relationship between those. It gave the knowledge needed to do observations and make new conclusions. The results were descriptions of spaces where the situation of the Pokémon-GO effect occurred: playgrounds. These playgrounds were spaces where the players could be free and use their imagination to build their own world, where humans can be playful. With my design I intent to have the same methodology as these playgrounds.Architecture, Urbanism and Building Sciences | Explorela
Biermannia averyanovii, comb. nov.
No full text<i>Biermannia averyanovii</i> (Vuong, Kumar, V.H. Bui, V.S.Dang in Pham <i>et al.</i>) Averyanov, <i>comb. nov.</i> <p> ≡ <i>Chamaeanthus averyanovii</i> Vuong, Kumar, V.H. Bui & V.S.Dang in Pham <i>et al.</i> (2021: 132, fig. 1).</p> <p> <b>Type</b>:— VIETNAM. Son La Province: Thuan Chau District, 18 June 2021, <i>Truong Ba Vuong, Bui Van Huong, BV 1194</i> (VNM 00069908).</p> <p> <b>Notes</b>:—We can not see any fundamental differences between <i>Biermannia</i> King & Pantling (1897: 591) and <i>Chamaeanthus</i> Schlechter ex J.J. Smith (1905: 552) except for insufficient variation on the length of the column foot. Following Seidenfaden & Wood (1992), we consider these genera congeneric and use here earlier valid name. Data on ecology, phenology, distribution, and conservation status for this species were reported earlier (Pham <i>et al.</i> 2021).</p>Published as part of <i>Averyanov, Leonid V., Nguyen, Van Canh, Truong, Ba Vuong, Nguyen, Khang Sinh, Nguyen, Cuong Huu, Maisak, Tatiana V., Doan, Nga Thi, Nguyen, Tuan Hoang, Pham, Van The, Dat, Pham Thi Thanh, Thai, Tran Huy, Nguyen, Van Khuong & Trinh, Ngoc Bon, 2023, New orchids in the flora of Vietnam VI (Orchidaceae, tribes Arethuseae, Cymbidieae, Diurideae, Epidendreae, Vandeae, and Vanilleae), pp. 87-110 in Phytotaxa 597 (2)</i> on page 101, DOI: 10.11646/phytotaxa.597.2.1, <a href="http://zenodo.org/record/7929197">http://zenodo.org/record/7929197</a>
Panisea sondangii Aver. 2023, comb. nov.
No full textPanisea sondangii (Vuong, Aver. & V.H.Bui) Aver., comb. nov. ≡ Coelogyne sondangii Vuong, Aver. & V.H.Bui in, D.T. Vo et al. (2022: 201, fig. 1). Type: — VIETNAM. Lai Chau Province, Sin Ho District, Lang Mo Commune, forest around Tu Cua Phin Village, 23 March 2022, Truong Ba Vuong, Bui Van Huong, BV 1357 (holotype VNM 00069946). Notes:—Following almost all recent orchid assessments and monographs (Seidenfaden 1986, 1992, Lund 1987, Pearce & Cribb 2002, Schuiteman et al. 2008, Chen et al. 2009, Rokaya et al. 2013: 539, Zhou et al. 2016: 34, Ormerod et al. 2021: 74), we accept Panisea (Lindley 1833: 44) Steudel (1841: 265) as a genus separate from Coelogyne Lindley (1821: t. 33) due to clear morphological evidence. Hence, we proposed the new nomenclatural combination made above. Data on ecology, phenology, distribution, and conservation status were reported earlier (Vo et al. 2022).Published as part of Averyanov, Leonid V., Nguyen, Van Canh, Truong, Ba Vuong, Nguyen, Khang Sinh, Nguyen, Cuong Huu, Maisak, Tatiana V., Doan, Nga Thi, Nguyen, Tuan Hoang, Pham, Van The, Dat, Pham Thi Thanh, Thai, Tran Huy, Nguyen, Van Khuong & Trinh, Ngoc Bon, 2023, New orchids in the flora of Vietnam VI (Orchidaceae, tribes Arethuseae, Cymbidieae, Diurideae, Epidendreae, Vandeae, and Vanilleae), pp. 87-110 in Phytotaxa 597 (2) on page 93, DOI: 10.11646/phytotaxa.597.2.1, http://zenodo.org/record/792919
Enhancing prediction of ride-hailing fares using advanced deep learning techniques
No full textFare prediction is a critical component of online ride-hailing services, as it significantly influences consumer decision-making and enhances operational efficiency for service providers. Reliable fare prediction is especially important in dynamic pricing environments, where fares are affected by factors such as demand fluctuations, traffic conditions, and weather patterns. This study aims to enhance fare prediction in ride-hailing services by utilizing advanced deep learning models. Using a comprehensive dataset of Uber and Lyft fare data collected in Boston during the winter of 2018, we evaluated three deep learning architectures: Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and BiLSTM with an attention mechanism (BiLSTM + Attention). The results showed that the BiLSTM + Attention model achieved the highest prediction accuracy, making it the most effective approach for fare prediction. However, its longer training time poses limitations for time-sensitive applications. Conversely, the LSTM model provided a strong balance between predictive accuracy and computational efficiency, making it a suitable alternative for scenarios that require faster model deployment. Additionally, our analysis identified key factors influencing fare variability – such as trip distance, time of day, and weather conditions – highlighting the importance of feature selection in enhancing model performance. By improving fare prediction accuracy, this study offers valuable insights for optimizing dynamic pricing strategies, enhancing consumer satisfaction, and helping ride-hailing platforms better manage supply–demand imbalances. These findings provide a foundation for future research exploring hybrid models and real-time data integration to further improve predictive capabilities in ride-hailing services
Establishment of a Rice Tiller Number Prediction Model Using Soil Compaction and Days After Transplanting
No full textSoil compaction has a real effect on rice growth in the Mekong Delta. The correlation between soil compaction and rice growth (tiller number and plant height) in a paddy field in An Giang province was evaluated in the 2020 Winter-Spring and Summer-Autumn crops using the Pearson's correlation test. The research results show that soil compaction 0-20 cm from the soil surface has a positive correlation with rice tiller number, while the effect on plant height is non-significant. Therefore, a prediction model for rice tiller numbers is constructed using the Curve Fitting application in Matlab software. The obtained prediction models can effectively predict the number of rice tillers from the value of the 0-20 cm soil layer compaction at times under 40 DAT in the two studied crops. This study provides the optimal value of soil compaction (about 229.8 and 337.6 kPa in these crops), which can aid in the utilization of soil tillage for paddy rice cultivation by farmers
Changes in total phenol, flavonoid contents and anti-Lactobacillus activity of Callisia fragrans due to extraction solvent
No full textChemInform Abstract: Identification of Six New Lupane‐Type Triterpenoids from Acanthopanax koreanum Leaves and Their Tyrosinase Inhibitory Activities.
No full textA Computer-Vision Based Application for Student Behavior Monitoring in Classroom
No full textAutomated learning analytics is becoming an essential topic in the educational area, which needs effective systems to monitor the learning process and provides feedback to the teacher. Recent advances in visual sensors and computer vision methods enable automated monitoring of behavior and affective states of learners at different levels, from university to pre-school. The objective of this research was to build an automatic system that allowed the faculties to capture and make a summary of student behaviors in the classroom as a part of data acquisition for the decision making process. The system records the entire session and identifies when the students pay attention in the classroom, and then reports to the facilities. Our design and experiments show that our system is more flexible and more accurate than previously published work
