Search

Open-ventilated greenhouses have reasonable setup costs and low operational costs for growers, which is crucial and most appealing for this research. These attributes fit developing nations like Thailand and other tropical regions. It is challenging to control the equipment intended to obtain an ideal microclimate. This research was conducted in an actual greenhouse setting for data collection and experiments, with a proposed system for adaptive equipment control via web integration. Also, the proposed multivariate multistep LSTM was forecasted over 1 h and cooperated with sensor data. Additional sensors, like a leaf wetness sensor and a CO2 sensor, were installed for detecting plant-level precision for vaporization, rather than greenhouse-level. The proposed system can optimize the indoor temperature within 34.5 to 36 °C with a 39 to 40 °C outdoor temperature. Also, humidity was still at the ideal level of 68 to 70%; more precisely, the wetness value was below 300 throughout the experiment. The model accuracy achieved a sufficient RMSE (0.49) and R2 (0.9788). This proposed system architecture and MM-LSTM model has potential as one dimension of a fully smart greenhouse system development in open-ventilated greenhouse settings in tropical regions and Southeast Asian nations for a better yield rate and less human interaction.

Sleep apnea, characterized by breathing interruptions or slow breathing at night, can cause various health issues. Detecting respiratory rate (RR) using Wireless Fidelity (Wi-Fi) can identify sleep disorders without physical contact avoiding sleep disruption. However, traditional methods using Network Interface Cards (NICs) like the Intel Wi-Fi Link 5300 NIC are often costly and limited in channel state information (CSI) resolution. Our study introduces an effective strategy using the affordable ESP32 single-board computer for tracking RR through detailed analysis of Wi-Fi signal CSI. We developed a technique correlating Wi-Fi signal fluctuations with RR, employing signal processing methods—Hampel Filtering, Gaussian Filtering, Linear Interpolation, and Butterworth Low Pass Filtering—to accurately extract relevant signals. Additionally, noise from external movements is mitigated using a Z-Score for anomaly detection approach. We also implemented a local peak function to count peaks within an interval, scaling it to bpm for RR identification. RR measurements were conducted at different rates—Normal (12–16 bpm), Fast (>16 bpm), and Slow (

In light of pressing global health concerns, the significance of indoor air quality in densely populated structures has been emphasized. This research introduces the Mimosa kinetic façade, an innovative design inspired by the adaptive responsiveness of the Mimosa plant to environmental stimuli. Traditional static architectural façades often hinder natural ventilation, leading to diminished air quality with potential health and cognitive repercussions. The Mimosa kinetic façade addresses these challenges by enhancing effective airflow and facilitating the removal of airborne contaminants. This study evaluates the façade’s impact on quality of life and its aesthetic contribution to architectural beauty, utilizing the biomimicry design spiral for a nature-inspired approach. Computational simulations and physical tests were conducted to assess the ventilation capacities of various façade systems, with a particular focus on settings in Bangkok, Thailand. The study revealed that kinetic façades, especially certain patterns, provided superior ventilation compared to static ones. Some patterns prioritized ventilation, while others optimized human comfort during extended stays. Notably, the most effective patterns of the kinetic façade inspired by the Mimosa demonstrated a high air velocity reaching up to 12 m/s, in contrast to the peak of 2.50 m/s in single-sided façades (traditional façades). This highlights the kinetic façade’s potential to rapidly expel airborne particles from indoor spaces, outperforming traditional façades. The findings underscore the potential of specific kinetic façade patterns in enhancing indoor air quality and human comfort, indicating a promising future for kinetic façades in architectural design. This study aims to achieve an optimal balance between indoor air quality and human comfort, although challenges remain in perfecting this equilibrium.

Remote sensing image scene classification with deep learning (DL) is a rapidly growing field that has gained significant attention in the past few years. While previous review papers in this domain have been confined to 2020, an up-to-date review to show the progression of research extending into the present phase is lacking. In this review, we explore the recent articles, providing a thorough classification of approaches into three main categories: Convolutional Neural Network (CNN)-based, Vision Transformer (ViT)-based, and Generative Adversarial Network (GAN)-based architectures. Notably, within the CNN-based category, we further refine the classification based on specific methodologies and techniques employed. In addition, a novel and rigorous meta-analysis is performed to synthesize and analyze the findings from 50 peer-reviewed journal articles to provide valuable insights in this domain, surpassing the scope of existing review articles. Our meta-analysis shows that the most adopted remote sensing scene datasets are AID (41 articles) and NWPU-RESISC45 (40). A notable paradigm shift is seen towards the use of transformer-based models (6) starting from 2021. Furthermore, we critically discuss the findings from the review and meta-analysis, identifying challenges and future opportunities for improvement in this domain. Our up-to-date study serves as an invaluable resource for researchers seeking to contribute to this growing area of research.

Abstract With the trend toward the use of large-scale vehicle probe data, an urban-scale analysis can now provide useful information for taxi drivers and passengers. Unfortunately, traffic congestion has become a critical problem in urban cities. Road traffic congestion reduces productivity in transportation services, and the daily profit earned is consequently reduced. This is opposite to the cost of living, which is increasing rapidly. Therefore, these issues are causing difficulties in all occupations in terms of managing daily expenses, particularly for taxi drivers. The taxi driving is classified as low income compared to other occupations. Such facts are a symbol of economic inefficiency. To this end, this study aims to assist taxi agencies and the government in improving taxi driver profits in Bangkok using large-scale data. To deal with these large-scale data, we propose a big data-driven model. With this model, we first calculate costs using a cost–distance algorithm and trip reconstruction. The data are then modeled to understand distance-based profits with respect to the departure time and traffic conditions. Finally, several cost predictive models using machine learning are evaluated using the ground truth from 50 taxis for a 1-month period. The experiment results show that more frequent trips over a short distance yield higher profits than long-distance trips. Finally, a solution to improve taxi driver profits is determined. We also compare the advantages and disadvantages of a unified solution.

Currently, the number of deliveries handled by transportation logistics is rapidly increasing because of the significant growth of the e-commerce industry, resulting in the need for improved functional vehicle routing measures for logistic companies. The effective management of vehicle routing helps companies reduce operational costs and increases its competitiveness. The vehicle routing problem (VRP) seeks to identify optimal routes for a fleet of vehicles to deliver goods to customers while simultaneously considering changing requirements and uncertainties in the transportation environment. Due to its combinatorial nature and complexity, conventional optimization approaches may not be practical to solve VRP. In this paper, a new optimization model based on reinforcement learning (RL) and a complementary tree-based regression method is proposed. In our proposed model, when the RL agent performs vehicle routing optimization, its state and action are fed into the tree-based regression model to assess whether the current route is feasible according to the given environment, and the response received is used by the RL agent to adjust actions for optimizing the vehicle routing task. The procedure repeats iteratively until the maximum iteration is reached, then the optimal vehicle route is returned and can be utilized to assist in decision making. Multiple logistics agency case studies are conducted to demonstrate the application and practicality of the proposed model. The experimental results indicate that the proposed technique significantly improves profit gains up to 37.63% for logistics agencies compared with the conventional approaches.

Floods and droughts cause catastrophic damage in paddy fields, and farmers need to be compensated for their loss. Mobile applications have allowed farmers to claim losses by providing mobile photos and polygons of their land plots drawn on satellite base maps. This paper studies diverse methods to verify those claims at a parcel level by employing (i) Normalized Difference Vegetation Index (NDVI) and (ii) Normalized Difference Water Index (NDWI) on Sentinel-2A images, (iii) Classification and Regression Tree (CART) on Sentinel-1 SAR GRD images, and (iv) a convolutional neural network (CNN) on mobile photos. To address the disturbance from clouds, we study the combination of multi-modal methods—NDVI+CNN and NDWI+CNN—that allow 86.21% and 83.79% accuracy in flood detection and 73.40% and 81.91% in drought detection, respectively. The SAR-based method outperforms the other methods in terms of accuracy in flood (98.77%) and drought (99.44%) detection, data acquisition, parcel coverage, cloud disturbance, and observing the area proportion of disasters in the field. The experiments conclude that the method of CART on SAR images is the most reliable to verify farmers’ claims for compensation. In addition, the CNN-based method’s performance on mobile photos is adequate, providing an alternative for the CART method in the case of data unavailability while using SAR images.

At present, buildings are increasingly being designed with transparent materials, with glass paneling being especially popular as an installation material due to its architectural allure. However, its major drawback is admitting impractical amounts of sunlight into interior spaces. Office buildings with excessive sunlight in indoor areas lead to worker inefficiency. This article studied kinetic façades as means to provide suitable sunlight for interior spaces, integrated with a triple-identity DNA structure, photosynthetic behavior, and the twist, which was divided into generation and evaluation. The generating phase first used an evolutionary engine to produce potential strip patterns. The kinetic façade was subsequently evaluated using the Climate Studio software to validate daylight admission in an indoor space with Leadership in Energy and Environmental Design (LEED) version 4.1 criteria. To analyze the kinetic façade system, the building envelope was divided into four types: glass panel, static façade, rotating façade (the kinetic façade, version 1); an existing kinetic façade that is commonly seen in the market, and twisting façade (the kinetic façade, version 2); the kinetic façade that uses the process to invent the new identity of the façade. In addition, for both the rotating façade and twisting façade, the degrees of simulation were 20, 50, 80, and 100 degrees, in order to ascertain the potential for both façades to the same degree. Comparing all façades receiving the daylight factor (DF) into the space with more or less sunlight resulted in a decreasing order of potential, as follows: entirely glass façade, twisting façade (the kinetic façade, version 2), rotating façade (the kinetic façade, version 1), and static façade. By receiving the daylight factor (DF), the façade moderately and beneficially filtered appropriate amounts of daylight into the working space. The daylight simulation results indicated that the newly designed kinetic façade (version 2) had more potential than other building envelope types in terms of filtering beneficial daylight in indoor areas. This article also experimented with the kinetic façade prototype in an actual situation to test conditional environmental potential. The twisting façade (the kinetic façade, version 2) was explored in the building envelope with varied adaptability to provide sunlight and for private-to-public, public-to-private, or semi-public working areas.

Accurate vehicle classification and tracking are increasingly important subjects for intelligent transport systems (ITSs) and for planning that utilizes precise location intelligence. Deep learning (DL) and computer vision are intelligent methods; however, accurate real-time classification and tracking come with problems. We tackle three prominent problems (P1, P2, and P3): the need for a large training dataset (P1), the domain-shift problem (P2), and coupling a real-time multi-vehicle tracking algorithm with DL (P3). To address P1, we created a training dataset of nearly 30,000 samples from existing cameras with seven classes of vehicles. To tackle P2, we trained and applied transfer learning-based fine-tuning on several state-of-the-art YOLO (You Only Look Once) networks. For P3, we propose a multi-vehicle tracking algorithm that obtains the per-lane count, classification, and speed of vehicles in real time. The experiments showed that accuracy doubled after fine-tuning (71% vs. up to 30%). Based on a comparison of four YOLO networks, coupling the YOLOv5-large network to our tracking algorithm provided a trade-off between overall accuracy (95% vs. up to 90%), loss (0.033 vs. up to 0.036), and model size (91.6 MB vs. up to 120.6 MB). The implications of these results are in spatial information management and sensing for intelligent transport planning.

The production of banana-one of the highly consumed fruits-is highly affected due to loss of certain number of banana plants in an early phase of vegetation. This affects the ability of farmers to forecast and estimate the production of banana. In this paper, we propose a deep learning (DL) based method to precisely detect and count banana plants on a farm exclusive of other plants, using high resolution RGB aerial images collected from Unmanned Aerial Vehicle (UAV). An attempt to detect the plants on the normal RGB images resulted less than 78.8% recall for our sample images of a commercial banana farm in Thailand. To improve this result, we use three image processing methods-Linear Contrast Stretch, Synthetic Color Transform and Triangular Greenness Index-to enhance the vegetative properties of orthomosaic, generating multiple variants of orthomosaic. Then we separately train a parameter-optimized Convolutional Neural Network (CNN) on manually interpreted banana plant samples seen on each image variants, to produce multiple results of detection on our region of interest. 96.4%, 85.1% and 75.8% of plants were correctly detected on three of our dataset collected from multiple altitude of 40, 50 and 60 meters, of same farm. Further discussion on results obtained from combination of multiple altitude variants are also discussed later in the research, in an attempt to find better altitude combination for data collection from UAV for the detection of banana plants. The results showed that merging the detection results of 40 and 50 meter dataset could detect the plants missed by each other, increasing recall upto 99%.

Availability of very high-resolution remote sensing images and advancement of deep learning methods have shifted the paradigm of image classification from pixel-based and object-based methods to deep learning-based semantic segmentation. This shift demands a structured analysis and revision of the current status on the research domain of deep learning-based semantic segmentation. The focus of this paper is on urban remote sensing images. We review and perform a meta-analysis to juxtapose recent papers in terms of research problems, data source, data preparation methods including pre-processing and augmentation techniques, training details on architectures, backbones, frameworks, optimizers, loss functions and other hyper-parameters and performance comparison. Our detailed review and meta-analysis show that deep learning not only outperforms traditional methods in terms of accuracy, but also addresses several challenges previously faced. Further, we provide future directions of research in this domain.

As the mobile phone data (CDR data) has gained an increasing interest in research, such as social science, transportation, urban informatics, and big data, this study aims at examining the representativeness of the CDR data in terms of resemblance of the actual population density distribution from three perspectives; operator’s market share, urban-rural user population ratio, and user gender ratio. The results reveal that the representativeness of the data does not scale at the same rate with the operator’s market share, the urban-rural user population ratio of 80:20 can best represent the population density distribution, and an equal mixture of male and female user population can best resemble the population density distribution. This study is the first investigation into the representativeness of the CDR data. The findings provide useful information, which can serve an insightful guideline when dealing with the CDR data.

This study explores the effects that the weather has on people's everyday activity patterns. Temperature, rainfall, and wind speed were used as weather parameters. People's daily activity patterns were inferred, such as place visited, the time this took place, the duration of the visit, based on the GPS location traces of their mobile phones overlaid upon Yellow Pages information. Our analysis of 31,855 mobile phone users allowed us to infer that people were more likely to stay longer at eateries or food outlets, and (to a lesser degree) at retail or shopping areas when the weather is very cold or when conditions are calm (non-windy). When compared to people's regular activity patterns, certain weather conditions affected people's movements and activities noticeably at different times of the day. On cold days, people's activities were found to be more diverse especially after 10AM, showing greatest variations between 2PM and 6PM. A similar trend is observed between 10AM and midnight on rainy days, with people's activities found to be most diverse on days with heaviest rainfalls or on days when the wind speed was stronger than 4 km/h, especially between 10AM-1AM. Finally, we observed that different geographical areas of a large metropolis were impacted differently by the weather. Using data of urban infrastructure to characterize areas, we found strong correlations between weather conditions upon people's accessibility to trains. This study sheds new light on the influence of weather conditions on human behavior, in particular the choice of daily activities and how mobile phone data can be used to investigate the influence of environmental factors on urban dynamics.