Search

Tobacco is a valuable crop, but its disease identification is rarely involved in existing works. In this work, we use few-shot learning (FSL) to identify abnormalities in tobacco. FSL is a solution for the data deficiency that has been an obstacle to using deep learning. However, weak feature representation caused by limited data is still a challenging issue in FSL. The weak feature representation leads to weak generalization and troubles in cross-domain. In this work, we propose a feature representation enhancement network (FREN) that enhances the feature representation through instance embedding and task adaptation. For instance embedding, global max pooling, and global average pooling are used together for adding more features, and Gaussian-like calibration is used for normalizing the feature distribution. For task adaptation, self-attention is adopted for task contextualization. Given the absence of publicly available data on tobacco, we created a tobacco leaf abnormality dataset (TLA), which includes 16 categories, two settings, and 1,430 images in total. In experiments, we use PlantVillage, which is the benchmark dataset for plant disease identification, to validate the superiority of FREN first. Subsequently, we use the proposed method and TLA to analyze and discuss the abnormality identification of tobacco. For the multi-symptom diseases that always have low accuracy, we propose a solution by dividing the samples into subcategories created by symptom. For the 10 categories of tomato in PlantVillage, the accuracy achieves 66.04% in 5-way, 1-shot tasks. For the two settings of the tobacco leaf abnormality dataset, the accuracies were achieved at 45.5% and 56.5%. By using the multisymptom solution, the best accuracy can be lifted to 60.7% in 16-way, 1-shot tasks and achieved at 81.8% in 16-way, 10-shot tasks. The results show that our method improves the performance greatly by enhancing feature representation, especially for tasks that contain categories with high similarity. The desensitization of data when crossing domains also validates that the FREN has a strong generalization ability.

Few-shot learning (FSL) is suitable for plant-disease recognition due to the shortage of data. However, the limitations of feature representation and the demanding generalization requirements are still pressing issues that need to be addressed. The recent studies reveal that the frequency representation contains rich patterns for image understanding. Given that most existing studies based on image classification have been conducted in the spatial domain, we introduce frequency representation into the FSL paradigm for plant-disease recognition. A discrete cosine transform module is designed for converting RGB color images to the frequency domain, and a learning-based frequency selection method is proposed to select informative frequencies. As a post-processing of feature vectors, a Gaussian-like calibration module is proposed to improve the generalization by aligning a skewed distribution with a Gaussian-like distribution. The two modules can be independent components ported to other networks. Extensive experiments are carried out to explore the configurations of the two modules. Our results show that the performance is much better in the frequency domain than in the spatial domain, and the Gaussian-like calibrator further improves the performance. The disease identification of the same plant and the cross-domain problem, which are critical to bring FSL to agricultural industry, are the research directions in the future.

Image-based deep learning method for plant disease diagnosing is promising but relies on large-scale dataset. Currently, the shortage of data has become an obstacle to leverage deep learning methods. Few-shot learning can generalize to new categories with the supports of few samples, which is very helpful for those plant disease categories where only few samples are available. However, two challenging problems are existing in few-shot learning: (1) the feature extracted from few shots is very limited; (2) generalizing to new categories, especially to another domain is very tough. In response to the two issues, we propose a network based on the Meta-Baseline few-shot learning method, and combine cascaded multi-scale features and channel attention. The network takes advantage of multi-scale features to rich the feature representation, uses channel attention as a compensation module efficiently to learn more from the significant channels of the fused features. Meanwhile, we propose a group of training strategies from data configuration perspective to match various generalization requirements. Through extensive experiments, it is verified that the combination of multi-scale feature fusion and channel attention can alleviate the problem of limited features caused by few shots. To imitate different generalization scenarios, we set different data settings and suggest the optimal training strategies for intra-domain case and cross-domain case, respectively. The effects of important factors in few-shot learning paradigm are analyzed. With the optimal configuration, the accuracy of 1-shot task and 5-shot task achieve at 61.24% and 77.43% respectively in the task targeting to single-plant, and achieve at 82.52% and 92.83% in the task targeting to multi-plants. Our results outperform the existing related works. It demonstrates that the few-shot learning is a feasible potential solution for plant disease recognition in the future application.

It is crucial to speed up the training process of multivariate deep learning models for forecasting time series data in a real-time adaptive computing service with automated feature engineering. Multivariate time series decomposition and recombining (MTS-DR) is proposed for this purpose with better accuracy. A proposed MTS-DR model was built to prove that not only the training time is shortened but also the error loss is slightly reduced. A case study is for demonstrating air quality forecasting in sub-tropical urban cities. Since MTS decomposition reduces complexity and makes the features to be explored easier, the speed of deep learning models as well as their accuracy are improved. The experiments show it is easier to train the trend component, and there is no need to train the seasonal component with zero MSE. All forecast results are visualized to show that the total training time has been shortened greatly and that the forecast is ideal for changing trends. The proposed method is also suitable for other time series MTS with seasonal oscillations since it was applied to the datasets of six different kinds of air pollutants individually. Thus, this proposed method has some commonality and could be applied to other datasets with obvious seasonality. [ABSTRACT FROM AUTHOR]

In the evolving landscape of the Internet of Things (IoT), Mobile Wireless Sensor Networks (MWSN) play a pivotal role, particularly in dynamic environments requiring mobile sensing capabilities. A primary challenge in MWSNs is achieving accurate node positioning with minimal energy consumption, as these networks often consist of battery-powered, mobile sensors where energy replenishment is difficult. This paper addresses the critical problem of energy-efficient node localization in MWSNs. We propose a novel positioning approach leveraging Cooperative Virtual Array (CVA) technology, which strategically utilizes the mobility of nodes to enhance positioning accuracy while conservatively using energy resources. The methodology revolves around optimizing the number of transceiver nodes, considering factors such as node moving speed, total energy consumption, and positioning errors. Central to our approach is the Signal Arrival and Interaction (SAI) algorithm, an innovative technique devised for efficient and precise mobile node localization, replacing traditional Time of Arrival (ToA) methods. Our simulations, conducted under various scenarios, demonstrate the significant advantages of the CVA-based positioning algorithm. Results show a marked reduction in energy consumption and robust performance in mobile node scenarios. Key findings include substantial improvements in localization accuracy and energy efficiency, highlighting the potential of our approach in enhancing the operational sustainability of MWSNs. The implications of this research are far-reaching for IoT applications, particularly those involving mobile sensors, such as in smart cities, industrial monitoring, and disaster management. By introducing a novel, energy-efficient positioning method, our work contributes to the advancement of MWSN technology, offering a sustainable solution to the challenge of mobile node localization. [ABSTRACT FROM AUTHOR]

This research addresses the challenges of visually impaired individuals' independent travel by avoiding obstacles. The study proposes a distance estimation method for uncontrolled three-dimensional environments to aid navigation towards labeled target objects. Utilizing a monocular camera, the method captures cuboid objects (e.g., fences, pillars) for near-front distance estimation. A Field of View (FOV) model calculates the camera's angle and arbitrary pitch relative to the target Point of Interest (POI) within the image. Experimental results demonstrate the method's proficiency in detecting distances between objects and the source camera, employing the FOV and Point of View (POV) principles. The approach achieves a mean absolute percentage error (MAPE) of 6.18% and 6.24% on YOLOv4-tiny and YOLOv4, respectively, within 10 m. The distance model only contributes a maximum error of 4% due to POV simplification, affected by target object characteristics, height, and selected POV. The proposed distance estimation method shows promise in drone racing navigation, EV autopilot, and aiding visually impaired individuals. It offers valuable insights into dynamic 3D environment distance estimation, advancing computer vision and autonomous systems. [ABSTRACT FROM AUTHOR]

Accurate storm surge forecasting is vital for saving lives and avoiding economic and infrastructural damage. Failure to accurately predict storm surge can have catastrophic repercussions. Advances in machine learning models show the ability to improve accuracy of storm surge prediction by leveraging vast amounts of historical and realtime data such as weather and tide patterns. This paper proposes a bidirectional attention-based LSTM storm surge architecture (BALSSA) to improve prediction accuracy. Training and evaluation utilized extensive meteorological and tide level data from 77 typhoon incidents in Hong Kong and Macao between 2017 and 2022. The proposed methodology is able to model complex non-linearities between large amounts of data from different sources and identify complex relationships between variables that are typically not captured by traditional physical methods. BALSSA effectively resolves the problem of long-term dependencies in storm surge prediction by the incorporation of an attention mechanism. It enables selective emphasis on significant features and boosts the prediction accuracy. Evaluation has been conducted using real-world datasets from Macao to validate our storm surge prediction model. Results show that accuracy and robustness of predictions were significantly improved by the incorporation of attention mechanisms in our models. BALSSA captures temporal dynamics effectively, providing highly accurate storm surge forecasts (MAE: 0.0126, RMSE: 0.0003) up to 72 h in advance. These findings have practical significance for disaster risk reduction strategies, saving lives through timely evacuation and early warnings. Experiments comparing BALSSA variations with other machine learning algorithms consistently validate BALSSA's superior predictive performance. It offers an additional risk management tool for civil-protection agencies and governments, as well as an ideal solution for enhancing storm surge prediction accuracy, benefiting coastal communities. [ABSTRACT FROM AUTHOR]