Vegetables constitute a major food source with huge nutritional values as well as major source of income. The cultivation of vegetables is dictated by climate and seasonal changes across Nigeria. Edo State lies within...
Vegetables constitute a major food source with huge nutritional values as well as major source of income. The cultivation of vegetables is dictated by climate and seasonal changes across Nigeria. Edo State lies within the South of Nigeria and enjoys the two popular seasons (rainy and dry) like many other parts of the country. However, the variability in soil distribution and weather conditions across different locations is a determining factor as to the category of not just vegetables to grow but other crops. In this paper, Edo state is used as a flagship project for its diverse potentials and uniqueness in respect of known variability in soil and weather conditions. The State is divided into three geo-referenced agricultural districts. A prototype system is proposed to provide vegetable farmers with real-time information on vegetablefarming requirements. The proposed system is an Internet of things (IoT)-enabled climate variability system with interfaces to popular mobile networks, existing Geographical Information System (GIS) in the State, and remote sensing stations respectively. Each geo-referenced point is a nexus to areas with similar weather variability and soil distribution. Historical data is collected from the existing GIS and a provision is made to constantly enrich the historical data with new information from the geo-referenced points including crops grown, trends in cultivation, queries from farmers, etc. The information generated from the geo-referenced locations are routed via GPS to the central analytics server in the cloud and appropriate algorithms are used to carry out data analysis for real-time prediction and messages to farmers through the Internet and Short Message Services (SMS). With this system, it is submitted that subsistent and mechanized farmers would benefit through the guidance of an analytics system thereby boosting vegetablefarming regardless of the season of the year.
With the increasing complexity of Cyber-Physical systems, their behavior and decisions become increasingly difficult to understand and comprehend for users and other stakeholders. Our vision is to build self-explainab...
详细信息
ISBN:
(纸本)9781728151267
With the increasing complexity of Cyber-Physical systems, their behavior and decisions become increasingly difficult to understand and comprehend for users and other stakeholders. Our vision is to build self-explainable systems that can, at run-time, answer questions about the system's past, current, and future behavior. As hitherto no design methodology or reference framework exists for building such systems, we propose the Monitor, Analyze, Build, Explain (MAB-EX) framework for building self-explainable systems that leverage requirements- and explainability models at run-time. The basic idea of MAB-EX is to first Monitor and Analyze a certain behavior of a system, then Build an explanation from explanation models and convey this EXplanation in a suitable way to a stakeholder. We also take into account that new explanations can be learned, by updating the explanation models, should new and yet un-explainable behavior be detected by the system.
DRAM is a significant source of server power consumption especially when the server runs memory intensive applications. Current power aware scheduling assumes that DRAM is as energy proportional as other components. H...
详细信息
Flower Pollination Algorithm (FPA) is the new breed of metaheuristic for general optimization problem. In this paper, an improved algorithm based on Flower Pollination Algorithm (FPA), called imFPA, has been proposed....
详细信息
Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offer a solution. LLMs trained on the vas...
详细信息
Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. ...
详细信息
Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. To address this issue, this paper proposes a novel approach to extracting vehicle velocity and acceleration, enabling the learning of vehicle dynamics and encoding them as auxiliary information. The VDI-LSTM model is designed, incorporating graph convolution and attention mechanisms to capture vehicle interactions using trajectory data and dynamic information. Specifically, a dynamics encoder is designed to capture the dynamic information, a dynamic graph is employed to represent vehicle interactions, and an attention mechanism is introduced to enhance the performance of LSTM and graph convolution. To demonstrate the effectiveness of our model, extensive experiments are conducted, including comparisons with several baselines and ablation studies on real-world highway datasets. Experimental results show that VDI-LSTM outperforms other baselines compared, which obtains a 3% improvement on the average RMSE indicator over the five prediction steps.
Secure communication is a necessity. However, encryption is commonly only applied to the upper layers of the protocol stack. This exposes network information to eavesdroppers, including the channel's type, data ra...
详细信息
Due to the advancements in autonomous units, more small unmanned aerial vehicles (sUAV's) are being utilized to accomplish commercial missions. Fixed wing, vertical takeoff-landing (FW-VTOL) sUAV's have been d...
详细信息
Metal rolling is a widespread and well-studied process, and many finite-element (FE) rolling simulations can be found in the scientific literature. However, these FE simulations are typically limited in their resoluti...
详细信息
Metal rolling is a widespread and well-studied process, and many finite-element (FE) rolling simulations can be found in the scientific literature. However, these FE simulations are typically limited in their resolution of through-thickness variations. In this paper, we carefully assess the accuracy of a number of FE approaches, and find that at least 60 elements through-thickness are needed to properly resolve through-thickness variation; this is significantly more than is used elsewhere in the metal rolling literature. In doing so, we reveal an oscillatory stress pattern, which is not usually observed in simulations but which we can validate by comparison with recent analytical work, and which is completely deterministic, not arising from numerical noise or error. We discuss the physical basis of these oscillations and their implications for outcomes such as curvature in asymmetric rolled sheets. Accurate through-thickness variation of stress and strain will also have implications for modelling of microstructure evolution and damage.
Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA d...
详细信息
Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly annotated in a crowdsource way, e.g., collecting questions and external reasons from different users via the internet. In addition to the challenge of knowledge reasoning, how to deal with the annotator bias also remains unsolved, which often leads to superficial over-fitted correlations between questions and answers. To address this issue, we propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning. Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases. The programs can select one or two triplets from the scene graph or knowledge base to push multi-step reasoning, avoid answer ambiguity, and balanced the answer distribution. In contrast to the existing VQA datasets, we further imply the following two major constraints on the programs to incorporate knowledge reasoning: i) multiple knowledge triplets can be related to the question, but only one knowledge relates to the image object. This can enforce the VQA model to correctly perceive the image instead of guessing the knowledge based on the given question solely;ii) all questions are based on different knowledge, but the candidate answers are the same for both the training and test sets. We make the testing knowledge unused during training to evaluate whether a model can unde
暂无评论