Q-Learning-Based Pesticide Contamination Prediction in Vegetables and Fruits

Pesticides have become more necessary in modern agricultural production.However,these pesticides have an unforeseeable long-term impact on people's wellbeing as well as the ecosystem.Due to a shortage of basic pesticide exposure awareness,farmers typically utilize pesticides extremely close to harvesting.Pesticide residues within foods,particularly fruits as well as veggies,are a significant issue among farmers,merchants,and particularly consumers.The residual concentrations were far lower than these maximal allowable limits,with only a few surpassing the restrictions for such pesticides in food.There is an obligation to provide a warning about this amount of pesticide use in farming.Previous technologies failed to forecast the large number of pesticides that were dangerous to people,necessitating the development of improved detection and early warning systems.A novel methodology for verifying the status and evaluating the level of pesticides in regularly consumed veggies as well as fruits has been identified,named as the Hybrid Chronic Multi-Residual Framework(HCMF),in which the harmful level of used pesticide residues has been predicted for contamination in agro products using Q-Learning based Recurrent Neural Network and the predicted contamination levels have been analyzed using Complex Event Processing(CEP)by processing given spatial and sequential data.The analysis results are used to minimize and effectively use pesticides in the agricultural field and also ensure the safety of farmers and consumers.Overall,the technique is carried out in a Python environment,with the results showing that the proposed model has a 98.57%accuracy and a training loss of 0.30.

Proactive Personalized Services Through Fog-Cloud Computing in Large-Scale IoT-Based Healthcare Application

With the development of medical sensors and IoT, personalized service assisted elder and patient living is a critical service in IoT-based healthcare application. However, the scale and complexity of personalized service is increasing because of ubiquitous deployment of various kinds of medical sensors, which cause response time increase and resource waste. Therefore, leveraging the advantage of complex event processing(CEP) in data stream processing, we propose a hierarchical fog-cloud computing CEP architecture for personalized service to accelerate response time and reduce resource waste. Firstly, we introduce the proposed architecture, which includes sensor layer, fog layer and cloud layer. Secondly, we propose a series of optimizations for the architecture, there are a partitioning and clustering approach and a communication and parallel processing policy to optimize the fog and cloud computing. Finally, we implement a prototype system based on the architecture named Fog Cep Care. Experimental result shows that Fog Cep Care is superior to the traditional IoT-based healthcare application.

Optimization Techniques for RFID Complex Event Processing

One research crucial to wider adoption of Radio Frequency Identification （RFID） technology is how to efficiently transform sequences of RFID readings into meaningful business events. Contrary to traditional events, RFID readings are usually of high volume and velocity, and have the attributes representing their reading objects, occurrence times and spots. Based on these characteristics and the Non-deterministic Finite Automata （NFA） implementation framework, this paper studies the performance issues of RFID complex event processing and proposes corresponding optimization techniques. Our techniques include： （1） taking advantage of negation events or exclusiveness between events to prune intermediate results, thus reduces memory consumption; （2） with different selectivities of complex events, purposefully reordering the join operations between events to improve overall efficiency, achieve higher stream throughput; （3） utilizing the slot-based or B＋-tree-based approach to optimizing the processing performance with the time window constraint. We present the analytical results of these techniques and validate their effectiveness through experiments.

An efficient complex event detection model for high proportion disordered RFID event stream

With the aim of solving the detection problems for current complex event detection models in detecting a related event for a complex event from the high proportion disordered RFID event stream due to its big uncertainty arrival,an efficient complex event detection model based on Extended Nondeterministic Finite Automaton(ENFA)is proposed in this paper.The achievement of the paper rests on the fact that an efficient complex event detection model based on ENFA is presented to successfully realize the detection of a related event for a complex event from the high proportion disordered RFID event stream.Specially,in our model,we successfully use a new ENFA-based complex event detection model instead of an NFA-based complex event detection model to realize the detection of the related events for a complex event from the high proportion disordered RFID event stream by expanding the traditional NFA-based detection model,which can effectively address the problems above.The experimental results show that the proposed model in this paper outperforms some general models in saving detection time,memory consumption,detection latency and improving detection throughput for detecting a related event of a complex event from the high proportion out-of-order RFID event stream.

Aggressive Complex Event Processing with Confidence over Out-of-Order Streams

In recent years, there has been a growing need for complex event processing （CEP）, ranging from supply chain management to security monitoring. In many scenarios events are generated in different sources but arrive at the central server out of order, due to the differences of network latencies. Most state-of-the-art techniques process out-of-order events by buffering the events until the total event order within a specified range can be guaranteed. Their main problems are leading to increasing response time and reducing system throughput. This paper aims to build a high performance out-of- order event processing mechanism, which can match events as soon as they arrive instead of buffering them till all arrive. A suffix-automaton-based event matching algorithm is proposed to speed up query processing, and a confidence-based accuracy evaluation is proposed to control the query result quality. The performance of our approach is evaluated through detailed accuracy and response time analysis. As experimental results show, our approach can obviously speed up the query matching time and produce reasonable query results.

A multiple-pattern complex event matching model based on merge sharing for massive event streams

Quickly matching the related primitive events for multiple complex events from the massive event streams usually faces with a great challenge due to the single-pattern characteristics of the existing complex event matching models. Aiming to solve the problem, amultiple-pattern complex event matching model based on merge sharing is proposed inthis paper. The achievement of the paper lies in the fact that a multiple-pattern complexevent matching model based on merge sharing is presented to successfully realize thequick matching of related primitive events for multiple complex events from the massiveevent streams. Specifically, in our scheme, we successfully use merge sharing technologyto merge all the same prefixes, suffixes or subpatterns existing in single-pattern matchingmodels into shared ones and to construct a multiple-pattern complex event matchingmodel. As a result, our proposed matching model in this paper can effectively solve theabove problem. The experimental results show that our proposed matching model in thispaper outperforms the existing single-pattern matching models in model constructionand related events matching for massive event streams.

Digital Twin Framework and Its Application to Power Grid Online Analysis

Digital twin(DT)framework is introduced in the context of application for power grid online analysis.In the development process of a new power grid real-time online analysis system,an online analysis digital twin(OADT)has been implemented to realize the new online analysis architecture.The OADT approach is presented and its prominent features are discussed.The presentation,discussion,and performance testing are based on a large-scale grid network model(40K+buses),exported directly from the EMS system of an actual power grid.A plan to apply the OADT approach to digitize power grid dispatching rules is also outlined.

A New Solution Architecture for Online Power System Analysis

The current DSA system used in the dispatching control centers in China is a near real-time analysis system with response speed in the order of minutes.Based on a review of the state-of-the-art in online analysis and discussion of distributed data processing and computation architecture patterns,a new online analysis architecture is proposed.The primary goal of the new architecture is to increase the online analysis response speed to the order of seconds.A reference implementation of the proposed online analysis architecture to validate the feasibility of implementing the architecture and some performance testing results are presented.