Much of today's software executes inside of Runtimes, which are software platforms that manage and run code submitted by other developers. Isolation, high performance and resource efficiency are three important go...
详细信息
ISBN:
(数字)9781665451420
ISBN:
(纸本)9781665451420
Much of today's software executes inside of Runtimes, which are software platforms that manage and run code submitted by other developers. Isolation, high performance and resource efficiency are three important goals for a Runtime. However, existing Runtimes cannot meet all of these goals simultaneously. In my thesis, I will explore the trade-offs between these goals and how to provide autonomous system support to maximize them in three important environments.
The connection between distributed Integrated Energy systems (DIES) and Distribution Network (DN) have a profound impact on their reliability of energy supply. To accurately calculate the reliability of DN while consi...
详细信息
The Byzantine fault-tolerant (BFT) consensus algorithm is widely used in blockchain systems due to its ability to tolerate malicious nodes and ensure system consistency. However, existing consensus protocols still fac...
详细信息
In order to improve the photovoltaic (PV) consumption rate and economy, a PV-accessible capacity assessment model for agricultural systems is established. Taking a village in north China as the research object, the mo...
详细信息
The proceedings contain 12 papers. The topics discussed include: auction mechanism based multi-agent DRL for multi-service placement in mobile edge computing;optimized embedded model for time sequence alignment within...
ISBN:
(纸本)9798350313048
The proceedings contain 12 papers. The topics discussed include: auction mechanism based multi-agent DRL for multi-service placement in mobile edge computing;optimized embedded model for time sequence alignment within distributed video streams environment;BSA tool: an experience report of software automation to perform sanity tests in a global software development environment;application and research of OFD-based e-procurement document management system;a fast decentralized scheduling method of cooperative localization based on actor-critic deep reinforcement learning;mobile based navigation system for visually impaired person using image detection with voice translation;efficient structure search for person re-identification;face detection using the Siamese network with reconstruction supervision;a rate compatible LDPC scheme in the quantum key distribution system;and a method of multiple targets DOA tracking with vector hydrophone based on unite processing in time and frequency domain.
作者：
Padmakala, S.Gopukumar, S.T.
Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai602 105 India
Saveetha Medical College and Hospital Tamil Nadu Chennai602 105 India
The recent integration of Machine Learning (ML) and sensor technologies in healthcare, particularly for diagnosing Major Depressive Disorder (MDD), has paved the way for advanced predictive analytics in mental health....
详细信息
The proceedings contain 207 papers. The topics discussed include: operation and configuration analysis of a power storage system with a high proportion of wind power;economic optimal operation of integrated rural sing...
ISBN:
(纸本)9798350313857
The proceedings contain 207 papers. The topics discussed include: operation and configuration analysis of a power storage system with a high proportion of wind power;economic optimal operation of integrated rural single household energy systems;an adaptability hybrid-frequency interleaved control strategy for double-frequency converters with parameter uncertainties;simulation analysis of conductive carbon black and hydrogen prepared by partial oxidation of benzene-doped acetylene;reliability evaluation of power generation system considering planned maintenance and energy storage;new technology and integrated optimization of distributed energy storage power generation;regional short-term power load forecasting considering user electricity consumption and seasonal characteristics;disturbance identification of power quality based on Markov transition field and deep residual network;and effect of discharge amplitude on electrical trees based on three-capacitance model.
Virtual sensors model the sensing operation of physical sensors deployed in an area of interest by generating sensory data with accuracy and precision close to those collected by physical sensors. Their use in applica...
详细信息
ISBN:
(纸本)9781665495127
Virtual sensors model the sensing operation of physical sensors deployed in an area of interest by generating sensory data with accuracy and precision close to those collected by physical sensors. Their use in applications such as augmenting the infrastructure of IoT facilities and test beds, monitoring and calibrating the operation of physical sensors, and developing Digital Twins of physical systems have led virtual sensors to attract research attention. Machine learning provides methods for modelling patterns in complex and big data generated by IoT sensing devices, allowing to model the behaviour of these devices. In this work, we investigate ML methods as means of implementation for virtual sensors. In particular, we evaluate the performance of six ML methods in terms of their effectiveness, accuracy and precision in generating sensory data based on data from physical sensors. In our study, we use a multi-modal dataset comprising IoT sensory data for temperature, humidity and illumination collected over a period of two years in an office space at University of Geneva. Our results show that the best performing model at predicting an output of a missing sensor is the Random Forest method, achieving MAPE error below 3%, 5% and 18% respectively for temperature, humidity and illuminance. The worst performing models were the linear radial basis function neural network and linear regression. In future research, we plan to deploy the best performing models natively on IoT devices, making use of tinyML and extreme edge computing methods.
Wireless sensor Networks (WSNs) have become a cornerstone technology in various fields, including environmental monitoring, industrial automation, and healthcare. This paper presents a novel hybrid resource allocation...
详细信息
Optimally siting distributed generations (DGs) is regarded as one of the most effective mechanisms for loss mitigation on a distribution network. Power loss curtailment on distribution networks is a very essential in ...
详细信息
暂无评论