Business Process Modelling (BPM) is a set of organised, structured, and related activities that boost the development and evolution of an organisation's success by understanding, improving, and automating existing...
详细信息
As a prominent category of imitation learning methods, adversarial imitation learning (AIL) has garnered significant practical success powered by neural network approximation. However, existing theoretical studies on ...
The problem of achieving performance-guaranteed finite-time exact tracking for uncertain strict-feedback nonlinear systems with unknown control directions is addressed. A novel logic switching mechanism with monitorin...
详细信息
Density peaks clustering (DPC) algorithm reported in science is a novel and efficient clustering method which has attracted great attention for its simplicity and practicability. Although it has shown promising result...
详细信息
Density peaks clustering (DPC) algorithm reported in science is a novel and efficient clustering method which has attracted great attention for its simplicity and practicability. Although it has shown promising results in some applications, there still exist some certain disadvantages. For example, the calculation method of local density without taking into account the impact of the surrounding areas may cause the wrong cluster centers selection results. In spite of the simple data points allocation strategy, the allocation strategy may cause the serial incorrect cluster results. Given these disadvantages of DPC algorithm, we propose a nearest neighbors similarity based clustering method which is called generalized neighbors similarity based clustering by fast search and find of density peaks (abbreviated as GNS-DPC). Considering the data points' K-nearest-neighbor information, we give a generalized neighbors similarity measurement between data points and present a new definition of local density and relative distance. In the data points allocation stage, this GNS-DPC also takes advantage of the nearest neighbors'information of a data point. The allocation process consists of several steps, which can solve the serial incorrect cluster results problem. The experimental results suggest that our method can correctly obtain the cluster centers and recognize clusters with higher accuracy.
UML artifacts constitute a key (but often neglected) asset supporting the comprehension of a system. Design documents "bind" developers in implementation phases and close the loop as documentation of the imp...
详细信息
ISBN:
(纸本)9798400705861
UML artifacts constitute a key (but often neglected) asset supporting the comprehension of a system. Design documents "bind" developers in implementation phases and close the loop as documentation of the implemented system itself. Nevertheless, the intended system (design), its current version (implementation), and its documentation, naturally tend to drift apart, negatively impacting the usefulness of UML diagrams contained in such artifacts. We present a novel approach to capture and understand the Design-Implementation-Documentation (DID) drift. We connect UML references in human-readable text-based UML formats (e.g., PlantUML) to the corresponding source code entities (e.g., Java classes), implementing novel metrics to capture the UML coverage of the system. We analyze project and file coverage evolution across releases and commits, with overall, method-level, and attribute-level detailedness, showing how they support DID drift analysis. We present interesting case studies exemplifying how through Drifter, the visual exploration tool we developed to validate our approach, we identify DID drift and ways to tackle it in the future.
Pedestrian Attribute Recognition has attracted increasing attention due to its wide range of potential applications. However, the pedestrian images are taken from a far distances significantly increase the difficulty ...
详细信息
The field of computer vision is predominantly driven by supervised models, which, despite their efficacy, are computationally expensive and often intractable for many applications. Recently, research has expedited alt...
详细信息
The cloud elasticity allows users to acquire resources and release useless resources as needed. This feature has attracted more and more web service providers to deploy their latency-crucial, user -oriented applicatio...
详细信息
The cloud elasticity allows users to acquire resources and release useless resources as needed. This feature has attracted more and more web service providers to deploy their latency-crucial, user -oriented applications on cloud platforms. For web service providers, in the case of fluctuating workloads, scaling their server clusters over time could save system expenditures without service quality violations. Therefore, a lot of cloud platforms begin to offer automatic scaling strategies based on threshold-based rules for helping web service providers to save system expenditures. However, building threshold-based rules requires expertise, and such reactive scaling strategies cannot guarantee low and consistent tail latencies. For those proactive scaling strategies depending on predictions, random user behaviors lead to declines in prediction accuracy. In this paper, we propose a reinforcement learning based proactive strategy for scaling a mixed cluster, which is composed of a variety of cloud instances. Ensuring the availability and quality of reward signals is the main problem to be solved for algorithms based on standard RL. We design a reward function which could balance service cost, service quality and other parameters which can affect decision-making. We assign different weights to parameters based on their effects on decision-making. In order to avoid the explosion of the state space caused by fluctuating workloads and various server status, we discretize the continuous state space of our model. Experimental results based on TailBench show that our Q-learning based scaling method can maintain low and consistent tail latencies while achieving fewer costs than three common baselines.
In autonomous driving, multi-object tracking (MOT) can help vehicles perceive surroundings better and perform well-informed motion-planning. Methods based on LiDAR suffer from the sparsity of LiDAR points and detect o...
详细信息
Developing policies that can adapt to non-stationary environments is essential for real-world reinforcement learning ***, learning such adaptable policies in offline settings, with only a limited set of pre-collected ...
详细信息
Developing policies that can adapt to non-stationary environments is essential for real-world reinforcement learning ***, learning such adaptable policies in offline settings, with only a limited set of pre-collected trajectories, presents significant challenges.A key difficulty arises because the limited offline data makes it hard for the context encoder to differentiate between changes in the environment dynamics and shifts in the behavior policy, often leading to context *** address this issue, we introduce a novel approach called Debiased Offline Representation learning for fast online Adaptation (DORA).DORA incorporates an information bottleneck principle that maximizes mutual information between the dynamics encoding and the environmental data, while minimizing mutual information between the dynamics encoding and the actions of the behavior *** present a practical implementation of DORA, leveraging tractable bounds of the information bottleneck *** experimental evaluation across six benchmark MuJoCo tasks with variable parameters demonstrates that DORA not only achieves a more precise dynamics encoding but also significantly outperforms existing baselines in terms of performance. Copyright 2024 by the author(s)
暂无评论