arXiv subjects

Feng Gu

Publications and source records attributed to Feng Gu.

At least 37 records · Page 2Linked to original sources

arXiv2024

Robust Control of An Aerial Manipulator Based on A Variable Inertia Parameters Model

Aerial manipulator, which is composed of an UAV (Unmanned Aerial Vehicle) and a multi-link manipulator and can perform aerial manipulation, has shown great potential of applications. However, dynamic coupling between the UAV and the manipulator makes it difficult to control the aerial manipulator with high performance. In this paper, system modeling and control problem of the aerial manipulator are studied. Firstly, an UAV dynamic model is proposed with consideration of the dynamic coupling from an attached manipulator, which is treated as disturbance for the UAV. In the dynamic model, the disturbance is affected by the variable inertia parameters of the aerial manipulator system. Then, based on the proposed dynamic model, a disturbance compensation robust $H_{\infty}$ controller is designed to stabilize flight of the UAV while the manipulator is in operation. Finally, experiments are conducted and the experimental results demonstrate the feasibility and validity of the proposed control scheme.

cs.RO↗

arXiv2023

CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding

Self-supervised learning (SSL) has gained widespread attention in the remote sensing (RS) and earth observation (EO) communities owing to its ability to learn task-agnostic representations without human-annotated labels. Nevertheless, most existing RS SSL methods are limited to learning either global semantic separable or local spatial perceptible representations. We argue that this learning strategy is suboptimal in the realm of RS, since the required representations for different RS downstream tasks are often varied and complex. In this study, we proposed a unified SSL framework that is better suited for RS images representation learning. The proposed SSL framework, Contrastive Mask Image Distillation (CMID), is capable of learning representations with both global semantic separability and local spatial perceptibility by combining contrastive learning (CL) with masked image modeling (MIM) in a self-distillation way. Furthermore, our CMID learning framework is architecture-agnostic, which is compatible with both convolutional neural networks (CNN) and vision transformers (ViT), allowing CMID to be easily adapted to a variety of deep learning (DL) applications for RS understanding. Comprehensive experiments have been carried out on four downstream tasks (i.e. scene classification, semantic segmentation, object-detection, and change detection) and the results show that models pre-trained using CMID achieve better performance than other state-of-the-art SSL methods on multiple downstream tasks. The code and pre-trained models will be made available at https://github.com/NJU-LHRS/official-CMID to facilitate SSL research and speed up the development of RS images DL applications.

cs.CV↗

arXiv2022

Observation of Structure Evolution and Reaction Intermediates at the Gate-tunable Suspended Graphene/Electrolyte Interface

Graphene serves as an ideal platform to investigate the microscopic structure and reaction kinetics at the graphitic electrode interfaces. However, graphene is susceptible to various extrinsic factors, e.g. substrate, causing much confusion and controversy. Hereby we have obtained cm-sized substrate-free monolayer graphene suspended on electrolyte surface with gate tunability. Using sum-frequency spectroscopy, we have observed the structural evolution versus the gate voltage at the graphene/water interface. The Stern layer structure is invariant within the water electrolysis window, but undergoes drastic change when switching on the electrochemical reactions. The electrode is turned from hydrophobic to hydrophilic near the onset of hydrogen evolution reaction due to hydrogen adsorption. The large-size suspended pristine graphene offers a new platform to unravel the microscopic processes at the graphitic electrode interfaces.

physics.chem-ph↗

arXiv2022

Measurement of DC Magneto-Optical Kerr Effect with Sensitivity of $10^{-7} \text{Rad}/\sqrt{\text{Hz}}$

A high-sensitive DC Magneto-Optical Kerr Effect (MOKE) apparatus is described in this letter. Via detailed analysis on several dominating noise sources, we have proposed solutions that significantly lower the MOKE noise, and a sensitivity of $1.5\times10^{-7} \text{rad}/\sqrt{\text{Hz}}$ is achieved with long-term stability. The sensitivity of the apparatus is tested by measuring a wedge-shaped Ni thin film on $\text{SiO}_2$ with Ni thickness varying from 0 to 3 nm. A noise floor of $1.5\times10^{-8}$ rad is demonstrated. The possibility of further improving sensitivity to $10^{-9}$ rad via applying ac modulation is also discussed.

physics.ins-det↗

arXiv2021

Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models

Purpose: Pelvic bone segmentation in CT has always been an essential step in clinical diagnosis and surgery planning of pelvic bone diseases. Existing methods for pelvic bone segmentation are either hand-crafted or semi-automatic and achieve limited accuracy when dealing with image appearance variations due to the multi-site domain shift, the presence of contrasted vessels, coprolith and chyme, bone fractures, low dose, metal artifacts, etc. Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored. Methods: In this paper, we aim to bridge the data gap by curating a large pelvic CT dataset pooled from multiple sources and different manufacturers, including 1, 184 CT volumes and over 320, 000 slices with different resolutions and a variety of the above-mentioned appearance variations. Then we propose for the first time, to the best of our knowledge, to learn a deep multi-class network for segmenting lumbar spine, sacrum, left hip, and right hip, from multiple-domain images simultaneously to obtain more effective and robust feature representations. Finally, we introduce a post-processing tool based on the signed distance function (SDF) to eliminate false predictions while retaining correctly predicted bone fragments. Results: Extensive experiments on our dataset demonstrate the effectiveness of our automatic method, achieving an average Dice of 0.987 for a metal-free volume. SDF post-processor yields a decrease of 10.5% in hausdorff distance by maintaining important bone fragments in post-processing phase. Conclusion: We believe this large-scale dataset will promote the development of the whole community and plan to open source the images, annotations, codes, and trained baseline models at https://github.com/ICT-MIRACLE-lab/CTPelvic1K.

cs.CV↗

arXiv2020

Learning under Concept Drift: A Review

Concept drift describes unforeseeable changes in the underlying distribution of streaming data over time. Concept drift research involves the development of methodologies and techniques for drift detection, understanding and adaptation. Data analysis has revealed that machine learning in a concept drift environment will result in poor learning results if the drift is not addressed. To help researchers identify which research topics are significant and how to apply related techniques in data analysis tasks, it is necessary that a high quality, instructive review of current research developments and trends in the concept drift field is conducted. In addition, due to the rapid development of concept drift in recent years, the methodologies of learning under concept drift have become noticeably systematic, unveiling a framework which has not been mentioned in literature. This paper reviews over 130 high quality publications in concept drift related research areas, analyzes up-to-date developments in methodologies and techniques, and establishes a framework of learning under concept drift including three main components: concept drift detection, concept drift understanding, and concept drift adaptation. This paper lists and discusses 10 popular synthetic datasets and 14 publicly available benchmark datasets used for evaluating the performance of learning algorithms aiming at handling concept drift. Also, concept drift related research directions are covered and discussed. By providing state-of-the-art knowledge, this survey will directly support researchers in their understanding of research developments in the field of learning under concept drift.

cs.LG↗

arXiv2019

Segmenting Potentially Cancerous Areas in Prostate Biopsies using Semi-Automatically Annotated Data

Gleason grading specified in ISUP 2014 is the clinical standard in staging prostate cancer and the most important part of the treatment decision. However, the grading is subjective and suffers from high intra and inter-user variability. To improve the consistency and objectivity in the grading, we introduced glandular tissue WithOut Basal cells (WOB) as the ground truth. The presence of basal cells is the most accepted biomarker for benign glandular tissue and the absence of basal cells is a strong indicator of acinar prostatic adenocarcinoma, the most common form of prostate cancer. Glandular tissue can objectively be assessed as WOB or not WOB by using specific immunostaining for glandular tissue (Cytokeratin 8/18) and for basal cells (Cytokeratin 5/6 + p63). Even more, WOB allowed us to develop a semi-automated data generation pipeline to speed up the tremendously time consuming and expensive process of annotating whole slide images by pathologists. We generated 295 prostatectomy images exhaustively annotated with WOB. Then we used our Deep Learning Framework, which achieved the $2^{nd}$ best reported score in Camelyon17 Challenge, to train networks for segmenting WOB in needle biopsies. Evaluation of the model on 63 needle biopsies showed promising results which were improved further by finetuning the model on 118 biopsies annotated with WOB, achieving F1-score of 0.80 and Precision-Recall AUC of 0.89 at the pixel-level. Then we compared the performance of the model against 17 biopsies annotated independently by 3 pathologists using only H\&E staining. The comparison demonstrated that the model performed on a par with the pathologists. Finally, the model detected and accurately outlined existing WOB areas in two biopsies incorrectly annotated as totally WOB-free biopsies by three pathologists and in one biopsy by two pathologists.

cs.CV↗

arXiv2018

A Deep Learning Framework for Automatic Diagnosis in Lung Cancer

We developed a deep learning framework that helps to automatically identify and segment lung cancer areas in patients' tissue specimens. The study was based on a cohort of lung cancer patients operated at the Uppsala University Hospital. The tissues were reviewed by lung pathologists and then the cores were compiled to tissue micro-arrays (TMAs). For experiments, hematoxylin-eosin stained slides from 712 patients were scanned and then manually annotated. Then these scans and annotations were used to train segmentation models of the developed framework. The performance of the developed deep learning framework was evaluated on fully annotated TMA cores from 178 patients reaching pixel-wise precision of 0.80 and recall of 0.86. Finally, publicly available Stanford TMA cores were used to demonstrate high performance of the framework qualitatively.

cs.CV↗

arXiv2018

Multi-Resolution Networks for Semantic Segmentation in Whole Slide Images

Digital pathology provides an excellent opportunity for applying fully convolutional networks (FCNs) to tasks, such as semantic segmentation of whole slide images (WSIs). However, standard FCNs face challenges with respect to multi-resolution, inherited from the pyramid arrangement of WSIs. As a result, networks specifically designed to learn and aggregate information at different levels are desired. In this paper, we propose two novel multi-resolution networks based on the popular `U-Net' architecture, which are evaluated on a benchmark dataset for binary semantic segmentation in WSIs. The proposed methods outperform the U-Net, demonstrating superior learning and generalization capabilities.

cs.CV↗

arXiv2016

Improving the Quality of Random Number Generators by Applying a Simple Ratio Transformation

It is well-known that the quality of random number generators can often be improved by combining several generators, e.g. by summing or subtracting their results. In this paper we investigate the ratio of two random number generators as an alternative approach: the smaller of two input random numbers is divided by the larger, resulting in a rational number from $[0,1]$. We investigate theoretical properties of this approach and show that it yields a good approximation to the ideal uniform distribution. To evaluate the empirical properties we use the well-known test suite \textsc{TestU01}. We apply the ratio transformation to moderately bad generators, i.e. those that failed up to 40\% of the tests from the test battery \textsc{Crush} of \textsc{TestU01}. We show that more than half of them turn into very good generators that pass all tests of \textsc{Crush} and \textsc{BigCrush} from \textsc{TestU01} when the ratio transformation is applied. In particular, generators based on linear operations seem to benefit from the ratio, as this breaks up some of the unwanted regularities in the input sequences. Thus the additional effort to produce a second random number and to calculate the ratio allows to increase the quality of available random number generators.

cs.OH↗

arXiv2013

Artificial Immune Systems (INTROS 2)

The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens. It is able to categorize all cells (or molecules) within the body as self or non-self substances. It does this with the help of a distributed task force that has the intelligence to take action from a local and also a global perspective using its network of chemical messengers for communication. There are two major branches of the immune system. The innate immune system is an unchanging mechanism that detects and destroys certain invading organisms, whilst the adaptive immune system responds to previously unknown foreign cells and builds a response to them that can remain in the body over a long period of time. This remarkable information processing biological system has caught the attention of computer science in recent years. A novel computational intelligence technique, inspired by immunology, has emerged, called Artificial Immune Systems. Several concepts from the immune system have been extracted and applied for solution to real world science and engineering problems. In this tutorial, we briefly describe the immune system metaphors that are relevant to existing Artificial Immune Systems methods. We will then show illustrative real-world problems suitable for Artificial Immune Systems and give a step-by-step algorithm walkthrough for one such problem. A comparison of the Artificial Immune Systems to other well-known algorithms, areas for future work, tips & tricks and a list of resources will round this tutorial off. It should be noted that as Artificial Immune Systems is still a young and evolving field, there is not yet a fixed algorithm template and hence actual implementations might differ somewhat from time to time and from those examples given here.

cs.NE↗

arXiv2013

Quiet in Class: Classification, Noise and the Dendritic Cell Algorithm

Theoretical analyses of the Dendritic Cell Algorithm (DCA) have yielded several criticisms about its underlying structure and operation. As a result, several alterations and fixes have been suggested in the literature to correct for these findings. A contribution of this work is to investigate the effects of replacing the classification stage of the DCA (which is known to be flawed) with a traditional machine learning technique. This work goes on to question the merits of those unique properties of the DCA that are yet to be thoroughly analysed. If none of these properties can be found to have a benefit over traditional approaches, then "fixing" the DCA is arguably less efficient than simply creating a new algorithm. This work examines the dynamic filtering property of the DCA and questions the utility of this unique feature for the anomaly detection problem. It is found that this feature, while advantageous for noisy, time-ordered classification, is not as useful as a traditional static filter for processing a synthetic dataset. It is concluded that there are still unique features of the DCA left to investigate. Areas that may be of benefit to the Artificial Immune Systems community are suggested.

cs.LG↗

arXiv2013

The Dendritic Cell Algorithm for Intrusion Detection

As one of the solutions to intrusion detection problems, Artificial Immune Systems (AIS) have shown their advantages. Unlike genetic algorithms, there is no one archetypal AIS, instead there are four major paradigms. Among them, the Dendritic Cell Algorithm (DCA) has produced promising results in various applications. The aim of this chapter is to demonstrate the potential for the DCA as a suitable candidate for intrusion detection problems. We review some of the commonly used AIS paradigms for intrusion detection problems and demonstrate the advantages of one particular algorithm, the DCA. In order to clearly describe the algorithm, the background to its development and a formal definition are given. In addition, improvements to the original DCA are presented and their implications are discussed, including previous work done on an online analysis component with segmentation and ongoing work on automated data preprocessing. Based on preliminary results, both improvements appear to be promising for online anomaly-based intrusion detection.

cs.CR↗

arXiv2013

Theoretical formulation and analysis of the deterministic dendritic cell algorithm

As one of the emerging algorithms in the field of Artificial Immune Systems (AIS), the Dendritic Cell Algorithm (DCA) has been successfully applied to a number of challenging real-world problems. However, one criticism is the lack of a formal definition, which could result in ambiguity for understanding the algorithm. Moreover, previous investigations have mainly focused on its empirical aspects. Therefore, it is necessary to provide a formal definition of the algorithm, as well as to perform runtime analyses to revealits theoretical aspects. In this paper, we define the deterministic version of the DCA, named the dDCA, using set theory and mathematical functions. Runtime analyses of the standard algorithm and the one with additional segmentation are performed. Our analysis suggests that the standard dDCA has a runtime complexity of O(n2) for the worst-case scenario, where n is the number of input data instances. The introduction of segmentation changes the algorithm's worst case runtime complexity to O(max(nN; nz)), for DC population size N with size of each segment z. Finally, two runtime variables of the algorithm are formulated based on the input data, to understand its runtime behaviour as guidelines for further development.

cs.NE↗

arXiv2010

PCA 4 DCA: The Application Of Principal Component Analysis To The Dendritic Cell Algorithm

As one of the newest members in the field of artificial immune systems (AIS), the Dendritic Cell Algorithm (DCA) is based on behavioural models of natural dendritic cells (DCs). Unlike other AIS, the DCA does not rely on training data, instead domain or expert knowledge is required to predetermine the mapping between input signals from a particular instance to the three categories used by the DCA. This data preprocessing phase has received the criticism of having manually over-?tted the data to the algorithm, which is undesirable. Therefore, in this paper we have attempted to ascertain if it is possible to use principal component analysis (PCA) techniques to automatically categorise input data while still generating useful and accurate classication results. The integrated system is tested with a biometrics dataset for the stress recognition of automobile drivers. The experimental results have shown the application of PCA to the DCA for the purpose of automated data preprocessing is successful.

cs.AI↗

arXiv2010

Integrating Real-Time Analysis With The Dendritic Cell Algorithm Through Segmentation

As an immune inspired algorithm, the Dendritic Cell Algorithm (DCA) has been applied to a range of problems, particularly in the area of intrusion detection. Ideally, the intrusion detection should be performed in real-time, to continuously detect misuses as soon as they occur. Consequently, the analysis process performed by an intrusion detection system must operate in real-time or near-to real-time. The analysis process of the DCA is currently performed offline, therefore to improve the algorithm's performance we suggest the development of a real-time analysis component. The initial step of the development is to apply segmentation to the DCA. This involves segmenting the current output of the DCA into slices and performing the analysis in various ways. Two segmentation approaches are introduced and tested in this paper, namely antigen based segmentation (ABS) and time based segmentation (TBS). The results of the corresponding experiments suggest that applying segmentation produces different and significantly better results in some cases, when compared to the standard DCA without segmentation. Therefore, we conclude that the segmentation is applicable to the DCA for the purpose of real-time analysis.

cs.NE↗

arXiv2010

Further Exploration of the Dendritic Cell Algorithm: Antigen Multiplier and Time Windows

As an immune-inspired algorithm, the Dendritic Cell Algorithm (DCA), produces promising performances in the field of anomaly detection. This paper presents the application of the DCA to a standard data set, the KDD 99 data set. The results of different implementation versions of the DXA, including the antigen multiplier and moving time windows are reported. The real-valued Negative Selection Algorithm (NSA) using constant-sized detectors and the C4.5 decision tree algorithm are used, to conduct a baseline comparison. The results suggest that the DCA is applicable to KDD 99 data set, and the antigen multiplier and moving time windows have the same effect on the DCA for this particular data set. The real-valued NSA with constant-sized detectors is not applicable to the data set, and the C4.5 decision tree algorithm provides a benchmark of the classification performance for this data set.

cs.AI↗

arXiv2010

Exploration Of The Dendritic Cell Algorithm Using The Duration Calculus

As one of the newest members in Artificial Immune Systems (AIS), the Dendritic Cell Algorithm (DCA) has been applied to a range of problems. These applications mainly belong to the field of anomaly detection. However, real-time detection, a new challenge to anomaly detection, requires improvement on the real-time capability of the DCA. To assess such capability, formal methods in the research of rea-time systems can be employed. The findings of the assessment can provide guideline for the future development of the algorithm. Therefore, in this paper we use an interval logic based method, named the Duration Calculus (DC), to specify a simplified single-cell model of the DCA. Based on the DC specifications with further induction, we find that each individual cell in the DCA can perform its function as a detector in real-time. Since the DCA can be seen as many such cells operating in parallel, it is potentially capable of performing real-time detection. However, the analysis process of the standard DCA constricts its real-time capability. As a result, we conclude that the analysis process of the standard DCA should be replaced by a real-time analysis component, which can perform periodic analysis for the purpose of real-time detection.

cs.AI↗