Longzhi Yang
YOU?
Author Swipe
View article: Optimisation of multiple clustering based undersampling using artificial bee colony: Application to improved detection of obfuscated patterns without adversarial training
Optimisation of multiple clustering based undersampling using artificial bee colony: Application to improved detection of obfuscated patterns without adversarial training Open
View article: 3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification
3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification Open
Unsupervised person re-identification (Re-ID) aims to learn a feature network with cross-camera retrieval capability in unlabelled datasets. Although the pseudo-label based methods have achieved great progress in Re-ID, their performance i…
View article: Leveraging ensemble clustering for privacy-preserving data fusion: Analysis of big social-media data in tourism
Leveraging ensemble clustering for privacy-preserving data fusion: Analysis of big social-media data in tourism Open
View article: Geometric Features Enhanced Human-Object Interaction Detection
Geometric Features Enhanced Human-Object Interaction Detection Open
Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes. Re…
View article: Comprehensive Botnet Detection by Mitigating Adversarial Attacks, Navigating the Subtleties of Perturbation Distances and Fortifying Predictions with Conformal Layers
Comprehensive Botnet Detection by Mitigating Adversarial Attacks, Navigating the Subtleties of Perturbation Distances and Fortifying Predictions with Conformal Layers Open
Botnets are computer networks controlled by malicious actors that present\nsignificant cybersecurity challenges. They autonomously infect, propagate, and\ncoordinate to conduct cybercrimes, necessitating robust detection methods. This\nres…
View article: Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs
Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs Open
Localization plays a crucial role in enhancing the practicality and precision of VQA systems. By enabling fine-grained identification and interaction with specific parts of an object, it significantly improves the system's ability to provi…
View article: A Query-Specific Representation-Based Sampling Strategy for Imbalanced Classification
A Query-Specific Representation-Based Sampling Strategy for Imbalanced Classification Open
Data imbalance is a common challenge for many classification tasks where the dataset suffers from disproportionate partitions of samples between classes. Typical techniques for handling class imbalance are either based on algorithmic or da…
View article: Framework development and flag-based quality control for a national scale dataset using UK's Historical 15-Minute Flow Data
Framework development and flag-based quality control for a national scale dataset using UK's Historical 15-Minute Flow Data Open
The United Kingdom has an extensive repository of 15-minute flow data dating back to the 1930s, yet this wealth of information has remained decentralized within respective measuring authorities responsible for localized quality control. Co…
View article: Geometric Features Enhanced Human–Object Interaction Detection
Geometric Features Enhanced Human–Object Interaction Detection Open
Cameras are essential vision instruments to capture images for pattern detection and measurement. Human–object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes. Re…
View article: A quality-control framework for sub-daily flow and level data for hydrological modelling in Great Britain
A quality-control framework for sub-daily flow and level data for hydrological modelling in Great Britain Open
The absence of an accessible and quality-assured national flow dataset is a limiting factor in sub-daily hydrological modelling in Great Britain. The recent development of measuring authority APIs and projects such as the Floods and Drough…
View article: Overview of Human Activity Recognition Using Sensor Data
Overview of Human Activity Recognition Using Sensor Data Open
Human activity recognition (HAR) is an essential research field that has been used in different applications including home and workplace automation, security and surveillance as well as healthcare. Starting from conventional machine learn…
View article: Android Malware Classification and Optimisation Based on BM25 Score of Android API
Android Malware Classification and Optimisation Based on BM25 Score of Android API Open
With the growth of Android devices, there is a rise in malware applications affecting these networked devices. Android malware classification is an important task in ensuring the security and privacy of Android devices. One promising appro…
View article: Use of high temporal resolution data to identify the key drivers and locations where walls of water occur in the UK
Use of high temporal resolution data to identify the key drivers and locations where walls of water occur in the UK Open
Walls of water (WoW) are a subset of flash floods characterised by an extremely fast increase in the discharge rate of rivers. In the UK, WoWs, events where an almost instantaneous increase in river flow happens, are responsible for severa…
View article: Fuzzy-Rough Intrigued Harmonic Discrepancy Clustering
Fuzzy-Rough Intrigued Harmonic Discrepancy Clustering Open
Fuzzy clustering decomposes data into clusters using partial memberships by exploring the cluster structure information, which demonstrates comparable performance for knowledge exploitation under the circumstance of information incompleten…
View article: Special issue on neuro, fuzzy and their hybridization
Special issue on neuro, fuzzy and their hybridization Open
View article: A Secure and Privacy-Preserving E-Government Framework Using Blockchain and Artificial Immunity
A Secure and Privacy-Preserving E-Government Framework Using Blockchain and Artificial Immunity Open
Electronic Government (e-Government) systems constantly provide greater services to people, businesses, organisations, and societies by offering more information, opportunities, and platforms with the support of advances in information and…
View article: Classification of Adversarial Attacks Using Ensemble Clustering Approach
Classification of Adversarial Attacks Using Ensemble Clustering Approach Open
As more business transactions and information services have been implemented via communication networks, both personal and organization assets encounter a higher risk of attacks. To safeguard these, a perimeter defence like NIDS (network-b…
View article: Adaptive ankle impedance control for bipedal robotic upright balance
Adaptive ankle impedance control for bipedal robotic upright balance Open
Upright balance control is a fundamental skill of bipedal robots for various tasks that are usually performed by human beings. Conventional robotic control is often realized by developing accurate dynamic models using a series of fixed tor…
View article: Solving Robotic Trajectory Sequential Writing Problem via Learning Character’s Structural and Sequential Information
Solving Robotic Trajectory Sequential Writing Problem via Learning Character’s Structural and Sequential Information Open
The writing sequence of numerals or letters often affects aesthetic aspects of the writing outcomes. As such, it remains a challenge for robotic calligraphy systems to perform, mimicking human writers' implicit intention. This article pres…
View article: ConvNet-based performers attention and supervised contrastive learning for activity recognition
ConvNet-based performers attention and supervised contrastive learning for activity recognition Open
Human activity recognition based on generated sensor data plays a major role in a large number of applications such as healthcare monitoring and surveillance system. Yet, accurately recognizing human activities is still challenging and act…
View article: A Self-Adaptive Discriminative Autoencoder for Medical Applications
A Self-Adaptive Discriminative Autoencoder for Medical Applications Open
Computer aided diagnosis (CAD) systems play an essential role in the early detection and diagnosis of developing disease for medical applications. In order to obtain the highly recognizable representation for the medical images, a self-ada…
View article: A Type 2 wavelet brain emotional learning network with double recurrent loops based controller for nonlinear systems
A Type 2 wavelet brain emotional learning network with double recurrent loops based controller for nonlinear systems Open
View article: Strengthening intrusion detection system for adversarial attacks: improved handling of imbalance classification problem
Strengthening intrusion detection system for adversarial attacks: improved handling of imbalance classification problem Open
View article: Special issue on emerging trends, challenges and applications in cloud computing
Special issue on emerging trends, challenges and applications in cloud computing Open
View article: Error Controlled Actor-Critic
Error Controlled Actor-Critic Open
On error of value function inevitably causes an overestimation phenomenon and has a negative impact on the convergence of the algorithms. To mitigate the negative effects of the approximation error, we propose Error Controlled Actor-critic…
View article: Special issue on recent advances in data science and systems
Special issue on recent advances in data science and systems Open
As an interdisciplinary area, Data Science draws scientific inquiry from a broad range of subject areas such as statistics, mathematics, computer science, machine learning, optimisation, signal processing, information retrieval, databases,…
View article: Exclusive lasso-based k-nearest-neighbor classification
Exclusive lasso-based k-nearest-neighbor classification Open
View article: Low-Cost Inertial Measurement Unit Calibration With Nonlinear Scale Factors
Low-Cost Inertial Measurement Unit Calibration With Nonlinear Scale Factors Open
Inertial measurement units (IMUs) have been widely used to provide accurate location and movement measurement solutions, along with the advances of modern manufacturing technologies. The scale factors of accelerometers and gyroscopes are l…
View article: Dilated causal convolution with multi-head self attention for sensor human activity recognition
Dilated causal convolution with multi-head self attention for sensor human activity recognition Open
Systems of sensor human activity recognition are becoming increasingly popular in diverse fields such as healthcare and security. Yet, developing such systems poses inherent challenges due to the variations and complexity of human behavior…
View article: A Recurrent Wavelet based Brain Emotional Learning Network Controller for Nonlinear Systems
A Recurrent Wavelet based Brain Emotional Learning Network Controller for Nonlinear Systems Open
Conventional control systems often suffer from the co-existence of non-linearity and uncertainty. This paper proposes a novel brain emotional neural network to support addressing such challenges. The proposed network integrates a wavelet n…