Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). However, existing solutions often rely on human intervention or underutilize the agent's ability to autonomously mitigate hallucination. To address these limitations, we draw inspiration from the way humans make reliable decisions in the real world. In particular, they begin with introspective reasoning to reduce uncertainty and form an initial judgment, then rely on external verification from diverse perspectives to reach a final decision. Motivated by this cognitive paradigm, we propose InEx, a training-free, multi-agent framework designed to autonomously mitigate hallucination. InEx introduces internal introspective reasoning, guided by entropy-based uncertainty estimation, to improve the reliability of the decision agent's reasoning process. The agent first generates a response, which is then iteratively verified and refined through external cross-modal multi-agent collaboration with the editing agent and self-reflection agents, further enhancing reliability and mitigating hallucination. Extensive experiments show that InEx consistently outperforms existing methods, achieving 4%-27% gains on general and hallucination benchmarks, and demonstrating strong robustness.

The task of stochastic human motion prediction has attracted significant attention in recent years due to its wide-ranging applications in robotics, animation, and human-computer interaction. While diffusion models have demonstrated promising progress in this domain, they remain hindered by two critical limitations: (1) slow inference speeds due to their reliance on iterative sampling, and (2) performance degradation resulting from suboptimal sample allocation during generation. To overcome these challenges, we propose SPARD (Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion Prediction), a novel framework that achieves efficient single-step inference while maintaining high predictive accuracy. Furthermore, we introduce a novel adaptive noise predictor module that dynamically samples latent representations based on observed motion sequences, ensuring both accuracy and plausibility in generated motions. Extensive experiments on benchmark datasets demonstrate that SPARD significantly outperforms state-of-the-art methods in both inference efficiency and motion quality, achieving a 15× to 18× speedup in sampling time compared to conventional diffusion-based baselines while preserving generation quality.

Many Particle Swarm Optimization (PSO) variants often fail to approach the global optimum due to complex fitness landscapes and/or the structural rigidity of these variants. We developed a novel framework named PSO-SEM, centered on macro-evolutionary population management. PSO-SEM introduces three landscape-driven operators: Split (Topological Fission), Extinction (Density-driven Recycling), and Migration (Knowledge Transfer). These operators autonomously regulate the lifecycle of sub-swarms to intensify search in high-potential areas by identifying promising basins and recycling computational resources from stagnant regions. Experimental results show that PSO-SEM achieves a top-tier ranking and demonstrates significant competitiveness against 14 state-of-the-art algorithms. Behavioral monitoring and ablation studies confirm PSO-SEM's ability to maintain autonomous exploration/exploitation balance through landscape-based computational resource re-allocation. Our findings verify that PSO-SEM is an interpretable architecture that meets the diverse requirements of black-box optimization.

Retrieval is being redefined by agentic AI, demanding multimodal reasoning beyond conventional similarity-based paradigms. Composed Image Retrieval (CIR) exemplifies this shift as each query combines a reference image with textual modifications, requiring compositional understanding across modalities. While embedding-based CIR methods have achieved progress, they remain narrow in perspective, capturing limited cross-modal cues and lacking semantic reasoning. To address these limitations, we introduce XR, a training-free multi-agent framework that reframes retrieval as a progressively coordinated reasoning process. It orchestrates three specialized types of agents: imagination agents synthesize target representations through cross-modal generation, similarity agents perform coarse filtering via hybrid matching, and question agents verify factual consistency through targeted reasoning for fine filtering. Through progressive multi-agent coordination, XR iteratively refines retrieval to meet both semantic and visual query constraints, achieving up to a 38% gain over strong training-free and training-based baselines on FashionIQ, CIRR, and CIRCO, while ablations show each agent is essential. Code is available: https://01yzzyu.github.io/xr.github.io/.

Short text classification, as a research subtopic in natural language processing, is more challenging due to its semantic sparsity and insufficient labeled samples in practical scenarios. We propose a novel model named MI-DELIGHT for short text classification in this work. Specifically, it first performs multi-source information (i.e., statistical information, linguistic information, and factual information) exploration to alleviate the sparsity issues. Then, the graph learning approach is adopted to learn the representation of short texts, which are presented in graph forms. Moreover, we introduce a dual-level (i.e., instance-level and cluster-level) contrastive learning auxiliary task to effectively capture different-grained contrastive information within massive unlabeled data. Meanwhile, previous models merely perform the main task and auxiliary tasks in parallel, without considering the relationship among tasks. Therefore, we introduce a hierarchical architecture to explicitly model the correlations between tasks. We conduct extensive experiments across various benchmark datasets, demonstrating that MI-DELIGHT significantly surpasses previous competitive models. It even outperforms popular large language models on several datasets.

… "Amusement" "Contentment" "Anger" "Excitement" "Fear" "Amusement" "Sadness" " F e a r " " S a d n e s s " MERMAID Figure 1: Demonstration of MERMAID.Given natural or facial images depicting various emotions, MERMAID produces precise emotion classifications by integrating multimodal self-reflection, generative augmentation to amplify and enrich subtle emotional cues, and cross-modal verification.

The growing interest in fair AI development is evident. The "Leave No One Behind" initiative urges us to address multiple and intersecting forms of inequality in accessing services, resources, and opportunities, emphasising the significance of fairness in AI. This is particularly relevant as an increasing number of AI tools are applied to decision-making processes, such as resource allocation and service scheme development, across various sectors such as health, energy, and housing. Therefore, exploring joint inequalities in these sectors is significant and valuable for thoroughly understanding overall inequality and unfairness. This research introduces an innovative approach to quantify cross-sectoral intersecting discrepancies among user-defined groups using latent class analysis. These discrepancies can be used to approximate inequality and provide valuable insights to fairness issues. We validate our approach using both proprietary and public datasets, including both EVENS and Census 2021 (England & Wales) datasets, to examine cross-sectoral intersecting discrepancies among different ethnic groups. We also verify the reliability of the quantified discrepancy by conducting a correlation analysis with a government public metric. Our findings reveal significant discrepancies both among minority ethnic groups and between minority ethnic groups and non-minority ethnic groups, emphasising the need for targeted interventions in policy-making processes. Furthermore, we demonstrate how the proposed approach can provide valuable insights into ensuring fairness in machine learning systems.

Recent advances in neural models have shown considerable promise in solving Traveling Salesman Problems (TSPs) without relying on much hand-crafted engineering. However, while non-autoregressive (NAR) approaches benefit from faster inference through parallelism, they typically deliver solutions of inferior quality compared to autoregressive ones. To enhance the solution quality while maintaining fast inference, we propose DEITSP, a diffusion model with efficient iterations tailored for TSP that operates in a NAR manner. Firstly, we introduce a one-step diffusion model that integrates the controlled discrete noise addition process with self-consistency enhancement, enabling optimal solution prediction through simultaneous denoising of multiple solutions. Secondly, we design a dual-modality graph transformer to bolster the extraction and fusion of features from node and edge modalities, while further accelerating the inference with fewer layers. Thirdly, we develop an efficient iterative strategy that alternates between adding and removing noise to improve exploration compared to previous diffusion methods. Additionally, we devise a scheduling framework to progressively refine the solution space by adjusting noise levels, facilitating a smooth search for optimal solutions. Extensive experiments on real-world and large-scale TSP instances demonstrate that DEITSP performs favorably against existing neural approaches in terms of solution quality, inference latency, and generalization ability.

Multimodal models leverage complementary information across modalities to enrich feature representations. While visual information shows potential in representing structure for some combinatorial optimization problems (COPs), its application to complex scheduling like the Flexible Job Shop Scheduling Problem (FJSP) remains underexplored. Current learning-based FJSP solvers predominantly rely on handcrafted state features. This dependence can lead to inconsistencies and may not fully capture the problem's intricate dynamics. Crucially, these methods overlook visual modalities. Visual representations offer a distinct advantage by inherently capturing the global topological structure and complex resource interactions within the FJSP state. Unlike localized handcrafted features, this holistic, structural view provides a richer foundation for understanding scheduling complexity and making informed decisions. To overcome these limitations by leveraging visual information-known for representing topological structures and providing richer state representations-we introduce the AO-framework. This multimodal feature fusion approach enhances handcrafted state features by integrating insights from visual data. Our core contribution is a novel fusion mechanism utilizing orthogonal projection and local attention. Unlike traditional methods that often rely on simple concatenation of visual data, our method uniquely reduces redundancy by projecting global image-derived features onto local handcrafted features. This process extracts distinct information inherent to the visual modality, significantly improving the quality and complementarity of the resulting state features and enabling more informed scheduling decisions. To our knowledge, the AO-framework represents the first multimodal framework applied to scheduling problems, demonstrating the significant potential of visual information in this domain. Extensive experiments across various FJSP solvers and datasets confirm that our framework yields substantial enhancements in solution quality, decision-making capabilities, and generalization.

Graph few-shot learning has attracted increasing attention due to its ability to rapidly adapt models to new tasks with only limited labeled nodes. Despite the remarkable progress made by existing graph few-shot learning methods, several key limitations remain. First, most current approaches rely on predefined and unified graph filters (e.g., low-pass or high-pass filters) to globally enhance or suppress node frequency signals. Such fixed spectral operations fail to account for the heterogeneity of local topological structures inherent in real-world graphs. Moreover, these methods often assume that the support and query sets are drawn from the same distribution. However, under few-shot conditions, the limited labeled data in the support set may not sufficiently capture the complex distribution of the query set, leading to suboptimal generalization. To address these challenges, we propose GRACE, a novel Graph few-shot leaRning framework that integrates Adaptive spectrum experts with Cross-sEt distribution calibration techniques. Theoretically, the proposed approach enhances model generalization by adapting to both local structural variations and cross-set distribution calibration. Empirically, GRACE consistently outperforms state-of-the-art baselines across a wide range of experimental settings. Our code can be found here.

Motivated by the geometric advantages of quaternions in representing rotations and postures, we propose a quaternion-valued supervised learning Hopfield-structured neural network (QSHNN) with a fully connected structure inspired by the classic Hopfield neural network (HNN). Starting from a continuous-time dynamical model of HNNs, we extend the formulation to the quaternionic domain and establish the existence and uniqueness of fixed points with asymptotic stability. For the learning rules, we introduce a periodic projection strategy that modifies standard gradient descent by periodically projecting each $4\times 4$ block of the weight matrix onto the closest quaternionic structure in the least-squares sense. This approach preserves both convergence and quaternionic consistency throughout training. Benefiting from this rigorous mathematical foundation, the experimental model implementation achieves high accuracy, fast convergence, and strong reliability across randomly generated target sets. Moreover, the evolution trajectories of the QSHNN exhibit well-bounded curvature, i.e., sufficient smoothness, which is crucial for applications such as control systems or path planning modules in robotic arms, where joint postures are parameterized by quaternion neurons. Beyond these application scenarios, the proposed model offers a practical implementation framework and a general mathematical methodology for designing neural networks under hypercomplex or non-commutative algebraic structures.

Knowledge distillation essentially maximizes the mutual information between teacher and student networks. Typically, a variational distribution is introduced to maximize the variational lower bound. However, the heteroscedastic noises derived from this distribution are often unstable, leading to unreliable data-uncertainty modeling. Our research identifies that bias-variance coupling in knowledge distillation causes this instability. We thus propose Bias-variance dEcomposition kNowledge dIstillatioN (BENIN) approach. Initially, we use bias-variance decomposition to decouple these components. Subsequently, we design a lightweight Feature Frequency Expectation Estimation Module (FF-EEM) to estimate the student's prediction expectation, which helps compute bias and variance. Variance learning measures data uncertainty in the teacher's prediction. A balance factor addresses the bias-variance dilemma. Lastly, the bias-variance decomposition distillation loss enables the student to learn valuable knowledge while reducing noise. Experiments on Synapse and Lits17 medical-image-segmentation datasets validate BENIN's effectiveness. FF-EEM also mitigates high-frequency noise from high mask rates, enhancing data-uncertainty estimation and visualization. Our code is available at https://github.com/duanzhongjian/BENIN .

OBJECTIVE: Considering the radiation hazard of X-ray, safer, more convenient and cost-effective ultrasound methods are gradually becoming new diagnostic approaches for scoliosis. For ultrasound images of spine regions, it is challenging to accurately identify spine regions in images due to relatively small target areas and the presence of a lot of interfering information. Therefore, we developed a novel neural network that incorporates prior knowledge to precisely segment spine regions in ultrasound images. MATERIALS AND METHODS: We constructed a dataset of ultrasound images of spine regions for semantic segmentation. The dataset contains 3136 images of 30 patients with scoliosis. And we propose a network model (ICPPNet), which fully utilizes inter-class positional prior knowledge by combining an inter-class positional probability heatmap, to achieve accurate segmentation of target areas. RESULTS: ICPPNet achieved an average Dice similarity coefficient of 70.83% and an average 95% Hausdorff distance of 11.28 mm on the dataset, demonstrating its excellent performance. The average error between the Cobb angle measured by our method and the Cobb angle measured by X-ray images is 1.41 degrees, and the coefficient of determination is 0.9879 with a strong correlation. DISCUSSION AND CONCLUSION: ICPPNet provides a new solution for the medical image segmentation task with positional prior knowledge between target classes. And ICPPNet strongly supports the subsequent reconstruction of spine models using ultrasound images.

Federated clustering (FC) performs well in independent and identically distributed (IID) scenarios, but it does not perform well in non-IID scenarios. In addition, existing methods lack proof of strict privacy protection. To address the above issues, we propose a new secure federated k-means clustering framework to achieve better clustering results under privacy requirements. Specifically, for the clients, we use cluster centers (representative points) generated by k-means to represent the corresponding clusters. These representative points can effectively preserve the structure of the local data and they are encrypted by differential privacy. For the server, we propose two methods to reprocess the uploaded encrypted representative points to obtain better final cluster centers, one uses k-means, and the other considers the improved density peaks (density cores) as final centers and then sends them back to the clients. Finally, each client assigns local data to their nearest centers. Experimental results show that the proposed methods perform better than several centralized (nonfederated) classical clustering algorithms [k-means, density-based spatial clustering of applications with noise (DBSCAN), and density peak clustering (DPC)] and state-of-the-art (SOTA) centralized clustering algorithms in most cases. In particular, the proposed algorithms perform better than the SOTA FC framework k-FED (ICML2021) and MUFC (ICLR2023).

The traveling salesman problem (TSP) is a well-known combinatorial optimization problem (COP) with broad real-world applications. Recently, neural networks (NNs) have gained popularity in this research area because as shown in the literature, they provide strong heuristic solutions to TSPs. Compared to autoregressive neural approaches, nonautoregressive (NAR) networks exploit the inference parallelism to elevate inference speed but suffer from comparatively low solution quality. In this article, we propose a novel NAR model named NAR4TSP, which incorporates a specially designed architecture and an enhanced reinforcement learning (RL) strategy. To the best of our knowledge, NAR4TSP is the first TSP solver that successfully combines RL and NAR networks. The key lies in the incorporation of NAR network output decoding into the training process. NAR4TSP efficiently represents TSP-encoded information as rewards and seamlessly integrates it into RL strategies, while maintaining consistent TSP sequence constraints during both training and testing phases. Experimental results on both synthetic and real-world TSPs demonstrate that NAR4TSP outperforms five state-of-the-art (SOTA) models in terms of solution quality, inference speed, and generalization to unseen scenarios.

Graph representation of molecular data enables extracting stereoscopic features, with graph neural networks (GNNs) excelling in molecular property prediction. However, selecting optimal hyper-parameters for GNN construction is challenging due to the vast search space and high computational costs. To tackle this, we introduce a hierarchical evaluation strategy integrated with a genetic algorithm (HESGA). HESGA combines full and fast evaluations of GNNs. Full evaluation involves training a GNN with preset epochs, using root mean square error (RMSE) to measure hyperparameter quality. Fast evaluation interrupts training early, using the difference in RMSE values as a score for GNN potential. HESGA integrates these evaluations, with fast evaluation guiding candidate selection for full evaluation, maintaining elite individuals. Applying HESGA to optimise deep GNNs for molecular property prediction, experimental results on three datasets demonstrate its superiority over traditional Bayesian optimisation, Tree-structured Parzen Estimator, and CMA-ES. HESGA efficiently navigates the complex GNN hyperparameter space, offering a promising approach for molecular property prediction.

Unsupervised domain adaptation (UDA) methods have recently been explored for their use in skeleton recognition tasks. Much work along this line has been focusing on the “close-set” problems, which often deviate from reality as human actions vary in application scenarios. Thus, there remains a need to thoroughly study the “open-set” problems with UDA methods for skeleton recognition, aiming to support those models capable of self-adapting to action changes in different scenarios. To this end, we delve into the “open-set” problems from a feature alignment perspective under UDA settings in reaching domain and class alignment. Specifically, the domain-wise alignment was achieved by the maximum mean discrepancy (MMD) combined with supervision signals from the source domain, which form clear feature boundaries between the “known” and “unknown” classes. Then, the class-wise alignment was achieved by contrastive learning methods, which are distinguished from previous binary classification methods, in reaching compactness inside of “unknown” or “known” classes. Moreover, we conducted the Fourier analysis during the evaluation phases to verify the model’s robustness. To our knowledge, we are the first to apply the Fourier Heatmap in UDA methods for skeleton recognition. The heatmap visualizes the model’s sensitivity steered for interpretability. Significant performance improvements are observed on the NTU and PKU data sets when adding the domain-wise alignment module to other contrastive learning methods. Furthermore, experimental results demonstrate that our approach, termed CStrCRL-UDA, is consistent with robustness and efficiency on these two benchmark data sets.

Federated clustering (FC) is an emerging and important topic in data clustering research. However, for existing works, there are two challenging issues as follows. 1) FC does not perform well on non-IID data. 2) Differential privacy is a common-used way to protect raw data in FC, but there is no solid theoretical basis for selecting privacy budget$\epsilon$in Laplacian noise, and$\epsilon$is randomly set in most algorithms. In this article, we propose a new framework called NN-FC for addressing the above-mentioned issues. Specifically, 1) we provide a rigorous mathematical proof when selecting$\epsilon$, we have shown that when the value of$\epsilon$satisfies certain conditions, the neighbor relationship of data points before and after adding Laplacian noises remains unchanged. 2) According to 1), we propose a new method of obtaining global cluster centers based on distance relationships at the server, and the results of clustering the original data and clustering the privacy data become close. The experimental results show that NN-FC performs better than eight traditional and state-of-the-art (SOTA) centralized (nonfederated) clustering algorithms. In particular, NN-FC performs better than two SOTA FC frameworks k-FED (ICML2021) and MUFC (ICLR2023).

Multivariate time series (MTS) analysis and forecasting are crucial in many real-world applications, such as smart traffic management and weather forecasting. However, most existing work either focuses on short sequence forecasting or makes predictions predominantly with time domain features, which is not effective at removing noises with irregular frequencies in MTS. Therefore, we propose WaveForM, an end-to-end graph enhanced Wavelet learning framework for long sequence FORecasting of MTS. WaveForM first utilizes Discrete Wavelet Transform (DWT) to represent MTS in the wavelet domain, which captures both frequency and time domain features with a sound theoretical basis. To enable the effective learning in the wavelet domain, we further propose a graph constructor, which learns a global graph to represent the relationships between MTS variables, and graph-enhanced prediction modules, which utilize dilated convolution and graph convolution to capture the correlations between time series and predict the wavelet coefficients at different levels. Extensive experiments on five real-world forecasting datasets show that our model can achieve considerable performance improvement over different prediction lengths against the most competitive baseline of each dataset.

Mechanistic models have been used for centuries to describe complex interconnected processes, including biological ones. As the scope of these models has widened, so have their computational demands. This complexity can limit their suitability when running many simulations or when real-time results are required. Surrogate machine learning (ML) models can be used to approximate the behaviour of complex mechanistic models, and once built, their computational demands are several orders of magnitude lower. This paper provides an overview of the relevant literature, both from an applicability and a theoretical perspective. For the latter, the paper focuses on the design and training of the underlying ML models. Application-wise, we show how ML surrogates have been used to approximate different mechanistic models. We present a perspective on how these approaches can be applied to models representing biological processes with potential industrial applications (e.g., metabolism and whole-cell modelling) and show why surrogate ML models may hold the key to making the simulation of complex biological systems possible using a typical desktop computer.

Abstract Many real-world problems can be naturally formulated as discrete multi-objective optimisation (DMOO) problems. We have proposed a novel Physarum-inspired competition algorithm (PCA) to tackle these DMOO problems. Our algorithm is based on hexagonal cellular automata (CA) as a representation of problem search space and reaction–diffusion systems that control the Physarum motility. Physarum’s decision-making power and the discrete properties of CA have made our algorithm a perfectly suitable approach to solve DMOO problems. Each cell in the CA grid will be decoded as a solution (objective function) and will be regarded as a food resource to attract Physarum. The n-dimensional generalisation of the hexagonal CA grid has allowed us to extend the solving capabilities of our PCA from only 2-D to n-D optimisation problems. We have implemented a novel restart procedure to select the global Pareto frontier based on both personal experience and shared information. Extensive experimental and statistical analyses were conducted on several benchmark functions to assess the performance of our PCA against other evolutionary algorithms. As far as we know, this study is the first attempt to assess algorithms that solve DMOO problems, with a large number of benchmark functions and performance indicators. Our PCA has confirmed our assumption that individual skills of competing Physarum are more efficient in exploration and increase the diversity of the solutions. It has achieved the best performance for the Spread indicator (diversity), similar performance results compared to the strength Pareto evolutionary algorithm (SPEA2) and even outperformed other well-established genetic algorithms.

Recent years have seen a renewed interest in evolutionary computation applied to the automatic design of deep neural network architectures, i.e. Neural Architecture Search (NAS). The advantages of evolutionary approaches in NAS include their conceptual simplicity and their flexibility with regards to search space definition and/or optimization objective.However, Artificial Immune Systems (AIS) that follow the evolutionary computation paradigm are less explored in NAS. In this research, we aim to leverage their intrinsic and excellent ability to balance performance and population diversity to develop a novel Neural Ensemble Search method, based on the Clonal Selection Algorithm [1]. For more generality, we focus on designing macro-architectures rather than architectural components.Experiments on popular computer vision benchmarks demonstrate that our method reaches competitive accuracy and efficiency despite minimal augmentation and post-processing. We show that the AIS brings tangible benefits, including maintaining the diversity of solutions, a semantically straightforward implementation, and high efficiency. Moreover, this AIS can exhibit a "secondary response": when presented with a related but more difficult task, the ensemble will perform competently with zero modification to the architectures or the training protocol.

In recent years, graph neural networks (GNNs) have gained increasing attention, as they possess the excellent capability of processing graph-related problems. In practice, hyperparameter optimisation (HPO) is critical for GNNs to achieve satisfactory results, but this process is costly because the evaluations of different hyperparameter settings require excessively training many GNNs. Many approaches have been proposed for HPO, which aims to identify promising hyperparameters efficiently. In particular, the genetic algorithm (GA) for HPO has been explored, which treats GNNs as a black-box model, of which only the outputs can be observed given a set of hyperparameters. However, because GNN models are sophisticated and the evaluations of hyperparameters on GNNs are expensive, GA requires advanced techniques to balance the exploration and exploitation of the search and make the optimisation more effective given limited computational resources. Therefore, we proposed a tree-structured mutation strategy for GA to alleviate this issue. Meanwhile, we reviewed the recent HPO works, which gives room for the idea of tree-structure to develop, and we hope our approach can further improve these HPO methods in the future.

Graph neural networks (GNNs) have been proposed for a wide range of graph-related learning tasks. In particular, in recent years, an increasing number of GNN systems were applied to predict molecular properties. However, a direct impediment is to select appropriate hyperparameters to achieve satisfactory performance with lower computational cost. Meanwhile, many molecular datasets are far smaller than many other datasets in typical deep learning applications. Most hyperparameter optimization (HPO) methods have not been explored in terms of their efficiencies on such small datasets in the molecular domain. In this paper, we conducted a theoretical analysis of common and specific features for two state-of-the-art and popular algorithms for HPO: TPE and CMA-ES, and we compared them with random search (RS), which is used as a baseline. Experimental studies are carried out on several benchmarks in MoleculeNet, from different perspectives to investigate the impact of RS, TPE, and CMA-ES on HPO of GNNs for molecular property prediction. In our experiments, we concluded that RS, TPE, and CMA-ES have their individual advantages in tackling different specific molecular problems. Finally, we believe our work will motivate further research on GNN as applied to molecular machine learning problems in chemistry and materials sciences.

Mild cognitive impairment (MCI) has been described as the intermediary stage before Alzheimer's Disease - many people however remain stable or even demonstrate improvement in cognition. Early detection of progressive MCI (pMCI) therefore can be utilised in identifying at-risk individuals and directing additional medical treatment in order to revert conversion to AD as well as provide psychosocial support for the person and their family. This paper presents a novel solution in the early detection of pMCI people and classification of AD risk within MCI people. We proposed a model, MudNet, to utilise deep learning in the simultaneous prediction of progressive/stable MCI classes and time-to-AD conversion where high-risk pMCI people see conversion to AD within 24 months and low-risk people greater than 24 months. MudNet is trained and validated using baseline clinical and volumetric MRI data (n = 559 scans) from participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI). The model utilises T1-weighted structural MRIs alongside clinical data which also contains neuropsychological (RAVLT, ADAS-11, ADAS-13, ADASQ4, MMSE) tests as inputs. The averaged results of our model indicate a binary accuracy of 69.8% for conversion predictions and a categorical accuracy of 66.9% for risk classifications.

This paper addresses two practical problems: the classification and prediction of properties for polymer and glass materials, as a case study of evolutionary learning for tackling soft margin problems. The presented classifier is modelled by support vectors as well as various kernel functions, with its hard restrictions relaxed by slack variables to be soft restrictions in order to achieve higher performance. We have compared evolutionary learning with traditional gradient methods on standard, dual and soft margin support vector machines, built by polynomial, Gaussian, and ANOVA kernels. Experimental results for data on 434 polymers and 1,441 glasses show that both gradient and evolutionary learning approaches have their advantages. We show that within this domain the chosen gradient methodology is beneficial for standard linear classification problems, whilst the evolutionary methodology is more effective in addressing highly non-linear and complex problems, such as the soft margin problem.

This study investigates the feasibility of applying state of the art deep learning techniques to detect precancerous stages of squamous cell carcinoma (SCC) cancer in real time to address the challenges while diagnosing SCC with subtle appearance changes as well as video processing speed. Two deep learning models are implemented, which are to determine artefact of video frames and to detect, segment and classify those no-artefact frames respectively. For detection of SCC, both mask-RCNN and YOLOv3 architectures are implemented. In addition, in order to ascertain one bounding box being detected for one region of interest instead of multiple duplicated boxes, a faster non-maxima suppression technique (NMS) is applied on top of predictions. As a result, this developed system can process videos at 16-20 frames per second. Three classes are classified, which are 'suspicious', 'high grade' and 'cancer' of SCC. With the resolution of 1920x1080 pixels of videos, the average processing time while apply YOLOv3 is in the range of 0.064-0.101 seconds per frame, i.e. 10-15 frames per second, while running under Windows 10 operating system with 1 GPU (GeForce GTX 1060). The averaged accuracies for classification and detection are 85% and 74% respectively. Since YOLOv3 only provides bounding boxes, to delineate lesioned regions, mask-RCNN is also evaluated. While better detection result is achieved with 77% accuracy, the classification accuracy is similar to that by YOLOYv3 with 84%. However, the processing speed is more than 10 times slower with an average of 1.2 second per frame due to creation of masks. The accuracy of segmentation by mask-RCNN is 63%. These results are based on the date sets of 350 images. Further improvement is hence in need in the future by collecting, annotating or augmenting more datasets.

This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning framework called LIME.Our study shows that selfreported rating of NLG explanation was higher than that for a non-NLG explanation.However, when tested for comprehension, the results were not as clearcut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.

As the important elements of the Internet of Things system, wireless sensor network (WSN) has gradually become popular in many application fields. However, due to the openness of WSN, attackers can easily eavesdrop, intercept, and rebroadcast data packets. WSN has also faced many other security issues. Intrusion detection system (IDS) plays a pivotal part in data security protection of WSN. It can identify malicious activities that attempt to violate network security goals. Therefore, the development of effective intrusion detection technologies is very important. However, many dimensions of the datasets of IDS are irrelevant or redundant. This causes low detection speed and poor performance. Feature selection is thus introduced to reduce dimensions in IDS. At the same time, many evolutionary computing (EC) techniques were employed in feature selection. However, these techniques usually have just one Candidate Solution Generation Strategy (CSGS) and often fall into local optima when dealing with feature selection problems. The self-adaptive differential evolution (SaDE) algorithm is adopted in our paper to deal with feature selection problems for IDS. The adaptive mechanism and four effective CSGSs are used in SaDE. Through this method, an appropriate CSGS can be selected adaptively to generate new individuals during evolutionary process. Besides, we have also improved the control parameters of the SaDE. The K-Nearest Neighbour (KNN) is used for performance assessment for feature selection. KDDCUP99 dataset is employed in the experiments, and experimental results demonstrate that SaDE is more promising than the algorithms it compares.

In this paper, we present a semi-automatic system (Sherlock) for quiz generation using Linked Data and textual descriptions of RDF resources. Sherlock is distinguished from existing quiz generation systems in its ability to control the difficulty level of the generated quizzes. We cast the problem of perceiving the level of knowledge difficulty as a similarity measure problem and propose a novel hybrid semantic similarity measure using linked data. Extensive experiments show that the proposed similarity measure outperforms four strong baselines in both the pilot evaluation using a synthetic gold standard as well as with human evaluation, giving more than 47% gain in clustering accuracy over the baselines.

Most of the initialization approaches are dedicated to the partitional clustering algorithms which process categorical or numerical data only. However, in real-world applications, data objects with both numeric and categorical features are ubiquitous. The coexistence of both categorical and numerical attributes make the initialization methods designed for single-type data inapplicable to mixed-type data. Furthermore, to the best of our knowledge, in the existing partitional clustering algorithms designed for mixed-type data, the initial cluster centers are determined randomly. In this paper, we propose a novel initialization method for mixed data clustering. In the proposed method, both the distance and density are exploited together to determine initial cluster centers. The performance of the proposed method is demonstrated by a series of experiments on three real-world datasets in comparison with that of traditional initialization methods.

Computational modelling of biochemical systems based on top-down and bottom-up approaches has been well studied over the last decade. In this research, after illustrating how to generate atomic components by a set of given reactants and two user pre-defined component patterns, we propose an integrative top-down and bottom-up modelling approach for stepwise qualitative exploration of interactions among reactants in biochemical systems. Evolution strategy is applied to the top-down modelling approach to compose models, and simulated annealing is employed in the bottom-up modelling approach to explore potential interactions based on models constructed from the top-down modelling process. Both the top-down and bottom-up approaches support stepwise modular addition or subtraction for the model evolution. Experimental results indicate that our modelling approach is feasible to learn the relationships among biochemical reactants qualitatively. In addition, hidden reactants of the target biochemical system can be obtained by generating complex reactants in corresponding composed models. Moreover, qualitatively learned models with inferred reactants and alternative topologies can be used for further web-lab experimental investigations by biologists of interest, which may result in a better understanding of the system.

Essential proteins are crucial to cellular survival and development. Traditionally, essential proteins are identified by knock-out experiments, which are expensive and often fatal to the target organisms. Regarding this, an important approach to essential protein identification is through computational prediction. In this research, we present a novel computational method, Integrated Edge Weights (IEW), to innovatively predict proteins' essentiality based on essential protein-protein interactions. The experimental results on all three organisms: Saccharomyces cere-visiae (Yeast), Escherichia coli (E. coli), and Caenorhabditis ele-gans (C. elegans) show that IEW achieves better performance than the state-of-the-art methods in terms of precision-recall. Furthermore, we have demonstrated that the highly-ranked protein-protein interactions predicted by our approach tend to be biologically significant in Yeast, E. coli, and C. elegans protein-protein interaction (PPI) networks.

In this paper we continue the research on learning qualitative differential equation (QDE) models of biological pathways building on previous work. In particular, we adapt opt-AiNet, an immune-inspired network approach, to effectively search the qualitative model space. To improve the performance of opt-AiNet on the discrete search space, the hypermutation operator has been modified, and the affinity between two antibodies has been redefined. In addition, to accelerate the model verification process, we developed a more efficient Waltz-like inverse model checking algorithm. Finally, a Bayesian scoring function is incorporated into the fitness evaluation to better guide the search. Experimental results on learning the detoxification pathway of Methylglyoxal with various hypothesised hidden species validate the proposed approach, and indicate that our opt-AiNet based approach outperforms the previous CLONALG based approach on qualitative pathway identification.

In this research we focus on dealing with fuzzy multivariate relations and how we could perform fuzzy qualitative simulation with models containing such relations. To achieve this, we extended Morven, a fuzzy qualitative reasoning framework, and proposed novel types of constraints for the framework. We first introduced fuzzy multivariate function (FMF) constraints, and presented their corresponding constraints in higher differential planes of a Morven model. We then implemented the fuzzy multivariate monotonicity (FMM) relations by FMF constraints and MM_add constraints, another kind of constraints we proposed for Morven. In addition, we employed alpha-cut to determine the "strictness" of qualitative signs in the MM_add constraints. Finally, proof-of-concept experiments were performed to validate the proposed constraints, and both fuzzy and non-fuzzy situations were considered in these experiments.

In this paper, we investigate the social-based recommendation algorithms on heterogeneous social networks and proposed Hete-CF, a social collaborative filtering algorithm using heterogeneous relations. Distinct from the exiting methods, Hete-CF can effectively utilise multiple types of relations in a heterogeneous social network. More importantly, Hete-CF is a general approach and can be used in arbitrary social networks, including event based social networks, location based social networks, and any other types of heterogeneous information networks associated with social information. The experimental results on a real-world dataset DBLP (a typical heterogeneous information network)demonstrate the effectiveness of our algorithm.

This letter addresses the problem of analyzing spatio-temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.