MMLUP: Multi-Source & Multi-Task Learning for User Profiles in Social Network

With the rapid development of the mobile Internet, users generate massive data in different forms in social network every day, and different characteristics of users are reflected by these social media data. How to integrate multiple heterogeneous information and establish user profiles from multiple perspectives plays an important role in providing personalized services, marketing, and recommendation systems. In this paper, we propose Multi-source & Multi-task Learning for User Profiles in Social Network which integrates multiple social data sources and contains a multi-task learning framework to simultaneously predict various attributes of a user. Firstly, we design their own feature extraction models for multiple heterogeneous data sources. Secondly, we design a shared layer to fuse multiple heterogeneous data sources as general shared representation for multi-task learning. Thirdly, we design each task’s own unique presentation layer for discriminant output of specific-task. Finally, we design a weighted loss function to improve the learning efficiency and prediction accuracy of each task. Our experimental results on more than 5000 Sina Weibo users demonstrate that our approach outperforms state-of-the-art baselines for inferring gender, age and region of social media users.     

Gene selection approach based on improved swarm intelligent optimisation algorithm for tumour classification

A number of different gene selection approaches based on gene expression profiles (GEP) have been developed for tumour classification. A gene selection approach selects the most informative genes from the whole gene space, which is an important process for tumour classification using GEP. This study presents an improved swarm intelligent optimisation algorithm to select genes for maintaining the diversity of the population. The most essential characteristic of the proposed approach is that it can automatically determine the number of the selected genes. On the basis of the gene selection, the authors construct a variety of the tumour classifiers, including the ensemble classifiers. Four gene datasets are used to evaluate the performance of the proposed approach. The experimental results confirm that the proposed classifiers for tumour classification are indeed effective.Inspec keywords: tumours, swarm intelligence, particle swarm optimisation, pattern classification, medical computing, geneticsOther keywords: gene datasets, ensemble classifiers, tumour classifiers, gene space, informative genes, gene expression profiles, tumour classification, swarm intelligent optimisation algorithm, gene selection approach     

In silico discovery of significant pathways in colorectal cancer metastasis using a two‐stage optimisation approach

Accurate and reliable modelling of protein–protein interaction networks for complex diseases such as colorectal cancer can help better understand mechanism of diseases and potentially discover new drugs. Different machine learning methods such as empirical mode decomposition combined with least square support vector machine, and discrete Fourier transform have been widely utilised as a classifier and for automatic discovery of biomarkers for the diagnosis of the disease. The existing methods are, however, less efficient as they tend to ignore interaction with the classifier. In this study, the authors propose a two‐stage optimisation approach to effectively select biomarkers and discover interactions among them. At the first stage, particle swarm optimisation (PSO) and differential evolution (DE) are used to optimise parameters of support vector machine recursive feature elimination algorithm, and dynamic Bayesian network is then used to predict temporal relationship between biomarkers across two time points. Results show that 18 and 25 biomarkers selected by PSO and DE‐based approach, respectively, yields the same accuracy of 97.3% and F1‐score of 97.7 and 97.6%, respectively. The stratified analysis reveals that Alpha‐2‐HS‐glycoprotein was a dominant hub gene with multiple interactions to other genes including Fibrinogen alpha chain, which is also a potential biomarker for colorectal cancer.Inspec keywords: cancer, proteins, particle swarm optimisation, evolutionary computation, support vector machines, recursive functions, Bayes methods, genetics, molecular biophysics, medical computingOther keywords: colorectal cancer metastasis, two‐stage optimisation approach, protein–protein interaction networks, biomarkers, particle swarm optimisation, differential evolution, support vector machine recursive feature elimination, dynamic Bayesian network, stratified analysis, Alpha‐2‐HS‐glycoprotein, hub gene, Fibrinogen alpha chain     

Bayesian Model Fusion for Forecasting Civil Unrest

With the rapid rise in social media, alternative news sources, and blogs, ordinary citizens have become information producers as much as information consumers. Highly charged prose, images, and videos spread virally, and stoke the embers of social unrest by alerting fellow citizens to relevant happenings and spurring them into action. We are interested in using Big Data approaches to generate forecasts of civil unrest from open source indicators. The heterogenous nature of data coupled with the rich and diverse origins of civil unrest call for a multi-model approach to such forecasting. We present a modular approach wherein a collection of models use overlapping sources of data to independently forecast protests. Fusion of alerts into one single alert stream becomes a key system informatics problem and we present a statistical framework to accomplish such fusion. Given an alert from one of the numerous models, the decision space for fusion has two possibilities: (i) release the alert or (ii) suppress the alert. Using a Bayesian decision theoretical framework, we present a fusion approach for releasing or suppressing alerts. The resulting system enables real-time decisions and more importantly tuning of precision and recall. Supplementary materials for this article are available online.     

Swarm intelligence-based strategic bidding in competitive electricity markets

In the competitive electricity markets, formation of supply bid is one of the main concerns, where suppliers have to maximise their profit under incomplete information of other competing generators. An environment is described in which suppliers bid strategically to sell electricity in a pool market. The bidding decision is optimised from a single supplier's viewpoint in both block-bid and linear-bid models of an electricity market. To include uncertain behaviour of other competing suppliers, two different probabilistic models are used. Their bids are constructed using probability distribution functions obtained from the decision-maker's observations of historical market data. Single supplier's decision-making problem is solved by a modern population-based heuristic algorithm, known as particle swarm optimisation (PSO). Search procedure of PSO is based on the concept of combined effect of cognitive and social learning of the members in a group. The effectiveness of the proposed method is tested with examples and the results are compared with the solutions obtained using the genetic algorithm approach.     

基于社交媒体的汽车缺陷识别方法

由于社交媒体上的信息传播具有广泛性和快速性,及时从社交媒体中挖掘汽车的缺陷信息对汽车厂商改进产品设计、优化质量管理具有指导意义。目前有关社交媒体缺陷识别的研究挖掘的缺陷信息较少且方法以聚类为主,效果不是很好。在现有关于社交媒体缺陷识别研究的基础上,结合企业的实际需求,扩展了具体的缺陷类别;基于朴素贝叶斯的分类方法详细对比了3种特征提取方法,并在此基础上结合EM算法实现了半监督的分类学习。实验结果表明,在缺陷类别划分符合企业实际需求的情况下,所提出的方法能够有效地识别出对应类别的缺陷,为企业缺陷管理提供决策支持,同时可以降低一半的人工标注成本。     

Transient stability constrained optimal power flow using particle swarm optimisation

A novel approach based on the particle swarm optimisation (PSO) technique is proposed for the transient-stability constrained optimal power flow (TSCOPF) problem. Optimal power flow (OPF) with transient-stability constraints considered is formulated as an extended OPF with additional rotor angle inequality constraints. For this nonlinear optimisation problem, the objective function is defined as minimising the total fuel cost of the system. The proposed PSO-based approach is demonstrated and compared with conventional OPF as well as a genetic algorithm based counterpart on the IEEE 30-bus system. Furthermore, the effectiveness of the PSO-based TSCOPF in handling multiple contingencies is illustrated using the New England 39-bus system. Test results show that the proposed approach is capable of obtaining higher quality solutions efficiently in the TSCOPF problem     

Underexposed and overexposed colour image enhancement using information set theory

This paper presents a new approach for improving the contrast of digital colour images in extreme lighting environment. The concept of information sets that are derived from fuzzy sets is applied for this purpose. The S and V components of the HSV (hue, saturation, value) colour model are fuzzified using Gaussian and triangular membership functions but H is preserved. Objective measures like contrast information, quality and visual factor (V_f) are defined to represent the image characteristics. A new entropy function and V_f are used to form the objective function which is optimised using particle swarm optimisation to learn the image-specific parameters required for the enhancement. These new measures defined here serve to evaluate the performance of the proposed algorithm. In addition to preserving the colour and specific image features, the subjective and objective evaluations clearly depict the improvement in the quality of both the underexposed and overexposed images. On comparison, it is found that the proposed technique outperforms the existing techniques in terms of entropy, information measure and mean opinion score.     

Gene expression feature selection for prostate cancer diagnosis using a two‐phase heuristic–deterministic search strategy

Here, a two‐phase search strategy is proposed to identify the biomarkers in gene expression data set for the prostate cancer diagnosis. A statistical filtering method is initially employed to remove the noisiest data. In the first phase of the search strategy, a multi‐objective optimisation based on the binary particle swarm optimisation algorithm tuned by a chaotic method is proposed to select the optimal subset of genes with the minimum number of genes and the maximum classification accuracy. Finally, in the second phase of the search strategy, the cache‐based modification of the sequential forward floating selection algorithm is used to find the most discriminant genes from the optimal subset of genes selected in the first phase. The results of applying the proposed algorithm on the available challenging prostate cancer data set demonstrate that the proposed algorithm can perfectly identify the informative genes such that the classification accuracy, sensitivity, and specificity of 100% are achieved with only nine biomarkers.Inspec keywords: cancer, biological organs, optimisation, feature extraction, search problems, particle swarm optimisation, pattern classification, geneticsOther keywords: biomarkers, gene expression feature selection, prostate cancer diagnosis, heuristic–deterministic search strategy, two‐phase search strategy, gene expression data, statistical filtering method, noisiest data, multiobjective optimisation, particle swarm optimisation algorithm, chaotic method, selection algorithm, discriminant genes, available challenging prostate cancer data, informative genes     

The role of social media data in operations and production management

Social media data contain rich information in posts or comments written by customers. If those data can be extracted and analysed properly, companies can fully utilise this rich source of information. They can then convert the data to useful information or knowledge, which can help to formulate their business strategy. This cannot only facilitate marketing research in view of customer behaviour, but can also aid other management disciplines. Operations management (OM) research and practice with the objective to make decisions on product and process design is a fine example. Nevertheless, this line of thought is under-researched. In this connection, this paper explores the role of social media data in OM research. A structured approach is proposed, which involves the analysis of social media comments and a statistical cluster analysis to identify the interrelationships amongst important factors. A real-life example is employed to demonstrate the concept.     

Machine Learning Approach for COVID-19 Detection on Twitter

Social networking services (SNSs) provide massive data that can be a very influential source of information during pandemic outbreaks. This study shows that social media analysis can be used as a crisis detector (e.g., understanding the sentiment of social media users regarding various pandemic outbreaks). The novel Coronavirus Disease-19 (COVID-19), commonly known as coronavirus, has affected everyone worldwide in 2020. Streaming Twitter data have revealed the status of the COVID-19 outbreak in the most affected regions. This study focuses on identifying COVID-19 patients using tweets without requiring medical records to find the COVID-19 pandemic in Twitter messages (tweets). For this purpose, we propose herein an intelligent model using traditional machine learning-based approaches, such as support vector machine (SVM), logistic regression (LR), naïve Bayes (NB), random forest (RF), and decision tree (DT) with the help of the term frequency inverse document frequency (TF-IDF) to detect the COVID-19 pandemic in Twitter messages. The proposed intelligent traditional machine learning-based model classifies Twitter messages into four categories, namely, confirmed deaths, recovered, and suspected. For the experimental analysis, the tweet data on the COVID-19 pandemic are analyzed to evaluate the results of traditional machine learning approaches. A benchmark dataset for COVID-19 on Twitter messages is developed and can be used for future research studies. The experiments show that the results of the proposed approach are promising in detecting the COVID-19 pandemic in Twitter messages with overall accuracy, precision, recall, and F1 score between 70% and 80% and the confusion matrix for machine learning approaches (i.e., SVM, NB, LR, RF, and DT) with the TF-IDF feature extraction technique.     

Deploying swarm intelligence in medical imaging identifying metastasis,micro‐calcifications and brain image segmentation

This study proposes an umbrella deployment of swarm intelligence algorithm, such as stochastic diffusion search for medical imaging applications. After summarising the results of some previous works which shows how the algorithm assists in the identification of metastasis in bone scans and microcalcifications on mammographs, for the first time, the use of the algorithm in assessing the CT images of the aorta is demonstrated along with its performance in detecting the nasogastric tube in chest X‐ray. The swarm intelligence algorithm presented in this study is adapted to address these particular tasks and its functionality is investigated by running the swarms on sample CT images and X‐rays whose status have been determined by senior radiologists. In addition, a hybrid swarm intelligence‐learning vector quantisation (LVQ) approach is proposed in the context of magnetic resonance (MR) brain image segmentation. The particle swarm optimisation is used to train the LVQ which eliminates the iteration‐dependent nature of LVQ. The proposed methodology is used to detect the tumour regions in the abnormal MR brain images.Inspec keywords: swarm intelligence, image segmentation, brain, neurophysiology, medical image processing, biomedical MRI, computerised tomography, diagnostic radiography, bone, diseases, learning (artificial intelligence), particle swarm optimisation, iterative methods, tumours, medical disordersOther keywords: medical imaging identifying metastasis, microcalcifications, umbrella deployment, stochastic diffusion, metastasis identification, bone scans, mammographs, CT imaging, aorta, nasogastric tube, chest X‐ray, hybrid swarm intelligence‐learning vector quantisation approach, magnetic resonance brain image segmentation, particle swarm optimisation, iteration‐dependent nature, tumour regions, abnormal MR brain imaging     

Development of Social Media Analytics System for Emergency Event Detection and Crisis Management

Social media platforms have proven to be effective for information gathering during emergency events caused by natural or human-made disasters. Emergency response authorities, law enforcement agencies, and the public can use this information to gain situational awareness and improve disaster response. In case of emergencies, rapid responses are needed to address victims’ requests for help. The research community has developed many social media platforms and used them effectively for emergency response and coordination in the past. However, most of the present deployments of platforms in crisis management are not automated, and their operational success largely depends on experts who analyze the information manually and coordinate with relevant humanitarian agencies or law enforcement authorities to initiate emergency response operations. The seamless integration of automatically identifying types of urgent needs from millions of posts and delivery of relevant information to the appropriate agency for timely response has become essential. This research project aims to develop a generalized Information Technology (IT) solution for emergency response and disaster management by integrating social media data as its core component. In this paper, we focused on text analysis techniques which can help the emergency response authorities to filter through the sheer amount of information gathered automatically for supporting their relief efforts. More specifically, we applied state-of-the-art Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning (DL) techniques ranging from unsupervised to supervised learning for an in-depth analysis of social media data for the purpose of extracting real-time information on a critical event to facilitate emergency response in a crisis. As a proof of concept, a case study on the COVID-19 pandemic on the data collected from Twitter is presented, providing evidence that the scientific and operational goals have been achieved.     

Globally optimal tool paths for sculptured surfaces with emphasis to machining error and cutting posture smoothness

Global optimisation for manufacturing problems is mandatory for obtaining versatile benefits to facilitate modern industry. This paper deals with an original approach of globally optimising tool paths to CNC-machine sculptured surfaces. The approach entails the development of a fully automated manufacturing software interface integrated by a non-conventional genetic/evolutionary algorithm to enable intelligent machining. These attributes have been built using already existing practical machining modelling tools such as CAM systems so as to deliver a truly viable computer-aided manufacturing solution. Since global optimisation is heavily based on the formulation of the problem, emphasis has been given to the definition of optimisation criteria as crucial elements for representing performance. The criteria involve the machining error as a combined effect of chord error and scallop height, the tool path smoothness and productivity. Experiments have been designed considering several benchmark sculptured surfaces as well as tool path parameters to validate the aforementioned criteria. The new approach was implemented to another sculptured surface which has been extensively tested by previous research works. Results were compared to those available in the literature and it was found that the proposed approach can indeed constitute a promising and trustworthy technique for the global optimisation of sculptured surface CNC tool paths.     

Optimal generator maintenance scheduling using a modified discrete PSO

A modified discrete particle swarm optimisation (MDPSO) algorithm to generate optimal preventive maintenance schedule of generating units for economical and reliable operation of a power system, while satisfying system load demand and crew constraints, is presented. Discrete particle swarm optimisation (DPSO) is known to effectively solve large-scale multi-objective optimisation problems and has been widely applied in power system. The MDPSO proposed for the generator maintenance scheduling optimisation problem generates optimal and feasible solutions and overcomes the limitations of the conventional methods, such as extensive computational effort, which increases exponentially as the size of the problem increases. The efficacy of the proposed algorithm is illustrated and compared with the genetic algorithm (GA) and DPSO in two case studies ? a 21-unit test system and a 49-unit system feeding the Nigerian national grid. The MDPSO algorithm is found to generate schedules with comparatively higher system reliability indices than those obtained with GA and DPSO.     

A hybrid particle swarm based method for process planning optimisation

A process planning (PP) problem is defined as to determine a set of operation-methods (machine, tool, and set-up configuration) that can convert the given stock to the designed part. Essentially, the PP problem involves the simultaneous decision making of two tasks: operation-method selection and sequencing. This is a combinatorial optimisation problem and it is difficult to find the best solution in a reasonable amount of time. In this article, an optimisation approach based on particle swarm optimisation (PSO) is proposed to solve the PP problem. Due to the characteristic of discrete process planning solution space and the continuous nature of the original PSO, a novel solution representation scheme is introduced for the application of PSO in solving the PP problem. Moreover, two kinds of local search algorithms are incorporated and interweaved with PSO evolution to improve the best solution in each generation. The numerical experiments and analysis have demonstrated that the proposed algorithm is capable of gaining a good quality solution in an efficient way.     

Fuzzy-metaheuristic methods to solve a hybrid flow shop scheduling problem with pre-assignment

This paper deals with a particular version of the hybrid flow shop scheduling problem inspired from a real application in the automotive industry. Specific constraints such as pre-assigned jobs, non-identical parallel machines and non-compatibility between certain jobs and machines are considered in order to minimise the total tardiness time. A mixed-integer programming model that incorporates these aspects is developed and solved using ILOG Cplex software. Thus, because of the computation time constraint, we propose approximate resolution methods based on genetic and particle swarm optimisation algorithms coupled or not with fuzzy logic control. The effectiveness of these methods is investigated via computational experiments based on theoretical and real case instances. The obtained results show that fuzzy logic control improves the performances of both genetic and particle swarm optimisation algorithms significantly.     

Chaotic emperor penguin optimised extreme learning machine for microarray cancer classification

Microarray technology plays a significant role in cancer classification, where a large number of genes and samples are simultaneously analysed. For the efficient analysis of the microarray data, there is a great demand for the development of intelligent techniques. In this article, the authors propose a novel hybrid technique employing Fisher criterion, ReliefF, and extreme learning machine (ELM) based on the principle of chaotic emperor penguin optimisation algorithm (CEPO). EPO is a recently developed metaheuristic method. In the proposed method, initially, Fisher score and ReliefF are independently used as filters for relevant gene selection. Further, a novel population‐based metaheuristic, namely, CEPO was proposed to pre‐train the ELM by selecting the optimal input weights and hidden biases. The authors have successfully conducted experiments on seven well‐known data sets. To evaluate the effectiveness, the proposed method is compared with original EPO, genetic algorithm, and particle swarm optimisation‐based ELM along with other state‐of‐the‐art techniques. The experimental results show that the proposed framework achieves better accuracy as compared to the state‐of‐the‐art schemes. The efficacy of the proposed method is demonstrated in terms of accuracy, sensitivity, specificity, and F‐measure.Inspec keywords: genetic algorithms, pattern classification, biology computing, cancer, learning (artificial intelligence), search problems, particle swarm optimisationOther keywords: optimal input weights, data sets, original EPO, genetic algorithm, particle swarm optimisation‐based ELM, microarray cancer classification, microarray technology, microarray data, intelligent techniques, Fisher criterion, ReliefF, chaotic emperor penguin optimisation algorithm, CEPO, recently developed metaheuristic method, Fisher score, relevant gene selection, population‐based, chaotic penguin optimised extreme learning machine, F     

Unit commitment computation by fuzzy adaptive particle swarm optimisation

A fuzzy adaptive particle swarm optimisation (FAPSO) for unit commitment (UC) problem has been proposed. FAPSO reliably and accurately tracks a continuously changing solution. By analyzing the social model of standard PSO for the UC problem of variable resource size and changing load demand, the fuzzy adaptive criterion is applied for the PSO inertia weight based on the diversity of fitness. In this method, the inertia weight is dynamically adjusted using fuzzy IF/THEN rules to increase the balance between global and local searching abilities. Velocity is digitised (0/1) by a logistic function for the binary UC schedule. To improve knowledge, the global best location is also moved instead of a fixed one in each generation. To avoid the system to be frozen, stagnated/idle particles are reset from time to time. Finally, benchmark data and methods are used to show effectiveness of the proposed method