Cloud computing primarily focuses on providing secure and reliable access to geographically distributed resources. Cloud computing is a parallel and distributed system that simplifies the virtualization of distributed computing. Job scheduling is one of the most important services in cloud computing. Job scheduling is used to schedule users' jobs to allocate suitable resources in a cloud environment. Recently, several efficient job scheduling algorithms have been proposed for cloud computing. The purpose of designing these algorithms is to achieve time and cost optimization for job execution. On the other hand, it is necessary to provide a model to assess the reliability of the different job scheduling algorithms. Unfortunately, no accurate and complete model has been proposed to evaluate the reliability of these algorithms. Scheduling failures are inevitable in cloud computing due to the harsh deployment environment, resource migration, non-compliance time or cost, etc. Therefore, providing a reliability model is necessary for successful scheduling algorithms. In this paper, a reliability model based on a discrete-time Markov chain is incorporated for the famous scheduling algorithms MCT, MET, BCO, HCOC, and PPO. We propose an approach to evaluating the reliability of scheduling algorithms based on time and cost constraints. The proposed approach is modeled by a Discrete Time Markov Chain, and the results show the reliability of scheduling algorithms in different states.
To address issues such as data sparsity, overfitting, and the inability to fully extract latent information in traditional recommendation methods, a new insurance product recommendation algorithm is proposed that combines knowledge graphs improved by matrix factorization with deep neural networks (DNN). First, to tackle the issue of sparse data in existing insurance products, an improved knowledge graph recommendation algorithm based on matrix factorization (FunkSVD) is proposed. By training the data through matrix factorization the problem of data sparsity is mitigated. After refining the customer-product matrix, knowledge graph triples are constructed based on customer characteristics and insurance product features such as insured age and coverage. Feature extraction and customer preference prediction are carried out using an alternating learning approach within a multi-task knowledge graph framework. Then, to alleviate issues like local optima and vanishing gradients during recommendation, DNN is applied for further recommendation. A fully connected layer is constructed, and forward propagation and backpropagation algorithms are used to train customer features and product matrices, predicting customer purchasing behavior and generating recommendations. Finally, comparative experimental results show that, compared to other recommendation algorithms such as collaborative filtering and DNN, the proposed algorithm improves accuracy, recall, F1 score, and other metrics. This algorithm not only speeds up recommendations but also improves recommendation quality.
To address the issue of low recall rates in detecting small faces within crowded scenes, this paper conducts an analysis of the primary reasons behind this challenge and introduces a real-time face detection system named CF-YOLO (Crowded-Face-YOLO). The study identifies a crucial factor contributing to this problem, which is the insufficient provision of positive samples for small faces during the training phase by conventional face detectors. To tackle this limitation, a Sa-SimOTA strategy is proposed to enhance the availability of positive samples for small targets. Additionally, in the post-processing stage, the utilization of the non-maximum suppression (NMS) algorithm for assigning optimal bounding boxes to detected faces is discussed. The traditional fixed threshold employed in the NMS algorithm for decision-making often results in the loss of small face detection boxes in crowded scenarios. To alleviate this issue, a Soft-Face-NMS algorithm is introduced, which incorporates facial feature variables into the Soft-NMS algorithm for weighted processing, facilitating the selection of face boxes with higher confidence in overlapping regions. Furthermore, to augment the feature extraction capabilities of the YOLO backbone, an EMA+ attention module is proposed, and modifications are made to the network structure of YOLOv7 to enhance the extraction of more effective features conducive to small face detection. The proposed model demonstrates impressive accuracy rates of 97.3 %, 96.4 %, and 92.8 % on the easy, medium, and hard subsets of the Wider-Face dataset, respectively. Notably, the accuracy achieved on the hard subset approaches the state-of-the-art level, which further demonstrates the effectiveness of our proposed approach for face detection in crowded scenes.
Deep generative models are widely used in recommendation systems because of their ability to deal with uncertainty by learning inherent data distribution. Among deep generative models, Generative Adversarial Networks (GAN) perform well in recommendation tasks. However, existing Collaborative Filtering (CF) recommendation algorithms based on GAN generally have problems such as mode collapse and training instability, which are further aggravated by sparse and noisy recommendation data. To solve these problems, a Collaborative Diffusion Generative Adversarial Networks (CDGAN) framework for recommendation systems is proposed in this paper. Specifically, CDGAN framework is mainly composed of three parts: feature encoder, diffusion generator, and self-attention discriminator. The feature encoder extracts the rating information and side information to obtain potential feature vectors to alleviate the data sparsity problem. The diffusion generator simulates the complex nonlinear mode of the user-item interaction matrix through forward diffusion and reverse denoising to reconstruct the user-item interaction matrix to alleviate the problem of data noise. The self-attention discriminator obtains the user's specific behaviors and preferences through the self-attention mechanism to improve the discriminator's discriminating ability. Furthermore, a corresponding CDGAN recommendation algorithm is designed based on our proposed CDGAN framework. Comprehensive experiments are conducted on three real-world recommendation datasets. The experimental results indicate that, when compared with multiple representative recommendation models, the proposed CDGAN model achieves superior performance in the evaluation metrics Precision and Recall on all datasets, thereby proving its effectiveness.
Accurate load forecasting is the premise of efficient and stable operation of integrated energy systems. For multiple integrated energy systems that have insufficient energy consumption data but similar energy consumption behavior, federated learning can establish a higher accuracy multi-load forecasting model for each system without disclosing data privacy. However, the existing federated learning methods cannot fully utilize common and individual characteristics in the energy consumption data of different nodes (that is, integrated energy systems), which obviously affects their prediction accuracy. In view of this, we propose a multi-time scale multi-load federated forecasting method based on mode decomposition (MD-MMFF). Firstly, a multivariate empirical mode decomposition method is introduced to decompose the energy consumption data of each node into two types, i.e., regular components and irregular components. Each node uses the local LSTM model to learn the regular components and predict their outputs. For the irregular components, a multi-load federated forecasting training mechanism based on knowledge distillation is proposed, and the corresponding multi-load forecasting model is jointly established for each node. Then, the predicted values of regular components and irregular components are integrated to obtain the final multivariate load forecasting results. Experimental results show that compared with the existing multi-load forecasting algorithms, the proposed MD-MMFF method can obtain higher accuracy multi-source load forecasting results.
Privacy-preserving process mining (PPPM) is a technology that analyses and optimises processes while safeguarding sensitive information. Earlier research on PPPM mainly focused on the data perspective, employing techniques such as noise insertion and data generalisation to protect the sensitive personal information of process executors. However, these studies overlooked the behavioural relationships between activities in the process. Attackers can exploit domain knowledge and certain behavioural information of executors to carry out re-identification attacks, leading to the leakage of personal sensitive information. To address this issue, a behaviour anonymous method of business process based on a log skeleton is proposed. This method begins with the individual process model of the executor, clustering based on the similarity between models and utilising K-anonymity and the log skeleton technology to achieve cluster division and the construction of behaviour constraint sets. Furthermore, the generation of privacy models is standardised by the behaviour constraint set to achieve global behaviour anonymization. To evaluate the effectiveness of this method, experiments were conducted using multiple real and synthetic datasets. The experimental results indicate that this method significantly outperforms the comparison methods.
Event logs of business systems are often dirty owing to recording errors or system conventions, and this dirty data can definitely affect the quality of the event logs. Consequently, many anomalous behaviors that deviate from preestablished process models are frequently seen in event logs. To properly assess and enhance business processes, it is imperative to identify and correct such anomalous behaviors. When the missing or anomalous location is known, the current repair methods have a high success rate; however, when the missing or anomalous location is unknown, they do not function well. Therefore, a formalized solution using an activity feature graph is proposed for event logs where uncertainty arises from missing, duplicate, and replaced occurrences. Several prediction and repair models are used in conjunction with the viewpoints of control flow and data flow to identify and address anomalous behaviors in event logs. In addition to fixing exceptions at the case level, the proposed repairing approach can also correct exceptions at the attribute level, or feature repairing. Process analysts are provided with an activity feature graph to examine and refine the repair outcomes. Finally, four event logs with various anomaly ratios are used to confirm the method's viability.
Human emotion plays a critical role in the purpose of communication, with the correct detection of emotion, one can analyze the human feeling without even asking, as it is non-verbal communication method. Human emotion through facial expression is one of the highlighted topics of study because of its wide range of application from robotics, security, artificial intelligence, marketing and health monitoring where human-computer interaction (HCI) is a key ingredient. To tackle the challenges that arise in accurate human facial emotion recognition, a modified version of the EfficientNet-B3 model is proposed, which shows promising results for emotion detection using the FER-2013 dataset. By leveraging the universal FER-2013 dataset, which contains more than 35 000 grey-scale human facial images, the proposed model aims to improve recognition performance. The modified architecture incorporates EfficientNet-B3 as the base model, with an additional batch normalization layer followed by a dense layer and an output layer. The model has been trained on the facial dataset while considering these crucial factors. Performance evaluation of the model is conducted using confusion matrix, precision, recall, accuracy, and F1 score as performance metrics. Remarkably, the proposed model achieved an impressive accuracy of 92 % for training and 83.0 % for validation of the dataset. This implies that the proposed model yields highly accurate emotion recognition with a given dataset and can provide improvement in the overall efficiency of emotional recognition applications, particularly in human-to-machine interactions.
Information systems play an important role in realizing business processes. Process mining uses event logs produced by information systems to construct the models of business processes. Then, the business process model can be used to verify and improve business processes. To represent a changing business process, some structures of the process model need to be replaced with other structures. However, existing model repair methods do not consider replacing the structures of the process model. This work proposes a logical Petri net-based approach to repair models based on the order relations among activities. First, we construct two relation sets of an event log and a process model, respectively. Comparing the two relation sets, the differences between a process model and an event log are collected in a deviation set. According to the deviation set, the model is repaired by constructing concurrent structures. Finally, we perform some experiments to illustrate the effectiveness and correctness of the proposed approach. The results show that the proposed method produces a more precise and simpler repaired model compared to state-of-the-art methods.
Coreference resolution, the task of identifying expressions in text that refer to the same entity, is a critical component in various natural language processing applications. This paper presents a novel end-to-end neural coreference resolution system utilizing the CorefUD 1.1 dataset, which spans 17 datasets across 12 languages. The proposed model is based on the standard end-to-end neural coreference resolution system. We first establish baseline models, including monolingual and cross-lingual variations, and then propose several extensions to enhance performance across diverse linguistic contexts. These extensions include cross-lingual training, incorporation of syntactic information, a Span2Head model for optimized headword prediction, and advanced singleton modeling. We also experiment with headword span representation and long-documents modeling through overlapping segments. The proposed extensions, particularly the heads-only approach, singleton modeling, and long document prediction, significantly improve performance across most datasets. We also perform zero-shot cross-lingual experiments, highlighting the potential and limitations of cross-lingual transfer in coreference resolution. Our findings contribute to the development of robust and scalable coreference systems for multilingual coreference resolution. Finally, we evaluate our model on the CorefUD 1.1 test set and surpass the best model from the CRAC 2023 shared task of comparable size by a large margin.
Knowledge tracing endeavors to track shifts in students' knowledge states throughout the learning process by utilizing students' work records, enabling the prediction of their responses to the next question. As knowledge tracing advances, more information can be mined from the datasets to improve the model. However, most existing models only consider the correctness of the question and the concept as input, ignoring much of the other information gathered by intelligent tutoring systems (ITS). Therefore, this paper presents a Behavior-Enhanced Knowledge Tracing Model (BEKT). The Behavior-Enhanced Knowledge Tracing Model first selects multi-dimensional features by calculating the mutual information. The mutual information value shows that the most relevant features to the prediction target are student behavior information, including the count of hints, attempts made, and time taken to answer questions. Then, the model proposes a cross-feature fusion method to change the students' knowledge mastery state. Finally, a multi-layer perceptron is applied to integrate student behavior features to enhance knowledge state representation. Compared to existing models, BEKT more accurately captures changes in knowledge state, improving model performance.
In a complex network comprising many devices, a set of nodes may be partitioned into multiple local clusters with distinct functions, properties, or communication protocols. Thus, there has been an increase in network design problems with additional constraints regarding the clustering of vertices, one of which is the Clustered Steiner Tree Problem - a variant of the Steiner Tree Problem. There have been a few studies working on this problem in the literature, but they either solve it only in the metric case or their exploration capability remains limited. Therefore, their results are not good in many cases. To overcome the drawbacks, we propose a Priority-Based Genetic Algorithm to solve the Clustered Steiner Tree Problem. The proposed algorithm maintains a balance between exploration and exploitation to prevent the search from getting stuck in local optima. Experiments and comparisons to existing works in non-metric and metric cases are carefully conducted to prove the remarkable performance of the proposed algorithm.
With the increasingly widespread application of MAS (Multi-Agent System), recent years have witnessed growing research interest in the verification of MAS properties. Similar to traditional concurrent and multi-component systems, the paramount challenge in MAS verification is the state space explosion problem. One approach to mitigating this issue is to reduce the original model before generating the state space, as reductions at the model level can often substantially alleviate state space complexity. However, for MAS modelled using Petri nets, existing methods primarily focus on reduction at the state space level. In contrast, this paper addresses reduction at the underlying model level by proposing a solution of structural reduction for Petri nets that preserves temporal epistemic logic properties. The main contributions consist of three aspects. Firstly, since existing structural reduction rules for Petri nets are not suitable for temporal epistemic logic verification, modifications and extensions to some of the rules are introduced to accommodate temporal epistemic logic, and corresponding theorems are provided to guarantee the correctness of these rules. Furthermore, given that the applicability of structural reduction rules in Petri nets is constrained by transition visibility, this paper conducts a refined visibility analysis of transitions based on semantic characteristics of epistemic logic for a subclass of Petri nets and a specific category of properties. The resulting analysis relaxes the visibility constraints when applying the rules, and its correctness is formally guaranteed by a theorem. Finally, case studies demonstrate that the proposed structural reduction rules save space overhead during verification and achieve better reduction performance under relaxed visibility constraints.
This article focuses on the design and implementation of a 3D Convolutional Neural Network (3D-CNN) for hyperspectral classification of tree species. Real data from repeated aerial imaging of selected sections of the Slovak electricity transmission system was used to test the models, using technology from our partner VUJE, a.s., which has a hyperspectral scanner consisting of two cameras, HySpex VNIR-1800 and HySpex SWIR-384, capturing wavelengths from 400 to 2 500 nm. The results of 3D-CNN classification based on autumn and spring data collection were compared, as well as classification after fusing data from selected areas for the purpose of comparing object vs. pixel classification. The presented object-based classification model based on 3D-CNN achieves on average 9 % better classification accuracy compared to pixel-based classification using a 1D Convolutional Neural Network (1D-CNN).
With the growing demand for personalised travel experiences, the development and application of travel point-of-interest (POI) recommendation systems have become increasingly important. However, many existing systems often underperform owing to insufficient integration of social features and contextual information. To address this issue, the S-LMF algorithm is proposed, combining social features with logistic matrix factorisation to improve recommendation accuracy. This approach simulates social influence by incorporating joint check-in similarity and data to refine POI recommendations. The effectiveness of social features and logistic matrix factorisation (S-LMF) was tested against five baseline algorithms using publicly available data sets from Yelp and Gowalla. Results demonstrated that S-LMF outperformed the best baseline model by improving Precision@20 by 22.95 % on Yelp and 28.60 % on Gowalla. Moreover, it increased Recall@10 by 17.95 % on Yelp and 8.19% on Gowalla.
Business processes realized by enterprise information systems are usually designed and verified in advance by process models. Event logs generated from such systems can be used to ensure the correctness of the business process. With the upgrade of systems or changing of customers' requests, it often appears that the actual behaviors observed in event logs are not consistent with those in process models. Process mining techniques are thus used to construct and repair process models by mining event logs. In this work, we propose a new model repair approach based on logic Petri nets (LPNs). It can repair a Petri-net-based process model containing a loop return structure. According to alignments, relations between the activities in event logs and the process models are analyzed such that the deviations can be found. Then, logic expressions of logic transitions are constructed and an LPN-based process model is thus constructed. The repaired model can accurately describe the same processes as the event logs. Finally, some cases related to a thoracic surgery process in a hospital are given. The correctness and effectiveness of the proposed approach are illustrated by experiments.
The Manufacturing Execution System (MES) is a critical component of intelligent manufacturing systems, enabling the automation and intelligent control of production processes. However, conventional MESs generally lack sufficient flexibility in coping with process reconfiguration and dynamic resource variations, thereby resulting in production bottlenecks and prolonged manufacturing time. propose a modeling, analysis, and resource allocation optimization framework for MESs. This framework employs rewritable timed Petri nets (RTPNs) to model and analyze MES behavior. Furthermore, a resource allocation optimization algorithm is developed to minimize production time. A clothes customization manufacturing system is adopted as a case study to demonstrate the effectiveness of the proposed method. The production process is reconstructed and optimized based on the RTPN model, and system performance is validated through simulation. Experimental results indicate that the proposed method significantly reduces production blocking and waiting rates, thereby improving overall operational efficiency.
Transformer models and their variants have shown significant advantages in natural language processing tasks, but their high computational requirements limit their deployment on resource-constrained devices. To achieve the balance of computational cost and accuracy, the lightweight model pNLP-Mixer utilizes parameter-free projection to generate text embeddings. Nevertheless, the text embeddings generated by projection involve shallow semantic information and ignore the exploration of implicit semantic information. To overcome the challenges of high parameter cost and insufficient representation capabilities in existing models, we propose a method that incorporates topic information to enhance semantic richness. Our approach leverages the Latent Dirichlet Allocation (LDA) topic model to capture latent semantic relationships between words, thereby improving the expressiveness of text representations for downstream tasks. Building on this method, we propose a lightweight model named TEP-Mixer, which integrates multiple feature extraction modules to further enhance representation capabilities. Experimental results demonstrate that TEP-Mixer outperforms other lightweight models in accuracy while maintaining a lower parameter count across multiple benchmark datasets. It is suitable for resource-constrained devices.
