Search

Random forest is one of the most heated machine learning tools in a wide range of industrial scenarios. Recently, federated learning enables efficient distributed machine learning without direct revealing of private participant data. In this paper, we present a novel framework of federated random forest (RevFRF), and further emphatically discuss the participant revocation problem of federated learning based on RevFRF. Specifically, RevFRF first introduces a suite of homomorphic encryption based secure protocols to implement federated random forest (RF). The protocols cover the whole lifecycle of an RF model, including construction, prediction, and participant revocation. Then, referring to the practical application scenarios of RevFRF, the existing federated learning frameworks ignore a fact that even every participant in federated learning cannot maintain the cooperation with others forever. In company-level cooperation, allowing the remaining companies to use a trained model that contains the memories from an off-lying company potentially leads to a significant conflict of interest. Therefore, we propose the revocable federated learning concept and illustrate how RevFRF implements participant revocation in applications.

Sketches, as a kind of probabilistic data structures, have been considered as the most promising solution for network measurement in recent years. Most sketches do not work well for skewed network traffic. To address this problem, we propose a family of sketch frameworks, namely the Pyramid family. The first member of our Pyramid family is the S-Pyramid framework, which includes two techniques: counter-pair sharing for high accuracy, and word acceleration for fast speed. The second member of our Pyramid family is the Mini-Pyramid framework, which projects the S-Pyramid framework into one counter, bringing more flexibility in application while keeping the accuracy. To demonstrate the generality of our Pyramid family, we apply both frameworks to sketches of CM, CU, Count, and Augmented. To demonstrate the flexibility of the Mini-Pyramid framework, we further apply Mini-Pyramid to SBF and the On-Off sketch. The experimental results show that, the S-Pyramid framework can reduce the ARE by up to 7.12 times compared with the original sketches, while improving the throughput by up to 2.37 times; the Mini-Pyramid framework can reduce the ARE by up to 29.2 times, at the cost of 21.3% lower throughput on average.

More and more attention has been paid to web service classification as it can improve the quality of service discovery and management in the service repository, and can be widely used to locate developers’ desired services. Although traditional classification method based on supervised learning model to this task shows promising results, it still suffered from the following shortcomings: (i) the performance of conventional machine learning methods highly depends on the quality of manual feature engineering; (ii) some classification methods (such as CNN, RNN, etc.) are usually limited to very shallow models due to the vanishing gradient problem and cannot extract more features, which have great impact on the accuracy of web service classification. To overcome these challenges, a novel web service classification model named Residual Attention Graph Convolutional Network (RAGCN) is proposed. Firstly, adding an attention mechanism to the graph convolutional network can assign different weights to the neighborhood nodes without complicated matrix operations or relying on understanding the entire graph structure. Secondly, using residual learning to deepen the depth of the model can extract more features. The comprehensive experimental results on real dataset show that the proposed model outperforms the state-of-the-art approaches and proves its potentially good interpretability for graphical analysis.

Background Machine learning has become an alternative approach for pharmaceutical formulation development. However, many machine learning applications in pharmaceutics only focus on model performance rather than model interpretability. Aim This study aims to propose an attention‐based deep neural network (DNN) for pharmaceutical formulation development. Methods An attention‐based DNN, AttPharm, was proposed. AttPharm separately handled feature values and feature physical meaning by representation learning to successfully apply the attention mechanism to the pharmaceutical tabular data. Furthermore, the distributions of the attention weights were computed using AttPharm. Two post hoc methods, local interpretable model‐agnostic explanation (LIME) and TreeSHAP, were utilized to obtain the post hoc model interpretability for lightGBM. Results The results demonstrated that AttPharm significantly improved the model performance of plain neural networks on a pharmaceutical cyclodextrin dataset because the attention mechanism could extract related features and find minute variation. Notably, the attention weights were analyzed, which illustrated global and local feature‐level and sample‐level model interpretability, thus providing insights for formulation design. Comparing with post hoc methods, AttPharm can be used without the concern of the faithfulness of interpretability. Conclusion This is the first step in applying the attention‐based DNN to pharmaceutical formulation development. Considering the importance of model interpretability, the proposed approach may have a wide range of applications in pharmaceutics.

With the development of Industry 4.0, the communication of smart grid has recently been taken seriously to ensure secure communication between operator and control center. However, the authentication process between them faces many challenges. Once the attacker successfully authenticated in the control center, the privacy data in the smart grid may leak and cause irreparable damage to the user. In addition, operator authentication is one of the most basic and crucial processes. Therefore, we propose the eye-movement and iris recognition based authentication ( EmIr-Auth ) , a novel biometrics-based remote operator authentication scheme. EmIr-Auth uses the recorded eye-movement trajectory and randomly selected iris image to authenticate operators, which is beneficial in that it is able to get rid of many cryptographic computations, as well as the need to minimize message exchange. Furthermore, except for a high-resolution camera, we do not require any additional biometric sensors in this scheme. Using the Burrows–Abadi–Needham logic, in this article, we demonstrate that our scheme provides secure authentication. Moreover, we analyze the attacks that EmIr-Auth can resist by informal security analysis. Experimental results show that EmIr-Auth is efficient enough to deploy on portable devices and reduce the overhead of authentication procedure.

Web service classification is one of the common approaches to discover and reuse services. Machine learning methods are widely used for web service classification. However, due to the limited high-quality services in the public dataset, the state-of-the-art deep learning methods can not achieve high accuracy. In this paper, we propose a transfer learning approach Tr-ServeNet to reuse the knowledge of the App classification problem for web service classification. We pre-train a deep learning model for the App classification problem, in which the dataset contains high-quality data from Apple Store, and then transfer the embedded and extracted features to assist web service classification. To demonstrate the effectiveness of our approach, we compare the proposed method with other existing machine learning methods on the 50-category benchmark with 10, 000 real-world web services. The experimental results indicate that the proposed transfer learning method can reach the highest Top-1 accuracy in the benchmark of service classification.

Problem Frames (PF) have attracted extensive attention and research in the requirements engineering community, particularly in the field of modeling environment-based CyberPhysical Systems (CPS). This paper proposes an approach based on the combination of PF and model-driven engineering (MDE). The approach builds an extended meta-model of the Problem Frames approach to support representing causal behaviours of the environment of CPS, which are essential domain knowledge of the environment for modelling CPS requirements and complexity analysis. EMF (Eclipse Model Framework) and the Sirius technology are used to create GUI items for the meta-model and provide a platform for modeling tools based on the Eclipse environment for PF modelers. An example case study is used to demonstrate the feasibility of our approach.

Non-functional requirements specify those qualities that software products must have in order to meet the user’s business requirements. The elicitation of these non-functional requirements requires expertise, experience, and domain knowledge, which is challenging and time-consuming for requirements engineers and developers. It would be very beneficial if the nonfunctional requirements can be automatically extracted from the requirements documentation to reduce the human efforts, time, and avoid the mental fatigue. In this paper, we present a novel deep neural network model called NFRNet to automatically extract non-functional requirements from software requirements documentation.

Problem analysis has long been considered the key to requirements engineering, and the Problem Frames (PF) approach provides a structured method by deploying a common model for analyzing various types of problems. Problem decomposition is an important technique in structuring the software solution and also the key to reducing problem size and complexity. However, there has not been a suite of flexible and effective tools to describe details of problem domains in PF models. In this paper, we combine model-driven engineering and PF to provide a tool that can refine domain descriptions. In order to support modeling between domain stakeholders and software designers, we provide a technique and tool to allow the modeller to zoom in the details of a problem diagram, by adding UML State Machine Diagrams and SysML Block Definition Diagrams to domain descriptions.A demo video of this tool is available at https://youtu.be/BcQPlDYiOa8. More details of this tool and the appendix to this article are available at https://github.com/Wsfff-lf/ZOOM4PF/tree/main.

Automatic service classification plays an important role in service discovery, selection, and composition. Recently, machine learning has been widely used in service classification. Though promising results are obtained, previous methods are merely evaluated on web services datasets with small-scale data and relatively balanced data, which limit their real-world applications. In this paper, we address the long-tailed web services classification problem with more categories and imbalanced data. Due to the long-tailed distribution of datasets, the existing machine learning and deep learning methods cannot work well. To deal with the long-tailed problem, we propose a normalized multi-head classifier learning strategy, which effectively reduces the classifier bias and benefit the generalization capacity of the extracted features. Extensive experiments are conducted on a large-scale long-tailed web services dataset, and the results show that our model outperforms the 11 compared service classification methods to a large margin.

Unified Modeling Language (UML) is the de facto standard for requirements modeling and system design. UML as a visual language can tremendously help customers, project managers, and developers to specify the requirements of a target system. However, UML lacks the ability to specify the requirements precisely such as the contracts of the system operation, and verify the consistency and refinement of the requirements. These disadvantages result in that the potential faults of software are hard to be discovered in the early stage of software development process, and then requiring more efforts in software testing to find the bugs. Service refinement is a formal method, which could be a supplement to enhance the UML. In this paper, we show how to integrate UML with service refinement to specify requirements, and verify the consistency and refinements of the requirements through a case study of online shopping system. Particularly, requirements are modeled through UML diagrams, which includes a) use case diagram, b) system sequence diagrams and c) conceptual class diagram. Service refinement enhances the requirements model by introducing the contracts. Furthermore, the consistency and refinements of requirement model can be verified through service refinement. Our approach demonstrates integrating UML with service refinement can require fewer efforts to achieve the consistency requirements than only using UML for requirement modeling.

Current pharmaceutical formulation development still strongly relies on the traditional trial-and-error methods of pharmaceutical scientists. This approach is laborious, time-consuming and costly. Recently, deep learning has been widely applied in many challenging domains because of its important capability of automatic feature extraction. The aim of the present research is to apply deep learning methods to predict pharmaceutical formulations. In this paper, two types of dosage forms were chosen as model systems. Evaluation criteria suitable for pharmaceutics were applied to assess the performance of the models. Moreover, an automatic dataset selection algorithm was developed for selecting the representative data as validation and test datasets. Six machine learning methods were compared with deep learning. Results showed that the accuracies of both two deep neural networks were above 80% and higher than other machine learning models; the latter showed good prediction of pharmaceutical formulations. In summary, deep learning employing an automatic data splitting algorithm and the evaluation criteria suitable for pharmaceutical formulation data was developed for the prediction of pharmaceutical formulations for the first time. The cross-disciplinary integration of pharmaceutics and artificial intelligence may shift the paradigm of pharmaceutical research from experience-dependent studies to data-driven methodologies. KEY WORDS: Pharmaceutical formulation, Deep learning, Small data, Automatic dataset selection algorithm, Oral fast disintegrating films, Oral sustained release matrix tablets

Automated service classification plays a crucial role in service discovery, selection, and composition. Machine learning has been widely used for service classification in recent years. However, the performance of conventional machine learning methods highly depends on the quality of manual feature engineering. In this paper, we present a novel deep neural network to automatically abstract low-level representation of both service name and service description to high-level merged features without feature engineering and the length limitation, and then predict service classification on 50 service categories. To demonstrate the effectiveness of our approach, we conduct a comprehensive experimental study by comparing 10 machine learning methods on 10,000 real-world web services. The result shows that the proposed deep neural network can achieve higher accuracy in classification and more robust than other machine learning methods., Accepted by ICWS'20

Cloud-based Convolutional neural network (CNN) is a powerful tool for the healthcare center to provide health condition monitor service. Although the new service has future prospects in the medical, patient's privacy concerns arise because of the sensitivity of medical data. Prior works to address the concern have the following unresolved problems: 1) focus on data privacy but neglect to protect the privacy of the machine learning model itself; 2) introduce considerable communication costs for the CNN inference, which lowers the service quality of the cloud server. To push forward this area, we propose PE-HEALTH, a privacy-preserving health monitor framework that supports fully-encrypted CNN (both input data and model). In PE-HEALTH, the medical Internet of Things (IoT) sensor serves as the health condition data collector. For protecting patient privacy, the IoT sensor additively shares the collected data and uploads the shared data to the cloud server, which is efficient and suited to the energy-limited IoT sensor. To keep model privacy, PE-HEALTH allows the healthcare center to previously deploy, and then, use an encrypted CNN on the cloud server. During the CNN inference process, PE-HEALTH does not need the cloud servers to exchange any extra messages for operating the convolutional operation, which can greatly reduce the communication cost.

Graphical Abstract The prediction model of oral disintegrating tablets formulations with direct compression process by artificial neural network (ANN) and deep neural network (DNN) techniques were established. 145 formulation data were extracted from Web of Science. All datasets were divided into three parts: training set (105 data), validation set (20) and testing set (20) to build prediction model.Image, graphical abstract, Oral disintegrating tablets (ODTs) are a novel dosage form that can be dissolved on the tongue within 3 min or less especially for geriatric and pediatric patients. Current ODT formulation studies usually rely on the personal experience of pharmaceutical experts and trial-and-error in the laboratory, which is inefficient and time-consuming. The aim of current research was to establish the prediction model of ODT formulations with direct compression process by artificial neural network (ANN) and deep neural network (DNN) techniques. 145 formulation data were extracted from Web of Science. All datasets were divided into three parts: training set (105 data), validation set (20) and testing set (20). ANN and DNN were compared for the prediction of the disintegrating time. The accuracy of the ANN model have reached 85.60%, 80.00% and 75.00% on the training set, validation set and testing set respectively, whereas that of the DNN model were 85.60%, 85.00% and 80.00%, respectively. Compared with the ANN, DNN showed the better prediction for ODT formulations. It is the first time that deep neural network with the improved dataset selection algorithm is applied to formulation prediction on small data. The proposed predictive approach could evaluate the critical parameters about quality control of formulation, and guide research and process development. The implementation of this prediction model could effectively reduce drug product development timeline and material usage, and proactively facilitate the development of a robust drug product.

Legacy electronic health record systems were not developed with the level of connectivity expected from them nowadays. Therefore, interoperability weakness inherent in the legacy systems can result in poor patient care and waste of financial resources. Simultaneously, healthcare providers are not yet ready to dispose of them. Large hospitals are also less likely to share their data with external care providers due to economic and political reasons. To overcome the barriers in the effective medical data exchange process, we present a novel hybrid cloud called MedShare, dealing with interoperability issues among disconnected but autonomously functioning healthcare providers. The proposed system architecture and its implementation is based upon: 1) custom data extractors to extract legacy medical data from the three hemodialysis centers under consideration; 2) negotiated and converted to a common data model in each of the private cloud of a provider; 3) indexed patient information using the HashMap technique into the public cloud that operates on private clouds, called a hybrid cloud; and 4) a set of services and tools installed as a coherent environment to exchange information smoothly. This paper enables healthcare professionals to appropriately access and securely share a patient’s medical information. MedShare allows the healthcare providers and administrators to maintain the control of their patient data, which is always the primary concern in building a trustworthy environment for exchanging patient information. Medshare effectively addresses primary security and privacy concerns surrounding the deployment of data exchange process by including patient consent and a two-way authorization process.

Prototyping is an effective and efficient way of requirements validation to avoid introducing errors in the early stage of software development. Our previous work presents a tool RM2PT to automatically generate prototypes from requirements models. The stakeholders can easily check whether the requirements reflect their real needs by investigating the executions of use cases in the generated prototypes. However, the conflict and contradictory of the requirements are hard to be discovered. In this paper, we enhance RM2PT by introducing consistency checking and state observations in the generated prototypes. Requirements inconsistency can be automatically detected and further fixed through carefully analyzing the contracts of system operations and system state observations. We have conducted four case studies with over 50 use cases. The experimental result shows that 107 requirements inconsistency are founded in requirements validations. Overall, the result is satisfiable, and the enhanced RM2PT can be further applied to the software industry for requirements validation. The tool can be downloaded at http://rm2pt.mydreamy.net and a demo video casting its features is at https://youtu.be/Y7GNa57WGfA

The relationships between agents can be cooperative and competitive in multi-agent systems, which are represented by positive weight and negative weight of edges. The rules of transforming initial digraph to its line graph are given and the information of edge dynamics are considered adequately. For the line graph, the distributed control protocol is proposed. Then, we give sufficient conditions for the third-order and high-order multi-agent system to achieve the bipartite consensus of edge dynamics under the protocol. The calculation method of final values of bipartite consensus are given.

Automated service classification plays a crucial role in service discovery, selection, and composition. Machine learning has been used for service classification in recent years. However, the performance of conventional machine learning methods highly depends on the quality of manual feature engineering. In this paper, we present a deep neural network to automatically abstract low-level representation of service description to high-level features without feature engineering and then predict service classification on 50 service categories. To demonstrate the effectiveness of our approach, we conduct a comprehensive experimental study by comparing 10 machine learning methods on 10,000 real-world web services. The result shows that the proposed deep neural network can achieve higher accuracy than other machine learning methods.

Prototyping is an effective and efficient way of requirement validation to avoid introducing errors in the early stage of software development. However, manually developing a prototype of a software system requires additional efforts, which would increase the overall cost of software development. Based on our proposed approach, we develop RM2PT: a tool for generating prototypes from requirements models automatically. A requirements model consists of a use case diagram, a conceptual class diagram, system sequence diagrams for use cases, and the formal contracts of their system operations in OCL (Object Constraint Language). RM2PT can generate executable MVC (Model View Controller) prototypes from requirements models automatically. We evaluate the tool with four case studies. 93.65% of requirement specifications can be generated to the executable Java source code successfully, and only 6.35% are non-executable for our current provided generation algorithm such as sorting and event-call, which can be implemented by developers manually or invoking the APIs of advanced algorithms in Java library. The tool is efficient that the one second generated prototype of a case study requires approximate nine hours manual implementation by skilled programmers. The tool can be downloaded at http://rm2pt.mydreamy.net, and a demo video casting its features is at https://youtu.be/rDdpXsjSq8A

The bipartite consensus of high-order edge dynamics is investigated for coopetition multiagent systems, in which the cooperative and competitive relationships among agents are characterized by positive weight and negative weight, respectively. By mapping the initial graph to a line graph, the distributed control protocol is proposed for the strongly connected, digon sign-symmetric structurally balanced line graph; and then we give sufficient conditions for the third-order multi-gent system to achieve both the bipartite consensus of edge dynamics and the final value of bipartite consensus. By transforming the coefficients of characteristic polynomial from complex domain to real number domain, the sufficient conditions for the bipartite consensus of high-order edge dynamics are also proposed, and the final values of the high-order edge dynamics on multiagent systems are obtained.

Background: Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, excretion prediction models still have limited accuracy. Aim: This study aims to construct an integrated transfer learning and multitask learning approach for developing quantitative structure-activity relationship models to predict four human pharmacokinetic parameters. Methods: A pharmacokinetic dataset included 1104 U.S. FDA approved small molecule drugs. The dataset included four human pharmacokinetic parameter subsets (oral bioavailability, plasma protein binding rate, apparent volume of distribution at steady-state and elimination half-life). The pre-trained model was trained on over 30 million bioactivity data. An integrated transfer learning and multitask learning approach was established to enhance the model generalization. Results: The pharmacokinetic dataset was split into three parts (60:20:20) for training, validation and test by the improved Maximum Dissimilarity algorithm with the representative initial set selection algorithm and the weighted distance function. The multitask learning techniques enhanced the model predictive ability. The integrated transfer learning and multitask learning model demonstrated the best accuracies, because deep neural networks have the general feature extraction ability, transfer learning and multitask learning improved the model generalization. Conclusions: The integrated transfer learning and multitask learning approach with the improved dataset splitting algorithm was firstly introduced to predict the pharmacokinetic parameters. This method can be further employed in drug discovery and development.

We present a formal OpenFlow-based network programming language (OF) including various flow rules, which can not only describe the behaviors of an individual switch, but also support to model a network of switches connected in the point-to-point topology. Besides, a topology-oriented operational semantics of the proposed language is explored to specify how the packet is processed and delivered in the OpenFlow-based networks. Based on the formal framework, we also propose an approach to detect potential security threats caused by the conflict of dynamic flow rules imposed by dynamic OpenFlow applications.

Nowadays, numerous corporations (such as Google, Baidu, etc.) require an efficient and effective search algorithm to crawl out the images with queried objects from databases. Moreover, privacy protection is a significant issue such that confidential images must be encrypted in corporations. Nevertheless, decrypting and then classifying millions of encrypted images becomes a heavy burden to computation. In this paper, we proposed an encrypted image classification framework based on multi-layer extreme learning machine that is able to directly classify encrypted images without decryption. Experiments were conducted on popular handwritten digits and letters databases. Results demonstrate that the proposed framework is secure, efficient and accurate for classifying encrypted images.

Prototyping is an effective and efficient way of requirement validation to avoid introducing errors in the early stage of software development. However, manually developing a prototype of a software system requires additional efforts, which would increase the overall cost of software development. In this paper, we present an approach with a developed tool to automatic generation of prototypes from formal requirements models. A requirements model consists of a use case diagram, a conceptual class diagram, use case definitions specified by system sequence diagrams and the contracts of their system operations. We propose a method to decompose a contract into executable parts and non-executable parts. A set of transformation rules is given to decompose the executable part into pre-implemented primitive operations. A non-executable part is usually realized by significant algorithms such as sorting a list, finding the shortest path or domain-specific computation. It can be implemented manually or by using existing code. A CASE tool is developed that provides an interface for developers to develop a program for each non-executable part of a contract, and automatically transforms the executables into sequences of pre-implemented primitive operations. We have conducted four cases studies with over 50 use cases. The experimental result shows that the 93.65% of requirement specifications are executable, and only 6.35% are non-executable such as sorting and event-call, which can be implemented by developers manually or invoking the APIs of advanced algorithms in Java library. The one second generated the prototype of a case study requires approximate nine hours manual implementation by a skilled programmer. Overall, the result is satisfiable, and the proposed approach with the developed CASE tool can be applied to the software industry for requirements engineering.

As a challenging pattern recognition task, automatic real-time emotion recognition based on multi-channel EEG signals is becoming an important computer-aided method for emotion disorder diagnose in neurology and psychiatry. Traditional machine learning approaches require to design and extract various features from single or multiple channels based on comprehensive domain knowledge. Consequently, these approaches may be an obstacle for non-domain experts. On the contrast, deep learning approaches have been used successfully in many recent literatures to learn features and classify different types of data. In this paper, baseline signals are considered and a simple but effective pre-processing method has been proposed to improve the recognition accuracy. Meanwhile, a hybrid neural network which combines `Convolutional Neural Network (CNN)’ and `Recurrent Neural Network (RNN)’ has been applied to classify human emotion states by effectively learning compositional spatial-temporal representation of raw EEG streams. The CNN module is used to mine the inter-channel correlation among physically adjacent EEG signals by converting the chain-like EEG sequence into 2D-like frame sequence. The LSTM module is adopted to mine contextual information. Experiments are carried out in a segment-level emotion identification task, on the DEAP benchmarking dataset. Our experimental results indicate that the proposed pre-processing method can increase emotion recognition accuracy by 32% approximately and the model achieves a high performance with a mean accuracy of 90.80% and 91.03% on valence and arousal classification task respectively.

This paper takes up the problem of medical resource sharing through MicroService architecture without compromising patient privacy. To achieve this goal, we suggest refactoring the legacy EHR systems into autonomous MicroServices communicating by the unified techniques such as RESTFul web service. This lets us handle clinical data queries directly and far more efficiently for both internal and external queries. The novelty of the proposed approach lies in avoiding the data de-identification process often used as a means of preserving patient privacy. The implemented toolkit combines software engineering technologies such as Java EE, RESTful web services, JSON Web Tokens to allow exchanging medical data in an unidentifiable XML and JSON format as well as restricting users to the need-to-know principle. Our technique also inhibits retrospective processing of data such as attacks by an adversary on a medical dataset using advanced computational methods to reveal Protected Health Information (PHI). The approach is validated on an endoscopic reporting application based on openEHR and MST standards. From the usability perspective, the approach can be used to query datasets by clinical researchers, governmental or non-governmental organizations in monitoring health care and medical record services to improve quality of care and treatment., Extended from our conference paper: arXiv:1501.05916

Model checking as a computer-assisted verification method is widely used in many fields to verify whether a design model satisfies the requirements specifications of the target system. In practice, it is difficult to design a system without the sophisticated requirements analysis. Unlike other model checking tools, the labeled transition system analyzer (LTSA) not only can specify the property specifications of the target system but also provides a structure diagram to specify the system architecture of the requirements model, which can be further used to design the target system. In this paper, we demonstrate the abilities of LTSA shipped with the classic case study of the steam boiler system. In the requirements analysis, the LTSA can specify the cyber and physical components of the target system and interactions between the components and the safety properties of the target system. In system design, the LTSA can automatically generate a start-up design model as the finite state process from the requirements model, and then a design model can be further accomplished by system architects and developers. Finally, the LTSA can automatically verify whether the design model meets the requirements specifications. Our work demonstrates the potential power of model checking tools can be applied and useful in software engineering for requirements analysis, system design, and verification.

Automatic emotion recognition based on EEG is an important issue in Brain-Computer Interface (BCI) applications. In this paper, baseline signals were taken into account to improve recognition accuracy. Multi-Layer Perceptron (MLP), Decision Tree (DT) and our proposed approach were adopted to verify the effectiveness of baseline signals on classification results. Besides, a 3D representation of EEG segment was proposed to combine features of signals from different frequency bands while preserving spatial information among channels. The continuous convolutional neural network takes the constructed 3D EEG cube as input and makes prediction. Extensive experiments on public DEAP dataset indicate that the proposed method is well suited for emotion recognition tasks after considering the baseline signals. Our comparative experiments also confirmed that higher frequency bands of EEG signals can better characterize emotional states, and that the combination of features of multiple bands can complement each other and further improve the recognition accuracy.

We present a technique for the automatic identification of clinically-relevant patterns in medical datasets. To preserve patient privacy, we propose and implement the idea of treating medical dataset as a black box for both internal and external users of data. The proposed approach directly handles clinical data queries on a given medical dataset, unlike the conventional approach of relying on the data de-identification process. Our integrated toolkit combines software engineering technologies such as Java EE and RESTful web services, which allows exchanging medical data in an unidentifiable XML format and restricts users to computed information. Existing techniques could make it possible for an adversary to succeed in data re-identification attempts by applying advanced computational techniques; therefore, we disallow the use of retrospective processing of data. We validate our approach on an endoscopic reporting application based on openEHR and MST standards. The implemented prototype system can be used to query datasets by clinical researchers, governmental or non-governmental organizations in monitoring health care services to improve quality of care.

Notwithstanding the advancement of service computing in recent years, service composition is still main issue in this field. In this paper, the authors present an integrated framework for semantic service composition using answer set programming. Unlike the AI planning approaches of top-down workflow with nested composition and combining composition procedure into service discovery, this proposed framework integrates designed workflow with nested composition. In addition, the planning is based on interface variables with validation through pre and post conditions. Moreover, a unified implementation of service discovery, selection, composition and validation is achieved by answer set programming. Finally, the framework performance is demonstrated by a travel booking example on QWSDataset.

Healthcare information exchange is an important research topic, which can benefit both healthcare providers and patients. In healthcare data sharing, many cloud-based solutions have been proposed, but the trustworthiness of a third-party cloud service is questionable. Recently, blockchain has been introduced in healthcare record sharing, which does not rely on trusting a third party. However, existing approaches only focus on the records collected from medical examination. They are not efficient in sharing data streams continuously generated from sensors and other monitoring devices. Today, IoT devices have been widely deployed and sensors and mobile applications can monitor patients&rsquo, body conditions. The collected data are shared to laboratories and institutions for diagnosis and further study. Moreover, existing approaches are too rigid to efficiently support metadata change. In this paper, an efficient data-sharing scheme is proposed, called MedChain, which combines blockchain, digest chain, and structured P2P network techniques to overcome the above efficiency issues in the existing approaches for sharing both types of healthcare data. Based on MedChain, a session-based healthcare data-sharing scheme is devised, which brings flexibility in data sharing. The evaluation results show that MedChain can achieve higher efficiency and satisfy the security requirements in data sharing.

Refering to single area crawler model based on p2p-chord network, designed and implemented a multi-area crawler model based on own design Skipnet-YL network which based on Skipnet protocol. It use better performance router protocol Skipnet-YL and the idea of SuperNodes and OSPF. Sequentially, it can solve the problem of low performance and the large of communication traffic during increasing nodes. After testing and analysing this model, this paper found out its deficiency, then put forward improved solutions for shortage. Eventually, it looked forward into future work.

With the development of multimedia technology, the rapid increasing usage of large image database becomes possible. To carry out its management and retrieval, Content-Based Image Retrieval (CBIR) is an effective method. This paper shows the advantage of content-based image retrieval system, as well as key technologies. Compare to the shortcoming that only certain one feature is used in the traditional system, this paper introduces a method that combines color, texture and shape for image retrieval and shows its advantage. Then this paper focuses on the feature extraction and representation, several commonly used algorithms and image matching methods.

This paper addresses the challenge of identifying clinically-relevant patterns in medical datasets without endangering patient privacy. To this end, we treat medical datasets as black box for both internal and external users of the data enabling a remote query mechanism to construct and execute database queries. The novelty of the approach lies in avoiding the complex data de-identification process which is often used to preserve patient privacy. The implemented toolkit combines software engineering technologies such as Java EE and RESTful web services, to allow exchanging medical data in an unidentifiable XML format along with restricting users to the need-to-know privacy principle. Consequently, the technique inhibits retrospective processing of data, such as attacks by an adversary on a medical dataset using advanced computational methods to reveal Protected Health Information (PHI). The approach is validated on an endoscopic reporting application based on openEHR and MST standards. The proposed approach is largely motivated by the issues related to querying datasets by clinical researchers, governmental or non-governmental organizations in monitoring health care services to improve quality of care.