Cross Domain Research Articles

SMART-FCD: IOT DATA INTEROPERABILITY USING SENSOR BASED FUZZY LINKED RULES FOR CROSS DOMAIN APPLICATIONS

Internet of Things (IoT) is connected everywhere and enables massive information exchange between objects and people. The unified global IoT must manage a massive amount of data generated by these connected smart which arises the interoperability challenges such as lack of communication protocols, device support, and accepted open standards in smart environments. To combat these issues, a novel Smart-Fuzzy linked rules for Cross Domain application (Smart-FCD) framework is proposed to ensure interoperability by enabling efficient communication and data exchange between multiple platforms and systems. Initially, the heterogenous data from the sensors such as temperature sensors and humidity sensors, and the descriptions are implemented according to the Sensor Measurement List (SenML) language. After composing, semantic modelling will occur which converts the relational data into Resource Description Framework (RDF) format. The Linked Open Vocabulary for the Internet of Things (LOV4IoT) dataset is used to extract interoperable domain knowledge, which is then fed into the related sensor-based fuzzy rules. The IoT preset semantic models which utilise interoperable datasets and domain instances, which are updated via fuzzy association rules. Semantic Web of Things (SWoT) is a technology that assists in creating semantic-based IoT applications, thus IoT developers may use it to create intelligent applications. The sensor data, RDF simulation, evolution time and latency are some of the parameters that are used to evaluate the effectiveness of the proposed Smart-FCD methodology.

Cross-domain collaboration. Lessons learned from three different communities in the Netherlands

Introduction: Primary care in the Netherlands faces major challenges. Health problems are becoming more complex and care is preferably provided in one's own environment. Application of the concept of Positive Health reveals that non-medical care is sometimes the better option. The aim is for people to be self-reliant, if required in collaboration with informal caregivers or applicable citizen initiatives. We call it collaborative self-reliance. These challenges require reorganization towards a health care system in which citizens, health- and welfare professionals and policy makers collaborate. However, the development of such collaboration is context specific and challenging.
 Aim and Methods: We applied participative action research to identify success factors and barriers to develop cross-domain collaborations in care and support networks, including healthcare and welfare professionals and citizens. Three different communities in the south-east part of the Netherlands were included, a small rural village, a medium sized village and a multicultural city district. Researchers joined the three communities to closely follow the developments and provide support from September 2021 to November 2022. Data were collected through document analysis, observation and interviews. Our approach was informed by community development theory. Interviews were thematically analysed using the qualitative analysis software Atlas.ti.
 Results: Preliminary results revealed several important points of attention. As regards their collaboration, networks should formulate an ambition but also concrete objectives. Because the energy is in the action, the group must prevent it from becoming a discussion group only without taking concrete action to achieve its objectives. Nevertheless, regular meetings are necessary for continuation towards the objectives of the network. For the change process, next to a driving force, a liaison is important to facilitate cross domain collaboration. Knowledge and skills in change management improves the efficiency of the process. Furthermore, it is important to consider the ecological level that the network intends or needs to influence to reach your goal. To involve citizens, a sense of community is a prerequisite. In general, successful networks are not discouraged by not achieving a goal, they reflect and persevere. Final results will be presented during the conference.
 Conclusion: The development of care- and support-networks is a complex and lengthy process in which various barriers need to be overcome. Consequently, it requires commitment and perseverance of all participants. A driving force and liaison are important to keep the process going. Making sound collaboration agreements is valuable for sustainable collaboration.
 Implications: It is recommended to be aware of the socio-ecological level on which the network operates. Networks need to identify concrete objectives and invest in commitment of stakeholders to facilitate sustainable collaboration. It is relevant to identify quick wins at the start in order to conserve the energy and commitment of the group.

Finding a way towards Population Health Management on the Central Coast, Australia

Background: To improve the health and wellbeing of the community members on the Central Coast, New South Wales, Australia, this project undertook an assessment of readiness for a Population Health Management (PHM) and neighbourhood based initiative. To do so, it focussed on community needs and strengths and weaknesses of local management on the Central Coast. The Central Coast Local Health District (CCLHD) and Hunter New England and Central Coast Primary Health Network (HNECCPHN) commissioned a joint strategic needs assessment (JSNA). During the project local managers, health professionals, and community members were consulted to gain insight in the readiness and needs of the region. 
 Methods: The JSNA carried out a data driven deep-dive of the health and care needs at a neighbourhood-level with the intent to drive a co-designed intensive place-based population health improvement initiative that optimizes health outcomes, improves access to care and care equity, and reduces total costs to the health system. Supported by the PHM Maturity Index (PHM-MI), the capability across the Central Coast to enable the implementation of PHM was mapped. This allowed gaining insight in the readiness of local management for this pro-active approach. 
 Results: This project is still running and aims to be completed in 2023. Preliminary results of the PHM-MI demonstrate an overall low occurrence of items that support the implementation of PHM. Participants recognized the need and voiced the willingness to work collaboratively. However, they confirmed the absence of a guiding coalition and visionary leadership leading to cross domain collaboration. The major weakness of the Central Coast is the high level bureaucracy and political influence in the health system. This hinders top-level collaboration between multiple organizations, and limits the possibilities of financial changes, the building of an integrated data-infrastructure, and the probability for community ideas to become sustainable. The major strengths of the Central Coast are the strong identity of the community members to the region, the willingness of local managers to focus on the community needs and the availability of data. The project shows that the Central Coast is a region with a lot of hidden potential for a neighbourhood based PHM initiative. 
 Discussion: Using the PHM-MI to map the capability of the Central Coast started the conversation about prerequisites that support a neighbourhood based initiative. Bringing several stakeholders together to participate in the project was challenging, but resulted in new connections between organizations. A next step for the Central Coast is to gain an overview of the most prominent processes in organizational governance, payment streams and budgets, involvement and consultation of community members, and availability of datasets. Therefore, inter- and intraorganizational collaboration is important to bring the hidden strengths on the Central Coast together and build a strong enabling environment to support the growth of the health and wellbeing of the community members on the Central Coast.

Ships Detection on Aerial Imagery using Transfer Learning and Selective Search

The traffic in the water area such as harbor and sea strait is highly important to be monitored because it helps to minimize unwanted ships accident. As a result, we proposed an automatic detection method to localize ships contained in sattelite image. We examine several deep learning method as the classification backbone, namely MobileNetV2, DenseNet121, VGG16, and ResNet50. Afterwards, we employed the trained model for detecting the ships. To make the detection faster, inspite of using a sliding window, we use selective search to sample the object candidates from the given scene. The experiments was done using Shipsnet dataset and tested on aerial images. We also conducted a cross domain evaluation where the images were taken using Google Earth. The results indicate that MobileNetV2 has the best performance on classification and detection tasks. The MobileNetV2 is also able to detect the ships on cross-domain scenarios.

DADIN: Domain Adversarial Deep Interest Network for cross domain recommender systems

The cross-domain recommendation (CDR) model addresses challenges such as data sparsity, the long tail distribution of user–item interactions, and the cold start of items or users. However, solely transferring domain-shared knowledge based on the co-occurrence patterns, without considering user preferences, leads to negative transfer in CDR. To overcome these limitations, we propose an advanced deep learning CDR model called the Domain Adversarial Deep Interest Network (DADIN) aims to facilitate smooth knowledge transfer from the source domain to the target domain and effectively alleviate negative transfer. Firstly, the joint distribution alignment of user preference in DADIN is realized by introducing a skip-connection-based domain agnostic layer, and then the domain classifier is artificially designed to distinguish between the information coming from the source domain or the target domain. Additionally, DADIN combines prediction loss, global domain confusion loss, and intra-class domain confusion losses through the Min-Max game and gradient reverse layer to achieve collaborative optimization. Two real-world experiments show the area under curve (AUC) of DADIN is 0.78 on the Huawei dataset, and it outperforms its competitors by 0.71% on the Amazon dataset, showcasing its state-of-the-art performance. Moreover, our ablation studies further demonstrate that domain adversarial technique increases the AUC by 2.34% on the Huawei dataset and 16.67% on the Amazon dataset, respectively.

Attention guided multi-wavelet adversarial network for cross domain fault diagnosis

Adversarial transfer learning is an effective method for diagnosing rotating machinery faults. However, it does not extract features completely and underutilizes unlabeled target data. Hence, an attention-guided multi-wavelet adversarial network (AMWAN) based on the hybrid metric strategy of a multi-wavelet convolutional feature extractor is proposed. First, hidden fault features in the input data are extracted via multi-wavelet convolution and an attention mechanism. Subsequently, the extracted features are input into the domain discriminator and label classifier. A gradient reversal layer is introduced to map and mix the source- and target- domain samples for feature extraction. Specifically, the k-nearest neighbor is adopted to construct a label propagation model in the source-domain feature layer to obtain pseudo-labels for the target-domain feature data. This extends the labeling information for the target-domain feature data. A hybrid metric based on the maximum mean discrepancy distance and feature cosine metric strategy is introduced in the feature layer for adversarial training, which can significantly enhance the domain adaptive effect and improve the cross-domain fault diagnosis performance of the AMWAN. Experimental validation based on two sets of planetary gearbox datasets indicate that the AMWAN exhibits outstanding fault diagnosis performance under both constant- and variable-speed and -load conditions, i.e., it achieves an average accuracy rate of up to 96.85 %, thus surpassing other methods.

Transfer learning: a cross domain LSTM way towards sustainable power predictive analytics

Transfer learning: a cross domain LSTM way towards sustainable power predictive analytics

A Review on Cross Weather Traffic Scene Understanding Using Transfer Learning for Intelligent Transport System

Intelligent transport systems (ITS) have revolutionized the transportation industry by integrating cutting-edge technologies to enhance road safety, reduce traffic congestion and optimize the transportation network. Scene understanding is a critical component of ITS that enables real-time decision-making by interpreting the environment's contextual information. However, achieving accurate scene understanding requires vast amounts of labeled data, which can be costly and time-consuming. It is quite challenging to Understand traffic scene captured from vehicle mounted cameras. In recent times, the combination of road scene-graph representations and graph learning techniques has demonstrated superior performance compared to cutting-edge deep learning methods across various tasks such as action classification, risk assessment, and collision prediction. It's a grueling problem due to large variations under different illumination conditions. Transfer learning is a promising approach to address this challenge. Transfer learning involves leveraging pre-trained deep learning models on large-scale datasets to develop efficient models for new tasks with limited data. In the context of ITS, transfer learning can enable accurate scene understanding with less data by reusing learned features from other domains.
 This paper presents a comprehensive overview of the application of transfer learning for scene understanding in cross domain. It highlights the benefits of transfer learning for ITS and presents various transfer learning techniques used for scene understanding. This survey paper provides systematic review on cross domain outdoor scene understanding and transfer learning approaches from different perspective, presents information on current state of art and significant methods in choosing the right transfer learning model for specific scene understanding applications.

Erratum to: Reinforcement learning as a basis for cross domain fusion of heterogeneous data

Erratum to: Reinforcement learning as a basis for cross domain fusion of heterogeneous data

XAutn: Blockchain-based cross domain authentication for digital certificates in the education sector

Traditional testimony and electronic endorsements are extremely challenging to uphold and defend, and there is a problem with challenging authentication. The identity of the student is typically not recognized when it comes to requirements for access to a student’s academic credentials that are scattered over numerous sites. This is an issue with cross-domain authentication methods. On the one hand, whenever the volume of cross-domain authentication requests increases dramatically, the response time can become intolerable because of the slow throughput associated with blockchain mechanisms. These systems still do not give enough thought to the cross-domain scenario’s anonymity problem. This research proposes an effective cross-domain authentication mechanism called XAutn that protects anonymity and integrates seamlessly through the present Certificate Transparency (CT) schemes. XAutn protects privacy and develops a fast response correctness evaluation method that is based on the RSA (Rivest, Shamir, and Adleman) cryptographic accumulator, Zero Knowledge Proof Algorithm, and Proof of Continuous work consensus Algorithm (POCW). We also provide a privacy-aware computation authentication approach to strengthen the integrity of the authentication messages more securely and counteract the discriminatory analysis of malevolent requests. This research is primarily used to validate identities in a blockchain network, which makes it possible to guarantee their authenticity and integrity while also increasing security and privacy. The proposed technique greatly outperformed the current methods in terms of authentication time, period required for storage, space for storage, and overall processing cost. The proposed method exhibits a speed gain of authentication of roughly 9% when compared to traditional blockchain systems. The security investigation and results from experiments demonstrate how the proposed approach is more reliable and trustworthy.

Machinery cross domain degradation prognostics considering compound domain shifts

Machinery cross domain degradation prognostics considering compound domain shifts

Cross domain fault diagnosis method based on MLP-mixer network

The quality of rolling bearings determines the safety of mechanical equipment operation, and bearings with more precise structures are prone to damage due to excessive operation. Therefore, cross domain fault diagnosis of bearings has become a research hotspot. To better improve the accuracy of bearing cross domain fault diagnosis, this study proposes two models. One is a cross domain feature extraction model constructed using a mixed attention mechanism, which recognizes and extracts high-level features of bearing faults through channel attention and spatial attention mechanisms. The other is a bearing cross domain fault diagnosis model based on multi-layer perception mechanism. This model takes the feature signals collected by the attention mechanism model as input to identify and align the differences between the source and target domain features, facilitating cross domain transfer of features. The experimental results show that the mixed attention mechanism model has a maximum accuracy of 97.3 % for feature recognition of different faults, and can successfully recognize corresponding signal values. The multi-layer perception model can achieve the highest recognition accuracy of 99.5 % in bearing fault diagnosis, and it can reach a stable state when it iterates to 26, and the final stable loss value is 0.28. Therefore, the two models proposed in this study have good application value.

The perceptron algorithm with uneven margins based transfer learning for turbofan engine fault detection

Aeroengine fault detection is an important means to ensure flight safety. The application premise of data driven fault detection method is that all data come from the same distribution. However, this assumption is invalid in the actual engine fault detection, because the engine state will change with the increase of operating time, and the collected data will also have distribution differences. Due to the high cost of collecting engine data, it is difficult to collect enough data from the current state. Fortunately, transfer learning can transfer data information from other fields to the target field, thus alleviating the problem of data scarcity in the target domain. Therefore, from the idea of transfer learning, this paper proposes a cross domain aeroengine fault detection method, viz. transfer learning based on kernel perception algorithm with uneven margins (TL-KPAUM). The proposed method is divided into two stages. In the first stage, KPAUM is trained using the data in the source domain to extract the information in the source domain. In the second stage, the data in the target domain is used to realize the adaptation to the target domain. Compared with several baseline methods, TL-KPAUM has better performance when the amount of data in the target domain is small. Finally, using the simulation data of turbofan engine, the fault detection experiments of degraded state are designed, and the results show that this method is effective.

Domain Specific and Cross Domain Associations between PASS Cognitive Processes and Academic Achievement.

The purpose of this study was to examine the role of intelligence-operationalized in terms of Planning, Attention, Simultaneous, and Successive (PASS) processing skills-in reading and mathematics. Two hundred and forty-two Grade 6 Greek-speaking students (114 boys and 128 girls, Mage = 135.65 months, SD = 4.12 months) were assessed on PASS processes, speed of processing (Visual Matching), reading (Wordchains and CBM-Maze), and mathematics (Mathematics Achievement Test and Mathematics Reasoning Test). The results of the hierarchical regression analyses showed that, after controlling for family's socioeconomic status and speed of processing, Attention and Successive processing predicted reading and Planning and Simultaneous processing predicted mathematics. Taken together, these findings suggest that different PASS processes may account for individual differences in reading and mathematics.

Autonomous Cross Domain Adaptation Under Extreme Label Scarcity.

A cross domain multistream classification is a challenging problem calling for fast domain adaptations to handle different but related streams in never-ending and rapidly changing environments. Notwithstanding that existing multistream classifiers assume no labeled samples in the target stream, they still incur expensive labeling costs since they require fully labeled samples of the source stream. This article aims to attack the problem of extreme label shortage in the cross domain multistream classification problems where only very few labeled samples of the source stream are provided before process runs. Our solution, namely, Learning Streaming Process from Partial Ground Truth (LEOPARD), is built upon a flexible deep clustering network where its hidden nodes, layers, and clusters are added and removed dynamically with respect to varying data distributions. A deep clustering strategy is underpinned by a simultaneous feature learning and clustering technique leading to clustering-friendly latent spaces. A domain adaptation strategy relies on the adversarial domain adaptation technique where a feature extractor is trained to fool a domain classifier by classifying source and target streams. Our numerical study demonstrates the efficacy of LEOPARD where it delivers improved performances compared to prominent algorithms in 15 of 24 cases. Source codes of LEOPARD are shared in https://github.com/wengweng001/LEOPARD.git to enable further study.

Transfer Discriminant Softmax Regression with Weighted MMD

As an efficient classical machine learning classifier, the Softmax regression uses cross-entropy as the loss function. Therefore, it has high accuracy in classification. However, when there is inconsistency between the distribution of training samples and test samples, the performance of traditional Softmax regression models will degrade. A transfer discriminant Softmax regression model called Transfer Discriminant Softmax Regression with Weighted MMD (TDS-WMMD) is proposed in this paper. With this method, the Weighted Maximum Mean Divergence (WMMD) is introduced into the objective function to reduce the marginal distribution and conditional distribution between domains both locally and globally, realizing the cross domain transfer of knowledge. In addition, to further improve the classification performance of the model, Linear Discriminant Analysis (LDA) is added to the label iteration refinement process to improve the class separability of the designed method by keeping the same kind of samples together and the different kinds of samples repeling each other. Finally, after conducting classification experiments on several commonly used public transfer learning datasets, the results verify that the designed method can enhance the knowledge transfer ability of the Softmax regression model, and deliver higher classification performance compared with other current transfer learning classifiers.

Augmenting hotel performance in Malaysia through big data analytics capability and artificial intelligence capability

PurposeAt the forefront of current research is the investigation of how big data analytics capability (BDAC) and artificial intelligence capability (AIC) can enhance performance in concert. Therefore, current study intended to conduct more deep research into emerging phenomena and attempts to cover the gap by exploring how entrepreneurial orientations (EO) emphasize the use of two emerging capabilities under the moderating role of environmental dynamism which in turn augment co-innovation and hotel performance.Design/methodology/approachData were collected from four-star and five-star hotels located in Kula Lumpur and Langkawi in Malaysia. A total of 260 responses were obtained from IT staff and senior managers with the assistance of a Manpower agency for data analysis. The hypotheses were examined by analyzing the data using PLS-SEM technique through Smart PLS 3 software.FindingsThe result revealed that EO has a positive and significant effect on co-innovation (CIN). Additionally, the BDAC and AIC have been tested and proven to be potential mediators between EO and CIN. Also, environmental dynamism as moderator has positive and significant effect on BDAC and co-innovation performance, however, not significant impact on AIC and co-innovation performance. Lastly, findings displayed positive and significant moderated mediation impact of environmental dynamics on BDAC and CIN with hotel performance, but not significant influence on AIC and co-innovation with hotel performance. For theoretical corroboration of the research findings, the current study integrated EO, resource-based view theory and contingent dynamic capabilities (CDC), because neither single stance can explicate an extant research framework.Practical implicationsThis study anticipated the several implications for the entrepreneurs of hospitality industry. Managers are recommended to invest in the entrepreneurial traits of the employees/organizations and make strategic readjustment of their capabilities for sustained business performance.Originality/valueThe study goes beyond the normal inquiry by investigating moderated mediation impact of environmental dynamism between two emerging capabilities, co-innovation and hotel performance relationships. Another novelty of this study is to culminate the exploitation and adoption of emerging IT-based capabilities in cross domains of management, entrepreneurship, information systems management within the hotel industry.

How to successfully implement population health management: a scoping review

BackgroundDespite international examples, it is unclear for multisector initiatives which want to sustainably improve the health of a population how to implement Population Health Management (PHM) and where to start. Hence, the main purpose of this research is to explore current literature about the implementation of PHM and organising existing knowledge to better understand what needs to happen on which level to achieve which outcome.MethodsA scoping review was performed within scientific literature. The data was structured using Context-Mechanism-Outcome, the Rainbow model of integrated care and six elements of PHM as theoretical concepts.ResultsThe literature search generated 531 articles, of which 11 were included. Structuring the data according to these three concepts provided a framework that shows the skewed distribution of items that influence the implementation of PHM. It highlights that there is a clear focus on normative integration on the organisational level in ‘accountable regional organisation’. There is less focus on the normative integration of ‘cross domain business model’, ‘integrated data infrastructure’, and ‘population health data analytics’, and overall the perspective of citizen and professionals, indicating possible gaps of consideration.ConclusionsA first step is taken towards a practical guide to implement PHM by illustrating the depth of the complexity and showing the partial interrelatedness of the items. Comparing the results with existing literature, the analysis showed certain gaps that are not addressed in practice, but should be according to other frameworks. If initiators follow the current path in literature, they may be missing out on some important components to achieve proper implementation of PHM.

Cross domain fault diagnosis based on generative adversarial networks

Data-driven fault diagnosis utilizing deep learning algorithms is currently a topic of great interest. Without proper training, data-driven models usually fail to generalize on operating conditions different from the ones used in the training set. The majority of domain adaptation research for machinery fault diagnosis focuses on the transfer between limited working conditions for the same machine. In real-life applications, machines operate under a wide range of operating conditions and the data are mostly available for healthy conditions with seldom failures. Hence, models generated from controlled experiments do not usually generalize well under substantial domain shifts. To address this issue, this paper proposes a semi-unsupervised domain adaptation approach for cross-machine fault diagnosis which integrates model optimization and Generative Adversarial Networks (GANs) to bridge the gap between source and target domains. Experiments of transferring between two bearing data sets show that the proposed method is able to effectively train an optimized model that generalizes on both the source and target domains, and train a generator that learns the source domain probability distribution to substitute for larger domain shifts.

An efficient LSTM based cross domain aspect based sentiment analysis (CD-ABSA)

This research study focuses the cross-domain aspect-based sentiment analysis (CD-ABSA) for existing source domain annotation data. The CD-ABSA tries to use the valuable information in a source domain to extract aspect terms and evaluate their sentiment polarities in a target domain. It can considerably increase the usage of the source domain annotation resources while also reducing the workload of newer domain data annotation. one of the main components of the CD-ABSA is aspect extraction. In this paper, we utilized the most common topic modelling techniques: LDA and LSA to extract aspects from the reviews as it does not require labelled data. The topics are extracted from the education domain of the Course and Teacher Performance Evaluation (CTPE) dataset. In this paper, we also evaluated the different hyper-parameters on the CD-ABSA model and selected the best and optimal combination. The proposed methodology train on domain-dependent and independent word embedding that achieves CD-ABSA, in particularly end-to-end fashion. The experiment carries out on Academica dataset, which consists of students’ comments/feedback and SemEval-2014 dataset, which includes laptops and restaurants reviews. The evaluation metrics such as (precision, recall, F1 score and validation Accuracy) is considered while judging the LSTM classifier performance for CD-ABSA as a result.