Knowledge Transfer Scheme Research Articles

Systematic development of an injury and illness prevention programme for athletes with a physical impairment: the TIPAS study

Background/aimThe participation of individuals with physical impairment in sports has numerous benefits, yet there is also the risk of sustaining sport-related injuries or illnesses. Therefore, prevention programmes of these problems...

Knowledge transfer based many-objective approach for finding bugs in multi-path loops

AbstractGenerating test cases is essential for discovering software bugs. However, finding bugs in multi-path loops is challenging, especially when bugs can only be exposed after a specific interleaving execution order. Furthermore, the number of paths increases exponentially when the iteration count increases. It results in running out of resources (e.g., allocated search budget) in existing algorithms for test case generation before finding program bugs. To overcome these challenges and improve the effectiveness of existing algorithms in finding bugs among multi-path loops, we propose a path-oriented test case generation framework to explore loop paths of bounded depth. To fulfill this task, we first present a method that groups loop paths based on their latent similarities. Then, we formulate the problem of generating test cases to cover loop paths as a many-objective optimization one. The many-objective optimization problem is designed to optimize one group of loop paths at a time. Finally, a many-objective test case generation framework is used to generate test cases for covering loop paths. In this framework, a knowledge transfer scheme is incorporated to reuse suitable archived test cases at the start of the search process for a similar group of paths. We have implemented the proposed knowledge transfer scheme with generalized differential evolution 3 (KT-GDE3) and evaluated it with benchmarks from the competition on software verification (SV-COMP16 and SV-COMP21). The experimental results show that KT-GDE3 outperforms alternative search-based test case generation algorithms in bug finding capability for multi-path loops. To evaluate the effectiveness of the proposed knowledge transfer scheme, our approach is compared with the variant without this scheme (called KT-GDE3-unarchived) in the benchmarks. The corresponding experimental results verify our assumption that the knowledge transfer scheme can significantly enhance the optimization process of multi-objective algorithms such as generalized differential evolution when finding bugs in multi-path loops.

An extended weak aggregating algorithm for a two dimensional data-driven multi-stage newsvendor problem

We investigate a multi-stage newsvendor problem with advance purchase discount (APD) in this paper. At the beginning of a stage, the decision maker (DM) makes the advance ordering decision for all the periods in this stage; at the start of every period within the stage, the DM makes the regular ordering decision. In this problem, the only available information we can observe is the past demands. To solve this problem, we extend the weak aggregating algorithm (WAA) with one decision variable, an online learning approach based on the theory of prediction and learning with expert advice, to a two-dimensional problem that involves advance ordering decisions in stages and regular ordering decisions nested in each stage. The difficulty of the problem lies in transferring learned knowledge of demand information from stage to stage. We design a cross-stage knowledge transfer scheme and obtain online ordering solutions for both advance-order and regular-order. We show that our solutions converge to the optimal solutions asymptotically. In addition, we derive theoretical guarantees for total gains in one stage and cumulative gains for all stages in the planning horizon. Through numerical studies, we find that our solutions are competitive to those offered by the best experts in hindsight. Finally, we do the sensitivity analysis to illustrate the effectiveness of our algorithm under different parameter values.

Knowledge Transfer and Reuse: A Case Study of Ai-Enabled Resource Management in RAN Slicing

An efficient resource management scheme is critical to enable network slicing in 5G networks and in envisioned 6G networks, and artificial intelligence (AI) techniques offer promising solutions. Considering the rapidly emerging new machine learning techniques, such as graph learning, federated learning, and transfer learning, a timely survey is needed to provide an overview of resource management and network slicing techniques of AI-enabled wireless networks. This article provides such a survey along with an application of knowledge transfer in radio access network (RAN) slicing. In particular, we first provide some background on resource management and network slicing, and review relevant state-of-the-art AI and machine learning (ML) techniques and their applications. Then, we introduce our AI-enabled knowledge transfer and reuse-based resource management (AKRM) scheme, where we apply transfer learning to improve system performance. Compared with most existing works, which focus on the training of standalone agents from scratch, the main difference of AKRM lies in its knowledge transfer and reuse capability between different tasks. Our paper aims to be a roadmap for researchers to use knowledge transfer schemes in AI-enabled wireless networks, and we provide a case study over the resource allocation problem in RAN slicing.

FedRadar: Federated Multi-Task Transfer Learning for Radar-Based Internet of Medical Things

Owing to increasing connected medical devices and rapid development of deep learning technologies, the Internet of Medical Things (IoMT) has attracted great attention for healthcare monitoring with intelligent sensors. Radar serves as a non-contact healthcare device, continuously measuring human’s vital signs and behavior to provide daily and comprehensive long-term record on health status. However, radar sensor data collected from various users and families usually involve sensitive personal information, while traditional deep learning technologies using IoMT radar data may present high privacy leakage risks. This paper proposes FedRadar, a novel federated multi-task transfer learning framework for radar-based heartbeat rate and activity monitoring in IoMT to solve these challenges. It deals with the decentralized structure, training personalized multi-task models collaboratively, combining the shared relevance knowledge of human’s physiological information while keeping personal radar data locally for privacy protection. First, the multi-task neural network is built on the spatial-temporal radar data to capture the potential relationship and shared representations between human’s vital sign and activity. Furthermore, the federated learning with knowledge transfer scheme is designed to achieve personalized local models by transferring coarse relevant features and keeping fine-grained individual information. Extensive experiments demonstrate the effectiveness and robustness of FedRadar with 2.8% and 2.5% superior than local training model respectively on the accuracy of heartbeat rate estimation and activity classification in realistic constructed radar datasets. In addition, FedRadar is extensible and suitable to continuously monitor multiple health indicators with privacy protection in IoMT. The FedRadar codes and constructed radar datasets are available on https://github.com/bupt-uwb/FedRadar.

Reinforcement learning for energy efficiency improvement in UAV-BS access networks: A knowledge transfer scheme

Reinforcement learning for energy efficiency improvement in UAV-BS access networks: A knowledge transfer scheme

Scene graph descriptors for visual place classification from noisy scene data

In visual robot place recognition (VPR), a scene graph is a rich scene model that can describe the complex contexts in a scene such as the relationships between various types of visual contents including appearance, space, and semantics. However, training an efficient scene graph classifier is not straightforward. Existing approaches typically rely on exhaustive matching between query and database graphs and are not scalable to large-size VPR problems. Our research is motivated by a recent development of the graph convolutional neural network (GCN) as an efficient and discriminative classifier for graph data, and it aims to explore the potential of the GCN as a scene graph classifier. However, unlike several existing GCN applications, no valid scene graph descriptor for a GCN classifier on noisy scene data exists. To address this issue, herein, we propose to train the GCN model in a teacher-to-student knowledge transfer scheme by employing an existing state-of-the-art single-view VPR system as the teacher model. The proposed approach is implemented within a practical VPR framework by combining the best of the following three independent fields: multimodal information retrieval, rank matching, and similarity-based pattern recognition. Experiments using the public NCLT dataset validate the effectiveness of the proposed approach.

Health-guided recipe recommendation over knowledge graphs

While the availability of large-scale online recipe collections presents opportunities for health consumers to access a wide variety of recipes, it can be challenging for them to discover relevant recipes. Whereas most recommender systems are designed to offer selections consistent with users’ past behavior, it remains an open problem to offer selections that can help users’ transition from one type of behavior to another, intentionally. In this paper, we introduce health-guided recipe recommendation as a way to incrementally shift users towards healthier recipe options while respecting the preferences reflected in their past choices. Introducing a knowledge graph (KG) into recommender systems as side information has attracted great interest, but its use in recipe recommendation has not been studied. To fill this gap, we consider the task of recipe recommendation over knowledge graphs. In particular, we jointly learn recipe representations via graph neural networks over two graphs extracted from a large-scale Food KG, which capture different semantic relationships, namely, user preferences and recipe healthiness, respectively. To integrate the nutritional aspects into recipe representations and the recommendation task, instead of simple fusion, we utilize a knowledge transfer scheme to enable the transfer of useful semantic information across the preferences and healthiness aspects. Experimental results on two large real-world recipe datasets showcase our model’s ability to recommend tasty as well as healthy recipes to users.

The effectiveness of a golf injury prevention program (GRIPP intervention) compared to the usual warm-up in Dutch golfers: protocol design of a randomized controlled trial

BackgroundSixty million golfers around the world play golf. Golf injuries are most frequently located in the spine, elbow, wrist, hand and shoulder. Those injuries are often seen in golfers with more playing hours and suboptimal swing biomechanics, resulting in overuse injuries. Golfers who do not perform a warm-up or do not warm-up appropriately are more likely to report an injury than those who do. There are several ways to warm-up. It is unclear, which warm-up is most useful for a golfer to perform. Moreover, there is currently no evidence for the effectiveness of a warm-up program for golf injury prevention. We previously have developed the Golf Related Injury Prevention Program (GRIPP) intervention using the Knowledge Transfer Scheme (KTS). We aim to evaluate the effect of the GRIPP intervention on golf-related injuries. The hypothesis is that the GRIPP intervention program will reduce the number of golf-related injuries.Methods and designThe GRIPP study is a two-armed randomized controlled trial. Twenty-eight golf clubs with 11 golfers per club will be randomly allocated to the intervention or control group. The intervention group will perform the GRIPP intervention program, and the control group will perform their warm-up as usual. The GRIPP intervention is conducted with the Knowledge Transfer Scheme framework, which is a systematic process to develop an intervention. The intervention consists of 6 exercises with a maximum total of 10 min. The primary outcome is the overall prevalence (%) of golf injuries measured with the Oslo Sports Trauma Research Center (OSTRC-H) questions on health problems every fortnight. The secondary outcome measures will be exposure to golf and compliance to the intervention program.DiscussionIn other sports warm-up prevention programs are effective in reducing the risk of injuries. There are no randomized trials on golf injury prevention. Therefore, an individual unsupervised golf athlete intervention program is conducted which reflects the daily practice of predominantly unsupervised exposure of amateur golfers.Trial registrationThe trial is retrospectively (28 October 2021) registered at the Dutch Trial Register: NL9847 (https://trialsearch.who.int).

Privacy preservation of cloud data in business application enabled by multi-objective red deer-bird swarm algorithm

Decision-making is one of the important deals in knowledge transfer and it can be useful for the multi-source domains. Meanwhile, the existing knowledge transfer schemes do not use privacy-preserving techniques for preserving security. This can be a problem for critical domains like financial market forecasting as the misuse of security can lead to legal and financial implications. In recent years, cloud services have revolutionized various technological applications. Cloud computing has become more popular with digital technologies as it provides uninterrupted services like transmission, storage, and intensive computing of data. The architecture of the cloud is also cost-efficient. Besides, various promising services from the cloud, some challenges need to be addressed to secure the privacy of the cloud users as millions of users access its services. Privacy preservation is an important aspect in the field of data mining, and the necessity of securing important data in the cloud from hackers is on the rise. Privacy-preserving data mining algorithms have been analyzed over recent years to provide sufficient solutions for securing the privacy of the data in the cloud. This paper plans to introduce a new hybrid meta-heuristic concept for developing a privacy preservation strategy towards business data under the cloud sector. The main objective of this paper is to design a new hybrid red deer-bird swarm algorithm (RD-BSA) to ensure higher convergence and since the use of control parameters over the solution generation is minimized. The proposed privacy preservation scheme on three financial databases is evaluated with the performance against the existing privacy preservation schemes. Different analyses like statistical, key sensitivity, Known-Plaintext Attack (KPA), and Chosen-Plaintext Attack (CPA) are used for evaluating the efficiency of the algorithm. The comparative analysis of the proposed model over the conventional models demonstrates its effective performance via diverse analysis.

A stacked dense denoising\u2013segmentation network for undersampled tomograms and knowledge transfer using synthetic tomograms

Over recent years, many approaches have been proposed for the denoising or semantic segmentation of X-ray computed tomography (CT) scans. In most cases, high-quality CT reconstructions are used; however, such reconstructions are not always available. When the X-ray exposure time has to be limited, undersampled tomograms (in terms of their component projections) are attained. This low number of projections offers low-quality reconstructions that are difficult to segment. Here, we consider CT time-series (i.e. 4D data), where the limited time for capturing fast-occurring temporal events results in the time-series tomograms being necessarily undersampled. Fortunately, in these collections, it is common practice to obtain representative highly sampled tomograms before or after the time-critical portion of the experiment. In this paper, we propose an end-to-end network that can learn to denoise and segment the time-series’ undersampled CTs, by training with the earlier highly sampled representative CTs. Our single network can offer two desired outputs while only training once, with the denoised output improving the accuracy of the final segmentation. Our method is able to outperform state-of-the-art methods in the task of semantic segmentation and offer comparable results in regard to denoising. Additionally, we propose a knowledge transfer scheme using synthetic tomograms. This not only allows accurate segmentation and denoising using less real-world data, but also increases segmentation accuracy. Finally, we make our datasets, as well as the code, publicly available.

Adversarial Optimization-Based Knowledge Transfer of Layer-Wise Dense Flow for Image Classification

A deep-learning technology for knowledge transfer is necessary to advance and optimize efficient knowledge distillation. Here, we aim to develop a new adversarial optimization-based knowledge transfer method involved with a layer-wise dense flow that is distilled from a pre-trained deep neural network (DNN). Knowledge distillation transferred to another target DNN based on adversarial loss functions has multiple flow-based knowledge items that are densely extracted by overlapping them from a pre-trained DNN to enhance the existing knowledge. We propose a semi-supervised learning-based knowledge transfer with multiple items of dense flow-based knowledge extracted from the pre-trained DNN. The proposed loss function would comprise a supervised cross-entropy loss for a typical classification, an adversarial training loss for the target DNN and discriminators, and Euclidean distance-based loss in terms of dense flow. For both pre-trained and target DNNs considered in this study, we adopt a residual network (ResNet) architecture. We propose methods of (1) the adversarial-based knowledge optimization, (2) the extended and flow-based knowledge transfer scheme, and (3) the combined layer-wise dense flow in an adversarial network. The results show that it provides higher accuracy performance in the improved target ResNet compared to the prior knowledge transfer methods.

Systematic development of an injury prevention programme for judo athletes: the IPPON intervention

ObjectivesTo systematically develop an injury prevention programme in judo and test its feasibility: Injury Prevention and Performance Optimization Netherlands (IPPON) intervention.MethodsWe used the five-step Knowledge Transfer Scheme (KTS) guidelines. In...

Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data

Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue, we present a novel framework named FIL. It provides a heterogeneous knowledge fusion mechanism for cloud robotic systems. Then, a knowledge fusion algorithm in FIL is proposed. It enables the cloud to fuse heterogeneous knowledge from local robots and generate guide models for robots with service requests. After that, we introduce a knowledge transfer scheme to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and efficiency. Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a self-driving task for robots (cars). The experimental results demonstrate that the shared model generated by FIL increases imitation learning efficiency of local robots in cloud robotic systems.

Stakeholder Perspectives to Prevent Soil Organic Matter Decline in Northeastern Italy

A transition from conventional to more sustainable soil management measures (SMMs) is required to reverse the current soil organic matter (SOM) losses in the agroecosystems. Despite the innovations and technologies that are available to prevent SOM decline, top–down knowledge transfer schemes that incentivize a certain measure are often ineffective. Here, we discuss relevant outcomes from a participatory approach where researchers, farmers, practitioners and government officials have discussed opportunities and barriers around SMM application to prevent SOM decline. Within a series of workshops, stakeholders identified, scored, and selected SMMs to field-tests and evaluated the benefits and drawbacks from their application. Results showed that the stakeholders recognized the need for innovations, although they valued the most promising SMM as already available continuous soil cover and conservation agriculture. In contrast, more innovative SMMs, such as biochar use and the variable rate application of organic amendments through precision farming, were the least valued, suggesting that people’s resistance to new technologies is often governed by the socio-cultural perception of them that goes beyond the economic and technological aspects. The valuation of benefits and drawbacks by stakeholders on trialed measures emphasized that stakeholders’ perspective about soil management is a combination of economic, environmental, and socio-cultural aspects, thus corroborating the need for transdisciplinary bottom–up approaches to prevent SOM depletion and increase soil rehabilitation and SOM content.

Densely Distilled Flow-Based Knowledge Transfer in Teacher-Student Framework for Image Classification.

We propose a new teacherstudent framework (TSF)-based knowledge transfer method, in which knowledge in the form of dense flow across layers is distilled from a pre-trained "teacher" deep neural network (DNN) and transferred to another "student" DNN. In the case of distilled knowledge, multiple overlapped flow-based items of information from the pre-trained teacher DNN are densely extracted across layers. Transference of the densely extracted teacher information is then achieved in the TSF using repetitive sequential training from bottom to top between the teacher and student DNN models. In other words, to efficiently transmit extracted useful teacher information to the student DNN, we perform bottom-up step-by-step transfer of densely distilled knowledge. The performance of the proposed method in terms of image classification accuracy and fast optimization is compared with those of existing TSF-based knowledge transfer methods for application to reliable image datasets, including CIFAR-10, CIFAR-100, MNIST, and SVHN. When the dense flow-based sequential knowledge transfer scheme is employed in the TSF, the trained student ResNet more accurately reflects the rich information of the pre-trained teacher ResNet and exhibits superior accuracy to the existing TSF-based knowledge transfer methods for all benchmark datasets considered in this study.

Stimulating injury-preventive behaviour in sports: the systematic development of two interventions

BackgroundIn addition to the beneficial health effects of being active, sports are also associated with a risk of sustaining injuries. To avoid the occurrence of sports injuries, preventive measures can be applied. The aim of the current article is to provide insight into the systematic developmental process of two evidence-based interventions designed to stimulate injury-preventive behaviour in runners and skiers, in which Intervention Mapping (IM) and Knowledge Transfer Scheme (KTS) are used as developmental protocols. However, the ultimate steps in the process are adjusted to meet requirements of the intervention and the target group.MethodsUsing a three-step process, we developed two interventions to stimulate injury-preventive behaviour in runners and skiers. Sports participants, sports experts and behaviour experts contributed throughout steps two and three of the developmental process.ResultsIn step one we started with a problem statement in which we used information about the number and the burden of running-related and skiing-related injuries in the Netherlands. In step two, in-depth research was performed using four research strategies. During this step we tried to answer the following question: Which preventive measures or actions should be executed to prevent what injuries by whom, and how should we do that? A desk research/systematic review of the literature, expert meetings, target user surveys, and target user focus group meetings were conducted. In step three of product development, both interventions were developed. During the developmental process, co-creation sessions with target users were held. Before finalizing the interventions, pre-tests of the interventions were performed with target users.ConclusionsThrough a three-step approach, we developed two interventions to stimulate injury-preventive behaviour in runners and skiers. To develop an intervention that fits the needs of the target population, and will be used by them, it is necessary to involve this population as soon and as much as possible. Several steps in the IM and KTS protocols have thus been adjusted in order to establish an optimal fit between intervention and target group.

Exploiting Web Images for Weakly Supervised Object Detection

In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations that require extensive human labelling. Object detection without bounding box annotations, i.e, weakly supervised detection methods, are still lagging far behind. As weakly supervised detection only uses image level labels and does not require the ground truth of bounding box location and label of each object in an image, it is generally very difficult to distill knowledge of the actual appearances of objects. Inspired by curriculum learning, this paper proposes an easy-to-hard knowledge transfer scheme that incorporates easy web images to provide prior knowledge of object appearance as a good starting point. While exploiting large-scale free web imagery, we introduce a sophisticated labour free method to construct a web dataset with good diversity in object appearance. After that, semantic relevance and distribution relevance are introduced and utilized in the proposed curriculum training scheme. Our end-to-end learning with the constructed web data achieves remarkable improvement across most object classes especially for the classes that are often considered hard in other works.

Knowledge Transfer in the Cultural and Creative Sector: Institutional Aspects and Perspectives from Actors in Selected Atlantic Regions

The 21st century has witnessed a growth in the importance given to the third mission of Higher Education Institutions (HEI). This third mission refers to the socioeconomic engagement with the surrounding social and business fabric, namely in the form of knowledge transfer (KT) schemes and policies. Despite its widely-recognized importance, the Cultural and Creative Sector (CCS) has remained only marginally engaged with HEI, in part due to the lack of explicit policy by public actors to bring the two types of actors together. This article seeks to explore the institutional frameworks that have been developed for knowledge transfer from HEI to the CCS in selected regions of the Atlantic Area. Towards this goal, it first analyses some of the sectoral specificities of the CCS, identifying three feature which distinguish the sector: the entrepreneurial structure and organization of CCS; the type of knowledge, innovation and motivations of firms; and their absence of connections to HEI. The article seeks then to analyze to what extent existing policy on CCS and KT policies in the regions has tackled these specificities, through a qualitative analysis of reports, policy documents, and academic analysis of the regional economies, before proposing a model for understanding KT policy in the CCS sector, which serves as a preliminary line of inquiry into the knowledge relations in the CCS. Finally, these policy concerns are related to the perceptions of CCS practitioners, attempting to understand the primary concerns of these actors according to their regional context. The article highlights the existing disconnect between public policy, the current state of understanding of the CCS and the industry actors, urging for greater research and policy-development to promote innovation and socioeconomic growth.

Empowering the health of retired professional footballers: the systematic development of an After Career Consultation and its feasibility

ObjectivesThis article describes (1) the systematic development of the intervention and (2) the assessment of its feasibility (in terms of relevancy, suitability, satisfaction and added value).MethodsThe intervention was developed based...