Cross-domain Applications Research Articles

Programmatic Pitch

Diffusion models have firmly established their excellence for image generation tasks, as evidenced by the success of renowned models such as DALL-E, Midjourney, and Stable Diffusion. This advanced development of diffusion models for visual content raises an interesting question: can diffusion models be adapted for audio generation tasks? In this study, we introduce a novel diffusion model architecture designed to generate mel spectrograms, visual representations of sound which can subsequently be converted into audible music. Given the exceptional capability of diffusion models to produce high- quality images, their application to mel spectrogram generation is particularly promising. Our proposed diffusion model deviates minimally from the conventional architectures employed for visual content, making this research especially useful for examining the potential for cross-domain application between image and audio generation. The proposed model has been trained on a dataset consisting of over 186 hours of Lofi audio, offering the model diverse samples for generalized learning. However, a combination of research limitations led to subpar results, paving the way for further studies to build on this one.

Rectangling and enhancing underwater stitched image via content-aware warping and perception balancing

Single underwater images often face limitations in field-of-view and visual perception due to scattering and absorption. Numerous image stitching techniques have attempted to provide a wider viewing range, but the resulting stitched images may exhibit unsightly irregular boundaries. Unlike natural landscapes, the absence of reliable high-fidelity references in water complicates the replicability of these deep learning-based methods, leading to unpredictable distortions in cross-domain applications. To address these challenges, we propose an Underwater Wide-field Image Rectangling and Enhancement (UWIRE) framework that incorporates two procedures, i.e., the R-procedure and E-procedure, both of which employ self-coordinated modes, requiring only a single underwater stitched image as input. The R-procedure rectangles the irregular boundaries in stitched images by employing the initial shape resizing and mesh-based image preservation warping. Instead of local linear constraints, we use complementary optimization of boundary-structure-content to ensure a natural appearance with minimal distortion. The E-procedure enhances the rectangled image by employing parameter-adaptive correction to balance information distribution across channels. We further propose an attentive weight-guided fusion method to balance the perception of color restoration, contrast enhancement, and texture sharpening in a complementary manner. Comprehensive experiments demonstrate the superior performance of our UWIRE framework over state-of-the-art image rectangling and enhancement methods, both in quantitative and qualitative evaluation.

PopBERT. Detecting Populism and Its Host Ideologies in the German Bundestag

Abstract The rise of populism concerns many political scientists and practitioners, yet the detection of its underlying language remains fragmentary. This paper aims to provide a reliable, valid, and scalable approach to measure populist rhetoric. For that purpose, we created an annotated dataset based on parliamentary speeches of the German Bundestag (2013–2021). Following the ideational definition of populism, we label moralizing references to “the virtuous people” or “the corrupt elite” as core dimensions of populist language. To identify, in addition, how the thin ideology of populism is “thickened,” we annotate how populist statements are attached to left-wing or right-wing host ideologies. We then train a transformer-based model (PopBERT) as a multilabel classifier to detect and quantify each dimension. A battery of validation checks reveals that the model has a strong predictive accuracy, provides high qualitative face validity, matches party rankings of expert surveys, and detects out-of-sample text snippets correctly. PopBERT enables dynamic analyses of how German-speaking politicians and parties use populist language as a strategic device. Furthermore, the annotator-level data may also be applied in cross-domain applications or to develop related classifiers.

Edge Computing: Opportunities and Challenges

Edge computing has emerged as an innovative paradigm, promising to reshape the landscape of computational processing by bringing data closer to the source of generation, namely Internet of Things (IoT) devices. As the proliferation of IoT devices surges, so does the need for efficient, low-latency processing. Edge computing addresses these demands by decentralizing computational tasks, optimizing bandwidth, and ensuring rapid data processing. This paper delves into the nuances of edge computing, highlighting its distinct advantages, particularly in latency reduction and bandwidth conservation. However, with these opportunities come challenges, notably in the domain of security. Through a systematic review and simulation-based experimentation, this research affirms the transformative potential of edge computing, while also underscoring the need for robust security frameworks. The study concludes with a forward-looking perspective, emphasizing areas of future research including security enhancements, integration with 5G technology, energy-efficient architectures, and cross-domain applications.

Advancing in RGB-D Salient Object Detection: A Survey

The human visual system can rapidly focus on prominent objects in complex scenes, significantly enhancing information processing efficiency. Salient object detection (SOD) mimics this biological ability, aiming to identify and segment the most prominent regions or objects in images or videos. This reduces the amount of data needed to process while enhancing the accuracy and efficiency of information extraction. In recent years, SOD has made significant progress in many areas such as deep learning, multi-modal fusion, and attention mechanisms. Additionally, it has expanded in real-time detection, weakly supervised learning, and cross-domain applications. Depth images can provide three-dimensional structural information of a scene, aiding in a more accurate understanding of object shapes and distances. In SOD tasks, depth images enhance detection accuracy and robustness by providing additional geometric information. This additional information is particularly crucial in complex scenes and occlusion situations. This survey reviews the substantial advancements in the field of RGB-Depth SOD, with a focus on the critical roles played by attention mechanisms and cross-modal fusion methods. It summarizes the existing literature, provides a brief overview of mainstream datasets and evaluation metrics, and quantitatively compares the discussed models.

A novel zero-shot learning approach for cross-domain fault diagnosis in high-voltage circuit breakers

High-voltage circuit breakers (HVCBs) are crucial for power system reliability, yet diagnosing their mechanical failures is a significant challenge due to their complex design and unique operating conditions, especially when facing new, unseen fault types. To address this challenge, we propose a novel zero-shot HVCB fault diagnosis method, named X-SAM, leveraging the Xception network and self-attention mechanism (SAM). X-SAM aims to identify new, unseen fault classes solely using known class fault samples during the training phase. X-SAM innovatively combines adaptive feature extraction from multi-source signals and a novel attribute learning system that maps these features to a universal set of fault attributes. This enables the diagnosis of new fault types by analyzing the similarity between predicted attribute vectors and a predefined attribute matrix. Demonstrated through zero-shot diagnosis tasks on multiple HVCBs, X-SAM not only successfully identifies unseen faults using limited data but also paves the way for cross-domain applications, offering a significant advancement in HVCB and electrical equipment fault diagnosis.

Screening of broad-host expression promoters for shuttle expression vectors in non-conventional yeasts and bacteria

BackgroundNon-conventional yeasts and bacteria gain significance in synthetic biology for their unique metabolic capabilities in converting low-cost renewable feedstocks into valuable products. Improving metabolic pathways and increasing bioproduct yields remain dependent on the strategically use of various promoters in these microbes. The development of broad-spectrum promoter libraries with varying strengths for different hosts is attractive for biosynthetic engineers.ResultsIn this study, five Yarrowia lipolytica constitutive promoters (yl.hp4d, yl.FBA1in, yl.TEF1, yl.TDH1, yl.EXP1) and five Kluyveromyces marxianus constitutive promoters (km.PDC1, km.FBA1, km.TEF1, km.TDH3, km.ENO1) were selected to construct promoter-reporter vectors, utilizing α-amylase and red fluorescent protein (RFP) as reporter genes. The promoters' strengths were systematically characterized across Y. lipolytica, K. marxianus, Pichia pastoris, Escherichia coli, and Corynebacterium glutamicum. We discovered that five K. marxianus promoters can all express genes in Y. lipolytica and that five Y. lipolytica promoters can all express genes in K. marxianus with variable expression strengths. Significantly, the yl.TEF1 and km.TEF1 yeast promoters exhibited their adaptability in P. pastoris, E. coli, and C. glutamicum. In yeast P. pastoris, the yl.TEF1 promoter exhibited substantial expression of both amylase and RFP. In bacteria E. coli and C. glutamicum, the eukaryotic km.TEF1 promoter demonstrated robust expression of RFP. Significantly, in E. coli, The RFP expression strength of the km.TEF1 promoter reached ∼20% of the T7 promoter.ConclusionNon-conventional yeast promoters with diverse and cross-domain applicability have great potential for developing innovative and dynamic regulated systems that can effectively manage carbon flux and enhance target bioproduct synthesis across diverse microbial hosts.Graphical

Exploring graph learning techniques for enhancing cross-domain applications in computer vision and natural language processing

With the rapid development of artificial intelligence, graph learning technology has become a research hotspot because of its unique data processing ability. This paper discusses the application of graph learning technology in computer vision (CV) and natural language processing (NLP), especially, it is applied to image segmentation and recognition, visual relationship detection, dynamic scene understanding, semantic role labeling and knowledge map enhancement. The graph neural network (GNN) can effectively learn the deep features of image or text data by defining pixels or hyperpixels as nodes and constructing the edges between nodes according to the spatial proximity or similarity between pixels. This paper also discusses the application of graph learning technology in improving model interpretability, including feature relation visualization, error analysis and diagnosis, and model decision path interpretation. By comparing the application effects of different graph learning models and algorithms, this paper aims to provide reference and inspiration for the follow-up research and application.

Adaptive fusion transfer learning-based digital multitwin-assised intelligent fault diagnosis

With the development of digital twin technology, mechanical failures can be more comprehensively described through the interaction between sensors and twin models, which thereby demonstrate significant potential in fault diagnosis. However, due to the limitations of modeling methods, digital twin model construction poses challenges and exhibits poor generalization, making it difficult to apply across domains. To address these issues, this paper proposes a digital multitwin fusion diagnostic algorithm based on transfer learning. The digital multitwin comprise the source domain mechanistic twin, the target domain distributional feature 1D Auxiliary Classifier GAN (1D-ACGAN) twin, and the target domain time-series feature shared weight stacking LSTM (SWSLSTM) twin. First, based on the fault features collected by multiple sensors in the mechanism twin, a multichannel, multiscale mid-fusion diagnostic network is constructed. Second, the network is hierarchically transferred to the target domain network using a frozen transfer technique, automatically finding the optimal network parameters. Furthermore, to enhance the data quality, a data twin composed of the SWSLSTM twin and 1D-ACGAN twin is proposed to capture the dependency relationships of target domain data features. Finally, the migrated network adaptively adjusts the generated samples of the data twin based on the designed indicators, achieving high-precision cross-domain application of the multitwin diagnostic model. The proposed algorithm has been validated utilising data from triple-piston pumps and openly accessible bearing datasets, achieving diagnostic accuracies of 91.6% and 95.28%, respectively. These results substantiate the efficacy of the algorithm, demonstrating its superior generalisation capability and robustness in comparison to extant classical methodologies.

BOTSH: Towards aligning semantic web of things with building ontologies

The W3C linked building data group is working on modeling the information for integrating building information with building life cycle data using Semantic Web technologies. The community has proposed a set of semantic models such as ifcOWL and Building Topology Ontology (BOT), to model various applications across Architecture, Engineering, Construction, and Operation (AECO) domain. On the other hand, the Semantic Web of Things (SWoT) group proposed standard semantic models such as M3-lite and BOSH ontologies for describing the sensor networks, observations, and sensor measurements. Both the aforementioned domains have their own siloed applications and with the evolution of the smart home domain, there is a need to combine the knowledge of building information with the sensor knowledge to develop cross-domain applications. However, in order to develop such downstream applications leveraging advantages from both domains requires interoperable knowledge. This paper proposes an interoperable ontology, Building Topology Ontology for Smart Homes (BOTSH), with the aim of aligning the building domain with sensors domain semantic models. The BOTSH ontology facilitates capturing knowledge from both domains and helps in developing cross-domain applications. The potential of the proposed model was demonstrated using a real-life building model based on the competency questions framed by the domain experts.

Shape-aware speckle matching network for cross-domain 3D reconstruction

The learning-based binocular 3D reconstruction method outperforms traditional vision algorithms in terms of precision and efficiency. However, in some cross-domain scenes, the precision of the well-trained network drastically decreases when handling samples in diverse contexts. This paper proposes an end-to-end shape-aware speckle matching network (SSMNet) that combines shape-mask information to achieve improved precision and completeness of disparity calculation in cross-domain applications. The cascade attention mechanism is inserted in the feature extraction stage to concentrate on valuable regions. The shape-aware module is designed to learn additional shape contour information, and multiscale features are integrated simultaneously to construct the cost-volume for the subsequent lightweight 3D aggregation. In addition, instance normalization is adopted to guarantee style migration, and a hybrid loss function is used to supervise the learning process. Furthermore, a high-precision binocular speckle dataset is built, including training and testing sets in different distributions. Extensive quantitative and qualitative experiments demonstrate that SSMNet enhances cross-domain capability and achieves state-of-the-art performance. Measurement precision evaluation illustrates that the proposed method can realize the desired highly precise 3D shape measurement in a real industrial scenario.

Multi-Scale Cross-Attention Fusion Network Based on Image Super-Resolution

In recent years, deep convolutional neural networks with multi-scale features have been widely used in image super-resolution reconstruction (ISR), and the quality of the generated images has been significantly improved compared with traditional methods. However, in current image super-resolution network algorithms, these methods need to be further explored in terms of the effective fusion of multi-scale features and cross-domain application of attention mechanisms. To address these issues, we propose a novel multi-scale cross-attention fusion network (MCFN), which optimizes the feature extraction and fusion process in structural design and modular innovation. In order to make better use of the attention mechanism, we propose a Pyramid Multi-scale Module (PMM) to extract multi-scale information by cascading. This PMM is introduced in MCFN and is mainly constructed by multiple multi-scale cross-attention modules (MTMs). To fuse the feature information of PMMs efficiently in both channel and spatial dimensions, we propose the cross-attention fusion module (CFM). In addition, an improved integrated attention enhancement module (IAEM) is inserted at the network’s end to enhance the correlation of high-frequency feature information between layers. Experimental results show that the algorithm significantly improves the reconstructed images’ edge information and texture details, and the benchmark dataset’s performance evaluation shows comparable performance to current state-of-the-art techniques.

Research on cross-field applications and future prospects of intelligent sensors

The Internet of Things (IoT) has transformed daily life through enhanced internet and communication technologies. Intelligent sensors, like temperature and humidity sensors, have revolutionized smart homes, enabling remote control and enhancing comfort. In agriculture, these sensors monitor soil moisture and crop conditions, optimizing farming practices for increased yields and sustainability. Healthcare benefits from the IoT with sensors in medical devices and wearables, offering real-time patient monitoring and cost reduction. Logistics employs intelligent sensors to track goods, boosting supply chain efficiency. Projects like IoT-based road analysis systems and pest monitoring exemplify data collection and intelligent decision-making, benefiting urban management and agriculture. It can be seen that intelligent sensors have an irreplaceable role in the Internet of Things, so this paper will introduce the technology and working principles of intelligent sensors and discuss the cross-domain applications and future expectations of intelligent sensors. Through literature analysis, it can be concluded that after the intelligent sensor receives the external signal, it will convert the signal into a physical signal related to the measured parameters and process, store, and communicate it so as to realize the detection, control, and data transmission of the environment. This means that intelligent sensors can be widely used in industrial production, environmental monitoring, medical health, and other fields.

Deep learning integrated Bayesian health indicator for cross-machine health monitoring

Constructing a good health indicator (HI) plays a key role in machinery health monitoring. However, due to the training dataset dependency, most conventional deep-learning-based HIs exhibit inconsistent HI scales and limited cross-domain applicability. This study proposes a deep learning integrated Bayesian health indicator (DBHI) to quantify and evaluate system health states in cross-domain applications accurately. The construction of the DBHI comprises two steps: probability space mapping and probabilistic inference. In the first step, the degradation features are extracted from the data and mapped into a probability space by the proposed adversarial autoencoder model. In the second step, the DBHI is calculated by evaluating the relative risk of the current state based on Bayes’ theorem. The effectiveness of the proposed DBHI was validated on two run-to-failure degradation test datasets. In a cross-domain application, the proposed DBHI achieved good performance without retraining compared to other deep learning-based methods that showed invalid results. The proposed DBHI addresses the limitations of conventional deep-learning-based HIs and provides a more reliable and consistent measure of system health, even in a cross-domain application.

Energy Management System of Luminosity Controlled Smart City Using IoT

INTRODUCTION: With the escalating rates of urbanization, there is a pressing need for enhanced urban services. The concept of smart cities, leveraging digital technologies, offers a promising solution to elevate urban living. The integration of Internet-of-Things (IoT) in urban infrastructure, particularly on highways, opens avenues for novel services and cross-domain applications through Information and Communication Technologies. However, the efficient functioning of an IoT-enabled smart city necessitates careful energy resource management.
 OBJECTIVES: Propose a Highway Lighting System (HWLS) integrating IoT technologies to enhance urban services, focusing on significant energy savings and real-time environmental parameter monitoring.
 METHODS: To achieve the objective of enhancing urban services through the proposed Highway Lighting System (HWLS), the system was designed and implemented by integrating cutting-edge sensors, communication links, and the Blynk IoT app. The deployment involved incorporating IoT technologies for real-time monitoring of air quality, air moisture, and soil moisture, alongside a fault identification system using GSM and GPS modules.
 RESULTS: The proposed HWLS demonstrates significant energy savings, consuming only 37.6% of the original power consumption. The incorporation of IoT technologies facilitates real-time monitoring of environmental parameters, enabling informed decision-making for urban service optimization. The fault-finding system, utilizing GSM and GPS modules, enhances the reliability of the lighting system.
 CONCLUSION: In conclusion, the Highway Lighting System (HWLS) represents a novel approach to smart city infrastructure, particularly in the context of urban lighting. The integration of IoT technologies not only contributes to energy savings but also enhances the overall efficiency of urban services. The proposed system's ability to monitor environmental parameters and identify faults demonstrates its potential for sustainable urban development and improved quality of life.

The C&C² Approach as a Thinking Tool in Mechatronic Systems

In recent times, interest in cross-domain system modeling has seen a significant increase. Despite the proven success of the Contact and Channel Approach (C&C2-Approach) in mechanical system modeling, a procedure for cross-domain applications has been largely absent. In this research, we discuss how mechatronic systems can be modeled with the C&C2-Approach. Based on extensive literature research, which allowed us to identify cross-domain reference models, we are introducing the integration of bond graphs into the C&C2-Approach. The principles of bond graph theory make it possible to represent embodiment function relations (EFRs) in non-mechanical domains. For this purpose, only a few extensions to the key elements of the C&C2-Approach are required: On the one hand, the information about the predominant direction of the energy flow is integrated into the C&C2-Model, while, on the other hand, we add the information about whether the EFR is static or dynamic. These adaptations offer the further possibility of building a bridge to mathematical models. At this point, a bond graph can be derived from the C&C2-Model and used to analyze the systems’ behavior in a simulation. This research therefore supports developers in modeling mechatronic systems and enables simulations at an early stage of product development.

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 Applications of MLOps: From Healthcare to Finance

In today's digital era, the significance of data cannot be overstated. It embodies the factual and numerical essence of our everyday transactions, arriving not just statically but dynamically, in the form of data streams. These streams constitute an influx of limitless, continuous, and swift information, particularly prominent in sectors like healthcare. However, navigating this torrent of data presents formidable challenges. The sheer volume, pace, and variety make processing data streams exceedingly complex. Moreover, the task of classifying data streams is compounded by the phenomenon of concept drift, where the underlying statistical characteristics of the target variable undergo unexpected changes, especially noticeable in supervised learning scenarios.Addressing these challenges head-on, our research delves into various manifestations of concept drift within healthcare data streams. We offer an overview of established statistical and machine learning techniques tailored to tackle concept drift. Furthermore, we underscore the efficacy of deep learning algorithms in detecting concept drift and elucidate the diverse healthcare datasets employed in this endeavor.

Learning efficacy of understanding by design-Internet of Things (UbD-IoT) education integrated with design thinking and computational thinking

PurposeThe study integrated understanding by design-Internet of Things (UbD-IoT) education with design thinking and computational thinking to plan and design an IoT course. Cross-domain application examples were employed to train students in problem-understanding, deep thinking and logical design for IoT applications.Design/methodology/approachIn this study, the UbD model was integrated with design thinking and computational thinking in the planning and design of an IoT course. The examples of cross-domain applications were used to train students to understand a problem by engaging themselves in deep thinking and helping them think and design logically for an IoT application.FindingsThe UbD-IoT learning design greatly decreased students' overall cognitive load. UbD-IoT learning has a significant impact on the performance of computational thinking in problem-solving and problem-understanding. The impact of UbD-IoT learning on logical thinking and program learning cognition in students needs to be verified.Originality/valueThe results of this study have shown that the UbD model is effective in reducing the cognitive load of a learning course and also strengthens T-competencies in the lateral skills of computational thinking, critical problem-solving, logical thinking and creative thinking.

ResMon: Domain-Adaptive Wireless Respiration State Monitoring via Few-Shot Bayesian Deep Learning

Under the outbreak of the COVID-19 pandemic, respiration state monitoring plays an important role in assisting respiratory disease diagnosis and treatment. Thanks to the non-intrusive nature and low deployment cost, Wi-Fi based wireless respiration state monitoring methods have gained increasing popularity. By analyzing the variation of channel state information (CSI) of Wi-Fi signals, the respiration states of a target person under the wireless coverage, such as cough, sneeze, and yawn, can be accurately detected. A major problem of the current wireless respiration state monitoring methods is being overly domain-dependent. That is, a sensing algorithm fine-tuned to a specific device placement and background setting (i.e., a domain) can result in drastic drop in detection accuracy when applied to a dissimilar new domain. To enhance the robustness of wireless sensing and reduce the sensing cost across different domains, we propose in this paper a domain-adaptive Respiration state Monitoring system (ResMon) that achieves highly accurate cross-domain detection performance while requiring very limited labeled samples in the new domain. In a nutshell, the proposed ResMon consists of a source domain meta-training stage and a target domain meta-testing stage. In the meta-training stage, we leverage the rich source domain labeled dataset to train an embedding model as a feature extractor of high-dimensional CSI data measurements. In particular, we apply the statistical Bayesian deep learning technique to improve the generalization performance of the embedding model in cross-domain applications. In the meta-testing stage, we combine the embedding model with a few-shot learning technique to train a domain-specific classifier using very limited labeled samples in the target domain. Experiment results show that the proposed ResMon can achieve on average 87.26% cross-domain detection accuracy in a 4-class respiration state classification task using only 5 labeled samples per class, which significantly outperforms the considered benchmark methods.