Model-based Techniques Research Articles

Research on BP neural network model-based data mining technique in KOL identification

Abstract. Accompanied by the development of artificial intelligence industry, to play the data value of web crawler technology has been the focus of research in the field of computer network and data science, and the data mining technology based on artificial neural network intelligent algorithm is widely used. In view of this, this paper takes the BP neural network data mining technology, which has excellent nonlinear mapping capability, parallel processing capability and fault tolerance and is widely used, as the basis, and integrates the methods and ideas of data mining into the mining of data laws in the field of KOL identification of key opinion leaders, with a view to finding valuable intrinsic laws and relationships between the mining of web crawler technology and the identification of KOL features. The research content of this paper mainly includes two aspects of research work, the design of high-performance data mining technology and the actual work in the field of KOL recognition. On the one hand, this paper comprehensively describes the basic theory and methods of data mining, and focuses on the in-depth analysis and elaboration of BP neural network-based data mining technology on the basis of understanding and analyzing a variety of data mining technologies. On the other hand, this paper aims to solve the problem of bias in the prediction of traditional KOL model and design the experimental method of KOL recognition by BP neural network algorithm.

Blockchain-Enhanced Machine Learning for Robust Detection of APT Injection Attacks in the Cyber-Physical Systems

Cyber-Physical Systems (CPS) have become a research hotspot due to their vulnerability to stealthy network attacks like ZDA and PDA, which can lead to unsafe states and system damage. Recent defense mechanisms for ZDA and PDA often rely on model-based observation techniques prone to false alarms. In this paper, we present an innovative approach to securing CPS against Advanced Persistent Threat (APT) injection attacks by integrating machine learning with blockchain technology. Our system leverages a robust ML model trained to detect APT injection attacks with high accuracy, achieving a detection rate of 99.89%. To address the limitations of current defense mechanisms and enhance the security and integrity of the detection process, we utilize blockchain technology to store and verify the predictions made by the ML model. We implemented a smart contract on the Ethereum blockchain using Solidity, which logs the input features and corresponding predictions. This immutable ledger ensures the integrity and traceability of the detection process, mitigating risks of data tampering and reducing false alarms, thereby enhancing trust in the system's outputs. The implementation includes a user-friendly interface for inputting features, a backend for data processing and model prediction, and a blockchain interaction module to store and verify predictions. The integration of blockchain with Machine learning enhances both the precision and resilience of APT detection while providing an additional layer of security by ensuring the transparency and immutability of the recorded data. This dual approach represents a substantial advancement in protecting CPS from sophisticated cyber threats.

Questionnaire surveys to investigate marine mammal fisheries bycatch: systematic review and best practice

Bycatch is the most significant threat to marine mammals globally. There are increasing requirements for national governments to fulfil their obligations to international agreements and treaties to assess fisheries catch and bycatch of non-target species. Questionnaire surveys represent one low-cost method to collect data to estimate fisheries catch and bycatch of vulnerable species including marine mammals. Questionnaire surveys can be particularly advantageous when bycatch is being investigated on large spatial and temporal scales, or in data-poor areas. This review aims to provide the necessary guidance required to design and conduct questionnaire studies investigating marine mammal bycatch. To do so, a systematic review was conducted of the methods used in 91 peer-reviewed or grey literature questionnaire studies from 1990 to 2023 investigating marine mammal bycatch. Literature was searched, screened, and analysed following the RepOrting standards for Systematic Evidence Syntheses (ROSES) protocols. A narrative synthesis and critical evaluation of the methods used were conducted and best practice recommendations are proposed. The recommendations include suggestions for how to generate representative samples, the steps that should be followed when designing a questionnaire instrument, how to collect reliable data, how to reduce under-reporting and interviewer bias, and how weighting or model-based bycatch estimation techniques can be used to reduce sampling bias. The review’s guidance and best practice recommendations provide much-needed resources to develop and employ questionnaire studies that produce robust bycatch estimates for marine mammal populations where they are currently missing. Recommendations can be used by scientists and decision-makers across the globe. Whilst the focus of this review is on using questionnaires to investigate marine mammal bycatch, the information and recommendations will also be useful for those investigating bycatch of any other non-target species.

Ensemble of hybrid model based technique for early detecting of depression based on SVM and neural networks

The prevalence of depression has increased dramatically over the last several decades: it is frequently overlooked and can have a significant impact on both physical and mental health. Therefore, it is crucial to develop an automated detection system that can instantly identify whether a person is depressed. Currently, machine learning (ML) and artificial neural networks (ANNs) are among the most promising approaches for developing automated computer-based systems to predict several mental health issues, such as depression. This study propose an ensemble of hybrid model-based techniques that aims to build a strong detection model that considers many psychological and sociodemographic characteristics of an individual to detect whether a person is depressed. Support vector machines (SVM) and multilayer perceptrons (MLP) are the two fundamental methods used to construct the suggested ensemble approach. The hybrid DeprMVM served as a meta-learner. In this study, the hybrid DeprMVM is a level-1 learner, whereas the SVM and MLP networks are level-0 learners. After the classifiers are trained and tested at level 0, their outputs are based on both the independent and dependent variables in the new data set that was used to train the meta-classifier. The training data class imbalance was reduced by applying the synthetic minority oversampling technique (SMOTE) and cluster sampling together, which improved the accuracy for detecting depression. Additionally, it can effectively reduce the risk of over-fitting from simply duplicating data points. To further confirm the effectiveness of the proposed method, various performance evaluation metrics were calculated and compared with previous studies conducted on this specific dataset. In conclusion, among all the techniques for identifying depression, the suggested ensemble approach had the best accuracy, at 99.39%, and an F1-score of 99.51%.

A Koopman-based residual modeling approach for the control of a soft robot arm

Soft robots are challenging to model and control due to their poorly defined kinematics and nonlinear dynamics. Recently, Koopman operator theory has been shown capable of constructing control-oriented soft robot models from data. However, building these models requires extensive data collection and they do not necessarily generalize well outside of the training observations. This paper presents a more data-efficient and generalizable approach to soft robot modeling that first identifies a physics-based Koopman model then supplements it with a data-driven residual Koopman model. The resulting combined model is linear and thus compatible with real-time model-based control techniques such as Model Predictive Control (MPC). The efficacy of the approach is demonstrated on several simulated systems and on a real soft robot arm, where it is shown to generate models that are more accurate than purely physics-based models and require less data to construct than purely data-driven models. Using a model-based controller, the soft arm is able to successfully track end effector trajectories, perform a pick-and-place task, and write on a dry-erase board, showcasing the applicability of this framework to increase the capabilities of soft robotic systems.

Motor Fault Detection and Isolation for Multi-Rotor UAVs Based on External Wrench Estimation and Recurrent Deep Neural Network

AbstractFast detection of motor failures is crucial for multi-rotor unmanned aerial vehicle (UAV) safety. It is well established in the literature that UAVs can adopt fault-tolerant control strategies to fly even when losing one or more rotors. We present a motor fault detection and isolation (FDI) method for multi-rotor UAVs based on an external wrench estimator and a recurrent neural network composed of long short-term memory nodes. The proposed approach considers the partial or total motor fault as an external disturbance acting on the UAV. Hence, the devised external wrench estimator trains the network to promptly understand whether the estimated wrench comes from a motor fault (also identifying the motor) or from unmodelled dynamics or external effects (i.e., wind, contacts, etc.). Training and testing have been performed in a simulation environment endowed with a physic engine, considering different UAV models operating under unknown external disturbances and unexpected motor faults. To further assess this approach’s effectiveness, we compare our method’s performance with a classical model-based technique. The collected results demonstrate the effectiveness of the proposed FDI approach.

Sex-Based Differences and Asymmetry in Hip Kinematics During Unilateral Extension From Deep Hip Flexion.

The purpose of this study was to identify side-to-side and sex-based differences in hip kinematics during a unilateral step-up from deep flexion. Twelve (eight men, four women) asymptomatic young adults performed a step ascent motion while synchronized biplane radiographs of the hip were collected at 50 images per second. Femur and pelvis position were determined using a validated volumetric model-based tracking technique that matched digitally reconstructed radiographs created from subject-specific computed tomography (CT) bone models to each pair of synchronized radiographs. Hip kinematics and side-to-side differences were calculated and a linear mixed effects model evaluated sex-based differences. Women were on average 10.2 deg more abducted and 0.2 mm more medially translated than men across the step up motion (p < 0.001). Asymmetry between hips was up to 14.1 ± 12.1 deg in internal rotation and 1.3 ± 1.4 mm in translation. This dataset demonstrates the inherent asymmetry during movements involving unilateral hip extension from deep flexion and may be used provide context for observed kinematics differences following surgery or rehabilitation. Previously reported kinematic differences between total hip arthroplasty and contralateral hips may be well within the natural side-to-side differences that exist in asymptomatic native hips.

ANALYSIS OF CONTENT RECOMMENDATION METHODS IN INFORMATION SERVICES

The object of the research is the process of selecting a content recommendation method in information services. The study's relevance stems from the rapid development of informational and entertainment resources and the increasing volume of data they operate on, thus prompting the utilisation of recommendation systems to maintain user engagement. Considering the different types of content, it is necessary to address the problem of data filtration based on their characteristics and user preferences. To solve this task, we analysed content-based and collaborative filtering methods using various techniques (model-based, memory-based, and hybrid collaborative filtering techniques), knowledge-based filtering, and hybrid filtering methods. Considering each method's advantages and disadvantages, we chose a hybrid method using model-based collaborative filtering and content-based filtering for the future development of our universal recommendation system.

Hyperspectral anomaly detection based on weighted low-rank sparse dictionary learning

The geometric model-based hyperspectral anomaly detection techniques have garnered a lot of interest recently. These methods are predicated on the assumption that the background can be represented by a dictionary of spectral vectors, but the anomaly cannot. Building an objective model with high representational capabilities and obtaining precise background modeling are therefore key aspects of this type of method. The background dictionary is also readily tainted by anomalies due to the limitations of the current approaches, making the detection findings less reliable. To address the above problems, this paper proposes a weighted low-rank sparse dictionary learning method (WLSDL). This model organically combines sparse representation with low-rank representation in order to effectively depict the intricate background distribution. The weights relating to the eigenvalues of the image are designed by mining the physical characteristics of the HSI. This can enhance the nuclear norm’s capacity for representation, resulting in a background dictionary with more representativeness. Furthermore, the capped norm constraint is incorporated in the objective function to decrease the effect of anomalies and noises on background modeling, hence minimizing anomaly pollution on the background dictionary. The residual image effectively increases the accuracy of anomaly identification since it makes it easier to distinguish between anomalies and background. We use three hyperspectral datasets to evaluate the proposed method. The experimental findings demonstrate the effectiveness and superiority of the proposed method over state-of-the-art methods.

Physics-informed neural network for volumetric sound field reconstruction of speech signals

Recent developments in acoustic signal processing have seen the integration of deep learning methodologies, alongside the continued prominence of classical wave expansion-based approaches, particularly in sound field reconstruction. Physics-informed neural networks (PINNs) have emerged as a novel framework, bridging the gap between data-driven and model-based techniques for addressing physical phenomena governed by partial differential equations. This paper introduces a PINN-based approach for the recovery of arbitrary volumetric acoustic fields. The network incorporates the wave equation to impose a regularization on signal reconstruction in the time domain. This methodology enables the network to learn the physical law of sound propagation and allows for the complete characterization of the sound field based on a limited set of observations. The proposed method’s efficacy is validated through experiments involving speech signals in a real-world environment, considering varying numbers of available measurements. Moreover, a comparative analysis is undertaken against state-of-the-art frequency domain and time domain reconstruction methods from existing literature, highlighting the increased accuracy across the various measurement configurations.

Feature-aware ultra-low dimensional reduction of real networks

In existing models and embedding methods of networked systems, node features describing their qualities are usually overlooked in favor of focusing solely on node connectivity. This study introduces FiD-Mercator, a model-based ultra-low dimensional reduction technique that integrates node features with network structure to create D-dimensional maps of complex networks in a hyperbolic space. This embedding method efficiently uses features as an initial condition, guiding the search of nodes’ coordinates toward an optimal solution. The research reveals that downstream task performance improves with the correlation between network connectivity and features, emphasizing the importance of such correlation for enhancing the description and predictability of real networks. Simultaneously, hyperbolic embedding’s ability to reproduce local network properties remains unaffected by the inclusion of features. The findings highlight the necessity for developing network embedding techniques capable of exploiting such correlations to optimize both network structure and feature association jointly in the future.

Proactive deadlock prevention based on traffic classification sub-graphs for triplet-based NoC TriBA-cNoC

Network topology and routing algorithms stand as pivotal decision points that profoundly impact the performance of Network-on-Chip (NoC) systems. As core counts rise, so does the inherent competition for shared resources, spotlighting the critical need for meticulously designed routing algorithms that circumvent deadlocks to ensure optimal network efficiency. This research capitalizes on the Triplet-Base Architecture (TriBA) and its Distributed Minimal Routing Algorithm (DM4T) to overcome the limitations of previous approaches. While DM4T exhibits performance advantages over previous routing algorithms, its deterministic nature and potential for circular dependencies during routing can lead to deadlocks and congestion. Therefore, this work addresses these vulnerabilities while leveraging the performance benefits of TriBA and DM4T. This work introduces a novel approach that merges a proactive deadlock prevention mechanism with Intermediate Adjacent Shortest Path Routing (IASPR). This combination guarantees both deadlock-free and livelock-free routing, ensuring reliable communication within the network. The key to this integration lies in a flow model-based data transfer categorization technique. This technique prevents the formation of circular dependencies. Additionally, it reduces redundant distance calculations during the routing process. By addressing these challenges, the proposed approach achieves improvements in both routing latency and throughput. To rigorously assess the performance of TriBA network topologies under varying configurations, extensive simulations were undertaken. The investigation encompassed both TriBA networks comprising 9 nodes and those with 27 nodes, employing DM4T, IASPR routing algorithms, and the proactive deadlock prevention method. The gem5 simulator, operating under the Garnet 3.0 network model using a standalone protocol for synthetic traffic patterns, was utilized for simulations at high injection rates, spanning diverse synthetic traffic patterns and PARSEC benchmark suite applications. Simulations rigorously quantified the effectiveness of the proposed approach, revealing reductions in average latency 40.17% and 34.05% compared to the lookup table and DM4T, respectively. Additionally, there were notable increases in average throughput of 7.48% and 5.66%.

A Dempster–Shafer Enhanced Framework for Urban Road Planning Using a Model-Based Digital Twin and MCDM Techniques

Rapid urbanization in developing countries presents a critical challenge in the need for extensive and appropriate road expansion, which in turn contributes to traffic congestion and air pollution. Urban areas are economic engines, but their efficiency and livability rely on well-designed road networks. This study proposes a novel approach to urban road planning that leverages the power of several innovative techniques. The cornerstone of this approach is a digital twin model of the urban environment. This digital twin model facilitates the evaluation and comparison of road development proposals. To support informed decision-making, a multi-criteria decision-making (MCDM) framework is used, enabling planners to consider various factors such as traffic flow, environmental impact, and economic considerations. Spatial data and 3D visualizations are also provided to enrich the analysis. Finally, the Dempster–Shafer theory (DST) provides a robust mathematical framework to address uncertainties inherent in the weighting process. The proposed approach was applied to planning for both new road constructions and existing road expansions. By combining these elements, the model offers a sustainable and knowledge-based approach to optimize urban road planning. Results from integrating weights obtained through two weighting methods, the Analytic Hierarchy Process (AHP) and the Bayesian best–worst Method (B-BWM), showed a very high weight for the “worn-out urban texture” criterion and a meager weight for “noise pollution”. Finally, the cost path algorithm was used to evaluate the results from all three methods (AHP, B-BWM, and DST). The high degree of similarity in the results from these methods suggests a stable outcome for the proposed approach. Analysis of the study area revealed the following significant challenge for road planning: 35% of the area was deemed unsuitable, with only a tiny portion (4%) being suitable for road development based on the selected criteria. This highlights the need to explore alternative approaches or significantly adjust the current planning process.

Automated shot-to-shot optimization of the plasma start-up scenario in the TCV tokamak

Plasma start-up is typically achieved manipulating poloidal magnetic fields, gas injection and possibly auxiliary heating. Model-based design techniques have been gaining increasing attention in view of future large tokamaks which have more stringent constraints and less room for trial-and-error. In this paper, we formulate the tokamak start-up scenario design problem as a constrained optimization problem and introduce a novel shot-to-shot correction algorithm, based on the Iterative Learning Control concept, to compensate for unavoidable modeling errors based on experimental data. The effectiveness of the approach is demonstrated in experiments on the TCV tokamak showing that the target ramp-up scenario could be obtained in a small number of shots with a rough electromagnetic model.

The Feasibility of a Model-Based Iterative Reconstruction Technique Tuned for the Myocardium on Myocardial Computed Tomography Late Enhancement.

This study evaluated the feasibility of a model-based iterative reconstruction technique (MBIR) tuned for the myocardium on myocardial computed tomography late enhancement (CT-LE). Twenty-eight patients who underwent myocardial CT-LE and late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) within 1 year were retrospectively enrolled. Myocardial CT-LE was performed using a 320-row CT with low tube voltage (80 kVp). Myocardial CT-LE images were scanned 7 min after CT angiography (CTA) without additional contrast medium. All myocardial CT-LE images were reconstructed with hybrid iterative reconstruction (HIR), conventional MBIR (MBIR_cardiac), and new MBIR tuned for the myocardium (MBIR_myo). Qualitative (5-grade scale) scores and quantitative parameters (signal-to-noise ratio [SNR] and contrast-to-noise ratio [CNR]) were assessed as image quality. The sensitivity, specificity, and accuracy of myocardial CT-LE were evaluated at the segment level using an American Heart Association (AHA) 16-segment model, with LGE-MRI as a reference standard. These results were compared among the different CT image reconstructions. In 28 patients with 448 segments, 160 segments were diagnosed with positive by LGE-MRI. In the qualitative assessment of myocardial CT-LE, the mean image quality scores were 2.9 ± 1.2 for HIR, 3.0 ± 1.1 for MBIR_cardiac, and 4.0 ± 1.0 for MBIR_myo. MBIR_myo showed a significantly higher score than HIR (P < 0.001) and MBIR_cardiac (P = 0.018). In the quantitative image quality assessment of myocardial CT-LE, the median image SNR was 10.3 (9.1-11.1) for HIR, 10.8 (9.8-12.1) for MBIR_cardiac, and 16.8 (15.7-18.4) for MBIR_myo. The median image CNR was 3.7 (3.0-4.6) for HIR, 3.8 (3.2-5.1) for MBIR_cardiac, and 6.4 (5.0-7.7) for MBIR_myo. MBIR_myo significantly improved the SNR and CNR of CT-LE compared to HIR and MBIR_cardiac (P < 0.001). The sensitivity, specificity, and accuracy for the detection of myocardial CT-LE were 70%, 92%, and 84% for HIR; 71%, 92%, and 85% for MBIR_cardiac; and 84%, 92%, and 89% for MBIR_myo, respectively. MBIR_myo showed significantly higher image quality, sensitivity, and accuracy than the others (P < 0.05). MBIR tuned for myocardium improved image quality and diagnostic performance for myocardial CT-LE assessment.

Synthesis of flexible inter-plant heat exchanger networks: A decomposition method considering intermedium fluid circles

The traditional methods for synthesizing flexible heat exchanger networks (HENs) are not directly applicable to inter-plant HEN challenges, primarily due to the spread of system uncertainty across plants via intermedium fluid circles. This complicates the synthesis process significantly. To tackle this issue, this study proposes a decomposed stepwise methodology to facilitate the flexible synthesis of the inter-plant HENs performing indirect heat integration. A decomposition strategy is proposed to divide the overall network into manageable sub-networks by dissecting the intermedium fluid circles. To address the variability in intermedium fluid temperatures, a temperature fluctuation analysis approach is developed and a heuristic rule is introduced to maintain the temperature feasibility of the intermedium fluids. To ensure adequate flexibility and cost-effectiveness of the designed networks, flexibility analysis and network retrofit steps are conducted through model-based optimization techniques. The efficacy of the method is demonstrated through two case studies, showing its potential in achieving the desired operational flexibility for inter-plant HENs.

Understanding world models through multi-step pruning policy via reinforcement learning

In model-based reinforcement learning, the conventional approach to addressing world model bias is to use gradient optimization methods. However, using a singular policy from gradient optimization methods in response to a world model bias inevitably results in an inherently biased policy. This is because of constraints on the imperfect and dynamic data of state-action pairs. The gap between the world model and the real environment can never be completely eliminated. This article introduces a novel approach that explores a variety of policies instead of focusing on either world model bias or singular policy bias. Specifically, we introduce the Multi-Step Pruning Policy (MSPP), which aims to reduce redundant actions and compress the action and state spaces. This approach encourages a different perspective within the same world model. To achieve this, we use multiple pruning policies in parallel and integrate their outputs using the cross-entropy method. Additionally, we provide a convergence analysis of the pruning policy theory in tabular form and an updated parameter theoretical framework. In the experimental section, the newly proposed MSPP method demonstrates a comprehensive understanding of the world model and outperforms existing state-of-the-art model-based reinforcement learning baseline techniques.

Useability Evaluation of Reinforcement Learning Toolboxes for Electrical Drives

The current direction of development predicts that Reinforcement Learning based data driven control methods can become a next generation technology to control electrical drives instead of the classical model-based techniques. The paper aims to evaluate toolboxes that can be used to train agents for control approaches. The paper helps lay the theoretical bases and provides guidelines for using these toolboxes via a case study. This is done to highlight each toolbox’s key aspects and workflow patterns, shifting the comparison to useability and peak-performance.

Backstepping based intelligent control of tractor-trailer mobile manipulators with wheel slip consideration

In this research, a new hybrid backstepping control strategy based on a neural network is proposed for tractor-trailer mobile manipulators in the presence of unknown wheel slippage and disturbances. To minimize the negative impacts of wheel slippage, the desired velocities of the tractor’s wheels are computed with a proposed kinematic control model with an adaptive term. As the system’s dynamical model contains unavoidable uncertainties, model-based backstepping control technique is unable to effectively manage these systems. Hence, the proposed controller blends a radial basis function neural network with the merits of a dynamical model-based backstepping approach. The neural networks are employed to approximate the non-linear unknown smooth function. To minimize the impact of external disturbances, and network reconstruction error an adaptive term is added to the control law. The Lyapunov theorem and Barbalat’s lemma are employed to guarantee the stability of the control method. The tracking error is shown to be bounded and to rapidly converge to zero with the proposed method. To demonstrate the efficacy and validity of the control mechanism, comparison simulation results are presented.

Efficient maximum power point extraction using hybrid optimisation based parameter estimation model of solar double diode model

ABSTRACT PV systems operate most efficiently when they are operated at their Maximum Power Point (MPP). Despite the wide range of MPPT approaches available, there is potential to improve the efficiency of MPP Tracking (MPPT). One method to achieve this improvement is to use model-based MPPT techniques, which can speed up the MPP search process by estimating the MPP with a high degree of accuracy. The main objective of the research, which is to create an efficient double-diode model-based MPPT technique with a focus on hybrid Optimisation, is informed by this justification. The suggested method for predicting the MPP voltage makes use of an accurate double-diode model for PV modules that is dependent on temperature and irradiance. This research employs a parameter estimation system based on the proposed Optimisation algorithm known as Memory Integrated Sand Cat Swarm Optimisation Algorithm (MI-SCS) to overcome the limitations of standard parameter estimate methods, which are related to the availability of experimental p-V curves or datasheets with precise temperature and irradiance values. The method that is being given is based on the integration of the Crow Search Optimisation (CSO) Algorithm with the Sand Cat Swarm Optimisation (SCSO) algorithm.