Search Results (42)

This work presents a data-driven modeling framework for predicting image-derived crystal size metrics in seeded cooling crystallization using Long Short-Term Memory (LSTM) neural networks. The model leverages in situ microscopy data to predict square-weighted D10, D50, D90, and particle counts based solely on seed loading and temperature profiles, without requiring real-time supersaturation measurements. To enhance predictive power, engineered process descriptors—including temperature derivatives and integrals—were incorporated as dynamic features. Experimental validation was performed using creatine monohydrate crystallization from aqueous solution, with LSTM models trained on a diverse dataset encompassing variable seed loadings and cooling profiles. The feature-engineered LSTM model consistently outperformed its non-engineered counterpart, particularly under nonlinear cooling conditions where crystallization dynamics were the most complex. This approach offers a practical alternative to mechanistic models and spectroscopic process analytical technology (PAT) tools by enabling accurate prediction of chord length distribution (CLD) metrics from routinely collected data. The framework is easily transferable to other crystallization systems and provides a low-complexity, high-accuracy tool for accelerating lab-scale crystallization development. Full article

This article proposes a multiscale classification framework for detecting voltage disturbances in electrical distribution systems using artificial neural networks (ANNs) combined with the Hilbert–Huang transform (HHT). The framework targets four core power quality (PQ) events defined in the IEEE 1159-2019 standard: normal operation and voltage sag, swell, and interruption. Unlike traditional methods that operate on a fixed disturbance duration, our approach incorporates multiple time scales (0.2 s, 0.4 s, and 0.8 s) to improve detection robustness across varied event lengths, a critical factor in real-world scenarios where disturbance durations are unpredictable. Features are extracted using empirical mode decomposition (EMD) and Hilbert spectral analysis, enabling accurate representation of the signals’ non-stationary and nonlinear characteristics. The ANN is trained using statistical descriptors derived from the first two intrinsic mode functions (IMFs), capturing both amplitude and frequency content. The method was validated in MATLAB on the IEEE 33-bus radial distribution test system using simulated disturbances. The proposed model achieved a classification accuracy of 94.09% and demonstrated consistent performance across all time windows, supporting its suitability for real-time monitoring in smart distribution networks. This study contributes a scalable and adaptable solution for automated PQ event classification under variable conditions. Full article

Alkaloids are naturally occurring metabolites with a wide variety of pharmacological activities and applications in science, particularly in medicinal chemistry as anti-inflammatory drugs. Because they can be labelled as active or inactive compounds against the inflammatory biological response, the aim of this work was to calibrate quantitative structure-activity relationships (QSARs) using machine learning classifiers to predict anti-inflammatory activity based on the molecular structures of alkaloids. A dataset of 100 alkaloids (58 active and 42 inactive) was retrieved from two systematic reviews. Molecules were properly curated, and the molecular geometries of the compounds were optimized using the semi-empirical method (PM3) to calculate molecular descriptors, binary fingerprints (extended-connectivity fingerprints and path fingerprints) and MACCS (Molecular ACCess System) structural keys. Then, we calibrated the QSAR models using well-known linear and non-linear machine learning classifiers, i.e., partial least squares discriminant analysis (PLSDA), random forests (RF), adaptive boosting (AdaBoost), k-nearest neighbors (kNN), N-nearest neighbors (N3) and binned nearest neighbors (BNN). For validation purposes, the dataset was randomly split into a training set and a test set in a 70:30 ratio. When using molecular descriptors, genetic algorithms-variable subset selection (GAs-VSS) was used for supervised feature selection. During the calibration of the models, a five-fold Venetian blinds cross-validation was used to optimize the classifier parameters and to control the presence of overfitting. The performance of the models was quantified by means of the non-error rate (NER) statistical parameter. Full article

Individuals grappling with severe central nervous system injuries often face significant challenges related to sensorimotor function and communication abilities. In response, brain–computer interface (BCI) technology has emerged as a promising solution by offering innovative interaction methods and intelligent rehabilitation training. By leveraging electroencephalographic (EEG) signals, BCIs unlock intriguing possibilities in patient care and neurological rehabilitation. Recent research has utilized covariance matrices as signal descriptors. In this study, we introduce two methodologies for covariance matrix analysis: multiple tangent space projections (M-TSPs) and Cholesky decomposition. Both approaches incorporate a classifier that integrates linear and nonlinear features, resulting in a significant enhancement in classification accuracy, as evidenced by meticulous experimental evaluations. The M-TSP method demonstrates superior performance with an average accuracy improvement of 6.79% over Cholesky decomposition. Additionally, a gender-based analysis reveals a preference for men in the obtained results, with an average improvement of 9.16% over women. These findings underscore the potential of our methodologies to improve BCI performance and highlight gender-specific performance differences to be examined further in our future studies. Full article

Fault data injection attacks may lead to a decrease in system performance and even a malfunction in system operation for an automatic feedback control system, which has motive to develop an effective method for rapidly detecting such attacks so that appropriate measures can be taken correspondingly. In this study, a secure descriptor estimation technique is proposed for continuous-time Lipschitz nonlinear cyber physical systems affected by actuator attacks, sensor attacks, and unknown process uncertainties. Specifically, by forming a new state vector composed of original system states and sensor faults, an equivalent descriptor dynamic system is built. A proportional and derivate sliding-mode observer is presented so that the system states, sensor attack, and actuator attack can be reconstructed successfully. The observer gains are obtained by using linear matrix inequality to secure robustly stable estimation error dynamics. Moreover, a robust descriptor fast adaptive observer estimator is presented as a complement. Finally, the efficacy levels of the proposed design approaches are validated using a vertical take-off and landing aircraft system. Comparison studies are also carried out to assess the tracking performances of the proposed algorithms. Full article

This paper deals with the constrained state regulation problem (CSRP) of descriptor fractional-order linear continuous-time systems (DFOLCS) with order $0<\alpha <1$. The objective is to establish the existence of conditions for a linear feedback control law within state constraints and to propose a method for solving the CSRP of DFOLCS. First, based on the decomposition and separation method and coordinate transformation, the DFOLCS can be transformed into an equivalent fractional-order reduced system; hence, the CSRP of the DFOLCS is equivalent to the CSRP of the reduced system. By means of positive invariant sets theory, Lyapunov stability theory, and some mathematical techniques, necessary and sufficient conditions for the polyhedral positive invariant set of the equivalent reduced system are presented. Models and corresponding algorithms for solving the CSRP of a linear feedback controller are also presented by the obtained conditions. Under the condition that the resulting closed system is positive, the given model of the CSRP in this paper for the DFOLCS is formulated as nonlinear programming with a linear objective function and quadratic mixed constraints. Two numerical examples illustrate the proposed method. Full article

Solubility is not only a crucial physicochemical property for laboratory practice but also provides valuable insight into the mechanism of saturated system organization, as a measure of the interplay between various intermolecular interactions. The importance of these data cannot be overstated, particularly when dealing with active pharmaceutical ingredients (APIs), such as dapsone. It is a commonly used anti-inflammatory and antimicrobial agent. However, its low solubility hampers its efficient applications. In this project, deep eutectic solvents (DESs) were used as solubilizing agents for dapsone as an alternative to traditional solvents. DESs were composed of choline chloride and one of six polyols. Additionally, water–DES mixtures were studied as a type of ternary solvents. The solubility of dapsone in these systems was determined spectrophotometrically. This study also analyzed the intermolecular interactions, not only in the studied eutectic systems, but also in a wide range of systems found in the literature, determined using the COSMO-RS framework. The intermolecular interactions were quantified as affinity values, which correspond to the Gibbs free energy of pair formation of dapsone molecules with constituents of regular solvents and choline chloride-based deep eutectic solvents. The patterns of solute–solute, solute–solvent, and solvent–solvent interactions that affect solubility were recognized using Orange data mining software (version 3.36.2). Finally, the computed affinity values were used to provide useful descriptors for machine learning purposes. The impact of intermolecular interactions on dapsone solubility in neat solvents, binary organic solvent mixtures, and deep eutectic solvents was analyzed and highlighted, underscoring the crucial role of dapsone self-association and providing valuable insights into complex solubility phenomena. Also the importance of solvent–solvent diversity was highlighted as a factor determining dapsone solubility. The Non-Linear Support Vector Regression (NuSVR) model, in conjunction with unique molecular descriptors, revealed exceptional predictive accuracy. Overall, this study underscores the potency of computed molecular characteristics and machine learning models in unraveling complex molecular interactions, thereby advancing our understanding of solubility phenomena within the scientific community. Full article

This paper proposes an observer-based proportional Derivative (O-BPD) fuzzy controller for uncertain discrete-time nonlinear descriptor systems (NDSs). Representing NDSs with the Takagi–Sugeno fuzzy model (T-SFM), the proportional derivative (PD) feedback method can be utilized in the fuzzy controller design via the Parallel Distributed Compensation (PDC) concept, such that the noncausal problem and impulse behavior are avoided. A fuzzy observer is proposed to obtain unmeasured states to fulfill the PD fuzzy controller. Moreover, uncertainties and transient response performances are taken into account for the NDSs. Then, a stability analysis process and corresponding stability conditions are derived from the Lyapunov theory with the robust control method and the pole constraint. Different from existing research, the Singular Value Decomposition (SVD) and the projection lemma are utilized to transfer the stability conditions into the Linear Matrix Inequation (LMI) form. Because of this reason, the conservatism of the analysis process can be reduced by eliminating the restriction on the positive definite matrix in the Lyapunov function. By giving the proper center and radius parameters of the pole constraint in the O-BPD fuzzy controller design process, the expected transient responses can be obtained for different designers and different practical applications. Finally, the effectiveness and applicability of the proposed O-BPD fuzzy controller are demonstrated by two examples of the simulation. Full article

This research focuses on the development of state-difference feedback controllers for discrete-time (DT) nonlinear descriptor systems. Discrete-time nonlinear DA systems consist of difference and algebraic equations and play a crucial role in describing dynamic behavior and capturing the constraints or relationships within the system. However, analytical stability may pose additional challenges due to the unique characteristics of the system. Utilizing fuzzy model-based techniques, the DT nonlinear DA system discussed in this study can be effectively represented using the Takagi–Sugeno (T-S) fuzzy model. After linearizing the nonlinear system through the T-S fuzzy model, traditional linear control techniques become applicable. These techniques are then applied to T-S fuzzy systems to establish stability criteria. This article chooses the Lyapunov function as the method used to analyze system stability. Additionally, we use a free-weighting matrix to introduce additional degrees of freedom. In summary, this paper presents simulation results and discussions to verify the effectiveness of the proposed design approach. Full article

This paper investigates the decentralized fuzzy control problems for nonlinear-state-unmeasured interconnected descriptor systems (IDSs) that utilize the observer-based-feedback approach and the proportional–derivative feedback control (PDFC) method. First of all, the IDS is represented as interconnected Takagi–Sugeno (T–S) fuzzy subsystems. These subsystems can effectively capture the dynamic behavior of the system through fuzzy rules. For the stability analysis of the system, this paper uses the free-weighing Lyapunov function (FWLF), which allows the designer to set the weight matrix, to achieve the desired control performance and design the controller more easily. Furthermore, the control problem can be transformed into a set of linear matrix inequalities (LMIs) through the Schur complement, which can be solved using convex optimization methods. Simulation results confirm the effectiveness of the proposed method in achieving the desired control objectives and ensuring system stability. Full article

Multiple Internet of Healthcare Things (IoHT)-based devices have been utilized as sensing methodologies for human locomotion decoding to aid in applications related to e-healthcare. Different measurement conditions affect the daily routine monitoring, including the sensor type, wearing style, data retrieval method, and processing model. Currently, several models are present in this domain that include a variety of techniques for pre-processing, descriptor extraction, and reduction, along with the classification of data captured from multiple sensors. However, such models consisting of multiple subject-based data using different techniques may degrade the accuracy rate of locomotion decoding. Therefore, this study proposes a deep neural network model that not only applies the state-of-the-art Quaternion-based filtration technique for motion and ambient data along with background subtraction and skeleton modeling for video-based data, but also learns important descriptors from novel graph-based representations and Gaussian Markov random-field mechanisms. Due to the non-linear nature of data, these descriptors are further utilized to extract the codebook via the Gaussian mixture regression model. Furthermore, the codebook is provided to the recurrent neural network to classify the activities for the locomotion-decoding system. We show the validity of the proposed model across two publicly available data sampling strategies, namely, the HWU-USP and LARa datasets. The proposed model is significantly improved over previous systems, as it achieved 82.22% and 82.50% for the HWU-USP and LARa datasets, respectively. The proposed IoHT-based locomotion-decoding model is useful for unobtrusive human activity recognition over extended periods in e-healthcare facilities. Full article

This paper studies the problem of linkage-bar synthesis by means of multiple deep neural networks (DNNs), which requires the inverse solution of linkage parameters based on a desired trajectory curve. This problem is highly complex due to the fact that the solution space is nonlinear and may contain multiple solutions, while a good quality of learning cannot be obtained by a single neural network approach. Therefore, this paper proposes employing Fourier descriptors to represent trajectory curves in a systematic and normalized form, developing a multi-solution distribution evaluation by random restart local searches (MDE-RRLS) to examine a better solution-space partitioning scheme, utilizing multiple DNNs to learn subspace regions separately, and creating a multi-facet query (MFQuery) to cooperatively predict multiple solutions. The experiments demonstrate that the proposed approach can obtain better or at least competitive outcomes compared to previous work in the literature. Furthermore, to verify the effectiveness and applicability, this paper investigates the design problem of an industrial six-linkage-bar ladle mechanism used in a die-casting system, and the proposed method can obtain several superior design solutions and offer alternatives in a short period of time when faced with redesign requirements. Full article

Cleansing foam is a common multicomponent polymeric functional material. It contains ingredients in innumerable combinations, which makes formulation optimization challenging. In this study, we used artificial intelligence (AI) with machine learning to develop a cleansing capability prediction system that considers the effects of self-assembled structures and chemical properties of ingredients. Over 500 cleansing foam samples were prepared and tested. Molecular descriptors and Hansen solubility index were used to estimate the cleansing capabilities of each formulation set. We used five machine-learning models to predict the cleansing capability. In addition, we employed an in silico formulation by generating virtual formulations and predicting their cleansing capabilities using an established AI model. The achieved accuracy was R² = 0.770. Our observations revealed that mixtures of cosmetic ingredients exhibit complex interactions, resulting in nonlinear behavior, which adds to the complexity of predicting cleansing performance. Nevertheless, accurate chemical property descriptors, along with the aid of in silico formulations, enabled the identification of potential ingredients. We anticipate that our system will efficiently predict the chemical properties of polymer-containing blends. Full article

This paper presents a fast Lidar inertial odometry and mapping (F-LIOM) method for mobile robot navigation on flat terrain with high real-time pose estimation, map building, and place recognition. Existing works on Lidar inertial odometry have mostly parameterized the keyframe pose as SE(3) even when the robots moved on flat ground, which complicated the motion model and was not conducive to real-time non-linear optimization. In this paper, F-LIOM is shown to be cost-effective in terms of model complexity and computation efficiency for robot SE(2) navigation, as the motions in other degrees of freedom in 3D, including roll, pitch, and z, are considered to be noise terms that corrupt the pose estimation. For front-end place recognition, the smoothness information of the feature point cloud is introduced to construct a novel global descriptor that integrates geometry and environmental texture characteristics. Experiments under challenging scenarios, including self-collected datasets and public datasets, were conducted to validate the proposed method. The experimental results demonstrated that F-LIOM could achieve competitive real-time performance in terms of accuracy compared with state-of-the-art counterparts. Our solution has significant superiority and the potential to be deployed in limited-resource mobile robot systems. Full article

Three-dimensional (3D) cameras used for gait assessment obviate the need for bodily markers or sensors, making them particularly interesting for clinical applications. Due to their limited field of view, their application has predominantly focused on evaluating gait patterns within short walking distances. However, assessment of gait consistency requires testing over a longer walking distance. The aim of this study is to validate the accuracy for gait assessment of a previously developed method that determines walking spatiotemporal parameters and kinematics measured with a 3D camera mounted on a mobile robot base (ROBOGait). Walking parameters measured with this system were compared with measurements with Xsens IMUs. The experiments were performed on a non-linear corridor of approximately 50 m, resembling the environment of a conventional rehabilitation facility. Eleven individuals exhibiting normal motor function were recruited to walk and to simulate gait patterns representative of common neurological conditions: Cerebral Palsy, Multiple Sclerosis, and Cerebellar Ataxia. Generalized estimating equations were used to determine statistical differences between the measurement systems and between walking conditions. When comparing walking parameters between paired measures of the systems, significant differences were found for eight out of 18 descriptors: range of motion (ROM) of trunk and pelvis tilt, maximum knee flexion in loading response, knee position at toe-off, stride length, step time, cadence; and stance duration. When analyzing how ROBOGait can distinguish simulated pathological gait from physiological gait, a mean accuracy of 70.4%, a sensitivity of 49.3%, and a specificity of 74.4% were found when compared with the Xsens system. The most important gait abnormalities related to the clinical conditions were successfully detected by ROBOGait. The descriptors that best distinguished simulated pathological walking from normal walking in both systems were step width and stride length. This study underscores the promising potential of 3D cameras and encourages exploring their use in clinical gait analysis. Full article