Batch Model Research Articles

Numerical research on the constraint effect of double steel plate–concrete composite structures

Double steel plate–concrete composite structures comprise two outer steel plates, steel flange plates, connectors, and infill concrete. Owing to their superior mechanical properties, double steel plate–concrete composite structures have been extensively used in construction engineering. Outer steel plates and connectors create a significant constraint effect on the infill concrete. However, no confined concrete constitutive model applies to double steel plate–concrete composite structures. To address this gap, this study established approximately 2000 shell-solid finite element models and derived a confined concrete compression constitutive model suitable for double steel plate–concrete composite structures through regression analysis. The structural parameters potentially affecting the confined performance were initially identified through theoretical analysis. Subsequently, an Abaqus shell-solid finite element model was established, with its accuracy verified through experiments. Thereafter, regression analysis was conducted by varying different parameters in batch modelling. Ultimately, a uniaxial compression constitutive model for concrete suitable for double steel plate–concrete composite structures was established.

High Efficiency Producing Technology Applied in Metal Optical Lens by 3D Wax Printing Combined with Investment Casting

3D printing technology can easily and quickly produce small batch models and full-size parts, which has obvious and important benefits in shortening development time. Since metals exhibit excellent mechanical strength and high wear resistance, metal additive manufacturing (MAM) is a popular technology for making metal parts. However, metal powders and 3D-printing machines are costly, which increases the difficulty of achieving mass production through MAM. In this study, the 3D wax printing and investment casting (WPIC) approach was developed to manufacture high-quality metal optical lenses with high efficiency and low cost. The manufactured lenses had a diameter of 38.1 mm, two radii of curvature (15 and 90 mm), and a cooling channel. These lenses were manufactured through 3D printing by using wax patterns produced through investment casting. The manufacturing efficiency and machining accuracy of the lenses produced using the proposed method were compared with those of lenses produced through MAM and investment casting. The results indicated that the total costs of manufacturing an optical lens through MAM and investment casting were nine and eight times greater, respectively than that of manufacturing an optical lens through WPIC. In addition, the surface roughness of metal lenses manufactured through WPIC was 45% lower than that of lenses manufactured through MAM. Finally, the time required to manufacture 50 metal lenses was only 15 days when WPIC was used; the corresponding time was 25 days and 6 months when MAM and investment casting were used, respectively. According to the above-mentioned results, the WPIC process has excellent advantages in product manufacturing cost and developing schedule over MAM and traditional methods of investment casting.

Mathematical modeling and kinetics of batch and continuous electro-catalytic oxidation of pharmaceutical-contaminated wastewater

An accurate yet simple model is the key to the design and control of intricate electro-catalytic oxidation of pharmaceutical contaminated wastewater. For both batch and unsteady-state continuous flow stirred tank reactors (CSTR), batch reactor models have been used earlier. Further, these models do not correlate rate to the operating conditions, and consider pseudo-first/second-order kinetics. Here, first-principles models are proposed by formulating unsteady-state mass balances, modifying them to attain realistic final conditions, and incorporating fractional variable-order kinetics. Following integral analysis, analytical solutions are obtained. These are independently applicable to design, unlike a numerical solution. Nonlinear regression is performed to estimate the model parameters from the transient experimental data. The simulations yield markedly accurate model parameters together with a better fit to the experimental data of Ti/RuO2-mediated amoxicillin-trihydrate electro-oxidation, for CSTR and batch reactors. For the batch reactor, the operating conditions are varied one at a time. Their effects on the model parameters are elucidated based on the oxidant and transformation species formed. The computed optimum model parameters are: rate constant 3.318 × 10−3 mg−0.092 m1.276 min−1, order 1.092, initial rate 4.032 × 102 mg m−2 min−1, and final conversion 90.6% in 180 min. The corresponding operating conditions are: pH 2.0, feed 50 mg L−1, electrolyte 2 g L−1, and current 1 A. A simple generalized power-law correlation, associating rate to the operating conditions, is then estimated. Statistical analysis of these models using central composite design delivers R2 0.99, predicted R2 0.96, and optimum set close to the above. The corresponding sensitivity analysis and generalized correlation, both show applied current to be the most significant operating condition. The dynamic modeling approaches proposed here can be extended to model, control, and scale-up complex reaction systems.

Exploring the Adsorption Efficiency of Local Apricot Seed Shell as a Sustainable Sorbent for Nitrate Ion

Locally available apricot seed shell as agro-waste was used for the preparation of adsorbents. The biochar was prepared at 370°C via pyrolysis and 80 mesh particle sizes were modified by 1N HCl. Nitrate adsorption and effect of co-ions from aqueous solution were studied under batch model using apricot seed shell powder (ASSP), apricot seed shell biochar (ASSB), and activated apricot seed shell biochar (AASSB). FTIR and pHPZC measurements were used to characterize the adsorbents. Based on the experimental findings, the optimum conditions follow pH 2, 0.3g dosage, initial concentration of 50 mg.L-1, and contact time of 90 min. The three forms of adsorbent exhibited good adsorption for nitrate. However, the maximum percentage removal of nitrate ions from the aqueous solution followed the order AASSB>ASSB>ASSP. The adsorption kinetic of nitrate ion was best fitted by pseudo 2nd order, and the parameters of adsorption isotherms elucidated favorable and improved sorption. This agro-waste could be used to develop sustainable adsorbents in water and wastewater treatment methods and has great potential to replace commercially available sorbents.

Comprehensive assessment of the water environment carrying capacity based on machine learning

Human activities and climate change are constantly threatening water environment systems. To alleviate pressure on the water environment and meet the requirements for sustainable societal development, it has become important to study the water environment carrying capacity (WECC). As science and technology have advanced, the use of artificial intelligence has penetrated various disciplines, and the application of machine learning has achieved many good results in the environmental sciences; however, little attention has been given to the WECC. To this end, a WECC assessment model was developed based on a variety of machine learning algorithms, to provide a novel approach and better understanding of the WECC. In this study, 13 natural and anthropogenic factors related to the water environment system in Liaoning Province (China) were selected, and the study period ranged from 2015 to 2019. Four basic machine learning algorithms, namely, random forest (RF), support vector machine (SVM), multilayer perceptron (MLP) and k-nearest neighbour (KNN), were used for batch modelling, and stacking was carried out based on the output results. A comparison and screening of the models revealed that RF and the stacking model had the best model prediction performances. Because RF was relatively simple and convenient, a comprehensive assessment of the regional WECC based on this algorithm was carried out. The results showed that most of the control units with an overloaded WECC are located in the central and northern regions of Liaoning Province, and the control units of overloading can be well identified and the trend of regional WECC status can be observed. To improve model transparency, we also performed an explanatory analysis based on the shapley additive explanations (SHAP). The results showed that precipitation, soil texture, sewage treatment plant, wind speed, and temperature were the most important factors influencing the water environment system. Precipitation is the most influential factor, and with increasing rainfall, the WECC first improves and then gradually deteriorates. For the anthropogenic factors, the WECC generally improves first and then worsens as these factors increase. These research results can be used to provide a powerful and practical new methodology for the comprehensive assessment of the WECC and provide a basis for the development of water environment policies and regulatory implementation in the region.

Submodular batch scheduling on parallel machines

AbstractThis article studies a submodular batch scheduling problem motivated by the vacuum heat treatment. The batch processing time is formulated by a monotone nondecreasing submodular function characterized by decreasing marginal gain property. The objective is to minimize the makespan. We show the NP‐hardness of the problem on a single machine and of finding a polynomial‐time approximation algorithm with the worst‐case performance ratio strictly less than for the problem on parallel machines. We introduce a bounded interval to model the batch processing time using two parameters, that is, the total curvature and the quantization indicator. Based on the decreasing marginal gain property and the two parameters, we make a systematic analysis of the full batch longest processing time algorithm and the longest processing time greedy algorithm, and propose the instances with the bound of batch capacity for these two algorithms for the submodular batch scheduling problem. Moreover, we prove the submodularity of batch processing time function of the existing batch models including the parallel batch, serial batch, and mixed batch models. We compare the worst‐case performance ratios in the existing batch models with those deduced from our work in the submodular batch model. In most situations, the worst‐case performance ratios deduced from our work are comparable to the best‐known worst‐case performance ratios with tailored examinations.

AdaGCR: An improved method for optimizing machine learning training process

In contemporary machine learning, training datasets are typically divided into batches, and models are updated incrementally through batch iterations to save memory and reduce overfitting. However, determining the optimal hyperparameters like learning rate, batch size and number of epochs remains a challenge which often relying on empirical insights. This paper explores a novel method called Adaptive Gradient Conflict Rate (AdaGCR) to optimize the training process. It leverages the idea of gradient conflict rate, which reflects the models position within a batch model set and accordingly adjusts the global learning rate. This proposed method is tested by training a Deep Neural Network (DNN) model with MNIST dataset which represents simple tasks and a ResNet-18 model with CIFAR-10 dataset which represents more complicated tasks for solving real world problems. Experiments conducted on DNN demonstrates the proposed methods effectiveness in reducing overfitting and enhancing convergence, particularly with a well-suited initial learning rate. However, its applicability to more complex models like ResNet-18 may require further refinements, such as layer-specific learning rate adjustments. Future research should focus on fine-tuning AdaGCR and extending its utility across diverse machine learning models and tasks.

Improvised contrastive loss for improved face recognition in open-set nature

Face recognition models often encounter various unseen domains and environments in real-world applications, leading to unsatisfactory performance due to the open-set nature of face recognition. Models trained on central datasets may exhibit poor generalization when faced with different candidates under varying illumination and blur conditions. In this paper, our goal is to enhance the generalization of face recognition models for diverse target conditions without relying on active or incremental learning. We propose an approach for face recognition that utilizes contrastive learning to synthesize positive and multiple negative samples. To address the combinatorial challenges posed by positive and negative samples, our framework incorporates a combination of contrastive regularizer loss and Arcface loss, along with an effective sampling strategy for batch model learning. We update the model weights by jointly back-propagating contrastive and ArcFace gradients. We validate our method on both generalized and standard face recognition benchmarks dataset namely IJB-B and IJB-C. Series of experimentation revealed the out-performance of proposed framework against other state-of-the-art methods.

Data-driven sensor delay estimation in industrial processes using multivariate projection methods

A key step in preparing industrial data for multivariate statistical modelling of (batch-)continuous processes is the estimation of sensor delays along the production line, to use as a correction for understanding relationships between them. Without such a correction, the measurements collected from the sensors do not all relate to the same portion of material travelling through the plant, which is where from a physical point of view the correlations are expected to arise from. Most methods to do these corrections currently reported in literature are limited in that they optimize only correlations bivariately between the different sensors, despite the eventual goal of being understood as a multivariate process model. This work proposes several methods for multivariate sensor delay estimation, based on multivariate projection methods, and critically investigates these using simulated and empirical process data from two industrial facilities. The objective is to provide more clarity on if, how, and why taking into account these multivariate correlations using such projection methods is beneficial. One of the proposed methods, named PLS-SEQ, was shown to outperform bivariate sensor delay estimation, which is regarded as benchmark method in this work, for all datasets. The average reduction in delay estimation error achieved by using PLS-SEQ is between 6% and 64%. The other newly proposed multivariate projection-based methods did not show such unanimous improvement in accuracy, but helped identifying the presence of sensor clusters in industrial data as a novel key challenge for sensor delay estimation. The presented results illustrate that projection-based multivariate methods, in particular the newly proposed method PLS-SEQ, show promising potential for sensor delay estimation, outperforming the bivariate sensor delay estimation methods used as benchmark. Ultimately, using these methods can improve the predictive and descriptive quality of statistical models for key industrial processes.

Synthesis and Sorption Profiles of Graphene‐Decorated Silane‐Modified Layered Clays for As(V) Removal: A Quantitative Assessment and Mechanistic Insights

AbstractA novel adsorbent material, graphene decorated silane modified layered clays enriched with Fe(III) (TEOS‐g‐LDH−Fe/rGO) was prepared via emulsion polymerization followed by in situ precipitation and its physicochemical characterization carried out by FTIR, XRD, SEM‐EDS, HRTEM, TG‐ DTG, XPS and Raman analysis. The TEOS‐g‐LDH−Fe/rGO composite utilized for the effective removal of As(V) from aqueous system and the process followed via inner‐sphere surface complexation through ligand exchange between hydroxyl groups in TEOS‐g‐LDH−Fe/rGO and As(V) species. The equilibrium data fitted well with Langmuir model and kinetic data with mixed batch model showed remarkable adsorption capacity of 103.91 mg/g at pH 5.5. The synergistic effects associated with precursors in the composite profoundly improved the removal efficiency of As(V). The optimal conditions for As(V) removal was evaluated by RSM coupled with central composite design(CCD) considering pH(3–6), dose(0.5–2.5) and time (1–80 min) at temperature 30 °C. The sorption efficacy of TEOS‐g‐LDH−Fe/rGO was found to be about four times greater than its precursors. In simulated water matrix, the TEOS‐g‐LDH−Fe/rGO exhibit a retention of sorption performance (90 %) from 98.8 % of its initial sorption capacity for As(V) removal during regeneration. This work proves TEOS‐g‐LDHFe/rGO as a promising candidate for addressing grievous environmental threats from arsenic contamination.

Study on the optimal design of specimens for stiffness coefficients identification of glass fiber-reinforced polymer composites by virtual fields method

Glass fiber-reinforced polymer composites are important structural materials and are widely used in structure engineering. In this study, a new V-notch non-standard tensile specimen is proposed. All the in-plane stiffness coefficients of glass fiber-reinforced polymer composites could be obtained by the virtual fields method with only one uniaxial tensile test. First, the special virtual fields method for inversion of elastic constitutive parameters of orthotropic materials in the uniaxial tensile test was introduced. The optimization of the geometrical design of the specimen was conducted using finite element simulation experiments. Batch modeling calculation was conducted within the designed range of the geometric parameters of the specimen. The generated ideal strain field data were substituted into the virtual fields method to invert and identify the stiffness coefficients. The optimized geometry of the specimen was determined according to the objective function of minimum error. Through a tensile experiment on glass fiber composites, the influence of specimen deformation on the identification results was assessed, and the load level suitable for parameter identification was determined. Based on the results, it can be concluded that the inversion identification accuracy meets the requirements of engineering measurement.

Remanufacturing system scheduling of batch products with the consideration of dynamic changes in machine efficiency using an improved artificial bee colony algorithm

Remanufacturing has the ability to bring the quality and condition of the recycled product back to the level of or even better than the new product. As remanufacturing continues to receive more and more attention from industry and academia, the scheduling of remanufacturing systems (RMS) has been extensively studied. However, few studies have not only focused on the dynamic changes (deterioration and learning) in machine efficiency during RMS scheduling but also considered that the three subsystems (disassembly, reprocessing and reassembly) of RMS collaborate with each other during scheduling. Therefore, this study proposes a new RMS scheduling model of batch recycled products with the consideration of dynamic changes in machine efficiency for handling the batch recycled products. It considers not only the collaboration among the three subsystems comprehensively, but also the dynamic changes in machine efficiency, i.e., deterioration effects and learning effects, during the scheduling. To solve this model, an improved artificial bee colony algorithm with a new representation scheme and a new population generating method is proposed. The effectiveness and practicality of this algorithm are examined through simulation experiments and comparison with other baseline algorithms.

Multi-dimensional population balance modeling of sonocrystallization of pyrazinamide with systematic estimation of kinetic parameters based on uncertainty and sensitivity analyses

Application of ultrasound has several beneficial effects on both crystallization process and product crystal properties. This work focuses on experimental study and population balance modeling of ultrasound-assisted unseeded batch cooling crystallization of an important polymorphic pharmaceutical. The δ-polymorph of pyrazinamide, a drug for mycobacterium tuberculosis, exhibits plate-like morphology, and such crystals are best described by atleast two dimensions: length and width. A multi-dimensional population balance model for batch cooling sonocrystallization of pyrazinamide from its 1,4-dioxane solution is developed and validated. A series of experiments are performed with different ultrasound amplitudes (silent, 10%, and 50%) to study the effect of ultrasound on nucleation rate, crystal size, and polymorphism. The ultrasound is applied till the point of nucleation and an enhanced nucleation rate is introduced in the model in the presence of ultrasound irradiation. The various kinetic parameters are estimated following a systematic methodology based on uncertainty quantification and sensitivity analysis using experimental observations related to solute concentration and crystal size distribution. The Polynomial Chaos Expansion (PCE) is used to quantify the uncertainties in model prediction due to kinetic parameter uncertainties and sensitivity analysis is performed using total order Sobol’s sensitivity indices derived from PCE model. The kinetic parameters are estimated in two steps. First, a global search technique is used to simultaneously estimate all the kinetic parameters. Next, the less sensitive parameters are kept fixed and the more significant parameters are fine-tuned using a gradient-based local optimizer. Out of total nine kinetic parameters, only four parameters appeared to be significant for both silent and sonicated cases. The high-resolution finite volume scheme is used to solve the multi-dimensional population balance model and the simulation results agree very well with experimental data related to both concentration and crystal size distributions. The results revealed that compared to silent cases, sonication increased the nucleation rate by 102 times and 104 times for 10% and 50% amplitude, respectively. The growth rate was also enhanced significantly with increase in ultrasonic amplitude. All the experiments yielded the desired δ-polymorph of pyrazinamide.

Online machine learning approach for system marginal price forecasting using multiple economic indicators: A novel model for real-time decision making

In comparison to other countries, South Korea has a high reliance on energy, with the majority of its electricity being generated by a government-run company to ensure a stable and affordable supply. Unlike the "pay-as-bid" pricing approach, South Korea utilizes the system marginal price (SMP), also known as "pay-as-clear." Accurate SMP forecasting is crucial for guaranteeing steady economic growth because manufacturing is South Korea's flagship industry and accounts for 50 % of the nation's power consumption. In this study, a combination of machine learning-based batch learning and online learning techniques were employed to forecast the SMP in South Korea, utilizing a dataset consisting of five energy sectors, two financial sectors, and one transportation sector. The analysis of the F-value revealed that the coal sector, which is one of the energy sectors, had the most significant influence on SMP indicating the greatest score of 2,328. In this study, three machine learning models, namely support vector regression, simple deep neural network, and deep neural network, were suggested and compared for batch learning to determine the best-trained model. The evaluation metrics were used to assess the performance of these models. Based on the results obtained, the simple deep neural network was found to outperform the other models in terms of accuracy. Furthermore, two methods such as weight modification and time interval updating between inputs and output were employed for online learning based on the trained batch model. Upon the implementation of model updates, an ongoing assessment of its performance transpired utilizing the metrics of coefficient of determination, root mean square error, mean absolute error, and mean absolute percentage error. The average values for these metrics were observed to be 0.924, 7.991, 5.035, and 0.052, respectively. This study is expected to provide direct assistance in the formulation of energy plans for decision-makers in the industrial sector.

Analysis and multiple index evaluation of SPO distribution of bone traction needles for pelvic fracture reduction.

For robot-assisted pelvic fracture reduction, at least two bone needles need to be inserted into the ilium of the affected pelvis, and the robot clamping device is connected with the bone needles. The biomechanical properties of the pelvic musculoskeletal tissues are different with the different Spatial Position and Orientation (SPO) of the bone needles. In order to determine the optimal SPO of bone needle pairs, the constraints between the bone needles and the pelvis are analyzed, and the SPO vectors of 150 groups bone needles are obtained by the KNN-hierarchical clustering method; a batch modeling method of bone needles with different SPO is proposed. 150 finite element models of damaged pelvic musculoskeletal tissue with different SPO of bone needles are established and simulated. The stress and strain distribution homogenization of musculoskeletal tissue with bone needles as evaluation index, the simulation results of 150 models are evaluated. Results show that, the anterior superior iliac spine and the anterior inferior iliac spine are suitable regions to place bone needles in the pelvis, and the optimal distribution of the needle combination is found in this region. The overall stress and strain distribution of the damaged pelvic musculoskeletal tissue under the large reduction force is the best.

Anomaly detection with a container-based stream processing framework for Industrial Internet of Things

Online anomaly detection is a key challenge for industrial internet of things (IIoT) applications, as anomalies may occur in data streams from sensors and cause losses or damages. However, most existing methods for online anomaly detection have limitations in efficiency, effectiveness and timeliness, especially with the massive and distributed data streams from IIoT devices. Therefore, developing a data stream processing framework to discover anomalies in time and ensure the proper operation of the system is an urgent issue for IIoT. In this paper, we propose a flexible stream processing framework that enables online anomaly detection for IIoT applications. The framework exploits a distributed computing architecture based on docker containers to improve flexibility, migration capability and customization. The framework also uses a central mediator to coordinate data stream processing tasks running on different docker nodes. Moreover, we develop a prediction-based online anomaly detection model that consists of batch model training and data stream anomaly detection processes. The model uses long short-term memory (LSTM) neural networks to predict data stream values and a dynamic sliding window method to model prediction errors and detect anomalies. We implement a case study to detect abnormal heating temperatures from an industrial heating plant and evaluate the performance of the proposed framework and anomaly detection model. The results show that our framework and model can achieve high accuracy and low latency in detecting anomalies, and they outperform existing methods in terms of scalability, efficiency and adaptability for IIoT applications.

Feature subset selection in data-stream environments using asymmetric hidden Markov models and novelty detection

With the increase of computational power and memory capacity, it is possible to record and analyse lots of features of different nature in real time or in a data stream manner. Nonetheless, in many applications, not all variables may be relevant to explain the nature of the data. Feature subset selection strategies are therefore required to extract the relevant features to understand the data generating process. Much work has been performed in the area of supervised classification problems regarding feature selection, whereas for unsupervised environments, scarce studies have been conducted. In current feature subset selection methodologies for unsupervised data streams, the set of relevant variables are reevaluated or forgotten whenever a new instance or chunk of data arrives: this approach can be computationally expensive or unnecessary. Therefore, in this article, we provide a method to perform feature subset selection in unsupervised data streams. An embedded feature subset selection methodology based on asymmetric hidden Markov models and novel concept discovery strategies is used. This methodology can be used to detect novel concepts in data, and update the set of relevant features when a drift in the data stream is detected. Thus, the relevant variables are updated only when needed. To make this possible, we provide a model for batch and online problems, that is capable of dynamically determining the relevant variables to address feature selection in data streams. Additionally, the model provides domain insights using context-specific Bayesian networks which can be helpful to understand the dynamic process. To validate the proposed methodology, synthetic and real data from ball-bearings are used. Additionally, the proposed methodology is compared with other state of the art methodologies. The proposed method can be used to update the relevant features when needed and is more stable than its competitors.

Fatty Acid Epoxidation on Enzymes: Experimental Study and Modeling of Batch and Semibatch Operation

Biolubricants, plasticizers, bio-based rigid foams, and non-isocyanate polyurethanes can be made in a green way from epoxidized fatty acids. The classical technology for fatty acid epoxidation requires a reaction carrier, which acts as the real epoxidation agent. The process is complicated and involves a safety risk because of the appearance of percarboxylic acids. Therefore, the direct epoxidation of fatty acids in the presence of an immobilized enzyme is an attractive pathway to epoxidized fatty acids. Oleic acid was used as the model compound is this work, and commercial immobilized lipase Novozym 435 was used as the catalyst and hydrogen peroxide as the epoxidation agent. Batch and semibatch operation modes were tested in a laboratory-scale stirred tank reactor. The experimental results showed that almost complete conversions of the double bonds in oleic acid were achievable under isothermal batch and semibatch operation, with low concentrations of ring-opening byproducts. Semibatch operation gave an improvement of the product yield. Mathematical modeling of the experimental data was based on the reaction stoichiometry OA + HP → POA + W and OA + POA → EOA + OA, where OA = oleic acid, HP = hydrogen peroxide, POA = peroleic acid, W = water, and EOA = epoxized OA. Rate equations for the formation of peroleic acid and epoxide were derived, and the numerical values of the kinetic and adsorption parameters were estimated with nonlinear regression analysis. The reactor models consisted of ordinary differential equations, which were solved numerically during the parameter estimation until the optimal parameter values were reached. The model gave a very good description of the experimental data.

Biosorption potential of viable and dead Aspergillus flavus biomass on polluted pond water

The State Industries Promotion Corporation of Tamil Nadu Ltd (SIPCOT) Lake is never dry; it is always full of water and was recently used as a waste reservoir by the native peoples and industrialists. Thus, this investigation was performed to assess the quality of the lake water and evaluate the possible biosorption potential of Aspergillus flavus on this lake water sample through batch model biosorption study. The water quality parameters analyses revealed that the lake water has been polluted with number of contaminates which including organic and inorganic. The most of the parameters such as pH (9.5 ± 0.7), turbidity (38 ± 1.1 NT unit), TDS (2350.12 ± 31.24 mg L−1), BOD (40.21 ± 3.27 mg L−1), and COD (278.61 ± 11.84 mg L−1), Ca (212.85 ± 9.64 mg L−1), Fe (3.1 ± 0.8 mg L−1), NH3 (15.62 ± 0.5 mg L−1), NO3-(5.84 ± 0.14 mg L−1), Cl− (1257.85 ± 4.6 mg L−1),Cd (15.64 ± 0.29 mg L−1), Cr (6.86 ± 0.34 mg L−1), Pb (25.61 ± 3.41 mg L−1), and Hg (1.8 ± 0.024 mg L−1) content of water sample were beyond the acceptable limits. Fortunately, the A. flavus dead biomass showed considerable biosorption potential (Cd: 27.5 ± 1.1%, Cr: 13.48 ± 1.2%, Pb: 21.27 ± 1.5%, and Hg: 6.49 ± 0.86% in 180 min of contact time) than viable form on polluted lake water. Since, reduced the quantities of most of the parameters which beyond the permissible limit and also increased remarkable percentage of DO in the water sample in a short period of contact time. These findings suggest that A. flavus dead biomass can be used for bioremediation of polluted water in a sustainable manner.

Identifying novelties and anomalies for incremental learning in streaming time series forecasting

Time series data can be defined as a chronological sequence of observations on a variable of interest. A streaming time series is a time series that arrives continuously at high speed and has a data distribution that may change over time. Streaming time series data usually comes from electronic devices such as sensors and many of the applications dealing with streaming data in Industry 4.0 require real-time responses. Performing real-time forecasting offers the possibility to consider new types of patterns in the incoming streaming data, which is not possible when working with batch models. This paper presents a new approach to detect novelties and anomalies in real-time using a nearest-neighbors based forecasting algorithm. The algorithm works with an offline base model that is updated as stream data arrives following an incremental learning approach. It detects unknown patterns called novelties and anomalies. Novelties are included in the model in an online way and anomalies trigger an alarm as they present unexpected behaviors that need to be specifically analyzed. The algorithm has been tested with Spanish electricity demand data. Results show that the prediction errors obtained when the model is updated considering novelties and anomalies are lower than the errors obtained when the model is not updated. Thus, the model adjusts in real-time to the new patterns of data providing accurate errors and real-time predictions.