HCSRL: hyperledger composer system for reducing logistics losses in the pharmaceutical product supply chain using a blockchain-based approach

Blockchain technology uses a secure and decentralised framework for transaction management and data sharing within supply chains. This is particularly crucial in the pharmaceutical industry, where product authenticity and traceability are paramount. Blockchain plays a pivotal role in preventing product loss and counterfeiting, while simultaneously enhancing transparency and efficiency throughout the supply chain. The research introduces a step-by-step approach to implementing a proof-of-concept (PoC) for Supply Chain Risk Management (SCRM) through blockchain technology. This PoC involves simulating a supply chain process to assess feasibility and measure key performance indicators. Engaging stakeholders and gathering feedback is integral to refining the blockchain-based SCRM system. The study rigorously evaluates the performance of the SCRM blockchain across various test scenarios, featuring differing numbers of organizations and clients. Multiple fabric networks are employed to assess the system's scalability and performance under diverse conditions. The results of these comprehensive tests inform practical deployment decisions and highlight areas for potential optimization and further development. So this research provides valuable insights into the application of blockchain in pharmaceutical supply chains, offering a roadmap for implementation and improving supply chain security, efficiency, and transparency.

Knotted artifacts in predicted 3D RNA structures

Unlike proteins, RNAs deposited in the Protein Data Bank do not contain topological knots. Recently, admittedly, the first trefoil knot and some lasso-type conformations have been found in experimental RNA structures, but these are still exceptional cases. Meanwhile, algorithms predicting 3D RNA models have happened to form knotted structures not so rarely. Interestingly, machine learning-based predictors seem to be more prone to generate knotted RNA folds than traditional methods. A similar situation is observed for the entanglements of structural elements. In this paper, we analyze all models submitted to the CASP15 competition in the 3D RNA structure prediction category. We show what types of topological knots and structure element entanglements appear in the submitted models and highlight what methods are behind the generation of such conformations. We also study the structural aspect of susceptibility to entanglement. We suggest that predictors take care of an evaluation of RNA models to avoid publishing structures with artifacts, such as unusual entanglements, that result from hallucinations of predictive algorithms.

Source term estimation for continuous plume dispersion in Fusion Field Trial-07: Bayesian inference probability adjoint inverse method

In scenarios involving sudden releases of unidentified gases or concealed pollution emergencies, source control emerges as a critical procedure to safeguard residential air quality. Appropriate inverse source tracking methodology depending on diverse measurement data could be utilized to promptly identify pollutant source parameters. In this study, source term estimation (STE) method, i.e., jointly combining probability adjoint method with the Bayesian inference method, has been proposed. General form of the pollutant inverse transport equation was firstly established. Subsequently, the pollution source information, assumed from single continuous point releases during Fusion Field Trials 2007 under an unsteady wind field, was identified using the Bayesian inference probability adjoint inverse method. Metropolis-Hastings Markov Chain Monte Carlo (MH-MCMC) and Differential Evolution Markov Chain Monte Carlo (DE-MCMC) were then compared as sampling methods for Bayesian inference. Results indicated that the DE-MCMC algorithm has superior convergence and could present higher accuracy of pollutant source information than that of MH-MCMC algorithm, particularly for highly nonlinear and multi-modal distribution systems. Furthermore, the integration of Union standard Adjoint Location Probability (UALP) as prior information into the Bayesian inference probability adjoint inverse method effectively narrowed the sampling range, enhancing both the accuracy and robustness of the proposed approach. Finally, the impact of the covariance matrix on the inverse identification accuracy was explored. Overall, this research has provided insights into the future applicability of this Bayesian inference inversion technique for point source identification.

Replacement of failed items in a two commodity retrial queueing-inventory system with multi-component demand and vacation interruption

This study investigates a crucial aspect of inventory management, which is the process of replacing failed items. In dynamic commercial environments, it is essential to efficiently and strategically replace failed items to maintain operational efficiency and ensure profitability. We consider a two-commodity retrial queueing-inventory system with vacation interruption. Upon purchasing the first commodity, the second commodity is provided as a complimentary item. In contrast, no item is given as a complimentary for the purchase of the second item. Only the first commodity is stored in a dedicated pooled storage for replacement when it fails. The ( s , Q ) policy governs replenishing the first commodity while the second is replenished through instantaneous ordering. The model considers the multi-component demand rate for customer arrivals. Server vacations are initiated during customer absence in waiting hall or when the first commodity is unavailable. We formulate a level-dependent quasi-birth-and-death process, and its steady-state probability vector is computed using Neuts and Rao's truncation method. The stability condition for the system is derived, and various system performance measures, including expected total cost, number of replaceable items, and customers in the waiting hall and orbit, are established. The comparative analysis between the system with replacement is done with the regular model without replacement, which revealed the efficiency of replacement. The analysis of multi-component demand towards homogeneous arrival highlights the impact of multi-component demand on boosting customer arrival. Also, parametric sensitivity analysis has been conducted numerically over total cost, mean number of failed items for replacement, and mean number of customers in the waiting hall and orbit.

Fall risk classification with posturographic parameters in community-dwelling older adults: a machine learning and explainable artificial intelligence approach

BACKGROUND

Computerized posturography obtained in standing conditions has been applied to classify fall risk for older adults or disease groups. Combining machine learning (ML) approaches is superior to traditional regression analysis for its ability to handle complex data regarding its characteristics of being high-dimensional, non-linear, and highly correlated. The study goal was to use ML algorithms to classify fall risks in community-dwelling older adults with the aid of an explainable artificial intelligence (XAI) approach to increase interpretability.

METHODS

A total of 215 participants were included for analysis. The input information included personal metrics and posturographic parameters obtained from a tracker-based posturography of four standing postures. Two classification criteria were used: with a previous history of falls and the timed-up-and-go (TUG) test. We used three meta-heuristic methods for feature selection to handle the large numbers of parameters and improve efficacy, and the SHapley Additive exPlanations (SHAP) method was used to display the weights of the selected features on the model.

RESULTS

The results showed that posturographic parameters could classify the participants with TUG scores higher or lower than 10 s but were less effective in classifying fall risk according to previous fall history. Feature selections improved the accuracy with the TUG as the classification label, and the Slime Mould Algorithm had the best performance (accuracy: 0.72 to 0.77, area under the curve: 0.80 to 0.90). In contrast, feature selection did not improve the model performance significantly with the previous fall history as a classification label. The SHAP values also helped to display the importance of different features in the model.

CONCLUSION

Posturographic parameters in standing can be used to classify fall risks with high accuracy based on the TUG scores in community-dwelling older adults. Using feature selection improves the model's performance. The results highlight the potential utility of ML algorithms and XAI to provide guidance for developing more robust and accurate fall classification models. Trial registration Not applicable.

Key Therapeutic Targets to Treat Hyperglycemia-Induced Atherosclerosis Analyzed Using a Petri Net-Based Model

Chronic superphysiological glucose concentration is a hallmark of diabetes mellitus (DM) and a cause of damage to many types of cells. Atherosclerosis coexists with glucose metabolism disturbances, constituting a significant problem and exacerbating its complications. Atherosclerosis in DM is accelerated, so it is vital to slow its progression. However, from the complex network of interdependencies, molecules, and processes involved, choosing which ones should be inhibited without blocking the pathways crucial for the organism's functioning is challenging. To conduct this type of analysis, in silicotesting comes in handy. In our study, to identify sites in the network that need to be blocked to have an inhibitory effect on atherosclerosis in hyperglycemia, which is toxic for the human organism, we created a model using Petri net theory and performed analyses. We have found that blocking isoforms of protein kinase C (PKC)-PKCβ and PKCγ-in diabetic patients can contribute to the inhibition of atherosclerosis progression. In addition, we have discovered that aldose reductase inhibition can slow down atherosclerosis progression, and this has been shown to reduce PKC (β and γ) expression in DM. It has also been observed that diminishing oxidative stress through the inhibitory effect on the AGE-RAGE axis may be a promising therapeutic approach in treating hyperglycemia-induced atherosclerosis. Moreover, the blockade of NADPH oxidase, the key enzyme responsible for the formation of reactive oxygen species (ROS) in blood vessels, only moderately slowed down atherosclerosis development. However, unlike aldose reductase blockade, or direct PKC (β and γ), the increased production of mitochondrial ROS associated with mitochondrial dysfunction effectively stopped after NADPH oxidase blockade. The results obtained may constitute the basis for further in-depth research.

Go-Game Image Recognition Based on Improved Pix2pix

Go is a game that can be won or lost based on the number of intersections surrounded by black or white pieces. The traditional method is a manual counting method, which is time-consuming and error-prone. In addition, the generalization of the current Go-image-recognition methods is poor, and accuracy needs to be further improved. To solve these problems, a Go-game image recognition based on an improved pix2pix was proposed. Firstly, a channel-coordinate mixed-attention (CCMA) mechanism was designed by combining channel attention and coordinate attention effectively; therefore, the model could learn the target feature information. Secondly, in order to obtain the long-distance contextual information, a deep dilated-convolution (DDC) module was proposed, which densely linked the dilated convolution with different dilated rates. The experimental results showed that compared with other existing Go-image-recognition methods, such as DenseNet, VGG-16, and Yolo v5, the proposed method could effectively improve the generalization ability and accuracy of a Go-image-recognition model, and the average accuracy rate was over 99.99%.

Emotional experiences of service robots' anthropomorphic appearance: a multimodal measurement method

Anthropomorphic appearance is a key factor to affect users' attitudes and emotions. This research aimed to measure emotional experience caused by robots' anthropomorphic appearance with three levels - high, moderate, and low - using multimodal measurement. Fifty participants' physiological and eye-tracker data were recorded synchronously while they observed robot images that were displayed in random order. Afterward, the participants reported subjective emotional experiences and attitudes towards those robots. The results showed that the images of the moderately anthropomorphic service robots induced higher pleasure and arousal ratings, and yielded significantly larger pupil diameter and faster saccade velocity, than did the low or high robots. Moreover, participants' facial electromyography, skin conductance, and heart-rate responses were higher when observing moderately anthropomorphic service robots. An implication of the research is that service robots' appearance should be designed to be moderately anthropomorphic; too many human-like features or machine-like features may disturb users' positive emotions and attitudes.Practitioner Summary: This research aimed to measure emotional experience caused by three types of anthropomorphic service robots using a multimodal measurement experiment. The results showed that moderately anthropomorphic service robots evoked more positive emotion than high and low anthropomorphic robots. Too many human-like features or machine-like features may disturb users' positive emotions.

RNA tertiary structure prediction using RNAComposer in CASP15

As CASP15 participants, in the new category of 3D RNA structure prediction, we applied expert modeling with the support of our proprietary system RNAComposer. Although RNAComposer is primarily known as an automated web server, its features allow it to be used interactively, for example, for homology-based modeling or assembling models from user-provided structural elements. In the paper, we present various scenarios of applying the system to predict the 3D RNA structures that we employed. Their combination with expert input, comparative analysis of models, and routines to select representative resultant structures form a ready-for-reuse workflow. With selected examples, we demonstrate its application for the in silico modeling of natural and synthetic RNA molecules targeted in CASP15.

Generalized vehicle routing problem: Contemporary trends and research directions

Generalized Vehicle Routing Problem (GVRP) is a challenging operational research problem which has been widely studied for nearly two decades. In this problem, it is assumed that graph nodes are grouped into a number of clusters, and serving any node of a cluster eliminates the need to visit the other nodes of that cluster. The general objective of this problem is to find the set of nodes to visit and determine the service sequence to minimize the total traveling cost. In addition to these general conditions, GVRP can be formulated with different assumptions and constraints to practically create different sub-types and variants. This paper aims to provide a comprehensive survey of the GVRP literature and explore its various dimensions. It first encompasses the definition of GVRP, similar problems, mathematical models, classification of different variants and solution methods developed for GVRPs, and practical implications. Finally, some useful suggestions are discussed to extend the problem. For this review study, Google Scholar, Scopus, Science Direct, Emerald, Springer, and Elsevier databases were searched for keywords, and 160 potential articles were extracted, and eventually, 45 articles were judged to be relevant.

Towards a Corpus (and Language)-Independent Screening of Parkinson's Disease from Voice and Speech through Domain Adaptation

End-to-end deep learning models have shown promising results for the automatic screening of Parkinson's disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These facts indicate a lack of generalisation or the presence of certain shortcuts in the decision, and also suggest the need for developing new corpus-independent models. In this respect, this work explores the use of domain adversarial training as a viable strategy to develop models that retain their discriminative capacity to detect Parkinson's disease across diverse datasets. The paper presents three deep learning architectures and their domain adversarial counterparts. The models were evaluated with sustained vowels and diadochokinetic recordings extracted from four corpora with different demographics, dialects or languages, and recording conditions. The results showed that the space distribution of the embedding features extracted by the domain adversarial networks exhibits a higher intra-class cohesion. This behaviour is supported by a decrease in the variability and inter-domain divergence computed within each class. The findings suggest that domain adversarial networks are able to learn the common characteristics present in Parkinsonian voice and speech, which are supposed to be corpus, and consequently, language independent. Overall, this effort provides evidence that domain adaptation techniques refine the existing end-to-end deep learning approaches for Parkinson's disease detection from voice and speech, achieving more generalizable models.

Hybrid deep learning model based smart IOT based monitoring system for Covid-19

Recently, COVID-19 becomes a hot topic and explicitly made people follow social distancing and quarantine practices all over the world. Meanwhile, it is arduous to visit medical professionals intermittently by the patients for fear of spreading the disease. This IoT-based healthcare monitoring system is utilized by many professionals, can be accessed remotely, and provides treatment accordingly. In context with this, we designed an IoT-based healthcare monitoring system that sophisticatedly measures and monitors the parameters of patients such as oxygen level, blood pressure, temperature, and heart rate. This system can be widely used in rural areas that are linked to the nearest city hospitals to monitor the patients. The collected data from the monitoring system are stored in the cloud-based data storage and for the classification our approach proposes an innovative Recurrent Convolutional Neural Network (RCNN) based Puzzle optimization algorithm (PO). Based on the outcome further treatments are made with the assistance of physicians. Experimental analyses are made and analyzed the performance with state-of-art works. The availability of more data storage capacity in the cloud can make physicians access the previous data effortlessly.

A paradigmatic approach to the molecular descriptor computation for some antiviral drugs

In theoretical chemistry, topological indices are commonly employed to model the physico-chemical properties of chemical compounds. Mathematicians frequently use Zagreb indices to calculate a chemical compound's strain energy, melting point, boiling temperature, distortion, and stability. The current global pandemic caused by the new SARS-CoV-2, also known as COVID-19, is a significant public health concern. Various therapy modalities are advised. The issue has become worse since there hasn't been enough counseling. Researchers are looking at compounds that might be used as SARS and MERS therapies based on earlier studies. In several quantitative structure-property-activity relationships (QSPR and QSAR) studies, a variety of physiochemical properties are successfully represented by topological indices, a sort of molecular descriptor that just specifies numerical values connected to a substance's molecular structure. This study investigates several irregularity-based topological indices for various antiviral medicines, depending on the degree of irregularity. In order to evaluate the effectiveness of the generated topological indices, a QSPR was also carried out using the indicated pharmaceuticals, the various topological indices, and the various physiochemical features of these antiviral medicines. The acquired results show a substantial association between the topological indices being studied by the curve-fitting approach and the physiochemical properties of possible antiviral medicines.

Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model

Introduction

Breast cancer stands as the second most deadly form of cancer among women worldwide. Early diagnosis and treatment can significantly mitigate mortality rates.

Purpose

The study aims to classify breast ultrasound images into benign and malignant tumors. This approach involves segmenting the breast's region of interest (ROI) employing an optimized UNet architecture and classifying the ROIs through an optimized shallow CNN model utilizing an ablation study.

Method

Several image processing techniques are utilized to improve image quality by removing text, artifacts, and speckle noise, and statistical analysis is done to check the enhanced image quality is satisfactory. With the processed dataset, the segmentation of breast tumor ROI is carried out, optimizing the UNet model through an ablation study where the architectural configuration and hyperparameters are altered. After obtaining the tumor ROIs from the fine-tuned UNet model (RKO-UNet), an optimized CNN model is employed to classify the tumor into benign and malignant classes. To enhance the CNN model's performance, an ablation study is conducted, coupled with the integration of an attention unit. The model's performance is further assessed by classifying breast cancer with mammogram images.

Result

The proposed classification model (RKONet-13) results in an accuracy of 98.41 %. The performance of the proposed model is further compared with five transfer learning models for both pre-segmented and post-segmented datasets. K-fold cross-validation is done to assess the proposed RKONet-13 model's performance stability. Furthermore, the performance of the proposed model is compared with previous literature, where the proposed model outperforms existing methods, demonstrating its effectiveness in breast cancer diagnosis. Lastly, the model demonstrates its robustness for breast cancer classification, delivering an exceptional performance of 96.21 % on a mammogram dataset.

Conclusion

The efficacy of this study relies on image pre-processing, segmentation with hybrid attention UNet, and classification with fine-tuned robust CNN model. This comprehensive approach aims to determine an effective technique for detecting breast cancer within ultrasound images.

Automatic identification and morphological comparison of bivalve and brachiopod fossils based on deep learning

Fossil identification is an essential and fundamental task for conducting palaeontological research. Because the manual identification of fossils requires extensive experience and is time-consuming, automatic identification methods are proposed. However, these studies are limited to a few or dozens of species, which is hardly adequate for the needs of research. This study enabled the automatic identification of hundreds of species based on a newly established fossil dataset. An available "bivalve and brachiopod fossil image dataset" (BBFID, containing >16,000 "image-label" data pairs, taxonomic determination completed) was created. The bivalves and brachiopods contained in BBFID are closely related in morphology, ecology and evolution that have long attracted the interest of researchers. We achieved >80% identification accuracy at 22 genera and ∼64% accuracy at 343 species using EfficientNetV2s architecture. The intermediate output of the model was extracted and downscaled to obtain the morphological feature space of fossils using t-distributed stochastic neighbor embedding (t-SNE). We found a distinctive boundary between the morphological feature points of bivalves and brachiopods in fossil morphological feature distribution maps. This study provides a possible method for studying the morphological evolution of fossil clades using computer vision in the future.

Classification of melanonychia, Beau's lines, and nail clubbing based on nail images and transfer learning techniques

Background

Nail diseases are malformations that appear on the nail plate and are classified according to their own signs and symptoms that may be related to other medical conditions. Although most nail diseases have distinct symptoms, making a differential diagnosis of nail problems can be challenging for medical experts.

Method

One early diagnosis method for any dermatological disease is designing an image analysis system based on artificial intelligence (AI) techniques. This article implemented a novel model using a publicly available nail disease dataset to determine the occurrence of three common types of nail diseases. Two classification models based on transfer learning using visual geometry group (VGGNet) were utilized to detect and classify nail diseases from images.

Result and Finding

The experimental design results showed good accuracy: VGG16 had a score of 94% accuracy and VGG19 had a 93% accuracy rate. These findings suggest that computer-aided diagnostic systems based on transfer learning can be used to identify multiple-lesion nail diseases.

Machine Learning Methods for Small Data Challenges in Molecular Science

Small data are often used in scientific and engineering research due to the presence of various constraints, such as time, cost, ethics, privacy, security, and technical limitations in data acquisition. However, big data have been the focus for the past decade, small data and their challenges have received little attention, even though they are technically more severe in machine learning (ML) and deep learning (DL) studies. Overall, the small data challenge is often compounded by issues, such as data diversity, imputation, noise, imbalance, and high-dimensionality. Fortunately, the current big data era is characterized by technological breakthroughs in ML, DL, and artificial intelligence (AI), which enable data-driven scientific discovery, and many advanced ML and DL technologies developed for big data have inadvertently provided solutions for small data problems. As a result, significant progress has been made in ML and DL for small data challenges in the past decade. In this review, we summarize and analyze several emerging potential solutions to small data challenges in molecular science, including chemical and biological sciences. We review both basic machine learning algorithms, such as linear regression, logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), kernel learning (KL), random forest (RF), and gradient boosting trees (GBT), and more advanced techniques, including artificial neural network (ANN), convolutional neural network (CNN), U-Net, graph neural network (GNN), Generative Adversarial Network (GAN), long short-term memory (LSTM), autoencoder, transformer, transfer learning, active learning, graph-based semi-supervised learning, combining deep learning with traditional machine learning, and physical model-based data augmentation. We also briefly discuss the latest advances in these methods. Finally, we conclude the survey with a discussion of promising trends in small data challenges in molecular science.

Polymeric Materials Selection for Flexible Pulsating Heat Pipe Manufacturing Using a Comparative Hybrid MCDM Approach

The right choice of polymeric materials plays a vital role in the successful design and manufacture of flexible fluidic systems, as well as heat transfer devices such as pulsating heat pipes. The decision to choose an acceptable polymeric material entails a variety of evaluation criteria because there are numerous competing materials available today, each with its own properties, applications, benefits, and drawbacks. In this study, a comparative hybrid multi-criteria decision-making (MCDM) model is proposed for evaluating suitable polymeric materials for the fabrication of flexible pulsating heat pipes. The decision model consists of fourteen evaluation criteria and twelve alternative materials. For this purpose, three different hybrid MCDM methods were applied to solve the material selection problems (i.e., AHP-GRA, AHP-CoCoSo, and AHP-VIKOR). According to the results obtained, PTFE, PE, and PP showed promising properties. In addition, Spearman's rank correlation analysis was performed, and the hybrid methods used produced consistent rankings with each other. By applying MCDM methods, it was concluded that PTFE is the most suitable material to be preferred for manufacturing flexible pulsating heat pipes. In addition to this result, PE and PP are among the best alternatives that can be recommended after PTFE. The study supports the use of MCDM techniques to rank material choices and enhance the selection procedure. The research will greatly assist industrial managers and academics involved in the selection process of polymeric materials.

Supply chain planning of vaccine and pharmaceutical clusters under uncertainty: The case of COVID-19

As an abrupt epidemic occurs, healthcare systems are shocked by the surge in the number of susceptible patients' demands, and decision-makers mostly rely on their frame of reference for urgent decision-making. Many reports have declared the COVID-19 impediments to trading and global economic growth. This study aims to provide a mathematical model to support pharmaceutical supply chain planning during the COVID-19 epidemic. Additionally, it aims to offer new insights into hospital supply chain problems by unifying cold and non-cold chains and considering a wide range of pharmaceuticals and vaccines. This approach is unprecedented and includes an analysis of various pharmaceutical features such as temperature, shelf life, priority, and clustering. To propose a model for planning the pharmaceutical supply chains, a mixed-integer linear programming (MILP) model is used for a four-echelon supply chain design. This model aims to minimize the costs involved in the pharmaceutical supply chain by maintaining an acceptable service level. Also, this paper considers uncertainty as an intrinsic part of the problem and addresses it through the wait-and-see method. Furthermore, an unexplored unsupervised learning method in the realm of supply chain planning has been used to cluster the pharmaceuticals and the vaccines and its merits and drawbacks are proposed. A case of Tehran hospitals with real data has been used to show the model's capabilities, as well. Based on the obtained results, the proposed approach is able to reach the optimum service level in the COVID conditions while maintaining a reduced cost. The experiment illustrates that the hospitals' adjacency and emergency orders alleviated the service level significantly. The proposed MILP model has proven to be efficient in providing a practical intuition for decision-makers. The clustering technique reduced the size of the problem and the time required to solve the model considerably.

Designing the home healthcare supply chain during a health crisis

During the COVID-19 pandemic, sectoral contributors to home healthcare supply chain (HHCSC) corporations highlighted the role of home care services. Pharmacies are located where patients are allocated to them, and nurses are routed and scheduled according to their patients' needs. It is the first study to propose an integrated location-allocation-routing model, which includes all preliminaries necessary to make these decisions. We implement the LP-metric and epsilon-constraint methods to solve this model, and then we discuss the results of these methods. A comparison is also made regarding the objective function values and the time taken to solve the problem. The average, mean ideal distance (MID) (3.74; 3.19), the rate of achievement of two objectives simultaneously (RAS) (1.71; 3.56), and computational time (CPU time) (1.92; 24.92) for two ɛ-constraint and LP-Metric methods is calculated. The superior technique is finally selected by utilizing the TOPSIS. To solve the study’s mathematical model, the LP-metric method is worth implementing. Based on these results, the suggested model for HHCSC companies, and employees’ performance, is efficient during the COVID-19 pandemic.

Effects of transport-carbon intensity, transportation, and economic complexity on environmental and health expenditures

Health and the environment are complex components of the countries, influenced by several factors, especially transport, and economics. Thus, this paper assesses the role of transportation and economic complexity in the environment and public health for the Organization for Economic Co-operation Development (OECD) countries from 2001 to 2020. This study also focuses on the relationship between transport and economic complexity with environmental and healthcare expenditures. Precisely, transport and economic activities stimulate healthcare expenditures through multiple channels. The current study employs the STIRPAT model to investigate the association with transportation, economic complexity, transport-carbon intensity, and healthcare expenditure. Besides, the current research confirms the plausible cross-sectional dependency across countries, and it adopts a second-generation technique. Analytical findings suggest that transportation-carbon intensity is positively and significantly associated with healthcare expenditures. Healthcare and transport-household expenditures increase transport-carbon intensity (TCI) by 75% and 45%, respectively, in the long run. In the contrast, TCI and transport-household expenditures have also a remarkable impact on healthcare expenditures and are estimated approximately 95% in the long run. Moreover, economic growth also upsurges TCI and healthcare expenditures through multiple economic activities. Besides, transport-household expenditures (THE) drastically impact transport-carbon intensity and healthcare expenditures (HEX) through passenger traffic (PTF). Diagnostic upshots unveil that the joint effect of THE and PTF increases TCI and HEX by 4 and 3%, respectively. Finally, findings recommend some policy implications and future research directions for the countries based on empirical outcomes. Countries should regulate economic activities to reduce transport carbon emissions.

Machine learning for RNA 2D structure prediction benchmarked on experimental data

Since the 1980s, dozens of computational methods have addressed the problem of predicting RNA secondary structure. Among them are those that follow standard optimization approaches and, more recently, machine learning (ML) algorithms. The former were repeatedly benchmarked on various datasets. The latter, on the other hand, have not yet undergone extensive analysis that could suggest to the user which algorithm best fits the problem to be solved. In this review, we compare 15 methods that predict the secondary structure of RNA, of which 6 are based on deep learning (DL), 3 on shallow learning (SL) and 6 control methods on non-ML approaches. We discuss the ML strategies implemented and perform three experiments in which we evaluate the prediction of (I) representatives of the RNA equivalence classes, (II) selected Rfam sequences and (III) RNAs from new Rfam families. We show that DL-based algorithms (such as SPOT-RNA and UFold) can outperform SL and traditional methods if the data distribution is similar in the training and testing set. However, when predicting 2D structures for new RNA families, the advantage of DL is no longer clear, and its performance is inferior or equal to that of SL and non-ML methods.

Identifying and ranking key technological capabilities in supply chain sustainability using ISM approach: case of food industry in Iran

The food industry is one of the strategic industries in developing countries, such as Iran and plays a critical role in the economy, food security, and public health. The growing populations can only have food security when the food industry's supply chain is sustainable. Therefore, due to the sustainable food supply chain's great importance, having technological capabilities compared to others is considered a competitive advantage for the companies involved in the food industry, as it can distinguish them as pioneer actors. Although many technologies have been investigated and used in the sustainable supply chain recently, no study has focused on identifying and ranking key technological capabilities related to the food industry in sustainable supply chain management. Also, we have not found any study using the ISM-MICMAC method to identify, rank, and interdependence between key technology capabilities in supply chain sustainability. Accordingly, the present study sought to identify and rank key technological capabilities in the supply chain sustainability of food industry companies. In this study, after reviewing the relevant literature, eleven technological capabilities in supply chain sustainability were identified. Then using experts' opinions and Interpretive Structural Modelling (ISM), interdependence among the technological capabilities ranked. Finally, dependent and independent drivers were presented using the MICMAC analysis. The ISM analysis results indicated that communication and information technology infrastructure was the most significant driver for other technological capabilities in companies' supply chain sustainability. Moreover, logistic optimization is imperative for improving supply chain sustainability performance. Therefore, if logistic optimization is appropriately implemented, it can improve supply chain sustainability. The present study results can increase supply chain productivity and effectiveness in Iranian food industry companies.

A novel computational fluid dynamic method and validation for assessing distal cerebrovascular microcirculatory resistance

BACKGROUND AND OBJECTIVE

The non-invasive assessment of microcirculatory resistance could improve the treatment of cerebrovascular stenosis. This study aimed to validate a novel computational strategy for determining the reference value of microcirculatory resistance in patients with cerebrovascular stenosis.

METHODS

We reconstructed a patient-specific 3-dimensional model of the extracranial-intracranial arteries. A computational strategy incorporating patient-specific pressure-wire measurements was developed to estimate the blood flow rate and microcirculatory resistance. Throughout the computational fluid dynamics (CFD) simulation, the boundary conditions were adjusted according to the developed algorithm. Pearson correlation and Bland-Altman analyses were used to quantify the correlation and agreement between CFD calculations and transcranial Doppler (TCD) assessment.

RESULTS

A strong correlation was found between the CFD-based and invasive distal pressure measurements (P<0.0001). Meanwhile, the CFD and TCD-based flow measurements were highly correlated (r = 0.853; P = 0.001). Furthermore, there was a correlation between the mean velocity measured by CFD and the mean velocity measured by TCD (r = 0.777; P<0.001). Good agreement was observed between the mass flow by CFD simulation and volumetric flow by TCD (P = 0.0266, mean difference: -0.7814 mmHg, limits of agreement, -4.0905 - 2.5276). However, the mean velocities from CFD simulation were in less agreement with those from the TCD assessment (P = 0.3992, mean difference, -0.0485; limits of agreement, -0.6141 - 0.5170). Results of the CFD simulation indicate that the flow resistance varies greatly between individuals.

CONCLUSIONS

The computational strategy of incorporating patient-specific pressure-wire measurements may serve as an effective approach to evaluate the actual reference values of microcirculatory resistance. In addition, an individualized assessment of non-invasive flow resistance is necessary for the accurate determination of non-invasive cerebrovascular pressure.

Obscene image detection using transfer learning and feature fusion

Deep learning-based methods have been proven excellent performance in detecting pornographic images/videos flooded on social media. However, in a dearth of huge yet well-labeled datasets, these methods may suffer from under/overfitting problems and may exhibit unstable output responses in the classification process. To deal with the issue we have suggested an automatic pornographic image detection method by utilizing transfer learning (TL) and feature fusion. The novelty of our proposed work is TL based feature fusion process (FFP) which enables the removal of hyper-parameter tuning, improves model performance, and lowers the computational burden of the desired model. FFP fuses low-level and mid-level features of the outperforming pre-trained models followed by transferring the learned knowledge to control the classification process. Key contributions of our proposed method are i) generation of a well-labeled obscene image dataset GGOI via Pix-2-Pix GAN architecture for the training of deep learning models ii) modification of model architectures by integrating batch normalization and mixed pooling strategy to obtain training stability (iii) selection of outperforming models to be integrated with the FFP by performing end-to-end detection of obscene images and iv) design of TL based obscene image detection method by retraining the last layer of the fused model. Extensive experimental analyses are performed on benchmark datasets i.e., NPDI, Pornography 2k, and generated GGOI dataset. The proposed TL model with fused MobileNet V2 + DenseNet169 network performs as the state-of-the-art model compared to existing methods and provides average classification accuracy, sensitivity, and F1 score of 98.50%, 98.46% and 98.49% respectively.

A Novel Parallel Simulated Annealing Methodology to Solve the No-Wait Flow Shop Scheduling Problem with Earliness and Tardiness Objectives

In this paper, the no-wait flow shop problem with earliness and tardiness objectives is considered. The problem is proven to be NP-hard. Recent no-wait flow shop problem studies focused on familiar objectives, such as makespan, total flow time, and total completion time. However, the problem has limited studies with solution approaches covering the concomitant use of earliness and tardiness objectives. A novel methodology for the parallel simulated annealing algorithm is proposed to solve this problem in order to overcome the runtime drawback of classical simulated annealing and enhance its robustness. The well-known flow shop problem datasets in the literature are utilized for benchmarking the proposed algorithm, along with the classical simulated annealing, variants of tabu search, and particle swarm optimization algorithms. Statistical analyses were performed to compare the runtime and robustness of the algorithms. The results revealed the enhancement of the classical simulated annealing algorithm in terms of time consumption and solution robustness via parallelization. It is also concluded that the proposed algorithm could outperform the benchmark metaheuristics even when run in parallel. The proposed algorithm has a generic structure that can be easily adapted to many combinatorial optimization problems.

An ensemble fraud detection approach for online loans based on application usage patterns

The fraud problem has drastically increased with the rapid growth of online lending. Since loan applications, approvals and disbursements are operated online, deceptive borrowers are prone to conceal or falsify information to maliciously obtain loans, while lenders have difficulty in identifying fraud without direct contacts and lack binding force on customers’ loan performance, which results in the frequent occurrence of fraud events. Therefore, it is significant for financial institutions to apply valuable data and competitive technologies for fraud detection to reduce financial losses from loan scams. This paper combines the advantages of statistical methods and ensemble learning algorithms to design the grouped trees and weighted ensemble algorithm (GTWE), and establishes fraud prediction models for online loans based on mobile application usage behaviors(App behaviors) by logistic regression, extreme gradient boosting (XGBoost), long short-term memory (LSTM) and the GTWE algorithm, respectively. The experimental results show that the fraud prediction model based on the GTWE algorithm achieves outstanding classification effect and stability with satisfactory interpretability. Meanwhile, the fraud probability of customers detected by the fraud prediction model is as high as 84.19%, which indicates that App behaviors have a considerable impact on predicting fraud in online loan application.

Eye-in-Hand Robotic Arm Gripping System Based on Machine Learning and State Delay Optimization

This research focused on using RGB-D images and modifying an existing machine learning network architecture to generate predictions of the location of successfully grasped objects and to optimize the control system for state delays. A five-finger gripper designed to mimic the human palm was tested to demonstrate that it can perform more delicate missions than many two- or three-finger grippers. Experiments were conducted using the 6-DOF robot arm with the five-finger and two-finger grippers to perform at least 100 actual machine grasps, and compared to the results of other studies. Additionally, we investigated state time delays and proposed a control method for a robot manipulator. Many studies on time-delay systems have been conducted, but most focus on input and output delays. One reason for this emphasis is that input and output delays are the most commonly occurring delays in physical or electronic systems. An additional reason is that state delays increase the complexity of the overall control system. Finally, it was demonstrated that our network can perform as well as a deep network architecture with little training data and omitting steps, such as posture evaluation, and when combined with the hardware advantages of the five-finger gripper, it can produce an automated system with a gripping success rate of over 90%. This paper is an extended study of the conference paper.

Listening to what the system tells us: Innovative auditing for distributed systems

Introduction

In recent years, software ecosystems have become more complex with the proliferation of distributed systems such as blockchains and distributed ledgers. Effective management of these systems requires constant monitoring to identify any potential malfunctions, anomalies, vulnerabilities, or attacks. Traditional log auditing methods can effectively monitor the health of conventional systems. Yet, they run short of handling the higher levels of complexity of distributed systems. This study aims to propose an innovative architecture for system auditing that can effectively manage the complexity of distributed systems using advanced data analytics, natural language processing, and artificial intelligence.

Methods

To develop this architecture, we considered the unique characteristics of distributed systems and the various signals that may arise within them. We also felt the need for flexibility to capture these signals effectively. The resulting architecture utilizes advanced data analytics, natural language processing, and artificial intelligence to analyze and interpret the various signals emitted by the system.

Results

We have implemented this architecture in the DELTA (Distributed Elastic Log Text Analyzer) auditing tool and applied it to the Hyperledger Fabric platform, a widely used implementation of private blockchains.

Discussion

The proposed architecture for system auditing can effectively handle the complexity of distributed systems, and the DELTA tool provides a practical implementation of this approach. Further research could explore this approach's potential applications and effectiveness in other distributed systems.

A Deep Batch Normalized Convolution Approach for Improving COVID-19 Detection from Chest X-ray Images

Pre-trained machine learning models have recently been widely used to detect COVID-19 automatically from X-ray images. Although these models can selectively retrain their layers for the desired task, the output remains biased due to the massive number of pre-trained weights and parameters. This paper proposes a novel batch normalized convolutional neural network (BNCNN) model to identify COVID-19 cases from chest X-ray images in binary and multi-class frameworks with a dual aim to extract salient features that improve model performance over pre-trained image analysis networks while reducing computational complexity. The BNCNN model has three phases: Data pre-processing to normalize and resize X-ray images, Feature extraction to generate feature maps, and Classification to predict labels based on the feature maps. Feature extraction uses four repetitions of a block comprising a convolution layer to learn suitable kernel weights for the features map, a batch normalization layer to solve the internal covariance shift of feature maps, and a max-pooling layer to find the highest-level patterns by increasing the convolution span. The classifier section uses two repetitions of a block comprising a dense layer to learn complex feature maps, a batch normalization layer to standardize internal feature maps, and a dropout layer to avoid overfitting while aiding the model generalization. Comparative analysis shows that when applied to an open-access dataset, the proposed BNCNN model performs better than four other comparative pre-trained models for three-way and two-way class datasets. Moreover, the BNCNN requires fewer parameters than the pre-trained models, suggesting better deployment suitability on low-resource devices.

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

Computer Vision Algorithms of DigitSeis for Building a Vectorised Dataset of Historical Seismograms from the Archive of Royal Observatory of Belgium

Archived seismograms recorded in the 20th century present a valuable source of information for monitoring earthquake activity. However, old data, which are only available as scanned paper-based images should be digitised and converted from raster to vector format prior to reuse for geophysical modelling. Seismograms have special characteristics and specific featuresrecorded by a seismometer and encrypted in the images: signal trace lines, minute time gaps, timing and wave amplitudes. This information should be recognised and interpreted automatically when processing archives of seismograms containing large collections of data. The objective was to automatically digitise historical seismograms obtained from the archives of the Royal Observatory of Belgium (ROB). The images were originallyrecorded by the Galitzine seismometer in 1954 in Uccle seismic station, Belgium. A dataset included 145 TIFF images which required automatic approach of data processing. Software for digitising seismograms are limited and many have disadvantages. We applied the DigitSeis for machine-based vectorisation and reported here a full workflowof data processing. This included pattern recognition, classification, digitising, corrections and converting TIFFs to the digital vector format. The generated contours of signals were presented as time series and converted into digital format (mat files) which indicated information on ground motion signals contained in analog seismograms. We performed the quality control of the digitised traces in Python to evaluate the discriminating functionality of seismic signals by DigitSeis. We shown a robust approach of DigitSeis as a powerful toolset for processing analog seismic signals. The graphical visualisation of signal traces and analysis of the performed vectorisation results shown that the algorithms of data processing performed accurately and can be recommended in similar applications of seismic signal processing in future related works in geophysical research.

Computational modelling and application of mechanical waves to detect arterial network anomalies: Diagnosis of common carotid stenosis

BACKGROUND AND OBJECTIVE

This paper proposes a novel strategy to localize anomalies in the arterial network based on its response to controlled transient waves. The idea is borrowed from system identification theories in which wave reflections can render significant information about a target system. Cardiovascular system studies often focus on the waves originating from the heart pulsations, which are of low bandwidth and, hence, can hardly carry information about the arteries with the desired resolution.

METHODS

Our strategy uses a relatively higher bandwidth transient signal to characterize healthy and unhealthy arterial networks through a frequency response function (FRF). We tested our novel approach on data simulated using a one-dimensional cardiovascular model that produced pulse waves in the larger arteries of the arterial network. Specifically, we excited the blood flow from the brachial artery with a relatively high bandwidth flow disturbance and collected the subsequent pressure waveform at peripheral positions. To better differentiate FRFs of healthy and unhealthy networks, we used a FRF that removes the effects of heart pulsations.

RESULTS

Results demonstrate the ability of the proposed FRF to detect and follow-up on the development of a common carotid artery (CCA) stenosis. We tested distinct geometrical variations of the stenosis (size, length and position) and observed differences between the FRFs of healthy and unhealthy networks in all cases; such differences were mainly due to geometrical variations determined by the stenosis.

CONCLUSIONS

We have provided a theoretical proof of concept that demonstrates the ability of our novel strategy to detect and track the development of CCA stenosis by using peripheral pressure waves that can be measured non-invasively in clinical practice.

Explanatory Change Detection in Financial Markets by Graph-Based Entropy and Inter-Domain Linkage

In this study, we analyzed structural changes in financial markets under COVID-19 to support investors' investment decisions. Because an explanation of these changes is necessary to respond appropriately to said changes and prepare for similar major changes in the future, we visualized the financial market as a graph. The hypothesis was based on expertise in the financial market, and the graph was analyzed from a detailed perspective by dividing the graph into domains. We also designed an original change-detection indicator based on the structure of the graph. The results showed that the original indicator was more effective than the comparison method in terms of both the speed of response and accuracy. Explanatory change detection of this method using graphs and domains allowed investors to consider specific strategies.

Chronic Kidney Disease as a Cardiovascular Disorder-Tonometry Data Analyses

Tonometry is commonly used to provide efficient and good diagnostics for cardiovascular disease (CVD). There are many advantages of this method, including low cost, non-invasiveness and little time to perform. In this study, the effort was undertaken to check whether tonometry data hides valuable information associated with different stages of chronic kidney disease (CKD) and end-stage renal disease (ESRD) treatment. For this purpose, six groups containing patients at different stages of CKD following different ways of dialysis treatment, as well as patients without CKD but with CVD and healthy volunteers were assessed. It was revealed that each of the studied groups had a unique profile. Only the type of dialysis was indistinguishable a from tonometric perspective (hemodialysis vs. peritoneal dialysis). Several techniques were used to build profiles that independently gave the same outcome: analysis of variance, network correlation structure analysis, multinomial logistic regression, and discrimination analysis. Moreover, to evaluate the classification potential of the discriminatory model, all mentioned techniques were later compared and treated as feature selection methods. Although the results are promising, it could be difficult to express differences as simple mathematical relations. This study shows that artificial intelligence can differentiate between different stages of CKD and patients without CKD. Potential future machine learning models will be able to determine kidney health with high accuracy and thereby classify patients. ClinicalTrials.gov Identifier: NCT05214872.

Identity and Gender Recognition Using a Capacitive Sensing Floor and Neural Networks

In recent publications, capacitive sensing floors have been shown to be able to localize individuals in an unobtrusive manner. This paper demonstrates that it might be possible to utilize the walking characteristics extracted from a capacitive floor to recognize subject and gender. Several neural network-based machine learning techniques are developed for recognizing the gender and identity of a target. These algorithms were trained and validated using a dataset constructed from the information captured from 23 subjects while walking, alone, on the sensing floor. A deep neural network comprising a Bi-directional Long Short-Term Memory (BLSTM) provided the most accurate identity performance, classifying individuals with an accuracy of 98.12% on the test data. On the other hand, a Convolutional Neural Network (CNN) was the most accurate for gender recognition, attaining an accuracy of 93.3%. The neural network-based algorithms are benchmarked against Support Vector Machine (SVM), which is a classifier used in many reported works for floor-based recognition tasks. The majority of the neural networks outperform SVM across all accuracy metrics.

Research on commodity business value and customer value of e-commerce platforms: Based on consumer psychology and cognition

Under the background of economic globalization and COVID-19, online shopping has gradually replaced offline shopping as the main shopping mode. In this paper, consumers' perceptions are introduced into the traditional BCG matrix to form a new BCG matrix, and according to it, the small gifts of a gift e-commerce platform are classified. We then performed a robustness test comparing the BCG matrix with K-means clustering. We found that new BCG matrix can objectively reflect the value of small gifts and provide suggestions for the e-commerce platform to make subsequent product decisions. Then we judge the customer value of the platform based on the improved RFM model and K-means++ clustering, and provide a reasonable customer value classification method for the e-commerce platform. Finally, we comprehensively consider the relationship between the commodity value and customer value, and analyze the preferences of different types of customer groups for different types of small gifts. Our research result shows that small gifts can be divided into 4 categories according to commodity value, namely "stars," "cash cows," "questions marks," and "dogs." These four categories of small gifts can be converted into each other through marketing ploys. Customers can be divided into important retention customers, key loyal customers and general development customers according to their values. Faced with different types of customers, managers can adopt different strategies to extract customer value. However, consumer psychology will affect consumer cognition, and different types of consumers prefer different types of small gifts, so the precise implementation of marketing strategies will effectively improve the profitability of the gift e-commerce platform. Compared with the traditional classification method, the commodity business value classification method proposed in this paper uses management analysis and planning methods, and introduces consumer psychological factors into the commodity and customer classification, so that the classification results are more credible. In addition, we jointly analyze the results of commodity value classification and customer value classification, and analyze in detail the preferences of different valued customer groups for different types of commodities, so as to provide directions for subsequent research on customer preference.

Non-coding RNAs, another side of immune regulation during triple-negative breast cancer

Triple-negative breast cancer (TNBC) is considered about 12-24 % of all breast cancer cases. Patients experience poor overall survival, high recurrence rate, and distant metastasis compared to other breast cancer subtypes. Numerous studies have highlighted the crucial roles of non-coding RNAs (ncRNAs) in carcinogenesis and proliferation, migration, and metastasis of tumor cells in TNBC. Recent research has demonstrated that long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) play a role in the regulation of the immune system by affecting the tumor microenvironment, the epithelial-mesenchymal transition, the regulation of dendritic cells and myeloid-derived stem cells, and T and B cell activation and differentiation. Immune-related miRNAs and lncRNAs, which have been established as predictive markers for various cancers, are strongly linked to immune cell infiltration and could be a viable therapeutic target for TNBC. In the current review, we discuss the recent updates of ncRNAs, including miRNAs and lncRNAs in TNBC, including their biogenesis, target genes, and biological function of their targets, which are mostly involved in the immune response.

Computational Modeling of Motile Cilia-Driven Cerebrospinal Flow in the Brain Ventricles of Zebrafish Embryo

Motile cilia are hair-like microscopic structures which generate directional flow to provide fluid transport in various biological processes. Ciliary beating is one of the sources of cerebrospinal flow (CSF) in brain ventricles. In this study, we investigated how the tilt angle, quantity, and phase relationship of cilia affect CSF flow patterns in the brain ventricles of zebrafish embryos. For this purpose, two-dimensional computational fluid dynamics (CFD) simulations are performed to determine the flow fields generated by the motile cilia. The cilia are modeled as thin membranes with prescribed motions. The cilia motions were obtained from a two-day post-fertilization zebrafish embryo previously imaged via light sheet fluorescence microscopy. We observed that the cilium angle significantly alters the generated flow velocity and mass flow rates. As the cilium angle gets closer to the wall, higher flow velocities are observed. Phase difference between two adjacent beating cilia also affects the flow field as the cilia with no phase difference produce significantly lower mass flow rates. In conclusion, our simulations revealed that the most efficient method for cilia-driven fluid transport relies on the alignment of multiple cilia beating with a phase difference, which is also observed in vivo in the developing zebrafish brain.

Application Research of IICA Algorithm in a Limited-Buffer Scheduling Problem

An improved imperialist competition algorithm (IICA) was proposed to resolve the problem of flexible flow shop scheduling that with limited buffer (LBFFSP). The IICA algorithm adds the elite personal retention strategy, reform operation and the discrete processing on the basis of ICA algorithm. This paper uses an individual selection mechanism based on Hamming distance to improve the ability of initial solution. The prospect is to use the IICA to work out related problems in cloud computing environment. The scheduling problem in the cloud-computing environment needs to consider the optimization of the completion time and cost of using cloud resources. At last, simulation tests and example tests are used to check the usefulness of improved imperialist competition algorithm in solving LBFFSP problem. Compared with standard ICA, the improved ICA has improved in the algorithm evolution process. As such, scheme 4 has a better ability to evolve, and its evolution time is greater than that of scheme 3. Scheme 5 has the best algorithm optimization performance.

Spectral Preprocessing Combined with Deep Transfer Learning to Evaluate Chlorophyll Content in Cotton Leaves

Rapid determination of chlorophyll content is significant for evaluating cotton's nutritional and physiological status. Hyperspectral technology equipped with multivariate analysis methods has been widely used for chlorophyll content detection. However, the model developed on one batch or variety cannot produce the same effect for another due to variations, such as samples and measurement conditions. Considering that it is costly to establish models for each batch or variety, the feasibility of using spectral preprocessing combined with deep transfer learning for model transfer was explored. Seven different spectral preprocessing methods were discussed, and a self-designed convolutional neural network (CNN) was developed to build models and conduct transfer tasks by fine-tuning. The approach combined first-derivative (FD) and standard normal variate transformation (SNV) was chosen as the best pretreatment. For the dataset of the target domain, fine-tuned CNN based on spectra processed by FD + SNV outperformed conventional partial least squares (PLS) and squares-support vector machine regression (SVR). Although the performance of fine-tuned CNN with a smaller dataset was slightly lower, it was still better than conventional models and achieved satisfactory results. Ensemble preprocessing combined with deep transfer learning could be an effective approach to estimate the chlorophyll content between different cotton varieties, offering a new possibility for evaluating the nutritional status of cotton in the field.