Search

An Exploratory Data Analysis (EDA) remains a major tool proving a better understanding of the time series dataset with assumptions that could culminate in obvious errors being eliminated. Yet this step during modeling is often done in a less exhaustive manner. This has resulted in assumptions without effective uncovering of the relationships and structure of the underlying dataset. Besides, possible trends and patterns that might not be readily apparent are often not exposed due to the lack of a comprehensive EDA. The primary step to forecasting entails the selection of the appropriate forecasting approach which remains a major challenge for analysts performing the forecasts. This challenge is the reason why many researchers continue to propose new approaches with the objective of forecasting accuracy enhancements. This study examines the impact of applying a robust EDA in improving Machine Learning model selection for electricity cost forecasting in home-based small businesses.

Deep learning algorithms can be applied to data acquired regularly from consumers' financial activity in order to create predictive tools used to foresee credit card defaults. Methods such as Convolutional Neural Networks and Recurrent Neural networks were utilized to improve the performance of loan risk prediction, hence lowering the risk to financial institutions. To compare the two models, the same data set was used. With the goal of better modeling and moving their precise measures for gauging model performance, the same initial dataset was used. Predictions from deep learning algorithms are helpful in many different areas of study, including representation and abstraction that make sense of images, sound, and text. The study laid the groundwork for filling the void left by outdated banking tools and inadequate computer technology by applying deep learning algorithms to the problem of credit card default prediction.

Big data has presented itself as a term, phenomena, and paradigm with the potential for many opportunities and challenges. The new potentials of big data seemingly continue to expand both in possibility and complexity. With efforts to exploit these new potentials requiring investments from businesses and organizations it becomes necessary to understand what value is gained from such efforts. Through the methodology of design science this study develops an artifact which incorporates the return on investment model which can be utilized by SMEs. The artifact provides an abstract process model for the use of value assessment of big data efforts by SMEs. This study finds through using test cases that the ROI model can be applied to a generalized artifact which guides the assessment of big data efforts. Further, it is found that through a graphical design the development of a simple and intuitive artifact can be accomplished.

To investigate the anticancer and osteogenic properties and mechanism of action of a selenium (Se4+) hydroxyapatite (HA) nanodelivery system for osteosarcoma (OS) therapy. We loaded different concentrations of Na2SeO3 (3% and 6%) into HA nanoparticles (HANP) for OS therapy. Simultaneously, we tested the stability and pH responsiveness of Se-HANP in vitro experiments, and OS MG-63 cells and mice BMSCs were cultured to further evaluate its permeability, anticancer ability and mineralization ability [alkaline phosphatase (ALP), osteocalcin (OCN)]. In addition, We conducted in vivo experiments by constructing OS mouse models to further investigate the anticancer mechanism of Se-HANP. Se-HANP showed good stability in blood; an acidic environment (pH 5) was more conducive to Se4+ ion release, and could effectively penetrate into OS MG-63 cells. In cell experiments, compared with HANP, Se-HANP could more effectively improve BMSCs viability and enhanced their mineralization performance, such as improving ALP and OCN levels. In addition, Se-HANP could effectively inhibit the activity and invasiveness of MG-63 cells; 6% Se-HANP showed stronger anticancer effects. In OS in vivo mouse experiments, Se-HANP could effectively inhibit tumor tissue growth (volume and weight) in a concentration dependent manner. In addition, Se4+ activated endogenous and exogenous apoptotic pathways by increasing the level of reactive oxygen species (8-OHdG) in tumor cells, leading to tumor cell apoptosis. Se-HANP could effectively penetrate OS cells, and its good stability and pH responsiveness could improve the anticancer efficiency of Se4+. Moreover, its excellent mineralization ability could effectively repair the bone defects caused by OS. Accordingly, Se-HANP can have great potential in OS treatment.

The Time Series Classification Residual Network (TSCResNet) deep learning model is introduced in this study to improve the classification performance in the human activity recognition (HAR) problem. Specifically in the context of closed-set classification where all labels or classes are present during the model training phase. This contrasts with open-set classification where new, unseen activities are introduced to the HAR system after the training phase. The proposed TSCResNet model is evaluated with the benchmark PAMAP2 Physical Activity Monitoring Dataset. By using the same quantitative methods and data preprocessing protocols as previous research in the field of closed-set HAR, results show that the TSCResNet model architecture is able to achieve improved classification results across accuracy, the weighted F1-score, and mean F1-score.

A large amount of data is available on Twitter that can be used to manage different types of risks in financial institutions. This paper shows how machine learning algorithms can be applied to analyze large unstructured data and train a model to make a future prediction on tweets to categorize them by risk type and use sentiment analysis to understand the risk type. This model reads each tweet and categorizes them by risk using a specified dictionary and adds sentiment analysis to show the risk type seen in each tweet. Logistic regression used in this research helped to formulate the prediction model. Twitter data from 2019 was used to train and test a supervised machine learning algorithm and once the model started predicting tweets efficiently, it was used to predict twitter data from 2022 in our experimental research. Our experiment confirmed that Twitter data can be used to manage risk with the right type of modeling using machine learning techniques.

Epithelial regeneration is an essential wound healing process, and recent work suggests that different types of exosomes (Exos) can improve wound repair outcomes by promoting such epithelial regeneration. Platelet-rich plasma (PRP) is known to facilitate enhanced wound healing, yet the mechanisms underlying its activity are poorly understood. To explore these mechanisms, we first isolated PRP-derived Exos (PRP-Exos). Using immortalized keratinocytes (HaCaT cells) treated with PBS, PRP, or PRP-Exos, we conducted a series of in vitro Cell Counting Kit-8 (CCK-8), EdU, scratch wound, and transwell assays. We then established a wound defect model in vivo in mice and assessed differences in the mRNA expression within these wounds to better understand the basis for PRP-mediated wound healing. The functions of PRP-Exos and USP15 in the context of wound healing were then confirmed through additional in vitro and in vivo experiments. We found that PRP-Exos effectively promoted the in vitro proliferation, migration, and wound healing activity of HaCaT cells. USP15 was further identified as a key mediator through which these PRP-Exos were able to promote tissue repair both in vitro and in vivo. At a mechanistic level, USP15 enhanced the functional properties of HaCaT cells by promoting EIF4A1 deubiquitination. Thus, PRP-Exos and USP15 represent promising tools that can promote wound healing via enhancing epithelial regeneration.

Diabetic foot ulcer (DFU) is one of the common ailments of elderly people suffering from diabetes. Exosomes containing various active regulators have been found to play a significant role in apoptosis, cell proliferation and other biological processes. However, the effect and the underlying mechanism of action of diabetes patients derived from circulating exosomes (Dia‐Exos) on DFU remain unclear. Herein, we aim to explore the potential regulatory role of Dia‐Exos. First, we attempted to demonstrate the harmful effect of Dia‐Exos both in vivo and in vitro. miRNA‐24‐3p (miR‐24‐3p) was found enriched with Dia‐Exos. Hence, inhibition of this miRNA could partially reverse the negative effect of Dia‐Exos, thus, in ture, accelerates wound repair. Luciferase assay further verified the binding of miR‐24‐3p to the 3′‐UTR of phosphatidylinositol 3‐kinase regulatory subunit gamma (PIK3R3) mRNA and the PIK3R3 expression enhanced human umbilical vein endothelial cells functionality in vitro. Hence, the findings of this study reveal the regulatory role of Dia‐Exos in the process of wound healing and provide experimental evidence for the therapeutic effects of knocking down miR‐24‐3p in DFU treatment.

Cutaneous wound healing, especially diabetic wound healing, is a common clinical problem. Reactive oxygen species (ROS) and bacterial infection are two major factors in the induction of oxidative stress and inflammation, leading to impeded angiogenesis and wound healing. However, it is still very difficult to reverse the harsh microenvironment of chronic inflammation and excessive oxidative stress on diabetic wound. Itaconate, an endogenous metabolite, has recently attracted extensive attention as a critical immune-regulator. In this study, we used 4-octyl itaconate (4OI), a cell-permeable itaconate derivative, to have antioxidative and anti-inflammatory functions for diabetic wound regeneration. Simultaneously, an injectable, self-healing, and antibacterial dynamic coordinative hydrogel was manufactured by binding the 4-arm polyethylene glycol (PEG) with silver nitrate to deliver the bioactive molecule. In vitro experiments confirmed that 4OI@PEG hydrogel could inhibit bacterial growth, protect human umbilical vein endothelial cells from ROS damage and enhance neovascularization. In addition, the hydrogel increased mitochondrial polarization and reduced mitochondrial fragmentation by activating the Keap1-Nrf2 antioxidant defense system. In vivo experiments proved that this multifunctional hydrogel facilitated diabetic wound healing by inhibiting local inflammation and promoting angiogenesis. Collectively, 4OI-loaded multifunctional materials could reverse various unfavorable microenvironments, such as excessive oxidative stress, inflammation, and infection, and can promote neovascularization; thus, such materials show great promise for the treatment of diabetic ulcers.

Cutaneous wound healing, especially diabetic wound healing, is a common clinical challenge. Reactive oxygen species (ROS) and bacterial infection are two major detrimental states that induce oxidative stress and inflammatory responses and impede angiogenesis and wound healing. A derivative of the metabolite itaconate, 4-octyl itaconate (4OI) has attracted increasing research interest in recent years due to its antioxidant and anti-inflammatory properties. In this study, 4OI-modified black phosphorus (BP) nanosheets are incorporated into a photosensitive, multifunctional gelatin methacrylamide hydrogel to produce a new photothermal therapy (PTT) and photodynamic therapy (PDT) system with antibacterial and antioxidant properties for diabetic wound regeneration. Under laser irradiation, the 4OI-BP-entrapped hydrogel enables rapid gelation, forming a membrane on wounds, and offers high PTT and PDT efficacy to eliminate bacterial infection. Without laser irradiation, BP acts as a carrier and controls the release of 4OI, with which it synergistically enhances antioxidant activity, thus alleviating excessive ROS damage to endothelial cells, promoting neovascularization, and facilitating faster diabetic wound closure. These findings indicate that 4OI-BP-entrapped multifunctional hydrogel provides a stepwise countermeasure with antibacterial and antioxidant properties for enhanced diabetic wound healing and may lead to novel therapeutic interventions for diabetic ulcers.

Background: As the rate of geriatric acetabular fractures was increasing gradually and accompanied with the quadrilateral surface(QLS) involved resulting by impacting from the head of femur, which usually leaded to the dislocation/subluxation of the head of femur and intra-pelvic medial displacement of the QLS. Traditionally, applying an infra-pectineal buttress plate in the true pelvis to resist the protrusive fragments of the QLS, however, these plates with small contact area could not provide enough buttress effect to age-related fractures. This study was to evaluate the “frame and buttress” fixation strategy for treatment of geriatric acetabular anterior fractures(GAAF).Methods: A cohort of 28 patients with acetabular fractures involving QLS were managed operatively with the “frame and buttress” fixation strategy with a single pelvic anterior approach. 7 cases were transverse, 3 cases were posterior column, 8 cases were associated both columns, 4 cases were anterior posterior hemi-transverse and 6 cases were T-type patterns fracture. The quality of reduction, functional outcomes and complicates were recorded for analyzing.Results: Functional outcomes were 15 cases in excellent; 9 cases were good; 3 cases were fair, and 1 case was poor. The quality of surgical reduction was evaluated by the Matta score system, which was graded as excellent in 17 cases, good in 9 cases and poor in 2 cases, respectively. No loss or failure of internal fixation, no second dislocation/subluxation of femoral head and no complications like infection were observed.Conclusions: The “frame and buttress” fixation strategy provided firm method for treating GAAF, the “frame” formed rigid fixation structure for acetabular fractures and the “buttress” resisted protrusive QLS.

Background. The treatment of C1-C2 fractures mainly depends on fracture type and the stability of the atlantoaxial joint. Disruption of the C1-C2 combination is a big challenge, especially in avoiding vertebral artery, nerve, and vein sinus injury during the operation. Purpose. This study aims to show the benefit of using the posterior approach and pedicle screw insertion by nailing technique and direct visualization to treat unstable C1-C2 and, moreover, to determine the advantages of performing early MRI in patients with limited neck movement after trauma. Method. Between Jan 2017–Feb 2019, we present 21 trauma patients who suffered from C1, C2, or unstable atlantoaxial joint. X-ray, computed tomography (CT), and magnetic resonance image (MRI) were performed preoperatively. All the patients underwent our surgical procedure (posterior approach and pedicle screw placement by direct visualization and nailing technique). Result. The mean age was 41.1 years old, 8 females and 14 males. The average follow-up time was 2.6 years. Four patients were with C1 fracture, seven with C2 fracture, six with atlantoaxial dislocation, and four with C1 and C2 fractures. The time of MRI was between 12 hours and 48 hours; neck movement symptoms appeared between 2 days and 2 weeks. Conclusion. The posterior approach to treat the C1 and C2 fractures or dislocation by direct visualization and nailing technique can reduce the risk of the vertebral artery, vein sinus, and nerve root injuries with significant improvement. It can show a better angle view while inserting the pedicle screws. An early MRI (12–48 hours) is essential even if no symptoms appear at the time of admission, and if it is normal, it is necessary to repeat it. The presence of skull bleeding can be associated with upper neck instability.

Bone morphogenetic protein 2 (BMP-2) is one of the most important factors for bone tissue formation. However, its use over the past decade has been associated with numerous side effects. This is due to the fact that recombinant human (rh) BMP-2 has several biological functions, as well as that non-physiological high dosages were commonly administered. In this study, we synthesized a novel BMP-2-related peptide (designated P28) and fused a mutant domain in placenta growth factor-2 (PlGF-2123-144*) that allowed for the “super-affinity” of extracellular matrix proteins to P28, effectively controlling the release of low dosage P28 from small intestinal submucosa/polylactic acid (SIS/PLA) scaffolds. These have been shown to be excellent scaffold materials both in vivo and in vitro. The aim of this study was to determine whether these scaffolds could support the controlled release of P28 over time, and whether the composite materials could serve as structurally and functionally superior bone substitutes in vivo. Our results demonstrated that P28 could be released slowly from SIS/PLA to promote the adhesion, proliferation, and differentiation of bone marrow stromal cells (BMSCs) in vitro. In vivo, radiographic and histological examination showed that SIS/PLA/P28/PlGF-2123-144* completely repaired critical-size bone defects, compared to SIS/PLA, SIS/PLA/PlGF-2123-144*, or SIS/PLA/P28 alone. These findings suggest that this controlled release system may have promising clinical applications in bone tissue engineering.