External Databases Research Articles

Bus Operation Safety Business Intelligence Solution: Applying Analytics for Key Performance Indicator, Investigation, and Targeted Actions Analyses with a Centralized Data Warehouse

A business intelligence (BI) system was designed to create a proactive, reactive, and precursor decision tool to improve safety of bus operations at the Massachusetts Bay Transportation Authority (MBTA). The system’s development was motivated in part by recommendations of a safety inspection by the Federal Transportation Administration, and the realization that the MBTA has access to vest amounts of data that are not being used to create information effectively. The developers reduced the complexity of the BI system by incorporating analytics to determine the areas of focus where safety has the most impact. Challenges were posed by the need to integrate internal and external databases with various formats and structures, and the desire to create a self-service BI solution for multiple MBTA users. The resulting BI solution includes applications that support key performance indicator analyses, root cause investigations, and targeted improvement actions. These applications represent an enhanced approach that combines data for a more holistic analysis and eliminates the need to transfer datasets or data analyses by email. The system includes various forms of visualizations to help users navigate the myriad of information, including geospatial maps, interactive pie, line, and bar charts, and word frequency and relationship mapping. The paper details the system’s development and how analytical approaches were used to expose important information that is hidden in the data. Examples of applications are shown using screenshots and a general workflow is presented that could be applicable to agencies with fewer resources.

Automatic segmentation of atrial fibrillation and flutter in single-lead electrocardiograms by self-supervised learning and Transformer architecture.

Automatic detection of atrial fibrillation and flutter (AF/AFL) is a significant concern in preventing stroke and mitigating hemodynamic instability. Herein, we developed a Transformer-based deep learning model for AF/AFL segmentation in single-lead electrocardiograms (ECGs) by self-supervised learning with masked signal modeling (MSM). We retrieved data from 11 open-source databases on PhysioNet; 7 of these databases included labeled ECGs, while the other 4 were without labels. Each database contained ECG recordings with durations of ≥30s. A total of 24 intradialytic ECGs with paroxysmal AF/AFL during 4h of hemodialysis sessions at Seoul National University Hospital were used for external validation. The model was pretrained by predicting masked areas of ECG signals and fine-tuned by predicting AF/AFL areas. Cross-database validation was used for evaluation, and the intersection over union (IOU) was used as a main performance metric in external database validation. In the 7 labeled databases, the areas marked as AF/AFL constituted 41.1% of the total ECG signals, ranging from 0.19% to 51.31%. In the evaluation per ECG segment, the model achieved IOU values of 0.9254 and 0.9477 for AF/AFL segmentation and other segmentation tasks, respectively. When applied to intradialytic ECGs with paroxysmal AF/AFL, the IOUs for the segmentation of AF/AFL and non-AF/AFL were 0.9896 and 0.9650, respectively. Model performance by different training procedure indicated that pretraining with MSM and the application of an appropriate masking ratio both contributed to the model performance. It also showed higher IOUs of AF/AFL labels than in previous studies when training and test databases were matched. The present model with self-supervised learning by MSM performs robustly in segmenting AF/AFL.

The Shifting Prognosis of FLT3 Mutations in Acute Myeloid Leukemia in the Era of Targeted Therapy: A Real-World Study Using Large-Scale Electronic Health Record Data

Background: Mutations in FLT3 occur in 20-30% of acute myeloid leukemia (AML), and their prognostic implications have varied over time with improved understanding of FLT3 (Döhner et al., Blood, 2022). However, since 2017, the US Food and Drug Administration (FDA) has approved three FLT3 inhibitors, and few studies have examined the prognosis of FLT3 mutations in the era of targeted therapy. Additionally, a real-world oncology data analysis suggested that novel therapies may have greater effects than clinical trials showed, due to the inclusion of previously ineligible patients (Liu et al., Nature, 2021). Therefore, we examined the relative prognosis of FLT3-mutated AML before and after the FDA approval date of the first FLT3-inhibitor, midostaurin. Methods: Patients were included if both FLT3-ITD (internal tandem duplication) and FLT3 D835 mutations were tested within 14 days of AML diagnosis at the Stanford Cancer Center. Data came from databases associated with Stanford's electronic health record (EHR), except that overall survival (OS) data was supplemented with external databases like the Social Security Death Index, and diagnosis dates came from the Stanford Cancer Registry. A FLT3 mutation was defined as either an ITD or D835 variant. The FDA approval of midostaurin served as a real-world, unplanned experiment illustrating the impact of FLT3 inhibitors' availability on the prognosis of FLT3-mutated AML. Thus, using a difference-in-differences approach, we built a logistic regression model predicting one-year overall survival using the variables FLT3 mutation, diagnosis before vs. after the midostaurin approval date, and an interaction between those terms. The model was adjusted for patient age at diagnosis, NPM1 mutation presence, and other interaction terms, and for that model, patients who were lost to follow-up before one year were excluded. Cox proportional hazards regression was used to make interpretation comparable to clinical trial hazard ratios, and Kaplan-Meier (KM) curves were used to explore age subgroups. Patients were excluded if they received gilteritinib, sorafenib, or midostaurin but were diagnosed before midostaurin's approval. Results: Between April 2008 and September 2022, 522 patients met inclusion criteria, and 120 (23%) had an ITD mutation only, 22 (4%) had a D835 mutation only, and 8 (2%) had both mutations at diagnosis, and the remainder were negative for FLT3 mutation. FLT3 mutation was not significantly associated with overall survival (p = 0.55), but the interaction between FLT3 and diagnosis after midostaurin's approval was associated with a lower chance of death in multiple logistic regression (Table 1, odds ratio [OR] 0.237, p = 0.0044), implying that a FLT3 mutation had a better prognosis after midostaurin's approval. This trend was present in patients both under age 60 (OR 0.153, p = 0.043; KM curves in Figure 1) and at least age 60 (OR 0.273, p = 0.04). In a Cox regression, the interaction term was similar (HR 0.54, p = 0.021), with a HR that compared favorably to 0.78, the HR seen in phase III clinical trials studying midostaurin or quizartinib at diagnosis (Stone et al., NEJM, 2017; Erba et al., Lancet, 2023). Younger patients with FLT3-mutated AML after midostaurin's approval were more likely to have a record of FLT3 inhibitor prescription (79% under age 60 vs. 56% at least age 60, p = 0.07). Conclusions: The relative prognosis of FLT3 mutations in AML has improved, including in older patients, likely due to the approval of FLT3 inhibitors, and the relative survival is more favorable than what was described in major clinical trials. Gathering real-world data to estimate prognosis of FLT3 mutations is crucial for accurate risk stratification, and this can be done more easily with EHR data.

Automated system for high-accuracy quantity takeoff using BIM

Reliable construction project cost estimation relies on accurate quantity takeoffs (QTOs), traditionally done with error-prone 2-D drawings, but the emergence of Building Information Modeling (BIM) has improved QTO speed, accuracy, and reliability. However, the quality of BIM models can influence quantity accuracy, an aspect often overlooked in research on automating QTO with BIM. This paper develops an integrated framework to automatically extract and visualize construction quantities from BIM models. The system includes a Quantity Precision Check (QPC) module for automating more accurate QTO outputs. These outputs are then automatically transferred to an external database and visualized through a user-friendly dashboard on the Microsoft Power BI platform. This dashboard allows for comparisons between 2-D and BIM quantities and helps track changes in quantities over time due to design changes. The system was successfully validated in an infrastructure construction project in Canada, where it identified a 39% inconsistency in wall elements' material quantities and reduced steel quantity by 10% due to design changes. Overall, the system offers a speedy, reliable, and efficient tool for construction estimators, site managers, and cost control teams to provide accurate quantities to the procurement team and make swift decisions in response to design change impacts on construction costs.

Automatic measurements of left ventricular volumes and ejection fraction by artificial intelligence: clinical validation in real time and large databases.

Echocardiography is a cornerstone in cardiac imaging, and left ventricular (LV) ejection fraction (EF) is a key parameter for patient management. Recent advances in artificial intelligence (AI) have enabled fully automatic measurements of LV volumes and EF both during scanning and in stored recordings. The aim of this study was to evaluate the impact of implementing AI measurements on acquisition and processing time and test-retest reproducibility compared with standard clinical workflow, as well as to study the agreement with reference in large internal and external databases. Fully automatic measurements of LV volumes and EF by a novel AI software were compared with manual measurements in the following clinical scenarios: (i) in real time use during scanning of 50 consecutive patients, (ii) in 40 subjects with repeated echocardiographic examinations and manual measurements by 4 readers, and (iii) in large internal and external research databases of 1881 and 849 subjects, respectively. Real-time AI measurements significantly reduced the total acquisition and processing time by 77% (median 5.3 min, P < 0.001) compared with standard clinical workflow. Test-retest reproducibility of AI measurements was superior in inter-observer scenarios and non-inferior in intra-observer scenarios. AI measurements showed good agreement with reference measurements both in real time and in large research databases. The software reduced the time taken to perform and volumetrically analyse routine echocardiograms without a decrease in accuracy compared with experts.

Design and Implementation of Enabling SQL–Query Processing for Ethereum-Based Blockchain Systems

A blockchain is designed to establish consistent and reliable agreements in an untrusted and decentralized environment. In addition, the blockchain enables transaction processing and the creation of smart contracts. It empowers end users to execute contracts without any intermediate entities. However, there are some issues when it comes to retrieving information, such as the state and history of smart contracts and regular transactions in the blockchain. For example, in a smart contract, user-defined data structures can be used to recall the state of the smart contract for a range query, which can decrease the general performance. In addition, an external database can be required to retrieve regular transactions for range queries, which increases management costs. To achieve this, we propose a new scheme that enables SQL query operations to retrieve a smart contract and regular transaction information within the blockchain system. To achieve this, we combine an embedded relational database with an Ethereum-based blockchain system to provide the SQL query. It enables range queries on smart contracts without requiring user-defined data structures and decreases management costs for regular transactions without any external database. We implement the proposed blockchain system on quorum, which is an Ethereum-based blockchain system. Also, we evaluate the proposed system using a synthetic benchmark. The performance of retrieving smart contract data is improved by up to approximately 22×, with low memory usage compared with the existing system. Moreover, the proposed system demonstrates a similar search performance to the existing system, even when considering external databases in regular transactions.

In silico discovery of novel calcineurin inhibitors using ligand-based 3-D pharmacophore modelling and molecular dynamics simulation

Calcineurin is a serine-threonine protein phosphatase that is activated with the binding of calmodulin in the presence of increased calcium concentration and has a major role in various signaling pathways. Its role in regulating homeostasis, developmental processes, and different disease progression has already been reported. The dysregulated Ca2+/calcineurin/NFAT1-4 pathway is observed in Autoimmune disorders and hence the use of Calcineurin inhibitors like Cyclosporin A (CsA) and Tacrolimus (FK506) is widely done in such cases. Recent studies indicate the uncontrolled overexpression of the Calcineurin protein in the pathophysiological pathway of neurodegenerative diseases. The in vitro and animal model studies with standard calcineurin inhibitors (CnIs), which are widely labeled as immunosuppressant drugs, have shown a significant reduction of neurodegeneration in respective models. These results compel the identification of novel calcineurin inhibitors against neurodegenerative diseases. With this scenario, the present work focuses on the computer-aided identification of novel CnIs via ligand-based 3-D pharmacophore modelling. Known CnIs, CsA, and FK506, were used to build the pharmacophore models which were validated and screened against external databases to retrieve possible hits. Docking investigations, pharmacokinetic properties, and molecular dynamics simulations along with toxicity predictions were performed on the hits that were obtained. According to the study, a total of 5 molecules ILB 162, ILB 005, ILB 439, ILB 390, and ILB 198, were found to be the best calcineurin inhibitors with binding affinity in the range of −9.7 to −9.0 Kcal/mol with 1MF8 (PDB). The stability of interactions of these molecules was further validated via Molecular dynamics simulation studies to confirm these to be the potential calcineurin-inhibiting molecules. HIGHLIGHTS Calcineurin inhibitors can be a novel therapeutic candidate against neurodegenerative diseases. The identification of novel Calcineurin inhibitors was done in silico using ligand-based 3-D pharmacophore modelling using Ligand Scout Essential 4.4. software. The model could identify 440 hits from various external databases like PubChem (2432 molecules), ChemSpider, MayBridge, DrugBank, and e-Drug 3D by Cheminformatic Tools and Databases for Pharmacology. Out of which 5 molecules: ILB 162, ILB 005, ILB 439, ILB 390, and ILB 198, were found to be the best calcineurin inhibitors with binding affinity in the range of –9.7 to –9.0 Kcal/mol with 1MF8 (PDB) which were further confirmed to be the best CnI candidates via Molecular dynamics simulation studies. Communicated by Ramaswamy H. Sarma

Uncovering the distinct macro-scale anatomy of dysexecutive and behavioural degenerative diseases.

There is a longstanding ambiguity regarding the clinical diagnosis of dementia syndromes predominantly targeting executive functions versus behaviour and personality. This is due to an incomplete understanding of the macro-scale anatomy underlying these symptomatologies, a partial overlap in clinical features and the fact that both phenotypes can emerge from the same pathology and vice versa. We collected data from a patient cohort of which 52 had dysexecutive Alzheimer's disease, 30 had behavioural variant frontotemporal dementia (bvFTD), seven met clinical criteria for bvFTD but had Alzheimer's disease pathology (behavioural Alzheimer's disease) and 28 had amnestic Alzheimer's disease. We first assessed group-wise differences in clinical and cognitive features and patterns of fluorodeoxyglucose (FDG) PET hypometabolism. We then performed a spectral decomposition of covariance between FDG-PET images to yield latent patterns of relative hypometabolism unbiased by diagnostic classification, which are referred to as 'eigenbrains'. These eigenbrains were subsequently linked to clinical and cognitive data and meta-analytic topics from a large external database of neuroimaging studies reflecting a wide range of mental functions. Finally, we performed a data-driven exploratory linear discriminant analysis to perform eigenbrain-based multiclass diagnostic predictions. Dysexecutive Alzheimer's disease and bvFTD patients were the youngest at symptom onset, followed by behavioural Alzheimer's disease, then amnestic Alzheimer's disease. Dysexecutive Alzheimer's disease patients had worse cognitive performance on nearly all cognitive domains compared with other groups, except verbal fluency which was equally impaired in dysexecutive Alzheimer's disease and bvFTD. Hypometabolism was observed in heteromodal cortices in dysexecutive Alzheimer's disease, temporo-parietal areas in amnestic Alzheimer's disease and frontotemporal areas in bvFTD and behavioural Alzheimer's disease. The unbiased spectral decomposition analysis revealed that relative hypometabolism in heteromodal cortices was associated with worse dysexecutive symptomatology and a lower likelihood of presenting with behaviour/personality problems, whereas relative hypometabolism in frontotemporal areas was associated with a higher likelihood of presenting with behaviour/personality problems but did not correlate with most cognitive measures. The linear discriminant analysis yielded an accuracy of 82.1% in predicting diagnostic category and did not misclassify any dysexecutive Alzheimer's disease patient for behavioural Alzheimer's disease and vice versa. Our results strongly suggest a double dissociation in that distinct macro-scale underpinnings underlie predominant dysexecutive versus personality/behavioural symptomatology in dementia syndromes. This has important implications for the implementation of criteria to diagnose and distinguish these diseases and supports the use of data-driven techniques to inform the classification of neurodegenerative diseases.

Spatial Transcriptomics Reveal Pitfalls and Opportunities for the Detection of Rare High-Plasticity Breast Cancer Subtypes

Breast cancer is one of the most prominent types of cancers, in which therapeutic resistance is a major clinical concern. Specific subtypes, such as claudin-low and metaplastic breast carcinoma (MpBC), have been associated with high nongenetic plasticity, which can facilitate resistance. The similarities and differences between these orthogonal subtypes, identified by molecular and histopathological analyses, respectively, remain insufficiently characterized. Furthermore, adequate methods to identify high-plasticity tumors to better anticipate resistance are lacking. Here, we analyzed 11 triple-negative breast tumors, including 3 claudin-low and 4 MpBC, via high-resolution spatial transcriptomics. We combined pathological annotations and deconvolution approaches to precisely identify tumor spots, on which we performed signature enrichment, differential expression, and copy number analyses. We used The Cancer Genome Atlas and Cancer Cell Line Encyclopedia public databases for external validation of expression markers. By focusing our spatial transcriptomic analyses on tumor cells in MpBC samples, we bypassed the negative impact of stromal contamination and identified specific markers that are neither expressed in other breast cancer subtypes nor expressed in stromal cells. Three markers (BMPER, POPDC3, and SH3RF3) were validated in external expression databases encompassing bulk tumor material and stroma-free cell lines. We unveiled that existing bulk expression signatures of high-plasticity breast cancers are relevant in mesenchymal transdifferentiated compartments but can be hindered by abundant stromal cells in tumor samples, negatively impacting their clinical applicability. Spatial transcriptomic analyses constitute powerful tools to identify specific expression markers and could thus enhance diagnosis and clinical care of rare high-plasticity breast cancers.

Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound

In recent years, computerized methods for analyzing respiratory function have gained increased attention within the scientific community. This study proposes a deep-learning model to estimate the dimensionless respiratory airflow using only respiratory sound without prior calibration. We developed hybrid deep learning models (CNN + LSTM) to extract features from the respiratory sound and model their temporal dependencies. Then, we used an ensemble approach to combine multiple outputs of our models and obtain the respiratory airflow waveform for entire respiratory audio signals as the final output. We conducted a comprehensive set of experiments and evaluated the models using several regression evaluation metrics to assess how the models would perform in various circumstances of different complexity. The methods were developed and evaluated considering respiratory sound and electrical impedance tomography (EIT) data from 50 respiratory patients (15 female and 35 male with an average age of 67.4 ± 8.9 years and body mass index of 27.8 ± 5.6 kg/m2). An external assessment was conducted using an external database, the Respiratory Sound Database (RSD). This was an indirect evaluation because the RSD does not provide the ground truth values of the dimensionless respiratory airflow. In the most complex evaluation task (Task II), we achieved the following results for the estimation of the normalized dimensionless respiratory airflow curve: mean absolute error = 0.134 ± 0.061; root mean squared error = 0.170 ± 0.075; dynamic time warping similarity = 3.282 ± 1.514; Pearson correlation coefficient = 0.770 ± 0.235. External assessment with the RSD showed that the performance of our model decreased when devices different from the ones used for their training were considered. Our study demonstrated that deep learning models could reliably estimate the dimensionless respiratory airflow.

Network-based analysis between SARS-CoV-2 receptor ACE2 and common host factors in COVID-19 and asthma: Potential mechanistic insights

ACE2 as a functional receptor for SARS coronavirus plays an important role in COVID-19 infection of the host. Thus, we aimed to explore interaction networks between ACE2 and common host factors in COVID-19/Asthma comorbidity. We identified 1,191 protein targets closely related to ACE2, and integrated the GEO database and multiple public databases to identify 305 host factors related to ACE2 between COVID-19/Asthma comorbidity. Further enrichment analyses showed that metabolic processes, Th1 and Th2 cell differentiation and PPAR signaling pathways had vital significance in the comorbidity of asthma and COIVD-19. HRAS, IFNG, CAT, CDH1, FASN, ACLY, CCL5, VCAM1, SCD and HMGCR were the key host factors related to ACE2. Tissue-specific enrichment and correlation analysis with ACE2 showed that SCD, CAT and FASN were highly expressed in the lung; and these 10 molecules were closely related to ACE2 and specifically expressed in multiple tissues. We also identified a series of drugs, such as estradiol, tetrachlorodibenzodioxin, resveratrol, cyclosporine, perfluorooctanoic acid and so on. Finally, the expression levels and diagnostic performance of HRAS and SCD showed statistical significance in external databases. This study explored the interaction networks of ACE2-related host factors in COVID-19 and asthma and identified several potential drugs for COVID-19/Asthma comorbidity. Although our research needs further verification, it still informs the mechanisms and treatment of COVID-19/Asthma comorbidity.

Delta-radiomics features for predicting the major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer.

To investigate if delta-radiomics features have the potential to predict the major pathological response (MPR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC) patients. Two hundred six stage IIA-IIIB NSCLC patients from three institutions (Database1 = 164; Database2 = 21; Database3 = 21) who received neoadjuvant chemoimmunotherapy and surgery were included. Patients in Database1 were randomly assigned to the training dataset and test dataset, with a ratio of 0.7:0.3. Patients in Database2 and Database3 were used as two independent external validation datasets. Contrast-enhanced CT scans were obtained at baseline and before surgery. The delta-radiomics features were defined as the relative net change of radiomics features between baseline and preoperative. The delta-radiomics model and pre-treatment radiomics model were established. The performance of Immune-Related Response Evaluation Criteria in Solid Tumors (iRECIST) for predicting MPR was also evaluated. Half of the patients (106/206, 51.5%) showed MPR after neoadjuvant chemoimmunotherapy. For predicting MPR, the delta-radiomics model achieved a satisfying area under the curves (AUCs) values of 0.768, 0.732, 0.833, and 0.716 in the training, test, and two external validation databases, respectively, which showed a superior predictive performance than the pre-treatment radiomics model (0.644, 0.616, 0.475, and 0.608). Compared with iRECIST criteria (0.624, 0.572, 0.650, and 0.466), a mixed model that combines delta-radiomics features and iRECIST had higher AUC values for MPR prediction of 0.777, 0.761, 0.850, and 0.670 in four sets. The delta-radiomics model demonstrated superior diagnostic performance compared to pre-treatment radiomics model and iRECIST criteria in predicting MPR preoperatively in neoadjuvant chemoimmunotherapy for stage II-III NSCLC. Delta-radiomics features based on the relative net change of radiomics features between baseline and preoperative CT scans serve a vital support tool in accurately identifying responses to neoadjuvant chemoimmunotherapy, which can help physicians make more appropriate treatment decisions. •The performances of pre-treatment radiomics model and iRECIST model in predicting major pathological response of neoadjuvant chemoimmunotherapy were unsatisfactory. •The delta-radiomics features based on relative net change of radiomics features between baseline and preoperative CT scans may be used as a noninvasive biomarker for predicting major pathological response of neoadjuvant chemoimmunotherapy. •Combining delta-radiomics features and iRECIST can further improve the predictive performance of responses to neoadjuvant chemoimmunotherapy.

Mean arterial pressure and mortality in patients with heart failure: a retrospective analysis of Zigong heart failure database.

It is commonly observed that a higher target of mean arterial pressure (MAP) is in previous studies. This study assessed the association of MAP with short-term mortality in heart failure (HF) patients. A retrospective cohort study was conducted by using data from Hospitalized patients with heart failure: integrating electronic healthcare records and external outcome database (v1.2 ). The characteristic of patients was described by 3 groups of MAP: below 80 mmHg, 80-100 mmHg, and above 100 mmHg. Univariate and multivariate logistic regression analyses were used to assess the relevance between MAP and all-cause mortality within 28 days and 6 months. For assessing the effect of multiple variables on patient survival time, 28-day and 6-month, Kaplan-Meier survival analysis and Forest plot were performed. The overall cohort comprised 2008 patients divided by MAP into 3 groups, each group had 344 (17.1%), 938 (46.7%), and 726 (36.2%) patients. Patients in MAP < 80 mmHg group had higher mortality than MAP 80-100 mmHg and MAP ≥ 100 mmHg in 28 days(3.8% versus 1.6% versus 1.2%) and in 6 months (4.9% versus 2.5% versus 2.3%). Univariate analysis showed that MAP as a continuous variate was associated with 28-day (OR was 0.98, 95% CIs: 0.96-0.99, P = 0.011) and 6-month mortality (OR was 0.98, 95% CIs: 0.97-1, P = 0.021) in HF patients. Model 4 put into multivariate logistic regression analyses showed MAP 80-100 mmHg (OR was 0.13, 95% CIs: 0.02-0.8, P = 0.027) stably associated with 28-day and 6-month mortality after adjusted covariable. Kaplan-Meier survival curves revealed a higher survival rate in the MAP ≥ 80 mmHg group than in the MAP < 80 mmHg group. The forest plot showed the stable effect of MAP ≥ 80 mmHg compared with MAP < 80 mmHg, the interaction analysis had no statistical significance effect between the two groups of MAP and multi-variable. It is indicated that MAP was independently associated with 28-day, 6-month all-cause mortality of HF patients, and compared with MAP < 80 mmHg, MAP ≥ 80 mmHg had a lower risk of 28-day, 6-month all-cause mortality of patients with HF.

Reconstrucción de fuentes sísmicas usando un enfoque de Redes Neuronales Profundas de Datos Previos

Seismic surveys are often affected by environmental obstacles or restrictions that prevent regular sampling in seismic acquisition. To address missing data, various methods, including deep learning techniques, have been developed to extract features from complex information, albeit with the limitation of requiring external seismic databases. While previous works have primarily focused on trace reconstruction, missing shot-gathers directly impact the seismic processing flow and represent a major challenge in seismic data regularization. In this paper, we propose DIPsgr, a seismic shot-gather reconstruction method that uses only the incomplete seismic acquisition measurements to estimate their missing information employing unsupervised deep learning. Numerical experiments on three databases demonstrate that DIPsgr recovers the complete set of traces in each shot-gather, with preserved information and seismic events.

TOWARDS BIM-GIS INTEGRATION FOR ROAD INTELLIGENT MANAGEMENT SYSTEM

Roads and highways are often managed by using Geographic Information Systems (GIS). However, these systems lack the level of detail that Building Information Modelling (BIM) can bring to an infrastructure management system. BMGIS integration allows the management of information from both infrastructure and environmental points of view. This provides an overview of the infrastructure, facilitating decision-making process throughout its complete life cycle. This article shows a semi-automated process to generate the hybrid BIM-GIS model of Madrid Calle30. The model together with an external database was uploaded to an intelligent management platform that allows visualising the available documentation, assisting management, and bringing the ring-road closer to a digital twin of the infrastructure.

The Bigger the Better?

This article looks at a controversy over the ‘better’ architecture for conversational AI that unfolds initially along the question of the ‘right’ size of models. Current generative models such as ChatGPT and DALL-E follow the imperative of the largest possible, ever more highly scalable, training dataset. I therefore first describe the technical structure of large language models and then address the problems of these models which are known for reproducing societal biases or so-called hallucinations. As an ‘alternative’, computer scientists and AI experts call for the development of much smaller language models linked to external databases, that should minimize the issues mentioned above. As this paper will show, the presentation of this structure as ‘alternative’ adheres to a simplistic juxtaposition of different architectures that follows the imperative of a computable reality, thereby causing problems analogous to the ones it tried to circumvent.

Having a better environmental performance translates into a better financial performance: A study of the European food industry

Abstract This study examined the relationship between Environmental Performance (EP) and Financial Performance (FP) in the European food industry. The food industry is essential for population sustenance, but the rising population and the consequent increase in food production demand have implications for climate change. The aim of this study was to determine if businesses that consume water more efficiently and have lower CO2 emission intensities might experience improved financial performance. Financial and environmental data were sourced from external databases and company reports, and both quantile regression and correlation analyses were conducted. The results reveal that various sectors within the food industry exhibit different linkages between Environmental Performance and Financial Performance. Furthermore, our findings indicate that water use efficiency can significantly influence financial performance, either positively or negatively, while CO2 emission intensity did not exhibit a definitive impact on Financial Performance.

Deciphering the Mechanism of Xijiao Dihuang Decoction in Treating Psoriasis by Network Pharmacology and Experimental Validation.

This study aims to confirm the efficacy of Xijiao Dihuang decoction (XJDHT), a classic prescription, in treating psoriasis and to explore the potential therapeutic mechanism. For pharmacodynamic analysis, a mouse model of imiquimod cream (IMQ)-induced psoriasis was constructed. Active ingredients and genes of XJDHT, as well as psoriasis-related targets, were obtained from public databases. Intersecting genes (IGEs) of XJDHT and psoriasis were collected by Venn Diagram. A protein-protein interaction (PPI) network of IGEs is constructed through the STRING database. The Molecular Complex Detection (MCODE) and Cytohubba plug-ins of Cytoscape software were used to identified hub genes. In addition, we conducted enrichment analysis of IGEs using the R package clusterProfiler. Hub genes were validated via external GEO databases. The influence of XJDHT on Hub gene expression was examined by qPCR and ELISA, and molecular docking was used to evaluate the binding efficacy between active ingredients and hub genes. The results revealed that XJDHT possesses 92 potential genes for psoriasis, and 8 Hub genes were screened. Enrichment analysis suggested that XJDHT ameliorate psoriasis through multiple pathways, including AGE-RAGE, HIF-1, IL-17 and TNF signaling pathway. Validation data confirmed the differential expression of IL6, VEGFA, TNF, MMP9, STAT3, and TLR4. Molecular docking revealed a strong affinity between active ingredients and Hub genes. The efficacy of XJDHT in improving psoriatic lesions in model mice was demonstrated by PASI score and HE staining, potentially attributed to the down-regulation of VEGFA, MMP9, STAT3, TNF, and IL-17A, as evidenced by ELISA and qPCR. This study employed network pharmacology and in vitro experiments to identify the potential mechanisms underlying the therapeutic effects of XJDHT on psoriasis, providing a new theoretical basis for its clinical application in the treatment of psoriasis.

SenticGAT: Sentiment Knowledge Enhanced Graph Attention Network for Multi-view Feature Representation in Aspect-based Sentiment Analysis

Currently, computational intelligence methods, especially artificial neural networks, are increasingly applied to many scenarios. We mainly attempt to explore the task of fine-grained sentiment classification of review data through computational intelligence methods, especially artificial neural networks, and this task is also known as aspect-based sentiment analysis (ABSA). We propose a new technique called SenticGAT which is a multi-view features fusion model enhanced by an external sentiment database. We encode the external sentiment information into the syntactic dependency tree to obtain an enhanced graph with rich sentiment representation. Then we obtain multi-view features including semantics, syntactic, and sentiment features through GAT based on the enhanced graph by external knowledge. We also design a new strategy for fusing multi-view features using the feature parallel frame and convolution method. Eventually, the sentiment polarity of a specific aspect is determined based on the completely fused multi-view features. Experimental results on four public benchmark datasets demonstrate that our method is effective and sound. And it performs superiorly to existing approaches in fusion multiple-view features.

Explainable Supervised Machine Learning Model To Predict Solvation Gibbs Energy.

Many challenges persist in developing accurate computational models for predicting solvation free energy (ΔGsol). Despite recent developments in Machine Learning (ML) methodologies that outperformed traditional quantum mechanical models, several issues remain concerning explanatory insights for broad chemical predictions with an acceptable speed-accuracy trade-off. To overcome this, we present a novel supervised ML model to predict the ΔGsol for an array of solvent-solute pairs. Using two different ensemble regressor algorithms, we made fast and accurate property predictions using open-source chemical features, encoding complex electronic, structural, and surface area descriptors for every solvent and solute. By integrating molecular properties and chemical interaction features, we have analyzed individual descriptor importance and optimized our model though explanatory information form feature groups. On aqueous and organic solvent databases, ML models revealed the predictive relevance of solutes with increasing polar surface area and decreasing polarizability, yielding better results than state-of-the-art benchmark Neural Network methods (without complex quantum mechanical or molecular dynamic simulations). Both algorithms successfully outperformed previous ΔGsol predictions methods, with a maximum absolute error of 0.22 ± 0.02 kcal mol-1, further validated in an external benchmark database and with solvent hold-out tests. With these explanatory and statistical insights, they allow a thoughtful application of this method for predicting other thermodynamic properties, stressing the relevance of ML modeling for further complex computational chemistry problems.