Intuitive Model Research Articles

A flexible symbolic regression method for constructing interpretable clinical prediction models

Machine learning (ML) models trained for triggering clinical decision support (CDS) are typically either accurate or interpretable but not both. Scaling CDS to the panoply of clinical use cases while mitigating risks to patients will require many ML models be intuitively interpretable for clinicians. To this end, we adapted a symbolic regression method, coined the feature engineering automation tool (FEAT), to train concise and accurate models from high-dimensional electronic health record (EHR) data. We first present an in-depth application of FEAT to classify hypertension, hypertension with unexplained hypokalemia, and apparent treatment-resistant hypertension (aTRH) using EHR data for 1200 subjects receiving longitudinal care in a large healthcare system. FEAT models trained to predict phenotypes adjudicated by chart review had equivalent or higher discriminative performance (p < 0.001) and were at least three times smaller (p < 1 × 10−6) than other potentially interpretable models. For aTRH, FEAT generated a six-feature, highly discriminative (positive predictive value = 0.70, sensitivity = 0.62), and clinically intuitive model. To assess the generalizability of the approach, we tested FEAT on 25 benchmark clinical phenotyping tasks using the MIMIC-III critical care database. Under comparable dimensionality constraints, FEAT’s models exhibited higher area under the receiver-operating curve scores than penalized linear models across tasks (p < 6 × 10−6). In summary, FEAT can train EHR prediction models that are both intuitively interpretable and accurate, which should facilitate safe and effective scaling of ML-triggered CDS to the panoply of potential clinical use cases and healthcare practices.

Optimized deep learning-based cricket activity focused network and medium scale benchmark

The recognition of different activities in sports has gained attention in recent years for its applications in various athletic events, including soccer and cricket. Cricket, in particular, presents a challenging task for automatic activity recognition methods due to its closely overlapped activities such as cover drive, and pull short, to name a few. Existing methods often rely on hand-crafted features as the limited availability of public data has restricted the scope of research to only the significant categories of cricket activities. To this end, we proposed a cricket activities dataset and an intuitive end-to-end deep learning model for cricket activity recognition. The data is collected from online sources and pre-processed through cleaning, resizing, and organizing. Similarly, an intuitive deep model is designed with a combination of time-distributed 2D CNN layers and LSTM cells for extracting and learning the spatiotemporal information from the input sequences. For benchmarking, we evaluated the model on our cricket datasets and four standard datasets namely UCF101, HMDB51, YouTube action, and Kinetics. The quantitative results show that the proposed model outperforms different variants of recurrent neural networks and achieved an accuracy of 92%, recall of 91%, and F1 score of 91%. Our code and dataset is publicly available for further research on https://drive.google.com/file/d/1c9qcAz4q00qvx4yFA3pSudWFczm1cWUL/view?usp=sharing.

A postsurgical prognostic nomogram for patients with lymph node positive rectosigmoid junction adenocarcinoma

ObjectiveThe definition of rectosigmoid junction (RSJ) is still in debate. The treatment and prognosis of patients with rectosigmoid junction cancer (RSJC) and positive lymph nodes (PLN-RSJCs) are mostly based on the American Joint Committee on Cancer (AJCC) staging system. Our study aims to assist clinicians in creating a more intuitive and accurate nomogram model for PLN-RSJCs for the prediction of patient overall survival (OS) after surgery.MethodsBased on the Surveillance, Epidemiology, and End Results (SEER) database, we extracted 3384 patients with PLN-RSJCs and randomly divided them into development (n = 2344) and validation (n = 1004) cohorts at a ratio of 7:3. Using univariate and multivariate COX regression analysis, we identified independent risk factors associated with OS in PLN-RSJCs in the development cohort, which were further used to establish a nomogram model. To verify the accuracy of the model, the concordance index (C-index), receiver operating characteristic (ROC) curves, calibration curves, and an internal validation cohort have been employed. Decision curve analysis (DCA) was used to assess the clinical applicability and benefits of the generated model. Survival curves of the low- and high-risk groups were calculated using the Kaplan–Meier method together with the log-rank test.ResultsAge, marital, chemotherapy, AJCC stage, T and N stage of TNM system, tumor size, and regional lymph nodes were selected as independent risk factors and included in the nomogram model. The C-index of this nomogram in the development (0.751;0.737–0.765) and validation cohorts (0.750;0.764–0.736) were more significant than that of the AJCC 7th staging system (0.681; 0.665–0.697). The ROC curve with the calculated area under the curve (AUC) in the development cohort was 0.845,0.808 and 0.800 for 1-year, 3-year and 5-year OS, AUC in the validation cohort was 0.815,0.833 and 0.814 for 1-year, 3-year and 5-year, respectively. The calibration plots of both cohorts for 1-year,3-year and 5-year OS all demonstrated good agreement between actual clinical observations and predicted outcomes. In the development cohort, the DCA showed that the nomogram prediction model is more advantageous for clinical application than the AJCC 7th staging system. Kaplan–Meier curves in the low and high groups showed significant difference in patient OS.ConclusionsWe established an accurate nomogram model for PLN-RSJCs, intended to support clinicians in the treatment and follow-up of patients.

Sistem Kearsipan di Bagian Umum pada Kantor Kelurahan Bunga Tanjung, Kecamatan Datuk Bandar Timur, Kota Tanjungbalai

&#x0D; The motivation behind the review was to decide and describe the administration of documents at the Bunga Tanjung Village Office, Datuk Bandar Timur District, Tanjungbalai City. As well as to distinguish and describe the inhibiting variables in Archives Management in the Office. This study uses a strategy of subjective involvement and information assurance using a purposive testing procedure. In this review, the main resource person is the Head of Tanjung Balai Village, the witness is the staff who oversees correspondence and keeps documents with exploration concentrates, particularly Archives Management or records administration and its suppressing elements. Information collection methods used are perception, interview/interview, documentation. The information checking procedure used is an intuitive model investigation created by Miles and Huberman. The Document Management System in Bunga Tanjung District, Datuk Bandar Timur District, Tanjung Balai City was found that currently the management files have been completed properly, but not yet ideal and the overall administration includes recording or making, insertion, bookkeeping. with and contracting or destroying chronic The repressive elements are that positions have not been established, positions and foundations have not been neglected, there is no extraordinary archive of administrators (Arsiparis) and there are no copies in the archives.&#x0D; Keywords: Archives, Records Management&#x0D;

Well-being impact assessment of artificial intelligence – A search for causality and proposal for an open platform for well-being impact assessment of AI systems

In recent years, the well-being impact assessment approach has been applied in the area of Artificial Intelligence (AI). Existing well-being frameworks and tools provide a relevant starting point. Taking into account its multidimensional nature, well-being assessment is well suited to assess both the expected positive effects of the technology as well as unintended negative consequences. To-date the establishment of causal links mostly stems from intuitive causal models. Such approaches neglect the fact that to prove causal links between the operation of an AI system and observed effects is difficult due to the immense complexity of the socio-technical context. This article aims at providing a framework for ascertaining the attribution of effects of observed impact of AI on well-being. An elaborated approach to impact assessment potentially enabling causal inferences is demonstrated. Furthermore, a new Open Platform for Well-Being Impact Assessment of AI systems (OPIA) is introduced, which is based on a distributed community to build reproducible evidence through effective identification, refinement, iterative testing, and cross-validation of expected causal structures.

Inverse-Designed Lithium Niobate Nanophotonics

Lithium niobate-on-insulator (LNOI) is an emerging photonic platform that exhibits favorable material properties (such as low optical loss, strong nonlinearities, and stability) and enables large-scale integration with stronger optical confinement, showing promise for future optical networks, quantum processors, and nonlinear optical systems. However, while photonics engineering has entered the era of automated “inverse design” via optimization in recent years, the design of LNOI integrated photonic devices still mostly relies on intuitive models and inefficient parameter sweeps, limiting the accessible parameter space, performance, and functionality. Here, we implement a 3D gradient-based inverse-design model tailored for topology optimization based on the LNOI platform, which not only could efficiently search a large parameter space, but also takes into account practical fabrication constraints, including minimum feature sizes and etched sidewall angles. We experimentally demonstrate a spatial-mode multiplexer, a waveguide crossing, and a compact waveguide bend, all with low insertion losses, tiny footprints, and excellent agreement between simulation and experimental results. The devices, together with the design methodology, represent a crucial step toward the variety of advanced device functionalities needed in future LNOI photonics and could provide compact and cost-effective solutions for future optical links, quantum technologies, and nonlinear optics.

Cooperators Pay More Attention to the Outcome of Mutual Cooperation in the One-Shot Prisoner’s Dilemma Game: Empirical Evidence From an Eye-Tracking Study

Based on the dual-process theory, we hypothesized that cooperators in the one-shot prisoner’s dilemma game would exhibit intuitive decision-making. We also hypothesized that an experimental manipulation that may prevent intuitive cooperation (in this study, inverting the payoff matrix) would result in more protracted decision-making and thus lower cooperation rates. To examine these hypotheses, we designed an experiment using an eye-tracking device. In one condition, the outcome of mutual cooperation in the one-shot prisoner’s dilemma game was presented in the upper left-hand corner explaining the result of mutual cooperation first, as in many previous studies (control condition). To suppress the function of intuitive cooperation, we also set the inverted payoff matrix condition in which the positions of the outcomes of mutual cooperation and mutual non-cooperation in the payoff matrix were inverted, explaining the result of mutual non-cooperation first. Although our results did not show the expected differences between the two conditions, it was suggested that cooperators’ decision-making time was shorter in the control condition and that cooperators consistently paid more attention to the outcome of mutual cooperation regardless of the conditions. These results are discussed in relation to the intuitive cooperation model and the social exchange heuristic.

Building insightful, memory-enriched models to capture long-time biochemical processes from short-time simulations

The ability to predict and understand complex molecular motions occurring over diverse timescales ranging from picoseconds to seconds and even hours in biological systems remains one of the largest challenges to chemical theory. Markov state models (MSMs), which provide a memoryless description of the transitions between different states of a biochemical system, have provided numerous important physically transparent insights into biological function. However, constructing these models often necessitates performing extremely long molecular simulations to converge the rates. Here, we show that by incorporating memory via the time-convolutionless generalized master equation (TCL-GME) one can build a theoretically transparent and physically intuitive memory-enriched model of biochemical processes with up to a three order of magnitude reduction in the simulation data required while also providing a higher temporal resolution. We derive the conditions under which the TCL-GME provides a more efficient means to capture slow dynamics than MSMs and rigorously prove when the two provide equally valid and efficient descriptions of the slow configurational dynamics. We further introduce a simple averaging procedure that enables our TCL-GME approach to quickly converge and accurately predict long-time dynamics even when parameterized with noisy reference data arising from short trajectories. We illustrate the advantages of the TCL-GME using alanine dipeptide, the human argonaute complex, and FiP35 WW domain.

Frequency selection for underwater wireless power transfer based on the analysis of eddy current loss

Wireless power transfer (WPT) technology is ideal for wireless charging of unmanned underwater vehicles (UUV). However, in underwater WPT systems, the eddy current loss (ECL) caused by the conductivity of seawater cannot be ignored. This paper obtains the expressions of the equivalent ECL resistance and mutual inductance by calculating the complex power generated by the current in the electric field. An intuitive circuit model is used to describe ECL and its superposition effect. Based on the system efficiency expressions, the influence of the medium conductivity, coil gap and operating frequency on the transmission efficiency is analyzed. Results show that there is an optimal frequency to achieve the maximum dc–dc efficiency in the seawater. Simulated and experimental results verify the validity of the method in calculating ECL and capturing the optimal transmission frequency.

Secure Message Authentication in the Presence of Leakage and Faults

Security against side-channels and faults is a must for the deployment of embedded cryptography. A wide body of research has investigated solutions to secure implementations against these attacks at different abstraction levels. Yet, to a large extent, current solutions focus on one or the other threat. In this paper, we initiate a mode-level study of cryptographic primitives that can ensure security in a (new and practically-motivated) adversarial model combining leakage and faults. Our goal is to identify constructions that do not require a uniform protection of all their operations against both attack vectors. For this purpose, we first introduce a versatile and intuitive model to capture leakage and faults. We then show that a MAC from Asiacrypt 2021 natively enables a leveled implementation for fault resilience where only its underlying tweakable block cipher must be protected, if only the tag verification can be faulted. We finally describe two approaches to amplify security for fault resilience when also the tag generation can be faulted. One is based on iteration and requires the adversary to inject increasingly large faults to succeed. The other is based on randomness and allows provable security against differential faults.

Psychiatryai.com: An exploratory online Artificial Intelligence and Data Science platform to enable near real-time psychiatry and mental health evidence-based medical research and data dissemination

IntroductionPsychiatryai.com is a prototype Artificial Intelligence (AI) and Data Science (DS) platform and research project developed for my Evidence-Based Healthcare (EBHC) course at University of Oxford in MSc studies (Kellogg College). This is a singular, multi-disciplinary, and beta-testing project in Computing Science, Psychiatry, and Mental Health for oral presentation at EPA 2023.ObjectivesAI and DS in Psychiatry and Mental Health have emerged as important research areas in the post Covid-19 pandemic era. This prototype University project (Psychiatryai.com) was launched on 22nd November 2021. It aims to develop a free, secure, and open access platform in near real-time about psychiatry and mental health evidence-based research - for healthcare professionals, doctors, and researchers in psychiatry. The project also aims to integrate findings from the Goldacre Review (2022) into practice and develop novel computing solutions utilising AI and DS, and present findings.MethodsA WordPress site (Psychiatryai.com) was developed with syndicated RSS feeds across 330 psychiatry topics and refreshed by data servers hourly, 24 hours a day, 7 days a week. A total of 43 WordPress plugins were utilised to develop this secure platform. The site is powered by intuitive data modelling and analytics in near real-time and available in open access coding format for peer-review, future development, and research. The primary sources of live evidence for the project are PubMed and University of Helsinki, Finland. The server performance data analytics will be available for poster presentation at EPA 2023. This includes full statistical results and discussion since its inception and launch (including traffic, MESH tags, and PubMed ID), and robust technical analysis and performance outcomes - available freely online to promote research in psychiatry and mental health.ResultsKnowledge Synthesis and Dissemination:Total Words: 4356886 *Live Psychiatry and Mental Health Citations from PubMed: Exceeds 325000Total Evidence Alerts Published: 54391 *Total Algorithms/Topics: 330Total site visitors: 8023 ** Since launch of Psychiatryai.com on 22 November 2021 inclusive to 31 October 2022ConclusionsPsychiatryai.com was able to demonstrate succesful development of an effective and viable platform to study AI and DS in Psychiatry and Mental Health, as evidenced by results table. The platform has also incorporated findings from the Goldacre Review (2022) and aims to continue to collect valuable insights towards full real-time data analytics and dissemination of peer-reviewed current evidence in the future. The emergence of these technologies will be useful in settings such as disaster psychiatry, psychiatry e-training and research, and e-mental health awareness/promotion ahead.Disclosure of InterestP. Naik Consultant of: Dr Paras Naik (Psychiatryai.com) Non-profit University Project

Percentages versus Rasch estimates: alternative methodological strategies for replication studies in mathematics education

ABSTRACT We present an external close replication of the 1985 Fischbein et al. study about intuitive models of multiplication and division. We administered two batteries of mathematics items developed in the original study, via a spiralling process, to a quota sample of 903 students attending grade 7. Compared with the analytic strategy based on the count of correct answers employed in the original research, our study goes a step further as we propose a methodological approach that guarantees measurement invariance, thus allowing for the direct comparison of different groups of students and/or items. The advantages of Rasch estimates compared to percentages of correct answers over the total are critically discussed to show why the former should be considered as more robust than the latter.

Mechanochemical Felkin-Anh Model: Achieving Forbidden Reaction Outcomes with Mechanical Force.

Anti-Felkin-Anh diastereoselectivity can be achieved for nucleophilic additions to α-chiral ketones upon stretching the ketone with a mechanical pulling force. Herein, a mechanochemical Felkin-Anh model is proposed for predicting the outcome of a nucleophilic addition to an α-chiral ketone. Essentially, the fully stretched chiral ketone has one substituent shielding each side of the carbonyl, in contrast to the Felkin-Anh model, in which free rotation around a bond is required to achieve the two rotamers of the ketone. Depending on the pulling scenario, either Felkin-Anh or anti-Felkin-Anh diastereoselectivity is obtained. The model is entirely based on the distance between the pulling points, which is maximized in the anti-periplanar arrangement. The major diastereomer is associated with the approach with the least steric interactions. The intuitive model is validated by means of mechanochemical density functional theory calculations. Importantly, the ketone is fully stretched in the sub 1 nN force regime, thus minimizing the risk of undesired homolytic bond rupture. Moreover, the mechanical force is not used for lowering the reaction barriers associated with the nucleophilic addition; instead, it is solely applied for locking the conformation of a molecule and provoking otherwise inaccessible reaction pathways on the force-modified potential energy surface.

Turbulent Magnetic Diffusivity β Effect in a Magnetically Forced System

We have studied the large-scale dynamo forced with helical magnetic energy. Compared to the kinetic forcing process, the magnetic process is not clearly observed nor intuitive. However, it may represent the actual B field amplification in the stellar corona, accretion disk, plasma lab, or other magnetically dominated systems where the strong kinetic effect does not exist. The interaction between the magnetic field and the plasma is essentially nonlinear. However, when the plasma system is driven by helical energy, whether kinetic or magnetic, the nonlinear process can be linearized with pseudotensors a, β and the large-scale magnetic field . Conventionally, the α effect is thought to be the main dynamo effect converting kinetic energy into magnetic energy and transferring it to the large-scale regime. In contrast, β effect has been thought to diffuse magnetic energy. However, these conclusions are not based on the exact definition of α and β. In this paper, instead of the analytic definition of α and β, we derive a semi-analytic equation and apply it to the simulation data. The half analytic and numerical result shows that the averaged α effect is not so important in amplifying the field. Rather, it is the negative β effect combined with the Laplacian (∇2 → −k 2) that plays a key role in the dynamo process. Further, the negative magnetic diffusivity accounts for the attenuation of the plasma kinetic energy in large scales. We discuss this process using the theoretical method and the intuitive field structure model.

Elasto-geometrical calibration of a hybrid mobile robot considering gravity deformation and stiffness parameter errors

• An elasto-geometrical calibration method taking into account structural and stiffness parameter errors is proposed for a hybrid mobile robot. • A compensation strategy comprehensively considering the pose errors of the 3-RCU parallel module and 2-DoF robotic arm is put forward to improve the accuracy of the robot. • Calibration experiments based on three different models are conducted and the accuracy of the robot before and after calibration is tested to show the validity of the proposed method. Hybrid mobile robots, which combine the advantages of serial and parallel robots and have the ability to realize processing in situ , have considerable application potential in the field of processing and manufacturing. In this paper, a hybrid mobile robot used for wind turbine blade polishing is presented. The robot combines an automated guided vehicle, a 2-DoF robotic arm, and a 3-RCU parallel module. To improve the accuracy, investigating the elasto-geometrical calibration of the robot is necessary. Considering that the 3-RCU parallel module has weak stiffness along the gravitational direction, the stiffness model was established to estimate the deformation caused by the gravity of the mobile platform, ball screws, and motors. Subsequently, a rigid-flexible coupling error model considering structural and stiffness parameter errors is established. Based on these, a parameter identification method for the simultaneous identification of structural and stiffness parameter errors is proposed herein. For the 2-DoF robotic arm with parallelogram mechanisms, an intuitive error model considering the posture error caused by the parallelogram mechanism errors is established. The regularized nonlinear least squares method was adopted for parameter identification. Thereafter, a compensation strategy for the hybrid mobile robot that comprehensively considers the pose errors of the 3-RCU parallel module and 2-DoF robotic arm is proposed. Finally, a verification experiment was performed on the prototype, and the results indicated that after elasto-geometrical calibration, the maximum/mean of the position and posture errors of the hybrid mobile robot decreased from 3.738 mm/2.573 mm to 0.109 mm/0.063 mm and 0.236°/0.179° to 0.030°/0.013°, respectively. Owing to the decrease in the robot pose errors, the quality of the polished surface was more uniform. The range and standard deviation of roughness distribution of the polished surface were reduced from 0.595 μm and 0.248 μm to 0.397 μm and 0.127 μm. The methods proposed herein have reference significance for elasto-geometrical calibration of other parallel or hybrid robots.

Electron Polarization in Ultrarelativistic Plasma Current Filamentation Instabilities

Plasma current filamentation of an ultrarelativistic electron beam impinging on an overdense plasma is investigated, with emphasis on radiation-induced electron polarization. Particle-in-cell simulations provide the classification and in-depth analysis of three different regimes of the current filaments, namely, the normal filament, abnormal filament, and quenching regimes. We show that electron radiative polarization emerges during the instability along the azimuthal direction in the momentum space, which significantly varies across the regimes. We put forward an intuitive Hamiltonian model to trace the origin of the electron polarization dynamics. In particular, we discern the role of nonlinear transverse motion of plasma filaments, which induces asymmetry in radiative spin flips, yielding an accumulation of electron polarization. Our results break the conventional perception that quasisymmetric fields are inefficient for generating radiative spin-polarized beams, suggesting the potential of electron polarization as a source of new information on laboratory and astrophysical plasma instabilities.

Construction of diagnostic prediction model for Wilson's disease.

Wilson's disease, also known as hepatolenticular degeneration, is a rare human autosomal recessive inherited disorder of copper metabolism. The clinical manifestations are diverse, and the diagnosis and treatment are often delayed. The purpose of this study is to establish a new predictive diagnostic model of Wilson's disease and evaluate its predictive efficacy by multivariate regression analysis of small trauma, good accuracy, low cost, and quantifiable serological indicators, in order to identify Wilson's disease early, improve the diagnosis rate, and clarify the treatment plan. A retrospective analysis was performed on 127 patients with Wilson's disease admitted to the First People's Hospital of Yunnan Province from January 2003 to May 2022 as the experimental group and 73 patients with normal serological indicators who were not diagnosed with Wilson's disease. SPSS version 26.0 software was used for single factor screening and a multivariate binary logistic regression analysis to screen out independent factors. R version 4.1.0 software was used to establish an intuitive nomogram prediction model for the independent influencing factors included. The accuracy of the nomogram prediction model was evaluated and quantified by calculating the concordance index (C-index) and drawing the calibration curve. At the same time, the area under the curve (AUC) of the nomogram prediction model and the receiver operating characteristic (ROC) curve of the Leipzig score was calculated to compare the predictive ability of the nomogram model and the current Leipzig score for Wilson's disease. Alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (AKP), albumin (ALB), uric acid (UA), serum calcium (Ca), serum phosphorus (P), and hemoglobin (HGB) are closely related to the occurrence of Wilson's disease (p < 0.1). The prediction model of Wilson's disease contains seven independent predictors: ALT, AST, AKP, ALB, UA, Ca, and P. The AUC value of the prediction model was 0.971, and the C-index value was 0.972. The calibration curve was well fitted with the ideal curve. The nomogram prediction model had a good predictive effect on the occurrence of Wilson's disease; the ROC curve of Leipzig score was drawn, and the AUC value was calculated. The AUC of the Leipzig score was 0.969, indicating that the prediction model and the scoring system had predictive value, and the nomogram prediction model had a better predictive effect on the research objects of the center. ALT, AST, AKP, ALB, UA, Ca, and P are independent predictors of Wilson's disease, and can be used as early predictors. Based on the nomogram prediction model, the optimal threshold was determined to be 0.698, which was an important reference index for judging Wilson's disease. Compared with the Leipzig score, the nomogram prediction model has a relatively high sensitivity and specificity and has a good clinical application value.

Image-Text Embedding Learning via Visual and Textual Semantic Reasoning.

As a bridge between language and vision domains, cross-modal retrieval between images and texts is a hot research topic in recent years. It remains challenging because the current image representations usually lack semantic concepts in the corresponding sentence captions. To address this issue, we introduce an intuitive and interpretable model to learn a common embedding space for alignments between images and text descriptions. Specifically, our model first incorporates the semantic relationship information into visual and textual features by performing region or word relationship reasoning. Then it utilizes the gate and memory mechanism to perform global semantic reasoning on these relationship-enhanced features, select the discriminative information and gradually grow representations for the whole scene. Through the alignment learning, the learned visual representations capture key objects and semantic concepts of a scene as in the corresponding text caption. Experiments on MS-COCO [1] and Flickr30K [2] datasets validate that our method surpasses many recent state-of-the-arts with a clear margin. In addition to the effectiveness, our methods are also very efficient at the inference stage. Thanks to the effective overall representation learning with visual semantic reasoning, our methods can already achieve very strong performance by only relying on the simple inner-product to obtain similarity scores between images and captions. Experiments validate the proposed methods are more than 30-75 times faster than many recent methods with code public available. Instead of following the recent trend of using complex local matching strategies [3], [4], [5], [6] to pursue good performance while sacrificing efficiency, we show that the simple global matching strategy can still be very effective, efficient and achieve even better performance based on our framework.

Quercetin@Gd3+ doped Prussian blue nanocubes induce the pyroptotic death of MDA-MB-231 cells: combinational targeted multimodal therapy, dual modal MRI, intuitive modelling of r1-r2 relaxivities.

Quercetin (Qu), a potential bioflavonoid has gained considerable interest as a promising chemotherapeutic drug which can inhibit the proliferation of triple-negative breast cancer (TNBC) cells due to its regulation of the expression of tumor-suppressor gene metastasis and antioxidant property. Notably, Qu exhibits a very negligible cytotoxic effect on normal cells, even with high-dose treatment, while it is shows high affinity to TNBC. However, the efficiency of Qu is limited clinically due to its poor bioavailability, caused by its low aqueous solubility (2.15 μg mL-1 at 25 °C), rapid gastrointestinal digestion and chemical instability in alkaline and neutral media. Herein, polydopamine (PDA)-coated, NH2-PEG-NH2 and hyaluronic acid (HA)-functionalized Gd3+-doped Prussian blue nanocubes (GPBNC) are reported as a multifunctional platform for the codelivery of Qu as a chemotherapeutic agent and GPBNC as a photodynamic (PDT) and photothermal (PTT) agent with improved therapeutic efficiency to overcome theses barriers. PDA, NH2-PEG-NH2 and HA stabilize GPBNC@Qu and facilitate bioavailability and active-targeting, while absorption of near infrared (NIR) (808 nm; 1 W cm-2) induces PDT and PTT activities and dual T1-T2-weighted magnetic resonance imaging (MRI) with high relaxometric parameters (r1 10.06 mM-1 s-1 and r2 24.96 mM-1 s-1 at a magnetic field of 3 T). The designed platform shows a pH-responsive Qu release profile and NIR-induced therapeutic efficiency of ∼79% in 20 minutes of irradiation, wherein N-terminal gardermin D (N-GSDMD) and a P2X7-receptor-mediated pyroptosis pathway induces cell death, corroborating the up-regulation of NLRP3, caspase-1, caspase-5, N-GSDMD, IL-1β, cleaved Pannexin-1 and P2X7 proteins. More interestingly, the increasing relaxivity values of Prussian blue nanocubes with Gd3+ doping have been explained on the basis of Solomon-Bloembergen-Morgan theory, considering inner- and outer-sphere relaxivity, wherein crystal defects, coordinated water molecules, tumbling rate, metal to water proton distance, correlation time, magnetisation value etc. play a significant role. In summary, our study suggests that GPBNC could be a beneficial nanocarrier for theranostic purposes against TNBC, while our conceptual study clearly demonstrates the role of various factors in increasing relaxometric parameters.

Prediction of Solar Energy Yield Based on Artificial Intelligence Techniques for the Ha’il Region, Saudi Arabia

In order to satisfy increasing energy demand and mitigate global warming worldwide, the implementation of photovoltaic (PV) clean energy installations needs to become common practice. However, solar energy is known to be dependent on several random factors, including climatic and geographic conditions. Prior to promoting PV systems, an assessment study of the potential of the considered location in terms of power yield should be conducted carefully. Manual assessment tools are unable to handle high amounts of data. In order to overcome this difficulty, this study aims to investigate various artificial intelligence (AI) models—with respect to various intuitive prediction benchmark models from the literature—for predicting solar energy yield in the Ha’il region of Saudi Arabia. Based on the daily data, seven seasonal models, namely, naïve (N), simple average (SA), simple moving average (SMA), nonlinear auto-regressive (NAR), support vector machine (SVM), Gaussian process regression (GPR) and neural network (NN), were investigated and compared based on the root mean square error (RMSE) and mean absolute percentage error (MAPE) performance metrics. The obtained results showed that all the models provided good forecasts over three years (2019, 2020, and 2021), with the naïve and simple moving average models showing small superiority. The results of this study can be used by decision-makers and solar energy specialists to analyze the power yield of solar systems and estimate the payback and efficiency of PV projects.