<p><span lang="EN-US">In the digital age, recommendation systems navigate vast alternatives. Content-based, collaborative filtering, deep-driven, and cross-domain recommendation (CDR) have been studied significantly but face cold-start and data sparsity. Though CDR methods outperform others, they struggle to optimize user-item matrices. Recent graph-based CDR methods improve efficiency by leveraging additional user-item interactions; however, optimizing graph features remains an open research area. Moreover, current techniques do not consider the impact of noise items (unrelated) on recommendation accuracy. To address this gap, this paper develops a heterogeneous semantic graph-embedding (HSGE) edge-pruning model that leverages user ratings and item metadata in the source and target domains to recommend items to target domain users. To achieve it, at first Word2Vec method is applied to explicit and implicit details, followed by Node2Vec-driven graph embedding matrix generation. Our HSGE method obtains user-user, user-item, and item-item connections to achieve more semantic features. To improve accuracy, our model prunes edges that drop source domain items and allied edges unrelated to the target domain users. Subsequently, the retained HSGE matrices from both domains are processed for element-wise attention. A multi-layer perceptron with cosine similarity processed combined features matrices to generate top-N recommendations with superior hit-rate (HR) and normalized discounted cumulative gain (NDCG).</span></p>

Recommendation systems are pivotal for personalized user experiences, employing algorithms to predict and suggest items aligned with user preferences. Deep learning (DL) models, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), excel in capturing sequential dependencies, enhancing recommendation accuracy. However, challenges persist in session-based recommendation systems, particularly with gradient descent and class imbalances. Addressing these challenges, this work introduces dynamic LSTM (D-LSTM), a novel DL-based recommendation system tailored for dynamic E-commerce environments. The primary objective is to optimize recommendation accuracy by effectively capturing temporal dependencies within user sessions. The methodology involves the integration of D-LSTM with weight matrix optimization and a Bayesian personalized ranking (BPR) adaptable learning rate optimizer to enhance learning efficiency. Experimental results demonstrate the efficacy of D-LSTM, showing significant improvements over existing models. Specifically, comparisons with the hybrid time-centric prediction (HTCP) model reveal a performance enhancement of 19.4%, 17.2%, 35.41%, and 21.99% for hit-rate (HR) and mean reciprocal rank (MRR) in 10k and 20k recommendation sets using the Tmall dataset. These findings underscore the superior performance of D-LSTM, highlighting its potential to advance personalized recommendations in dynamic E-commerce settings.

Background: Methylene blue and some of its analogues have known antibacterial activity, however their exact mechanism of action is unknown Objective: In this study, the minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) of several methylene blue analogues were determined against five bacterial strains, whereafter the data were used to create and validate a pharmacophore model. Methods: The agar dilution method was used to screen the analogues for antibacterial activity, while the broth microdilution method was used to determine their MIC and MBC. A pharmacophore model was constructed and validated using the rank score, fit value, enrichment factor (EF10%), hit rate (HR10%) and receiver operating characteristic area under the curve (ROC-AUC) as metrics. Results: Against Staphylococcus aureus, pyronin B (0.125 µg/ml) was more active than tetracycline (1 µg/ml) and pyronin Y (0.5 µg/ml), 1,9-dimethylmethylene blue (2 µg/ml), basic blue 3 (2 µg/ml), new methylene blue (2 µg/ml) and Nile blue (2 µg/ml) had similar activity compared to tetracycline. Pyronin B, 1,9-dimethylmethylene blue and new methylene blue were bactericidal. A pharmacophore model was created (rank score: 36.55, max. fit value: 3), which was able to identify active analogues out of the test set (EF10%: 2.83, HR10%: 28.57%, ROC-AUC: 0.84 ± 0.04). The pharmacophore model highlighted that a positive ionisable, aromatic ring as well as a hydrophobic moiety are important for antibacterial activity. Conclusion: Methylene blue analogues were found to have potent antibacterial activity and a pharmacophore model was created to understand the structural requirements for activity.

To study the degree of accuracy in gingival shade matching of undergraduate students using a computer application. In total, 76 undergraduate dental students' gingival shade selection abilities were evaluated using an in-house developed computer application. A total of 15 intraoral gingival photographs and 21 pink gingival color porcelain samples were used. The environmental conditions were standardized, and no time limit was set for answering in the computer application. Fourteen gingival color samples (66.6%) were not useful for representing the studied gingival shades. Not all natural gingival colors studied were represented within the 50.50% acceptability limits of the pink samples. There were no statistically significant differences between men and women in terms of "hit" percentages. The highest correlation coefficient (in absolute value) was for the L* coordinate (the darker the gingiva in the picture, the higher the hit rate for choosing the "ideal" shade tab); however, none of the linear correlation coefficients were statistically significant. Not all colors provided in the pink ceramic system were useful for subjective gingival selection. There were no statistically significant differences between male and female dental students in gingival color perception. The L* coordinate was the only one that influenced the correct perception of gingival color by dental students, and it did so more in women than in men.

Optimization of high-speed fixed-wing UAV penetration strategy based on deep reinforcement learning

‘‘Learned” admission policies have shown promise in improving Content Delivery Network (CDN) cache performance and lowering operational costs. Unfortunately, existing learned policies are optimized with a few fixed cache sizes while in reality, cache sizes often vary over time in an unpredictable manner. As a result, existing solutions cannot provide consistent benefits in production settings. We present SLAP , a learned CDN cache admission approach based on segmented object reuse time prediction. SLAP predicts an object’s reuse time range using the Long-Short-Term-Memory model and admits objects that will be reused (before eviction) given the current cache size. SLAP decouples model training from cache size, allowing it to adapt to arbitrary sizes. The key to our solution is a novel segmented labeling scheme that makes SLAP without requiring precise prediction on object reuse time. To further make SLAP a practical and efficient solution, we propose aggressive reusing of computation and training on sampled traces to optimize model training, and a specialized predictor architecture that overlaps prediction computation with miss object fetching to optimize model inference. Our experiments using production CDN traces show that SLAP achieves significantly lower write traffic (38%-59%), longer SSDs lifetime (104%-178%), a consistently higher hit rate (3.2%-11.7%), and requires no effort to adapt to changing cache sizes, outperforming existing policies.

In vehicular networks, some edge servers may not function properly due to the time-varying load condition and the uneven computing resource distribution, resulting in a low quality of caching services. To overcome this challenge, we develop a Vehicular dew computing (VDC) architecture for the first time by combining dew computing with vehicular networks, which can achieve wireless communication between vehicles in a resource-constrained environment. Consequently, it is crucial to develop an adaptive caching scheme that empowers vehicles to form efficient cooperation in VDC. In this paper, we propose an intelligent caching scheme based on VDC architecture, which includes two parts. First, to meet the dynamic nature of VDC, a spatiotemporal vehicle clustering algorithm is proposed to establish adaptive cooperation to assist content caching for vehicles. Second, the multi-armed bandit algorithm is employed to select suitable content for caching in vehicles based on real-time file popularity, and a model is established to dynamically update each vehicle’s request preferences. Extensive experiments are conducted to demonstrate that the proposed scheme has excellent performance in terms of cluster head stability and cache hit rate.

Influenza remains a significant threat to public health. In severe cases, excessive inflammation can lead to severe pneumonia or acute respiratory distress syndrome, contributing to patient morbidity and mortality. While antivirals can be effective if administered early, current anti-inflammatory drugs have limited success in treating severe cases. Therefore, discovering new anti-inflammatory agents to inhibit influenza-related inflammatory diseases is crucial. Herein, we screened a drug library with known targets using a human monocyte U937 infected with the influenza virus to identify novel anti-inflammatory agents. We also evaluated the anti-inflammatory effects of the hit compounds in an influenza mouse model. Our research revealed that JAK inhibitors exhibited a higher hit rate and more potent inhibition effect than inhibitors targeting other drug targets in vitro. Of the 22 JAK inhibitors tested, 15 exhibited robust anti-inflammatory activity against influenza virus infection in vitro. Subsequently, we evaluated the efficacy of 10 JAK inhibitors using an influenza mouse model and observed that seven provided protection ranging from 40% to 70% against lethal influenza virus infection. We selected oclacitinib as a representative compound for an extensive study to further investigate the in vivo therapeutic potential of JAK inhibitors for severe influenza-associated inflammation. Our results revealed that oclacitinib effectively suppressed neutrophil and macrophage infiltration, reduced pro-inflammatory cytokine production, and ultimately mitigated lung injury in mice infected with lethal influenza virus without impacting viral titer. These findings suggest that JAK inhibitors can modulate immune responses to influenza virus infection and may serve as potential treatments for influenza.IMPORTANCEAntivirals exhibit limited efficacy in treating severe influenza when not administered promptly during the infection. Current steroidal and nonsteroidal anti-inflammatory drugs demonstrate restricted effectiveness against severe influenza or are associated with significant side effects. Therefore, there is an urgent need for novel anti-inflammatory agents that possess high potency and minimal adverse reactions. In this study, 15 JAK inhibitors were identified through a screening process based on their anti-inflammatory activity against influenza virus infection in vitro. Remarkably, 7 of the 10 selected inhibitors exhibited protective effects against lethal influenza virus infection in mice, thereby highlighting the potential therapeutic value of JAK inhibitors for treating influenza.

Although screening technology has heavily impacted the fields of metal catalysis and drug discovery, its application to the discovery of new catalyst classes has been limited. The diversity of on- and off-cycle pathways, combined with incomplete mechanistic understanding, means that screens of potential new ligands have thus far been guided by intuitive analysis of the metal binding potential. This has resulted in the discovery of new classes of ligands, but the low hit rates have limited the use of this strategy because large screens require considerable cost and effort. Here, we demonstrate a method to identify promising screening directions via simple and scalable computational and linear regression tools that leads to a substantial improvement in hit rate, enabling the use of smaller screens to find new ligands. The application of this approach to a particular example of Ni-catalyzed cross-electrophile coupling of aryl halides with alkyl halides revealed a previously overlooked trend: reactions with more electron-poor amidine ligands result in a higher yield. Focused screens utilizing this trend were more successful than serendipity-based screening and led to the discovery of two new types of ligands, pyridyl oxadiazoles and pyridyl oximes. These ligands are especially effective for couplings of bromo- and chloroquinolines and isoquinolines, where they are now the state of the art. The simplicity of these models with parameters derived from metal-free ligand structures should make this approach scalable and widely accessible.

Loftus (1978) highlighted the distinction between a theoretical concept such as memory or attention, and its observed measure such as hit rate or percent correct. If the functional relationship between the concept and its measure is nonlinear then only some interaction effects are interpretable. This is an example of the wider "problem of coordination" which pervades scientific measurement. Loftus drew on the principles of additive conjoint measurement (ACM) to discuss the consequences when the coordination function is assumed to be monotonic. This led to the distinction between removable interactions that are consistent with an additive effect on the underlying theoretical concept and nonremovable interactions that are not. However, the adoption of these ideas by researchers has been greatly limited by the fact that no statistical procedure exists to determine if and to what extent an interaction is removable or otherwise. The lack of such a procedure has similarly limited the impact of ACM on research practice. The aim of this article is to present such a procedure. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Session-based recommendations with sequential context using attention-driven LSTM

Real-time monitoring of rainfall areas based on satellite remote sensing is of vital importance for extreme rainfall research and disaster prediction. In this study, a new rainfall area identification algorithm was developed for the new generation of geostationary satellites with high spatial and temporal resolution and rich bands. As the main drivers of the rainfall process, the macro and micro physical properties of clouds play an important role in the formation and development of rainfall. We considered differences in the absorption capacity of the water vapor absorption channels in the infrared band and introduced a sensitivity difference of rainfall area in water vapor channels to construct a sensitive detection of the water vapor region. The results of this algorithm were evaluated using Global Precipitation Measurement (GPM) satellite products and CloudSat measurements in various scenarios, with hit rates of 70.03% and 81.39% and false alarm rates of 2.05% and 21.34%, respectively. Spatiotemporal analysis revealed that the types of upper clouds in the rainfall areas mainly consisted of deep convection, cirrostratus, and nimbostratus clouds. Our study provides supporting data for weather research and disaster prediction, as well as an efficient and reliable method for capturing temporal and spatial features.

The shape and convexity are crucial quality assessment indicators for hot-rolled electrical steel strips. Besides bending rolls, shifting rolls, and the original roll profile, the thermal roll profile also plays a significant role in controlling the shape and convexity during the hot-rolling process. However, it is always overlooked due to its dynamic uncertainty. To solve this problem, it is necessary to achieve online cooling-status control for the local thermal expansion of rolls. Based on the existing structure of a mill, a pair of special partition-cooling beams with an intelligent cooling system was designed. For high efficiency and practicality, a new online predictive model was established for the dynamic temperature field of the hot-rolling process. An equivalent treatment was applied to the boundary condition corresponding to the practical cooling water flow. In addition, by establishing the corresponding target distribution curve for the partitioned water flow cooling, online water-flow-partitioning control of the thermal roll profile was achieved. In the practical application process, a large number of onsite results exhibited that the predicted error was within 5% compared to the experimental results. The temperature difference between the upper and lower rolls was within 5 °C, and the temperature difference on both sides of the rolls was controlled within 0.7 °C. The hit rate of convexity (C40) increased by 33%. It was demonstrated that the partition-cooling processes of hot rolling are effective for the local shape and special convexity. They are able to serve as a better control method in the hot-rolling process.

Abstract. The Maritime Continent (MC) regularly experiences powerful convective storms that produce intense rainfall, flooding and landslides, which numerical weather prediction models struggle to forecast. Nowcasting uses observations to make more accurate predictions of convective activity over short timescales (∼ 0–6 h). Optical flow algorithms are effective nowcasting methods as they are able to accurately track clouds across observed image series and predict forward trajectories. Optical flow is generally applied to weather radar observations; however, the radar coverage network over the MC is not complete and the signal cannot penetrate the high mountainous regions. In this research, we apply optical flow algorithms from the pySTEPS nowcasting library to satellite imagery to generate both deterministic and probabilistic nowcasts over the MC. The deterministic algorithm shows skill up to 4 h on spatial scales of 10 km and coarser and outperforms a persistence nowcast for all lead times. Lowest skill is observed over the mountainous regions during the early afternoon, and highest skill is seen during the night over the sea. A key feature of the probabilistic algorithm is its attempt to reduce uncertainty in the lifetime of small-scale convection. Composite analysis of 3 h lead time nowcasts, initialised in the morning and afternoon, produces reliable ensembles but with an under-dispersive distribution and produces area under the curve scores (i.e. ratio of hit rate to false alarm rate across all probability thresholds) of 0.80 and 0.71 over the sea and land, respectively. When directly comparing the two approaches, the probabilistic nowcast shows greater skill at ≤ 60 km spatial scales, whereas the deterministic nowcast shows greater skill at larger spatial scales ∼ 200 km. Overall, the results show promise for the use of pySTEPS and satellite retrievals as an operational nowcasting tool over the MC.

Numerical and experimental study on the calcination process of the raw materials of lithium battery cathode

Named Data Networking (NDN) has emerged as a promising network architecture for content delivery in edge infrastructures, primarily due to its name-based routing and integrated in-network caching. Despite these advantages, sub-optimal performance often results from the decentralized decision-making processes of caching devices. This article introduces a paradigm shift by implementing a Software Defined Networking (SDN) controller to optimize the placement of highly popular content in NDN nodes. The optimization process considers critical networking factors, including network congestion, security, topology modification, and flowrules alterations, which are essential for shaping content caching strategies. The article presents a novel content caching framework, Popularity-aware Caching in Popular Programmable NDN nodes (PaCPn). Employing a multi-variant vector autoregression (VAR) model driven by an SDN controller, PaCPn periodically updates content popularity based on time-series data, including 'request rates' and 'past popularity'. It also introduces a controller-driven heuristic algorithm that evaluates the proximity of caching points to consumers, considering factors such as 'distance cost,' 'delivery time,' and the specific 'status of the requested content'. PaCPn utilizes customized DATA named packets to ensure the source stores content with a valid residual freshness period while preventing intermediate nodes from caching it. The experimental results demonstrate significant improvements achieved by the proposed technique PaCPn compared to existing schemes. Specifically, the technique enhances cache hit rates by 20% across various metrics, including cache size, Zipf parameter, and exchanged traffic within edge infrastructure. Moreover, it reduces content retrieval delays by 28%, considering metrics such as cache capacity, the number of consumers, and network throughput. This research advances NDN content caching and offers potential optimizations for edge infrastructures.

Abstract With the rapid development of the Internet-of-Things (IoT), a massive amount of transient data is transmitted in edge networks. Transient data are highly time-sensitive, such as monitoring data generated by industrial devices. Due to their inefficiency, traditional caching strategies in edge networks are inadequate for handling transient data. Thus, to improve the efficiency of transient data caching, we construct a freshness model of transient data and propose a maximum entropy Actor–Critic-based caching strategy, TD-MEAC-which can improve the freshness of cached data and reduce the long-term caching cost. Simulation results show that the proposed TD-MEAC achieves a higher cache hit rate and maintains a higher average freshness of cached transient data compared with the existing DRL and baseline caching strategies.

Prenatal alcohol exposure (PAE) continues to be a worldwide problem. Affected offspring display impaired neurodevelopment, including difficulties with executive control. Although PAE has also been associated with decreased blood flow to fetuses, the relationship between PAE and altered blood flow is not well understood. We used preclinical models of PAE, transient systemic hypoxia ischemia (TSHI), and PAE + TSHI combined to assess the effects on neurodevelopmental outcomes using translationally relevant touchscreen operant platform testing. Twenty-eight Long-Evans (Blue Spruce, Strain HsdBlu:LE) dams were randomly assigned to one of four experimental groups: Saccharin Control (Sham), 5% Ethanol (PAE), TSHI, or 5% Ethanol and TSHI (PAE + TSHI). Dams consumed either saccharin or 5% ethanol during gestation. TSHI was induced on Embryonic Day 19 (E19) during an open laparotomy where the uterine arteries were transiently occluded for 1 h. Pups were born normally and, after weaning, were separated by sex. A total of 80 offspring, 40 males and 40 females, were tested on the 5-Choice Continuous Performance paradigm (5C-CPT). Female offspring were significantly impacted by TSHI, but not PAE, with an increase in false alarms and a decrease in hit rates, omissions, accuracy, and correct choice latencies. In contrast, male offspring were mildly affected by PAE, but not TSHI, showing decreases in premature responses and increases in accuracy. No significant interactions between PAE and TSHI were detected on any measure. Transient systemic hypoxia ischemia impaired performance on the 5C-CPT in females, leading to a bias toward stimulus responsivity regardless of stimulus type. In contrast, TSHI did not affect male offspring, and only slight effects of PAE were seen. Together, these data suggest that TSHI in females may cause alterations in cortical structures that override alterations caused by moderate PAE.

Abstract BackgroundGiven the strikingly high diagnostic error rate in hospitals, and the recent development of Large Language Models (LLMs), we set out to measure the diagnostic sensitivity of two popular LLMs: GPT‐4 and PaLM2. Small‐scale studies to evaluate the diagnostic ability of LLMs have shown promising results, with GPT‐4 demonstrating high accuracy in diagnosing test cases. However, larger evaluations on real electronic patient data are needed to provide more reliable estimates.MethodsTo fill this gap in the literature, we used a deidentified Electronic Health Record (EHR) data set of about 300,000 patients admitted to the Beth Israel Deaconess Medical Center in Boston. This data set contained blood, imaging, microbiology and vital sign information as well as the patients' medical diagnostic codes. Based on the available EHR data, doctors curated a set of diagnoses for each patient, which we will refer to as ground truth diagnoses. We then designed carefully‐written prompts to get patient diagnostic predictions from the LLMs and compared this to the ground truth diagnoses in a random sample of 1000 patients.ResultsBased on the proportion of correctly predicted ground truth diagnoses, we estimated the diagnostic hit rate of GPT‐4 to be 93.9%. PaLM2 achieved 84.7% on the same data set. On these 1000 randomly selected EHRs, GPT‐4 correctly identified 1116 unique diagnoses.ConclusionThe results suggest that artificial intelligence (AI) has the potential when working alongside clinicians to reduce cognitive errors which lead to hundreds of thousands of misdiagnoses every year. However, human oversight of AI remains essential: LLMs cannot replace clinicians, especially when it comes to human understanding and empathy. Furthermore, a significant number of challenges in incorporating AI into health care exist, including ethical, liability and regulatory barriers.

Predicting compound activity in assays is a long-standing challenge in drug discovery. Computational models based on compound-induced gene expression signatures from a single profiling assay have shown promise toward predicting compound activity in other, seemingly unrelated, assays. Applications of such models include predicting mechanisms-of-action (MoA) for phenotypic hits, identifying off-target activities, and identifying polypharmacologies. Here, we introduce transcriptomics-to-activity transformer (TAT) models that leverage gene expression profiles observed over compound treatment at multiple concentrations to predict the compound activity in other biochemical or cellular assays. We built TAT models based on gene expression data from a RASL-seq assay to predict the activity of 2692 compounds in 262 dose-response assays. We obtained useful models for 51% of the assays, as determined through a realistic held-out set. Prospectively, we experimentally validated the activity predictions of a TAT model in a malaria inhibition assay. With a 63% hit rate, TAT successfully identified several submicromolar malaria inhibitors. Our results thus demonstrate the potential of transcriptomic responses over compound concentration and the TAT modeling framework as a cost-efficient way to identify the bioactivities of promising compounds across many assays.