Search

In this work, bundlelike CuCo2O4 microstructures (CuCo2O4 BMs) assembled with ultrathin nanosheets were fabricated through employing an easy and scalable hydrothermal method along with an extra the...

In the business domain,bundling is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers. Existing recommender systems mostly focus on recommending individual items that users may be interested in, such as the considerable research work on collaborative filtering that directly models the interaction between users and items. In this paper, we target at a practical but less explored recommendation problem named personalized bundle composition, which aims to offer an optimal bundle (i.e., a combination of items) to the target user. To tackle this specific recommendation problem, we formalize it as a combinatorial optimization problem on a set of candidate items and solve it within a neural combinatorial optimization framework. Extensive experiments on public datasets are conducted to demonstrate the superiority of the proposed method.

As one of the core components of online games, matchmaking is the process of arranging multiple players into matches, where the quality of matchmaking systems directly determines player satisfaction and further affects the life cycle of game products. With the number of candidate players increases, the number of possible match combinations grows exponentially, which makes the current implementation for multiplayer matchmaking can only obtain locally optimal arrangement in an inefficient fashion. In this paper, we focus on the globally optimized matchmaking problem, in which the objective is to decide an optimal matching sequence for the queuing players. To tackle this challenging problem, we propose a novel data-driven matchmaking framework, called GloMatch, based on machine learning principles. Through transforming the matchmaking problem into a sequential decision problem, we solve it with the help of an effective policy-based deep reinforcement learning algorithm. Quantitative experiments on simulation and online game environments demonstrate the effectiveness of the presented framework.

Bone morphogenetic protein 7 (BMP7), a member of the transforming growth factor-β (TGF-β) family, plays pivotal roles in energy expenditure. However, whether and how BMP7 regulates hepatic insulin sensitivity is still poorly understood. Here, we show that hepatic BMP7 expression is reduced in high-fat diet (HFD)-induced diabetic mice and palmitate (PA)-induced insulin-resistant HepG2 and AML12 cells. BMP7 improves insulin signaling pathway in insulin resistant hepatocytes. On the contrary, knockdown of BMP7 further impairs insulin signal transduction in PA-treated cells. Increased expression of BMP7 by adenovirus expressing BMP7 improves hyperglycemia, insulin sensitivity and insulin signal transduction. Furthermore, BMP7 inhibits mitogen-activated protein kinases (MAPKs) in both the liver of obese mice and PA-treated cells. In addition, inhibition of MAPKs recapitulates the effects of BMP7 on insulin signal transduction in cultured hepatocytes treated with PA. Activation of p38 MAPK abolishes the BMP7-mediated upregulation of insulin signal transduction both in vitro and in vivo. Together, our results show that hepatic BMP7 has a novel function in regulating insulin sensitivity through inhibition of MAPKs, thus providing new insights into treating insulin resistance-related disorders such as type 2 diabetes.

The radical S-adenosylmethionine (SAM) superfamily is currently the largest known enzyme family. These enzymes reductively cleave SAM to produce a highly reactive 5'-deoxyadenosyl (dAdo) radical, which abstracts a hydrogen from the substrate and initiates diverse reactions. The canonic dAdo radical-mediated hydrogen abstraction can be changed to radical addition reactions by using olefin-containing substrate analogues, which result in adenosylation reactions. Here we report investigation of the adenosylation reactions catalyzed by four radical SAM l-Tyr lyases (RSTLs), including HydG, FbiC, and two ThiH enzymes from different organisms. We show RSTLs have diverse substrate specificity, and ThiH from E. coli exhibits the highest substrate tolerance toward the tested substrates. We also show ThiH from Clostridium berjerinckii does not act on 4-amino-l-phenylalanine, but catalyzes adenosylation of the corresponding olefin-containing analogue, suggesting adenosylation may occur more easily than the canonic radical SAM reactions. Our study highlights the remarkable catalytic promiscuity of radical SAM enzyme and the potential in using these enzymes for the synthesis of nucleotide-containing compounds.

In this work, uniform MnCo

OBJECTIVES: To investigate the impact of total variation regularized expectation maximization (TVREM) reconstruction on the image quality of (68)Ga-PSMA-11 PET/CT using phantom and patient data. METHODS: Images of a phantom with small hot sphere inserts and 20 prostate cancer patients were acquired with a digital PET/CT using list-mode and reconstructed with ordered subset expectation maximization (OSEM) and TVREM with seven penalisation factors between 0.01 and 0.42 for 2 and 3 minutes-per-bed (m/b) acquisition. The contrast recovery (CR) and background variability (BV) of the phantom, image noise of the liver, and SUV(max) of the lesions were measured. Qualitative image quality was scored by two radiologists using a 5-point scale (1-poor, 5-excellent). RESULTS: The performance of CR, BV, and image noise, and the gain of SUV(max) was higher for TVREM 2 m/b groups with the penalization of 0.07 to 0.28 compared to OSEM 3 m/b group (all p < 0.05). The image noise of OSEM 3 m/b group was equivalent to TVREM 2 and 3 m/b groups with a penalization of 0.14 and 0.07, while lesions’ SUV(max) increased 15 and 20%. The highest qualitative score was attained at the penalization of 0.21 (3.30 ± 0.66) for TVREM 2 m/b groups and the penalization 0.14 (3.80 ± 0.41) for 3 m/b group that equal to or greater than OSEM 3 m/b group (2.90 ± 0.45, p = 0.2 and p < 0.001). CONCLUSIONS: TVREM improves lesion contrast and reduces image noise, which allows shorter acquisition with preserved image quality for PSMA PET/CT. ADVANCES IN KNOWLEDGE: TVREM reconstruction with optimized penalization factors can generate higher quality PSMA-PET images for prostate cancer diagnosis.

Instrumental variables (IVs), sources of treatment randomization that are conditionally independent of the outcome, play an important role in causal inference with unobserved confounders. However, the existing IV-based counterfactual prediction methods need well-predefined IVs, while it is an art rather than science to find valid IVs in many real-world scenes. Moreover, the predefined hand-made IVs could be weak or erroneous by violating the conditions of valid IVs. These thorny facts hinder the application of the IV-based counterfactual prediction methods. In this paper, we propose a novel Automatic Instrumental Variable decomposition (AutoIV) algorithm to automatically generate representations serving the role of IVs from observed variables (IV candidates). Specifically, we let the learned IV representations satisfy the relevance condition with the treatment and exclusion condition with the outcome via mutual information maximization and minimization constraints, respectively. We also learn confounder representations by encouraging them to be relevant to both the treatment and the outcome. The IV and confounder representations compete for the information with their constraints in an adversarial game, which allows us to get valid IV representations for IV-based counterfactual prediction. Extensive experiments demonstrate that our method generates valid IV representations for accurate IV-based counterfactual prediction., Comment: Accepted by ACM Transactions on Knowledge Discovery from Data (TKDD) 2022

Behavior tracing or predicting is a key component in various application scenarios like online user modeling and ubiquitous computing, which significantly benefits the system design (e.g., resource pre-caching) and improves the user experience (e.g., personalized recommendation). Traditional behavior tracing methods like Markovian and sequential models take recent behaviors as input and infer the next move by using the most real-time information. However, these existing methods rarely comprehensively model the low-level temporal irregularity in the recent behavior sequence, i.e., the unevenly distributed time intervals between consecutive behaviors, and the high-level periodicity in the long-term activity cycle, i.e., the periodic behavior patterns of each user. In this paper, we propose an intuitive and effective embedding method called Multi-level Aligned Temporal Embedding (MATE), which can tackle the temporal irregularity of recent behavior sequence and then align with the long-term periodicity in the activity cycle. Specifically, we combine time encoding and decoupled attention mechanism to build a temporal self-attentive sequential decoder to address the behavior-level temporal irregularity. To embed the activity cycle from the raw behavior sequence, we employ a novel temporal dense interpolation followed by a self-attentive sequential encoder. Then we first propose the periodic activity alignment to capture the long-term activity-level periodicity and construct the activity-behavior alignment to combine the activity-level with behavior-level representation to make the final prediction. We experimentally prove the effectiveness of the proposed model on a game player behavior sequence dataset and a real-world App usage trace dataset. Further, we deploy the proposed behavior tracing model into a game scene preloading service which can effectively reduce the waiting time of scene transfer by preloading the predicted game scene for each user.

Win prediction and performance evaluation are two core subjects in the sport analytics. Traditionally, they are treated separately and studied by two independent communities. However, this is not the intuitive way how humans interpret the matches: we predict the match results with the competition carrying on, and simultaneously evaluate each action based on the game context and its downstream impact. Predicting the match outcomes and evaluating the actions are coupled tasks, and the more accurately we predict, the better the evaluation is To this end, we develop a unified Match Tracing framework (namely, MT), for tackling the win prediction and performance evaluation jointly. The main idea of MT is to learn a real-time look-ahead win rate curve rather than a single scalar (win or lose). And the value of an action can be objectively measured with respect to the increase or decrease of the curve. To meet the low-latency restrictions of the online deployments, an efficient model equipped with recurrent attention mechanism and matrix perturbation (i.e., MT-Net) is built for learning and yielding the win rate curve. MT-Net encodes the players' behavior sequence through an attention mechanism and captures the player-interaction effects through a graph embedding method. With the action values derived from the win rate curve, performance can be quantified at different granularities (action/player/match level) by integrated analysis. Experiments on an e-sport game demonstrate the prediction effectiveness and the feasibility of the MT framework. Furthermore, we present the detailed application cases of MT, including key actions recognition and close match detection.

In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers. Existing recommender systems mostly focus on recommending individual items that users may be interested in. In this paper, we target at a practical but less explored recommendation problem named bundle recommendation, which aims to offer a combination of items to users. To tackle this specific recommendation problem in the context of the \emph{virtual mall} in online games, we formalize it as a link prediction problem on a user-item-bundle tripartite graph constructed from the historical interactions, and solve it with a neural network model that can learn directly on the graph-structure data. Extensive experiments on three public datasets and one industrial game dataset demonstrate the effectiveness of the proposed method. Further, the bundle recommendation model has been deployed in production for more than one year in a popular online game developed by Netease Games, and the launch of the model yields more than 60\% improvement on conversion rate of bundles, and a relative improvement of more than 15\% on gross merchandise volume (GMV)., Comment: 8 pages, 10 figures, accepted paper on CIKM 2020

Matchmaking is a core problem for the e-sports and online games, which determines the player satisfaction and further influences the life cycle of the gaming products. Most of matchmaking systems take the form of grouping the queuing players into two opposing teams by following certain rules. The design and implementation of matchmaking systems are usually product-specific and labor-intensive. This paper proposes a two-stage data-driven matchmaking framework (namely OptMatch), which is applicable to most of gaming products and has the minimal product knowledge required. OptMatch contains an offline learning stage and an online planning stage. The offline learning stage includes (1) relationship mining modules to learn the low-dimensional representations of individuals by capturing the high-order inter-personal interactions, and (2) a neural network to incorporate the team-up effect and predict the match outcomes. The online planning stage optimizes the gross player utilities (i.e., satisfaction) during the matchmaking process, by leveraging the learned representations and predictive model. Quantitative evaluations on four real-world datasets and an online experiment on Fever Basketball game are conducted to empirically demonstrate the effectiveness of OptMatch.

Profiling game players, especially potential churn and payment prediction, is of paramount importance for online games to improve the product design and the revenue. However, current solutions view either churn or payment prediction as an independent task and most of the previous attempts only depend on the single data source, i.e., the tabular portrait data. Based on the data of two real-world online games, we conduct extensive data analysis. On the one hand, there exists a significant correlation between the player churn and payment. On the other hand, heterogeneous multi-source data, including player portrait, behavior sequence, and social network, can complement each other for a better understanding of each player. To this end, we propose a novel Multi-source Data Multi-task Learning approach, named MSDMT, to capture the multi-source implicit information and predict the churn and payment of each player simultaneously in a multi-task learning fashion. Comprehensive experiments on two real-world datasets validate the effectiveness and rationality of our proposed method, which yields significant improvements against other baseline approaches.

Online gaming is one of the most successful applications having a large number of players interacting in an online persistent virtual world through the Internet. However, some cheating players gain improper advantages over normal players by using illegal automated plugins which has brought huge harm to game health and player enjoyment. Game industries have been devoting much efforts on cheating detection with multiview data sources and achieved great accuracy improvements by applying artificial intelligence (AI) techniques. However, generating explanations for cheating detection from multiple views still remains a challenging task. To respond to the different purposes of explainability in AI models from different audience profiles, we propose the EMGCD, the first explainable multi-view game cheating detection framework driven by explainable AI (XAI). It combines cheating explainers to cheating classifiers from different views to generate individual, local and global explanations which contributes to the evidence generation, reason generation, model debugging and model compression. The EMGCD has been implemented and deployed in multiple game productions in NetEase Games, achieving remarkable and trustworthy performance. Our framework can also easily generalize to other types of related tasks in online games, such as explainable recommender systems, explainable churn prediction, etc.

In this work, porous MgCo

For energy-limited wireless sensor networks (WSNs), we propose a multiparameter fusion decision routing (MPFDR) algorithm in this study. This algorithm gives a comprehensive account of the residual energy and forward distance, single-hop transmission ratio, cache queue, and energy equilibrium degree. It calculates the routing evaluation parameters of the forward neighbors, realizing a multidirectional reflection of the network status. Simultaneously, combined with the defined routing selection strategy based on the parameter contribution degree and fuzzy contribution degree, the fusion contribution degree of each forward neighbor is obtained. Then, the node with the most considerable fusion contribution degree is selected as the next hop. Finally, the performance of the MPFDR algorithm is simulated and compared with other algorithms. Simulation results indicate that our algorithm has good congestion control ability in energy-limited wireless sensor networks and can significantly reduce the packet loss rate and average hops.

Parametric imaging using the Patlak model has been shown to provide improved lesion detectability and specificity. The Patlak model requires both tissue time-activity curves (TACs) after equilibrium and knowledge of the input function from the start of injection. Therefore, the conventional dynamic scanning protocol typically starts from the radiotracer injection all the way to equilibrium. In this paper, we propose the use of hybrid population-based and model-based input function estimation and evaluate its use for whole-body Patlak analysis, in order to reduce the total scan time and simplify clinical Patlak parametric imaging protocols. Possible quantitative errors caused by the simplified scanning protocol were also analyzed both theoretically and with the use of clinical data.Clinical data from 24 patients referred for tumor staging were included in this study. The patients underwent a whole-body dynamic PET study, 20 min after FDG injection (0.13 mCi/kg). The proposed whole-body scanning protocol includes 6 passes with 4-5 bed positions, depending on the size of the patient, with 2 min for each bed position. An input function from the literature was selected as the shape of the population-based input function. The descending aorta from the corresponding CT image was segmented and applied on the reconstructed dynamic PET images to acquire an image-based input function, which was later fitted using an exponential model. Due to the late scan time, only the later portion of the input function was available, which was used to scale the population-based input function. The hybrid input function was used to derive the whole-body Patlak images. Assuming a given error in the population-based input function, its influence on the final Patlak images were also derived theoretically and verified using the clinical data sets. Finally, the image quality of the reconstructed Patlak slope image was evaluated by an experienced radiologist in four different aspects: image artifacts, image noise, lesion sharpness, and lesion detectability.It was found that errors in the population-based input function only affect the absolute scale of the Patlak slope image. The induced error is proportional to the percentage area-under-curve (AUC) error in the input function. These findings were also confirmed by numerical analysis. The predicted global scale was in good agreement with results from both image-based Patlak and direct Patlak approach. The fractions of the AUC from the early portion population-based input function were also found to be around 18% of the total AUC of the input function, further limiting the propagation of quantitation error from population-based input function to the final Patlak slope image. The reconstructed Patlak images were also found by the radiologist to provide excellent confidence in lesion detection tasks.We have proposed a simplified whole-body scanning protocol that utilizes both population-based input function and model-based input function. The error from the population-based function was found to only affect the global scale and the overall quantitative impact can be predicted using our proposed formulas.

Recent decades have witnessed the rapid growth of educational data mining (EDM), which aims at automatically extracting valuable information from large repositories of data generated by or related to people’s learning activities in educational settings. One of the key EDM tasks is cognitive modelling with examination data, and cognitive modelling tries to profile examinees by discovering their latent knowledge state and cognitive level (e.g. the proficiency of specific skills). However, to the best of our knowledge, the problem of extracting information from both objective and subjective examination problems to achieve more precise and interpretable cognitive analysis remains underexplored. To this end, we propose a fuzzy cognitive diagnosis framework (FuzzyCDF) for examinees’ cognitive modelling with both objective and subjective problems. Specifically, to handle the partially correct responses on subjective problems, we first fuzzify the skill proficiency of examinees. Then we combine fuzzy set theory and educational hypotheses to model the examinees’ mastery on the problems based on their skill proficiency. Finally, we simulate the generation of examination score on each problem by considering slip and guess factors. In this way, the whole diagnosis framework is built. For further comprehensive verification, we apply our FuzzyCDF to three classical cognitive assessment tasks, i.e., predicting examinee performance, slip and guess detection, and cognitive diagnosis visualization. Extensive experiments on three real-world datasets for these assessment tasks prove that FuzzyCDF can reveal the knowledge states and cognitive level of the examinees effectively and interpretatively.

In this work, MgCo2O4 nanoflakes (NFs) and nanowires (NWs) on stainless steel foil (SSF) were hydrothermally prepared followed with an additional annealing conversion of the precursors. These MgCo2O4 nanomaterials possessed mesoporous structures and electrochemical tests demonstrated their battery-like feature. The MgCo2O4 were peeled off the SSF, and the NF-based powders exhibited a high specific capacity of 424.98 C g−1 at 1 A g−1, while the NW powders delivered 351.17 C g−1. An asymmetric supercapacitor (ASC) was assembled with MgCo2O4 as cathode and AC as anode, respectively, and the MgCo2O4 NFs//AC ASC possessed an excellent electrochemical performance such as a capacity up to 146.10 C g−1, a long-life cycling stability with 108.28% capacity retention over 5000 cycles at 6 A g−1, and an high energy density of 41.10 W h kg−1 at a power density of 1012.80 W kg−1. In contrast, the MgCo2O4 NWs//AC ASC exhibited a similar cycling durability and an inferior energy density of 36.97 W h kg−1. Such impressive results indicate that the mesoporous MgCo2O4 NFs and NWs may serve as promising battery-like cathode materials for the next-generation advanced supercapacitors. Besides, the present method can provide some merits including simple and cost-effective synthesis, large production, and especially the shape of MgCo2O4 is uniform and can be easily tuned by changing the reaction parameters. The current method can be extended for the preparation of other transition metal oxides (TMOs)-based electrode materials with superior performances.

With the accelerated development of clean energies for carbon emission reduction, floating photovoltaic (FPV) has become an emerging solution. With its advantages of saving land, suppressing evaporation, and improving power generation efficiency, it has attracted the attention of the global clean energy field. According to the available surface area of artificial water bodies worldwide and system assumptions, the maximum global technical potential of FPV power plants is estimated to be 1000 GW. As FPV interacts tightly with the constructed water area, design of FPV is still lacking in theory, data, and experience. Environmental effects of FPV should also be clarified. This article introduces the current FPV power plant construction and future development trends. The site selection conditions of FPV power plant, the design elements of the upper power generation structure, and the overall characteristics of different types of lower floating structures are summarized. Finally, the complex interaction between the FPV power plant and the ecological environment is explained in terms of construction and operation. This review has a significant reference value for the design and construction of FPV power plants and the formulation of related construction codes.

Although temperature is a main external effect on rock decay, the relationship between a rock’s decay rate and temperature still remains unclear and there is limited information about the rate of rock decay under varied temperatures during dry–wet cycle conditions in southwest China. Therefore, the aim of the present paper was to explore the rate of mudstone decay through an experiment, in which a model was proposed to calculate their decay rates under varied temperatures conditions. A set of customized test device, including a model test container, a thermostat-controlled heating plate, and a water supply and drainage device, was applied in the experiment. Three dry–wet cycles were conducted on five samples at 60, 90, 105, 120 and 180 °C, respectively. The crack width, vertical displacement and wetted area were measured to analyse the temperature-induced decay mechanism during dry–wet cycle processes. The results showed that tiny cracks appeared on the surface of samples after heating and that the vertical displacement increased in the upward direction due to swelling of the mudstone after water exposure. The crack width extended with increasing water exposure, but it decreased after the surface of samples was gradually wetted after several hours of water exposure. The continually increasing wetted area and progressively fast wetting speed were the outward manifestation of the increasing number of internal cracks. Temperature-induced stress could promote the generation of cracks and decay rates of the tested rocks raised with higher temperatures. Quantitative analysis revealed that the rock decay rate is significantly related to temperature in the form of a S-Curve. The sample barely decayed at 60 °C, but the decay rate was close to 90% at 180 °C. The higher the temperature was, the faster the wetting speed was and the more cracks generated, and ultimately rocks decayed as a result of crack extension.

Rock masses in southwest China are dominated by alternating layers of sandstone and mudstone. When exposed to natural conditions, mudstone is vulnerable to disintegration, causing the overlying sandstone to be extremely likely to collapse under the action of a load or other conditions. An effective and innovative experimental method to characterize weathering processes would contribute to collapse prevention. In this study, a customized test unit, including a model test container, a lever-loading device and a thermostat-controlled heating plate, was applied to explore the mechanism of crack development in mudstone over multiple dry-wet cycles. The crack width, vertical displacement and wetted area were measured to analyse the slaking mechanism acting during these cycles. The results show that tiny cracks appeared on the surface of the sample after heating and that the vertical displacement increased in the upward direction because of swelling of mudstone. The crack width expanded with increasing water exposure, but after the water infiltrated the surface of the sample, the crack width decreased. The external surface of the sample was gradually infiltrated in the second dry-wet cycle, and the infiltration area increased continually. The infiltrating speed grew progressively faster with each cycle, and the number and size of internal cracks monotonically increased. The sample fractured as a result of crack extension. These results have theoretical significance regarding the ground collapse of alternating layers of sandstone and mudstone.

Cognitive radio has been regarded as a promising technology to improve spectrum utilization significantly. Many studies have discussed underlay spectrum sharing and power control, but issues such as the interference of the primary system have just been considered as the constraint. In this paper, we build a spectrum allocation mathematical model which considers different interference intensity according to relative geographic locations between two SLs in the spectrum-sharing mode of cognitive radio network. Then it’s converted into multi-objective optimization problem. To solve the spectrum sharing problem, the multi-objective improved genetic algorithm is adopted. Simulation results show that our proposed methods greatly outperform the commonly used K-max-cut in graph theory. It can better realize the network benefit maximization and reduce the disturbance to the primary system by using the multi-objective optimization algorithm.

Online gaming is a multi-billion dollar industry that entertains a large, global population. However, one unfortunate phenomenon known as real money trading harms the competition and the fun. Real money trading is an interesting economic activity used to exchange assets in a virtual world with real world currencies, leading to imbalance of game economy and inequality of wealth and opportunity. Game operation teams have been devoting much efforts on real money trading detection, however, it still remains a challenging task. To overcome the limitation from traditional methods conducted by game operation teams, we propose, MVAN, the first multi-view attention networks for detecting real money trading with multi-view data sources. We present a multi-graph attention network (MGAT) in the graph structure view, a behavior attention network (BAN) in the vertex content view, a portrait attention network (PAN) in the vertex attribute view and a data source attention network (DSAN) in the data source view. Experiments conducted on real-world game logs from a commercial NetEase MMORPG( JusticePC) show that our method consistently performs promising results compared with other competitive methods over time and verifiy the importance and rationality of attention mechanisms. MVAN is deployed to several MMORPGs in NetEase in practice and achieving remarkable performance improvement and acceleration. Our method can easily generalize to other types of related tasks in real world, such as fraud detection, drug tracking and money laundering tracking etc.

The network lifetime of wireless rechargeable sensor network (WRSN) is commonly extended through routing strategy or wireless charging technology. In this paper, we propose an optimization algorithm from the aspects of both charging and routing process. To balance the network energy in charging part, node&rsquo, s charging efficiency is balanced by dynamically planning charging point positions and the charging time is allocated according to the energy consumption rate of nodes. Moreover, the routing method is adapted to the node&rsquo, s charging efficiency. The adaptive routing strategy assigns more forwarding tasks to nodes that can get more energy during the charging phase, and makes the data packets transmit farther away, thus reducing the average hops and energy consumption of the network. Finally, the simulation results reveal that the proposed algorithm has certain advantages in prolonging the network lifetime, reducing the average hop counts and balancing the energy of each node.

Objectives: To investigate the impact of total variation regularized expectation maximization (TVREM) reconstruction on the image quality of 68Ga-PSMA-11 PET/CT using phantom and patient data. Methods: Images of a phantom with small hot sphere inserts and 20 prostate cancer patients were acquired with a digital PET/CT using list-mode and reconstructed with ordered subset expectation maximization (OSEM) and TVREM with seven penalisation factors between 0.01 and 0.42 for 2 and 3 minutes-per-bed (m/b) acquisition. The contrast recovery (CR) and background variability (BV) of the phantom, image noise of the liver, and SUVmax of the lesions were measured. Qualitative image quality was scored by two radiologists using a 5-point scale (1-poor, 5-excellent). Results: The performance of CR, BV, and image noise, and the gain of SUVmax was higher for TVREM 2 m/b groups with the penalization of 0.07 to 0.28 compared to OSEM 3 m/b group (all p < 0.05). The image noise of OSEM 3 m/b group was equivalent to TVREM 2 and 3 m/b groups with a penalization of 0.14 and 0.07, while lesions’ SUVmax increased 15 and 20%. The highest qualitative score was attained at the penalization of 0.21 (3.30 ± 0.66) for TVREM 2 m/b groups and the penalization 0.14 (3.80 ± 0.41) for 3 m/b group that equal to or greater than OSEM 3 m/b group (2.90 ± 0.45, p = 0.2 and p < 0.001). Conclusions: TVREM improves lesion contrast and reduces image noise, which allows shorter acquisition with preserved image quality for PSMA PET/CT. Advances in knowledge: TVREM reconstruction with optimized penalization factors can generate higher quality PSMA-PET images for prostate cancer diagnosis.

Objectives:To investigate the impact of deep learning (DL) on radiologists’ detection accuracy and reading efficiency of rib fractures on CT.Methods:Blunt chest trauma patients (n = 198) undergoing thin-slice CT were enrolled. Images were read by two radiologists (R1, R2) in three sessions: S1, unassisted reading; S2, assisted by DL as the concurrent reader; S3, DL as the second reader. The fractures detected by the readers and total reading time were documented. The reference standard for rib fractures was established by an expert panel. The sensitivity and false-positives per scan were calculated and compared among S1, S2, and S3.Results:The reference standard identified 865 fractures on 713 ribs (102 patients) The sensitivity of S1, S2, and S3 was 82.8, 88.9, and 88.7% for R1, and 83.9, 88.7, and 88.8% for R2, respectively. The sensitivity of S2 and S3 was significantly higher compared to S1 for both readers (all p < 0.05). The sensitivity between S2 and S3 did not differ significantly (both p > 0.9). The false-positive per scan had no difference between sessions for R1 (p = 0.24) but was lower for S2 and S3 than S1 for R2 (both p < 0.05). Reading time decreased by 36% (R1) and 34% (R2) in S2 compared to S1.Conclusions:Using DL as a concurrent reader can improve the detection accuracy and reading efficiency for rib fracture.Advances in knowledge:DL can be integrated into the radiology workflow to improve the accuracy and reading efficiency of CT rib fracture detection.

As the coupling relationship between information systems and physical power grids is getting closer, various types of cyber attacks have increased the operational risks of a power cyber-physical System (CPS). In order to effectively evaluate this risk, this paper proposed a method of cross-domain propagation analysis of a power CPS risk based on reinforcement learning. First, the Fuzzy Petri Net (FPN) was used to establish an attack model, and Q-Learning was improved through FPN. The attack gain was defined from the attacker&rsquo, s point of view to obtain the best attack path. On this basis, a quantitative indicator of information-physical cross-domain spreading risk was put forward to analyze the impact of cyber attacks on the real-time operation of the power grid. Finally, the simulation based on Institute of Electrical and Electronics Engineers (IEEE) 14 power distribution system verifies the effectiveness of the proposed risk assessment method.