Search

Social relationships are the basis for communication and collaboration between players in many online games. In this paper, we propose a machine learning-based approach to model the relationship between players and guilds in online games. Our approach combines deep learning techniques with useful prior expert knowledge, where the core component is a graph convolutional network that is designed to utilize both social relationships and behavior preference of players. For each player in the game, the model is trained to estimate the likelihood of whether the player matches the guild, which enables rapid matching of players and guilds via recommendation. The proposed approach is evaluated on a industrial dataset collected from a popular online game, and also deployed in the game as a basic component of the social system. Experimental results show that our approach is not only intuitive but also very superior to other baseline methods.

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.

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.

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.

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.

Recent progress in wireless charging technologies has greatly promoted the development of rechargeable wireless sensor networks (RWSN). The network lifetime of RWSN can be commonly extended through routing strategy and wireless charging technology. However, the node accepts the relay request of its neighbor unconditionally, and it cannot remove its overload on its own in a timely manner in traditional routing strategies. The energy balancing efficiency of the network may be limited by this passive mechanism, which poses a great challenge to obtaining optimal joint efficiency of routing and charging strategies. In this paper, we propose an autonomous load regulation mechanism-based energy balanced routing algorithm (ALRMR) for RWSN. In addition to an efficient framework of joint wireless energy transfer and multi-hop routing where the routing strategy is adapted to the charging scheme, an innovative load regulation mechanism is proposed. Under this mechanism, each node can actively adjust its own load by controlling its relay radius. The simulation demonstrates the advantages of our algorithm for energy balance efficiency and improving the network lifetime through the charging scheme and the innovative mechanism.

The Hybrid energy supply (HES) wireless relay system is a new green network technology, where the source node is powered by the grid and relay is powered by harvested renewable energy. However, the network&rsquo, s performance may degrade due to the intermittent nature of renewable energy. In this paper, our purpose is to minimize grid energy consumption and maximize throughput. However, improving the throughput requires increasing the transmission power of the source node, which will lead to a higher grid energy consumption. Linear weighted summation method is used to turn the two conflicting objectives into a single objective. Link assignment and a power control strategy are adopted to maximize the total reward of the network. The problem is formulated as a discrete Markov decision model. In addition, a backwards induction method based on state deletion is proposed to reduce the computational complexity. Simulation results show that the proposed algorithm can effectively alleviate performance degradation caused by the lack of renewable energy, and present the trade-off between energy consumption and throughput.

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.

Great improvement recently appeared in terms of efficient service delivery in wireless sensor networks (WSNs) for Internet of things (IoT). The IoT is mainly dependent on optimal routing of energy-aware WSNs for gathering data. In addition, as the wireless charging technology develops in leaps and bounds, the performance of rechargeable wireless sensor networks (RWSNs) is greatly ameliorated. Many researches integrated wireless energy transfer into data gathering to prolong network lifetime. However, the mobile collector cannot visit all nodes under the constraints of charging efficiency and gathering delay. Thus, energy consumption differences caused by different upload distances to collectors impose a great challenge in balancing energy. In this paper, we propose an adaptive dual-mode routing-based mobile data gathering algorithm (ADRMDGA) in RWSNs for IoT. The energy replenishment capability is reasonably allocated to low-energy nodes according to our objective function. Furthermore, the innovative adaptive dual-mode routing allows nodes to choose direct or multi-hop upload modes according to their relative upload distances. The empirical study confirms that ADRMDGA has excellent energy equilibrium and effectively extends the network lifetime.

Diagnosing students' knowledge proficiency, i.e., the mastery degrees of a particular knowledge point in exercises, is a crucial issue for numerous educational applications, e.g., targeted knowledge training and exercise recommendation. Educational theories have converged that students learn and forget knowledge from time to time. Thus, it is necessary to track their mastery of knowledge over time. However, traditional methods in this area either ignored the explanatory power of the diagnosis results on knowledge points or relied on a static assumption. To this end, in this paper, we devise an explanatory probabilistic approach to track the knowledge proficiency of students over time by leveraging educational priors. Specifically, we first associate each exercise with a knowledge vector in which each element represents an explicit knowledge point by leveraging educational priors (i.e., Q-matrix ). Correspondingly, each student is represented as a knowledge vector at each time in a same knowledge space. Second, given the student knowledge vector over time, we borrow two classical educational theories (i.e., Learning curve and Forgetting curve ) as priors to capture the change of each student's proficiency over time. After that, we design a probabilistic matrix factorization framework by combining student and exercise priors for tracking student knowledge proficiency. Extensive experiments on three real-world datasets demonstrate both the effectiveness and explanatory power of our proposed model.

Target detection methods based on region proposal are complicated and the detection speed is slow, which is difficult to meet the requirement of real-time detection of massive power inspection pictures. SSD (Single Shot MultiBox Detector) is simpler than the one that requires region proposal, eliminates the generation of proposals and subsequent feature resampling phases, and encapsulates all calculations in a single network. The model is more easily trained while meeting the high accuracy and real-time detection requirements. In this paper, we described the SSD method in detail, compared and analyzed the DPM (Deformable Parts Model), Faster R-CNN and SSD methods. The three methods are tested and verified by using the actual data set of transmission line foreign body, and the influence of different parameters on the identification results is discussed. The experimental results show that the SSD method can achieve 85.2% of the mAP(mean average precision) at 26FPS (GTX1050Ti), it can meet the real-time requirements while ensuring the accuracy of detection, and the feasibility of the recognition method based on deep learning is verified in real time foreign body detection of transmission line.

The new generation intelligent park is demanded for the flexible utilization mode of distributed renewable energy, energy storage equipment and the various characteristic load access. However, the energy router is correspondingly responsible for energy routing and dynamic control. Its uniform interface supports the plug and play of distributed power, energy storage and load of the intelligent park. In our paper, the new energy network architecture are firstly presented. Then, the function structure and the bidirectional flow control strategy of these energy routers are designed to satisfy the energy routing demands. The bidirectional flow control among users and a variety of distributed power, energy storage equipment is achieved by implementing our energy exchange scheme of the energy routing interface design. Meanwhile, we put the energy router interface design into the practical operation in local energy internet, construct the application system based on the energy internet technology with Cell in intelligent park, and ultimately make the collaborative operation and green resource sharing in intelligent system.

With the analysis of the actual structure property of data network in power grid, a network model based on a layered structure named DWS is introduced in this paper. In this DWS layered network featured with the tree structure, aiming to meet the requirements of network operation reliability, we combine the relative access distance with node degree for the nodes for lower levels to add redundant connections correspondingly. In order to evaluate the network invulnerability under the change of weight factor for relative access distance, the load redistribution and the impact of different node capacity redundancy are also considered to illustrate the typical cascading failure process. To note that, the scale in the remaining effective connected components after the deliberate attack is the major measurement of structural invulnerability. In the simulation, it has been illustrated that, with the improvement in the weight of relative access distance and in the capacity redundancy, the cascading failure impact on the layered network structure in the condition of heavy load is decreased obviously, which shows the better structural invulnerability and ensures the applicability of the data network model which we proposed.

Researches on blast-resistant measures for underground structures such as tunnels and underground shopping malls are of great importance for their significant role in economic and social development. In this paper, a new blast-resistant method based on wave converters with spring oscillator for underground structures was put forward, so as to convert the shock wave with high frequency and high peak pressure to the periodic stress wave with low frequency and low peak pressure. The conception and calculation process of this new method were introduced. The mechanical characteristics and motion evolution law of wave converters were deduced theoretically. Based on the theoretical deduction results and finite difference software FLAC3D, the dynamic responses of the new blast-resistant structure and the traditional one were both calculated. Results showed that, after the deployment of wave converters, the peak absolute values of the bending moment, shear force, and axial force of the structure decreased generally, which verified the good blast-resistant effect of the new blast-resistant method.

To investigate the image quality and the minimum required radiation dose for automatic tube potential selection (ATPS) in dual-source computed tomography (DSCT) coronary computed tomography angiography (CCTA). Three hundred twenty-five consecutive patients (153 men and 172 women) undergoing CCTA were assigned to either the ATPS group (n = 172) or the control group (n = 153); the control group underwent imaging at a constant current of 120 kV. All patients were scanned in either prospectively ECG-triggered high-pitch helical mode or sequential mode. The subjective image quality score, attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), volume CT dose index (CTDIvol), and effective dose (ED) were compared between the two groups with the Student t test or Mann–Whitney U test. The subjective image quality score was not significantly different between the two groups. Imaging noise and attenuation were both significantly higher in the ATPS group than in the control group (imaging noise: 25.6 ± 7.6 versus 15.8 ± 4.0 HU, P < 0.001; attenuation: 559.6 ± 142.0 versus 412.5 ± 64.3 HU, P < 0.001). SNR and CNR were significantly lower in the ATPS group than in the control group (SNR: 23.21 ± 7.40 versus 27.71 ± 8.25, P < 0.001; CNR: 27.81 ± 8.44 versus 33.94 ± 9.69, P < 0.001). ED was significantly lower in the ATPS group than in the control group (ED: 1.25 ± 1.24 versus 2.19 ± 1.77 mSv, P < 0.001). For both groups, ED was significantly lower in the high-pitch mode than in the sequential mode. The use of ATPS for CCTA significantly reduced the radiation dose while maintaining image quality.

With the advent of the new information technologies, the power communication service object is continuously improved by the modernization level of the electric power industry. The long term planning goal is not only to provide a transmission pipeline of power dispatching, but also a variety of service type, which requires a reliable and high efficiency power system communication network. Previous researches on the wide area protection propose a feasible solution on adaptive protection by using IP/SDH-based WAN. With the increasing capacity requirement, tradition IP/SDH device will be replaced gradually by the optical transport network. In this paper, we propose a novel hybrid switching fabric reconfigurable optical add-drop multiplexer/optical cross-connect (ROADM/OXC) by using electric coding embedded approach on the high speed backbone router. Also, the corresponding hybrid switching network coding (HSNC) scheme is propose to implement real-time cross-connect operation. HSNC schemes are integrated with MAWAPS of previous research and the results show that it is an efficient approach for various granularities switching structure. Performance of HSNC under different switching ratio and fiber core is presented and is also compared with traditional approach, and it is concluded to be a competitive approach that can be widely used in the next generation power grid backbone.

The contrast medium (CM) induced nephropathy required new CT imaging protocol. This study evaluated the feasibility of low contrast medium (CM) volume and injection flow using aortic dual-energy CT (DECT) angiography with non-linear blending technique. Sixty patients were randomly assigned to two groups: control group (n=30), single-energy CT 70 ml CM at injection rate of 5 ml/s; study group (n=30), DECT mode, 0.5 ml per kg of patient weight CM at injection rate=(weight × 0.5 ml/kg)/(4+scan time). Non-linear blending technique was used for dual-energy images. Mean attention, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of aorta were compared. The level of visible renal artery branches was scored. There was no significant difference between the two groups in the mean aortic attention, SNR and CNR (all P > 0.05). Significant difference was showed in CM injection rate (p < 0.001) and volume (P < 0.001). The renal artery score had no statistically significant difference (P=0.771). Compared conventional scan and CM injection protocol, DECT with non-linear blending technique maintained the image quality of aortic CT angiography with reduced CM volume and flow rate, which could reduce the risks associated with CM injection.

PURPOSE To investigate the diagnostic accuracy of coronary computed tomographic (CT) angiography (CCTA) using filtered back projection (FBP) and sinogram-affirmed iterative reconstruction (SAFIRE) of different strength factors with invasive coronary angiography as the reference standard. MATERIALS AND METHODS Fifty consecutive patients (32 men and 18 women) prospectively underwent electrocardiogram-triggered CCTA on a dual-source CT system. The acquisition window was set depending on the heart rate (HR): HR of less than 60 beats per minute (bpm) at the 70% RR interval, 61 to 80 bpm at 30% to 80% RR interval, and greater than 80 bpm at 30% to 50% RR interval; 100 kV and 359 to 377 mA s for patients with a body mass index of less than 24 kg/m, and 410 to 438 mA s at 120 kV for patients with a body mass index of 24 kg/m or greater. Image data were reconstructed using both FBP and SAFIRE. Sinogram-affirmed iterative reconstruction series were reconstructed using 3 different strength factors. Two blinded observers independently assessed the image quality and image impression of each coronary segment using a 4-point scale (1, non-diagnostic; and 4, excellent). Image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured. Filtered back projection and all SAFIRE series were independently evaluated for coronary artery stenosis (>50%), and their diagnostic accuracy was compared with invasive coronary angiography. RESULTS Statistically significant increases in SNR and CNR were obtained when higher strength factors were used. The highest SNR and CNR were found with the highest SAFIRE strength factor of 5; however, this strength also resulted in a more unfamiliar, "plasticlike" image appearance. Imaging quality scores of FBP and different SAFIRE strengths were 3.37 ± 0.49, 3.41 ± 0.47, 3.52 ± 0.30, and 3.48 ± 0.35, respectively (P < 0.001). The diagnostic accuracies were 92.91%, 93.76%, 95.28%, and 94.94% on per-segment level, respectively (P = 0.993). A tendency toward higher diagnostic performance was observed with SAFIRE strength factor 3 on per-segment analysis, albeit without reaching statistical significance. The effective radiation dose equivalent was 5.7 ± 1.6 mSv. CONCLUSION Sinogram-affirmed iterative reconstruction provides significant improvements in image noise, SNR, and CNR compared with FBP, which are progressive with increasing SAFIRE strength factors. Sinogram-affirmed iterative reconstruction strength factor 3 or 5 is recommended for use with CCTA.

Mobile payment (m-payment) enables consumers to perform their payment tasks via a mobile technology platform. In this study, we summarized, evaluated, and expanded upon the literature about m-payment usage intention by synthetically integrating the advantages of three information systems theories into an integrated model, which details the complementary relationship between the objective measures, subjective perception of m-payment services, and m-payment technology&ndash, task fit characteristics. Based on a sample of 908 individuals in two different Kakaopay user groups (467 Chinese Kakaopay users in Korea and 441 local Korean Kakaopay users) and the three-model integrated optimization, we integrated the unified theory of acceptance and use of technology model (UTAUT), the information systems success model (D&amp, M ISS), and the task-technology fit model (TTF), considering moderating variables (Chinese and Korea experienced consumers) and multi-group analysis. We chose the factors influencing Chinese and Korean consumers' usage intention as the research objects, and ultimately achieved our purpose of more accurately predicting consumer behavior patterns to expand the scale of potential Chinese consumers. The empirical results theoretically contribute to academic and practical solutions for the Korean m-payment product and help technology suppliers to stimulate the sustainable growth of Korean mobile payment consumer groups in Korea.

Objectives This study sought to determine whether a 50%-reduced radiation dose protocol using iterative reconstruction (IR) preserves image quality and diagnostic accuracy at coronary computed tomography angiography (CTA) as compared with a routine dose protocol using traditional filtered back projection (FBP). Background IR techniques show promise to decrease radiation requirements at coronary CTA. No study has performed a direct head-to-head, intraindividual comparison of IR algorithms with FBP vis-a-vis diagnostic accuracy and radiation dose at coronary CTA. Methods Sixty consecutive subjects (45 men, 53.3 ± 9.4 years of age) prospectively underwent coronary catheter angiography (CCA) and 2 coronary CTA scans. One coronary CTA acquisition used routine radiation dose settings and was reconstructed with FBP. For another scan, the tube current–time product was reduced by 50%, and data were reconstructed with IR. Studies were blindly and randomly interpreted. Image quality, radiation dose, and diagnostic accuracy were compared using CCA as the reference standard. Results Sensitivity and specificity for diagnosing ≥50% coronary artery stenosis on a per-segment level were 88.5% and 92.1% with FBP and 84.2% and 93.4% with IR, respectively. On a per-patient level, sensitivity and specificity were 100% and 93.1% with FBP and 96.8% and 89.7% with IR, respectively (all p > 0.05). With FBP versus IR, the area under the receiver-operating characteristic curve was 0.903 (95% confidence interval [CI]: 0.881 to 0.922) and 0.888 (95% CI: 0.864 to 0.909) on a per-segment level, and 0.966 (95% CI: 0.883 to 0.996) and 0.932 (95% CI: 0.836 to 0.981) on a per-patient level, respectively (p = 0.290 and 0.330). Compared with FBP, the iterative series showed no significant (p > 0.05) differences in image quality analyses. Median dose–length product was 52% lower for the IR protocol compared with the FBP protocol (109.00 [interquartile range: 82.00 to 172.50] mGy·cm vs. 52.00 [interquartile range: 39.00 to 84.00] mGy·cm, p Conclusions Compared with a routine radiation dose FBP protocol, 50% reduced dose acquisition using IR preserves image quality and diagnostic accuracy at coronary CTA.

Aim To investigate image quality and potential for radiation dose reduction using sinogram-affirmed iterative reconstruction (SAFIRE) at computed tomography (CT) coronary angiography (CTCA) compared with filtered back-projection (FBP) reconstruction. Materials and methods A water phantom and 49 consecutive patients were scanned using a retrospectively electrocardiography (ECG)-gated CTCA protocol on a dual-source CT system. Image reconstructions were performed with both conventional FBP and SAFIRE. The SAFIRE series were reconstructed image data from only one tube, simulating a 50% radiation dose reduction. Two blinded observers independently assessed the image quality of each coronary segment using a four-point scale and measured image noise (the standard deviation of Hounsfield values, SD), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Radiation dose estimates were calculated. Results In the water phantom, image noise decreased at the same ratio as the tube current increased for both reconstruction algorithms. Despite an estimated radiation dose reduction from 7.9 ± 2.8 to 4 ± 1.4 mSv, there was no significant difference in the SD and SNR within the aortic root and left ventricular chamber between the two reconstruction methods. There was also no significant difference in the image quality between the FBP and SAFIRE series. Conclusion Compared with traditional FBP, there is potential for substantial radiation dose reduction at CTCA with use of SAFIRE, while maintaining similar diagnostic image quality.

To individually optimize contrast medium protocol for high-pitch prospective ECG-triggering coronary CT angiography using body weight. Ninety patients undergoing high-pitch coronary CT angiography were randomly assigned to 3 contrast medium injection protocols with bolus tracking technique: Group A, 0.7 ml CM per kg patient weight (ml/kg); Group B, 0.6 ml/kg; Group C, 0.5 ml/kg. Each group had 30 patients. The CT values of superior vena cava (SVC), pulmonary artery (PA), ascending aorta (AA), left atrium (LA), left ventricle (LV), left main artery (LM) and proximal segment of right coronary artery (RCA) were measured. The image quality of coronary artery was evaluated on per-segment basis using a 4-point scale (1-excellent, 4-non-diagnosis). The CT value was not significantly different on AA (p = 0.735), LM (p = 0.764), and proximal segment of RCA (p = 0.991). The CT value was significantly different on SVC, PA, LA and LV (all p < 0.05). The mean image quality score was 1.6 ± 0.1, 1.6 ± 0.1 and 1.6 ± 0.1 (p = 0.217). The volume of CM was 47 ± 8, 44 ± 8 and 36 ± 6 ml for 3 groups (p < 0.001). The effective radiation dose was 0.88 ± 0.04, 0.87 ± 0.06, and 0.85 ± 0.07 mSv for 3 groups. Contrast medium could be reduced to 0.5 ml/kg for high-pitch coronary CT angiography without compromising diagnostic image quality, which associated ~50 % reduction of total contrast volume compared with standard contrast protocol with test bolus technique.

In this paper, we study the service importance evaluation problem in the smart grid. Considering the complexity of power communication services is gradually deepening with the accelerated intelligent process of modern power grid, we propose an evaluation method combining multiple factors fusion aimed at improving the accuracy of evaluation results and reflecting the real status of services in the smart grid. In the proposed method, we first establish a comprehensive evaluation model that contains the complete evaluation indicator system for two factors and introduce the concept of contribution coefficient. Then we propose the evaluation method for single factor and quantify the evaluation indicators of service importance based on communication factor and power grid factor respectively. According to the multi-factorial characteristics of services, the fusion process of two-factor service importance is carried out by contribution coefficient finally. Case analysis shows proposed approach can overcome the disadvantage that traditional methods only apply to single factor or fail to effectively combine expert's subjective judgment and the objectivity of evaluation methods, meanwhile guarantee the rationality of evaluation results.

Power grid dispatching has involved large amount of multi-source heterogeneous data with high complexity, therefore transforming power data into knowledge by data mining is the inevitable trend of intelligent dispatching development. Applying big data technology to power grid dispatching, the analysis model of multi-source heterogeneous data based on big data is built and a frequent itemset mining (FIM) algorithm for processing big data is proposed in this paper. Combining MapReduce programming and combinatorics, the algorithm will scan transaction database once to complete the target frequent itemset mining, and support is changing with no need to mining. The algorithm can overcome the problem of multiple scanning transaction database and low mining efficiency. In this paper, compared with other frequent itemset mining, the algorithm take advantage of Hadoop to deal with fault information transaction database. Experimental results show the proposed algorithm performs well in expansibility and has a little time cost with large transaction database. The method in this paper will provide useful knowledge for realizing intelligent analysis and decision making with comprehensive optimal objectives of accuracy, security, economic, which single data source can't achieve.

Electric power communication network is an important part of power system, which plays a vital role in the operation of power network. This paper established an index system of electric power communication network and proposed a diagnostic method of electric power communication network system based on extension rating. This evaluation method can not only evaluate the impact factors of the electric power communication network, but also can diagnose and rate the whole electric power communication network.

With a number of students, the purpose of collaborative learning is to assign these students to the right teams so that the promotion of skills of each team member can be facilitated. Although some team formation solutions have been proposed, the problem of extracting more effective features to describe the skill proficiency of students for better collaborative learning is still open. To that end, we provide a focused study on exploiting cognitive diagnosis to model students' skill proficiency for team formation. Specifically, we design a two-stage framework. First, we propose a cognitive diagnosis model SDINA, which can automatically quantify students' skill proficiency in continuous values. Then, given two different objectives, we propose corresponding algorithms to form collaborative learning teams based on the cognitive modeling results of SDINA. Finally, extensive experiments demonstrate that SDINA could model the students' skill proficiency more precisely and the proposed algorithms can help generate collaborative learning teams more effectively.

Purpose To investigate the image quality and radiation dose of low radiation dose CT coronary angiography (CTCA) using sinogram affirmed iterative reconstruction (SAFIRE) compared with standard dose CTCA using filtered back-projection (FBP) in obese patients. Materials and methods Seventy-eight consecutive obese patients were randomized into two groups and scanned using a prospectively ECG-triggered step-and-shot (SAS) CTCA protocol on a dual-source CT scanner. Thirty-nine patients (protocol A) were examined using a routine radiation dose protocol at 120 kV and images were reconstructed with FBP (protocol A). Thirty-nine patients (protocol B) were examined using a low dose protocol at 100 kV and images were reconstructed with SAFIRE. Two blinded observers independently assessed the image quality of each coronary segment using a 4-point scale (1 = non-diagnostic, 4 = excellent) and measured the objective parameters image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Radiation dose was calculated. Results The coronary artery image quality scores, image noise, SNR and CNR were not significantly different between protocols A and B (all p > 0.05), with image quality scores of 3.51 ± 0.70 versus 3.55 ± 0.47, respectively. The effective radiation dose was significantly lower in protocol B (4.41 ± 0.83 mSv) than that in protocol A (8.83 ± 1.74 mSv, p Conclusion Compared with standard dose CTCA using FBP, low dose CTCA using SAFIRE can maintain diagnostic image quality with 50% reduction of radiation dose.

Aim To investigate the accuracy of high-pitch prospectively electrocardiogram (ECG)-triggering low-dose, dual-source computed tomography (CT) coronary angiography for assessing coronary artery stenosis compared with conventional coronary angiography. Materials and methods One hundred and three patients undergoing high-pitch CT coronary angiography (CTCA) and conventional coronary angiography (CCA) within 30 days were enrolled. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of high-pitch CTCA for detecting >50 and >70% stenosis were evaluated using CCA as the reference standard on a per-segment, per-vessel, and per-patient basis. Two experienced radiologists independently rated high-pitch CTCA images for quality using a four-point scale (1 = excellent, 4 = non-diagnostic) on a per-segment basis. The effective dose was calculated by multiplying the conversion coefficient of 0.028 by the dose–length product. Results The mean heart rate of patients was 57 ± 6 beats/min. For detecting >50% stenosis, the sensitivity, specificity, PPV, and NPV of high-pitch CTCA were 89, 97, 87, and 97% on a per-segment basis; 91, 92, 92, and 91% on a per-vessel basis; and 99, 85, 96, and 94% on a per-patient basis. For detecting >70% stenosis, the sensitivity, specificity, PPV, and NPV of high-pitch CTCA were 96, 98, 90, and 99% on a per-segment basis. Coronary segments were rated as diagnostic in 98.6% (1355/1375) of cases (score 1, 72.5%; score 2, 23.1%; score 3, 3%; score 4, 1.4%). The effective dose of high-pitch CTCA was 1.51 ± 0.31 mSv. Conclusion High-pitch prospectively ECG-triggering dual-source CTCA provides good image quality and high diagnostic accuracy with a 1.51 mSv radiation dose.

The purpose of this study is to investigate whether an iterative reconstruction in image space (IRIS) algorithm improves the image quality of dual-energy CT abdominal examinations performed during the hepatic arterial phase.Seventy patients with suspected liver masses underwent contrast-enhanced multiphase abdominal examination and were enrolled in the study. A dual-energy CT protocol was performed in the hepatic arterial phase (parameters: tube A, 140 kV and 90 mA; tube B, 80 kV and 382 mA; automatic tube current modulation on; and collimation, 14 × 1.2 mm). The reconstructions were performed with filtered back projection (FBP) and IRIS algorithms at a slice thickness of 3 mm and kernels of B30 and I30. The image noise was measured on the liver, aorta, and subcutaneous fat on the FBP and IRIS fusion images (m = 0.3) at the same position. The image noise and diagnostic acceptability of all images were scored by two radiologists.The image noise using the IRIS algorithm was lower than that using the standard FBP algorithm on the liver, aorta, and subcutaneous fat, respectively. The signal-to-noise ratio and contrast-to-noise ratio of images reconstructed with the IRIS algorithm also were significantly higher than for those reconstructed with the FBP algorithm. The diagnostic acceptability score using the IRIS algorithm was higher than that using the FBP algorithm at the same dose level (1.20 ± 0.40 vs 1.37 ± 0.57; p0.05).Compared with standard FBP reconstruction, an IRIS algorithm enables significant reduction of image noise and improvement of image quality and has the potential to decrease radiation exposure during contrast-enhanced dual-energy CT abdominal examination.

With the large-scale deployment of optical network equipments, the problems of separated domains management and the multi-domain-based survivability have become the primary challenge in new generation intelligent optical networks. Aimed at resisting multi-link failures in multi-domain optical networks (MDON), a heuristic multi-link fault-tolerant (MLFT) algorithm for survivability in MDON is proposed in this article, which applied Hamiltonian cycle protection and segment-shared protection to establish a novel survivability strategy for either intra-domain's or inter-domain's multiple links, respectively. Furthermore, a new virtual-link mapping scheme and link-cost formulas are presented to encourage the appropriate routing selection and load balancing, which can also contributed to better resource utilization ratio and blocking ratio. Simulation results show that MLFT realizes the multi-link fault-tolerant survivability at a lower cost with better performances in redundancy ratio, blocking ratio, and computation complexity.

To investigate the image quality and dose performance of 80 kV high-pitch spiral (HPS) coronary CT angiography (CCTA). 106 patients consecutively enrolled into prospectively ECG-triggering HPS CCTA (pitch = 3.4) exam using kV/ref. mAs = 80/400, 100/370, and 120/370 when patient BMI was ≤22.5 (n = 40), between 22.5 and 27.5 (n = 53) and >27.5 kg/m² (n = 13). Image quality was assessed per-segment by two observers independently using a 4-point scale (1—excellent, 4—non-diagnosable). Image noise and signal-to-noise ratio (SNR), contrast-to-noise ratio were measured. Diagnostic image quality was obtained in 503 of 507, 687 of 693, 164 of 167 coronary segments in 80, 100, 120 kV groups without significant difference (P = 0.482). The proportions of segments with score 1–4 were not significantly different among three kV groups (all P > 0.05). Image noise were significantly higher in 80 kV group than 100 and 120 groups (P < 0.001), while SNR was not (P = 0.097). The effective dose of 80 kV group (0.36 ± 0.03 mSv) was significantly lower than that of 100 kV group (0.86 ± 0.08 mSv) and 120 kV group (1.77 ± 0.18 mSv). The mean ± SD of HR in all patients was 54.8 ± 5.1 bpm. 80 kV HPS CCTA is feasible for patient with BMI ≤ 22.5 kg/m² which can save 58% dose than 100 kV group, while maintain diagnosable image quality.

The revenue-sharing contract is one of the most important supply chain coordination contracts; it has been applied in various supply chains. However, studies related to service supply chains with mass customization (MC) are lacking. Considering the equity of benefit distribution between the members of service supply chains, in this paper, we designed two revenue-sharing contracts. The first contract for the maximum equity of a single logistics service integrator (LSI) and single functional logistics service provider (FLSP) in a two-echelon logistics service supply chain was designed by introducing the fair entropy function (“one to one” model). Furthermore, the method is extended to a more complex supply chain, which consists of a single LSI and multiple FLSPs. A new contract was designed not only for considering the equity of an LSI and each FLSP but also for the equity between each FLSP (“one toN” model). The “one to one” model in three-echelon LSSC is also provided. The result exemplifies that, whether in the “one to one” model or “one toN” model, there exists a best interval of customized level when the revenue-sharing coefficient reaches its maximum.

Address dynamic configuration in the IP-based network is often accomplished by the dynamic host configuration protocol (DHCP), however, the mobility of mobile ad hoc network (MANET) nodes always involve unpredictable topology changes. Previous works on IP address in ad hoc network assumes that all the address is configured statically by the centralized administration. However, as with the rapid development of wireless network, there are not enough IP addresses available to identify each individual user. DHCP can not be utilized in a mobile ad hoc network due to the lack of any centralized DHCP server in distributed dynamic environment. There are also two typical enhanced solutions for dynamic host configurations, i.e., MANETConf and Quorum approaches. Consider the information of geographical position that from a GPS, we proposed a simplified configuration protocol to reduce controlling overhead and the associate traffic loss during handover period. Extensive environments are implemented comparing the performance of the three approaches. The results shown that the GPS based configuration is more efficient than the traditional methods.