Managing diverse data formats and improving query processing efficiency at cloud service centers is crucial in the era of interconnected heterogeneous devices. Lakehouse effectively manages heterogeneous data but faces challenges in maintaining SQL query performance and data independence in large-scale analyses. Precomputation, which stores intermediate results in advance, reduces query latency by a space-for-time trade-off. This paper addresses the challenges of matching and rewriting results in lakehouse environments. By combining pre-computation with the low-cost and dynamically scalable storage characteristics of cloud storage, we introduce an optimized lakehouse architecture with an in-memory index and dynamic task scheduling to enhance OLAP performance while balancing data center resources. Experiments demonstrate improvements in query performance ranging from 6.1 % to 64.9% over native lakehouse architectures and reductions in resource occupation from the original 75.6% to 17.3% with preloading and 25.0% with dynamic scheduling.

The expansion of unmanned intelligent vehicles in daily living spaces increases the demand for their safe operation in human-machine coexistence environments. Effective space management is crucial to ensuring the safety and reliability of intelligent vehicles by preventing conflicts and controlling fear toward humans to a low level. Traditional spatial models, such as trajectory-based operation (TBO) and free-flight operation (FFO), are more or less deficient in maintaining low space occupancy and reducing the probability of conflicts. Hence, we present a MAPPO algorithm based on real-time dynamic motion data and a fear index model that quantifies human apprehension towards vehicles, aiming to allocate exclusive operational spaces for each vehicle. An octree-based spatial partitioning method is used to further mitigate conflicts among these space. Simulation experiments indicate that the proposed solution ensures collision-free allocation and reduced spatial occupancy that is 6.24% to 40.84% of other schemes , which achieves equilibrium between TBO and FFO.

This paper presents a novel framework called Failure-Alarm Correlation Tree based Failure Localization (FACT-FL), designed to localize failed optical layer device boards in an Optical Transport Network (OTN). Specifically, FACT-FL aims to construct a set of FACTs by correlating the failed boards and alarms, where each FACT takes one failed board and its correlated alarms as the root and leaves, respectively. Furthermore, a FACT consists of a suite of kth order Failure-Alarm Correlation Chains (k-FACCs) with different order values of k. Each k-FACC indicates the chain-like correlation established by k alarms due to one common failed board. To identify all previously undetected k-FACCs, a set of binary classifiers is trained that characterizes each k-FACC from various dimensions, including time, network topology, traffic distribution, and board/alarm attributes. Eventually, an integer linear programming (ILP) problem is formulated to extract the most likely FACT(s) from those k-FACCs. Extensive case studies demonstrate the superior results of FACT-FL in terms of metrics evaluating the identified failed boards and root alarms. We also analyze its performance under different maximum order values of k and environmental changes, including failure scenarios, network topologies, traffic distributions, and noise alarms.

How to optimally dispatch orders to vehicles and how to trade off between immediate and future returns are fundamental questions for a typical ride-hailing platform. We model ride-hailing as a large-scale parallel ranking problem and study the joint decision-making task of order dispatching and fleet management in online ride-hailing platforms. This task brings unique challenges in the following four aspects. First, to facilitate a huge number of vehicles to act and learn efficiently and robustly, we treat each region cell as an agent and build a multi-agent reinforcement learning framework. Second, to coordinate the agents from different regions to achieve long-term benefits, we leverage the geographical hierarchy of the region grids to perform hierarchical reinforcement learning. Third, to deal with the heterogeneous and variant action space for joint order dispatching and fleet management, we design the action as the ranking weight vector to rank and select the specific order or the fleet management destination in a unified formulation. Fourth, to achieve the multi-scale ride-hailing platform, we conduct the decision-making process in a hierarchical way where a multi-head attention mechanism is utilized to incorporate the impacts of neighbor agents and capture the key agent in each scale. The whole novel framework is named as CoRide. Extensive experiments based on multiple cities real-world data as well as analytic synthetic data demonstrate that CoRide provides superior performance in terms of platform revenue and user experience in the task of city-wide hybrid order dispatching and fleet management over strong baselines.

Improving the efficiency of dispatching orders to vehicles is a research hotspot in online ride-hailing systems. Most of the existing solutions for order-dispatching are centralized controlling, which require to consider all possible matches between available orders and vehicles. For large-scale ride-sharing platforms, there are thousands of vehicles and orders to be matched at every second which is of very high computational cost. In this paper, we propose a decentralized execution order-dispatching method based on multi-agent reinforcement learning to address the large-scale order-dispatching problem. Different from the previous cooperative multi-agent reinforcement learning algorithms, in our method, all agents work independently with the guidance from an evaluation of the joint policy since there is no need for communication or explicit cooperation between agents. Furthermore, we use KL-divergence optimization at each time step to speed up the learning process and to balance the vehicles (supply) and orders (demand). Experiments on both the explanatory environment and real-world simulator show that the proposed method outperforms the baselines in terms of accumulated driver income (ADI) and Order Response Rate (ORR) in various traffic environments. Besides, with the support of the online platform of Didi Chuxing, we designed a hybrid system to deploy our model.

As the technology of cloud computing becomes mature, the service idea of IT resources has been promoted rapidly. The various available cloud services have different quality of service (QoS). Different users have different QoS requirements for services. Finding the best QoS strategy which a user is satisfied with is a multi-criteria NP-hard problem. The completed theory and applied research have proved that the swarm intelligence method can effectively solve most multiobjective optimization problems. Therefore, a Pareto optimal solution for QoS strategy can be found by an evolutionary algorithm based on swarm intelligence. However, so far, only few solutions based on these approaches have been proposed and there exists no comparative study published to date. This motivated us to perform an analysis of state of the art evolutionary algorithm based on swarm intelligence. By a large number of contrast experiments under different circumstances, three QoS evolutionary algorithms based on swarm intelligence are analyzed and compared.

For both the traditional street-hailing taxi industry and the recently emerged on-line ride-hailing, it has been a major challenge to improve the ride-hailing marketplace efficiency due to spatio-temporal imbalance between the supply and demand, among other factors. Despite the numerous approaches to improve marketplace efficiency using pricing and dispatch strategies, they usually optimize pricing or dispatch separately. In this paper, we show that these two processes are in fact intrinsically interrelated. Motivated by this observation, we make an attempt to simultaneously optimize pricing and dispatch strategies. However, such a joint optimization is extremely challenging due to the inherent huge scale and lack of a uniform model of the problem. To handle the high complexity brought by the new problem, we propose InBEDE (Integrating contextual Bandit with tEmporal DiffErence learning), a learning framework where pricing strategies are learned via a contextual bandit algorithm, and the dispatch strategies are optimized with the help of temporal difference learning. The two learning components proceed in a mutual bootstrapping manner, in the sense that the policy evaluations of the two components are inter-dependent. Evaluated with real-world datasets of two Chinese cities from Didi Chuxing, an online ride-hailing platform, we show that the market efficiency of the ride-hailing platform can be significantly improved using InBEDE.

Order dispatching and driver repositioning (also known as fleet management) in the face of spatially and temporally varying supply and demand are central to a ride-sharing platform marketplace. Hand-crafting heuristic solutions that account for the dynamics in these resource allocation problems is difficult, and may be better handled by an end-to-end machine learning method. Previous works have explored machine learning methods to the problem from a high-level perspective, where the learning method is responsible for either repositioning the drivers or dispatching orders, and as a further simplification, the drivers are considered independent agents maximizing their own reward functions. In this paper we present a deep reinforcement learning approach for tackling the full fleet management and dispatching problems. In addition to treating the drivers as individual agents, we consider the problem from a system-centric perspective, where a central fleet management agent is responsible for decision-making for all drivers.

In this demo, we will present a simulation-based human-computer interaction of deep reinforcement learning in action on order dispatching and driver repositioning for ride-sharing. Specifically, we will demonstrate through several specially designed domains how we use deep reinforcement learning to train agents (drivers) to have longer optimization horizon and to cooperate to achieve higher objective values collectively.

A fundamental question in any peer-to-peer ridesharing system is how to, both effectively and efficiently, dispatch user's ride requests to the right driver in real time. Traditional rule-based solutions usually work on a simplified problem setting, which requires a sophisticated hand-crafted weight design for either centralized authority control or decentralized multi-agent scheduling systems. Although recent approaches have used reinforcement learning to provide centralized combinatorial optimization algorithms with informative weight values, their single-agent setting can hardly model the complex interactions between drivers and orders. In this paper, we address the order dispatching problem using multi-agent reinforcement learning (MARL), which follows the distributed nature of the peer-to-peer ridesharing problem and possesses the ability to capture the stochastic demand-supply dynamics in large-scale ridesharing scenarios. Being more reliable than centralized approaches, our proposed MARL solutions could also support fully distributed execution through recent advances in the Internet of Vehicles (IoV) and the Vehicle-to-Network (V2N). Furthermore, we adopt the mean field approximation to simplify the local interactions by taking an average action among neighborhoods. The mean field approximation is capable of globally capturing dynamic demand-supply variations by propagating many local interactions between agents and the environment. Our extensive experiments have shown the significant improvements of MARL order dispatching algorithms over several strong baselines on the accumulated driver income (ADI), and order response rate measures. Besides, the simulated experiments with real data have also justified that our solution can alleviate the supply-demand gap during the rush hours, thus possessing the capability of reducing traffic congestion.

For cognitive radio (CR), cooperation in spectrum sensing (SS) using energy detection can increase the detection of primary user signal. However, it also brings extra cooperative sensing overhead due to mutual exchange of large information among CR users. To reduce cooperative sensing overhead and improve sensing performance, the authors propose a novel clustering scheme consists of three stages: pruning , selecting , and clustering . In pruning stage, the CR users without sensing results will not join the following two stages; in the subsequent selecting stage, the CR user who has the most reliable sensing data is selected as the cluster header. For CR network, channel availability is an essence cause of cluster change. Hence, the authors proposed cluster constructing based on SS results correlation in the clustering stage. The simulation results show that the proposed clustering scheme not only has low overhead but also suit to perform in the low signal noise ratio environment.

Background Geber and Murphy [1] found that a sex and stature bias is evident among adults in which males and taller individuals displayed statistically significantly higher levels of scorbutic lesions. Thus the study provided evidence to support an investigation on the gender difference with a lack of vitamin C (VC) in humans. In an animal study, a sex difference has also been evidenced [2,3]. Previously, we have studied a spontaneous bone fracture (sfx) mouse [4] which lacks the gene for Lgulonolactone oxidase (Gulo), a key enzyme in the ascorbic acid (AA) synthesis pathway. In this study, we investigated the gene expression profiles between female and male mice using the sfx mouse model and BXD RI strains. The objective of this study is to identify sex differentially expressed genes in bone using the sfx model and BXD RI strains.

Background Interleukin 1 (IL-1) is a major contributor to the development of immune-mediated arthritis. BALB/c mice that are homozygous for the deficiency (BALB/c) spontaneously develop joint-specific inflammation that resembles human rheumatoid arthritis [1]. To understand the role of genetic factors involved in the development of spontaneous arthritis (SAD) in mice deficient in IL-1 receptor antagonist protein (IL_1RA), we have identified a genomic region containing a major quantitative trait locus (QTL) for this disease. The QTL is on chromosome 1 and appears to be the strongest genetic region regulating arthritis [2]. To confirm the importance of this QTL in SAD, we next developed congenic mouse strains that contain the strong QTL genomic fragments from BALB/c on a DBA/1 genetic background [3] and conversely a similar genomic fragment from DBA/1 on a BALB/c background. When the DBA/1 fragment was placed on a BALB/c background, arthritis was delayed and less severe. When the BALB/c fragment was placed on a DBA/1 background, arthritis occurred in varying degrees.

Background Recent evidence suggests that leukocyte-associated immunoglobulin-like receptor-1 (LAIR-1) may play an important role in down-regulating immune activities upon collagen binding [1], and its defective expression or dysfunction is clinically associated with some autoimmune diseases [2-5], cancer [6-8] and viral infection [9-12]. The human genome encodes the counterpart to LAIR-1, soluble protein LAIR-2 [13], which also binds collagen and can interfere with LAIR-1/collagen interactions [14]. However, LAIR-2 has no homologue in mouse or rat [13]. To clarify the extrapolative credibility of a murine model to human disease, we compared LAIR-1 genetic pathways in internal organs of the two species.

Background Many quantitative trait loci (QTL) influencing mouse model phenotypes for alcoholism have been mapped genetically. However, the gene(s) comprising the QTL (QTG) are largely unknown. In previous work, Bennett and colleagues created congenic strains carrying the DBA/2IBG (D2) region for alcohol preference (AP) on chromosome 2, on a C57BL/6IBG (B6) background [1]. Subsequently, interval specific congenic recombinant strains (ISCRS), in which the full D2 QTL region was broken into smaller, partially overlapping regions of introgression, were generated and tested. With information from two ISCRS, the QTL has been mapped onto mouse chromosome 2 (Chr2) in a region of 3.4Mb by using C57BL/6J (B6) x DBA/2J (D2) recombinant inbred (RI) strains as well as by using F2 populations. Several candidate genes, Gad1, Atp5g3, Atf2, Sp3 and Sp9, have been evaluated but none of them has been confirmed for a definitive role in the regulation of the QTL of AP on Chr2 [2,3].

Background Mitochondrial ATP synthase, subunit c, isoform 3 (Atp5g3), encodes subunit 9 of a multisubunit enzyme that catalyzes the synthesis of ATP during oxidative phosphorylation. Each ATP synthase complex has multiple copies of subunit 9 in its transmembrane portion (Fo). While much is known about the molecular mechanisms and function of this complex in the mitochondrial membrane, the impact of variants in this complex and its connection to other pathways and human diseases and disorders is unknown.

Background In humans, gender difference has been suggested by previous studies. Sex difference in vitamin C requirements have also been reported from animal models. Mouse spontaneous fracture model (sfx) lacks L-gulonolactone oxidase (LGO), an essential gene for the synthesis of ascorbic acid (Vitamin C). We have been using sfx model for the past eight years and we are the first group to identify the LGO mutation in this mouse model.

Background Human species and guinea pigs have to obtain vitamin C (VC) from food because they are unable to synthesize ascorbic acid due to the absence of the gene that encodes L-gulonolactone oxidase (Gulo). The spontaneous bone fracture (sfx) mouse is a mouse model which is deficient in the synthesis of VC because of the deletion in Gulo gene. Because muscle forces are a strong determinant of bone structure, particularly during the process of growth and development, we examined the gene expression of muscle in sfx mice.

Background Quantitative trait loci (QTLs) for bone mineral density (BMD) are defined as regions of the genome that contain sequence variations that cause differences in either bone deposition or rates of resorption. In this study, we investigate QTLs for BMD of whole bones using femurs and tibiae from the BXD family of recombinant inbred (RI) strains derived by crossing C57BL/6J (B6) and DBA/2J (D2) inbred strains.

Previously, a quantitative trait loci (QTL) for hearing loss on chromosome 16 in a 118 TNE and CAST background has been identified. The overlap of two of interval specific congenic recombinant strains (ISCRS) strains reduced the QTL interval into a 5,378,407 bps genome region. By examining the genomic information of the QTL on chromosome 16, between the two flanking markers, D16mit191 and D16mit86, we identified a total of 84 genetic elements in the 5,378,407 bps genome region. Among these genetic elements, we found seven with potential function in hearing loss preference (Table 1 ). We then examined the SNPs, insertions and deletions, and gene expression levels of those seven genes. Our current data suggest that the Kcne1 and Sod1 genes are potentially the most hearing loss relevant genes. However, further experiments and examination are still needed to confirm their candidacy. Several other candidate genes are also in the process of being identified.

BACKGROUND: Inferring molecular pathway activity is an important step towards reducing the complexity of genomic data, understanding the heterogeneity in clinical outcome, and obtaining molecular correlates of cancer imaging traits. Increasingly, approaches towards pathway activity inference combine molecular profiles (e.g gene or protein expression) with independent and highly curated structural interaction data (e.g protein interaction networks) or more generally with prior knowledge pathway databases. However, it is unclear how best to use the pathway knowledge information in the context of molecular profiles of any given study. RESULTS: We present an algorithm called DART (Denoising Algorithm based on Relevance network Topology) which filters out noise before estimating pathway activity. Using simulated and real multidimensional cancer genomic data and by comparing DART to other algorithms which do not assess the relevance of the prior pathway information, we here demonstrate that substantial improvement in pathway activity predictions can be made if prior pathway information is denoised before predictions are made. We also show that genes encoding hubs in expression correlation networks represent more reliable markers of pathway activity. Using the Netpath resource of signalling pathways in the context of breast cancer gene expression data we further demonstrate that DART leads to more robust inferences about pathway activity correlations. Finally, we show that DART identifies a hypothesized association between oestrogen signalling and mammographic density in ER+ breast cancer. CONCLUSIONS: Evaluating the consistency of prior information of pathway databases in molecular tumour profiles may substantially improve the subsequent inference of pathway activity in clinical tumour specimens. This de-noising strategy should be incorporated in approaches which attempt to infer pathway activity from prior pathway models.

Previously, a quantitative trait loci (QTL) for alcohol preference on chromosome 2 in a C57BL/6IBG (B6) background has been identified. The overlap of two of interval specific congenic recombinant strains (ISCRS) strains reduced the QTL interval into a 3.4 mbp region. By using the keyword alcohol, we identified a total of 39 genetic elements in the region between markers D2Mit56 and D2Mit10. Among these genetic elements, we found seven with potential function in alcohol preference (Table 1 ). We then examined the SNPs, insertions and deletions, and gene expression levels of those seven genes. Our current data suggest that the Atf2 and Titin genes are potentially the most alcohol relevant genes. However, further experiments and examination are still needed to confirm their candidacy. Several other candidate genes are also in the process of being identified.

An approach to identifying ground targets from sequential high-range-resolution (HRR) radar signatures is presented. A hidden Markov model (HMM) is employed to model the sequential information contained in multi-aspect target signatures. Dominant range-amplitude features are extracted via RELAX for dimension reduction. A new distance measure is incorporated into the HMM to allow a direct matching operation in the feature domain without requiring interpolation. The approach is applied to the dataset of ten MSTAR targets and is shown to yield an average identification rate of 90.3% using sequential information from 6 degree angular spans.