This study explores the global Mittag-Leffler stability and finite time stability of incommensurate fractional-order inertial delay BAM neural networks. Initially, the system, characterized by high-order incommensurate fractional-order dynamics, is transformed into a low-order system through an appropriate variable substitution. Subsequently, sufficient conditions for the achievement of global Mittag-Leffler stability and finite time stability are derived. These conditions are based on the properties of the Riemann-Liouville fractional derivative and integral, and the relation of fractional integral inequalities to the Bellman-Gronwall inequality. The efficacy and accuracy of the proposed theoretical results are substantiated through two numerical simulations.

Deep neural network (DNN)-based real-time video analytics service, as a core module for numerous crucial applications such as augmented reality (AR), has garnered increasing research attention, where mobile edge computing (MEC) is often leveraged to mitigate its real-time processing burden on resource-constrained user devices. For Quality of Experience (QoE) optimization, latest works employ reinforcement learning (RL)-based methods to adaptively adjust configurations (e.g., resolution and frame rate), yet still presenting significant challenges. Firstly, we observe a substantial diversity in QoE patterns among users. Given that existing methods integrate a fixed QoE pattern in parameter training, it is intuitive to customize a policy network for each user. However, this necessitates significant training investment, failing to support on-the-fly deployment for new users. Secondly, given the dual dynamics from both the network and video content in edge video analytics system, existing methods often fall into the dilemma of fitting newly emerged and diverse system states with offline-trained fixed parameters. While it is promising to employ online learning algorithms, most of them struggle to catch up with the high dynamics. We hence proposeMystique. In real-time edge video analytics domain, it is the first meta-RL-based user-level configuration adaptation framework. Mystique establishes an initial model in offline meta training with model-agnostic meta-learning (MAML), enabling swift online adaptation to new users and system states through limited gradient updates from initial parameters. Comprehensive experiments illustrate that Mystique can improve QoE by 42% on average compared to prior works.

With the advent of the Internet of Things (IoT), the volume of real-time data has surged, necessitating efficient data analytics frameworks like Spark to handle the deluge. Traditional caching strategies, which rely on either historical data or anticipated access patterns, often overlook the complexities of parallel computations in IoT environments, resulting in suboptimal performance. Our paper introduces a dynamic caching approach tailored for multi-job IoT data analytics that leverages both historical and future access patterns, accounting for parallel processing. By proposing the concepts of critical path, hot data and representative RDD, we simplify the caching problem and convert it to a knapsack problem. Our proposed algorithm, DCSR, employs dynamic programming to optimize caching decisions. Experimental results demonstrate that DCSR significantly outperforms existing methods, reducing job completion time by at least 25.94%.

Deploying microservice instances in geo-distributed edge clouds which are located at the network edge and in proximity to end-users can provide on-site processing, thereby improving the quality of service (QoS). To accommodate the time-varying request arrival rate of each edge cloud, the deployment scheme of microservice instances is dynamically adapted, which is called microservice autoscaling. However, existing studies on microservice autoscaling at the edge either only optimize the QoS without considering the cost of deploying microservice instances or simply focus on the cost per individual timeslot, and thus always severely violate the long-term budget constraint. To solve this problem, in this article, we propose GeoScale, a novel method that aims to optimize the average request response time under the long-term cost budget constraint. GeoScale first utilizes the Lyapunov optimization framework to decompose the long-term optimization problem into a series of per-timeslot sub-problems and then applies a signomial geometric programming (SGP)-based algorithm to obtain a near-optimal solution to each NP-hard sub-problem. Through extensive trace-driven experiments, we validate the superiority of GeoScale. The experimental results show that compared with existing strategies and designed baselines, GeoScale can improve QoS by reducing the average request response time up to 87.8% while significantly mitigating the violation of the long-term cost budget constraint.

In this paper, we propose a highly efficient computing method for game character control with phase-functioned neural networks (PFNN). The primary challenge to accelerate PFNN on mobile platforms is that PFNN dynamically produces weight matrices with an argument, phase, which is individual to each game character. Therefore existing libraries that generally assume frozen weight matrices are inefficient to accelerate PFNN. The situation becomes even worse when multiple characters are present. To address the challenges, we reformulate the equations and leverage the deep learning compiler stack TVM to build a cross-platform, high-performance implementation. Evaluations reveal that our solutions deliver close-to-peak performance on various platforms, from high-performance servers to energy-efficient mobile platforms. This work is publicly available at https://github.com/turbo0628/pfnn_tvm.

The bandwidth of a kernel function is a crucial parameter in the mean shift algorithm. This paper proposes a novel adaptive bandwidth strategy which contains three main contributions. (1) The differences among different adaptive bandwidth are analyzed. (2) A new mean shift vector based on bidirectional adaptive bandwidth is defined, which combines the advantages of different adaptive bandwidth strategies. (3) A bidirectional adaptive bandwidth mean shift (BAMS) strategy is proposed to improve the ability to escape from the local maximum density. Compared with contemporary adaptive bandwidth mean shift strategies, experiments demonstrate the effectiveness of the proposed strategy.

An optimized occlusion detection method for true orthophoto make is proposed in this paper, aimed at solving the occlusion and shadow problems caused by rectification using digital surface model (DSM). This method draws lessons from sweep way of angle-based detection method and idea of radial tracing detection method. It adds three judge rules to the occlusion detection process to increase its executing efficiency. Using neighbor image's best corresponding pixels can compensate the occlusion area.