Convolutional Neural Network (CNN) has made extraordinary progress in image classification tasks. However, it is less effective to use CNN directly to detect image manipulation. To address this problem, we propose an image filtering layer and a multi-scale feature fusion module which can guide the model more accurately and effectively to perform image manipulation detection. Through a series of experiments, it is shown that our model achieves improvements on image manipulation detection compared with the previous researches.

With the high development of computation requirements in Internet of Things, resource-limited edge servers usually require to cooperate to perform the tasks. Most related studies usually assume a static cooperation approach which might not suit the dynamic environment of edge computing. In this paper, we consider a dynamic cooperation approach by guiding edge servers to form coalitions dynamically. It raises two issues: 1) how to guide them to optimally form coalitions and 2) how to cope with the dynamic feature where server statuses dynamically change as the tasks are performed. The coalitional Markov decision process (CMDP) model proposed in our previous work can handle these issues well. However, its basic solution, coalitional Q-learning, cannot handle the large scale problem when the task number is large in edge computing. Our response is to propose a novel algorithm called deep coalitional Q-learning (DCQL) to solve it. To sum up, we first formulate the dynamic cooperation problem of edge servers as a CMDP: each edge server is regarded as an agent and the dynamic process is modeled as a MDP where the agents observe the current state to formulate several coalitions. Each coalition takes an action to impact the environment which correspondingly transfers to the next state to repeat the above process. Then, we propose DCQL which includes a deep neural network and so can well cope with large scale problem. DCQL can guide the edge servers to form coalitions dynamically with the target of optimizing some goal. Furthermore, we run experiments to verify our proposed algorithm's effectiveness in different settings.

Packet processing on commodity hardware is a cost-efficient and flexible alternative to specialized networking hardware. However, virtualizing dedicated networking hardware as a virtual machine (VM) or a container on a commodity server results in performance problems, such as longer latency and lower throughput. This paper focuses on obtaining a low-latency networking system in a VM and a container. We reveal mechanisms that cause millisecond-scale networking delays in a VM through a series of experiments. To eliminate such delays, we design and implement a low-latency networking system, kernel busy poll (KBP), which achieves three goals: (1) microsecond-scale tail delays and higher throughput than conventional solutions are achieved in a VM and a container; (2) application customization is not required, so applications can use the POSIX sockets application program interface; and (3) KBP software does not need to be developed for every Linux kernel security update. KBP can be applied to both a VM configuration and a container configuration. Evaluation results indicate that KBP achieves microsecond-scale tail delays in both a VM and a container. In the VM configuration, KBP reduces maximum round-trip latency by more than 98% and increases the throughput by up to three times compared with existing NAPI and Open vSwitch with the Data Plane Development Kit (OvS-DPDK). In the container configuration, KBP reduces maximum round-trip latency by 21% to 96% and increases the throughput by up to 1.28 times compared with NAPI.

Distributed edge cloud computing is an important computation infrastructure for Internet of Things (IoT) and its task offloading problem has attracted much attention recently. Most existing work on task offloading in distributed edge cloud computing usually assumes that each self-interested user owns one edge server and chooses whether to execute its tasks locally or to offload the tasks to cloud servers. The goal of each edge server is to maximize its own interest like low delay cost, which corresponds to a non-cooperative setting. However, with the strong development of smart IoT communities such as smart hospital and smart factory, all edge and cloud servers can belong to one organization like a technology company. This corresponds to a cooperative setting where the goal of the organization is to maximize the team interest in the overall edge cloud computing system. In this paper, we consider a new problem called cooperative task offloading where all edge servers try to cooperate to make the entire edge cloud computing system achieve good performance such as low delay cost and low energy cost. However, this problem is hard to solve due to two issues: 1) each edge server status dynamically changes and task arrival is uncertain; 2) each edge server can observe only its own status, which makes it hard to optimize team interest as global information is unavailable. For solving these issues, we formulate the problem as a decentralized partially observable Markov decision process (Dec-POMDP) which can well handle the dynamic features under partial observations. Then, we apply a multi-agent reinforcement learning algorithm called value decomposition network (VDN) and propose a VDN-based task offloading algorithm (VDN-TO) to solve the problem. Specifically, the motivation is that we use a team value function to evaluate the team interest, which is then divided into individual value functions for each edge server. Then, each edge server updates its individual value function in the direction that can maximize the team interest. Finally, we choose a part of a real dataset to evaluate our algorithm and the results show the effectiveness of our algorithm in a comparison with some other existing methods.

We show that for any convex body Q in the plane, the average distance from the Fermat-Weber center of Q to the points in Q is at least Δ(Q)/6, where Δ(Q) denotes the diameter of Q. Our proof is simple and straightforward, since it needs only elementary calculations. This simplifies a previously known proof that is based on Steiner symmetrizations.

This paper proposes a low-complexity variational Bayesian inference (VBI)-based method for massive multiple-input multiple-output (MIMO) downlink channel estimation. The temporal correlation at the mobile user side is jointly exploited to enhance the channel estimation performance. The key to the success of the proposed method is the column-independent factorization imposed in the VBI framework. Since we separate the Bayesian inference for each column vector of signal-of-interest, the computational complexity of the proposed method is significantly reduced. Moreover, the temporal correlation is automatically uncoupled to facilitate the updating rule derivation for the temporal correlation itself. Simulation results illustrate the substantial performance improvement achieved by the proposed method.

In this paper, event-triggered control over a sensor network is studied as one of the control methods of cyber-physical systems. Event-triggered control is a method that communications occur only when the measured value is widely changed. In the proposed method, by solving an LMI (Linear Matrix Inequality) feasibility problem, an event-triggered output feedback controller such that the closed-loop system is asymptotically stable is derived. First, the problem formulation is given. Next, the control problem is reduced to an LMI feasibility problem. Finally, the proposed method is demonstrated by a numerical example.

As the mainstream approach in the field of machine translation, neural machine translation (NMT) has achieved great improvements on many rich-source languages, but performance of NMT for low-resource languages ae not very good yet. This paper uses data enhancement technology to construct Mongolian-Chinese pseudo parallel corpus, so as to improve the translation ability of Mongolian-Chinese translation model. Experiments show that the above methods can improve the translation ability of the translation model. Finally, a translation model trained with large-scale pseudo parallel corpus and integrated with soft context data enhancement technology is obtained, and its BLEU value is 39.3.

In our previous paper, we have proposed a new numerical technique for transient scattering problem of periodically arrayed dispersion media by using a combination of the fast inversion Laplace transform (FILT) method and Fourier series expansion method (FSEM), and analyzed the pulse response for several widths of the dispersion media or rectangular cavities. From the numerical results, we examined the influence of a periodically arrayed dispersion media with a rectangular cavity on the pulse response. In this paper, we analyzed the transient scattering problem for the case of dispersion media with slanted air regions by utilizing a combination of the FILT, FSEM, and multilayer division method (MDM), and investigated an influence for the slanted angle of an air region. In addition, we verified the computational accuracy for term of the MDM and truncation mode number of the electromagnetic fields.

Visual Question Answering (VQA) is multi-task research that requires simultaneous processing of vision and text. Recent research on the VQA models employ a co-attention mechanism to build a model between the context and the image. However, the features of questions and the modeling of the image region force irrelevant information to be calculated in the model, thus affecting the performance. This paper proposes a novel dual self-guided attention with sparse question networks (DSSQN) to address this issue. The aim is to avoid having irrelevant information calculated into the model when modeling the internal dependencies on both the question and image. Simultaneously, it overcomes the coarse interaction between sparse question features and image features. First, the sparse question self-attention (SQSA) unit in the encoder calculates the feature with the highest weight. From the self-attention learning of question words, the question features of larger weights are reserved. Secondly, sparse question features are utilized to guide the focus on image features to obtain fine-grained image features, and to also prevent irrelevant information from being calculated into the model. A dual self-guided attention (DSGA) unit is designed to improve modal interaction between questions and images. Third, the sparse question self-attention of the parameter δ is optimized to select these question-related object regions. Our experiments with VQA 2.0 benchmark datasets demonstrate that DSSQN outperforms the state-of-the-art methods. For example, the accuracy of our proposed model on the test-dev and test-std is 71.03% and 71.37%, respectively. In addition, we show through visualization results that our model can pay more attention to important features than other advanced models. At the same time, we also hope that it can promote the development of VQA in the field of artificial intelligence (AI).

Five Cells and Tilepaint are Nikoli's pencil puzzles. We study the computational complexity of Five Cells and Tilepaint puzzles. It is shown that deciding whether a given instance of each puzzle has a solution is NP-complete.

A rep-cube is a polyomino that is a net of a cube, and it can be divided into some polyominoes such that each of them can be folded into a cube. This notion was invented in 2017, which is inspired by the notions of polyomino and rep-tile, which were introduced by Solomon W. Golomb. A rep-cube is called regular if it can be divided into the nets of the same area. A regular rep-cube is of order k if it is divided into k nets. Moreover, it is called uniform if it can be divided into the congruent nets. In this paper, we focus on these special rep-cubes and solve several open problems.

The challenges posed by big data in the 21st Century are complex: Under the previous common sense, we considered that polynomial-time algorithms are practical; however, when we handle big data, even a linear-time algorithm may be too slow. Thus, sublinear- and constant-time algorithms are required. The academic research project, “Foundations of Innovative Algorithms for Big Data,” which was started in 2014 and will finish in September 2021, aimed at developing various techniques and frameworks to design algorithms for big data. In this project, we introduce a “Sublinear Computation Paradigm.” Toward this purpose, we first provide a survey of constant-time algorithms, which are the most investigated framework of this area, and then present our recent results on sublinear progressive algorithms. A sublinear progressive algorithm first outputs a temporary approximate solution in constant time, and then suggests better solutions gradually in sublinear-time, finally finds the exact solution. We present Sublinear Progressive Algorithm Theory (SPA Theory, for short), which enables to make a sublinear progressive algorithm for any property if it has a constant-time algorithm and an exact algorithm (an exponential-time one is allowed) without losing any computation time in the big-O sense.

Multiparty computation (MPC) is the technology that computes an arbitrary function represented as a circuit without revealing input values. Typical MPC uses secret sharing (SS) schemes, garbled circuit (GC), and homomorphic encryption (HE). These cryptographic technologies have a trade-off relationship for the computation cost, communication cost, and type of computable circuit. Hence, the optimal choice depends on the computing resources, communication environment, and function related to applications. The private decision tree evaluation (PDTE) is one of the important applications of secure computation. There exist several PDTE protocols with constant communication rounds using GC, HE, and SS-MPC over the field. However, to the best of our knowledge, PDTE protocols with constant communication rounds using MPC based on SS over the ring (requiring only lower computation costs and communication complexity) are non-trivial and still missing. In this paper, we propose a PDTE protocol based on a three-party computation (3PC) protocol over the ring with one corruption. We also propose another three-party PDTE protocol over the field with one corruption that is more efficient than the naive construction.

Low power consumption is important in edge artificial intelligence (AI) chips, where power supply is limited. Therefore, we propose reconfigurable neural network accelerator (ReNA), an AI chip that can process both a convolutional layer and fully connected layer with the same structure by reconfiguring the circuit. In addition, we developed tools for pre-evaluation of the performance when a deep neural network (DNN) model is implemented on ReNA. With this approach, we established the flow for the implementation of DNN models on ReNA and evaluated its power consumption. ReNA achieved 1.51TOPS/W in the convolutional layer and 1.38TOPS/W overall in a VGG16 model with a 70% pruning rate.

We study a new reconfiguration problem inspired by classic mechanical puzzles: a colored token is placed on each vertex of a given graph; we are also given a set of distinguished cycles on the graph. We are tasked with rearranging the tokens from a given initial configuration to a final one by using cyclic shift operations along the distinguished cycles. We call this a cyclic shift puzzle. We first investigate a large class of graphs, which generalizes several classic cyclic shift puzzles, and we give a characterization of which final configurations can be reached from a given initial configuration. Our proofs are constructive, and yield efficient methods for shifting tokens to reach the desired configurations. On the other hand, when the goal is to find a shortest sequence of shifting operations, we show that the problem is NP-hard, even for puzzles with tokens of only two different colors.

In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.

We study the computational complexity of the puzzle game Critter Crunch, where the player has to rearrange Critters on a board in order to eliminate them all. Smaller Critters can be fed to larger Critters, and Critters will explode if they eat too much. Critters come in several different types, sizes, and colors. We prove the NP-hardness of levels that contain Blocker Critters, as well as levels where the player must clear the board in a given number of moves (i.e., “puzzle mode”). We also characterize the complexity of the game, as a function of the number of columns on the board, in two settings: (i) the setting where Critters may have several different colors, but only two possible sizes, and (ii) the setting where Critters come in all three sizes, but with no color variations. In both settings, the game is NP-hard for levels with exactly two columns, and solvable in linear time for levels with only one column or more than two columns.

The efficient implementation strategy for speeding up high-quality clustering algorithms is developed on the basis of general purpose graphic processing units (GPGPUs) in this work. Among various clustering algorithms, a sophisticated Gaussian mixture model (GMM) by estimating parameters through variational Bayesian (VB) mechanism is conducted due to its superior performances. Since the VB-GMM methodology is computation-hungry, the GPGPU is employed to carry out massive matrix-computations. To efficiently migrate the conventional CPU-oriented schemes of VB-GMM onto GPGPU platforms, an entire migration-flow with thirteen stages is presented in detail. The CPU-GPGPU co-operation scheme, execution re-order, and memory access optimization are proposed for optimizing the GPGPU utilization and maximizing the clustering speed. Five types of real-world applications along with relevant data-sets are introduced for the cross-validation. From the experimental results, the feasibility of implementing VB-GMM algorithm by GPGPU is verified with practical benefits. The proposed GPGPU migration achieves 192x speedup in maximum. Furthermore, it succeeded in identifying the proper number of clusters, which is hardly conducted by the EM-algotihm.

In secure multiparty computation (MPC), floating-point numbers should be handled in many potential applications, but these are basically expensive. In particular, for MPC based on secret sharing (SS), the floating-point addition takes many communication rounds though the addition is the most fundamental operation. In this paper, we propose an SS-based two-party protocol for floating-point addition with 13 rounds (for single/double precision numbers), which is much fewer than the milestone work of Aliasgari et al. in NDSS 2013 (34 and 36 rounds, respectively) and also fewer than the state of the art in the literature. Moreover, in contrast to the existing SS-based protocols which are all based on “roundTowardZero” rounding mode in the IEEE 754 standard, we propose another protocol with 15 rounds which is the first result realizing more accurate “roundTiesToEven” rounding mode. We also discuss possible applications of the latter protocol to secure Validated Numerics (a.k.a. Rigorous Computation) by implementing a simple example.