Ryohei KANKE Masanobu TAKAHASHI
Amodal Instance Segmentation (AIS) aims to segment the regions of both visible and invisible parts of overlapping objects. The mainstream Mask R-CNN-based methods are unsuitable for thin objects with large overlaps because of their object proposal features with bounding boxes for three reasons. First, capturing the entire shapes of overlapping thin objects is difficult. Second, the bounding boxes of close objects are almost identical. Third, a bounding box contains many objects in most cases. In this paper, we propose a box-free AIS method, Seed-to-Mask, for thin objects with large overlaps. The method specifies a target object using a seed and iteratively extends the segmented region. We have achieved better performance in experiments on artificial data consisting only of thin objects.
The prediction of peak power load is a critical factor directly impacting the stability of power supply, characterized significantly by its time series nature and intricate ties to the seasonal patterns in electricity usage. Despite its crucial importance, the current landscape of power peak load forecasting remains a multifaceted challenge in the field. This study aims to contribute to this domain by proposing a method that leverages a combination of three primary models - the GRU model, self-attention mechanism, and Transformer mechanism - to forecast peak power load. To contextualize this research within the ongoing discourse, it’s essential to consider the evolving methodologies and advancements in power peak load forecasting. By delving into additional references addressing the complexities and current state of the power peak load forecasting problem, this study aims to build upon the existing knowledge base and offer insights into contemporary challenges and strategies adopted within the field. Data preprocessing in this study involves comprehensive cleaning, standardization, and the design of relevant functions to ensure robustness in the predictive modeling process. Additionally, recognizing the necessity to capture temporal changes effectively, this research incorporates features such as “Weekly Moving Average” and “Monthly Moving Average” into the dataset. To evaluate the proposed methodologies comprehensively, this study conducts comparative analyses with established models such as LSTM, Self-attention network, Transformer, ARIMA, and SVR. The outcomes reveal that the models proposed in this study exhibit superior predictive performance compared to these established models, showcasing their effectiveness in accurately forecasting electricity consumption. The significance of this research lies in two primary contributions. Firstly, it introduces an innovative prediction method combining the GRU model, self-attention mechanism, and Transformer mechanism, aligning with the contemporary evolution of predictive modeling techniques in the field. Secondly, it introduces and emphasizes the utility of “Weekly Moving Average” and “Monthly Moving Average” methodologies, crucial in effectively capturing and interpreting seasonal variations within the dataset. By incorporating these features, this study enhances the model’s ability to account for seasonal influencing factors, thereby significantly improving the accuracy of peak power load forecasting. This contribution aligns with the ongoing efforts to refine forecasting methodologies and addresses the pertinent challenges within power peak load forecasting.
Yi Wen JIAO Ze Fu GAO Wen Ge YANG
In future deep space communication missions, VLBI (Very Long Baseline Interferometry) based on antenna array technology remains a critical detection method, which urgently requires the improvement of synthesis performance for antenna array signals. Considering this, focusing on optimizing the traditional antenna grouping method applied in the phase estimation algorithm, this letter proposes a “L/2 to L/2” antenna grouping method based on the maximum correlation signal-to-noise ratio (SNR). Following this idea, a phase difference estimation algorithm named “Couple” is presented. Theoretical analysis and simulation verification illustrate that: when ρ < -10dB, the proposed “Couple” has the highest performance; increasing the number of antennas can significantly improve its synthetic loss performance and robustness. The research of this letter indicates a promising potential in supporting the rising deep space exploration and communication missions.
This paper proposes a scheme for reducing pilot interference in cell-free massive multiple-input multiple-output (MIMO) systems through scalable access point (AP) selection and efficient pilot allocation using the Grey Wolf Optimizer (GWO). Specifically, we introduce a bidirectional large-scale fading-based (B-LSFB) AP selection method that builds high-quality connections benefiting both APs and UEs. Then, we limit the number of UEs that each AP can serve and encourage competition among UEs to improve the scalability of this approach. Additionally, we propose a grey wolf optimization based pilot allocation (GWOPA) scheme to minimize pilot contamination. Specifically, we first define a fitness function to quantify the level of pilot interference between UEs, and then construct dynamic interference relationships between any UE and its serving AP sets using a weighted fitness function to minimize pilot interference. The simulation results shows that the B-LSFB strategy achieves scalability with performance similar to large-scale fading-based (LSFB) AP selection. Furthermore, the grey wolf optimization-based pilot allocation scheme significantly improves per-user net throughput with low complexity compared to four existing schemes.
Yuto ARIMURA Shigeru YAMASHITA
Stochastic Computing (SC) allows additions and multiplications to be realized with lower power than the conventional binary operations if we admit some errors. However, for many complex functions which cannot be realized by only additions and multiplications, we do not know a generic efficient method to calculate a function by using an SC circuit; it is necessary to realize an SC circuit by using a generic method such as polynomial approximation methods for such a function, which may lose the advantage of SC. Thus, there have been many researches to consider efficient SC realization for specific functions; an efficient SC square root circuit with a feedback circuit was proposed by D. Wu et al. recently. This paper generalizes the SC square root circuit with a feedback circuit; we identify a situation when we can implement a function efficiently by an SC circuit with a feedback circuit. As examples of our generalization, we propose SC circuits to calculate the n-th root calculation and division. We also show our analysis on the accuracy of our SC circuits and the hardware costs; our results show the effectiveness of our method compared to the conventional SC designs; our framework may be able to implement a SC circuit that is better than the existing methods in terms of the hardware cost or the calculation error.
Chengyu WU Jiangshan QIN Xiangyang LI Ao ZHAN Zhengqiang WANG
Real-time matting is a challenging research in deep learning. Conventional CNN (Convolutional Neural Networks) approaches are easy to misjudge the foreground and background semantic and have blurry matting edges, which result from CNN’s limited concentration on global context due to receptive field. We propose a real-time matting approach called RMViT (Real-time matting with Vision Transformer) with Transformer structure, attention and content-aware guidance to solve issues above. The semantic accuracy improves a lot due to the establishment of global context and long-range pixel information. The experiments show our approach exceeds a 30% reduction in error metrics compared with existing real-time matting approaches.
Haochen LYU Jianjun LI Yin YE Chin-Chen CHANG
The purpose of Facial Beauty Prediction (FBP) is to automatically assess facial attractiveness based on human aesthetics. Most neural network-based prediction methods do not consider the ranking information in the task. For scoring tasks like facial beauty prediction, there is abundant ranking information both between images and within images. Reasonable utilization of these information during training can greatly improve the performance of the model. In this paper, we propose a novel end-to-end Convolutional Neural Network (CNN) model based on ranking information of images, incorporating a Rank Module and an Adaptive Weight Module. We also design pairwise ranking loss functions to fully leverage the ranking information of images. Considering training efficiency and model inference capability, we choose ResNet-50 as the backbone network. We conduct experiments on the SCUT-FBP5500 dataset and the results show that our model achieves a new state-of-the-art performance. Furthermore, ablation experiments show that our approach greatly contributes to improving the model performance. Finally, the Rank Module with the corresponding ranking loss is plug-and-play and can be extended to any CNN model and any task with ranking information. Code is available at https://github.com/nehcoah/Rank-Info-Net.
In the software testing phase, software reliability growth models (SRGMs) are commonly used to evaluate the reliability of software systems. Traditional SRGMs are restricted by their assumption of a continuous growth pattern for the failure detection rate (FDR) throughout the testing phase. However, the assumption is compromised by Change-Point phenomena, where FDR fluctuations stem from variations in testing personnel or procedural modifications, leading to reduced prediction accuracy and compromised software reliability assessments. Therefore, the objective of this study is to improve software reliability prediction using a novel approach that combines genetic algorithm (GA) and deep learning-based SRGMs to account for the Change-point phenomenon. The proposed approach uses a GA to dynamically combine activation functions from various deep learning-based SRGMs into a new mutated SRGM called MuSRGM. The MuSRGM captures the advantages of both concave and S-shaped SRGMs and is better suited to capture the change-point phenomenon during testing and more accurately reflect actual testing situations. Additionally, failure data is treated as a time series and analyzed using a combination of Long Short-Term Memory (LSTM) and Attention mechanisms. To assess the performance of MuSRGM, we conducted experiments on three distinct failure datasets. The results indicate that MuSRGM outperformed the baseline method, exhibiting low prediction error (MSE) on all three datasets. Furthermore, MuSRGM demonstrated remarkable generalization ability on these datasets, remaining unaffected by uneven data distribution. Therefore, MuSRGM represents a highly promising advanced solution that can provide increased accuracy and applicability for software reliability assessment during the testing phase.
Rongqi ZHANG Chunyun PAN Yafei WANG Yuanyuan YAO Xuehua LI
With maturation of 5G technology in recent years, multimedia services such as live video streaming and online games on the Internet have flourished. These multimedia services frequently require low latency, which pose a significant challenge to compute the high latency requirements multimedia tasks. Mobile edge computing (MEC), is considered a key technology solution to address the above challenges. It offloads computation-intensive tasks to edge servers by sinking mobile nodes, which reduces task execution latency and relieves computing pressure on multimedia devices. In order to use MEC paradigm reasonably and efficiently, resource allocation has become a new challenge. In this paper, we focus on the multimedia tasks which need to be uploaded and processed in the network. We set the optimization problem with the goal of minimizing the latency and energy consumption required to perform tasks in multimedia devices. To solve the complex and non-convex problem, we formulate the optimization problem as a distributed deep reinforcement learning (DRL) problem and propose a federated Dueling deep Q-network (DDQN) based multimedia task offloading and resource allocation algorithm (FDRL-DDQN). In the algorithm, DRL is trained on the local device, while federated learning (FL) is responsible for aggregating and updating the parameters from the trained local models. Further, in order to solve the not identically and independently distributed (non-IID) data problem of multimedia devices, we develop a method for selecting participating federated devices. The simulation results show that the FDRL-DDQN algorithm can reduce the total cost by 31.3% compared to the DQN algorithm when the task data is 1000 kbit, and the maximum reduction can be 35.3% compared to the traditional baseline algorithm.
Gyulim KIM Hoojin LEE Xinrong LI Seong Ho CHAE
This letter studies the secrecy outage probability (SOP) and the secrecy diversity order of Alamouti STBC with decision feedback (DF) detection over the time-selective fading channels. For given temporal correlations, we have derived the exact SOPs and their asymptotic approximations for all possible combinations of detection schemes including joint maximum likehood (JML), zero-forcing (ZF), and DF at Bob and Eve. We reveal that the SOP is mainly influenced by the detection scheme of the legitimate receiver rather than eavesdropper and the achievable secrecy diversity order converges to two and one for JML only at Bob (i.e., JML-JML/ZF/DF) and for the other cases (i.e., ZF-JML/ZF/DF, DF-JML/ZF/DF), respectively. Here, p-q combination pair indicates that Bob and Eve adopt the detection method p ∈ {JML, ZF, DF} and q ∈ {JML, ZF, DF}, respectively.
The steady-state and convergence performances are important indicators to evaluate adaptive algorithms. The step-size affects these two important indicators directly. Many relevant scholars have also proposed some variable step-size adaptive algorithms for improving performance. However, there are still some problems in these existing variable step-size adaptive algorithms, such as the insufficient theoretical analysis, the imbalanced performance and the unachievable parameter. These problems influence the actual performance of some algorithms greatly. Therefore, we intend to further explore an inherent relationship between the key performance and the step-size in this paper. The variation of mean square deviation (MSD) is adopted as the cost function. Based on some theoretical analyses and derivations, a novel variable step-size algorithm with a dynamic limited function (DLF) was proposed. At the same time, the sufficient theoretical analysis is conducted on the weight deviation and the convergence stability. The proposed algorithm is also tested with some typical algorithms in many different environments. Both the theoretical analysis and the experimental result all have verified that the proposed algorithm equips a superior performance.
Junko SHIROGANE Daisuke SAYAMA Hajime IWATA Yoshiaki FUKAZAWA
Webpage texts are often emphasized by decorations such as bold, italic, underline, and text color using HTML (HyperText Markup Language) tags and CSS (Cascading Style Sheets). However, users with visual impairment often struggle to recognize decorations appropriately because most screen readers do not read decorations appropriately. To overcome this limitation, we propose a method to read emphasized texts by changing the reading voice parameters of a screen reader and adding sound effects. First, the strong emphasis types and reading voices are investigated. Second, the intensity of the emphasis type is used to calculate a score. Then the score is used to assign the reading method for the emphasized text. Finally, the proposed method is evaluated by users with and without visual impairment. The proposed method can convey emphasized texts, but future improvements are necessary.
Qingping YU You ZHANG Zhiping SHI Xingwang LI Longye WANG Ming ZENG
In this letter, a deep neural network (DNN) aided joint source-channel (JSCC) decoding scheme is proposed for polar codes. In the proposed scheme, an integrated factor graph with an unfolded structure is first designed. Then a DNN aided flooding belief propagation decoding (FBP) algorithm is proposed based on the integrated factor, in which both source and channel scaling parameters in the BP decoding are optimized for better performance. Experimental results show that, with the proposed DNN aided FBP decoder, the polar coded JSCC scheme can have about 2-2.5 dB gain over different source statistics p with source message length NSC = 128 and 0.2-1 dB gain over different source statistics p with source message length NSC = 512 over the polar coded JSCC system with existing BP decoder.
A PBN is well known as a mathematical model of complex network systems such as gene regulatory networks. In Boolean networks, interactions between nodes (e.g., genes) are modeled by Boolean functions. In PBNs, Boolean functions are switched probabilistically. In this paper, for a PBN, a simplified representation that is effective in analysis and control is proposed. First, after a polynomial representation of a PBN is briefly explained, a simplified representation is derived. Here, the steady-state value of the expected value of the state is focused, and is characterized by a minimum feedback vertex set of an interaction graph expressing interactions between nodes. Next, using this representation, input selection and stabilization are discussed. Finally, the proposed method is demonstrated by a biological example.
Koichi KITAMURA Koichi KOBAYASHI Yuh YAMASHITA
In cyber-physical systems (CPSs) that interact between physical and information components, there are many sensors that are connected through a communication network. In such cases, the reduction of communication costs is important. Event-triggered control that the control input is updated only when the measured value is widely changed is well known as one of the control methods of CPSs. In this paper, we propose a design method of output feedback controllers with decentralized event-triggering mechanisms, where the notion of uniformly ultimate boundedness is utilized as a control specification. Using this notion, we can guarantee that the state stays within a certain set containing the origin after a certain time, which depends on the initial state. As a result, the number of times that the event occurs can be decreased. First, the design problem is formulated. Next, this problem is reduced to a BMI (bilinear matrix inequality) optimization problem, which can be solved by solving multiple LMI (linear matrix inequality) optimization problems. Finally, the effectiveness of the proposed method is presented by a numerical example.
Haijun LIANG Yukun LI Jianguo KONG Qicong HAN Chengyu YU
Air Traffic Control (ATC) communication suffers from issues such as high electromagnetic interference, fast speech rate, and low intelligibility, which pose challenges for downstream tasks like Automatic Speech Recognition (ASR). This article aims to research how to enhance the audio quality and intelligibility of civil aviation speech through speech enhancement methods, thereby improving the accuracy of speech recognition and providing support for the digitalization of civil aviation. We propose a speech enhancement model called DIUnet_V (DenseNet & Inception & U-Net & Volume) that combines both time-frequency and time-domain methods to effectively handle the specific characteristics of civil aviation speech, such as predominant electromagnetic interference and fast speech rate. For model evaluation, we assess the denoising and enhancement effects using three metrics: Signal-to-Noise Ratio (SNR), Mean Opinion Score (MOS), and speech recognition error rate. On a simulated ATC training recording dataset, DIUnet_Volume10 achieved an SNR value of 7.3861, showing a 4.5663 improvement compared to the original U-net model. To address the challenge of the absence of clean speech in the ATC working environment, which makes it difficult to accurately calculate SNR, we propose evaluating the denoising effects indirectly based on the recognition performance of an ATC speech recognition system. On a real ATC speech dataset, the average word error rate decreased by 1.79% absolute and the average sentence error rate decreased by 3% absolute for DIUnet_V processed speech compared to the unprocessed speech in the built speech recognition system.
Kazuma TAKAHASHI Wen GU Koichi OTA Shinobu HASEGAWA
In academic presentation, the structure design of presentation is critical for making the presentation logical and understandable. However, it is difficult for novice researchers to construct required academic presentation structure due to the flexibility in structure creation. To help novice researchers revise and improve their presentation structure, we propose an academic presentation structure modification support system based on structural elements of the presentation slides. In the proposed system, we build a presentation structural elements model (PSEM) that represents the essential structural elements and their relations to clarify the ideal structure of academic presentation. Based on the PSEM, we also designed two evaluation indices to evaluate the academic presentation structure. To evaluate the proposed system with real-world data, we construct a web application that generates evaluation and feedback to academic presentation slides. The experimental results demonstrate the effectiveness of the proposed system.
Zikang CHEN Wenping GE Henghai FEI Haipeng ZHAO Bowen LI
The combination of multiple-input multiple-output (MIMO) technology and sparse code multiple access (SCMA) can significantly enhance the spectral efficiency of future wireless communication networks. However, the receiver design for downlink MIMO-SCMA systems faces challenges in developing multi-user detection (MUD) schemes that achieve both low latency and low bit error rate (BER). The separated detection scheme in the MIMO-SCMA system involves performing MIMO detection first to obtain estimated signals, followed by SCMA decoding. We propose an enhanced separated detection scheme based on lightweight graph neural networks (GNNs). In this scheme, we raise the concept of coordinate point relay and full-category training, which allow for the substitution of the conventional message passing algorithm (MPA) in SCMA decoding with image classification techniques based on deep learning (DL). The features of the images used for training encompass crucial information such as the amplitude and phase of estimated signals, as well as channel characteristics they have encountered. Furthermore, various types of images demonstrate distinct directional trends, contributing additional features that enhance the precision of classification by GNNs. Simulation results demonstrate that the enhanced separated detection scheme outperforms existing separated and joint detection schemes in terms of computational complexity, while having a better BER performance than the joint detection schemes at high Eb/N0 (energy per bit to noise power spectral density ratio) values.
Yuta NAKAHARA Toshiyasu MATSUSHIMA
Previously, we proposed a probabilistic data generation model represented by an unobservable tree and a sequential updating method to calculate a posterior distribution over a set of trees. The set is called a meta-tree. In this paper, we propose a more efficient batch updating method.
Koshi SHIMADA Shota SAITO Toshiyasu MATSUSHIMA
The context tree model has the property that the occurrence probability of symbols is determined from a finite past sequence and is a broader class of sources that includes i.i.d. or Markov sources. This paper proposes a non-stationary source with context tree models that change from interval to interval. The Bayes code for this source requires weighting of the posterior probabilities of the context tree models and change points, so the computational complexity of it usually increases to exponential order. Therefore, the challenge is how to reduce the computational complexity. In this paper, we propose a special class of prior probability distribution of context tree models and change points and develop an efficient Bayes coding algorithm by combining two existing Bayes coding algorithms. The algorithm minimizes the Bayes risk function of the proposed source in this paper, and the computational complexity of the proposed algorithm is polynomial order. We investigate the behavior and performance of the proposed algorithm by conducting experiments.