Cold-start item recommendation is a significant challenge in recommendation systems, particularly when new items are introduced without any historical interaction data. While existing methods leverage multi-modal content to alleviate the cold-start issue, they often neglect the inherent multi-view structure of modalities, namely the distinction between shared and modality-specific features. In this paper, we propose Multi-Modal Multi-View Variational AutoEncoder (M²VAE), a generative model that addresses the challenges of modeling common and unique views in attribute and multi-modal features, as well as user preferences over single-typed item features. Specifically, we generate type-specific latent variables for item IDs, categorical attributes, and image features, and use Product-of-Experts (PoE) to derive a common representation. A disentangled contrastive loss decouples the common view from unique views while preserving feature informativeness. To model user inclinations, we employ a user-aware hierarchical Mixture-of-Experts (MoE) to adaptively fuse representations. We further incorporate co-occurrence signals via contrastive learning, eliminating the need for pretraining. Extensive experiments on real-world datasets validate the effectiveness of our approach.

In advertising recommendation systems, click-through rate (CTR) prediction is a critical task. Capturing users' interests from their rich historical behaviors is key to improving prediction results. Although traditional deep learning methods can capture users' interests to some extent, they fail to account for the local and global interests reflected in users' historical behaviors and the dynamic relationships between them. In this paper, we propose a novel architecture - Dual-Interest Adaptive Network (DIAN), which adaptively extracts both local and global interests of users. Specifically, to better explore users' interests in depth, we propose an Adaptive Interest Extraction Block applied to users' historical behavior sequences. By introducing an attention mechanism, this module can flexibly allocate weights to users' local and global interests after decoupling user behaviors. Additionally, to capture complex feature interactions, our model introduces two feature extractors: one combines a Multi-Layer Perceptron (MLP) with a Cross Network for high-order feature extraction, and the other incorporates an Attention Factorization Machine (AFM) for low-order feature extraction. We conducted extensive experiments on the Movielens-1M and Amazon Electronics datasets, validating the effectiveness of DIAN.

Root cause analysis (RCA) is crucial for the stability and reliability of large-scale microservice architectures. Existing multi-source RCA methods primarily rely on logs, traces, and metrics data to detect anomalies and identify abnormal services and root causes. And most multi-source methods focus only on service-level operations and inter-service dependencies, neglecting transactions and their dynamic changes. Furthermore, these approaches typically address only a subset of the RCA tasks, such as anomaly detection, root cause service localization, or root cause type determination. To address these limitations, we propose MicroTR, a transaction reproduction fault diagnosis framework for multi-source RCA in microservice environments. MicroTR deeply analyzes transaction execution logic and service states, utilizing multi-source data to reproduce the dynamic changes of transaction execution states in knowledge graph. This approach enables efficient and synchronized anomaly detection, root cause service localization, and root cause type determination. Experimental evaluations on two widely-adopted open-source microservice platforms demonstrate that MicroTR outperforms state-of-the-art multi-source methods, achieving an average F1 of 97.3% for anomaly detection, an average Hit@l of 90.8% for root cause service localization, and an average Hit@1 of 89.2% for root cause type determination. These results highlight the effectiveness of reproducing transaction execution states for RCA.

Sequential recommendation (SR) aims to predict the next purchasing item according to users' dynamic preference learned from their historical user-item interactions. To improve the performance of recommendation, learning dynamic heterogeneous cross-type behavior dependencies is indispensable for recommender system. However, there still exists some challenges in Multi-Behavior Sequential Recommendation (MBSR). On the one hand, existing methods only model heterogeneous multi-behavior dependencies at behavior-level or item-level, and modeling interaction-level dependencies is still a challenge. On the other hand, the dynamic multi-grained behavior-aware preference is hard to capture in interaction sequences, which reflects interaction-aware sequential pattern. To tackle these challenges, we propose a Multi-Grained Preference enhanced Transformer framework (M-GPT). First, M-GPT constructs an interaction-level graph of historical cross-typed interactions in a sequence. Then graph convolution is performed to derive interaction-level multi-behavior dependency representation repeatedly, in which the complex correlation between historical cross-typed interactions at specific orders can be well learned. Secondly, a novel multifaceted transformer architecture equipped with multi-grained user preference extraction is proposed to encode the interaction-aware sequential pattern enhanced by capturing temporal behavior-aware multi-grained preference . Experiments on the real-world datasets indicate that our method M-GPT consistently outperforms various state-of-the-art recommendation methods. Our code is available at: https://github.com/hchchchchchchc/MGPT.

Lane detection plays a crucial role in autonomous driving. Though modern anchor-based deep lane detection methods have demonstrated remarkable performance on standard benchmarks, they continue to struggle with complex topological variations. In this work, we propose the Dual Weighting Attention Feature Fusion Network(DW_AFFNet), which enhances detection performance through two key innovations: (1) hierarchical feature fusion for improved location and (2) anchor’s IoU classification score consistency optimisation. In computer vision, shallow low-level features provide precise spatial localization while deep high-level features capture essential global information. Therefore, complementary global-local representations for enhanced lane detection accuracy are established via Iterative Coordinate Attention Feature Fusion (ICAFF) module, which systematically combines these hierarchical features through coordinate-sensitive attention mechanisms. Furthermore, we introduce the Dual Weighting Label Assignment Scheme (DW Scheme) to align IoU and classification scores through importance-aware dynamic weighting, significantly improving sample discrimination capability. We evaluate our method on two benchmarks of lane detection and the results demonstrate its effectiveness. Our method surpasses baseline on CULane. On CULane, it obtains 56.45 mF1 with 64.21/55.76/22.16 F1@75/80/90 scores, outperforming CLRNet by 1.52%/2.27%/3.06%/7.4% respectively. Significant improvements are observed across most scenarios in complex road conditions.

In the field of object detection, Feature Pyramid Network have gained widespread adoption in object detection algorithms due to its simplicity, efficiency, and robust feature generation capabilities. Despite its merits, the Feature Pyramid Network exhibits certain limitations in its architectural design. Within the scope of this paper, we aim to dissect the structural limitations inherent in the Feature Pyramid Network and introduce a new network architecture, termed Hybrid-Residual Feature Pyramid Network(HR-FPN), which is designed to effectively mitigate these identified issues. The HR-FPN is primarily composed of two key modules: the Hybrid-Operation Module and the Residual Feature Augmentation Module. The Hybrid-Operation Module effectively integrates semantic information from high-level features into low-level features, while the Residual Feature Augmentation Module mitigates information loss in the highest pyramid layer feature maps by extracting scale-invariant contextual information. Then, We have designed an enhanced version of Sparse R-CNN, termed Specific Proposal Feature R-CNN(SPF R-CNN), which incorporates Learnable Proposal Classification Features and Learnable Proposal Regression Features to effectively mitigate the issue of the discrepancy between classification and localization tasks. Extensive experiments have demonstrated the effectiveness of our approach. Compared to the baseline model, Sparse R-CNN, our method achieved a 1.9 average precision (AP) improvement on the MS-COCO dataset.

Few-shot object detection usually faces the challenge of imbalanced data distribution. The limited training data for novel classes not only leads to insufficient representation of support features but also biases the detector toward base classes. To address these problems, we propose a novel dynamic latent feature guidance method. First, the latent feature reconstruction module utilizes a variational autoencoder to reconstruct query and support features, extracting additional information representations from the latent space, thereby enriching feature representation and compensating for the information deficiencies caused by limited samples. Second, we design the dynamic multiscale similarity guidance module, which highlights information relevant to query images and suppresses background noise and occlusion interference through global, regional, and local similarities. Extensive experimental results demonstrate that our proposed method significantly improves detection accuracy on the PASCAL VOC and MS COCO datasets, outperforming existing state-of-the-art methods.

Mobile Crowd Sensing (MCS) represents an emerging paradigm for collecting sensory data, leveraging the extensive sensing capabilities of widely used mobile devices to execute sensing tasks. Among the array of challenges facing current MCS systems, the incentive mechanism for data requesters and participants consistently stands out as a paramount concern. Existing incentive mechanisms often rely on model-based approaches, assuming a certain degree of prior knowledge about the MCS system, such as expected pricing for data requesters and participants. However, these assumptions are impractical in real-world scenarios. To address this challenge, we endeavor to explore a wholly model-free incentive mechanism. Specifically, we propose a Simulated Annealing Deep Q-learning (SADQ-learning) algorithm to dynamically generate the pricing policy for the sensing platform. Furthermore, to accommodate diverse incentive needs, we devise three distinct incentive modes: one focuses on maximizing the profit of the sensing platform, another dedicates to maximizing the successful matching amount of sensing tasks, and an equilibrium mode seeks a balance between the aforementioned objectives. Finally, numerical results demonstrate the superiority of SADQ-learning through comparisons with baseline algorithms.

Real-world applications of object detection, such as video referee at the Hangzhou Asian Games, have high requirements for accuracy. However, the performance of detectors is hindered by the discrepancy between the two sub-tasks of classification and localization, which mainly includes inconsistent feature requirements and inconsistent output pre-dictions. To alleviate the discrepancy, this paper presents a new end-to-end object detection framework named Decouple and Align (DA) Sparse R-CNN. Specifically, the Proposal Feature Decoupling (PFD) module is proposed to decouple the shared proposal features into classification and regression proposal features, which meets the inconsistent feature requirements of both classification and localization tasks. Additionally, to solve the misalignment problem between the output predictions of the two tasks, we introduce a localization precision aware classification loss to jointly optimize classification and localization. Extensive experiments demonstrate the effectiveness of our DA Sparse R-CNN. In particular, our proposed method can improve 2.1 average precision (AP) on the MS-COCO dataset compared with Sparse R-CNN.

The sensing coverage of roadside sensing system usually does not cover the entire road network, resulting in block missing values in traffic data. Traditional methods either adopted simple hints or graph neural networks to capture the speed variation. However, these methods fail to consider that block missing values have less surrounding values and are less susceptible to the influence of adjacent data. The paper proposes Dynamic Style Transfer-based Generative Adversarial Imputation Network (ST-GAIN) for block missing traffic speed imputation. The core idea is to adopt temporal clustering to abstract a large volume of traffic speed into a series of style data. Subsequently, a dynamic encoding network of latent style codes is performed based on the similarity between the missing speed data and the style data. These style codes are then fed into a style transfer network to guide the imputation of the missing values. Additionally, a style discriminator is used to guide style transfer during training. The experimental results demonstrate that the proposed model outperforms state-of-the-art methods by an average of more than 15% in accuracy.

Traffic flow prediction, as one of the problems of spatial correlation analysis of time series, has been extensively studied. The extraction and fusion of effective spatio-temporal features are crucial for achieving high-precision traffic flow prediction. Traditionally, the adjacency graph designed based on the neighboring nodes of real-world road networks has been indispensable for learning spatial features. However, this single connected component graph structure is prone to the phenomenon of over-smoothing, leading to homogenization of the learned spatial feature. Addressing this challenge, this paper proposes a novel Semantic Multi-connected Graph Neural Network (SMGNN) aimed at mitigating the homogeneity of spatial features and effectively modeling spatio-temporal interactions. Firstly, considering the existence of several nodes in large-scale road networks with similar traffic flow variation patterns, we semantically connect these nodes to construct multi-connected semantic spatial graphs (MSSG), replacing the traditionally used neighboring node graph in conventional graph neural networks. Correspondingly, we design a novel graph neural network architecture that cyclically fuses dynamic scale spatio-temporal features from MSSG using an improved Dynamic Spatial Graph Attention (DSGA) module. Secondly, to achieve a more effective representation, we design a Inverted Temporal Attention (ITA) module to supplement static scale temporal features. Furthermore, we introduce a Multi-dimensional and Multi-scale Feature Extraction (MMFE) module to fuse spatio-temporal features at various scales within different receptive fields. Extensive experiments conducted on real-world datasets have verified the effectiveness of our proposed method, significantly outperforming various baseline models.

UAVs (Unmanned Aerial Vehicles) are promising tools for efficient data collections of sensors in IoT networks. Existing studies exploited both spatial and temporal data correlations to reduce the amount of collected redundant data, in which sensors are first partitioned into different clusters, a master sensor in each cluster then collects raw data from other sensors and compresses the received data. An energy-constrained UAV finally collects the maximum amount of compressed data from different master sensors. We however notice that the compressed data from only a portion of clusters are collected by the UAV in the existing studies, while the data from other clusters are not collected at all. In this paper, we study a problem of finding a data collection trajectory for an energy-constrained UAV, so that the accumulative utility of collected data is maximized, where the accumulative utility measures the quality of spatiotemporally correlated data collected from different clusters. We propose a novel 16+-approximation algorithm for the problem, where is a given constant with >0. Experimental results with real datasets show that the accumulative utility by the proposed algorithm is at least 23% larger than those by the existing studies, and the number of clusters collected by the proposed algorithm is from 45% to 105% larger than those by the existing studies.

The rapid development of technology such as virtual reality and augmented reality, coupled with the reduced direct contact due to the COVID-19 pandemic, has led to the emergence of a more advanced mode of interaction: air handwriting. This new form of human-computer interaction allows users to input text by writing in the air freely. However, deploying and applying existing air handwriting recognition systems in real-world scenarios still presents challenges, particularly in real-time performance, privacy protection, and label scarcity. To address these challenges, we propose a federated active learning framework called FedAWR for air handwriting recognition tasks. FedAWR utilizes distributed learning to train a shared global model in the cloud from multiple user devices at the network's edge, while keeping the user's handwritten data local to ensure privacy. In addition, FedAWR employs an interactive active learning strategy to collect user-provided annotations for iterative training during the online federated learning process, bootstrapping personalized models for each client. To further enhance interactivity and real-time performance, we designed a lightweight recognition model, which is integrated into FedAWR. Finally, extensive experiments were conducted on real-world air handwritten datasets to validate the superiority of FedAWR.

Mobile Crowd Sensing (MCS) represents a novel paradigm which utilizes intelligent devices carried by mobile users to collect and transmit data. Appropriate incentives are essential to recruit enough participants for sensing tasks. Existing works have designed some incentive mechanisms for MCS, which are not suitable for scenarios when the participants increase significantly as a result of the booming cost. To solve the above cost problem, a Utility-Maximization Incentive Mechanism (UMIM) is proposed in this paper by leveraging the influence propagation on the social network. Participants in the same social network can benefit from the data shared by others, which shows the utility of sensing data and can be regarded as a non-monetary incentive and make the participants stay positive under relative low payoff. Therefore, by improving the utility of sensing data, the incentive cost can be effectively reduced. To maximize the data utility, we further design a tree-based structure to improve the priority experience replay mechanism of Proximal Policy Optimization (PPO) in UMIM. This improvement makes the high priority experience to be sampled more quickly and efficiently, as a result, the network can learn more effectively. Numerical results show that UMIM can further improve the data utility and have better convergence.

In this paper we study the deployment of an Unmanned Aerial Vehicle (UAV) network that consists of multiple UAVs to provide emergent communication service for people who are trapped in a disaster area, where each UAV is equipped with a base station that has limited computing capacity and power supply, and thus can only serve a limited number of people. Unlike most existing studies that focused on homogeneous UAVs, we consider the deployment of heterogeneous UAVs where different UAVs have different computing capacities. We study a problem of deploying$K$heterogeneous UAVs in the air to form a temporarily connected UAV network such that the network throughput – the number of users served by the UAVs, is maximized, subject to the constraint that the number of people served by each UAV is no greater than its service capacity. We then propose a novel$O(\sqrt{\frac{s}{K}})$-approximation algorithm for the problem, where$s$is a given positive integer with$1 \le s\le K$, e.g.,$s=3$. We also devise an improved heuristic, based on the approximation algorithm. We finally evaluate the performance of the proposed algorithms. Experimental results show that the numbers of users served by UAVs in the solutions delivered by the proposed algorithms are increased by 25% than state-of-the-arts.

Learning effective image representation and constructing a suitable metric space are two main challenges in few-shot image classification. Existing methods normally consider the joint characteristic distribution of the image to improve the image representation ability, but it also brings high computational cost and produces high-dimensional embedding vectors, which limit their real-world applicability. In this paper, in order to reduce computational complexity and embedding dimension, we propose an effectively low-dimensional feature representation module (LDFR), which introduces a window mechanism to make the model focus on the correlation between local channels by using Brownian Distance Covariance. Furthermore, we combine LDFR with Hybrid Attention (LDFR-HA) to solve the problem of unbalanced sample features in few-shot image classification. Specifically, weighted average is adopted in the Hybrid Attention to construct the metric space and perform classification. Numerous experiments are conducted on two standard few-shot image classification benchmarks, i.e., general object recognition and fine-grained categorization. Extensive evaluations demonstrate that LDFR-HA significantly outperforms existing approaches. On popular datasets miniImageNet and CUB, LDFR-HA achieves 3.52 percentage point(pp)/2.29pp and 2.1pp/1.45pp gains over the state-of-the-art method on 5-way 1-shot/5-shot tasks, respectively.

Click-Through Rate(CTR) prediction aims to predict the possibility of users clicking on products, which has become the core task of advertising recommendation systems. Due to the richness of user historical behavior, a key to making effective prediction is to capture users' diverse interests from historical behavior. An efficient way to do this is to perform dot product of behavior and target embedding with attentive neural networks. To better model the users' diverse interests, our proposed disentangled interest extraction block decouples the unary terms modeling the impact of user behavior sequence from pairwise interactions. Specifically, the decoupled pairwise term can learn the pure pairwise interactions, whereas the unary term models the impact of behavior sequence on each target items. Meanwhile, our model emphasizes both high- and low-order feature interactions by combining Attentional Factorization Machines(AFMs) with deep learning. This work intends to accomplish our goal by proposing a novel architecture Deep Disentangled Interest Network(DDIN). We conduct comprehensive experiments on Movielens dataset and Amazon electronic dataset. The results demonstrate the effectiveness of DDIN which is superior to some state-of-art models by up to 26.271 %.

The popularity of the microservices architecture has led to an evident trend of integration in system design, enabling systems to integrate numerous services to meet the diverse requirements of users. However, with extensive integration, it is difficult to quickly identify the root cause of the issues. In this paper, we propose MicroKGCL, a knowledge graph for root cause localization of feedback issues in microservices. Through the knowledge graph constructed with historical cases, MicroKGCL explores the potential relationship between user feedback and the root cause of system issues, it analyzes possible issues and ranks candidate root causes. In detail, in order to provide a more accurate representation of the feedback profile, we design a multi-modal embedding block, which utilizes a contrastive learning model and BERT model to extract feedback features from visual and content modalities. Experimental results demonstrate the superiority of the proposed MicroKGCL in terms of both MRR and Hits@n by comparing with the baselines. Moreover, to further verify the MicroKGCL, it has been deployed in the real production environment of Ant Group, achieving a top-3 hit ratio of 75% and a coverage ratio of 81.8%.

Nowadays, backscatter, radio-frequency (RF) energy harvesting (EH), and cognitive radio (CR) technologies have been widely applied in Internet of Things (IoT) to address the issues of energy supply and spectrum scarcity. This article focuses on the throughput maximization problem of backscatter-aided wireless-powered heterogeneous CR networks (WPHetCRNs), where two types of secondary transmitters (STs), i.e., the STs with backscatter units (STBs) and the STs with RF-EH units (STEs), coexist. The STBs operate in the ambient backscatter (AB) mode, and the STEs operate in the harvest-then-transmit (HTT) mode. Inspired by the potential benefits of cooperations between different users, we propose a backscatter-aided cooperative relay transmission (BaCRT) strategy to improve the sum-throughput of the secondary users (SUs). The main idea is that when the licensed spectrum of the primary users (PUs) is busy, the STBs first help to relay the primary data via the passive relay mode, and then transmit the secondary data via the AB mode, while the STEs harvest energy in the HTT mode. With the help of relaying, the target throughput of the PUs could be met in shorter duration and the licensed spectrum could become idle more quickly. When the licensed spectrum becomes idle, the STEs transmit data in the HTT mode. The goal of this article is to identify the optimal time allocation among the passive relay mode, AB mode, and data transmission of HTT mode that maximizes the sum-throughput of the SUs. To reach this goal, we first investigate the single-ST case for each type and derive the closed-form solution of the optimal time allocation. We then extend to the multiple-ST case for each type, where three scenarios are classified with respect to the fairness issue of the STBs. We prove that the sum-throughput maximization problem is convex in each scenario and employ the block coordinate descent and gradient descent iterative algorithms to solve the problem. Numerical results show that the proposed BaCRT strategy significantly improves the sum-throughput of the SUs compared with other strategies.

Motivated by the benefits of cognitive radio (CR), energy harvesting (EH), and backscatter communication (BC) technologies to support Internet of Things (IoT) systems, we investigate the backscatter-aided EH CR networks (EH-CRNs) in a multichannel scenario. To achieve high throughput on various channels, we propose a novel hybrid communication scheme that the secondary transmitter (ST) selects one channel for spectrum sensing, and performs multiple actions based on the sensing result. To be specific, if the selected channel is detected as busy, the ST potentially performs underlay mode transmission, ambient BC (AmBC), or radio frequency (RF) EH. Otherwise, the ST performs interweave mode transmission. Based on the ST’s knowledge of the channel availability and the amount of the available energy, the decisions of channel and specific action selections are made. Furthermore, the sequential decision problem is formulated as a mixed observability Markov decision process (MOMDP), and addressed by the classic value iteration algorithm. The proposed scheme could be flexibly adapted to the changes in energy and channel availabilities. Simulations demonstrate the superiority of this scheme in terms of throughput, and show that even without channel selection, the proposed scheme conducted on the channels with different idle probabilities always achieves high throughput.

Wireless power transfer (WPT) and edge computing have been validated as effective ways to solve the energy-limited problem and computation-capacity-limited problem of wireless devices (WDs), respectively. This paper studies the wireless-powered multi-access edge computing (WP-MEC) network, where WDs conduct either local computing or task offloading for their individable computation tasks. We aim to minimize total computation delay (TCD) when each WD has a computation task to execute, referred to as the total computation delay minimization (TCDM) problem, by jointly optimizing the offloading-decision, WPT duration, and transmission durations of offloading WDs. The TCDM problem is a mixed integer programming (MIP) problem that is challenging to efficiently obtain the optimal or near-optimal solution. To tackle this challenge, we decompose the TCDM problem into the sub-problem of optimizing the WPT duration and transmission durations, and the top-problem of optimizing the offloading decision. For the nonconvex sub-problem, we design a worst-WD-adjusting (WDA) algorithm to efficiently obtain its optimal solution. For the top-problem, under the time-varying channel conditions, traditional optimization methods are hard to determine the optimal or near-optimal offloading decision within the channel coherence duration. To fast obtain the near-optimal offloading decision, we propose a deep neural networks (DNN)-based deep reinforcement learning (DRL) model, which takes the sub-problem solving as one component for utility evaluation. Finally, numerical results demonstrate that the proposed online DRL-based offloading algorithm achieves the near-minimal TCD with low computational complexity, and is suitable for the fast-fading WP-MEC network.

The topic of identification for sparse vector in a distributed way has triggered great interest in the area of adaptive filtering. Grouping components in the sparse vector has been validated to be an efficient way for enhancing identification performance for sparse parameter. The technique of pairwise fused lasso, which can promote similarity between each possible pair of nonnegligible components in the sparse vector, does not require that the nonnegligible components have to be distributed in one or multiple clusters. In other words, the nonnegligible components may be randomly scattered in the unknown sparse vector. In this article, based on the technique of pairwise fused lasso, we propose the novel pairwise fused lasso diffusion least mean-square (PFL-DLMS) algorithm, to identify sparse vector. The objective function we construct consists of three terms, i.e., the mean-square error (MSE) term, the regularizing term promoting the sparsity of all components, and the regularizing term promoting the sparsity of difference between each pair of components in the unknown sparse vector. After investigating mean stability condition of mean-square behavior in theoretical analysis, we propose the strategy of variable regularizing coefficients to overcome the difficulty that the optimal regularizing coefficients are usually unknown. Finally, numerical experiments are conducted to verify the effectiveness of the PFL-DLMS algorithm in identifying and tracking sparse parameter vector.

The advancement of nano communication has opened the door for the development of intrabody medical application services. Flow-guided nano-communication networks have gained major attraction in recent years as an effective solution for intrabody sensing and actuation. This article builds a three-layer vertical network structure for intrabody nanonetworks, i.e., nano nodes, nano routers, and gateway, where data packets generated by nano nodes are relayed to the gateway through nano routers or other nodes. However, how to guarantee the data transmission through the way of multiple hops in such a scenario is an unsolved challenge. In order to improve the throughput and reduce the energy consumption of intrabody nanonetworks in a single-flow environment where the nano devices are restricted, a flow-guided opportunistic routing (FGOR) protocol is proposed. In FGOR, a relative position (RP) model is proposed to formulate the criterion for candidate relay selection (CRS) and enable the nodes’ direction awareness to the gateway. Moreover, the CRS criterion is redesigned through a mobility gradient (MG) model further derived from the RP model. The candidate nodes are prioritized based on node ID, available energy, and RP information of nodes to perform backoff forwarding for decreasing transmission redundancy. Simulation results show that the RP model improves the throughput and significantly extends the lifecycle of intrabody nanonetwork by reducing the energy consumption. Compared with the RP model, the MG model performs better in terms of delay and successful transmission rate, especially within the circulation environment of intrabody.

Nanonetworks are composed of interacting nano-nodes, whose size ranges from several hundred cubic nanometers to several cubic micrometers. The extremely constrained computational resources of nano-nodes, the fluctuations in their energy caused by energy harvesting processes, and their very limited transmission range at Terahertz (THz)-band frequencies (0.1-10 THz), make the design of routing protocols in nanonetworks very challenging. A multi-hop deflection routing algorithm based on reinforcement learning (MDR-RL) is proposed in this paper to dynamically and efficiently explore the routing paths during packet transmissions. First, new routing and deflection tables are implemented in nano-nodes, so that nano-nodes can deflect packets to other neighbors when route entries in the routing table are invalid. Second, one forward updating scheme and two feedback updating schemes based on reinforcement learning are designed to update the tables, namely, on-policy and off-policy updating schemes. Finally, extensive simulations in networks simulator-3 are conducted to analyze the performance of MDR-RL using different updating policies, as well as to compare the performance with other machine learning routing algorithms based on Neural Networks and Decision Tree. The results show that the MDR-RL can increase the packet delivery ratio and number of delivered packets, and can decrease the packet average hop count.

Abstract A general framework to investigate the interference and coverage probability is proposed in this paper for indoor terahertz (THz) communications with beamforming antennas. Due to the multipath effects of THz band (0.1–10 THz), the line of sight and non-line of sight interference from users and access points (APs) (both equipped with beamforming antennas) are separately analyzed based on distance-dependent probability functions. Moreover, to evaluate the effects of obstacles in real applications, a Poisson distribution blockage model is implemented. Moreover, the coverage probability is derived by means of signal to interference plus noise ratio (SINR). Numerical results are conducted to present the interference and coverage probability with different parameters, including the indoor area size, SINR threshold, numbers of interfering users and APs and half-power bandwidth of beamforming antenna.

In this study, the authors propose a novel component‐wise variable step‐size diffusion least mean square (CWVSS‐DLMS) algorithm for distributed estimation. Different from the traditional variable step‐size DLMS (VSS‐DLMS) algorithms in which the updating of all components in the weight vector are the same, the step sizes vary from each other on all components at each iteration in the CWVSS‐DLMS algorithm. After deriving the CWVSS‐DLMS algorithm, they perform theoretical analysis in terms of mean stability and mean‐square behaviour. They have also compared the performance of the CWVSS‐DLMS algorithm with several other DLMS algorithms through numerical simulations in both stationary and non‐stationary environments. Simulation results show that the performance of the CWVSS‐DLMS algorithm is more outstanding than the fixed step‐size DLMS algorithm, several non‐component‐wise VSS‐DLMS algorithms and existing component‐wise VSS‐DLMS algorithms in balancing high convergence rates and low steady‐state misadjustment. Moreover, they have investigated the performance of the CWVSS‐DLMS algorithm for estimating sparse parameter in a distributed way. Simulation results show that the CWVSS‐DLMS algorithm can yield satisfying performance in sparsely distributed estimation regardless of the degree of sparsity in the real parameter.

The rapid development of Internet-of-Things is yielding a huge volume of time series data, the real-time mining of which becomes a major load for data centers. The computation bottleneck in time series data mining is distance function, which is the fundamental element of many high data mining tasks. Recently various software optimization and hardware acceleration techniques have been proposed to tackle the challenge. However, each of these techniques is only designed or optimized for a specific distance function. To address this problem, in this paper we propose MDA, a high-throughput reconfigurable memristor-based distance accelerator for real-time and energy-efficient data mining with time series in data centers. Common circuit structure is extracted for efficiency, and the circuit can be configured to any specific distance functions. Particularly, we adopt the emerging device memristor for the design of MDA. Comprehensive experiments are presented with public available datasets to evaluate the performance of the proposed MDA. Experimental results show that compared with existing works, MDA has achieved a speedup of 3.5×-376× on performance and an improvement of 1-3 orders of magnitude on energy efficiency with little accuracy loss.

Nanonetworks composed by communicating nano-devices enable new applications in the consumer, biomedical, and environmental fields. Three main characteristics introduce strict requirements for routing protocols design for nanonetworks, namely, short transmission range at Terahertz (THz) frequency (0.1-10 THz), fluctuations in the energy of nano-nodes due to the energy harvesting processes and very limited memory/buffer size of nano-nodes. In this paper, a multi-hop deflection routing algorithm based on Q-learning for energy-harvesting nanonetworks (MDRQEN) is proposed to guarantee the network energy efficiency, while ensuring a low packet loss probability. First, a deflection table is introduced to deflect the packets when the next hop nano-nodes are unavailable due to energy or memory/buffer constraints. Then, a Q-learning scheme is proposed to update the routing table and deflection table by utilizing the reward information contained in the forwarded packet from the previous nano-node. In the Q-learning update scheme, packet deflection ratio, packet loss ratio, packet hop count and node energy status of nano-nodes are taken into consideration. As numerically shown through extensive simulations in Network Simulator 3 (NS-3), the proposed MDRQEN algorithm can achieve a better packet delivery ratio and energy efficiency than random routing algorithm, flooding routing algorithm and the MDRQEN algorithm without the Q-learning update scheme.

The rapid development of Internet of Things is yielding a huge volume of time series data, the real-time mining of which becomes a major load for data centers. The computation bottleneck in time series mining is the distance measure, in which dynamic time warping (DTW) is one of the most widely used distance measures. Recently, various software optimization and hardware acceleration techniques have been proposed for DTW acceleration. However, the throughput and energy efficiency of DTW are still big concerns considering the ever-increasing volume of times series. In this paper, we propose a high-throughput and efficient memristor-based DTW architecture for real-time time series mining on data centers. Specifically, memristors have been adopted for both computation and configuration of the computing architecture. The computation flow in this architecture is fully presented in a continuous and asynchronous manner. To improve the computation efficiency, we propose an early lower bound algorithm by exploiting the predictability in the circuit characteristic. Experiments are performed with module evaluation and end-to-end evaluation including three popular applications: 1) similarity search; 2) classification; and 3) anomaly detection. Experimental results indicate that, compared to existing approaches, the speedup and energy efficiency improvement are 12x-43x and 51x-287x, respectively.

Interference and coverage is a critical factor affecting the performance of nanonetworks in the terahertz (THz) band. In this paper, on the basis of THz channel model, the interferences from surrounding omnidirectional nanosensors (NSs) and beamforming Base Stations (BSs) are derived in closed forms by using stochastic geometry methods respectively. Furthermore, the corresponding Signal-to-Interference-plus-Noise-Ratio (SINR) and the coverage probabilities are investigated based on the proposed interference model. Simulation results, observed from the spectral windows at 1.0 THz, 4.5 THz and 9.1 THz, demonstrate that high density of BSs, beamforming antenna with small beam-width and low density of NSs are recommended to mitigate the interference and improve the coverage performance. Moreover, low frequency in THz band with low absorption coefficient is advocated to guarantee the correct reception with enough high received signal strength.

The optimization of the network throughput and transmission range is one of the most important issues in cognitive relay networks (CRNs). Existing research has focused on the dual-hop network, which cannot be extended to a triple-hop network due to its shortcomings, including the limited transmission range and one-way communication. In this paper, a novel, triple-hop relay scheme is proposed to implement time-division duplex (TDD) transmission among secondary users (SUs) in a three-phase transmission. Moreover, a superposition coding (SC) method is adopted for handling two-receiver cases in triple-hop networks with a cognitive relay. We studied a joint optimization of time and power allocation in all three phases, which is formulated as a nonlinear and concave problem. Both analytical and numerical results show that the proposed scheme is able to improve the throughput of SUs, and enlarge the transmission range of primary users (PUs) without increasing the number of hops.

The irrational use of limited network resources in conjunction with the unpredictable nature of traffic load injection in wireless multimedia sensor networks (WMSN) may lead to congestion. Traditional transmission schemes were not designed for supporting prioritized QoS, especially not for guaranteeing strict QoS required by real-time services such as voice and video. To overcome these deficiencies, an optimized rate control approach is proposed for multi-priority data transmission based on the extended Lotka-Volterra competitive model. The key idea is, when some new traffic flows are initialized and injected into the WMSN due to unexpected events, a novel bio-inspired rate control (Bio-RC) approach is designed to consider their effects on the system stability according to the limited network resources and competitions with others traffic flows, ensuring that the system will rapidly converge to a global and stable equilibrium point (EP) and all traffic flows are of peaceful coexistence and differentiated with QoS and priorities. At the same time, the network resources can be utilized adequately and congestion can be brought down or avoided effectively. Extensive simulations reveal that the proposed approach achieves adaptability and scalability to dynamic network traffic load, and coexistence with service differentiation for data flows.

Transmitting delay-sensitive video streaming over IEEE 802.11e wireless local area networks (WLANs) is becoming increasingly popular. However, the transmission of real-time video streaming is very challenging because of the time-varying wireless channels and video content characteristics. The authors propose an accurate model to assess the perceived quality of video streaming over WLANs with enhanced distributed coordination function (EDCF) mechanism. The analytical model considers not only the packet loss caused by wireless interference and channel fading, but also the effects of loss from channel access competition. Based on the Markov chain, the authors then present the discrete probability distribution of medium access control (MAC) layer packet service time by using the signal transfer function of the generalised state transition diagram. Moreover, the coding relation of lost video frames is also explored in the performance analysis of the proposed model. Simulations based on Network Simulator 2 (NS-2) are conducted to verify the performance of the analytical model. The results show that the proposed model provides superior accuracy for the perceived quality of MPEG-4 video streaming over IEEE 802.11e EDCF-based WLANs.