As deep learning expands across emerging domains, computational demands are pushing traditional electronic accelerators to their limits. Silicon photonics has emerged as a promising technology for accelerating deep learning workloads, but precision remains a challenge due to noise and non-idealities. In this paper, we present BITLUME, a novel photonic computing unit that enables multiplications beyond 8-bit precision through a precision-flexible scheme. We further propose an optimized round-truncation algorithm and data mapping strategy for BITLUME to reduce optoelectronic conversions, enhance data reuse, and maintain computational accuracy. A hybrid optoelectronic architecture integrating BITLUME is developed and validated using a prototype built with FPGA, RF, and photonic components, achieving 3.7× lower end-to-end latency than the A100 GPU in dot product. Simulations of training seven DNN models at FP32 show that BITLUME achieves up to 3.35× and 10.78× speedup, and 1.53× and 4.12× energy savings, compared to the state-of-the-art photonic accelerator and A100 GPU, respectively.

Model Heterogeneous Federated Learning(MHFL) builds on traditional Federated Learning (FL) to better leverage the knowledge and data distributed across hardware-heterogeneous devices. Among various heterogeneous FL approaches, the Partially Training (PT)-based methods are one of the most promising approaches, which extract submodels from the global model for local training. However, existing state-of-the-art(SOTA) methods lack effective guidance for updating the global model, making it challenging to handle the Non-IID data distribution and maintain generalization across clients. To guide the update of the global model to mitigate the impact of Non-IID data and enhance the generalization of the global model, we proposed FedShapleX: Shapley Value Driven Context-Aware Submodel Extraction for Model-Heterogeneous Federated Learning. In this work, we first proposed a Parameter-based Class-Specific Shapley Value (PCSV), which quantifies each client’s class-specific contribution to the global model, providing a measure of how effectively the local knowledge is utilized. Leveraging the contribution assessment, we further develop a Reinforcement Learning-aided Large Neighbourhood Search Algorithm (RL-LNS) algorithm, which optimizes the submodel extraction scheme based on context-aware contribution information, thereby guiding the global model update more effectively. Leveraging the actor-critic scheme, the RL-LNS combines the strengths of Large Neighbourhood Search (LNS) and Reinforcement Learning (RL), improving the LNS’s search efficiency while simplifying the design of RL policies. To validate the RL-LNS, we have compared the FedShaplex against the state-of-the-art (SOTA) partial training-based approach MHFL, the global model performance, and its average accuracy on clients’ datasets.

In recent years, the rapid development of Deep Neural Networks (DNNs) has posed significant challenges in terms of training duration and costs. High-frequency, low-power photonic computing has emerged as a highly promising solution. However, the substantial cost of data conversion and the limitations introduced by noise in photonic devices continue to hinder the realization of high-precision and energy-efficient DNN training. To address this challenge, we propose a novel photonic accelerator, ROCKET, based on the Residue Number System (RNS). RNS is based on modular arithmetic and enables support for high-precision computation through parallel multi-path low-precision operations. First, we leverage specialized lookup tables to enable high-throughput, low-latency conversions between high-precision and low-precision numerical representations. Next, we design a low-power photonic accelerator architecture utilizing intensity modulators, which minimizes the number of computational components while maximizing data reuse. Subsequently, we propose a hybrid photonic-electronic pipelined dataflow to maximize parallelism within the photonic-electronic computation path. Finally, we develop a high-frequency (4.096 GHz) hybrid photonic-electronic prototype using FPGA, Radio Frequency (RF), and photonic components to validate the feasibility of the ROCKET. Our large-scale simulations on seven mainstream DNN models show that, compared to the A100 GPU, TPU v4, and the state-of-the-art photonic accelerator Mirage, ROCKET achieves speedups of 33×, 243×, and 198×, respectively, while saving energy by factors of 64×, 204×, and 142×.

To address the challenges of hardware heterogeneity in Federated Learning (FL), several model-heterogeneous FL schemes have been proposed based on the traditional model-homogeneous approaches. Among the state-of-the-art (SOTA) model-heterogeneous FL approaches, the Partial Training (PT) approach is considered one of the most promising approaches, where submodels are extracted from the global model for local training. However, existing studies focus on either the submodel extraction scheme or the creation of personalized submodels for each client, which lack global model updating or introduce high computational complexity. This can result in poor adaptability, especially in edge computing environments with Non-IID data distribution. In this paper, we presented CDPFL, Contribution-Driven Personalization for Model Heterogeneous Federated Learning, in which the contributions made by the local clients to the global model are evaluated using the Shapley Value. Using the contribution information, Gate Recurrent Unit (GRU) is then used to determine the weight of each client in the next round of model aggregation. In this way, CDPFL is capable of controlling the update of the global model based on the contribution information. To evaluate CDPFL, we compare it against the SOTA PT-based methods. Experimental results show that our approach achieves an improvement of up to 10.17% in global model accuracy under high data heterogeneity scenarios and consistently outperforms all baselines in both high and low heterogeneity scenarios.

To enhance the precision of inference, deep neural network (DNN) models have been progressively growing in scale and complexity, leading to increased latency and computational resource demands. This growth necessitates scalable architectures, such as chiplet-based accelerators, to accommodate the substantial volume of deep learning inference tasks. However, the efficiency, energy consumption, and scalability of existing accelerators are severely constrained by metallic interconnects. Photonic interconnects, on the contrary, offer a promising alternative, with their advantages of low latency, high bandwidth, high energy efficiency, and simplified communication processes. In this paper, we propose ChipAI, an accelerator designed based on photonic interconnects for accelerating DNN inference tasks. ChipAI implements an efficient hybrid optical network that supports effective inter-chiplet and intra-chiplet data sharing, thereby enhancing parallel processing capabilities. Additionally, we propose a flexible dataflow leveraging the ChipAI architecture and the characteristics of DNN models, facilitating efficient architectural mapping of DNN layers. Simulation on various DNN models demonstrates that, compared to the state-of-the-art chiplet-based DNN accelerator with photonic interconnects, ChipAI can reduce the DNN inference time and energy consumption by up to 82% and 79%, respectively.

Session-based Recommender Systems (SBRSs) aim to recommend the next item to users based on their historical interactions with items within or between sessions. A session is constituted by a sequence of interactions between the user and items within a continuous period. Existing SBRSs often focus on modeling co-occurrence-based inter-item transitions within or between sessions only. They generally overlook intrinsic inter-item semantic relations. Specifically, in practice, many items are substitutable or complementary to each other. Such relations provide significant signals to guide user interaction behaviors as well as the next-item recommendations. Moreover, existing works overlook the fact that user behaviors are driven simultaneously by both user intent and item attributes, failing to consider the implicit item characteristics embedded within. Such practice leads to entangled user intent and latent item characteristics, bringing unnecessary interference between these two aspects, impeding accurate modeling of each aspect, ultimately significantly impeding recommendation performance. To bridge these gaps, we propose a novel framework called S emantic relation guided dual-view C ontrastive L earning for S ession-based R ecommendations (SCL-SR). SCL-SR introduces a novel semantic relation-guided contrastive learning module to capture additional supervision signals from both user intent view and item attribute view to guide the next-item prediction better. Then, we propose a novel intent-attribute disentangler to effectively mitigate the interference between user intent and latent item characteristics for further improving the recommendation performance. Extensive experiments on three real-world datasets demonstrate the significant superiority of SCL-SR over the state-of-the-art approaches, including achieving substantial improvements ranging from 7.10% to 12.82% on the Tmall dataset. Our source code and datasets are available at https://github.com/Nishikata97/SCL-SR .

This paper introduces a cooperative and decentralized collision avoidance algorithm (CoDe) for small-scale UAV swarms consisting of up to three UAVs. CoDe improves energy efficiency of UAVs by achieving effective cooperation among UAVs. Moreover, CoDe is specifically tailored for UAV’s operations by addressing the challenges faced by existing schemes, such as ineffectiveness in selecting actions from continuous action spaces and high computational complexity. CoDe is based on Multi-Agent Reinforcement Learning (MARL), and finds cooperative policies by incorporating a novel credit assignment scheme. The novel credit assignment scheme estimates the contribution of an individual by subtracting a baseline from the joint action value for the swarm. The credit assignment scheme in CoDe outperforms other benchmarks as the baseline takes into account not only the importance of a UAV’s action but also the interrelation between UAVs. Furthermore, extensive experiments are conducted against existing MARL-based and conventional heuristic-based algorithms to demonstrate the advantages of the proposed algorithm.

While LoRa networks typically handle very infrequent communications, they can occasionally encounter sudden data bursts in response to unpredictable events such as a forest fire or volcanic eruption. LoRaWAN, the MAC protocol for LoRa, lacks a collision avoidance mechanism due to the severe energy constraints of the nodes. Burst traffic can result in substantial collisions, retransmissions, and packet loss when dealing with burst traffic, leading to rapid depletion of node batteries, increased network latencies, and significantly degraded throughput. In this paper, we propose Burst-MAC, a low-overhead MAC protocol for LoRa networks to efficiently handle burst traffic. When the network traffic is light and infrequent, Burst-MAC operates just like LoRaWAN. Upon detecting a data burst, it switches to burst mode that functions as follows: (i) nodes with bursty data are organized into virtual groups based on channel and spreading factor, and (ii) nodes within each group transmit in a semi-distributed TDMA fashion with each node determining its transmission time slots using a hash function to eliminate the need for centralized schedule distribution. Hash function collisions are resolved through piggybacking with acknowledgements from the gateway, ensuring bounded latencies for transmitted packets. We evaluate Burst-MAC through both physical experiments on LoRa devices and NS-3 simulations under various burst scenarios. Our results demonstrate that Burst-MAC significantly outperforms LoRaWAN and other baselines in several aspects, including a $4.5 \times$ improvement in packet reception rate, up to $6 \times$ reduction in energy consumption, and up to $2.5 \times$ decrease in latency.

The traditional slow-start mechanism in TCP can result in slow ramping-up of the data delivery rate, inefficient bandwidth utilization, and prolonged completion time for small-size flows, especially in networks with a large bandwidth-delay product (BDP). Existing solutions either only work in specific situations, or require network assistance, making them challenging (if even possible) to deploy. This paper presents SUSS (Speeding Up Slow Start): a lightweight, sender-side add-on to the traditional slow-start mechanism, that aims to safely expedite the growth of the congestion window when a flow is significantly below its optimal fair share of the available bandwidth. SUSS achieves this by accelerating the growth in cwnd when exponential growth is predicted to continue in the next round. SUSS employs a novel combination of ACK clocking and packet pacing to effectively mitigate traffic burstiness caused by accelerated increases in cwnd. We have implemented SUSS in the Linux kernel, integrated into the CUBIC congestion control algorithm. Our real-world experiments span many device types and Internet locations, demonstrating that SUSS consistently outperforms traditional slow-start with no measured negative impacts. SUSS achieves over 20% improvement in flow completion time in all experiments with flow sizes less than 5MB and RTT larger than 50 ms.

With the development of Fifth Generation (5G)/Sixth Generation (6G) -enabled Internet of Things (IoT) networks, different user equipment (UE) dynamically generates massive raw data and delay-sensitive computation tasks to be offloaded and processed at the mobile edge computing (MEC) nodes. In this paper, we propose a comprehensive digital twin-empowered UAV-assisted edge intelligent IoT framework, which enables UEs to offload their delay-sensitive tasks to a UAV-assisted MEC node. We aim to minimise the maximum total service delay including the transmission delay and the processing delay among all UEs. A deep deterministic policy gradient-based offloading and resource allocation optimisation algorithm, named (DDPG-ORAO), is proposed to optimise task offloading decisions among all UEs, which jointly optimising the communication and computation resources allocation among all UEs and all UAV-assisted MEC nodes. Simulation results show that our proposed optimisation algorithm outperforms the benchmarks in terms of the total service delay of all UEs.

Radio links in Wireless Body Area Networks (WBANs) are highly subject to short and long-term attenuation due to the unstable network topology and frequent body blockage. This instability makes it challenging to achieve reliable and energy-efficient communication, but on the other hand, provides a great potential for the sending nodes to dynamically schedule the transmissions at the time with the best-expected channel quality. Motivated by this, we propose IGE (Improved Gilbert-Elliott Markov chain model), a memory-efficient Markov chain model to monitor channel fluctuations and provide a long-term channel prediction. We then design ATPS (Adaptive Transmission Power Selection), a deadline-constrained channel scheduling scheme that enables a sending node to buffer the packets when the channel is bad and schedule them to be transmitted when the channel is expected to be good within a deadline. ATPS can self-learn the pattern of channel changes without imposing a significant computation or memory overhead on the sending node. We evaluate the performance of ATPS through experiments using TelosB motes under different scenarios with different body postures and packet rates. We further compare ATPS with several state-of-the-art schemes including the optimal scheduling policy in which the optimal transmission time for each packet is calculated based on the collected RSSI (Received Signal Strength Indicator) samples in an off-line manner. The experimental results reveal that ATPS performs almost as efficiently as the optimal scheme in high-date-rate scenarios and has a similar trend on power level usage.

This paper presents a novel solution to address the challenges in achieving energy efficiency and cooperation for collision avoidance in UAV swarms. The proposed method combines Artificial Potential Field (APF) and Particle Swarm Optimization (PSO) techniques. APF provides environmental awareness and implicit coordination to UAVs, while PSO searches for collision-free and energy-efficient trajectories for each UAV in a decentralized manner under the implicit coordination. This decentralized approach is achieved by minimizing a novel cost function that leverages the advantages of the active contour model from image processing. Additionally, future trajectories are predicted by approximating the minima of the novel cost function using calculus of variation, which enables proactive actions and defines the initial conditions for PSO. We propose a two-branch trajectory planning framework that ensures UAVs only change altitudes when necessary for energy considerations. Extensive experiments are conducted to evaluate the effectiveness and efficiency of our method in various situations.

Federated Learning (FL) has emerged as a promising collaborative learning paradigm that enables to train machine learning models across decentralized devices, while keeping the training data localized to preserve user privacy. However, the heterogeneity in both decentralized training data and distributed computing resources has posed significant challenges to the design of effective and efficient FL schemes. Most existing solutions either focus on tackling a single type of heterogeneity, or are unable to fully support model heterogeneity with low communication overhead, fast convergence, and good interpretability. In this paper, we present CloREF, a novel rule-based collaborative learning framework that allows devices in FL to use completely different local learning models to cater to both data and resource heterogeneity. In CloREF, each rule is represented as a linear model, which provides good interpretability. Each participating device chooses a local model and trains it using its local data. The decision boundary of each trained local model is then approximated using a set of rules, which effectively bridges the gap arising from model heterogeneity. All participating devices collaborate to select the optimal set of rules as the global model, employing evolutionary optimization to effectively fuse the knowledge acquired from all local models. Experimental results on both synthesized and real-world datasets demonstrate that the rules generated by our proposed method can mimic the behaviors of various learning models with high fidelity ($\gt $0.95 in most tests), and CloREF gives competitive performance in accuracy, AUC, and communication overhead, compared with both the best-performing model trained centrally and several state-of-the-art model-heterogeneous federated learning schemes.

All-gather collective communication is one of the most important communication primitives in parallel and distributed computation, which plays an essential role in many high performance computing (HPC) applications such as distributed Deep Learning (DL) with model and hybrid parallelisms. To solve the communication bottleneck of All-gather, optical interconnection network can provide unprecedented high bandwidth and reliability for data transfer among the distributed nodes. However, most traditional All-gather algorithms are designed for electrical interconnection, which cannot fit well for optical interconnect systems, resulting in poor performance. This paper proposes an efficient scheme, called OpTree, for All-gather operation on optical interconnect systems. OpTree derives an optimal m-ary tree corresponding to the optimal number of communication stages, which achieves the minimum communication time. We further analyze and compare the communication steps of OpTree with existing All-gather algorithms. Theoretical results exhibit that OpTree requires much less number of communication steps than existing All-gather algorithms on optical interconnect systems. Simulation results show that OpTree can reduce communication time by 72.21 %, 94.30%, and 88.58% compared to three existing All-gather schemes Wrht, Ring, and NE, respectively.

Communication efficiency is crucial for accelerating distributed deep neural network (DNN) training. All-reduce, a vital communication primitive, is responsible for reducing model parameters in distributed DNN training. However, most existing All-reduce algorithms, designed for traditional electrical interconnect systems, fall short due to bandwidth limitations. Optical interconnects, with superior bandwidth, low transmission delay, and less power consumption, emerge as viable alternatives. We propose Wrht (Wavelength Reused Hierarchical Tree), an efficient scheme for implementing the All-reduce operation in optical interconnect systems. Wrht leverages wavelength-division multiplexing (WDM) to minimize the communication time in distributed data-parallel DNN training. We calculate the required wavelengths, minimum communication steps, and optimal communication time, considering optical communication constraints. Simulations with real-world DNN models indicate that Wrht notably reduces communication time. On average, compared with three conventional All-reduce algorithms, Wrht achieves reductions of 65.23%, 43.81%, and 82.22% respectively in optical interconnect systems, and 61.23% and 55.51% compared with two algorithms in electrical systems. This highlights Wrht’s potential to enhance communication efficiency in DNN training using optical interconnects.

The continuous increase in GPU performance benefits a wide range of high-performance computing (HPC) applications. Slower growth of transistor density and limited size of chip die are now posing significant challenges to scale GPUs. The chiplet technology provides a potential solution to surpass these limitations. However, the performance of these chiplet-based GPUs is often constrained by the metallic-based interconnects between the chiplets. Emerging technologies such as photonic interconnect can overcome the limitations of metallic interconnects, offering several superior properties, such as high bandwidth density and low energy consumption. In this paper, we propose SEECHIP: a Scalable and Energy-Efficient CHIPlet-based GPU architecture using photonic links. SEECHIP introduces a novel photonic inter-chiplet network that supports both unicast and broadcast communication, providing the same transmission bandwidth at both the sending and receiving ends. In addition, we propose a tailored hierarchical memory architecture, which is more suitable for the parallelization of general-purpose HPC applications. Simulation results using 14 benchmarks show that SEECHIP can achieve and reduction in execution time and energy consumption, respectively, as compared to other GPUs with metallic or photonic interconnects. Simulation results also show that SEECHIP has good scalability compared with the other GPUs.

All-reduce is the crucial communication primitive to reduce model parameters in distributed Deep Neural Networks (DNN) training. Most existing all-reduce algorithms are designed for traditional electrical interconnect systems, which cannot meet the communication requirements for distributed training of large DNNs due to the low data bandwidth of the electrical interconnect systems. One of the promising alternatives for electrical interconnect is optical interconnect, which can provide high bandwidth, low transmission delay, and low power cost. We propose an efficient scheme called WRHT (Wavelength Reused Hierarchical Tree) for implementing all-reduce operation in optical interconnect systems. WRHT can take advantage of WDM (Wavelength Division Multiplexing) to reduce the communication time of distributed data-parallel DNN training. Simulations using real DNN models show that, compared to all-reduce algorithms in the electrical and optical network systems, our approach reduces communication time by 75.76% and 91.86%, respectively.

Abstract The dynamical performance of vehicles on railway tracks is significantly influenced by wheel‐rail interactions, which makes the wheel‐rail force be a safety indicator of vehicle systems. Owing to the high cost of direct measurement, inversion models are widely used to measure the wheel‐rail force. This study proposes a model called the Lightweight Wheel‐Rail Force Inversion Model (LFIM) to calculate the wheel‐rail force by using vibration signals collected from the vehicle system. The model can extract the relevant features, and outperforms prevalent models. It is also resource efficient and small in size, which makes it suitable for edge computing environment. The basic LFIM yielded a correlation coefficient of 0.99 in experiments, significantly higher than the value recorded by the traditional dynamic methods. The compressed LFIM yielded a 91% reduction in floating‐point operations (FLOPs) and had an R2 score of 90%, which satisfies the demands for vehicle monitoring. By balancing accuracy and size, LFIM is a feasible model to deploy on edge devices to monitor the wheel‐rail force in real‐time and assess the safety of railway vehicles.

Optical network-on-chip (ONoC) is an emerging chip-scale optical interconnection technology to realize high-performance and power-efficient intercore communication for many-core processors. Multicast communication is popularly used in parallel applications on chip. However, existing researches for multicast in ONoC mainly focus on the optimization of one multicast. This limits the practical applications of the research outcomes because we often face the dynamic formation of multiple multicast groups in real network systems. In this article, we define the problem of routing and wavelength assignment for multiple multicasts in ONoC with the objective of minimizing the number of wavelengths required. To solve the problem, we first formulate it as an integer programming model for general topologies. Then we design routing policies for special instances that optimally use only one wavelength on mesh topology. For general instances, we design a group-partitioning routing algorithm for multiple multicasts (GPRMM). GPRMM decouples a group of multicasts into a number of subgroups, each of which matching one of the special instances. Theoretical results show that the number of wavelengths required by GPRMM is no more than the Destination Density$\sigma _{d}$, i.e., the maximum number of multicasts with destinations in the same row or column. Moreover, we find the upper bound and the lower bound on the number of wavelengths required for GPRMM. The wavelength requirement is also upper bounded by the network size$n$for an$n\times n$mesh network. Simulation results show that GPRMM can reduce the number of wavelengths by 26.7% compared with previous methods. GPRMM has the advantages of low routing complexity, low wavelength requirement, low power consumption, and good scalability.

Deep Neural Networks (DNNs) have demonstrated great success in many fields such as image recognition and text analysis. However, the ever-increasing sizes of both DNN models and training datasets make deep leaning extremely computation- and memory-intensive. Recently, photonic computing has emerged as a promising technology for accelerating DNNs. While the design of photonic accelerators for DNN inference and forward propagation of DNN training has been widely investigated, the architectural acceleration for equally important backpropagation of DNN training has not been well studied. In this paper, we propose a novel silicon photonic-based backpropagation accelerator for high performance DNN training. Specifically, a general-purpose photonic gradient descent unit named STADIA is designed to implement the multiplication, accumulation, and subtraction operations required for computing gradients using mature optical devices including Mach-Zehnder Interferometer (MZI) and Mircoring Resonator (MRR), which can significantly reduce the training latency and improve the energy efficiency of backpropagation. To demonstrate efficient parallel computing, we propose a STADIA-based backpropagation acceleration architecture and design a dataflow by using wavelength-division multiplexing (WDM). We analyze the precision of STADIA by quantifying the precision limitations imposed by losses and noises. Furthermore, we evaluate STADIA with different element sizes by analyzing the power, area and time delay for photonic accelerators based on DNN models such as AlexNet, VGG19 and ResNet. Simulation results show that the proposed architecture STADIA can achieve significant improvement by 9.7× in time efficiency and 147.2× in energy efficiency, compared with the most advanced optical-memristor based backpropagation accelerator.

The continuing increase in the incidence and recognition of children's sleep disorders has heightened the demand for automatic pediatric sleep staging. Supervised sleep stage recognition algorithms, however, are often faced with challenges such as limited availability of pediatric sleep physicians and data heterogeneity. Drawing upon two quickly advancing fields, i.e., semi-supervised learning and self-supervised contrastive learning, we propose a multi-task contrastive learning strategy for semi-supervised pediatric sleep stage recognition, abbreviated as MtCLSS. Specifically, signal-adapted transformations are applied to electroencephalogram (EEG) recordings of the full night polysomnogram, which facilitates the network to improve its representation ability through identifying the transformations. We also introduce an extension of contrastive loss function, thus adapting contrastive learning to the semi-supervised setting. In this way, the proposed framework learns not only task-specific features from a small amount of supervised data, but also extracts general features from signal transformations, improving the model robustness. MtCLSS is evaluated on a real-world pediatric sleep dataset with promising performance (0.80 accuracy, 0.78 F1-score and 0.74 kappa). We also examine its generality on a well-known public dataset. The experimental results demonstrate the effectiveness of the MtCLSS framework for EEG based automatic pediatric sleep staging in very limited labeled data scenarios.

Radio links in wireless body area networks (WBANs) suffer from both short-term and long-term variations due to the dynamic network topology and frequent blockage caused by body movements, making it challenging to achieve reliable, energy-efficient and real-time data communication. Through experiments with TelosB motes, we observe a strong positive relationship between the channel quality and the location of the sensor node relative to the gateway. Motivated by this observation, we design Tuatara, a novel power-aware communication protocol that allows each sensor node to dynamically adjust its transmission power based on the channel status inferred from its instant location, aiming to save energy, reduce interference, and improve communication reliability. Combining the orientations measured by motion sensors with the anatomical constraints of body movements, each sensor node can locally estimate its instant location relative to the gateway. Based on a probabilistic model, power level selection is converted to calculate the optimal probability of selecting each power level at a given location, with the objective of minimizing the transmission cost. A learning scheme is designed to adaptively update the power level selection probabilities, making Tuatara self-adaptable to changes in the signal propagation environment. Experimental results demonstrate that Tuatara outperforms the state-of-the-art protocols in various scenarios, with performance close to that of the optimal power selection solution even in scenarios where the packet rate is very low.

The imbalanced data classification problem widely exists in many real-world applications. Data resampling is a promising technique to deal with imbalanced data through either oversampling or undersampling. However, the traditional data resampling approaches simply take into account the local neighbor information to generate new instances in linear ways, leading to the generation of incorrect and unnecessary instances. In this study, we propose a new data resampling technique, namely, Gaussian Distribution based Oversampling (GDO), to handle the imbalanced data for classification. In GDO, anchor instances are selected from the minority class instances in a probabilistic way by taking into account the density and distance information carried by the minority instances. Then new minority instances are generated following a Gaussian distribution model. The proposed method is validated in experimental study by comparing with seven imbalanced learning approaches on 40 data sets from the KEEL repository and 10 large data sets from the UCI repository. Experimental results show that our method outperforms the other compared methods in terms of AUC, G-mean and memory usage with an increase in running time. We also apply GDO to deal with two real imbalanced data classification problems: Internet video traffic identification and metastasis detection of esophageal cancer. The experimental results once again validate the effectiveness of our approach.

Downlink mobile edge computing (MEC) networks are requiblack to serve increasing large number of Internet of Things (IoT) devices with limited battery capacity. In order to serve massive user equipments with low power consumption requirements, in this paper, we propose an energy-efficient multi-carrier non-orthogonal multiple access (MC-NOMA) design which allows more than two IoT devices to multiplex and access the same subcarrier band. With the aim to minimize the total transmit energy while meeting the demands of each IoT device such as the low latency, in our design, we first derive the optimal successive interference cancellation (SIC) policy and minimum power allocated to every IoT device. Then we propose an optimal greedy algorithm to allocate the frequency blocks, and formulate the optimization of the computational resource allocation as a min-max problem. Subsequently, we characterize the MC-NOMA network with the potential game model, and present a scheduling scheme to manage massive IoT devices. Simulation results demonstrate that our proposed scheme can consume 3-10 dB less energy in a MEC network deployed with 256 IoT devices compablack with the conventional orthogonal multiple access (OMA) scheme and non-orthogonal multiple access (NOMA) scheme.

Digital beamforming (DBF) with full Radio-Frequency (RF) complexity requires a separate RF chain per transmit antenna, which is not only difficult to realize for large-scale MIMO systems but also vulnerable to hardware imperfection. In this paper, we show that DBF architectures don’t necessarily require the number of RF chains to be the same as the number of transmit antennas. We propose a low RF-complexity transmit DBF architecture that enables to use a small number of RF chains to serve a large number of transmit antennas. In our architecture, the transmit antennas are divided into groups. All antennas in the same group share the same RF chain in a time-multiplexed manner to preserve the signal from baseband till the antenna aperture. A novel antenna grouping algorithm is proposed to dynamically group the transmit antennas in a way that each antenna group forms a close-to-rank-one channel matrix with the receive antennas. Under ideal hardware conditions, we show that our DBF architecture can achieve nearly the same performance as that of the conventional full RF-complexity DBF in terms of bandwidth and spectral efficiency. However, when hardware imperfection is considered, our architecture outperforms full RF-complexity DBF in both spectral and energy efficiency because it is more robust to inter RF-chain cross-talk effects due to the reduction on the number of required RF chains.

Malware detection has attracted widespread attention due to the growing malware sophistication. Machine learning based methods have been proposed to find traces of malware by analyzing network traffic. However, network traffic exhibits a series of growing and changing states, which makes it challenging to design a detection model that can detect malicious traffic over a long period without the need for costly retraining. In this paper, we present, IEdroid, an Android malicious network behavior detection method that leverages incremental ensembles for model update. Specifically, we train multiple classifiers to form an interim ensemble in distributed cluster environment, and update the interim ensemble by removing and adding classifiers. The generated model is composed of multiple interim ensembles that can adapt to the network traffic. We evaluated the performance of IEdroid using a dataset consisting of 98,565 benign and 41,267 malicious flows. Results show that IEdroid can effectively detect malicious traffic compared with state-of-the-art detection models. The experiment trained IEdroid on datasets incrementally for 10 times without a significant loss on accuracy, precision, recall, and F-Measure, compared with re-training from scratch with full data.

Conventional full digital transmit beamforming requires a separate Radio-Frequency (RF) chain per transmit antenna, which is not easy to realize for large-scale antenna systems due to the high hardware cost, system complexity and power consumption. In this paper, we propose a new scheme that enables full digital transmit beamforming with low RF complexity. We consider a multiple-input-multiple-output (MIMO) system with N transmit antennas and M receive antennas where N > M, and transmit antennas are connected to L RF chains, where L <; N. In our scheme, transmit antennas are dynamically divided into L groups based on the multipath channel spatial correlation profile. The beamforming gain is achieved by letting highly correlated antennas in the same group. Each group of antennas is connected to one out of L RF chains and each group transmits an independent data stream. RF chain is designed in such a way that it independently preserves baseband signals of a group of antennas in a time-division-multiplexing (TDM) way. Our scheme is evaluated in simulations by comparing with full RF complexity digital transmit beamforming. Simulation results demonstrate that, our proposal is suitable for doubly massive MIMO systems, particularly in line-of-sight (LOS) scenarios.

TCP slow-start grows the congestion window exponentially, aims to quickly probe the throughput of the network path. Stopping this growth at the wrong time can affect the overall network performance. In this paper, we introduce StopEG, an efficient mechanism to accurately and quickly detect when to stop this exponential growth. StopEG reacts to the changes on congestion window size rather than traditional congestion signals such as packet loss. We show that theoretically the number of inflight packets in the forward path is no more than 56.8% of all the inflight packets when the bottleneck link is unsaturated, and use this value as the threshold to stop the exponential growth. StopEG is evaluated through simulations in ns-3 by incorporating it into Google's BBR congestion control algorithm. Simulation results demonstrate its effectiveness in BBR, with a reduction of ≈68% in the length of the bottleneck queue when new connections are initiated.

While more and more antennas are integrated into a single mobile user equipment to increase communication quality and throughput, the number of antennas used for transmission is commonly restricted due to the concerns on hardware complexity and energy consumption, making it impossible to achieve the maximum channel capacity. This paper investigates the problem of reconstructing the full downlink channel from incomplete uplink channel measurements in Massive MIMO systems. We present ARDI, a scheme that builds a bridge between radio channel and physical signal propagation environment to link spatial information about the non-transmitting antennas with their radio channels. By inferring locations and orientations of the non-transmitting antennas from an incomplete set of uplink channels, ARDI can reconstruct the downlink channels for non-transmitting antennas. We derive closed-form solution to reconstruct antenna orientation in both single-path and multipath propagation environments. The performance of ARDI is evaluated using simulations with realistic human movement. The results demonstrate that ARDI is capable of accurately reconstructing full downlink channels when the signal-to-noise ratio is higher than 15dB, thereby expanding the channel capacity of Massive MIMO networks.

Radio links in wireless body area networks (WBANs) commonly experience highly time-varying attenuation due to the dynamic network topology and frequent occlusions caused by body movements, making it challenging to design a reliable, energy-efficient, and real-time communication protocol for WBANs. In this article, we present Chimp, a learning-based power-aware communication protocol in which each sending node can self-learn the channel quality and choose the best transmission power level to reduce energy consumption and interference range while still guaranteeing high communication reliability. Chimp is designed based on learning automata that uses only the acknowledgment packets and motion data from a local gyroscope sensor to infer the real-time channel status. We design a new cost function that takes into account the energy consumption, communication reliability and interference and develop a new learning function that can guarantee to select the optimal transmission power level to minimize the cost function for any given channel quality. For highly dynamic postures such as walking and running, we exploit the correlation between channel quality and motion data generated by a gyroscope sensor to fastly estimate channel quality, eliminating the need to use expensive channel sampling procedures. We evaluate the performance of Chimp through experiments using TelosB motes equipped with the MPU-9250 motion sensor chip and compare it with the state-of-the-art protocols in different body postures. Experimental results demonstrate that Chimp outperforms existing schemes and works efficiently in most common body postures. In high-date-rate scenarios, it achieves almost the same performance as the optimal power assignment scheme in which the optimal power level for each transmission is calculated based on the collected channel measurements in an off-line manner.

Manycore processor is becoming the mainstream platform for cloud computing applications. However, the design of high-performance and sustainable inter-core communication network is still a challenging problem. Optical Network on Chip (ONoC) is an emerging chip-scale optical communication technology with high bandwidth capacity and energy efficiency. In this paper, we present a Wavelength Reused Hierarchical ONoC architecture, WRH-ONoC. It leverages the nonblocking wavelength-routed λ-router and hierarchical networking to reuse the limited number of wavelengths. In WRH-ONoC, all the cores are grouped into multiple subsystems, and the cores in the same subsystem are directly interconnected using a λ-router for nonblocking communication. For inter-subsystem communication, all subsystems are further connected through multiple λ-routers and gateways in a hierarchical manner. Thus, the available wavelengths can be reused in different λ-routers. Furthermore, WRHm-ONoC, an efficient extension with multicast ability is also proposed. Given the numbers of cores and available wavelengths, we derive the minimum hardware requirement, the expected end-to-end delay, and the maximum data rate. Theoretical analysis and simulation results indicate WRH-ONoC achieves prominent improvement on the communication performance and sustainability, e.g., 46.0 percent of reduction on zero-load delay and 72.7 percent of improvement on throughput for 400 cores with the modest hardware/energy costs.

Recent studies show that real-time precise user localization enables to deliver accurate beamforming in MIMO systems without the need for channel estimation. This paper presents new solutions for accurate user localization in massive MIMO LTE systems. A key novelty of the developed schemes is the ability to locate users during LTE's random access channel synchronization procedure before they are connected to the network, by which the obtained location information can be immediately used to optimize the allocation of radio resource and perform accurate beamforming. To achieve this, the developed solutions leverage the advantages of spherical wave propagation since it allows simultaneously estimating the angle of arrival and the propagation distance from the user equipment to each antenna element in the base station. We design solutions for both single-path line-of-sight communication and multi-path propagation environments. The developed schemes were evaluated through both simulations and proof-of-concept experiments. Simulation results show that both algorithms can achieve decimeter-level localization accuracy using 64 and more antenna elements for the distances up to 300 meters. The proof-of-concept experiment justifies the feasibility of user localization based on the estimation of the shape of the incoming wavefront.

With the continuing-scaling of future multicore processors, the performance requirements on memory access has been put forward much higher. Memory- centric network is deemed as a promising communication paradigm for core-to-memory interconnect in future multicore processors. However, the traditional electrical interconnect has the drawbacks of limited capacity, high communication delay, poor scalability and low energy efficiency, which further limits the performance improvement of the system. To support high-performance communication for memory access, we propose the Testudo architecture, an optically connected memory-centric network (MCN), which utilizes the emerging optical interconnect technology and 3D-stacking memory technology to achieve high bandwidth, low power consumption and high scalability. Testudo is designed based on multiple optical crossbar organized in a torus- like topology. Each optical crossbar is in multiple-write- multiple-read construction, which provides high connectivity for IP cores. By employing an all optical, token-based arbitration scheme with low complexity, the memory access communication is contention-free. Simulation results show that Testudo improves the performance significantly compared to the electrical mesh topology.

For high-resolution massive MIMO and very large antenna arrays, wireless channel models have to scrutinize the detailed space features of the surrounding environment. Existing models such as WINNER and 3GPP are not appropriate for validating and evaluating new concepts for 4G/5G as they do not consider the spatial characteristics of the real environment. The simplified 3D shapes of simulated objects in geometry-based channel models, which are constructed using vertical and horizontal planes, may cause significant difference from the real channel. In this paper, we present an approach to model the specular reflection of a signal from an arbitrary inclined surface by taking into account the signal's polarization and a spatial distribution of massive MIMO antenna elements. The approach was validated through simulating LTE uplink transmissions in an environment modeled based on Google Maps. Results showed the importance of considering detailed 3D characteristics of the surroundings in simulations. We observed that even slightly inclined walls can have significant influence on channels in comparison with models with only vertical and horizontal surfaces due to different propagation paths, different angles of reflection, and different changes of polarizations.

Since radio links in wireless body area networks (WBANs) commonly experience highly time-varying attenuation due to topology instability, communication protocols with fixed transmission power cannot produce a very good performance in terms of energy consumption, interference range, and communication reliability. We explain that how channel behaviourcan be modelled using Markov Chain. Then, a power-adaptive communication protocol for WBANs is developed in which each sensor node can self-learn its channel and dynamically adjust itstransmission power. We evaluate our scheme through implementing the idea using the TelosB motes. The results demonstrate that our scheme can self-learn the channel behaviours, and reduce energy consumption and interference.

Indoor localisation systems have slowly become more and more accurate. Each localisation system needs tuning to affect reasonable performance. In this paper we propose CRAFT, a crowd sourced approach to constructing a WiFi fingerprint database. The method uses a temporarily deployment of a small number of anchor nodes to roughly locate the position of the WiFi sample. Through thorough experiments in a real-world building, CRAFT's error is 2.2 m a decrease of 25% when compare to other published results.

Summary The rapidly growing demand for accident‐free driving in intelligent transportation makes reliable broadcast a critical factor for vehicularad hocnetworks. Existing solutions always try to improve the broadcast reliability by retransmitting lost packets. However, the excessive retransmissions can easily cause unpredictable time delay and even broadcast storms, rendering the reliable broadcast problem unsolved. In this paper, a novel reliable broadcast scheme is proposed by exploring the advantages of lost data piggybacking. Our scheme allows all the vehicles to piggyback some received packets cooperatively to help other vehicles to recover the lost packets. We formulate the cooperative piggybacking problem as a cooperative offloading game and present a decentralized solution to compute the optimal data piggybacking solutions based on only partial network information. A reward‐penalty scheme is designed for the offloading process to impel all the vehicles' decisions that converge to the Nash equilibrium, which is proved to be the global optimal solution to the decentralized offloading scheme. Simulation results show that the proposed cooperative offloading scheme can achieve much higher broadcast reliability and lower propagation delay, in comparison with existing solutions. In a small vehicle network, all lost cooperative awareness messages can be successfully recovered within 25 ms after the initial broadcast by using the data traces generated by GEMV2. Copyright © 2016 John Wiley & Sons, Ltd.

Mobile opportunistic networking is a promising technology that can supplement existing cellular and WiFi networks to provide desirable services for smart and connected communities. Message routing is the most compelling challenge in mobile opportunistic networks due to the lack of contemporaneous end-to-end paths and the resource constraints at mobile devices. To improve the probability of successful message delivery, most existing routing schemes use the past contact history to predict future contacts for message forwarding, and exploit message replication and redundancy for multicopy routing. However, most existing prediction-based routing schemes simply use the average pairwise contact probability as the routing metric and neglect the benefits of exploring fine-grained contact information such as pairwise repeated contact patterns to improve the accuracy of predicting future contacts. Moreover, there is no efficient mechanism that can adaptively control message replication in a decentralized manner to achieve both high probability of successful message delivery and low message overhead. To address these problems, we present FGAR, a routing protocol designed for mobile opportunistic networks by leveraging fine-grained contact characterization and adaptive message replication. In FGAR, contact history is characterized in a fine-grained manner with timing information using a sliding window mechanism, and future contacts are predicted based on the fine-grained contact information, thereby improving the accuracy of contact prediction. We further design an efficient message replication scheme in which message replication is controlled in a fully decentralized manner by taking into account the expected message delivery probability, the replication history, and the quality of the encountered device. A replica is generated only when it is necessary to fulfill the expected message delivery probability. We evaluate our scheme through trace-driven simulations, and the simulation results show that FGAR outperforms existing schemes. In comparison with PRoPHET, FGAR can achieve more than 20% improvement on average on successful message delivery, whereas the message overhead has been reduced by a factor up to 15.

Various applications of indoor localisation (e.g. tracking firemen in a burning building, or navigation for the blind) require accurate location estimates. A common indoor localisation approach using commodity mobile phones is to perform trilateration with distance estimates derived from the strength of radio signals, however, they can vary wildly especially indoors. We propose a simple filtering technique to exclude measurements which adversely effect localisation accuracy. Through experimentation in a real building, across state of the art geometries and filtering techniques, our proposed filter shows an increase in accuracy by at least 30% and decrease the time taken to estimate the location by an order of magnitude.

Reliably broadcasting safety information to neighboring vehicles is a big challenge in vehicular ad-hoc networks (VANETs), due to the dynamic network topology and the unreliable wireless channels. In this paper we present two decentralized cooperative schemes to enhance broadcast reliability by exploiting the advantage of message piggybacking. The key idea is to let each vehicle optimally piggyback some messages it has received when broadcasting with the expectation that the neighboring vehicles can recover its lost messages through the piggybacked messages. We first present greedy piggybacking, in which each vehicle announces its lost messages to neighboring vehicles and makes piggybacking decisions based on message losses in its neighbors. We observed that some lost messages still cannot be successfully recovered in greedy piggybacking due to the asymmetric wireless communications, and further proposed a mutual learning based scheme to overcome the drawback of greedy piggybacking. We evaluated the performance of the two schemes through trace-driven simulations, and results show that both schemes can achieve significant improvement on broadcast reliability in VANETs in comparison with the existing solutions.

Pairwise contacts in Delay-Tolerant Networks (DTNs) for applications such as bus or smartphone based social networking commonly show some regular repeating patterns. Most existing routing protocols only implicitly exploit these patterns to predict future contacts. To enhance message delivery rate, most of the schemes allow messages to be replicated and forwarded to encountered nodes. However, there is no efficient mechanism for dynamically controlling message replication to achieve high message delivery rate with very low message overhead. In this paper, we present FGDR, a routing protocol designed for DTNs by leveraging fine-grained contact characterisation and dynamic message replication. In FGDR, the history contact is characterised in a fine-grained manner using a sliding window mechanism, and an up-to-date future contact prediction can be made based on the most recent history data. We design an efficient message replication scheme, in which replication is controlled in a fully decentralised manner by taking into account the expected message delivery rate, the replication history, and the quality of the encountered node. A replica can be generated only when it is necessary to fulfill the expected message delivery rate. We evaluate our scheme through trace-driven simulations, and results show FGDR can achieve much higher message delivery rate with lower message overhead in comparison with existing schemes.

The failure on all homogeneous devices due to the same reason is called homogeneous fault in networks. In contrast, heterogeneous platforms deployed simultaneously in the network are more robust against homogeneous faults. One of the challenging problems is how to design survivable networks that against homogeneous faults. This paper utilizes edge-colored graphs to investigate the network topology with homogeneous faults, in order to guarantee network connectivity using minimum number of links. Two types of network topologies are proposed on the edge-colored graph. One type of networks is characterized by the fact that all the edges of the same color form a Hamiltonian path or a Hamiltonian cycle. An upper bound on the number of colors used in the proposed network topologies is obtained. The network topologies of the second type have edges colored with at most five colors. Additionally, the subnetworks induced by the edges of two colors contain a Hamiltonian path, or a Hamilton cycle in some cases.

Optical Network on Chip (ONoC) is a promising technology for the next-generation many-core chip multiprocessors owing to its tremendous advantages in low power consumption, low communication delay, and high bandwidth. In this paper we present WRH-ONoC, a novel wavelength-reused hierarchical architecture that is capable of interconnecting thousands of cores using a limited number of wavelengths while providing extremely high-throughput data communication between connected cores. In WRH-ONoC, the cores are divided into small subsystems that are interconnected using multiple λ-routers and gateways in a hierarchical manner. Each λ-router can provide non-blocking parallel communication among the directly connected cores or gateways, and all λ-routers can reuse the limited number of available wavelengths. Communications between cores in different subsystems are routed via gateways in which optical signals can change their wavelengths via optical-electrical signal conversions. For a given number of cores, we give the minimum number of levels, λ-routers, and gateways required to interconnect these cores, and derive the expected end-to-end data communication delay under the Uniform-Poisson traffic pattern. Both theoretical analysis and simulation results demonstrate that WRH-ONoC can achieve significant improvement on performance and reduction on hardware cost in comparison with the existing solutions.

Real-time train localization using wireless sensor networks (WSNs) offers huge benefits in terms of cost reduction and safety enhancement in railway environments. A challenging problem in WSN-based train localization is how to guarantee timely communication between the anchor sensors deployed along the track and the gateway deployed on the train with minimum energy consumption. This paper presents an energy-efficient scheme for timely communication between the gateway and the anchor sensors, in which each anchor sensor runs an asynchronous duty-cycling protocol to conserve energy and wakes up only when it goes into the communication range of the gateway. A beacon-driven wake-up scheme is designed, and we establish the upper bound on the amount of time that an anchor sensor can sleep in one duty cycle to guarantee timely wake-up once a train approaches. We also give a thorough theoretical analysis for the energy efficiency of our scheme and give the optimal amount of time that an anchor sensor should sleep in terms of minimizing the total energy consumption at each anchor sensor. We evaluate the performance of our scheme through simulations, and results show that our scheme can wake up anchor sensors timely at a very low cost on energy consumption.

This paper investigates the problem of scheduling delay-constrained traffic in a single-hop wireless industrial network in which different source devices have different data rates. We aim to maximize the packet delivery reliability while meeting the deadline for each packet. The transmission scheduling problem is decomposed into two sub-problems: subperiod-based slot allocation and slot-based transmission scheduling. The former sub-problem is formulated as a nonlinear integer programming problem, and we present a solution with polynomial-time complexity by converting it to a linear integer programming problem. For the latter sub-problem, we demonstrate that the existence of a feasible optimal schedule depends on the order of the elements in the slot allocation vector produced by solving the former subproblem. An algorithm is designed to compute a feasible slot allocation that sustains a realizable schedule. Simulation results demonstrate that our scheme ensures each device has almost the same packet delivery rate in different report periods, which is important for maintaining the stability of control systems.

Research efforts into indoor localisation have focused on improving the accuracy of location estimates. In this paper, we propose a novel approach called SIB that uses RSSI values from low-power transmissions to exclude the noisy measurements from usual high-power RSSI measurements. SIB can effectively reduce the effect of noise in fingerprint-based localisation according to our analysis on the function of power loss ratio to transmission distance. Our results, based on evaluation in a real-world environment with noisy data, show a decrease in the geometric error of 85% in our indoor localisation.

Current peer-to-peer (P2P) file sharing methods in mobile ad hoc networks (MANETs) can be classified into three groups: flooding-based, advertisement-based, and social contact-based. The first two groups of methods can easily have high overhead and low scalability. They are mainly developed for connected MANETs, in which end-to-end connectivity among nodes is ensured. The third group of methods adapts to the opportunistic nature of disconnected MANETs but fails to consider the social interests (i.e., contents) of mobile nodes, which can be exploited to improve the file searching efficiency. In this paper, we propose a P2P content-based file sharing system, namely SPOON, for disconnected MANETs. The system uses an interest extraction algorithm to derive a node's interests from its files for content-based file searching. For efficient file searching, SPOON groups common-interest nodes that frequently meet with each other as communities. It takes advantage of node mobility by designating stable nodes, which have the most frequent contact with community members, as community coordinators for intracommunity searching, and highly mobile nodes that visit other communities frequently as community ambassadors for intercommunity searching. An interest-oriented file searching scheme is proposed for high file searching efficiency. Additional strategies for file prefetching, querying-completion, and loop-prevention, and node churn consideration are discussed to further enhance the file searching efficiency. We first tested our system on the GENI Orbit testbed with a real trace and then conducted event-driven experiment with two real traces and NS2 simulation with simulated disconnected and connected MANET scenarios. The test results show that our system significantly lowers transmission cost and improves file searching success rate compared to current methods.

Data centers host diverse applications with stringent QoS requirements. The key issue is to eliminate network congestions which severely degrade application performance. One effective solution is to balance the traffic load in the datacenter regular topologies. Many previous strategies focused on optimized flow routing, and these solutions can hardly achieve ideal load balance while guaranteeing QoS of different traffic flows due to the limitations in practical. In this paper, we discuss packet-level routing and analyze its merit for fine-grained load balance in data centers. Though packet-level routing interacts poorly with TCP in traditional network settings, we prove that it can be adapted to datacenter environment. Motived by the work done by Dixit [4] [5], we assert that packet-level routing is the right choice for data centers. Our simulation results demonstrate that packet-level routing better fulfills datacenter requirements.

Real-time train localization is essential to ensure the safety of modern railway transportation. This paper investigates the feasibility to achieve real-time and accurate train localization using wireless sensor networks. We carry out on-site experiments in a railway environment and demonstrate that Received Signal Strength Indicator (RSSI) is a good estimator for train localization. By combining the advantages of RSSI-based distance estimation and particle filtering techniques, we design a particle filter based train localization scheme and propose a novel Weighted RSSI Likelihood Function (WRLF) for updating the weights of particles. The proposed scheme is evaluated through simulations using the data obtained from the on-site measurements. Simulation results demonstrate that our scheme can achieve high localization accuracy, and is robust to changes in train speed and the deployment density of anchor sensors.

Most existing history-based routing protocols for delay tolerant networks resort to coarse-grained encounter information for making message forwarding decisions. However, this coarse-grained information can not give precise expression of the contact patterns between nodes in the network, thereby leading to inaccurate forwarding decisions. In this paper, we present FG-PRoPHET, a probabilistic routing scheme based on fine-grained contact characterization. Each node in FG-PRoPHET uses a slotted sliding window mechanism to maintain the information of historical contacts, by which new contact information can be quickly incorporated and outdated history data can be easily removed. The granularity of collected history data can be controlled by adjusting the size of the sliding window to reflect the contact patterns. Based on the fine-grained contact statistics, a greedy forwarding scheme is designed by combining the advantages of contact duration based forwarding and quota-based routing. The performance of FG-PRoPHET was evaluated through extensive simulations, and results show that, compared with existing schemes, FG-PRoPHET can significantly enhance message delivery rate with very low communication overhead.

Convergecast, in which data from a set of source devices is delivered to a single data sink, is a critical functionality in networks deployed for industrial monitoring and control. We address the latency-optimal link scheduling problem for convergecast in networks operating according to the recent WirelessHART standard. When there is no restriction on the number of channels, we present a latency-optimal scheduling policy in which each routing node is required to buffer at most one packet at any point in time. For networks with a limited number of channels, we first establish a lower bound on the number of channels for latency-optimal convergecast and a lower bound on latency for convergecast using a fixed number of channels, and then present a heuristic scheme for channel-constrained latency-optimal convergecast scheduling. Simulation results confirm that, at much modest computational cost, our heuristic scheme can construct convergecast schedules with latency close to that of the optimal schedules.

Next Generation Wireless Networks (NGWNs) are expected to provide high data rate and optimized quality of service to multimedia and real-time applications over the Internet Protocol (IP) networks. To achieve these goals, handover plays a very critical role in maintaining the seamless connectivity when mobile terminals move across different cells or networks. In this paper, we propose a novel scheme compliant with the IEEE 802.21 standard for handover in an integrated scenario with UMTS and WiMAX networks. We use the call quality, measured using Mean Opinion Score (MOS), as the major metric for handover optimization. We compare the proposed MOS-based handover scheme with the traditional RSS-based handover scheme. The numerical results demonstrate that our proposed scheme can maintain high call quality and reduce the probabilities for both handover dropping and call dropping.

Reliability and real-timeliness of wireless communications are the major concerns that hamper the wide deployment of wireless technologies for mission- and time-critical applications. This paper investigates the problem of maximizing transmission reliability of delay constrained traffic in a single-hop network by exploring the advantages of TDMA and Slotted Aloha. In our scheme, each time slot is either exclusively allocated to a dedicated node or shared by a group of nodes. All nodes sharing the same time slot operate based on the Slotted Aloha protocol. The key problem we address is: given a delay constraint, how to construct the transmission schedule by allocating the dedicated and shared slots in such a way that the probability that all packets are received at the destination is maximized. We show that the optimal schedules have some good structures, and propose both optimal and heuristic scheduling schemes. Numerical simulation results demonstrate that our schemes significantly outperform the traditional TDMA scheduling scheme in which time slots are all exclusively allocated. Moreover, our heuristic scheme can construct schedules with success probability coming very close to the optimal schedules at much more modest computational cost.

Unlike the conventional routing techniques in the Internet where routing privileges are given to trustworthy and fully authenticated nodes, Delay Tolerant Networks (DTNs) allow any node to participate in routing due to the lack of consistent infrastructure and central administration. This creates new security challenges as even authorized nodes in DTNs could inject several malicious threats against the network. This paper investigates novel solutions based on the Spray-and-Wait (SnW) routing protocol for mitigating black hole attacks in DTNs. A new knowledge-based routing scheme, called Trust-Based Spray- and-Wait protocol (TB-SnW), is proposed. The routing decisions in TB-SnW protocol are made based on the trust levels that are computed at each node using its historic routing records. Simulation results show that the TB-SnW protocol can achieve better performance in terms of mitigating Byzantine attacks and reducing message delivery delay compared with the Spray-and-Wait protocol.

This paper studies the problem of optimal forwarding for reliable and energy-efficient real-time communication over multi-hop wireless lossy networks. We impose a strict per-packet latency bound and develop forwarding policies that maximize the probability that the packet is delivered within the specified deadline minus a transmission energy cost. A solution to this problem allows to characterize the set of achievable latency-reliability pairs and to trace out the Pareto frontier between achievable deadline-constrained reliability and transmission energy cost. We develop dynamic programming-based solutions under a finite-state Markov channel model. Particular instances with Bernoulli and Gilbert-Elliot loss models that admit numerically efficient solutions are discussed and our results are demonstrated on several examples.

Current P2P file sharing methods in mobile ad hoc networks (MANETs) can be classified into three groups: flooding-based, advertisement-based and social contact-based. The first two groups of methods can easily generate high overhead and low scalability, and the third group fails to consider the social interests (content) of mobile nodes, which otherwise can improve file searching efficiency. In this paper, we propose a P2P content-based file sharing system for MANETs. The system uses an interest extraction algorithm to derive a node's interests from its files for complex queries. For efficient file searching, it groups common-interest nodes that frequently meet with each other as communities. Further, it takes advantage of node mobility by designating stable nodes, which has frequent contact with community members, as community coordinators for intra-community searching, and highly-mobile nodes as community ambassadors for inter-community searching. An interest-oriented file searching scheme further enhances the file searching success rate. We first deployed our system on the real-world GENI Orbit testbed with a real trace and then conducted experiment on the ns2 simulator with both real trace and simulated disconnected and connected MANET scenario. The test results show that our system significantly lowers transmission cost and improves file searching success rate compared to current methods.

Achieving low-power operation in wireless sensor networks with high data load or bursty traffic is challenging. The hidden terminal problem is aggravated with increased amounts of data in which traditional backoff-based contention resolution mechanisms fail or induce high latency and energy costs. We analyze and optimize Strawman, a receiver-initiated contention resolution mechanism that copes with hidden terminals. We propose new techniques to boost the performance of Strawman while keeping the resolution overhead small. We finally validate our improved mechanism via experiments.

Next Generation Wireless Networks (NGWNs) focus on convergence of different Radio Access Technologies (RATs) providing good Quality of Service (QoS) for applications such as Voice over IP traffic (VoIP) and video streaming. The voice applications over IP networks are growing rapidly due to their increasing popularity and cost. To meet the demand of providing high-quality of VoIP at anytime and from anywhere, it is imperative to design suitable QoS model. In this paper we conduct simulation study to evaluate the QoS performance of WiMAX and UMTS for supporting VoIP. We designed simulation modules in OPNET for WiMAX and UMTS, and carried out extensive simulations to evaluate and analyze several important performance metrics such as Mean Opinion Score (MOS), end-to-end delay, jitter and packet delay variation. Simulation results show that WiMAX outscores the UMTS with a sufficient margin, and is the better technology to support VoIP applications compared with UMTS.

The traditionally wired automation infrastructure is quickly migrating to more flexible and scalable wireless solutions. To cope with the stringent requirements of process automation in terms of latency and reliability, the network resources must be optimized to ensure timely and reliable communication. This paper considers the joint routing and transmission scheduling problem for reliable real-time communication over lossy networks. Specifically, we impose a strict latency bound for packet delivery from source to destination, and devise optimal transmission scheduling policies that maximize the success probability of delivering the packet within the specified deadline. A solution to this problem allows to characterize the set of achievable latencies and packet reliability for a given network. We offer a complete understanding of the problem when erasure events on links are independent and follow a Bernoulli process. We consider both static and dynamic resource allocation policies, and compare them in numerical examples.

The increased industrial interest in wireless sensor networks demands a shift from optimizing protocols for energy-efficient reporting of sporadic events to developing solutions for high-rate real-time data collection and dissemination. We study time-optimal convergecast under the communication constraints of commodity sensor network platforms, and propose a novel convergecast model in which packet copying between the microcontroller and the radio transceiver is separated from packet transmission, thereby improving channel utilization and system throughput. Based on this model, we establish tight lower bound on the number of time slots for convergecast in networks with tree routing topology, and present both centralized and distributed algorithms for generating time-optimal convergecast schedules. Our scheme is also memory-efficient as each node needs to buffer at most one packet at any time. We evaluate our scheme in simulation and on real hardware, and show that our scheme can achieve a throughput of 203 kbit/s (86.4% of the theoretical upper bound) and up to 86.24% improvement compared with traditional TDMA-based convergecast. With optimal routing tree and maximum MAC layer payload, convergecast in a network with 20 sensor nodes can be completed in only 100 ms.

Geographic routing is an attractive localized routing scheme for wireless sensor networks (WSNs) due to its desirable scalability and efficiency. Maintaining neighborhood information for packet forwarding can achieve a high efficiency in geographic routing, but may not be appropriate for WSNs in highly dynamic scenarios where network topology changes frequently due to nodes mobility and availability. We propose a novel online routing scheme, called Energy-efficient Beaconless Geographic Routing (EBGR), which can provide loop-free, fully stateless, energy-efficient sensor-to-sink routing at a low communication overhead without the help of prior neighborhood knowledge. In EBGR, each node first calculates its ideal next-hop relay position on the straight line toward the sink based on the energy-optimal forwarding distance, and each forwarder selects the neighbor closest to its ideal next-hop relay position as the next-hop relay using the Request-To-Send/Clear-To-Send (RTS/CTS) handshaking mechanism. We establish the lower and upper bounds on hop count and the upper bound on energy consumption under EBGR for sensor-to-sink routing, assuming no packet loss and no failures in greedy forwarding. Moreover, we demonstrate that the expected total energy consumption along a route toward the sink under EBGR approaches to the lower bound with the increase of node deployment density. We also extend EBGR to lossy sensor networks to provide energy-efficient routing in the presence of unreliable communication links. Simulation results show that our scheme significantly outperforms existing protocols in wireless sensor networks with highly dynamic network topologies.

This paper describes a methodology for controller and communication scheduling co-design in control systems operating over wirelessHART networks. Data collection and dissemination operations are identified and scheduled to minimize the nominal communication latency. Techniques for improving the reliability of the network when link transmissions are unreliable are discussed, and a Markov-chain model for computing the latency distribution of data collection operations for a given schedule is proposed. The resulting latency models allow to represent the networked control loop as a jump-linear system, whose performance can be analyzed using techniques from stochastic control. We demonstrate how this framework can be used to co-design a networked LQG controller for a five-by-five MIMO control loop.

Peer-to-peer file sharing applications are increasingly popular and they enable users to share various files with high scalability. However, in intermittently connected mobile network environment, existing file sharing systems are hindered by the lack of node stable connectivity and constant network topology change. We propose a social network based file sharing system in mobile P2P networks. It takes advantage of node mobility and builds communities based on social network. Instead of being hindered by the mobility of the nodes, the proposed system utilizes the node mobility to facilitate communications and provide efficient message routing and file retrieval services. Experiment results show that the proposed system significantly lowers the transmission cost and achieves satisfactory file retrieval success rate.

Convergecast, in which data from a set of sources is routed toward one data sink, is a critical functionality for wireless networks deployed for industrial monitoring and control. We address the joint link scheduling and channel assignment problem for convergecast in networks operating according to the recent WirelessHART standard. For a linear network with N single-buffer devices, we demonstrate that the minimum time to complete convergecast is 2N-1 time-slots, and that the minimum number of channels required for this operation is lceilN/2rceil. When the devices are allowed to buffer multiple packets, we prove that the optimal convergecast time remains the same while the number of required channels can be reduced to . For both cases, we present jointly time- and channel-optimal scheduling policies with complexity O(N2). Numerical results demonstrate that our schemes are also efficient in terms of memory utilization.

Unbalanced energy consumption is an inherent problem in wireless sensor networks characterized by multihop routing and many-to-one traffic pattern, and this uneven energy dissipation can significantly reduce network lifetime. In this paper, we study the problem of maximizing network lifetime through balancing energy consumption for uniformly deployed data-gathering sensor networks. We formulate the energy consumption balancing problem as an optimal transmitting data distribution problem by combining the ideas of corona-based network division and mixed-routing strategy together with data aggregation. We first propose a localized zone-based routing scheme that guarantees balanced energy consumption among nodes within each corona. We then design an offline centralized algorithm with time complexity O(n) (n is the number of coronas) to solve the transmitting data distribution problem aimed at balancing energy consumption among nodes in different coronas. The approach for computing the optimal number of coronas in terms of maximizing network lifetime is also presented. Based on the mathematical model, an energy-balanced data gathering (EBDG) protocol is designed and the solution for extending EBDG to large-scale data-gathering sensor networks is also presented. Simulation results demonstrate that EBDG significantly outperforms conventional multihop transmission schemes, direct transmission schemes, and cluster-head rotation schemes in terms of network lifetime.

No abstract available.

This paper introduces a novel geographic routing protocol called Energy-Efficient Geographic Routing (EEGR) for wireless sensor networks. In EEGR, both geographic information and transceiver power characteristics are employed to make forwarding decisions, thereby enabling an energy-aware localized routing strategy. We prove that EEGR is loop-free and derive the bounds on hop count for sensor- to-sink packet delivery. In particular, we analyze the energy dissipation under EEGR and present the approximated expected energy consumption for sensor-to-sink data delivery when nodes are uniformly deployed. Simulation results demonstrate that EEGR can provide near-optimal energy- efficient routing only based on local information.

Unbalanced energy consumption is an inherent problem in wireless sensor networks where some nodes may be overused and die out early, resulting in a short network lifetime. In this paper, we investigate the problem of balancing energy consumption for data gathering sensor networks. Our key idea is to exploit the tradeoff between hop-by-hop transmission and direct transmission to balance energy dissipation among sensor nodes. By assigning each node a transmission probability which controls the ratio between hop-by-hop transmission and direct transmission, we formulate the energy consumption balancing problem as an optimal transmission probability allocation problem. We discuss this problem for both chain networks and general networks. Moreover, we present the solution to compute the optimal number of sections in terms of maximizing the network lifetime. Numerical results demonstrate that our methods outperform the traditional hop-by-hop and direct transmission schemes and achieve significant lifetime extension especially for dense sensor networks.

In this paper, we study the problem of data gathering in multi-hop wireless sensor networks. To tackle the high degree of channel contention and high probability of packet collision induced by bursty traffic, we introduce a novel model based on random channel access scheme for data gathering. In our model, both data delivery reliability and latency are considered, and our goal is to tune the attempt probability for each sensor node so that the data gathering duration can be minimized on condition that each link in the data gathering tree can provide guaranteed per-hop packet delivery reliability. We formulate this problem as an optimization problem and propose a distributed heuristic algorithm which exploits only two hop neighbors information to solve it for tree networks. We evaluate the algorithm and the model by simulations, and results show that our algorithm has low computational complexity and our model can provide a good trade-off between reliability and latency for data gathering

Hypercube communication is one of the most versatile and efficient communication patterns for parallel computation. Routing and wavelength assignments for realizing hypercube communications on WDM linear arrays, rings, meshes and tori have been discussed in our past researches. In this paper, we study routing and wavelength assignment for realizing hypercube communications on WDM chordal ring networks of degree 3. We design embedding scheme and derive the number of wavelengths required for different chord length. Based on embedding scheme of double cycle embedding, we also provide the analysis of chord length with optimal number of wavelengths to realize hypercube communications on 3-degree chordal rings. Results show that the wavelength requirement for realizing hypercube communications on optical networks has been further reduced on optical 3-degree chordal ring networks compared with some topologies discussed before. Our results have both theoretical and practical significance as WDM optical networks have an increasing popularity

Segmentation is a crucial precursor to most medical image analysis applications. This paper presents a new three-dimensional adaptive region growing algorithm for the automatic segmentation of three-dimensional images. The principle of our algorithm is to obtain a satisfactory segment result by self-tuning the homogeneity constraint step by step, which effectively resolves the dilemma of threshold auto-selection. Novel homogeneity and leakage detection criteria are designed to improve accuracy and robustness. Cavities auto-filling algorithm is also proposed to eliminate the interior cavities. Our algorithm was tested by segmenting lungs from 3D throat CT images and compared with manual segmentation and traditional 3D region growing. Results demonstrate that our algorithm greatly outperforms traditional 3D region growing method and its segment result is close to that of manual segmentation.