Abstract The security of operating system has always been challenged by the hidden operation of rootkits. Based on virtual machine introspection technology, security tools are deployed outside the target virtual machine (TVM) that provides strict isolation between them and enhances the anti-interference of security tools. However, the current methods based on virtualization can only detect the hidden objects but cannot make them visible to TVM that leads to handling failure for host-based security tools. To solve this problem, this paper proposes a hidden object detection and recovery method RecObj based on virtualization technology. RecObj uses multidimensional semantic views cross-comparison to discover the hidden processes and files. By dynamically monitoring the change of logical relationship between loadable kernel modules and the change of their states, the hiding detection of rootkit itself can be realized. For processes and modules hidden by direct kernel object manipulation technology, RecObj uses memory writable mapping to restore hidden objects to be visible objects. Finally, the processing signal is transmitted to the hidden object manager in TVM through xenstore, and the cleanup operation to the hidden object is completed. The feasibility and effectiveness of RecObj is proved through the hiding detection, recovery, and processing experiments.

Few-shot Named Entity Recognition (NER) is the task of identifying and classifying entities under conditions of low resources. The preceding approach relies on meta-learning, wherein the classification model is trained through N-way K-shot. However, It neglects essential information: the model’s input is organized at the sentence level. To tackle the aforementioned issues, we introduce a sampling strategy — the Loose Nway K˜shot sampling algorithm. This approach combines the number of entities and sentence level which is the smallest unit of NER models’ input. Experimental results demonstrate that our strategy currently stands as the most effective method for Few-shot NER. Furthermore, our investigation reveals that various classes of entities within the same sentence can impede the prototype representation of each class. Consequently, we introduce a training method that involves utilizing sentences with single entity class for pre-training purposes. The experimental outcomes substantiate that this training methodology maximizes the utilization of labeled data, enabling the pre-training model to swiftly adapt to new domains. This approach significantly enhances the performance of NER.

Few-shot detection in remote sensing images has witnessed significant advancements recently. Despite these progresses, the capacity for continuous conceptual learning still poses a significant challenge to existing methodologies. In this article, we explore the intricate task of incremental few-shot object detection (iFSOD) in remote sensing images. We present a pioneering transfer-learning-based technique, termed InfRS, designed to enable the incremental learning of novel classes using a restricted set of examples, while simultaneously preserving the knowledge learned from previously seen classes without the need to revisit old data. Specifically, we pretrain the detector using sufficient data from base datasets and then generate a set of classwise prototypes that represent the intrinsic characteristics of the data. In the incremental learning session, we design a hybrid prototypical contrastive (HPC) encoding module for learning discriminative representations. Furthermore, we develop a prototypical calibration strategy based on the Wasserstein distance to overcome the catastrophic forgetting problem. Comprehensive evaluations conducted with two aerial imagery datasets show that our InfRS effectively addresses the iFSOD issue in remote sensing imagery. Code is available athttps://github.com/lyanna4869/InfRS.git.

An inevitable trend of hyperspectral remote sensing has been toward hyperspectral with high spatial resolution (H2) images. However, the higher resolution also brings higher spatial/spectral heterogeneity of surface features, which increases the difficulty of fine classification. Fully using global spatial–spectral features and contextual information is an effective method to alleviate spatial/spectral heterogeneity. Recently, to extract global spatial–spectral features with long-range dependencies, the self-attention mechanism has been widely used in H2 image classification and has achieved excellent results. As is well known, the simultaneous use of spatial and spectral information has always been a key aspect of hyperspectral image (HSI) processing; however, the current spatial and spectral attention modules only focus on the spatial and spectral features separately. This prevents further improvement in network performance, especially when the sample size is small. Therefore, a spatial–spectral attention-in-attention network (S2AiANet) is proposed, which solves the problem of the current spatial–spectral attention maps only focusing on single features through the spatial–spectral attention-in-attention (S2AiA) module. In addition, a multiscale attention (MSA) module is proposed to enhance the network’s adaptability to various complex scenarios. The experiments on two H2 datasets and one classic HSI dataset demonstrate that S2AiANet can achieve a significant performance improvement compared with the state-of-the-art hyperspectral classifiers.

Pest detection is critical for achieving effective pest control. However, the current deep learning-based pest detection algorithm is unsuitable for deployment on resource-limited edge devices due to its extensive computation and long inference time. Although lightweight models have been widely used for practical detection, their insufficient feature extraction capability leads to a decline in detection accuracy. This paper proposes a fast algorithm for crop pest detection based on lightweight feature extraction and knowledge distillation. Firstly, we introduce partial convolution and propose a lightweight feature extraction module, C3Faster, which reduces the model's computation and speeds up model inference while ensuring effective feature extraction. Secondly, we use knowledge distillation to improve the model's detection accuracy by using teacher networks to assist in training. Finally, we created a dataset, CropPest6, consisting of six crop pest categories and conducted experiments. The experimental results demonstrate that our method reduces the detection time, number of parameters, and computation by 17%, 38%, and 44%, respectively, compared to the baseline model. Furthermore, our method achieves 93.9% Precision, 93.6% Recall, and 97.5% mean Average Precision (mAP), demonstrating its practical suitability for fast crop pest detection.

In recent years, wireless networks and applications have grown rapidly and converged across a wide variety of scenarios. More and more applications require wireless networks for high bandwidth and low latency. However, due to the attenuated propagation of wireless signals, bandwidth changes rapidly in a short period. TCP fails to work properly in such an environment and suffers from low network link utilization and high latency. To solve above problems, this paper proposes a receiver-driven congestion control framework, named NUiVa. NUiVa decouples the congestion avoidance phase of sender side congestion control and implements it on the receiver side. In addition, NUiVa uses one-way delay to detect network congestion and controls the sending rate of senders via the receiving window field in the packet header. We confirm that the throughput degradation caused by network flips can be mitigated by NUiVa. And the throughput of data transmission can be further improved by the design of the receiver’s algorithm. The evaluation results show that NUiVa improves the throughput of TCP stream by 10 to 23 percent in most cases and reduces the queuing delay by an average of 29 percent.

Water segmentation is essential for autonomous navigation of Unmanned Surface Vehicles (USV) in inland waterways. However, most of the existing methods are suitable for maritime environments. Due to their poor real-time performance and a high false-positive rate of water surface reflection and water-sky interference in inland waterways, we propose a radarassisted real-time water segmentation network (RaRWS) to solve the above problems. We obtain pseudo-waterlines based on radar data by deleting points, fitting them multiple times, and generating a radar mask. While simplifying the encoder backbone network, we use the Attention Refinement Module (ARM) to fuse radar masks to improve detection and waterside accuracy. In addition, a Feature Fusion Module (FFM) is introduced to help the decoder fuse high- and low-level features and further fuse radar data. RaRWS is tested in both normal and bad weather. The results show that RaRWS can achieve higher performance compared with the current state-of-the-art methods (F1is above 99%), while gaining real-time performance (41.3fps).

Rivers are an essential part of the aquatic environment. The accurate detection and timely cleaning of river floating debris plays a vital role in the landscape and aquatic ecological environment. At present, the detection of river floating debris mainly relies on manually patrolling rivers and fixed camera monitoring, which has the problem of low efficiency and high cost. In this paper, we used Unmanned Aerial Vehicle (UAV) to photograph rivers and then utilized deep learning algorithms to detect floating debris in the images to improve the efficiency of river regulation. However, its application faces some problems, including the lack of datasets, the complex background of UAV images, and the small and sparsely distributed objects. To address the above issues, we used a UAV to capture river images and labeled the floating debris to construct a dataset. Moreover, to enhance the detection capability of river floating debris, we proposed an improved algorithm based on YOLOv5s. Firstly, the algorithm adds a microscale detection layer in the detection phase to improve small targets' detection. Secondly, it introduces an improved CBAM in the feature fusion phase to suppress the effects of useless and complex background information. Finally, in the loss function, a weighting factor is added to objectness loss to raise the loss weight of positive samples to ameliorate where negative samples loss much more than positive samples. The experimental results illustrated that compared to the baseline, our method has superior precision, recall, and [email protected], reaching 87.4%, 85.6%, and 91.8%, respectively. The proposed method can accurately detect river floating debris in UAV images and provide technical support for river regulation.

Acoustic-communication-based intelligent devices attract attention for their simplicity and cost-effectiveness. Still, there is a lack of research on acoustic communication solutions that can simultaneously balance low Bit Error Rate(BER), inaudible sound, low power consumption, high throughput, and operate on embedded devices. This paper proposes an acoustic communication framework based on Chirp Spread Spectrum (CSS) modulation technology, which can accomplish reliable acoustic communication on common MCU such as stm32 and ESP32. Our proposed Custom Rolling Matching Encoding (CRME) protocol matches complex acoustic channel states with a vote-queue algorithm. It performs reliable low-rate acoustic communication in a low signal-to-noise ratio (SNR) environment. Results show that the framework has surpassed technologies such as Bluetooth Low Energy (BLE) and Radio-frequency Identification (RFID) in terms of BER, power consumption for device usage, and communication distance: BER is below 0.5% at a 272 bps data reception rate. Also, the framework can be deployed on embedded devices, consumes less power than RFID, and performs similarly to BLE, providing an alternative to cost-effective acoustic communication.

Bandwidth-sensitive applications rely on the accurate estimation of the bottleneck bandwidth. The real-time bandwidth prediction enables the application to cope with bandwidth fluctuation and adjust the transmission strategy to improve the Quality of Experience (QoE) of user. The traditional bandwidth prediction model hardly considers the bandwidth characteristics in various scenarios, making it challenging to achieve high accuracy. In this paper, we propose ALSTM model, which is based on the Long Short Term Memory (LSTM) recurrent neural network and the attention mechanism for multi-scenario bandwidth prediction. Firstly, we conduct the bandwidth trajectories feature analysis, and then we adopt the Support Vector Machine (SVM) to classify scenarios based on the bandwidth characteristics. Secondly, we apply an attention mechanism to assign weights to the input of the bandwidth series, and the attention feature is utilized to effectively select the feature sequences as input to the LSTM model for the prediction. The experimental results show that the ALSTM reduces the Root Mean Square Error (RMSE) by 20%, and the Mean Average Error (MAE) is improved by 26%. For practical applications, we adopt the pre-trained SVM model for real-time scenario detection, dynamic switch the corresponding ALSTM model, and the switching success rate is up to 86%. In addition, by deploying the proposed bandwidth prediction model ALSTM, the DASH's QoE has increased by more than 25%.

Block‐matching and three‐dimensional filtering (BM3D) is generally considered as a milestone for its outstanding performance in the area of image denoising. However, it still suffers from the loss of image detail due to the utilisation of hard thresholding on transform domain during the phase of the basic estimate. In the frequency domain, a large amount of image detail information is in high frequency, which tends to be mixed with noise. Since its low amplitude is below the threshold, some image detail is filtered out with the noise. To retain more details, this study proposes an improved BM3D. It adopts an adaptable threshold with the core of Gaussian function during hard thresholding, which can filter out more noise while retaining more high‐frequency information. When grouping, the normalised angular distance is taken as a measure of similarity to relieve the interference of noise further and achieve a higher peak signal‐to‐noise ratio (PSNR). The experimental results show that under the background of Gaussian noise with standard deviation of 20–60, the PSNR of denoised images (with a large amount of detail), applied with the authors’ improved algorithm, can be improved by compared with original BM3D.

The ongoing expansion and addition of new features in software development bring inefficiency and vulnerabilities into programs, resulting in an increased attack surface with higher possibility of exploitation. Creating customized software systems that contain just-enough features and yet satisfy specific user needs is currently an extremely slow, build-to-order process. In this paper, we propose MORPH, an Interactive Program Feature Customization framework to provide broad capabilities for automated program feature identification and feature customization. Our preliminary results show that MORPH can identify program features at an average accuracy of 92.7% and swiftly generate variations of self-contained, customized programs in an unsupervised fashion.

The high-throughput, low-latency, and reliable data delivery are fundamental demands of many networked applications, e.g. BitTorrent and Skype. But the inappropriate congestion control of TCPs, caused by the reactive and coarse- grained congestion feedbacks, brings the low link utilization, high queuing delay and frequent packet loss in high bandwidth-delay product network. To mitigate this issue, TCP variants have been developed. Thereinto, the load factor based congestion control (LFCC), e.g. VCP, BMCC, have shown the powerful capabilities to achieve better performances in terms of high link utilization, low persistent queue length, negligible packet loss, and fairness. However, due to the conservative increase and synchronized feedbacks, LFCC faces the slow convergence of the link utilization and inter-flow fairness. This could incur the large flow completion time of new-coming flows indirectly. To solve the issue of existing LFCCs, an asynchronous congestion control based on hybrid feedbacks, called HFCC, is proposed to achieve the faster convergence while keeping the features of LFCCs in this paper. Specifically, HFCC decreases the congestion window when the bottleneck link is in the high-load region and the flow rate exceeds the fair share of the bottleneck bandwidth, or the bottleneck link is in overload region. Otherwise, HFCC increases the congestion window. Note that an overlay coding method is developed in HFCC. To reduce the flow completion time, HFCC adopts an available bandwidth estimation method to speed up the data delivery in low-load region. The simulation results indicate that HFCC has the better performance and faster convergence than VCP, MLCP, and BMCC.

The increasing popularity of smart mobile devices enables a widespread use of Location Based Services (LBS). LBSs require real-time processing of frequent updating data (i.e., Streams), and return customized results to mobile users based on their own locations. The mobile environment brings additional design and development considerations to LBS applications, such as real-time awareness, energy efficiency, and privacy preservation. In a recent project, we worked on the Emergency Medical Service as an example LBS application, and developed a Cloud-based LBS prototype, named as Early Alert System (EARS), to deliver real-time emergency vehicle's information to smart mobile devices based on their geo-proximity. EARS leverages Cloud-based stream processing systems to address the real-time stream processing needs, and also develops effective methods to conserve energy consumption and preserve user privacy. EARS is an efficient approach to deliver real-time geo-information from the Cloud to mobile users, and can be easily generalized to other LBS applications in the mobile environment.

In this paper, the degradation based reliability demonstration test (RDT) plan design problems for long life products under a small sample circumstance are studied. Fixed sample method, sequential probability ratio test (SPRT) method, and sequential Bayesian decision method are provided based on univariate degradation testing. The simulation examples show the superiority of degradation based RDT methods compared with the traditional failure based methods, and the sequential-type methods have more test power than their fixed sample counterparts. The test power can be further improved by combining the test data of a reliability indicator with the data of its marker, based on which the bivariate fixed sample method and the sequential Bayesian decision method are defined. The simulation study shows the benefit from the combination. The degradation based RDT plan optimization model, and the corresponding searching-based solution algorithm using some heuristic rules discovered in the paper, are also presented. The case study of Rubidium Atomic Frequency Standard with a RDT plan design demonstrates the effectiveness of our methods on overcoming the difficulties of small samples in reliability demonstration of long life products.

In this paper, we consider revenues of the NSP (network service provider) when there exists a "congestion externality." In particular, we compare revenues obtained using a flat price and two-part tariff and analyze the effect of congestion on the revenue loss when using a simple entry fee in lieu of the two-part tariff. Previous study has shown that when there is no delay disutility the revenue loss is small, which leads to a low "Price of Simplicity." However, in this study, we show that in an extreme case where all users are identical, the price of simplicity is substantial. Then we consider a more practical scenario where users have different preferences, and show that even in this case, under congestion externality, the price can be extremely high.

Geosensor networks are deployed to detect, monitor and track continuous environmental phenomena such as toxic clouds or dense areas of air pollution in an urban environment. In this paper, we abstract such continuous phenomena as 2D objects and only consider their boundary using wireless sensor networks to monitor them over time. In order to maximize energy-efficient monitoring of the phenomena, we present an in-network algorithm based on the concept of deformable curves to incrementally track spatiotemporal changes of the object. We show that the in-network incremental boundary tracking approach based on deformable curves collects sufficient information efficiently to track the overall spatiotemporal properties about a 2D object. By simulations, we demonstrate the energy-efficiency of our approach.

Recent research on sensor networks has focused on the efficient processing of declarative SQL queries over sensor nodes. Users are often interested in querying an underlying continuous phenomenon such as a toxic plume, whereas only discrete readings of sensor nodes are available. Therefore, additional information estimation methods are necessary to process the sensor readings to generate the required query results. Most estimation methods are computationally intensive, even when computed in a traditional centralized setting. Furthermore, energy and communication constraints of sensor networks challenge the efficient application of established estimation methods in sensor networks. In this paper, we present an approach using Gaussian kernel estimation to process spatial window queries over continuous phenomena in sensor networks. The key contribution of our approach is the use of a small number of Hermite coefficients to approximate the Gaussian kernel function for subclustered sensor nodes. As a result, our algorithm reduces the size of messages transmitted in the network by logarithmic order, thus saving resources while still providing high-quality query results.

Wireless sensor networks provide an advanced platform to observe the physical world. Different users may be interested in different events derived from a same spatial phenomenon. The constrained and noisy environment of sensor networks, however, challenges successful in-network solutions to monitor and detect events and event boundaries. This paper presents an efficient algorithm, named NED, to support event and event boundary detection in wireless sensor networks. NED encodes partial event estimation results into variable length messages exchanged locally among neighboring nodes. Sensor nodes estimate events and event boundaries based on moving averages to eliminate noise effects. Thus, NED is resource-friendly to constrained sensor networks, and scales well to very large networks. Our experiment results illustrate that NED’s communication cost is flexible and moderate to different noise levels, and NED provides high quality estimation results of event and event boundary detection.