The rapid evolution of unmanned aerial vehicles (UAVs) has positioned air-ground networks as vital infrastructures for diverse applications. However, the open channels of air-ground networks remain inherently vulnerable to persistent eavesdropping threats. While physical-layer key generation (PLKG) offers a lightweight security mechanism by leveraging channel reciprocity to extract shared secrets, the inherent mobility of UAVs introduces a paradoxical tradeoff. Increased channel randomness from dynamic flight patterns enhances security through entropy amplification but simultaneously disrupts channel reciprocity, leading to key mismatch between legitimate parties. Existing PLKG schemes struggle to maintain reliability in key generation due to static channel characteristics and synchronization overhead, limiting their practical deployment in air-ground networks. To resolve this conflict, we propose a Doppler shift key generation (DSKG) scheme that systematically regulates Doppler shifts through UAV trajectory design to derive secure keys. By formulating the problem as a Markov decision process, we develop a proximal policy optimization (PPO)-clip-based reinforcement learning algorithm to dynamically control UAV speed and steering angle, ensuring robust Doppler shift reciprocity while maximizing both key entropy and generation rate. Experimental results quantify the improvements of our scheme over benchmarks in maintaining high key unpredictability and generation efficiency. Furthermore, the analysis provides valuable insights into parameter impacts, confirming the practical viability of the DSKG scheme for securing air-ground communications.

The space-air-ground integrated network (SAGIN) can enable global range and seamless coverage in the future network. SAGINs consist of three spatial layer network nodes: 1) satellites on the space layer, 2) aerial vehicles on the aerial layer, and 3) ground devices on the ground layer. Data transmissions in SAGINs include six unique cross-spatial-layer scenarios, i.e., three uplink and three downlink transmissions across three spatial layers. For simplicity, we call them six cross-layer scenarios. Considering the diverse cross-layer scenarios, it is crucial to conduct a unified network modeling regarding node coverage and distributions in all scenarios. To achieve this goal, we develop a unified modeling approach of coverage regions for all six cross-layer scenarios. Given a receiver in each scenario, its coverage region on a transmitter-distributed surface is modeled as a spherical dome. Utilizing spherical geometry, the analytical models of the spherical-dome coverage regions are derived and unified for six cross-layer scenarios. We conduct extensive numerical results to examine the coverage models under varying carrier frequencies, receiver elevation angles, and transceivers' altitudes. Based on the coverage model, we develop an algorithm to generate node distributions under spherical coverage regions, which can assist in testing SAGINs before practical implementations.

In this study, we investigate the resource management challenges in next-generation mobile crowdsensing networks with the goal of minimizing task completion latency while ensuring coverage performance, i.e., an essential metric to ensure comprehensive data collection across the monitored area, yet it has been commonly overlooked in existing studies. To this end, we formulate a weighted latency and coverage gap minimization problem via jointly optimizing user selection, subchannel allocation, and sensing task allocation. The formulated minimization problem is a non-convex mixed-integer programming issue. To facilitate the analysis, we decompose the original optimization problem into two subproblems. One focuses on optimizing sensing task and subband allocation under fixed sensing user selection, which is optimally solved by the Hungarian algorithm via problem reformulation. Building upon these findings, we introduce a time-efficient two-sided swapping method to refine the scheduled user set and enhance system performance. Extensive numerical results demonstrate the effectiveness of our proposed approach compared to various benchmark strategies.

Due to their flexibility, aerial vehicles (AVs), such as unmanned aerial vehicles and airships, are widely employed as relays to assist communications between massive ground users (GUs) and satellites, forming an AV-relayed ground-air-satellite solution (GASS). In GASS, the deployment of AVs is crucial to ensure overall performance from GUs to satellites. This paper develops a stochastic geometry-based analytical model for GASS under Matérn hard-core point process (MHCPP) distributed AVs. The 3D distributions of AVs and GUs are modeled by considering their locations on spherical surfaces in the presence of high-altitude satellites. Accordingly, we derive an overall connectivity analytical model for GASS, which includes the average performance of AV-relayed two-hop transmissions. Extensive numerical results validate the accuracy of the connectivity model and provide essential insights for configuring AV deployments.

The growing reliance on mobile crowdsensing net-works for real-time data collection in various applications, from urban infrastructure monitoring to environmental sensing, ne-cessitates the reduction of latency for enhanced efficiency. In this work, we address this critical challenge by focusing on the joint subband and sensing task allocation for next-generation mobile crowdsensing networks, emphasizing the minimization of latency. To achieve this goal, an optimization problem is formulated to minimize the system's total latency, taking various practical constraints into account. Therein, the latency is comprised of sensing delay and transmission delay. The considered problem is a mixed-integer programming problem, which is also non-convex. To facilitate the analysis, we utilize the underlying structural properties of the problem and derive the optimal sensing task allocation strategy under a given sub band allocation scheme. With the discussions, we show that the original optimization problem can be transformed into a maximum weighted matching problem in a bipartite graph. This problem can be optimally solved by the Hungarian algorithm in a cubic time complexity. Building upon these analyses, we further approximate the optimal network delay in closed form under certain circumstances. Extensive simulation results validate that our proposed joint optimization method outperforms various benchmark strategies in terms of latency saving under comprehensive system settings.

By integrating the merits of aerial, terrestrial, and satellite communications, the space-air-ground integrated network (SAGIN) is an emerging solution that can provide massive access, seamless coverage, and reliable transmissions for global-range applications. In SAGINs, the uplink connectivity from ground users (GUs) to the satellite is essential because it ensures global-range data collections and interactions, thereby paving the technical foundation for practical implementations of SAGINs. In this article, we aim to establish an accurate analytical model for the uplink connectivity of SAGINs in consideration of the global distributions of both GUs and aerial vehicles (AVs). Particularly, we investigate the uplink path connectivity of SAGINs, which refers to the probability of establishing the end-to-end path from GUs to the satellite with or without AV relays. However, such an investigation on SAGINs is challenging because all GUs and AVs are approximately distributed on a spherical surface (instead of the horizontal surface), resulting in the complexity of network modeling. To address this challenge, this paper presents a new analytical approach based on spherical stochastic geometry. Based on this approach, we derive the analytical expression of the path connectivity in SAGINs. Extensive simulations confirm the accuracy of the analytical model.

Since it is difficult to filter out the rainfall interference directly from the X-band marine radar image, it is necessary to detect whether the collected radar image contains rainfall interference to control the quality of the radar image. Aiming at the problem of rainfall recognition in X-band marine radar images, a new rainfall detection method is proposed by using principal component analysis (PCA) technology to reduce dimensions and extract features from radar images. Based on the calculated distance between the features to be tested and the known features, the$k$-nearest neighbor (KNN) algorithm is utilized to determine the classification task of the radar image and recognize the rainfall radar image. The experimental result illuminates that the detection accuracy of the proposed method reaches 99.3% and is 2.0% higher than that of the support vector machine (SVM)-based method. Meanwhile, the proposed method shows good classification performance for the rain-contaminated images under different rainfall intensities.

Recent breakthroughs in deep-learning (DL) approaches have resulted in the dynamic generation of trace links that are far more accurate than was previously possible. However, DL-generated links lack clear explanations, and therefore non-experts in the domain can find it difficult to understand the underlying semantics of the link, making it hard for them to evaluate the link's correctness or suitability for a specific software engineering task. In this paper we present a novel NLP pipeline for generating and visualizing trace link explanations. Our approach identifies domain-specific concepts, retrieves a corpus of concept-related sentences, mines concept definitions and usage examples, and identifies relations between cross-artifact concepts in order to explain the links. It applies a post-processing step to prioritize the most likely acronyms and definitions and to eliminate non-relevant ones. We evaluate our approach using project artifacts from three different domains of interstellar telescopes, positive train control, and electronic healthcare systems, and then report coverage, correctness, and potential utility of the generated definitions. We design and utilize an explanation interface which leverages concept definitions and relations to visualize and explain trace link rationales, and we report results from a user study that was conducted to evaluate the effectiveness of the explanation interface. Results show that the explanations presented in the interface helped non-experts to understand the underlying semantics of a trace link and improved their ability to vet the correctness of the link.

Non-terrestrial Networks (NTNs) refer to the networks, where either satellites or unmanned aerial vehicles (UAVs) are deployed to extend the current terrestrial networks for serving the growing mobile broadband and machine-type communications. With the advantages of UAVs' flexibility and satellites' global coverage, the solution of UAV-To-satellite communications (U2SC) can provide promising global communication services for the emerging NTNs. Previous literature has explored many potential directions of U2SC, including channel tracking, deployment design, and link analysis. However, as a vital role in system performance, the connectivity of U2SC has not been well investigated yet. This research gap motivates us to present an analytical model to evaluate the connectivity of U2SC. In particular, we first present the system model of the U2SC by considering the distribution model of UAVs, antenna models, and the path loss model. We then utilize stochastic geometry to derive a theoretical formulation of the successful connection probability of U2SC. The comprehensive numerical results are given to evaluate the received power, the interference, and the successful connection probability of U2SC and analyze the impacts of system parameters, such as the number of frequency carriers, the type of frequency bands, the number of UAVs, and the satellite altitude.

The emerging unmanned aerial vehicles (UAVs) pose a potential security threat for terrestrial communications when UAVs can be maliciously employed as UAV-eavesdroppers to wiretap confidential communications. To address such an aerial security threat, we present a friendly jamming scheme named terrestrial mobile jamming (TMJ) to protect terrestrial confidential communications from UAV eavesdropping. In our TMJ scheme, a jammer moving along the protection area can emit jamming signals toward the UAV-eavesdropper so as to reduce the eavesdropping risk. We evaluate the performance of our scheme by analyzing a secrecy-capacity maximization problem subject to the legitimate connectivity and eavesdropping probability. In addition, we investigate the optimized position for the jammer as well as its jamming power. Simulation results verify the effectiveness of the proposed scheme.

In this paper, we employ stochastic geometry to analyze ground-to-unmanned aerial vehicle (UAV) communications. We consider multiple UAVs to provide user-equipments (UEs) with uplink transmissions, where the distribution of UEs follows the Poisson Cluster process (PCP) and each UAV is dedicated to a specific cluster. In particular, we characterize the Laplace transform of the interference caused by multiple UEs in terms of the distribution of UEs as well as the transmission probability of each UE. We then derive analytical expressions of the successful transmission probability. We next conduct a comprehensive numerical analysis with consideration of different system parameters. The results show that four factors (i.e., the geographical surroundings, the transmission powers, the Signal-to-Interference-plus-Noise Ratio (SINR) thresholds, and the UAV height) have main influences on ground-to-UAV communications.

Software traceability establishes and leverages associations between diverse development artifacts. Researchers have proposed the use of deep learning trace models to link natural language artifacts, such as requirements and issue descriptions, to source code; however, their effectiveness has been restricted by availability of labeled data and efficiency at runtime. In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts. To address data sparsity, we leverage a three-step training strategy to enable trace models to transfer knowledge from a closely related Software Engineering challenge, which has a rich dataset, to produce trace links with much higher accuracy than has previously been achieved. We then apply the T-BERT framework to recover links between issues and commits in Open Source Projects. We comparatively evaluated accuracy and efficiency of three BERT architectures. Results show that a Single-BERT architecture generated the most accurate links, while a Siamese-BERT architecture produced comparable results with significantly less execution time. Furthermore, by learning and transferring knowledge, all three models in the framework outperform classical IR trace models. On the three evaluated real-word OSS projects, the best T-BERT stably outperformed the VSM model with average improvements of 60.31% measured using Mean Average Precision (MAP). RNN severely underperformed on these projects due to insufficient training data, while T-BERT overcame this problem by using pretrained language models and transfer learning.

In the past decades, due to the low design cost and easy maintenance, text-based CAPTCHAs have been extensively used in constructing security mechanisms for user authentications. With the recent advances in machine/deep learning in recognizing CAPTCHA images, growing attack methods are presented to break text-based CAPTCHAs. These machine learning/deep learning-based attacks often rely on training models on massive volumes of training data. The poorly constructed CAPTCHA data also leads to low accuracy of attacks. To investigate this issue, we propose a simple, generic, and effective preprocessing approach to filter and enhance the original CAPTCHA data set so as to improve the accuracy of the previous attack methods. In particular, the proposed preprocessing approach consists of a data selector and a data augmentor. The data selector can automatically filter out a training data set with training significance. Meanwhile, the data augmentor uses four different image noises to generate different CAPTCHA images. The well-constructed CAPTCHA data set can better train deep learning models to further improve the accuracy rate. Extensive experiments demonstrate that the accuracy rates of five commonly used attack methods after combining our preprocessing approach are 2.62% to 8.31% higher than those without preprocessing approach. Moreover, we also discuss potential research directions for future work.

Software traceability provides support for various engineering activities including Program Comprehension; however, it can be challenging and arduous to complete in large industrial projects. Researchers have proposed automated traceability techniques to create, maintain and leverage trace links. Computationally intensive techniques, such as repository mining and deep learning, have showed the capability to deliver accurate trace links. The objective of achieving trusted, automated tracing techniques at industrial scale has not yet been successfully accomplished due to practical performance challenges. This paper evaluates high-performance solutions for deploying effective, computationally expensive trace-ability algorithms in large scale industrial projects and leverages generated trace links to answer Program Comprehension Queries. We comparatively evaluate four different platforms for supporting industrial-scale tracing solutions, capable of tackling software projects with millions of artifacts. We demonstrate that tracing solutions built using big data frameworks scale well for large projects and that our Spark implementation outperforms relational database, graph database (GraphDB), and plain Java implementations. These findings contradict earlier results which suggested that GraphDB solutions should be adopted for large-scale tracing problems.

Software traceability establishes associations between diverse software artifacts such as requirements, design, code, and test cases. Due to the non-trivial costs of manually creating and maintaining links, many researchers have proposed automated approaches based on information retrieval techniques. However, many globally distributed software projects produce software artifacts written in two or more languages. The use of intermingled languages reduces the efficacy of automated tracing solutions. In this paper, we first analyze and discuss patterns of intermingled language use across multiple projects, and then evaluate several different tracing algorithms including the Vector Space Model (VSM), Latent Semantic Indexing (LSI), Latent Dirichlet Allocation (LDA), and various models that combine mono-and cross-lingual word embeddings with the Generative Vector Space Model (GVSM). Based on an analysis of 14 Chinese-English projects, our results show that best performance is achieved using mono-lingual word embeddings integrated into GVSM with machine translation as a preprocessing step.

In many regulated domains, traceability is established across diverse artifacts such as requirements, design, code, test cases, and hazards - either manually or with the help of supporting tools, and the resulting trace links are used to support activities such as impact analysis, compliance verification, and safety inspections. Automated tracing techniques need to leverage the semantics of underlying artifacts in order to establish more accurate trace links and to provide explanations of links that have been created in either a manual or automated fashion. To support this, we propose an automated technique which leverages source code, project artifacts and an external domain corpus to generate a domain-specific concept model. We then use the generated concept model to improve traceability results and to provide explanations of the results. Our approach overcomes existing problems with deep-learning traceability algorithms, as it does not require a training set of existing trace links. Finally, as an initial proof-of-concept, we apply our semantically-guided approach to the Dronology project, and show that it improves over other tracing techniques that do not use a concept model.

Non-negative matrix factorization (NMF) has attracted great attentions in speech separation as it can preserve the non-negativity property of the magnitude spectrogram of speech signal. However, NMF sometimes performs poorly because it cannot extract the non-linear features in speech. In this paper, we propose a deep transductive NMF model (DTNMF) which incorporates a multi-layer structure into NMF and learns a shared dictionary on source signal of each speaker and the mixture signal to be separated. Since the multi-layer structure enables DTNMF to learn more precise presentation of source signal with the non-linear features extracted, DTNMF significantly enhances the performance of speech separation. Experimental results on Non-negative matrix factorization (NMF) has attracted great attentions in speech separation as it can preserve the non-negativity property of the magnitude spectrogram of speech signal. However, NMF sometimes performs poorly because it cannot extract the non-linear features in speech. In this paper, we propose a deep transductive NMF model (DTNMF) which incorporates a multi-layer structure into NMF and learns a shared dictionary on source signal of each speaker and the mixture signal to be separated. Since the multi-layer structure enables DTNMF to learn more precise presentation of source signal with the non-linear features extracted, DTNMF significantly enhances the performance of speech separation. Experimental results on the popular LibriSpeech dataset show that DTNMF outperforms the representative NMF models for separating the mixture of single-channel speech signals.

Software projects produce large quantities of data such as feature requests, requirements, design artifacts, source code, tests, safety cases, release plans, and bug reports. If leveraged effectively, this data can be used to provide project intelligence that supports diverse software engineering activities such as release planning, impact analysis, and software analytics. However, project stakeholders often lack skills to formulate complex queries needed to retrieve, manipulate, and display the data in meaningful ways. To address these challenges we introduce TiQi, a natural language interface, which allows users to express software-related queries verbally or written in natural language. TiQi is a web-based tool. It visualizes available project data as a prompt to the user, accepts Natural Language (NL) queries, transforms those queries into SQL, and then executes the queries against a centralized or distributed database. Raw data is stored either directly in the database or retrieved dynamically at runtime from case tools and repositories such as Github and Jira. The transformed query is visualized back to the user as SQL and augmented UML, and raw data results are returned. Our tool demo can be found on YouTube at the following link:http://tinyurl.com/TIQIDemo.

To address scalability concerns, hierarchical control plane organization has been proposed for SDN. However, an open question is how such a hierarchy should look like. In this paper, we model the impact of hierarchies on control plane performance and derive an expression for an optimal hierarchical organization for a given network scale. We then show that using a 4-layer SDN is sufficient for practical network scales, suggesting feasibility and relevance of this approach. Finally, we illustrate the elasticity of hierarchical SDN, which enables a more flexible cost evolution of the SDN control plane.

In this paper, we investigate an energy-efficient coordinated multiple point (CoMP) transmission strategy for downlink heterogeneous cellular networks. We combine CoMP joint processing (CoMP-JP) and coordinated beamforming (CoMP-CB), two special cases of CoMP, in a time division manner to improve both energy efficiency (EE) and spectral efficiency (SE). We formulate the problem as minimizing the total transmit power consumed by both the macro- and pico-base stations (BSs) under the constraints on the data rate requirements from the macro- and pico-users, and on the maximum transmit powers of the macro- and pico-BSs. Both the transmit time and the transmit powers allocated to the CoMP-JP and CoMP-CB transmissions are optimized. Simulation results show that the hybrid CoMP-JP and CoMP-CB strategy provides a larger capacity region than the CoMP-JP-only or CoMP-CB-only transmission. The time proportion of the CoMP-JP in the hybrid strategy decreases with the data rate requirement of the macro-user and increases with the maximum transmit power of the pico-BS and the average channel gain from the macro-BS to the macro-user. Increasing the transmit power of the pico-BS can improve the EE in the high SE region of the macro-user.

The tremendous popularity of smart phones and electronic tablets has spurred the explosive growth of high-rate multimedia services and promptly boomed energy consumption in wireless networks. Therefore, energy-efficient design in wireless networks is very important and is attracting more and more attention, just like the conventional spectral-efficient design. In this paper, we study energy-efficient design in downlink orthogonal frequency division multiple access (OFDMA) networks with effective capacity-based delay provisioning for delay-sensitive traffic. By integrating information theory with the concept of effective capacity, we formulate an energy efficiency (EE) optimization problem with statistical delay provisioning, which is a complicated nonconvex combinatorial fractional programming problem. To solve the problem, we first relax it with an upper bound on the original one and then prove and exploit the quasiconcave property of the EE-versus-transmit power curve, which facilitates the optimal algorithm development. Then, we demonstrate that the resultant solution is quite close to the true optimal value when the number of subcarriers is larger than that of the users. We also analyze the tradeoff between EE and delay, the relationship between spectral-efficient and energy-efficient designs, and the impact of system parameters, including circuit power and delay exponents, on the overall performance. Numerical results show that the proposed energy-efficient design scheme greatly improves EE while maintaining the delay requirement.

The ubiquitous applications of high-data-rate realtime wireless services have promptly boomed energy consumption in wireless networks. Therefore, energy-efficient design in wireless networks is very important and is attracting more and more research attention. In this paper, we study the quality-of-service (QoS) driven energy-efficient design in the downlink orthogonal frequency division multiple access (OFDMA) network. By integrating information theory with the concept of effective capacity, we formulate an energy efficiency (EE) optimization problem with statistical QoS provisioning. To solve the problem, we first modify it with a tight upper bound on the original EE and solve the modified problem. Then, we demonstrate that the resultant solution is quite close to the true optimal value when the number of subcarriers is large than that of the users. We also find out the tradeoff relation between EE and delay. Numerical results show that the proposed energy-efficient design scheme greatly improves EE whiling maintaining QoS requirements.

Widespread application of multimedia wireless services and requirement of ubiquitous access have triggered rapidly booming energy consumption at both transmitter and the receiver sides. Hence, energy-efficient design in wireless networks is very important and is becoming an inevitable trend. In this paper, we take decoding power into consideration when studying joint transmitter and receiver design for achieving high energy efficiency (EE). Based on a new function between transmit power and data rate that is derived by minimizing a lower bound on the overall transmit and receiver power, we investigate when and how should the decoding power be considered for optimizing EE. We find that the decoding power cannot be ignored for short-range wireless communications with a large bandwidth where the transmit power is usually low and give an analytical expression for quantifying the impact of decoding power on EE.