The explosive growth of user-generated time-series data fuels countless real-time analytics applications but also raises acute privacy risks. Local Differential Privacy (LDP) mitigates this risk by having each client perturb its own data, yet existing pattern-aware LDP techniques still process every stream element, making them unsuitable for resource-limited or latency-constrained environments. We propose Pattern-Aware Unified Local Sampling for Efficient Local Differential Privacy, called PULSE-LDP, a lightweight framework that inserts a Bernoulli sampling step at a per-dataset sampling raterselected via a lightweight per-dataset warm-up procedure before any pattern-aware perturbation. Only the sampled subset of sizer nundergoes local noise addition, and the full stream is reconstructed via piecewise linear interpolation. This design reduces both computation and memory requirements tor2andrtimes those of the unsampled pattern-aware baseline, respectively, while preserving the same ϵ-LDP guarantee and retaining essential temporal motifs. On four diverse public datasets, 15-minute electricity load, transformer telemetry, daily exchange rates, and ten-minute meteorological readings, PULSE-LDP withr= 0.8 incurs only a 7.8% increase in Mean Relative Error (MRE) and a 3.1% rise in Dynamic Time Warping (DTW) relative to the full-data pattern-aware baseline, while reducing runtime by 24.5%. These results demonstrate that PULSE-LDP makes pattern-aware LDP practical for IoT deployments, secure cloud services, and real-time encrypted search.

Deep Neural Networks (DNNs) are increasingly adopted across various industries, driving the demand for deploying their capabilities on mobile devices. However, current mobile inference frameworks often rely on a single processor to execute each model inference, limiting hardware utilization and leading to suboptimal performance and energy efficiency. Expanding DNN accessibility on mobile platforms requires more adaptive and resource-efficient solutions to meet increasing computational demands without compromising device functionality. Nevertheless, performing parallel inference of multiple DNNs on heterogeneous processors remains a significant challenge. Existing studies have explored partitioning DNN operations into subgraphs to enable parallel execution across heterogeneous processors. However, these approaches typically generate excessive subgraphs based solely on hardware compatibility, increasing scheduling complexity and memory management overhead. To address these limitations, we propose the Advanced Multi-DNN Model Scheduling (ADMS) strategy that optimizes multi-DNN inference across heterogeneous processors on mobile devices. ADMS constructs an offline subgraph partitioning strategy that considers both hardware support for operations and scheduling granularity. It also employs a processor-state-aware scheduling algorithm to dynamically balance workloads based on real-time system conditions. This ensures efficient workload distribution and maximizes the utilization of available processors. Experimental results demonstrate that, compared to vanilla inference frameworks, ADMS achieves a 4.04× reduction in multi-DNN inference latency.

Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE–FND framework, context‐aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity‐oriented context‐aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self‐adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero‐shot and few‐shot experiments using GPT‐3.5‐turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE–FND framework, even surpassing advanced GPT‐4.0 and human performance in certain scenarios. To support further LLM–based FND, we have made our approach’s code publicly available on GitHub (our CAPE–FND code: https://github.com/albert-jin/CAPE-FND [Accessed on 2024.09]).

The escalating threats posed by deepfakes to society and cybersecurity have triggered public anxiety, and growing efforts have been devoted to this pivotal research on deepfake detection. The generalization capability of existing models encounters a serious challenge. A prevailing explanation is that models tend to overfit artifacts in fake samples, thereby neglecting the exploration of available real ones. Prior studies have indicated that real images exhibit intra-class clustering and inter-class uniformity in the latent feature space, termed as compactness. Since deepfakes disrupt this property, exploring the common compactness of real samples may boost the generalization of models. In light of this, this paper proposes a targeted C ompact R econstruction L earning ( CRL ) strategy. It applies an enhanced Multi-View Reconstruction Loss (for self-compactness) to reconstruct only real images and a new Real-Sample Compactness Loss (for other-compactness) to bolster ties across real samples. Besides, a novel Joint - G uided R easoning ( JointGR ) module is introduced, which richly fuses features from the encoder-decoder and reconstructed differences. It fully capitalizes on multi-source features from CRL while improving the representational ability of our model. Under the latest benchmark, extensive experiments show our model keeps the competitive performance on most challenging datasets, even achieving state-of-the-art results on some. The code will be open-sourced at https://github.com/Dongyu-Han/CRL .

The widespread adoption of 5 G networks and mobile devices has led to a surge in the generation of private data, creating massive data streams. Securing and continuously releasing histogram data over sliding windows in these streams has become a critical issue, as it enables understanding recent collective phenomena in data streams while preserving individual privacy. Existing state-of-the-art methods require buffering all data from each sliding window to reconstruct accurate histograms, which is unnecessary and significantly hampers efficiency. This paper proposes an online streaming sampling publication framework with differential privacy, named thePublishingApproach withSliding window estimation-count sketch(PAS), which constructs an approximate histogram without buffering each sliding window and subsequently generates publishable histograms. Specifically, we introduce a novel memory-efficient sketch structure called theSliding WindowEstimation-CountSketch(SES), which facilitates rapid retrieval of counts within sliding window intervals while providing guaranteed data protection. The output of this sketch structure approximates true counts while theoretically incorporating differentially private noise, thus ensuring$(\epsilon , \delta )$-differential privacy. Moreover, to improve the speed of histogram generation and reduce processing time in PAS, we propose an adaptive histogram generation algorithm based on SES. Extensive experiments are conducted to demonstrate the effectiveness of the proposed methods in comparison with other publication methods.

In many RFID-enabled applications, objects are classified into different categories, and the information associated with each object's category (called category information) is written into the attached tag, allowing the reader to access it later. The category information sampling in such RFID systems, which is to randomly choose (sample) a few tags from each category and collect their category information, is fundamental for providing real-time monitoring and analysis in RFID. However, to the best of our knowledge, two technical challenges, i.e., how to guarantee a minimized execution time and reduce collection failure caused by missing tags, remain unsolved for this problem. In this paper, we address these two limitations by considering how to use the shortest possible time to sample a different number of random tags from each category and collect their category information sequentially in small batches. In particular, we first obtain a lower bound on the execution time of any protocol that can solve this problem. Subsequently, we present a near-OPTimalCategory information sampling protocol (OPT-C) that solves the problem with an execution time close to the lower bound. Finally, extensive simulation results demonstrate the superiority of OPT-C over existing protocols, while real-world experiments further validate its practicality.

The proliferation of location-aware devices has led to a wide-ranging applicability of trajectory data in diverse real-world scenarios. Despite the prevalent use of the k-means algorithm and differential privacy techniques in mainstream research for the generalization and protection of privacy-sensitive data, limitations persist in effectively reducing noise errors and enhancing overall algorithmic efficiency. This paper addresses the deficiencies observed in existing clustering methodologies applied to user trajectory data, focusing on data privacy preservation and enhanced utility. To this end, we propose a novel incremental clustering framework based on personalized differential privacy. The framework employs dynamic time warping for similarity assessment and incorporates temporal-based cluster protection mechanisms to fulfill privacy requirements. Moreover, it augments the Geo Indistinguishability (GI) privacy protection mechanism to tailor personalized privacy budgets. Subsequently, learning vector quantization is employed for incremental clustering synthesis of trajectory data, completing trajectory publication. Through experimental validation, our proposed model demonstrates significant improvements, with the data usability metric HD increasing by a minimum of 22% compared to existing algorithms, the privacy protection metric AMI improving by at least 18%, and the algorithm’s efficiency enhancing by no less than 20%.

In order to adapt to the development of teaching informatization and meet the needs of students, teachers and parents, it is necessary to strengthen the active participation of students and integrate various curriculum resources, and improve teaching quality and the modes. Comprehensive multimedia software should be produced, including audiovisual and other sensory experiences. This is a concentrated expression of media diversity and networking, which not only breaks the traditional single-source education model, but also improves students’ interest and enthusiasm for learning. As a new teaching tool, multimedia teaching uses the latest computer, multimedia and network technologies to make the presentation of teaching materials more dynamic. This is because it can break through the constraints of time and space and show a high degree of flexibility and interactivity. However, most multimedia teaching and learning in China are faced with problems such as poor interactivity, insufficient programming, product personalization, intellectual property rights and insufficient knowledge of software automation. Therefore, this paper designed the multimedia teaching system from the perspective of psychology through human-computer interaction, so as to improve the teaching quality and promote the diversified development of teaching. The results showed that the multimedia teaching improved by about 9% compared with the traditional model, and the students’ learning effect also improved by about 11% compared with the traditional model.

Many areas are now experiencing data streams that contain privacy-sensitive information. Although the sharing and release of these data are of great commercial value, if these data are released directly, the private user information in the data will be disclosed. Therefore, how to continuously generate publishable histograms (meeting privacy protection requirements) based on sliding data stream windows has become a critical issue, especially when sending data to an untrusted third party. Existing histogram publication methods are unsatisfactory in terms of time and storage costs, because they must cache all elements in the current sliding window (SW). Our work addresses this drawback by designing an efficient online histogram publication (EOHP) method for local differential privacy data streams. Specifically, in the EOHP method, the data collector first crafts a histogram of the current SW using an approximate counting method. Second, the data collector reduces the privacy budget by using the optimized budget absorption mechanism and adds appropriate noise to the approximate histogram, making it possible to publish the histogram while retaining satisfactory data utility. Extensive experimental results on two different real datasets show that the EOHP algorithm significantly reduces the time and storage costs and improves data utility compared to other existing algorithms.

Mobile radio frequency identification (RFID) systems typically experience the continual movement of many tags rapidly going in and out of the interrogating range of readers. Readers that are deployed to maintain a current, real-time list of tags, which are present in the interrogating zone at any moment, must repeatedly execute a series of reading cycles. Each of these reading cycles provides the readers very limited time to identify unknown tags (those newly entering into the reader’s range), and, at the same time, to detect missing tags (those just leaving the reader’s range). In this paper, we study the continuous tag recognition problem, which is critical for mobile RFID systems. First, we obtain a lower bound on communication time for solving this problem. We then design a near-OPTimal protocoL, called OPT-L, and prove that its communication time is approximately equal to the lower bound. Finally, we present extensive simulation and experimental results that demonstrate OPT-L’s superior performance over other existing protocols.

Abstract Today's internet applications generate massive temporal data anywhere and anytime. Although some disk‐based temporal systems are currently available, they suffer from poor I/O performance, especially when applied in intelligent applications deployed in the cloud and edge environments. Therefore, how to process temporal operations with low latency and high throughput becomes a crucial problem for efficient data processing. This paper proposes Timo, a distributed in‐memory temporal query and analytic model for big temporal data. Firstly, a space‐efficient temporal index is proposed to support more efficiently query performance with less memory space than the state‐of‐art methods. Secondly, based on the temporal locality feature of temporal queries, Timo proposes a partitioner mechanism, which utilizes forward scan algorithm, to improve query throughput. Thirdly, some optimal strategies are proposed to improve the execution process of temporal query and analysis, which reduce intermediate result data size and improve the throughput much further. Lastly, we implement the Timo system on the Apache Spark platform, which extends Spark dataset API with temporal query and analysis API functions for users. Extensive experimental results show that the Timo system outperforms other Spark‐based temporal systems in terms of both query latency and throughput.

Connected vehicles, whether equipped with advanced driver-assistance systems or fully autonomous, require human driver supervision and are currently constrained to visual information in their line-of-sight. A cooperative perception system among vehicles increases their situational awareness by extending their perception range. Existing solutions focus on improving perspective transformation and fast information collection. However, such solutions fail to filter out large amounts of less relevant data and thus impose significant network and computation load. Moreover, presenting all this less relevant data can overwhelm the driver and thus actually hinder them. To address such issues, we present Augmented Informative Cooperative Perception (AICP), the first fast-filtering system which optimizes the informativeness of shared data at vehicles to improve the fused presentation. To this end, an informativeness maximization problem is presented for vehicles to select a subset of data to display to their drivers. Specifically, we propose (i) a dedicated system design with custom data structure and lightweight routing protocol for convenient data encapsulation, fast interpretation and transmission, and (ii) a comprehensive problem formulation and efficient fitness-based sorting algorithm to select the most valuable data to display at the application layer. We implement a proof-of-concept prototype of AICP with a bandwidth-hungry, latency-constrained real-life augmented reality application. The prototype adds only 12.6 milliseconds of latency to a current informativeness-unaware system. Next, we test the networking performance of AICP at scale and show that AICP effectively filters out less relevant packets and decreases the channel busy time.

Abstract Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost of scheduling and improving the user satisfaction. However, it is a challenging issue due to stochasticity and non-linearity in bike-sharing systems. In this paper, a model called pseudo-double hidden layer feedforward neural networks is proposed to approximately predict actual demands of bike-sharing. Specifically, to overcome limitations in traditional back-propagation learning process, an algorithm, an extreme learning machine with improved particle swarm optimization, is designed to construct learning rules in neural networks. The performance is verified by comparing with other learning algorithms on the dataset of Streeter Dr bike-sharing station in Chicago.

Radio frequency identification (RFID) has been widely used in many fields such as object tracking and inventory management. For RFID systems, grouping is a fundamental issue which can support efficient multicast transmissions, dynamic tag management, and accurate aggregate queries. Existing grouping protocols have drawbacks of unknown theoretical communication time, high computational cost on the server end and inability to deal with unexpected tags which are those tags whose IDs have not been collected by readers. In this paper, we would like to address the above limitations and consider a more general grouping problem that allows an arbitrary number of unexpected tags to present. Our objective is to design a protocol that guarantees the reader to efficiently and correctly notify each known tag of its group-ID, while the probability that an unexpected tag is mistakenly notified of any group-ID is smaller than a pre-determined value. In this paper, we first obtain a lower bound on the communication time for solving this generalized grouping problem. Then, we propose a near-optimal protocol, called OPT-G, and prove that its communication time approximately equals the lower bound. Finally, we report extensive simulation results that demonstrate OPT-G's near-optimal performance and its superiority over existing baseline schemes.

In many real-time RFID-enabled applications (e.g., logistic tracking and warehouse controlling), a subset of wanted tags is often selected from a tag population for monitoring and querying purposes. How this subset of tags is rapidly selected, which is referred to as the subset selection problem, becomes pivotal for boosting the efficiency in RFID systems. Current state-of-the-art schemes result in high communication latencies, which are far from the optimum, and this degrades the system performance. This problem is addressed in this paper by using a simple Bit-Counting Function BCF(), which has also been employed widely by other protocols in RFID systems. In particular, we first propose a near-OPTimal SeLection protocol, denoted by OPTSL, to rapidly solve this problem based on the simple function BCF(). Second, we prove that the communication time of OPTSL is near-optimal with rigorous theoretical analysis. Finally, we conduct extensive simulations to verify that the communication time of the proposed OPT-SL is not only near-optimal but also significantly less than that of benchmark protocols.

It is an inspiring way to provide emergence communication services in natural disaster areas by deploying wireless routers on the ground and multiple unmanned aerial vehicles (UAVs) in the air. The wireless routers serve as access points. UAVs relay data from routers and themselves to a remote base station in a safe place. Thus, people can communicate with others outside the disaster. The network lifetime is restricted to battery lifetime of routers which are scattered over a complex post-disaster area. There is a potential to prolong the network lifetime by utilizing UAV mobility. We consider the trajectory planning of UAVs with the goal of maximizing the network lifetime, which is modeled as a cooperative game with complete information. However, the time complexity of the problem increases exponentially with the number of UAVs as well as UAV candidate strategies. In our proposal, we boost the game process by excluding some of candidates from the strategy space for each UAV. Specifically, there is no influence for a given UAV, taking the strategies excluded, over the other UAVs. In addition, these strategies are dominated by another strategy at least. Our proposed model is verified through simulations that show its advantage on time complexity over others.

Facilitating real-time query over massive IoT data streams becomes increasingly important nowadays, for that it can boost the performances of real-time network services significantly. Let δ = e1, e2, ⋯ , et, ⋯ represent an IoT data stream, where each element et arrives at time point t. In this paper, we consider the problem of how to support fast range emptiness querying over an IoT data stream δ in sliding window model with a space-efficient data structure, and we denote this problem as the (ε, L)-ARE-problem. To be more formally, subjected to the constraint of one-pass scan of stream δ, the main task of the (ε, L)-ARE-problem is to design a space-efficient data structure that is capable of always representing W(t, n), which are the n latest elements of stream δ until time point t (i.e., W(t, n) = emax{1,t-n+1}, ⋯ , et-1, et), and quickly answering an emptiness query of the form ”W(t, n) ∩ I = 0?”, with a false positive rate no larger than ε, for any query interval I of length up to L. We design a space-efficient data structure D to solve the (ε, L)-ARE-problem and prove that D has constant time cost for querying an interval, inserting a stream element and evicting outdated elements. The efficiency is demonstrated with extensive simulation results as well.

Deploying wireless routers on the ground and unmanned aerial vehicles (UAVs) in the air is believed to be a fast and efficient approach to providing the emergency communication service to disaster areas. The network lifetime is restricted to the lifetime of mesh networks of routers that are scattered across a complex disaster environment. We consider the problem of multi-UAVs relaying and moving with the goal of maximizing the network lifetime. UAVs must learn where to move in order to relay messages from the routers efficiently. However, under the dynamics of the router traffic, that is, the uncertainty of the environment, it is challenging for UAVs to find a movement mechanism that maximizes the network lifetime. By embracing the on-policy reinforcement learning algorithm Sarsa, we are able to demonstrate a greedy movement policy. Specifically, we study the trajectory planning of multiple UAVs in a dense wireless router mesh networks (WMNs) on the ground. UAVs can learn the unknown environment by a little movement of UAVs in each step, in which communication connections between routers with UAVs are retained. A Q-table of movement actions and environment states is formed after multiple attempts of movements. Simulation results show the proposal effectiveness comparing with other methods.

The application of plastic microfluidic chips can be extended with quartz capillaries connected at the end of their microchannels, e.g. UV absorption detection method can be carried out, which responds to almost 80% chemical compounds in detection. A vision-based experiment system for automatically assembling capillaries to plastic microfluidic chips was set up. UN-curing adhesive is used for the joining procedure. Visual feedback is implemented in the assembly system and the control algorithm is briefly introduced. The methods for obtaining the spatial position deviation between the capillary and the end of the chip's micro channel are described. The deviation information in x-y plane is obtained by performing image processing and converting pixels into actual distance with calibrated data. Two methods for recovering vertical deviation information were explored, and both are feasible for application, one is the depth-in-focus, the other is with the use of microscopic stereovision