Recent advancements in multimodal large models have significantly bridged the representation gap between diverse modalities, catalyzing the evolution of video multimodal interpretation, which enhances users' understanding of video content by generating correlated modalities. However, most existing video multimodal interpretation methods primarily concentrate on global comprehension with limited user interaction. To address this, we propose a novel task, Controllable Video Segmentation and Captioning (SegCaptioning), which empowers users to provide specific prompts, such as a bounding box around an object of interest, to simultaneously generate correlated masks and captions that precisely embody user intent. An innovative framework, Scene Graph-guided Fine-grained SegCaptioning Transformer (SG-FSCFormer), is designed to integrate a Prompt-guided Temporal Graph Former to effectively capture and represent user intent through an adaptive prompt adaptor, ensuring that the generated content aligns well with the user's requirements. Furthermore, our model introduces a Fine-grained Mask-linguistic Decoder to collaboratively predict high-quality caption-mask pairs using a Multi-entity Contrastive loss, while providing fine-grained alignment between each mask and its corresponding caption tokens, thereby enhancing the user's comprehension of videos. Comprehensive experiments conducted on two benchmark datasets demonstrate that SG-FSCFormer achieves remarkable performance, effectively capturing user intent and generating precise multimodal outputs tailored to user specifications. Our code is available at https://github.com/XuZhang1211/SG-FSCFormer.

Radio Frequency Identification (RFID) technology plays a pivotal role in modern applications ranging from retail and logistics to healthcare and security. However, a fundamental challenge persists in large-scale RFID systems: maximizing the coverage capacity of readers – the ability to reliably identify and communicate with the maximum number of tags within their operational range. While previous research has explored various aspects of RFID performance, the systematic optimization of coverage capacity remains underinvestigated. This paper addresses this gap by developing a comprehensive framework that integrates theoretical analysis with practical implementation strategies. We first establish a novel coverage capacity model that incorporates critical factors such as tag spatial distribution and link loss dynamics, providing a theoretical foundation for determining the upper bounds of reader performance. Building on this, we propose a cutoff-power-based optimization approach that dynamically adapts to real-world conditions without relying on predefined system parameters. Furthermore, to extend coverage across larger areas, we investigate advanced multi-reader configurations and present strategic deployment methodologies. Our framework is designed to characterize the baseline coverage capacity of existing RFID readers, rather than to enlarge the interrogation zone through additional hardware or protocol modifications. Moreover, it can be naturally extended to advanced configurations such as MIMO or phased-array systems once their antenna parameters are specified. The effectiveness of our approach is validated through extensive experiments using commercial RFID hardware, demonstrating measurable improvements in coverage capability. By bridging theoretical principles with practical constraints, this work offers actionable insights for designing and deploying high-performance RFID systems.

Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leaked gradients. However, can gradient perturbation protection mechanisms truly defend against all gradient leakage attacks? In this paper, we present the first attempt to break the shield of gradient perturbation protection in Federated Learning for the extraction of private information. We focus on common noise distributions, specifically Gaussian and Laplace, and apply our approach to DNN and CNN models. We introduce Mjölnir, a perturbation-resilient gradient leakage attack that is capable of removing perturbations from gradients without requiring additional access to the original model structure or external data. Specifically, we leverage the inherent diffusion properties of gradient perturbation protection to develop a novel diffusion-based gradient denoising model for Mjölnir. By constructing a surrogate client model that captures the structure of perturbed gradients, we obtain crucial gradient data for training the diffusion model. We further utilize the insight that monitoring disturbance levels during the reverse diffusion process can enhance gradient denoising capabilities, allowing Mjölnir to generate gradients that closely approximate the original, unperturbed versions through adaptive sampling steps. Extensive experiments demonstrate that Mjölnir effectively recovers the protected gradients and exposes the Federated Learning process to the threat of gradient leakage, achieving superior performance in gradient denoising and private data recovery.

Adversarial examples generated in digital space may fail to work in the physical world because the recapture process will ruin the adversarial property of the examples. Several approaches have been proposed to generate adversarial examples that can survive in the physical world, they however either introduce markedly perceptible patterns (e.g., adversarial patches) or suffer from a low attack success rate due to improper perturbation propagation. In this work, we propose PRIA, a frequency-based approach to generating Physically Robust and Imperceptible Adversarial examples. PRIA reforms the pipeline of perturbation generation such that adversarial property of the generated examples retains after the recapture process. The experimental results reveal that PRIA outperforms state-of-the-art solutions, improves the attack success rate in the physical world by up to 19%, and meanwhile achieves the highest perceptual quality.

Large language models (LLMs) have been shown to face hallucination issues due to the data they trained on often containing human bias; whether this is reflected in the decision-making process of LLM agents remains under-explored. As LLM Agents are increasingly employed in intricate social environments, a pressing and natural question emerges: Can we utilize LLM Agents' systematic hallucinations to mirror human cognitive biases, thus exhibiting irrational social intelligence? In this paper, we probe the irrational behavior among contemporary LLM agents by melding practical social science experiments with theoretical insights. Specifically, we propose CogMir, an open-ended Multi-LLM Agents framework that utilizes hallucination properties to assess and enhance LLM Agents’ social intelligence through cognitive biases. Experimental results on CogMir subsets show that LLM Agents and humans exhibit high consistency in irrational and prosocial decision-making under uncertain conditions, underscoring the prosociality of LLM Agents as social entities and highlighting the significance of hallucination properties. Additionally, CogMir framework demonstrates its potential as a valuable platform for encouraging more research into the social intelligence of LLM Agents.

Wireless-based human activity recognition has gained increasing attention due to its low cost and non-invasiveness. Among them, RFID stands out for its passive nature and low power consumption. However, existing RFID gesture recognition systems typically assume static device deployment, limiting their applicability in mobile scenarios. To address this, we propose RF-movdev, an RFID-based gesture recognition frame-work that functions reliably under uniform device motion. By introducing a phase correction model, we compensate for motion-induced signal distortion, enabling accurate segmentation, feature extraction, and classification. Experiments under various conditions including different motion speeds, users, and environments demonstrate that RF-movdev improves classification accuracy from 0.14 to 0.61, and achieves up to 0.96 in static settings.

The wide adoption of encryption network traffic protocols, such as TLS/SSL, poses great challenges in the detection and recognition of network traffic. Recently, deep learning techniques have been exploited to detect malicious encrypted traffic. While achieving good performance, deep learning models can be bypassed due to their vulnerabilities to adversarial attacks. There has been some work on generating adversarial traffic to evade deep learning-based systems, however, they fail to generate traffic that complies with network constraints and does not work in practical scenarios. In this paper, we propose a method that can generate legitimate traffic and evade deep models in practical scenarios. The effectiveness of the method comes from two novel designs. First, the perturbations are added to only the payload field to generate legitimate packets. Second, the perturbations are generated in a way that adversarial examples with different multiple of the perturbations can both evade the detection system. Thus, the traffic generated with our method can be restored while all previous works fail to do so. We further designed a joint training method to improve the evasion rate of the generated traffic. Experimental results demonstrated that traffic generated by our method can evade state-of-the-art deep learning detection models with an overall escape success rate of higher than 94 %.

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during training and has been widely adopted in LLM development, potential security risks it may introduce remain uninvestigated. This paper systematically evaluates the resilience of synthetic-data-integrated training paradigm for LLMs against mainstream poisoning and backdoor attacks. We reveal that such a paradigm exhibits strong resistance to existing attacks, primarily thanks to the different distribution patterns between poisoning data and queries used to generate synthetic samples. To enhance the effectiveness of these attacks and further investigate the security risks introduced by synthetic data, we introduce a novel and universal attack framework, namely, Virus Infection Attack (VIA), which enables the propagation of current attacks through synthetic data even under purely clean queries. Inspired by the principles of virus design in cybersecurity, VIA conceals the poisoning payload within a protective “shell” and strategically searches for optimal hijacking points in benign samples to maximize the likelihood of generating malicious content. Extensive experiments on both data poisoning and backdoor attacks show that VIA significantly increases the presence of poisoning content in synthetic data and correspondingly raises the attack success rate (ASR) on downstream models to levels comparable to those observed in the poisoned upstream models.

A boundary is a physical or virtual line that marks the edge or limit of a specific region, which has been widely used in many applications, such as autonomous driving, virtual wall, and robotic lawn mowers. However, none of existing work can well balance the deployability and the scalability of a boundary. In this paper, we propose a brand new RFID-based virtual boundary scheme together with its detection algorithm called RF-Boundary, which has the competitive advantages of being battery-free and easy-to-maintain. We develop two technologies of phase gradient and dual-antenna AoA to address the key challenges posed by RF-boundary, in terms of lack of calibration information and multi-edge interference. Besides, we consider the presence of multipath in the real world applications, model the effect on signals in the dynamic scenarios, and demonstrate the robustness of our phase gradient-based scheme under multipath. We implement a prototype of RF-Boundary with commercial RFID systems and a mobile robot. Extensive experiments verify the feasibility as well as the good performance of RF-Boundary, with a mean detection error of only 8.6 cm.

While decentralized training is attractive in multi-agent reinforcement learning (MARL) for its excellent scalability and robustness, its inherent coordination challenges in collaborative tasks result in numerous interactions for agents to learn good policies. To alleviate this problem, action advising methods make experienced agents share their knowledge about what to do, while less experienced agents strictly follow the received advice. However, this method of sharing and utilizing knowledge may hinder the team's exploration of better states, as agents can be unduly influenced by suboptimal or even adverse advice, especially in the early stages of learning. Inspired by the fact that humans can learn not only from the success but also from the failure of others, this paper proposes a novel knowledge sharing framework called Cautiously-Optimistic kNowledge Sharing (CONS). CONS enables each agent to share both positive and negative knowledge and cautiously assimilate knowledge from others, thereby enhancing the efficiency of early-stage exploration and the agents' robustness to adverse advice. Moreover, considering the continuous improvement of policies, agents value negative knowledge more in the early stages of learning and shift their focus to positive knowledge in the later stages. Our framework can be easily integrated into existing Q-learning based methods without introducing additional training costs. We evaluate CONS in several challenging multi-agent tasks and find it excels in environments where optimal behavioral patterns are difficult to discover, surpassing the baselines in terms of convergence rate and final performance.

The training of multi-agent reinforcement learning (MARL) tasks with the public goods dilemma (PGD) is difficult because the selfish actions of individual agents for high personal rewards may reduce the collective utility of the whole group. Existing solutions to this problem, e.g., reward gifting or intrinsic rewards, although inducing cooperation among agents in small groups, cannot guarantee fairness among agents’ policies and fail to achieve optimal group utility in large-scale systems. In this paper, we propose F4PGD, an effective method to train large-scale MARL tasks with PGD in a decentralized manner, which is inspired by Adam’s equity theory that the match between a person’s payoff and his contribution is the key incentive for people to contribute to the common good. In F4PGD, a mechanism is designed to match an agent’s reward with its contribution, which suppresses agents from taking a free ride and meanwhile encourages well-learned agents to contribute to public goods. Experimental results show that F4PGD effectively learns optimal policies for the whole group and guarantees fairness among agents in several typical MARL tasks with PGD.

A boundary is a physical or virtual line that marks the edge or limit of a specific region, which has been widely used in many applications, such as autonomous driving, virtual wall, and robotic lawn mowers. However, none of existing work can well balance the cost, the deployability, and the scalability of a boundary. In this paper, we propose a new RFID-based boundary scheme together with its detection algorithm called RF-Boundary, which has the competitive advantages of being battery-free, low-cost, and easy-to-maintain. We develop two technologies of phase gradient and dual-antenna DoA to address the key challenges posed by RF-boundary, in terms of lack of calibration information and multi-edge interference. We implement a prototype of RF-Boundary with commercial RFID systems and a mobile robot. Extensive experiments verify the feasibility as well as the good performance of RF-Boundary.

Federated Learning (FL) preserves privacy by training a global model via gradient exchange between the parameter server and local clients rather than raw data sharing. Edge devices with sensors serve as local clients receiving multimodal signals and contributing multimodal data for training. Despite the privacy-centric design of FL, it remains vulnerable to gradient leakage attacks. However, existing studies predominantly focus on single-modality data recovery from gradients, leaving a critical research void in multimodal data scenarios. In this letter, we proposeMGIS: Mutual Gradient Inversion Strategy, the first gradient inversion attack and defense paradigm dealing with multimodal data. Inspired by knowledge distillation, MGIS utilizes common information (e.g., labels) between different modalities to extract multimodal data from gradients. Experimental results demonstrate that MGIS outperforms single-modality gradient attacks in the quality of privacy data recovery and highlight the increased privacy leakage risk associated with multi-modality data compared to single-modality data.

Domain adaptation leverages labeled data from a source domain to learn an accurate classifier for an unlabeled target domain. Since the data collected in practical applications usually contain noise, the weakly-supervised domain adaptation algorithm has attracted widespread attention from researchers that tolerates the source domain with label noises or/and features noises. Several weakly-supervised domain adaptation methods have been proposed to mitigate the difficulty of obtaining the high-quality source domains that are highly related to the target domain. However, these methods assume to obtain the accurate noise rate in advance to reduce the negative transfer caused by noises in source domain, which limits the application of these methods in the real world where the noise rate is unknown. Meanwhile, since source data usually comes from multiple domains, the naive application of single-source domain adaptation algorithms may lead to sub-optimal results. We hence propose a universal and scalable weakly-supervised domain adaptation method called PDCAS to ease restraints of such assumptions and make it more general. Specifically, PDCAS includes two stages: progressive distillation and domain alignment. In progressive distillation stage, we iteratively distill out potentially clean samples whose annotated labels are highly consistent with the prediction of model and correct labels for noisy source samples. This process is non-supervision by exploiting intrinsic similarity to measure and extract initial corrected samples. In domain alignment stage, we consider Class-Aligned Sampling which balances the samples for both source and target domains along with the global feature distributions to alleviate the shift of label distributions. Finally, we apply PDCAS in multi-source noisy scenario and propose a novel multi-source weakly-supervised domain adaptation method called MSPDCAS, which shows the scalability of our framework. Extensive experiments on Office-31 and Office-Home datasets demonstrate the effectiveness and robustness of our method compared to state-of-the-art methods.

Performing accurate sensing in diverse environments is a challenging issue in wireless sensing technologies. Existing solutions usually require collecting a large number of samples to train a classifier for every environment, or further assume similar sample distribution between different environments such that a model trained in one environment can be transferred to another. In this paper, we propose RF-Siamese, an RFID-based gesture sensing approach that achieves comparable accuracy to existing solutions but requires only a few samples in each eivironment. RF-Siamese leverages Siamese networks to distinguish different gestures with only a small number of samples and is enhanced by several novel designs to achieve high accuracy in diverse environments. First, the network structure and parameters (e.g., loss function and distance metric) are carefully designed to be suitable for RFID gesture recognition. Second, a permutation-based dataset generation strategy is proposed to make full use of the collected samples to enhance the recognition accuracy. Third, a template matching method is proposed to extend the Siamese network to classify multiple gestures. Extensive experiments on commercial RFID devices demonstrate that RF-Siamese achieves a high accuracy of 0.93 with only one sample of each gesture when recognizing 18 different gestures, while state-of-the-art approaches based on transfer learning and meta learning achieve an accuracy of only 0.59 and 0.70, respectively.

WiFi-based wireless sensing has gained popularity for enabling smart indoor services, one of which is fall detection which plays a vital role in mitigating health risks for elders. Previous approaches have treated daily activities as independent events and built models to distinguish falls from others. However, human activities are usually adjoint in practice, e.g., the elder may suddenly fall when she walks. This adjoining introduces shared features between different activities, thereby affecting the classification performance. To address this problem, we propose Fall-attention, an attention-based fall detection method that can focus on the features related to fall events and suppress interference of irrelevant activities to improve performance. Its basic idea is to produce a task-oriented feature representation of fall events inside the signal using attention-based sentence embedding techniques and Recurrent Neural Network (RNN). We incorporate multi-task learning into Fall-attention by adopting multiple independent classification modules. This enables the model to explore different regions of the signal, capturing the composition of adjoint activities. A series of signal preprocessing and data enhancement techniques are also adopted to promote model training. Experimental results of the dataset containing adjoint activities demonstrate the superiority of Fall-attention over previous methods, which achieves an average accuracy of 95%.

Recent studies have demonstrated that local training data in Federated Learning can be recovered from gradients, which are called gradient inversion attacks. These attacks display powerful effects on either computer vision or natural language processing tasks. As it is known that there are certain correlations between multi-modality data, we argue that the threat of such attacks combined with Multi-modal Learning may cause more severe effects. Different modalities may communicate through gradients to provide richer information for the attackers, thus improving the strength and efficiency of the gradient inversion attacks. In this paper, we propose the Mutual Gradient Inversion Attack (MGIA), by utilizing the shared labels between image and text modalities combined with the idea of knowledge distillation. Our experimental results show that MGIA achieves the best quality of both modality data and label recoveries in comparison with other methods. In the meanwhile, MGIA verifies that multi-modality gradient inversion attacks are more likely to disclose private information than the existing single-modality attacks.

Histopathological images are the gold standard for diagnosing liver cancer. However, the accuracy of fully digital diagnosis in computational pathology needs to be improved. In this paper, in order to solve the problem of multi-label and low classification accuracy of histopathology images, we propose a locally deep convolutional Swim framework (LDCSF) to classify multi-label histopathology images. In order to be able to provide local field of view diagnostic results, we propose the LDCSF model, which consists of a Swin transformer module, a local depth convolution (LDC) module, a feature reconstruction (FR) module, and a ResNet module. The Swin transformer module reduces the amount of computation generated by the attention mechanism by limiting the attention to each window. The LDC then reconstructs the attention map and performs convolution operations in multiple channels, passing the resulting feature map to the next layer. The FR module uses the corresponding weight coefficient vectors obtained from the channels to dot product with the original feature map vector matrix to generate representative feature maps. Finally, the residual network undertakes the final classification task. As a result, the classification accuracy of LDCSF for interstitial area, necrosis, non-tumor and tumor reached 0.9460, 0.9960, 0.9808, 0.9847, respectively.

Due to the sensitive and confidential nature of healthcare data, it cannot be freely transmitted, resulting in the challenge of data silos. While federated learning offers a solution to this data island dilemma, it also faces potential threats from malicious client attacks. The system becomes more vulnerable when dealing with non-independent and identically distributed (non-IID) data. Hence, a robust federated learning framework is indispensable to defend against malicious attacks. In this study, we employ a dynamic feature extractor based on the sparse representation, and the parameters of each iteration construct the feature extractor for the subsequent parameters. Then, we use optimized k-means clustering to get benign clients and aggregate them. The experimental results show that the system robustness is lower for non-IID datasets compared to IID healthcare datasets. And our RobustHealthFL can significantly enhance the robustness of the system when facing non-IID data. Our code is available at https://github.com/xipengp/RobustHealthFL.

Protein-nucleic acid interactions play a very important role in a variety of biological activities. Accurate identification of nucleic acid-binding residues is a critical step in understanding the interaction mechanisms. Although many computationally based methods have been developed to predict nucleic acid-binding residues, challenges remain. In this study, a fast and accurate sequence-based method, called ESM-NBR, is proposed. In ESM-NBR, we first use the large protein language model ESM2 to extract discriminative biological properties feature representation from protein primary sequences; then, a multi-task deep learning model composed of stacked bidirectional long short-term memory (BiLSTM) and multi-layer perceptron (MLP) networks is employed to explore common and private information of DNA- and RNA-binding residues with ESM2 feature as input. Experimental results on benchmark data sets demonstrate that the prediction performance of ESM2 feature representation comprehensively outperforms evolutionary information-based hidden Markov model (HMM) features. Meanwhile, the ESM-NBR obtains the MCC values for DNA-binding residues prediction of 0.427 and 0.391 on two independent test sets, which are 18.61 and 10.45% higher than those of the second-best methods, respectively. Moreover, by completely discarding the time-cost multiple sequence alignment process, the prediction speed of ESM-NBR far exceeds that of existing methods (5.52s for a protein sequence of length 500, which is about 16 times faster than the second-fastest method). A user-friendly standalone package and the data of ESM-NBR are freely available for academic use at: https://github.com/wwzll123/ESM-NBR.

Learning effective strategies in sparse reward tasks is one of the fundamental challenges in reinforcement learning. This becomes extremely difficult in multi-agent environments, as the concurrent learning of multiple agents induces the non-stationarity problem and sharply increased joint state space. Existing works have attempted to promote multi-agent cooperation through experience sharing. However, learning from a large collection of shared experiences is inefficient as there are only a few high-value states in sparse reward tasks, which may instead lead to the curse of dimensionality in large-scale multi-agent systems. This paper focuses on sparse-reward multi-agent cooperative tasks and proposes an effective experience-sharing method, Multi-Agent Selective Learning (MASL), to boost sample-efficient training by reusing valuable experiences from other agents. MASL adopts a retrogression-based selection method to identify high-value traces of agents from the team rewards, based on which some recall traces are generated and shared among agents to motivate effective exploration. Moreover, MASL selectively considers information from other agents to cope with the non-stationarity issue while enabling efficient training for large-scale agents. Experimental results show that MASL significantly improves sample efficiency compared with state-of-the-art MARL algorithms in cooperative tasks with sparse rewards.

To recognize the target classes with only a few samples, few-shot learning (FSL) uses prior knowledge learned from the source classes and is usually expressed as a special domain adaptation problem. However, Existing few-shot learning methods make the implicit assumption that the few target class samples are from the same domain or different domain as the source class samples, which greatly limits their application in the wild. This paper introduces a few-shot learning method in multiple scenarios which requires no prior knowledge on the label set. For a given target domain labels set, it may overlap with the set of source domain labels to varying degrees, thereby bringing up an additional class gap based on the domain gap. In order to solve this problem in a unified framework, we propose a novel domain adaptation network which is designed to address a specific challenge: How to achieve domain adaptation whilst maintaining source/target per-class discriminativeness when the target domain label set is unseen. Our solution is to design corresponding soft label transfer network and minimax entropy network for different target domain label set, then we quantify the transferability of the source domain label set during the training process to discover the relationship between the source domain label set and the target domain label set. Further, we broaden the model's understanding of the data by learning from self-supervised signals how to solve a jigsaw puzzle on the same sample. Extensive experiments show that our model outperforms the state-of-the-art models.

The number of devices connected to the Internet has been exploding in recent years, and the wide range of device types poses a serious challenge for asset management and maintenance. We need to know if IoT devices are under cyberattack and if there are devices that violate our privacy, such as pinhole cameras. Traffic-oriented IoT device type identification has become an effective method to prevent cyberattacks and manage assets, but at this stage, in the face of the proliferation of novel IoT devices, the current mainstream IoT device type identification methods are difficult to identify them successfully. At the same time, for a significant number of lightweight IoT devices, most identification methods are simply unable to make correct identifications because the traffic generated by these devices is too little. In this paper, we propose IoT-Siamese, a type identification method for IoT devices based on few-shot traffic, which mainly relies on Siamese network to solve the problem of few samples. Experiments show that our proposed identification method has high identification accuracy for those devices that generate a small volume of traffic, and effectively identify novel devices that join the network.

Recently there has been many studies on backdoor attacks, which involve injecting poisoned samples into the training set in order to embed backdoors into the model. Existing multiple poisoned samples attacks usually randomly select a subset from clean samples to generate the poisoned samples. Filtering-and-Updating Strategy (FUS) has shown that the poisoning efficiency of each poisoned sample is inconsistent and random selection is not optimal. However, FUS does not fully considered the selection of multiple poisoned samples, there are still some issues with the selection of multiple poisoned samples. In this paper, we formulate the selection of multiple types of poisoned samples as a multi-objective optimization problem and proposed a Multiple Poisoned Samples Selection Strategy (MPS) to solve the issue. Unlike FUS, we consider the potential of clean samples that are not selected as to become efficient poisoned samples. Specifically, we use a weight-based contribution approach to calculate the contribution of each sample (clean sample and poisoned sample) during the training process from multiple dimensions. Finally, based on the greedy approach, we retain a subset of samples with the largest contribution in each dimension through iterations. We evaluate the effectiveness of MPS on various attack methods, including BadNet, Blended, ISSBA, and WaNet, as well as benchmark datasets. The experimental results on CIFAR-10 and GTSRB show that MPS can increase the attack strength by 1.45% to 18.34% compared to RSS and 0.43% to 10.84% compared to FUS in multiple poisoned samples attacks, thereby enhancing the stealthiness of the attack. Meanwhile, MPS is suitable for black-box settings, meaning that poisoned samples selected in one setting can be applied to other settings.

Deep neural network (DNN) models have been widely used in many tasks due to their superior performance. However, DNN models are usually vulnerable to adversarial example attacks, which limits their applications in many safety-critic scenarios. How to effectively detect adversarial examples to enhance the robustness of DNN models has attracted much attention in recent years. Most adversarial example detection methods require modifying or retraining the model, which is impractical and reduces the classification accuracy of normal examples. In this paper, we propose an adversarial example detection approach that does not require modification of the DNN models and meanwhile retains the classification accuracy of normal examples. The key observation is that when we transform the input example with some operations (e.g., masking a pixel with a reference value), feed the transformed example to the target model, and use the output of the intermediate layers to predict the label of the example, the generated label sequences of adversarial examples will be extremely discrepant but the label sequences of normal examples keep nearly unchanged. Motivated by this observation, we design an approach to detect adversarial examples based on the label sequence discrepancy (LSD) of the given examples. The experimental results against five mainstream adversarial attacks on three benchmark datasets demonstrate that LSD outperforms the state-of-the-art solutions in the detection rate of adversarial examples. Moreover, LSD performs well at various confidence levels and exhibits good generalizability between different attacks.

How to efficiently coordinate multiple readers to work together is critical for high throughput in RFID systems. Existing researchs focus on designing efficient reader scheduling strategies that arrange adjacent readers to work in different time to avoid signal collisions. However, the impact of unbalanced tag number of readers on tag read throughput is still challenging. In RFID systems, the distribution of tags is usually variable and uneven, making the number of tags covered by each reader (i.e., the load) imbalanced. This imbalance leads to different execution time for readers: the heavily loaded readers take longer time to collect all tags, while the other readers whose finish execution earlier have to wait in vain. To avoid this useless waiting and improve the system throughput, this paper focuses on the load balancing problem of multiple readers, which is an NP-hard problem. In this paper, we design heuristic algorithms to adjust readers interrogation regions and efficiently balance their loads. The amazing advantage of our algorithm is that it can be adopted by almost all existing protocols in multi-reader systems, including the reader scheduling protocol, to improve system throughput. Extensive experiments demonstrate that our algorithm can significantly improve the throughput in various scenarios.

RFID systems have been widely deployed for various applications such as inventory control, retail management, and object tracking. In many scenarios, coarse-grained system management of tag categories is more common than traditional system management of individual tags. Existing works on tag category management require knowing category IDs in advance, however, few protocols have been specially designed to obtain category IDs in multi-category RFID systems. In this paper, we proposeCIP, a time-efficient protocol specially designed to collect category IDs in multi-category RFID systems. The challenge in solving this problem is to avoid repeatedly collecting category IDs from multiple tags belonging to the same category. We address this challenge by squeezing tags in the same category into the same time slot and letting them reply to the reader simultaneously. Considering that the reader may receive signals from different tags in a slot, we exploit the Manchester coding to decode the aggregated signals. With this design, CIP collects each category ID only once and thus achieves high time efficiency by avoiding redundant identification of the same category ID. We further enhance CIP by utilizing the lightweight vectors to specify the order of tags’ replying and avoid useless slots. Rigorous theoretical analysis is presented to optimize the performance of CIP and guidelines on how to set optimal parameters to minimize the overall execution time are given. We conduct extensive experiments to evaluate the performance of our protocols. The experimental results show that our protocols can significantly improve time efficiency by 67 percent when compared with the state-of-the-art solutions.

Lip reading can help people with speech disorders to communicate with others and provide them with a new channel to interact with the world. In this paper, we design and implementHearMe, an accurate and real-time lip-reading system built on commercial RFID devices. HearMe can be used to accurately recognize different words in a pre-defined vocabulary without limitations in light conditions and can be used in multiple user scenarios by leveraging RFID's ability in identifying different users. We design an effective data collection strategy to well capture the tiny and complex signal patterns caused by mouth motion and propose a set of algorithms to extract signal profiles related to mouth motions and mitigate interference factors like multi-path. A carefully designed set of features, including time-domain statistical features and frequency-domain features, are then extracted from the signal to lift the recognition accuracy at the word level. To reduce training costs when the model is used in a new environment, a transfer-learning-based approach is adopted to enhance the robustness of the model in cross-environment scenarios. Experimental results show that HearMe detects speaking actions of the user with an accuracy higher than 0.95 and recognizes different words in a 20-words vocabulary with an average accuracy higher than 0.88. Moreover, the latency of HearMe ($\sim$150ms) is nearly two orders of magnitude less than traditional approaches, making it applicable to practical scenarios that require real-time lip reading.

Gesture recognition based on radio frequency identification (RFID) has attracted much research attention in recent years. Most existing RFID-based gesture recognition approaches use signal profile matching to distinguish different gestures, which incur large recognition latency and fail to support real-time applications. In this paper, we design and implement ReActor, a real-time and accurate gesture recognition system that recognizes a user's gestures with low latency and high accuracy even when the gestures'speed varies. ReActor combines the time-domain statistical features and the frequency-domain features to precisely represent the signal profile corresponding to different gestures. To maintain high accuracy across different environments, we preprocess the signals to remove reflection signals from surrounding objects and use only the signals related to gestures to train the classifier. Moreover, we train a classifier to predict the speed of the gesture and feed the extracted features to different classifiers according to the speed. We implement ReActor and evaluate its performance in different scenarios. Experimental results show that ReActor achieves an average accuracy of 97.2% in recognizing 18 different gestures with an average latency of 72 ms, more than two orders of magnitude faster than approaches based on profile template matching.

Although multistage tasks involving multiple sequential goals are common in real-world applications, they are not fully studied in multi-agent reinforcement learning (MARL). To accomplish a multi-stage task, agents have to achieve cooperation on different subtasks. Exploring the collaborative patterns of different subtasks and the sequence of completing the subtasks leads to an explosion in the search space, which poses great challenges to policy learning. Existing works designed for single-stage tasks where agents learn to cooperate only once usually suffer from low sample efficiency in multi-stage tasks as agents explore aimlessly. Inspired by human’s improving cooperation through goal consistency, we propose Multi-Agent Goal Consistency (MAGIC) framework to improve sample efficiency for learning in multi-stage tasks. MAGIC adopts a goal-oriented actor-critic model to learn both local and global views of goal cognition, which helps agents understand the task at the goal level so that they can conduct targeted exploration accordingly. Moreover, to improve exploration efficiency, MAGIC employs two-level goal consistency training to drive agents to formulate a consistent goal cognition. Experimental results show that MAGIC significantly improves sample efficiency and facilitates cooperation among agents compared with state-of-art MARL algorithms in several challenging multistage tasks.

Accurate and reliable indoor location estimate is crucial for many Internet-of-Things (IoT) applications in the era of smart buildings. However, the positioning accuracy and security of the existing positioning works cannot meet the demands in the large-scale smart buildings scenarios covering multiple multifloor buildings. Therefore, in this article, we focus on the reliable and accurate localization under multibuilding and multifloor environments. We propose two novel designs, including a two-step reliable feature selector and a multitask collaborative positioning model. First, we design a two-step reliable feature selector based on an access point (AP) confidence model and manifold learning, to help select the most representative and reliable fingerprint features. Second, we propose a multitask cooperative positioning model, which consists of a multiscale feature fusion module to adaptively fuse multiscale features and a multitask joint learning module to effectively constrain the cumulative error of multiscale position. Finally, based on the above two, we propose a reliable multibuilding and multifloor localization method (RMBMFL), which can achieve accurate and reliable location estimates with low computational complexity in a smart building complex. We did real-world experiments in a 20 000${m^{2}}$site that covers three multistory buildings to evaluate the performance of the proposed RMBMFL. The experimental results show that RMBMFL achieves a building identification accuracy and a floor identification accuracy of 99%, and a room-level indoor localization with an average positioning error within 2 m, and outperforms state-of-the-art solutions.

RFID technology has been widely applied in a range of applications such as inventory control, warehouse management and supply chain logistics. Many practical applications need to search a given set of tags (calledwanted tags) to determine which of them are present in the system, which is usually calledtag searching. Existing tag searching protocols suffer performance bottleneck and the time efficiency and need to be improved. The bottleneck stems from two factors. First, the existing methods validate the wanted tags in a random way due to the randomness of the hash function, which unavoidably generate many useless slots. Second, in order to achieve the predefined reliability requirement, the existing methods have to repeatedly validate target tags multiple times. In this paper, we design new tag searching techniques of compact exclusive validation that break through the existing performance bottleneck from two aspects. First, our protocols avoid slot waste. Different from random tag validation, our protocols validate tags orderly by mapping the wanted tags and the slots in a one-to-one manner, which makes the reader be able to validate tags in every slot. Second, our protocols avoid repeated tag responding. By combining two lightweight indicators, we rapidly filter out non-wanted tags so that there is no interference when validating the wanted tags. Hence, we need to validate each wanted tag only once, which avoids redundant validation and greatly improves time efficiency. Our protocols work with the assumption that the rough number of tags in the system can be obtained by using existing estimation algorithms, but they do not need to know exactly which tags are in the system. Theoretical analysis illustrates our methods achieve linear time complexity. Extensive experimental results show that, our best protocol can improve the time efficiency by up to 81 percent when compared with the-state-of-art solution.

RFID is becoming ubiquitously available in our daily life. After RFID tags are deployed to make attached objects identifiable, a natural next step is to communicate with the tags and collect their information for the purpose of tracking tagged objects or monitoring their surroundings in real-time. In this paper, we study an under-investigated problem range detection in a commodity RFID system, which aims to check if there are any tags with the data between an upper and lower boundary in a time-efficient way. This is important especially in a large RFID system, which can help users quickly pinpoint the target tags (if any) and give an early warning to users for taking urgent actions and reducing the potential risk in the nascent stage. We propose two tailored protocols, selective query and range query, to achieve range detection within the scope of the C1G2 standard. The novelty is that, instead of querying each tag, we exploit the capability of C1G2-compatible selection and quickly separate target tags from others by silencing most of tags. The final result is that range query is able to achieve a range detection with only one query command. We implement the proposed protocols in commodity RFID systems, with no need for any hardware modifications. Extensive experiments show that range query is able to improve the time efficiency by an order of magnitude, compared with the baseline.

Weakly-supervised domain adaptation has been introduced to address the source domain with label noise or/and feature noise. However, the existing weakly-supervised domain adaptation methods only work under ideal assumptions, which assume either the annotated data of the target domain can be accessed or the noise rate of all the classes is identical and already known. This limits their practical application. To tackle this, we propose a universal weakly-supervised domain adaptation method called PDCAS which relaxes the ideal assumptions and makes it more general. Specially, PD- CAS includes two stages: progressive distillation and domain alignment. In progressive distillation, we iteratively distill out potentially corrected samples whose annotated labels are consistent with the prediction of model. By exploiting intrinsic similarity to extract initial corrected samples, this process does not need any supervision. In domain alignment, besides taking the global feature distributions into consideration, we also adopt Class-Aligned Sampling which balances the samples for both source and target domains to alleviate the shift of label distributions. Extensive experiments on Office-31 and Office-Home datasets demonstrate the effectiveness and robustness of our method compared to state-of-the-art methods.

How to efficiently coordinate multiple readers to work together is critical for high throughput in RFID systems. Existing researchers focus on designing efficient reader scheduling strategies that arrange adjacent readers to work in different time to avoid signal collisions. However, the impact of unbalanced tag number of readers on tag read throughput is still very challenging. In RFID systems, the distribution of tags is usually variable and uneven, which makes the number of tags covered by each reader (i.e. the load of it) imbalanced. This imbalance leads to different execution time for readers: the heavy load readers take longer time to collect all tags, while the other readers that finish execution earlier have to wait for nothing. To avoid this useless waiting and improve the system throughput, this paper focuses on the load balancing problem of multiple readers. It is an NP-hard problem, for which we design heuristic algorithms that adjust readers’ interrogation regions according to designed strategies to efficiently balance their loads. The amazing advantage of our algorithm is that it can be adopted by almost all existing protocols in multi-reader systems, including the reader scheduling protocol, to improve system throughput. Extensive experiments demonstrate that our algorithm can significantly improve the throughput in various scenarios.

Radio-frequency identification (RFID) has been utilized in many applications, such as supply chain and stock management in supermarkets. RFID systems in such practical applications are inherently dynamic because tags may move in and out frequently. One important but challenging problem in such systems is how to estimate the number of dynamic tags fast and reliably. This article proposes effective solutions to this problem, which guarantee the accuracy of estimation and time efficiency. Especially, we want to simultaneously estimate the number of tags that moved out of the system (missing tags) and the number of tags that entered the system (unknown tags) in a specified time interval. We design a novel method called time slot reuse (TSR) that generates two logical frames corresponding to the two types of tags from only one physical frame. Based on TSR, we propose a protocol called SSR that can accurately estimate the number of dynamic tags by using the generated logic frames. However, the performance of SSR degrades significantly when the disparity between the number of the two types of tags is remarkable. We further propose an enhanced version of SSR (ESSR), which overcomes this drawback by partitioning the frame into ranges and mapping different types of tags into different ranges. Rigorous theoretical analysis is performed to tune parameters in SSR and ESSR to minimize the execution time. The simulation results demonstrate up to 80% improvement in time efficiency when compared with state-of-the-art solutions to the same problem.

Vital signs (e.g., respiration rate or heartbeat rate) sensing is of great importance to implement pervasive in-home healthcare. Traditional vital signs monitoring approaches usually require users to wear some dedicated sensors. These approaches are intrusive and inconvenient to use, especially for elderly people. Some non-intrusive vital signs monitoring approaches based on wireless sensing have been proposed in recent years. However, these approaches require the target user to be in situ during the monitoring process, which greatly limits their utilization in practical scenarios where the target users usually move around. In this paper, we propose RF-RMM, an RFID-based approach to accurate and continuous respiration monitoring for mobile users. The major challenge in respiration monitoring for moving people is that the tiny body displacement caused by the user's respiration is overwhelmed by the user's entire body movement. To address this issue, we propose a novel approach that uses a pair of tags to eliminate the effect of the user's body movement. We fuse the data from the paired tags to cancel the effect of the user's entire body movement and retain only the displacement caused by the user's respiration. Another challenging issue in implementing RF-RMM is how to resolve the phase ambiguity problem when the target user moves around, which becomes more serious than in the static case. We propose a distance tracking algorithm to track the phase transition during the user's movement, according to which the phase ambiguity problem can be well handled. We implement RF-RMM on commercial RFID devices and conduct extensive real-world experiments to evaluate its performance. The results show that RF-RMM achieves accurate respiration rate monitoring with an average error of 0.54 BPM in estimating different users' respiration rate and an average relative error of less than 13% in estimating the user's individual breath length.

By integrating the micro-sensor on RFID tags to obtain the environment information, the sensor-augmented RFID system greatly supports the applications that are sensitive to environment. To quickly collect the information from all tags, many researchers dedicate on well arranging tag replying orders to avoid the signal collisions. Compared to from all tags, collecting information from a part of tags (i.e., target tags) is more challenging because the collecting process is interfered by useless replying from non-target tags. The existing works of target tag information collection are designed for single reader systems. However, they cannot work efficiently in more common multi-reader scenarios, where each reader lacks knowledge of tag distribution among all readers. In this paper, we propose time-efficient protocols to collect target tag information in multi-reader systems. The high efficiency of our protocol is enabled by two novel designs. First, we develop a technique that quickly detects and silences non-target tags without a priori knowledge of which tags are in the readers' interrogation regions. Second, we design an allocation vector to efficiently arrange the replying order of only target tags. Different from previous bit-vector based approaches that make use of only singleton slots, our allocation vector approach also makes use of collision slots to speed up target tag information collection. We further propose an enhancement protocol which can reconcile the collision slots with higher probability and therefore collect information from more target tags simultaneously. The extensive simulation results demonstrate that our protocols significantly outperform the state-of-the-art protocols in terms of time-efficiency.

Multi-agent reinforcement learning system is used to solve the problem that agents achieve specific goals in the interaction with the environment through learning policies. Almost all existing multi-agent reinforcement learning methods assume that the observation of the agents is accurate during the training process. It does not take into account that the observation may be wrong due to the complexity of the actual environment or the existence of dishonest agents, which will make the agent training difficult to succeed. In this paper, considering the limitations of the traditional multi-agent algorithm framework in noisy environments, we propose a multi-agent fault-tolerant reinforcement learning (MAFTRL) algorithm. Our main idea is to establish the agent's own error detection mechanism and design the information communication medium between agents. The error detection mechanism is based on the autoencoder, which calculates the credibility of each agent's observation and effectively reduces the environmental noise. The communication medium based on the attention mechanism can significantly improve the ability of agents to extract effective information. Experimental results show that our approach accurately detects the error observation of the agent, which has good performance and strong robustness in both the traditional reliable environment and the noisy environment. Moreover, MAFTRL significantly outperforms the traditional methods in the noisy environment.

The complicated interior structure of the high-rise buildings brings great difficulties for fire escape routes planning. Existing two-dimensional (2D) emergency evacuation models are utilized to solve the problem of guidance and rescue for fire responders. However, these models are faced with a bottleneck of low security due to limited environmental information and no consideration of trapped personnel behavior features. In this paper, we propose DERP, a dynamic escape route planning method that achieves accurate disaster site avoidance and safety route planning considering fire situation awareness in a smart building. DERP is enabled by two novel designs. First, a three-dimensional (3D) fire information model is constructed by cellular automata considering the overall situation of indoor 3D topological structure, fire situation and crowd distribution. Second, a multiple constraints 3D indoor emergency escape route planning algorithm is designed based on a 3D path safety function. The experimental results show that DERP can plan and adjust the escape route timely and dynamically, thus increasing the escape probability of the trapped people.

Radio frequency identification (RFID) has been widely used in many smart applications. In many scenarios, it is essential to know the ordering of a set of RFID tags. For example, to quickly detect misplaced books in smart libraries, we need to know the relative ordering of the tags attached to the books. Although several relative RFID localization algorithms have been proposed, they usually suffer from large localization latency and cannot support applications that require real-time detection of tag (product) positions like automatic manufacturing on an assembly line. Moreover, existing approaches face significant degradation in ordering accuracy when the tags are close to each other. In this paper, we propose RLLL, an accurate Relative Localization algorithm for RFID tags with Low Latency. RLLL reduces localization latency by proposing a novel geometry-based approach to identifying the V-zone in the phase reading sequence of each tag. Moreover, RLLL uses only the data in the V-zone to calculate relative positions of tags and thus avoids the negative effects of low-quality data collected when the tag is far from the antenna. Experimental results with commercial RFID devices show that RLLL achieves an ordering accuracy of higher than 0.986 with latency less than 0.8 seconds even when the tags are spaced only 7 mm from adjacent tags, in which case the state-of-the-art solutions only achieve ordering accuracy of lower than 0.8 with localization latency larger than 3 seconds.

Tag searching is a fundamental problem for a variety of radio frequency identification (RFID) applications. Prior works focus on single group searching, which refers to determining which ones in a given set of tags exist in the system. In this paper, we propose PTS, a protocol that can perform fast Parallel Tag Searching for multiple users simultaneously. Different from prior works that have to execute k times to search k groups separately, PTS obtains searching results for all the k groups with only one-shot execution. PTS achieves high parallelism due to some novel designs. First, we develop a grouping filter that encodes the membership of tags in different groups, with which non-target tags can be efficiently filtered out for all the k groups simultaneously. Second, we design two new codes, grouping code and mapping code, with which the remaining tags can quickly verify and confirm which group they belong to. We theoretically analyze how to set optimal parameters for PTS to minimize the execution time and conduct extensive simulation experiments to evaluate its performance. Compared with the state-of-the-art solutions, PTS significantly improves time efficiency in multiple group searching scenarios (by a factor of up to 7.54X when k = 10) and achieves the same time efficiency in single group searching scenarios.

We propose a new radio frequency identification (RFID) localization approach that achieves both low latency and high accuracy by fusing multiple type of signal features. Existing RFID tag localization approaches either suffer from large localization latency (e.g., approaches based on phase measurements), or cannot provide high localization accuracy (e.g., approaches based on received signal strength (RSS)). We propose a two-step approach that fuses phase measurements and RSS measurements to resolve this dilemma. First, coarse-grained RSS measurements are utilized to Figure out a small bounding box that encloses the position of the target tag. Second, fine-grained phase measurements are used to refine the position estimation of the target tag in the bounding box. Experimental results show that the proposed fusion approach achieves centimeter-level localization accuracy with less than 10 feature measurements, reducing localization latency by more than one order of magnitude when compared to state-of-the-art solutions.

Domain adaptation aims to transfer knowledge across different domains and bridge the gap between them. While traditional knowledge transfer considers identical domain, a more realistic scenario is to transfer from a larger and more diverse source domain to a smaller target domain, which is referred to as partial domain adaptation (PDA). However, matching the whole source domain to the target domain for PDA might produce negative transfer. Samples in the shared classes should be carefully selected to mitigate negative transfer in PDA. We observe that the correlations between different target domain samples and source domain samples are diverse: classes are not equally correlated and moreover, different samples have different correlation strengthes even when they are in the same class. In this study, we propose ECDT, a novel PDA method that Exploits the Correlation Diversity for knowledge Transfer between different domains. We propose a novel method to estimate target domain label space that utilizes the label distribution and feature distribution of target samples, based on which outlier source classes can be filtered out and their negative effects on transfer can be mitigated. Moreover, ECDT combines class-level correlation and instance-level correlation to quantity sample-level transferability in domain adversarial network. Experimental results on three commonly used cross-domain object data sets show that ECDT is superior to previous partial domain adaptation methods.

Unmanned aerial vehicles (UAVs) are powerful tools for several applications like transportation and observation. The main reason is the enormous capabilities of such aerial vehicles in terms of mobility, autonomy, communication and processing power at a relatively low-cost. In recent years, due to the continuous development of UAV technology, it has broad prospects in regional coverage application. However, in practical applications, it is very difficult to get an actual mathematical model because of the limited data obtained. Therefore, we chose to use reinforcement learning to solve this problem. In this paper, we form a rule by Reinforcement Learning to cover the coverage of UAVs. We mainly solve two problems: (1) Reduce UAV energy consumption by reducing UAV action times. (2) Solve the huge problem of the dimension space of the value function by using the Actor-Critic algorithm. We compare our method with the traditional coverage method, the result shows that the UAV using the reinforcement learning model consumes less energy often when the same coverage area is completed.

Contactless gesture recognition has emerged as a promising technique to enable diverse smart applications, e.g., novel human-machine interaction. Among others, gesture recognition based on radio frequency identification (RFID) is preferred due to its prevalent availability, low cost, and ease in deployment. However, current RFID-based gesture recognition approaches usually use profile template matching to distinguish different gestures, making them suffer from large recognition latency and fail to support real-time applications. In this paper, we propose a real-time and accurate contactless RFID-based gesture recognition approach called ReActor. ReActor uses machine learning rather than time-consuming profile template matching to distinguish different gestures, and thus achieves both very low recognition latency and high recognition accuracy. The major challenge of our approach is to determine a set of suitable attributes that can preserve the profile features of the signals related to different gestures. We combine two types of attributes in ReActor: the statistics of the signal profile that characterize coarse-grained features and the wavelet (transformation) coefficients of the signal profile that characterize fine-grained local features, both of which can be calculated fast. Experimental results demonstrate that ReActor can recognize a gesture with average latency less than 51ms, two orders of magnitude faster than state-of-the-art approaches based on profile template matching. Furthermore, ReActor also achieves higher recognition accuracy than previous works due to its optimized attribute set.

Internet of Things (IoT) have been widely used in many fields including smart city, industry Internet and automatic driving. Because IoT end devices usually have only limited capability in computation and power supply, they are not suitable to execute energy-consuming computational tasks. In many cases, we need to offload computational tasks from IoT end devices to edge servers in order to save energy consumption on the end devices. This process is usually termed as computing offloading. In this paper, we study computing offloading in radio frequency identification (RFID) systems built with mobile readers. We analyze the energy consumption characteristics of different components in mobile RFID systems, based on which we propose a framework to perform energy-aware offloading for such systems. By using tag searching as an example, we illustrate how our framework can help offload computational intensive tasks to edge servers to save energy consumption on mobile readers while satisfying the constraint on total execution time. Simulation results shown that the energy consumption of mobile readers can be greatly reduced by using our offloading framework.

Localization plays a pivotal role in wireless sensor networks. Many range-based localization algorithms have been proposed for 2-D sensor networks or densely deployed 3-D sensor networks. However, range-based localization in sparse 3-D sensor networks is still a challenging problem, because the sparseness of the network makes it difficult to obtain a proper order of nodes to be sequentially localized. The patch-and-stitching localization strategy can conquer the sparseness problem in 2-D networks, but for 3-D networks it is still unknown how to uniquely merge two patches when there are not enough common nodes. In this paper, we solve this challenging problem by deriving the conditions under which two subnetworks can be uniquely merged. In the proposed approach, we treat the translation parameters as unknowns and form a set of equations with which the unknowns can be uniquely solved. The novelty of our algorithm also lies in that we exploit both common nodes and connecting edges among adjacent subnetworks to merge them, resulting in very high chances that two subnetworks can be merged. We conduct extensive simulation experiments to evaluate the performance of the proposed algorithm. The results show that the proposed algorithm could localize more than 90% of nodes in sparse 3-D networks with average node degree of 11 and anchor ratio of 5%, while the best existing solution can localize only 52% of nodes in the same situation.

RFID tags have been widely deployed to report valuable information about tagged objects or surrounding environment. To collect such information, the key is to avoid the tag-to-tag collision in the open wireless channel. Polling, as a widely used anti-collision protocol, provides a request-response way to interrogate tags. The basic polling however needs to broadcast the tedious tag ID (96 bits) to query a tag, which is time-consuming. For example, collecting only 1-bit information (e.g., battery status) but with 96-bit overhead is a great limitation. This paper studies how to design efficient polling protocols to collect tag information quickly. The basic idea is to minimize the length of the polling vector as well as to avoid useless communication. We first propose an efficient Hash polling protocol (HPP) that uses hash indices rather than tag IDs as the polling vector to query each tag. The length of the polling vector is dropped from 96 bits to no more than 16 bits (the number of tags is less than 100,000). We then propose a tree-based polling protocol (TPP) that avoids redundant transmission in HPP. By constructing a binary polling tree, TPP transmits only different postfix of the neighbor polling vectors; the same prefix is reserved without any retransmission. The result is that the length of the polling vector reduces to only 3.4 bits. Finally, we propose an incremental polling protocol (IPP) that updates the polling vector based on the difference in value between the current polling vector and the previous one. By sorting the indices and dynamically updating them, IPP drops the polling vector to 1.6 bits long, 60 times less than 96-bit IDs. Extensive simulation results show that our best protocol IPP outperforms the state-of-the-art information collection protocol.

Traditional mobile crowdsensing photo selection process focuses on selecting photos from participants to a server. The server may contain tons of photos for a certain area. A new problem is how to select a set of photos from the server to a smartphone user when the user requests to view an area (e.g., a hot spot). The challenge of the new problem is that the photo set should attain both photo coverage and view quality (e.g., with clear Points of Interest). However, contributions of these geo-tagged photos could be uncertain for a target area due to unavailable information of photo shooting direction and no reference photos. In this paper, we propose a novel and generic server-to-requester photo selection approach. Our approach leverages a utility measure to quantify the contribution of a photo set, where photos' spatial distribution and visual correlation are jointly exploited to evaluate their performance on photo coverage and view quality. Finding the photo set with the maximum utility is proven to be NP-hard. We then propose an approximation algorithm based on a greedy strategy with rigorous theoretical analysis. The effectiveness of our approach is demonstrated with real-world datasets. The results show that the proposal outperforms other approaches with much higher photo coverage and better view quality.

As one of the enabling technologies for Internet of Things (IoTs), radio frequency identification (RFID) has been widely adopted in many applications. Among others, RFID-based localization has attracted much research attention in recent years. Existing RFID localization algorithms are usually based on single signal feature, e.g., received signal strength (RSS) or phase information. These algorithms cannot achieve high localization accuracy and low delay simultaneously: Algorithms based on RSS usually suffer from low localization accuracy, while algorithms based on phase suffer from large localization delay because they need to collect a large number of phase readings to resolve phase ambiguity. In this paper, we propose an RFID localization algorithm that can achieve both high accuracy and low delay by fusing multiple types of signal features. We first use the RSS measurements to quickly shrink the possible region of the target tag, and then use phase measurements to refine the position estimation. Experiment results demonstrate the effectiveness of this novel design.

In this paper, we study the tag size profiling (TSP) problem in RFID systems with multiple readers, which is to estimate the number of tags in every subregion in the system covered by different set of readers. The TSF problem is vitally important to reader scheduling and many other related operations in large scale multi-reader RFID systems. To our knowledge, however, it is not well solved in previous researches. We propose a novel approach to the TSF problem. The key idea is to treat the size of subregions as variables and construct a linear system in these variables to solve them. We theoretically prove that for any multi-reader RFID system, a linear system that can be used to uniquely solve the variables corresponding to the subregion sizes can always be constructed. We then propose a time-efficient algorithm that uses two heuristics to quickly find enough linearly independent equations to construct the linear system. Extensive simulation results show that the proposed approach achieves very high accuracy. When the estimation results of individual readers contain 5% errors, our approach achieves median estimation error of smaller than 0.02 and 90-percentile estimation error of smaller than 0.04 in large systems containing more than one hundred readers.

Radio Frequency IDentification (RFID) plays a vital role in smart computing applications. Due to the limited communication range of individual RFID readers, large RFID systems deployed in real applications usually contain multiple readers. Existing reader scheduling algorithms either disallow adjacent readers to simultaneously work in order to avoid collisions among them, or simply activate all the readers to work together to exploit the parallel working of readers to increase identification throughput. In this paper, we propose a reader scheduling algorithm that tolerates collisions among readers but selects an optimal set of readers that can maximize tag identification throughput to work in parallel. The proposed algorithm thus achieves much higher tag identification throughput than existing solutions. Experiment results in a small testbed containing three readers show that, compared with the state-of-the-art solution, the proposed algorithm enhances tag identification throughput by 40%. Results from extensive simulation experiments further demonstrate that the proposed algorithm performs much better than existing solutions in large RFID systems. For example, the proposed algorithm achieves 132% higher identification throughput than previous best solution in systems containing more than one hundred readers when the readers are randomly deployed, meanwhile achieves much smaller identification delay.

An RFID system can greatly improve the efficiency of tagged object inventory setup and update. It is necessary to periodically take stock of tags and update the inventory accordingly (i.e., deleting absent tags and adding new tags) in dynamic scenarios such as warehouses and shopping malls. Fast tag stocktaking is critical for the dynamic RFID system management. Previous work can take stock of tags by either collecting IDs of all the tags in the system, which is known to be inefficient, or broadcasting a long indicator vector to save tag identification time, which is not compatible with current commercial-off-the-shelf (COTS) tags. In this paper, we propose HARN, a protocol that can quickly take stock of tags in dynamic RFID systems but is compatible with COTS RFID tags and easily applied in a real RFID system. HARN uses only one more hash in the standard EPC C1G2 protocol. It leverages the new hash to generate the random number (RN) for a tag that can be used for both channel contention and known tag recognition, which can save the tedious ID transmission from known tags to readers and greatly speed up the stocktaking of tags. Simulation results demonstrate that HARN improves stocktaking throughput by up to 3.8x when compared to the state-of-the-art solutions in dynamic RFID systems.

Fast tag identification is a fundamental challenging problem in multi-reader RFID systems. The challenge is how to effectively handle Reader-Tag (RT) collisions and Reader-Reader (RR) collisions among adjacent readers. These collisions are caused by interfering signals simultaneously transmitted by the readers, and may disallow adjacent readers to work together. Prior works tackle this problem by scheduling adjacent readers to work in different time slots. The readers that are selected to simultaneously work, however, are usually only a small proportion of the total readers. This greatly restricts the identification throughput. Our insightful investigation on the current tag identification protocol reveals that RT collisions are caused by asynchronous actions of readers. i.e., a reader transmits signal while its adjacent readers receive. We thus develop Slot Splitting, a technique that can completely eliminate RT collisions by synchronizing actions of readers. We also propose a reader selection algorithm that minimizes RR collisions by selecting a reader set with maximum reading efficiency. The combination of these new techniques inspires Federal, a Fast and efficient tag identification protocol with interference-elimination-based reader scheduling. To our knowledge, Federal is the first identification protocol that completely eliminates RT collisions and minimizes RR collisions in both regularly and randomly deployed multi-reader systems. We validate the feasibility of Slot Splitting with experiments on the USRP platform and evaluate the performance of Federal through extensive simulations. The results show that Federal can increase tag identification throughput by up to 218% compared with the state-of-the-art work.

Polling is a widely used anti-collision protocol that interrogates RFID tags in a request-response way. In conventional polling, the reader needs to broadcast 96-bit tag IDs to separate each tag from others, leading to long interrogation delay. This paper takes the first step to design fast polling protocols by shortening the polling vector. We first propose an efficient Hash Polling Protocol (HPP) that uses hash indices rather than tag IDs as the polling vector to query each tag. The length of the polling vector is dropped from 96 bits to no more than log(n) bits (n is the number of tags). We then enhance HPP (EHPP) to make it not only more efficient but also more steady with respect to the number of tags. To avoid redundant transmissions in both HPP and EHPP, we finally propose a Tree-based Polling Protocol (TPP) that reserves the invariant portion of the polling vector while updates only the discrepancy by constructing and broadcasting a polling tree. Theoretical analysis shows that the average length of the polling vector in TPP levels off at only 3.44, 28 times less than 96-bit tag IDs. We also apply our protocols to collect tag information and simulation results demonstrate that our best protocol TPP outperforms the state-of-the-art information collection protocol.

Radio Frequency Identification (RFID) technology brings a revolutionary change in warehouse management by automatically monitoring and tracking products. For many RFID-enabled applications, fast searching a particular group of products is practically important in a large-scale RFID system. Different from previous searching protocols, we propose a physical layer tag searching (PLAT) protocol, which makes three fundamental improvements. First, PLAT can exactly pinpoint the search result without false positives at a small delay expense. Second, based on the physical layer signals, PLAT can interpret the accurate number of tags replying in a collision slot, speeding up the execution of tag searching. Third, PLAT can take the global view of the accurate replying information from slots to extract each tag identifier, further improving the protocol performance. We also implement a prototype system based on the USRP and WISP platform. Experimental results validate the feasibility of our protocol. The extensive simulations show PLAT produces the performance gain by a factor of above 2 compared with the state-of-the-art works.

Tag scanning is an important issue to dynamically manage tag IDs in radio frequency identification (RFID) systems. Different from tag identification that collects IDs of all the tags, tag scanning first verifies whether or not a responding tag has already been identified and retrieves its ID when the answer is yes, and collects the tag's ID only when it is unidentified. In this paper, we present the first study on spot scanning with a handheld reader, which aims to scan tags in the reader's interrogation range at an arbitrarily specified position in the system. Existing studies mainly focus on continuous scanning, and they are highly time inefficient in performing spot scanning. The inefficiency stems from the small overlap between tag populations in different spot scanning operations, in which case existing solutions cannot efficiently recognize unidentified tags. We develop a novel technique called LOCK to efficiently recognize unidentified tags even when the overlapped tags are few. LOCK does not simply use a tag's reply slot index but also compact short responses from tags to efficiently distinguish unidentified tags from identified ones. The valuable compact short responses are firstly investigated, which are the keys for efficient tag identification in the paper. Based on LOCK, three tag scanning protocols are proposed to solve the spot scanning problem. Simulation results show that, for spot scanning, our best protocol reduces per tag scanning time by up to 70 percent when compared with the state-of-the-art solution. Moreover, the proposed protocols can also be employed to perform continuous scanning with better time efficiency than the best existing solutions.

The radio frequency identification (RFID) technology is greatly revolutionizing applications such as warehouse management and inventory control in retail industry. In large RFID systems, an important and practical issue is tag searching: Given a particular set of tags called wanted tags, tag searching aims to determine which of them are currently present in the system and which are not. As an RFID system usually contains a large number of tags, the intuitive solution that collects IDs of all the tags in the system and compares them with the wanted tag IDs to obtain the result is highly time inefficient. In this paper, we design a novel technique called testing slot, with which a reader can quickly figure out which wanted tags are absent from its interrogation region without tag ID transmissions. The testing slot technique thus greatly reduces transmission overhead during the searching process. Based on this technique, we propose two protocols to perform time-efficient tag searching in practical large RFID systems containing multiple readers. In our protocols, each reader first employs the testing slot technique to obtain its local searching result by iteratively eliminating wanted tags that are absent from its interrogation region. The local searching results of readers are then combined to form the final searching result. The proposed protocols outperform existing solutions in both time efficiency and searching precision. Simulation results show that, compared with the state-of-the-art solution, our best protocol reduces execution time by up to 60 percent, meanwhile promotes the searching precision by nearly an order of magnitude.

Cloning attacks seriously impede the security of radio-frequency identification (RFID) applications. This paper tackles deterministic clone detection for anonymous RFID systems without tag identifiers (IDs) as a priori. Existing clone detection protocols either cannot apply to anonymous RFID systems due to necessitating the knowledge of tag IDs or achieve only probabilistic detection with a few clones tolerated. This paper proposes three protocols—BASE, DeClone, and DeClone+—toward fast and deterministic clone detection for large anonymous RFID systems. BASE leverages the observation that clone tags make tag cardinality exceed ID cardinality. DeClone is built on a recent finding that clone tags cause collisions that are hardly reconciled through rearbitration. For DeClone to achieve detection certainty, this paper designs breadth first tree traversal toward quickly verifying unreconciled collisions and hence the cloning attack. DeClone+ further incorporates optimization techniques that promise faster clone detection when clone ratio is relatively high. The performance of the proposed protocols is validated through analysis and simulation. This paper also suggests feasible extensions to enrich their applicability to distributed design.

Position information plays a pivotal role in wireless sensor network (WSN) applications and protocol/algorithm design. In recent years, range-free localization algorithms have drawn much research attention due to their low cost and applicability to large-scale WSNs. However, the application of range-free localization algorithms is restricted because of their dramatic accuracy degradation in practical anisotropic WSNs, which is mainly caused by large error of distance estimation. Distance estimation in the existing range-free algorithms usually relies on a unified per hop length (PHL) metric between nodes. But the PHL between different nodes might be greatly different in anisotropic WSNs, resulting in large error in distance estimation. We find that, although the PHL between different nodes might be greatly different, it exhibits significant locality ; that is, nearby nodes share a similar PHL to anchors that know their positions in advance. Based on the locality of the PHL, a novel distance estimation approach is proposed in this article. Theoretical analyses show that the error of distance estimation in the proposed approach is only one-fourth of that in the state-of-the-art pattern-driven scheme (PDS). An anchor selection algorithm is also devised to further improve localization accuracy by mitigating the negative effects from the anchors that are poorly distributed in geometry. By combining the locality-based distance estimation and the anchor selection, a range-free localization algorithm named Selective Multilateration (SM) is proposed. Simulation results demonstrate that SM achieves localization accuracy higher than 0.3 r , where r is the communication radius of nodes. Compared to the state-of-the-art solution, SM improves the distance estimation accuracy by up to 57% and improves localization accuracy by up to 52% consequently.

Radio-Frequency Identification (RFID) technology brings revolutionary changes to many fields like retail industry. One important research issue in large RFID systems is the identification of unknown tags, i.e., tags that just entered the system but have not been interrogated by reader(s) covering them yet. Unknown tag identification plays a critical role in automatic inventory management and misplaced tag discovery, but it is far from thoroughly investigated. Existing solutions either trivially interrogate all the tags in the system and thus are highly time inefficient due to re-identification of already identified tags, or use probabilistic approaches that cannot guarantee complete identification of all the unknown tags. In this paper, we propose a series of protocols that can identify all of the unknown tags with high time efficiency. We develop several novel techniques to quickly deactivate already identified tags and prevent them from replying during the interrogation of unknown tags, which avoids re-identification of these tags and consequently improves time efficiency. To our knowledge, our protocols are the first non-trivial solutions that guarantee complete identification of all the unknown tags. We illustrate the effectiveness of our protocols through both rigorous theoretical analysis and extensive simulations. Simulation results show that our protocols can save up to 70 percent time when compared with the best existing solutions.

Radio-Frequency Identification (RFID) technology has fostered many object monitoring systems. Along with this trend, tagged objects' value and privacy become a primary concern. A corresponding important problem is to verify the intactness of a set of tagged objects without leaking tag identifiers (IDs). However, existing solutions necessitate the knowledge of tag IDs. Without tag IDs as a priori, this paper studies intactness verification in anonymous RFID systems. We identify three critical solution requirements, that is, deterministic verification, anonymity preservation, and scalability. We propose Cardiff and Divar, two crypto-free, lightweight protocols that isolate tag IDs from intactness verification and satisfy solution requirements. Cardiff explores tag cardinality as intactness proof while Divar leverages Direct-Sequence Spread Spectrum (DSSS) enabled RFID. Both analytical and simulation results demonstrate that Cardiff and Divar can satisfy the requirements of accuracy, privacy, and scalability.

The Radio Frequency IDentification (RFID) technology provides a promising solution to location discovery in indoor environments. Existing RFID reader positioning algorithms usually use all the collected reference tags to determine the position of the target reader, and thus are time-consuming as well as susceptible to the communication irregularity between the reader and reference tags. Especially, they usually perform poorly when the target reader is near the wall or at the corner. In this paper, we propose ArPat, an Accurate RFID reader Positioning algorithm that uses mere boundary reference Tags to calculate the position of the reader. ArPat uses only boundary tags to determine the position of the target reader, which effectively mitigates the negative impact of communication irregularity on the localization accuracy. The localization accuracy of ArPat is higher than 0.2 ft when the space between references tags is 1 ft. Compared with state-of-the-art solutions for RFID reader positioning, ArPat improves localization accuracy by up to 42 percent and 36 percent on average. Furthermore, it uses a geometric approach rather than iterative optimization approaches employed by previous solutions, making it superior in time efficiency. Compared with previous solutions, the computational time of ArPat is nearly two orders of magnitude less. This is critical for a localization system to provide real time location discovery and tracking services.

Tag identification is the most fundamental problem in Radio Frequency Identification (RFID) systems. Time efficiency is the top quality of service (QoS) metric in RFID tag identification. Traditional tag scanning approaches suffer from low time efficiency because they need to transmit tag IDs that are usually very long (e.g., 96 bits). In this paper, we investigate how to employ handheld readers to improve the time efficiency of tag identification and provide flexibility to scan tags on different purposes. A fast and flexible tag scanning mechanism called LOCK is proposed, which combines both the information and the replying slot index of a tag's response. In LOCK, tags transmit only short responses instead of tag IDs. Based on LOCK, we propose two novel tag scanning protocols that progressively add new techniques on top of one another to improve the time efficiency. Compared to the state-of-the-art solution in literature, our best protocol reduces scanning time by up to 53 percent.

Cloning attacks seriously impede the security of Radio-Frequency Identification (RFID) applications. In this paper, we tackle deterministic clone detection for anonymous RFID systems without tag identifiers (IDs) as a priori. Existing clone detection protocols either cannot apply to anonymous RFID systems due to necessitating the knowledge of tag IDs or achieve only probabilistic detection with a few clones tolerated. We propose two protocols, BASE and DeClone, toward fast and deterministic clone detection for large anonymous RFID systems. BASE leverages the observation that clone tags make tag cardinality exceed ID cardinality. DeClone is built on a recent finding that clone tags cause collisions that are hardly reconciled through re-arbitration. For DeClone to achieve detection certainty, we design breadth first tree traversal toward quickly verifying unreconciled collisions and hence the cloning attack. We validate their detection performance through analysis and simulation. The results show that BASE delivers faster detection for small systems while DeClone for large ones especially when clone ratio increases.

Radio-Frequency Identification (RFID) technology has successfully proven its potential for locating objects in a 3-dimensional (3D) space. Current RFID-based 3D localization is built on the ethos of striving for accuracy. This paper takes the first step toward efficient localization with high time efficiency and energy efficiency, which are important for accelerating positioning operation and prolonging system lifetime. To this end, we propose leveraging known locations of deployed reference readers and reference tags to probe as a few reference tags as sufficient for localization. Counter-intuitively, localization using fewer reference tags promises rather higher efficiency yet without necessarily sacrificing accuracy. We design efficient passive scheme and efficient active scheme for both typical RFID-based 3D localization scenarios, locating a target tag using reference readers/tags and locating a target reader using reference tags. We evaluate their performance through quantitative analysis and extensive simulation. The results show that the proposed schemes outperform existing schemes in time efficiency and energy efficiency by over 95% on average.

Cloning attacks threaten radio-frequency identification (RFID) applications but are hard to prevent. Existing cloning attack detection methods are enslaved to the knowledge of tag identifiers (IDs). Tag IDs, however, should be protected to enable and secure privacy-sensitive applications in anonymous RFID systems. In a first step, this paper tackles cloning attack detection in anonymous RFID systems without requiring tag IDs as a priori. To this end, we leverage unreconciled collisions to uncover cloning attacks. An unreconciled collision is probably due to responses from multiple tags with the same ID, exactly the evidence of cloning attacks. This insight inspires GREAT, our pioneer protocol for cloning attack detection in anonymous RFID systems. We evaluate the performance of GREAT through theoretical analysis and extensive simulations. The results show that GREAT can detect cloning attacks in anonymous RFID systems fairly fast with required accuracy. For example, when only six out of 50,000 tags are cloned, GREAT can detect the cloning attack in 75.5 s with a probability of at least 0.99.

Tag cloning attacks threaten a variety of Radio Frequency Identification (RFID) applications but are hard to prevent. To secure RFID applications that confine tagged objects in the same RFID system, this paper studies the cloned-tag identification problem. Although limited existing work has shed some light on the problem, designing fast cloned-tag identification protocols for applications in large-scale RFID systems is yet not thoroughly investigated. To this end, we propose leveraging broadcast and collisions to identify cloned tags. This approach relieves us from resorting to complex cryptography techniques and time-consuming transmission of tag IDs. Based on this approach, we derive a time lower bound on cloned-tag identification and propose a suite of time-efficient protocols toward approaching the time lower bound. The execution time of our protocol is only 1.4 times the value of the time lower bound, being up to 91% less than that of the existing protocol. The proposed protocols may benefit also RFID applications that distribute tagged objects across multiple places.

The RFID technology greatly improves efficiency of many applications including inventory control, object tracking, and supply chain management. In such applications, it is common that new objects are added into the system or existing objects are misplaced in wrong regions. When this happens, fast and complete identification of such tags is very important. We name this problem unknown tag identification, as these tags appear to be unknown by the reader(s) currently covering them. In this paper, we propose a series of protocols to identify unknown tags completely and fast. In these protocols, we develop several novel techniques to efficiently resolve collisions caused by known tags when identifying unknown tags, which greatly improve the time efficiency. To our knowledge, this is the first work that completely identify all the unknown tags with deterministic approaches. Simulation results show the superior performance of the proposed protocols: Compared with a baseline method which collects IDs of all the tags in the system, our best protocol reduces the execution time by 63% in average and by 85% at most.

In anisotropic wireless sensor networks, range-free multilateration-based localization (RFML) protocols severely suffer from large error in node-anchor distance estimations or the bad geometry of anchors involved in the localization process. In this paper, we propose selective multilateration (SM), a RFML protocol in which a node adaptively selects a subset of anchor nodes with accurate distance estimates and good geometric distribution to perform multilateration. We make two main contributions: (1) We exploit the locality property of per hop length (two nearby nodes share similar per hop length to a far anchor node) to estimate node-anchor distances. This induces smaller distance estimation error than previous approaches that use a unified average per hop length for all nodes. (2) We propose a method to heuristically select a subset of good anchor nodes that have small distance estimation errors and good geometry quality measured by geometric dilution of precision (GDOP) to perform multilateration. We also use a method which mines sub-hop resolution proximity between neighboring nodes to reduce error in distance estimates which further improves localization accuracy. Simulation results show that, compared with PDM, SM improves distance estimation accuracy by up to 45 percent. The localization accuracy in SM is improved by up to 45 percent and 27 percent in average. Furthermore, SM incurs much less communication and computational overhead than PDM does, making it more suitable for large scale WSNs.

Distance estimation is a key issue in range-free localization algorithms for wireless sensor networks. Approaches that assume isotropy of networks, such as Dv-hop and Gradient, cannot obtain accurate distance estimations in anisotropic sensor networks thus are not applicable to such networks. The anisotropy of sensor networks comes from two aspects: uneven nodal distribution and irregularity of deployment region. Existing localization algorithms for anisotropic wireless sensor networks usually only deal with one of the two aspects. In this paper, we propose an anchor supervised distance estimation approach which can simultaneously cope with both of the two aspects. In this approach, an anchor node selects a “friendly” subset from all other anchor nodes to which its distance estimates are accurate and broadcasts the selection result to neighboring common nodes. The common nodes then use these friendly anchors to perform distance estimation. We analyze distance estimation accuracy of this approach through extensive simulations. The results show that, compared with Dv-hop, our proposed approach dramatically reduces distance estimation error in anisotropic wireless sensor networks with an average factor of 67%. Consequently, the localization error of Dv-hop is reduced by an average factor of 71% if enhanced with our distance estimation approach.

Mobile agent technologies have been widely used in distributed computing to take care of the task execution for the user. However, pervasive computing presents new challenges to existing mobile agent systems, especially the need for the context-aware self-configuring collaboration with the services provided by the physical objects. In order to address the problem, this paper presents a self-configuring personal agent platform to enable a mobile agent to adapt to the on-demand collaboration with the services. The platform consists of a Ubiquitous Intelligent Object (UIO) model the pervasive computing environment modeling, a code repository to provide executable codes which can be downloaded and instantiated as a mobile agent's capability at runtime, a service registry server for UIOs to publish and subscribe services, and personal agents, one for each individual user. A prototype of platform has been implemented as proof-of-concept and a preliminary performance study has also been carried out on it using a case study.