Edge computing brings computing resources closer to the Internet of Things (IoT) devices, significantly reducing transmission latency and bandwidth usage. However, the limited resources of edge servers require efficient management. Serverless computing meets this demand through its elastic resource provisioning , leading to the emergence of serverless edge computing—a promising computing paradigm . Despite its potential, real-time task dispatching and scheduling in the highly complex and dynamic environment of serverless edge computing present significant challenges. On the one hand, task execution requires not only sufficient CPU resources but also free containers; on the other hand, tasks are typically event-driven, with strong burstiness and high concurrency, and impose stringent demands on fast decision-making. To address these challenges, we propose a real-time task dispatching and scheduling method, aiming to maximize the satisfaction rate of Service Level Objectives (SLOs) for tasks. First, we design a task dispatching algorithm named Adaptive Deep Reinforcement Learning (ADRL). This algorithm can quickly decide the execution position of tasks based on coarse information and effectively adapt to the changes in available servers in dynamic environments. Second, we propose a task scheduling algorithm named Warm-aware Shortest Remaining Idle Time (WSRIT), which guides the edge servers to schedule the tasks in the request queue based on the tasks’ remaining idle time and the state of the warm containers. Considering the limited storage space of the edge servers, we further introduce a container replacement algorithm named Low Priority First (LPF) to ensure smooth container launches. Extensive simulation experiments are conducted based on Azure datasets. The results show that our methodcan improve the satisfaction rate of SLOs by 12.57 ∼ 41.87% and achieve the lowest cold start rate compared to existing methods.

Sparse mobile crowdsensing is a cost-effective sensing paradigm that infers global data by sensing data from partial areas in a city. With the rapid development of diverse autonomous mobile agents such as unmanned aerial vehicles (UAVs) and ground vehicles, they have been widely applied in sparse mobile crowdsensing. However, existing works often predefine the role structures and behavioral preferences of these agents in tasks, which significantly limits their flexibility and adaptability, and making it difficult to fully exploit the collaborative potential of crowdsensing agents to efficiently achieve high-quality data sensing. In this paper, we propose an adaptive role learning framework for sparse mobile crowdsensing (ARL-SMCS), which focuses on role recognition for heterogeneous agents and role refinement among homogeneous agents. This framework, based on a multi-agent reinforcement learning model, introduces a variational autoencoder to learn the latent role representations of agents and uses maximum mean discrepancy to distinguish the functionalities of different types of agents. Additionally, ARL-SMCS incorporates an evolutionary algorithm to further refine task preferences among homogeneous agents. This framework overcomes the limitations of static role assignment in adapting to dynamic environments and task conflicts during task execution, significantly improving sensing quality and resource utilization efficiency. Extensive experiments on two real-world datasets demonstrate that ARL-SMCS consistently outperforms other baseline methods under various conditions, including different numbers, endurance, and decision interval lengths.

The multimodal knowledge graph completion (MMKGC) task aims to acquire accurate entity representations by learning different modal information about entities, which can be used to predict missing entities or relations in knowledge graphs (KGs). The lack of multimodal information accumulation and the noise in the various modal information collected leads to different modal information contributing differently to knowledge graph completion (KGC). Therefore, it becomes crucial to effectively fusion and fully utilize the multimodal information. To solve the above problems, we propose a knowledge graph completion method based on gated adaptive fusion and conditional generative adversarial networks (GAF-CGAN). GAF-CGAN is based on a gating mechanism for deeply extracting critical information in different modal features. After this, the model fuses the features by adapting the weights between different modal features. Ultimately, we utilize the relations in the triples as conditions to guide the generator in generating fake samples with specific meanings for adversarial training, enhancing the model’s robustness. We conduct link prediction experiments on two publicly available datasets, DB15K and FB15K-237, and the results show that our method significantly outperforms existing benchmark methods and effectively improves the model’s capacity for KGC.

Quantifying the chemical process of milk spoilage is challenging due to the need for bulky, expensive equipment that is not user-friendly for milk producers or customers. This lack of a convenient and accurate milk spoilage detection system can cause two significant issues. First, people who consume spoiled milk may experience serious health problems. Secondly, milk manufacturers typically provide a “best before” date to indicate freshness, but this date only shows the highest quality of the milk, not the last day it can be safely consumed, leading to significant milk waste. A practical and efficient solution to this problem is proposed in this paper: a vibration-based milk spoilage detection method called VibMilk that utilizes the ubiquitous vibration motor and Inertial Measurement Unit (IMU) of off-the-shelf smartphones. The method detects spoilage based on the fact that the milk’s physical properties change, inducing different vibration responses at various stages of degradation. Using the InceptionTime deep learning model, VibMilk achieves 98.35% accuracy in detecting milk spoilage across 23 different stages, from fresh (pH = 6.6) to fully spoiled (pH = 4.4).

In recent years, the Internet of Vehicles (IoV) has experienced significant growth, but the lack of effective secret key establishment remains a security concern due to the dynamic and ad-hoc nature of IoV communications. Physical layer key generation has emerged as a promising solution for establishing a pair of cryptographic keys in a lightweight and information-theoretic secure manner. However, previous works have primarily focused on legacy communication technologies, such as Wi-Fi, ZigBee, and 5 G, which are limited to short-range IoV communications. With the emergence of Long-range (LoRa) communication technology, which features long-range, low power, and extremely low data rates, new challenges arise for key generation in long-range IoV scenarios. This paper presentsVehicle-Key, a secret key generation system designed to secure LoRa-enabled IoV communications.Vehicle-Keypresents an innovative scenario adaptive deep learning model that performs channel prediction and quantization concurrently while reducing the training cost through a data augmentation pipeline and enhancing the model's generalization using a domain-adaption method. Additionally, we propose a bloom filter-assisted autoencoder-based reconciliation method to significantly improve the key agreement rate. Comprehensive real-world experiments show thatVehicle-Keysurpasses the State-of-the-Art, achieving a 15.26%–50.35% improvement in key agreement rate and a 9–15× increase in key generation rate. Moreover, the proposed method attains a 4.37--9.33% improvement when adapted to new scenarios with limited data sizes. A security analysis demonstrates thatVehicle-Keyis resilient against several common attacks. Furthermore, we implementVehicle-Keyon a Raspberry Pi and demonstrate its ability to execute within 3.5 ms.

Wearable devices-based biometrics has become mainstream in the biometric domain, especially in mobile computing, due to its convenience, flexibility, and potentially high user acceptance. Among various modalities, wearable devices-based gait recognition has been recognized as an effective user authentication method and employed in various applications, such as automated entry systems for home, school, work, vehicles, and automated ticket payment/validation for public transport. However, how secure wearable gait remains an open research question. In this study, we conduct a comprehensive security analysis of the wearable gait. Then, we demonstrate that gait itself is not robust against some attacking methods, such as spoofing or forgery. Therefore, we argue that an anti-spoofing mechanism is important for enhancing the security of wearable gait biometric systems. To this end, we proposed a novel authentication protocol called$Pistis$that embedded gait biometrics and a liveness detection mechanism that is aiming to detect various attacks of gait authentication systems. Our extensive experiments based on 50 subjects demonstrate that$Pistis$is effective in liveness detection and authentication performance enhancement, providing 100% accuracy for human and nonhuman detection, and 99.53% accuracy for user authentication. Pistis can be used as a liveness detection method for wearable devices-based biometrics, significantly for wearable gait.

The ability to recognize and detect changes in human posture is important in a wide range of applications such as health care and human–computer interaction. Achieving this goal using loose-fit garments instrumented with sensors is particularly challenging, due to the complex interaction between garments and human body. Herein we present a method to detect and recognize human posture with casual loose-fitting smart garments integrated with highly sensitive, stretchable, optical transparent, and low-cost strain sensors. By attaching these sensors to an off-the-shelf casual jacket, we developed a smart loose-fitting sensing garment that enables posture recognition using a deep learning model, domain-adaptive Convolutional Neural Networks–Long Short-Term Memory (CNN-LSTM). This deep learning model overcame the noise and variation due to the complex interaction between loose-fitting garments and human body. Considering that users’ labeled data are usually not available in the training stage, an additional domain discriminator path on the conventional CNN-LSTM model has been introduced to further improve the adaptability. To evaluate the potential of this loose-fitting smart garment, three case studies were conducted under realistic conditions: recognitions of human activities, stationary postures with random hand movements and slouch. Our results demonstrate the potential of the proposed smart garment system for practical applications.

Recent years have witnessed the remarkable growth of the Internet of Vehicles (IoV). Due to the high dynamics and ad-hoc nature of IoV communication, the lack of effective secret key establishment in IoV remains a security bottleneck. Physical layer key generation has emerged as a promising technology to establish a pair of cryptographic keys in a lightweight and information-theoretic secure way. However, prior works mainly focus on legacy communication technologies such as Wi-Fi, ZigBee, and 5G which can only achieve short range IoV communications. The emergence of Long-range (LoRa) communication technology that features long-range, low power, and extremely low data rate, brings new challenges for key generation in long range IoV scenarios. In this paper, we present Vehicle-Key, which is a secret key generation system to secure LoRa-enabled IoV communications. In Vehicle-Key, we design a novel deep learning model that can achieve channel prediction and quantization simultaneously. Additionally, we propose an autoencoder-based reconciliation method that improves the key agreement rate significantly. Extensive real-world experiments show that Vehicle-Key improves the key agreement rate by 15.10%–49.81% and key generation rate by 9–14× compared with the state-of-the-art. Security analysis demonstrates that Vehicle-Key is secure against several common attacks. Moreover, we implement Vehicle-Key on a Raspberry Pi and show that it can be executed in 3.4 ms.

As the human hand makes direct physical contact with smartphones, significant efforts have recently been made to study the behavioral information of hand gripping of smartphones for user authentication purposes. Most existing methods leverage hand gripping behavior (e.g., gripping gesture, gripping position, gripping strength) of smartphones as biometrics to identify users. However, behavioral-based biometric authentication approaches may suffer from two problems: authentication performance (accuracy) degradation due to high-intra class variations arising from changes in user behavior over time, and vulnerability under spoofing attacks. To address these issues, we propose HoldPass, which is a behavior-independent in-hand user authentication method using vibration. HoldPass is able to adapt to the changes of hand gripping behavior of smartphones by extracting unique and stable physical features of human hands and eliminating the behavior-related prior information. Specifically, in HoldPass, we propose an adversarial neural network to achieve authentication based on unique physical features. Experiments with 10 users show that HoldPass can authenticate users with 97.39% accuracy while keeping False Accepted Rates (FAR) at a minimum of 2.1%.

Next‐generation networks are data‐driven by design but face uncertainty due to various changing user group patterns and the hybrid nature of infrastructures running these systems. Meanwhile, the amount of data gathered in the computer system is increasing. How to classify and process the massive data to reduce the amount of data transmission in the network is a very worthy problem. Recent research uses deep learning to propose solutions for these and related issues. However, deep learning faces problems like overfitting that may undermine the effectiveness of its applications in solving different network problems. This paper considers the overfitting problem of convolutional neural network (CNN) models in practical applications. An algorithm for maximum pooling dropout and weight attenuation is proposed to avoid overfitting. First, design the maximum value pooling dropout in the pooling layer of the model to sparse the neurons and then introduce the regularization based on weight attenuation to reduce the complexity of the model when the gradient of the loss function is calculated by backpropagation. Theoretical analysis and experiments show that the proposed method can effectively avoid overfitting and can reduce the error rate of data set classification by more than 10% on average than other methods. The proposed method can improve the quality of different deep learning‐based solutions designed for data management and processing in next‐generation networks.

The device group based on the Internet of Things (IoT) has been used in face recognition in real life, so it is more necessary to discuss the current data security issues and social hot issues. The Internet of Things device combines edge conditions and many recognizers to generative adversarial networks. On the premise of meeting the needs of partial occlusion of users, face recovery is completed through information reorganization. CelebA training set is used to simulate face occlusion, and the model is trained and tested. The results show that the method can recover the complete image of the protection for the facial privacy of specific people. At the same time, the IoT device using this method ensures that the face information is not easy to have tampered with when attacked.

We explore the feasibility of Multiple-Input-Multiple-Output (MIMO) communication through vibrations over human skin. Using off-the-shelf motors and piezo transducers as vibration transmitters and receivers, respectively, we build a 2x2 MIMO testbed to collect and analyze vibration signals from real subjects. Our analysis reveals that there exist multiple independent vibration channels between a pair of transmitter and receiver, confirming the feasibility of MIMO. Unfortunately, the slow ramping of mechanical motors and rapidly changing skin channels make it impractical for conventional channel sounding based channel state information (CSI) acquisition, which is critical for achieving MIMO capacity gains. To solve this problem, we propose Skin-MIMO, a deep learning based CSI acquisition technique to accurately predict CSI entirely based on inertial sensor (accelerometer and gyroscope) measurements at the transmitter, thus obviating the need for channel sounding. Based on experimental vibration data, we show that Skin-MIMO can improve MIMO capacity by a factor of 2.3 compared to Single-Input-Single-Output (SISO) or open-loop MIMO, which do not have access to CSI. A surprising finding is that gyroscope, which measures the angular velocity, is found to be superior in predicting skin vibrations than accelerometer, which measures linear acceleration and used widely in previous research for vibration communications over solid objects.

We address the problem of human posture detection with casual loose-fitting smart garments by fabricating a new type of highly sensitive, stretchable, optical transparent and low-cost strain sensor enabled by uniquely designed microcracks within a hybrid conductive thin film. In terms of sensitivity and stretchability, the developed sensor outperformed most of the works reported in recent literature, and has a gauge factor of 103 at the high strain of 58%. By attaching these sensors to an off-the-self casual jacket, we implement E-Jacket, a smart loose-fitting sensing garment prototype. To detect postures from sensor data, we implement a conventional deep learning model, CNN-LSTM, capable of overcoming the noise induced by the loose-fitting of the sensors to the human skin. To evaluate E-Jacket, we conducted three case studies in experimental environments: recognition of daily activities, recognition of stationary postures with random hand movements, and slouch detection. Our evaluation results demonstrate the feasibility of the proposed E-Jacket smart garment system for different posture recognition applications.

We demonstrate a human activity detection with casual loose-fitting smart garment system. By employing a new type of highly sensitive, stretchable, optical transparent and low-cost strain sensor and a deep learning model enabled by CNN-LSTM, the loose-fitting jacket is able to recognize 5 activities with 90.9% accuracy when the system is trained with the user data, and 73.5% accuracy when an unseen user wears the smart jacket, which is comparable with tight-fitting smart garment system. In the demonstration, we will showcase activity recognition of three activities: walk, sit, and stand.

Recent work has shown that two wearable devices worn on the same user can exploit gait as a secret source to generate a common key for secure pairing. The main threat of using gait comes from side-channel attackers who can use cameras to record the walking user and extract accelerations from the video to pair with legitimate devices. We propose a novel pre-step that uses a CNN-LSTM deep learning model to classify the acceleration measurement devices, i.e., between IMU vs. Camera. We prototype the pre-step and evaluate it using real subjects. Our results show that the proposed pre-step can achieve high classification success rates. The experiments with different cut-off frequencies show that the higher acceleration frequencies appear to contain more distinguishable features to classify camera from IMU.

The Internet has become one of the important channels for users to obtain information and knowledge. It is crucial to work out how to acquire personalized requirement of users accurately and effectively from huge amount of network document resources. Group recommendation is an information system for group participation in common activities that meets the common interests of all members in the group. This paper proposes a group recommendation system for network document resource exploration using the knowledge graph and LSTM in edge computing, which can solve the problem of information overload and resource trek effectively. An extensive system test has been carried out in the field of big data application in packaging industry. The experimental results show that the proposed system recommends network document resource more accurately and further improves recommendation quality using the knowledge graph and LSTM in edge computing. Therefore, it can meet the user’s personalized resource need more effectively.

Swing tracking is one of the key information for many sports such as golf. One approach to track swing is to use IMU to measure linear acceleration then get position by two-time integration. However, the complex noise model of the IMU limit the accuracy of the tracking. Another approach is to use depth sensor to measure 3D location of a point of interest directly. Unfortunately, the depth sensor-based approach cannot accurately measure the trajectory of a swing when the sensor is occluded, which happens regularly. To overcome these limitations, we develop a novel solution to make use of these two sensor modalities (i.e., IMU and depth sensor) by a novel deep neural network to produce high precision swing trajectory tracking. The learned network automatically makes use of the IMU when the depth sensor is occluded, and relies on depth sensor when IMU signal is noisy. Our experiment shows that the proposed method outperforms state-of-the-art swing tracking method by 62% of error reduction.

Two factors that have a major impact on the performance of an optimization method are (1) formal algorithm specifications and (2) practical implementations. The impact of the latter is typically ignored, although it defines the results measured in experiments. We present an in-depth study of algorithm implementation issues and ask questions such as Does optimizing the implementation of an optimization algorithm pay off? Do bugs matter? and Is using more complicated but also more efficient data structures worth the effort? The intuitive answer to all of these questions is yes, but there is little published evidence. To bridge this gap, we use one of the most studied combinatorial optimization problems – the Traveling Salesman Problem – as a test bed and implement two state-of-the-art approaches for solving it – the Lin-Kernighan Heuristic and an Ejection Chain Method. We investigate implementation effort and performance gain, in order to provide further insights to the above questions.

Recent work has shown that it is possible for two wearable devices worn by the same user to generate a common key for secure pairing by exploiting gait as a common secret. A key challenge for such device pairing lies in matching the bits of the keys generated by two independent devices despite the noisy on-board sensor measurements. We propose a novel machine learning framework that uses an autoencoder to help one device predict the sensor observations at another device and generate the key using the predicted sensor data. We prototype the proposed method and evaluate it using real subjects. Our results show that the proposed method achieves a 10% increase in bit agreement rate between two keys generated independently by two different wearable devices.

The Traveling Salesman Problem (TSP) is one of the most well-known optimization problems. Ejection Chain Methods (ECM) and the Lin-Kernighan (LK) heuristic are the state-of-art local search (LS) algorithms for solving the TSP. Multi-Neighborhood Search (MNS) is known to be especially suitable for hybridization with Evolutionary Computation (EC). Hybridizing two different LS algorithms with each other (LS-LS) can combine their mutual advantages and lead to better performance. We introduce the new concept of LS-LS-X hybrids, which combines two different LS algorithms with a crossover operator. We enhance the two best LS-LS hybrids, ECM-LK and LK-MNS, with Order Based Crossover and Heuristic Crossover. We hybridize these LS-LS-X algorithms with an Evolutionary Algorithm, the most prominent EC method, and obtain highly-efficient (memetic) EC-LS-LS-X algorithms. We conduct a large-scale experimental study with many different algorithm setups on all 110 symmetric instances of the TSPLib benchmark set. We find that the LS-LS-X hybrids have significantly better performance than the original LS-LS and their component algorithms. They even outperform several memetic EC-LS-LS and EC-LS algorithm setups. The EC-LS-LS-X hybrids are the best hybrid EA-based TSP solvers by a large margin in our experiment and the wide range of algorithms available in the popular TSP Suite.