Real-world Experiments Research Articles

Enhancing Security and Energy Efficiency in Wireless Sensor Networks for IoT Applications

Wireless Sensor Networks (WSNs) are fundamental components within the Internet of Things (IoT) scene, empowering information collection and transmission in different applications. This research papers on upgrading the security and vitality effectiveness of WSNs for ideal IoT usefulness. Novel strategies were created and assessed to address these vital perspectives. Security improvements included the usage of lightweight cryptographic calculations, intrusion detection systems (IDS), and secure directing conventions. These measures essentially reinforced organized strength against cyber dangers, with interruption discovery rates surpassing 95% and secure steering conventions accomplishing a strength score of over 97%. Vitality productivity optimizations enveloped communication convention improvements, information accumulation strategies, and energetic control administration methodologies. These procedures come about in outstanding decreases in vitality utilization, with optimized conventions diminishing vitality utilization by up to 30% and information conglomeration techniques yielding vitality reserve funds of up to 50%. Test assessments were conducted utilizing both simulation-based approaches and real-world organizations. Recreation comes about, obtained utilizing NS-3, showcasing the viability of the proposed strategies over different network topologies, activity designs, and attack scenarios. Real-world experimentation employing a WSN testbed approved the viable achievability and viability of the techniques. Comparative investigations with existing writing highlighted the oddity and importance of the commitments, checking considerable progressions in WSN security and vitality proficiency.

SDN-based detection and mitigation of DDoS attacks on smart homes

The adoption of the Internet of Things (IoT) has proliferated across various domains, where everyday objects like refrigerators and washing machines are now equipped with sensors and connected to the internet. Undeniably, the security of such devices, which were not primarily designed for internet connectivity, is of utmost importance but has been largely neglected. In this paper, we propose a framework for the real-time DDoS attack detection and mitigation in SDN-enabled smart home networks. We capture network traffic during regular operations and during DDoS attacks. This captured traffic is used to train several machine learning (ML) models, including Support Vector Machine (SVM), Logistic Regression, Decision Trees, and K-Nearest Neighbors (KNN) algorithms. These trained models are executed as SDN controller applications and subsequently employed for real-time attack detection. While we utilize ML techniques to protect IoT devices, we propose the use of SNORT, a signature-based detection technique, to secure the SDN controller itself. Real-world experiments demonstrate that without SNORT, the SDN controller goes offline shortly after an attack, resulting in a 100% packet loss. Furthermore, we show that ML algorithms can efficiently classify traffic into benign and attack traffic, with the Decision Tree algorithm outperforming others with an accuracy of 99%.

Improved Hybrid Model for Obstacle Detection and Avoidance in Robot Operating System Framework (Rapidly Exploring Random Tree and Dynamic Windows Approach).

The integration of machine learning and robotics brings promising potential to tackle the application challenges of mobile robot navigation in industries. The real-world environment is highly dynamic and unpredictable, with increasing necessities for efficiency and safety. This demands a multi-faceted approach that combines advanced sensing, robust obstacle detection, and avoidance mechanisms for an effective robot navigation experience. While hybrid methods with default robot operating system (ROS) navigation stack have demonstrated significant results, their performance in real time and highly dynamic environments remains a challenge. These environments are characterized by continuously changing conditions, which can impact the precision of obstacle detection systems and efficient avoidance control decision-making processes. In response to these challenges, this paper presents a novel solution that combines a rapidly exploring random tree (RRT)-integrated ROS navigation stack and a pre-trained YOLOv7 object detection model to enhance the capability of the developed work on the NAV-YOLO system. The proposed approach leveraged the high accuracy of YOLOv7 obstacle detection and the efficient path-planning capabilities of RRT and dynamic windows approach (DWA) to improve the navigation performance of mobile robots in real-world complex and dynamically changing settings. Extensive simulation and real-world robot platform experiments were conducted to evaluate the efficiency of the proposed solution. The result demonstrated a high-level obstacle avoidance capability, ensuring the safety and efficiency of mobile robot navigation operations in aviation environments.

Dynamic characteristics and deep reinforcement learning of proportional-integral-differential controller for quadruped stator-based ultrasonic linear motor

Ultrasonic linear motors have many advantages, such as small size, light weight, and a lack of electromagnetic interference. In our previous study, a quadruped stator-based ultrasonic linear motor that mimics the motion of an inchworm based on longitudinal and bending modes was proposed. However, our previous studies focused on voltage control, overlooking the influence of phase, which made accurate and sustainable operation difficult. This study measures the dynamic characteristics of this motor using polymer-based rods and combines deep reinforcement learning (DRL) with proportional-integral-differential (PID) algorithms for both position and speed control through phase manipulation. The proposed DRL-PID controller outperforms voltage control in both simulation and real-world experiments.

Trends in Theorizing Sortition

In recent years, political scientists have devoted increasing attention to sortition – the random selection of ordinary citizens for political decision-making. This has been accompanied by a number of real-world experiments in which randomly-selected bodies provide input into the political process. The result has been a large and growing literature on the topic. Recent contributions to that literature have detailed proposals for expanded use of sortition, most of which combine election and sortition in innovative and ambitious ways. The use of sortition in these proposals is justified in various ways, many of which involve the way random selection can generate bodies capable of high-quality deliberation. There is more controversy regarding the connection between sortition and democracy. Some regard sortition as a uniquely democratic selection mechanism, while others regard election and sortition as advancing competing democratic values, generating the need for a tradeoff between them. Future research on sortition will no doubt further explore both the value of sortition and its democratic credentials.

Securing the Internet of Things: Predictive Defense Algorithm for Attack Mitigation

The Internet of Things (IoT) presents unprecedented opportunities for connectivity and efficiency across various sectors. However, its decentralized nature and the vast number of interconnected devices also pose significant security challenges, making IoT networks vulnerable to cyber-attacks. In this paper, we propose a predictive defense algorithm leveraging Differential Privacy (DP) techniques to enhance IoT security. By analyzing historical attack data while preserving the privacy of sensitive information, our algorithm predicts potential cyber threats and proactively mitigates them before they manifest. We present the theoretical framework of the DP algorithm, its implementation in IoT environments, and evaluate its effectiveness through simulations and real-world experiments. Our results demonstrate the algorithm’s ability to accurately predict and prevent a wide range of attacks, thus bolstering the resilience of IoT ecosystems against evolving cyber threats.

A comparative study of methods for estimating model-agnostic Shapley value explanations

Shapley values originated in cooperative game theory but are extensively used today as a model-agnostic explanation framework to explain predictions made by complex machine learning models in the industry and academia. There are several algorithmic approaches for computing different versions of Shapley value explanations. Here, we consider Shapley values incorporating feature dependencies, referred to as conditional Shapley values, for predictive models fitted to tabular data. Estimating precise conditional Shapley values is difficult as they require the estimation of non-trivial conditional expectations. In this article, we develop new methods, extend earlier proposed approaches, and systematize the new refined and existing methods into different method classes for comparison and evaluation. The method classes use either Monte Carlo integration or regression to model the conditional expectations. We conduct extensive simulation studies to evaluate how precisely the different method classes estimate the conditional expectations, and thereby the conditional Shapley values, for different setups. We also apply the methods to several real-world data experiments and provide recommendations for when to use the different method classes and approaches. Roughly speaking, we recommend using parametric methods when we can specify the data distribution almost correctly, as they generally produce the most accurate Shapley value explanations. When the distribution is unknown, both generative methods and regression models with a similar form as the underlying predictive model are good and stable options. Regression-based methods are often slow to train but quickly produce the Shapley value explanations once trained. The vice versa is true for Monte Carlo-based methods, making the different methods appropriate in different practical situations.

Topological Map-Based Autonomous Exploration in Large-Scale Scenes for Unmanned Vehicles

Robot autonomous exploration is a challenging and valuable research field that has attracted widespread research interest in recent years. However, existing methods often encounter problems such as incomplete exploration, repeated exploration paths, and low exploration efficiency when facing large-scale scenes. Considering that many indoor and outdoor scenes usually have a prior topological map, such as road navigation maps, satellite road network maps, indoor computer-aided design (CAD) maps, etc., this paper incorporated this information into the autonomous exploration framework and proposed an innovative topological map-based autonomous exploration method for large-scale scenes. The key idea of the proposed method is to plan exploration paths with long-term benefits by tightly merging the information between robot-collected and prior topological maps. The exploration path follows a global exploration strategy but prioritizes exploring scenes outside the prior information, thereby preventing the robot from revisiting explored areas and avoiding the duplication of any effort. Furthermore, to improve the stability of exploration efficiency, the exploration path is further refined by assessing the cost and reward of each candidate viewpoint through a fast method. Simulation experimental results demonstrated that the proposed method outperforms state-of-the-art autonomous exploration methods in efficiency and stability and is more suitable for exploration in large-scale scenes. Real-world experimentation has also proven the effectiveness of our proposed method.

Position Checking-Based Sampling Approach Combined with Attraction Point Local Optimization for Safe Flight of UAVs.

Trading off the allocation of limited computational resources between front-end path generation and back-end trajectory optimization plays a key role in improving the efficiency of unmanned aerial vehicle (UAV) motion planning. In this paper, a sampling-based kinodynamic planning method that can reduce the computational cost as well as the risks of UAV flight is proposed. Firstly, an initial trajectory connecting the start and end points without considering obstacles is generated. Then, a spherical space is constructed around the topological vertices of the environment, based on the intersections of the trajectory with the obstacles. Next, some unnecessary sampling points, as well as node rewiring, are discarded by the designed position-checking strategy to minimize the computational cost and reduce the risks of UAV flight. Finally, in order to make the planning framework adaptable to complex scenarios, the strategies for selecting different attraction points according to the environment are designed, which further ensures the safe flight of the UAV while improving the success rate of the front-end trajectory. Simulations and real-world experiment comparisons are conducted on a vision-based platform to verify the performance of the proposed method.

Cloud Security Using Fine-Grained Efficient Information Flow Tracking

This study provides a comprehensive review and comparative analysis of existing Information Flow Tracking (IFT) tools which underscores the imperative for mitigating data leakage in complex cloud systems. Traditional methods impose significant overhead on Cloud Service Providers (CSPs) and management activities, prompting the exploration of alternatives such as IFT. By augmenting consumer data subsets with security tags and deploying a network of monitors, IFT facilitates the detection and prevention of data leaks among cloud tenants. The research here has focused on preventing misuse, such as the exfiltration and/or extrusion of sensitive data in the cloud as well as the role of anonymization. The CloudMonitor framework was envisioned and developed to study and design mechanisms for transparent and efficient IFT (eIFT). The framework enables the experimentation, analysis, and validation of innovative methods for providing greater control to cloud service consumers (CSCs) over their data. Moreover, eIFT enables enhanced visibility to assess data conveyances by third-party services toward avoiding security risks (e.g., data exfiltration). Our implementation and validation of the framework uses both a centralized and dynamic IFT approach to achieve these goals. We measured the balance between dynamism and granularity of the data being tracked versus efficiency. To establish a security and performance baseline for better defense in depth, this work focuses primarily on unique Dynamic IFT tracking capabilities using e.g., Infrastructure as a Service (IaaS). Consumers and service providers can negotiate specific security enforcement standards using our framework. Thus, this study orchestrates and assesses, using a series of real-world experiments, how distinct monitoring capabilities combine to provide a comparatively higher level of security. Input/output performance was evaluated for execution time and resource utilization using several experiments. The results show that the performance is unaffected by the magnitude of the input/output data that is tracked. In other words, as the volume of data increases, we notice that the execution time grows linearly. However, this increase occurs at a rate that is notably slower than what would be anticipated in a strictly proportional relationship. The system achieves an average CPU and memory consumption overhead profile of 8% and 37% while completing less than one second for all of the validation test runs. The results establish a performance efficiency baseline for a better measure and understanding of the cost of preserving confidentiality, integrity, and availability (CIA) for cloud Consumers and Providers (C&P). Consumers can scrutinize the benefits (i.e., security) and tradeoffs (memory usage, bandwidth, CPU usage, and throughput) and the cost of ensuring CIA can be established, monitored, and controlled. This work provides the primary use-cases, formula for enforcing the rules of data isolation, data tracking policy framework, and the basis for managing confidential data flow and data leak prevention using the CloudMonitor framework.

Sample-Constrained Black Box Optimization for Audio Personalization

We consider the problem of personalizing audio to maximize user experience. Briefly, we aim to find a filter h*, which applied to any music or speech, will maximize the user’s satisfaction. This is a black-box optimization problem since the user’s satisfaction function is unknown. Substantive work has been done on this topic where the key idea is to play audio samples to the user, each shaped by a different filter hi, and query the user for their satisfaction scores f(hi). A family of “surrogate” functions is then designed to fit these scores and the optimization method gradually refines these functions to arrive at the filter ˆh* that maximizes satisfaction. In certain applications, we observe that a second type of querying is possible where users can tell us the individual elements h*[j] of the optimal filter h*. Consider an analogy from cooking where the goal is to cook a recipe that maximizes user satisfaction. A user can be asked to score various cooked recipes (e.g., tofu fried rice) or to score individual ingredients (say, salt, sugar, rice, chicken, etc.). Given a budget of B queries, where a query can be of either type, our goal is to find the recipe that will maximize this user’s satisfaction. Our proposal builds on Sparse Gaussian Process Regression (GPR) and shows how a hybrid approach can outperform any one type of querying. Our results are validated through simulations and real world experiments, where volunteers gave feedback on music/speech audio and were able to achieve high satisfaction levels. We believe this idea of hybrid querying opens new problems in black-box optimization and solutions can benefit other applications beyond audio personalization.

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation learning approach, GCL achieves impressive successes in various graph benchmarks. However, such an approach falls short of recognizing the topology isomorphism of graphs, resulting in that graphs with relatively homogeneous node features cannot be sufficiently discriminated. By revisiting classic graph topology recognition works, we disclose that the corresponding expertise intuitively complements GCL methods. To this end, we propose a novel hierarchical topology isomorphism expertise embedded graph contrastive learning, which introduces knowledge distillations to empower GCL models to learn the hierarchical topology isomorphism expertise, including the graph-tier and subgraph-tier. On top of this, the proposed method holds the feature of plug-and-play, and we empirically demonstrate that the proposed method is universal to multiple state-of-the-art GCL models. The solid theoretical analyses are further provided to prove that compared with conventional GCL methods, our method acquires the tighter upper bound of Bayes classification error. We conduct extensive experiments on real-world benchmarks to exhibit the performance superiority of our method over candidate GCL methods, e.g., for the real-world graph representation learning experiments, the proposed method beats the state-of-the-art method by 0.23% on unsupervised representation learning setting, 0.43% on transfer learning setting. Our code is available at https://github.com/jyf123/HTML.

A Simulation of the Mechanical Testing of the Cell Membrane and Cytoskeleton.

Cell models play a crucial role in analyzing the mechanical response of cells and quantifying cellular damage incurred during micromanipulation. While traditional models can capture the overall mechanical behavior of cells, they often lack the ability to discern among distinct cellular components. Consequently, by employing dissipative particle dynamics, this study constructed a triangular network-like representation of the cell membrane along with cross-linked cytoskeletal chains. The mechanical properties of both the membrane and cytoskeleton were then analyzed through a series of simulated mechanical tests, validated against real-world experiments. The investigation utilized particle-tracking rheology to monitor changes in the mean square displacements of membrane particles over time, facilitating the analysis of the membrane's storage and loss moduli. Additionally, the cytoskeletal network's storage and loss moduli were examined via a double-plate oscillatory shear experiment. The simulation results revealed that both the membrane and cytoskeleton exhibit viscoelastic behavior, as evidenced by the power-law dependency of their storage and loss moduli on frequency. Furthermore, indentation and microinjection simulations were conducted to examine the overall mechanical properties of cells. In the indentation experiments, an increase in the shear modulus of the membrane's WLCs correlated with a higher Young's modulus for the entire cell. Regarding the microinjection experiment, augmenting the microinjection speed resulted in reduced deformation of the cell at the point of membrane rupture and a lower percentage of high strain.

Construction and Research on Cloud-edge Collaborative Power Measurement and Security Model

Accurate power consumption assessment is of critical importance in the fast-evolving world of cloud and edge computing. These technologies enable rapid data processing and storage but they also require huge amounts of energy. This energy requirement directly impacts operational costs, as well as environmental responsibility. We are conducting research to develop a specialized cloud-edge power measurement and security model. This model delivers reliable power usage data from these systems while maintaining security for the data they process and store. A combination of simulation-based analysis and real-world experimentation helped us to deliver these results. Monte Carlo based simulations produced power usage predictions under various conditions and Load Testing validated their real-world performance. A Threat Modeling-based security study identified potential vulnerabilities and suggested protection protocols. A collaborative approach enhances power measurements accuracy and encourages secure operation of the combined cloud-edge systems. By fusing these metrics, a more efficient and secure operation of computing resources becomes possible. This research underscores the critical importance of developing advanced techniques for power metering and security in cloud-edge computing systems. Future research may focus on both expanding the model’s use to an array of larger, more complex networks, as well as the inclusion of AI driven predictive analytics to amplify accuracy of power management.

Control of a quadrotor on a mobile device using machine learning-based monocular gaze tracking

A machine learning-based monocular gaze tracking method for mobile devices is proposed. A non-invasive, convenient, and low-cost gaze tracking framework is developed using our constructed convolutional neural network. This framework is applied to the 3D motion control of quadrotors, which can convert the operator’s gaze attention into control intention for the quadrotor, thus allowing the operator to control the quadrotor to complete flight tasks through visual interaction. Extensive challenging indoor and outdoor real-world experiments and benchmark comparisons validate that the proposed system is robust and effective, even for unskilled operators. The proposed method can improve the smoothness and reasonableness of the motion trajectory of the quadrotor, make it more consistent with the operator’s control intention, and introduce diversity, convenience, and intuition into the control of the quadrotor. We released the source code3 3 https://github.com/hujavahui/Gaze_MAV of our system to benefit related research.

MeshID: Few-Shot Finger Gesture Based User Identification Using Orthogonal Signal Interference.

Radio frequency (RF) technology has been applied to enable advanced behavioral sensing in human-computer interaction. Due to its device-free sensing capability and wide availability on Internet of Things devices. Enabling finger gesture-based identification with high accuracy can be challenging due to low RF signal resolution and user heterogeneity. In this paper, we propose MeshID, a novel RF-based user identification scheme that enables identification through finger gestures with high accuracy. MeshID significantly improves the sensing sensitivity on RF signal interference, and hence is able to extract subtle individual biometrics through velocity distribution profiling (VDP) features from less-distinct finger motions such as drawing digits in the air. We design an efficient few-shot model retraining framework based on first component reverse module, achieving high model robustness and performance in a complex environment. We conduct comprehensive real-world experiments and the results show that MeshID achieves a user identification accuracy of 95.17% on average in three indoor environments. The results indicate that MeshID outperforms the state-of-the-art in identification performance with less cost.

Using multi-actor labs as a tool to drive sustainability transitions in coastal-rural territories: Application in three European regions

Evidence on the efficacy of impacts from real-world experiments in triggering transformative processes is still scarce. This study evaluates multi-actor labs to provide examples of direct impacts of real-world experiments in tackling long-standing, local, sustainability challenges.Multi-actor labs (MALs), a form of real-world social experiments, were implemented in three coastal-rural regions in France (Charente River Basin), Spain (Mar Menor), and Greece (South-West Messinia) to better assess and tackle coastal-rural interactions that govern local sustainability challenges, such as water use conflicts and biodiversity degradation. The MALs used participative methodologies based on systems thinking and transition management. Stakeholders were continuously engaged in a series of workshops to co-produce knowledge, reach a common understanding of the sustainability challenges and issues at stake, and co-design solutions in the form of a roadmap for sustainable transitions in coastal-rural regions. This paper evaluates MALs to provide examples of successful sustainability transition experiments based on the outputs produced, outcomes achieved, and processes used in the three coastal, rural regions.

Virtual tactile POMDP-based path planning for object localization and grasping

Tactile sensation endows humans with the capacity to localize objects, which is also significant for robots. However, it is challenging for robots to localize and grasp objects only by tactile sensation. One potential snag is that tactile sensors do not provide feedback without external contact, which means the robot cannot spontaneously plan its path. To address this issue, we propose a novel Virtual Tactile POMDP (VT-POMDP)-based method for object localization and grasping in a 3D workspace, which models the path planning problem as the VT-POMDP to plan the motion path of the grasper. The state space and action space in the VT-POMDP are classified into seven categories to reduce the spatial dimension and the computational cost of path planning. Furthermore, we model the motion scale of the grasper using a variable-scale moving strategy to improve the efficiency of object localization. Finally, we verify the effectiveness and generalization of the method through a series of simulation experiments and real-world experiments.

Beyond scalable impacts: Roles of mobility experiments in local transition governance

The impact of short-term, localized real-world experiments on sustainable change is debated. Our analysis of three mobility experiments shows that even in the absence of quantifiable results, these experiments are still perceived as successful. By highlighting the underlying collective discursive strategies, we emphasize the different roles of experimentation in local mobility transitions and the importance of social learning and collective understanding in urban experimentation.In this article, we explore the role of real-world experiments in local transition governance, focusing on the negotiation between measurable impacts and the evaluation of localized, tangible outcomes. In our qualitative comparative analysis, we examine three distinct mobility experiments aimed at advancing sustainable transformation in mobility and urban planning, namely the co-creative research project City2Share in Munich, the political program of the Superblocks in Barcelona, and the real-world test bed for automated shuttles Digibus Austria in Koppl near Salzburg. Despite the structural limitations of the temporal, spatial, and legal framework and the uncertainties in measuring the impact, all experiments were presented as successful. This success was negotiated and re-framed via five discursive strategies: mobilizing citizen engagement, highlighting small achievements, manifesting institutional embedding, generating political momentum, and delegating responsibility. As we argue, success and scaling are not just the result of scientific proof, but also a matter of negotiating the political issues raised by the experiment.

Speaking of success: Real-world experiments for sustainability transformations and causal inference

Reports of successful sustainability-oriented real-world experiments can be categorized by the type of explanatory approaches employed, namely, the variance approach, which looks for correlations, and the process approach, which draws causal inferences in a narrative way. Their validity could benefit from a more critical reflection on the data and methods used.This paper examines a sample of 20 sustainability-oriented real-world experiment reports from 2006 to 2020, with the aim of uncovering the logic and methods used to demonstrate their success, that means, to show that they achieved their stated objectives. Following a distinction often made in the social sciences, I look for features of either the variance or the process approach to causal inference. I find that reports of transition experiments, socio-technical experiments, and community-based interventions display characteristic features of the process approach. Reports of trials, pilots, and field experiments, on the other hand, mostly use the variance approach to demonstrate success. An important observation is the limited recognition of possible biases related to the methods used or the data. I describe a number of possible biases that may be of importance in the context of sustainability-oriented real-world experiments. Important examples include measurement errors and biases in participant selection. Recognising the biases and correcting them where necessary can strengthen the validity of the findings obtained and help other researchers in designing their experiments.