Real-world Deployment Research Articles

Development of a Wearable Electromyographic Sensor with Aerosol Jet Printing Technology

Electromyographic (EMG) sensors are essential tools for analyzing muscle activity, but traditional designs often face challenges such as motion artifacts, signal variability, and limited wearability. This study introduces a novel EMG sensor fabricated using Aerosol Jet Printing (AJP) technology that addresses these limitations with a focus on precision, flexibility, and stability. The innovative sensor design minimizes air interposition at the skin–electrode interface, thereby reducing variability and improving signal quality. AJP enables the precise deposition of conductive materials onto flexible substrates, achieving a thinner and more conformable sensor that enhances user comfort and wearability. Performance testing compared the novel sensor to commercially available alternatives, highlighting its superior impedance stability across frequencies, even under mechanical stress. Physiological validation on a human participant confirmed the sensor’s ability to accurately capture muscle activity during rest and voluntary contractions, with clear differentiation between low and high activity states. The findings highlight the sensor’s potential for diverse applications, such as clinical diagnostics, rehabilitation, and sports performance monitoring. This work establishes AJP technology as a novel approach for designing wearable EMG sensors, providing a pathway for further advancements in miniaturization, strain-insensitive designs, and real-world deployment. Future research will explore optimization for broader applications and larger populations.

Machine Learning-Based Network Anomaly Detection: Design, Implementation, and Evaluation

Background: In the last decade, numerous methods have been proposed to define and detect outliers, particularly in complex environments like networks, where anomalies significantly deviate from normal patterns. Although defining a clear standard is challenging, anomaly detection systems have become essential for network administrators to efficiently identify and resolve irregularities. Methods: This study develops and evaluates a machine learning-based system for network anomaly detection, focusing on point anomalies within network traffic. It employs both unsupervised and supervised learning techniques, including change point detection, clustering, and classification models, to identify anomalies. SHAP values are utilized to enhance model interpretability. Results: Unsupervised models effectively captured temporal patterns, while supervised models, particularly Random Forest (94.3%), demonstrated high accuracy in classifying anomalies, closely approximating the actual anomaly rate. Conclusions: Experimental results indicate that the system can accurately predict network anomalies in advance. Congestion and packet loss were identified as key factors in anomaly detection. This study demonstrates the potential for real-world deployment of the anomaly detection system to validate its scalability.

A Comprehensive Review of Disease Detection Techniques for Tomato Leaves

Tomato plants plays vital role in global agriculture, significantly impacting food security and economic stability. However, diseases affecting tomato leaves present substantial challenges to crop yields and quality, highlighting the need for effective detection methods. This paper presents a comprehensive review of disease detection techniques for tomato leaves, emphasizing the transformative impact of advancements in image processing, machine learning, and deep learning. Approaches are categorized based on their methodologies, including traditional image processing, machine learning, and cutting-edge deep learning frameworks. Key concepts such as disease segmentation, feature extraction, and transfer learning are defined to provide a foundational understanding. The review also identifies critical research gaps, particularly concerning the generalizability of solutions to real-world conditions and the necessity for computational efficiency in field applications. Organized by method categories, evaluation metrics, and dataset utilization, this review encompasses recent advancements up to 2024, focusing on improving accuracy, scalability, and practical implementation. Ultimately, this work aims to serve as an insightful reference for researchers and practitioners, facilitating the advancement of disease detection systems for tomato leaves for real-world deployment

A Comparative Analysis of Advanced Routing and Cluster Head Selection Algorithm Using Lagrange Interpolation

This paper presents a unified performance metric for evaluating the chronological wild geese optimization (CWGO) algorithm in wireless sensor networks (WSNs). The metric combines key performance factors—energy consumption, delay, distance, and trust—into a single measure using Lagrange interpolation, providing a more comprehensive assessment of WSN algorithms. We evaluate CWGO against E-CERP, EECHIGWO, DUCISCA, and DE-SEP across static and dynamic sensor node configurations in various wireless technologies, including LoRa, Wi-Fi, Zigbee, and Bluetooth low energy (BLE). The results show that CWGO consistently outperforms the other algorithms, especially in larger node configurations, demonstrating its scalability and robustness in static and dynamic environments. Moreover, the unified metric reveals significant performance gaps with EECHIGWO, which underperforms all wireless technologies. DUCISCA and DE-SEP show moderate and fluctuating results, underscoring their limitations in larger networks. While E-CERP performs competitively, it generally lags behind CWGO. The unified metric offers a holistic view of algorithm performance, conveying clearer comparisons across multiple factors. This study emphasized the importance of a unified evaluation approach for WSN algorithms and positions CWGO as a superior solution for efficient cluster head selection and routing optimization in diverse WSN scenarios. While CWGO demonstrates superior performance in simulation, future research should validate these findings in real-world deployments, accounting for hardware limitations and in a highly dynamic environment. Further optimization of the unified metrics’ computational efficiency could enhance its real-time applicability in larger, energy-resource-constrained WSNs.

System Center Virtual Machine Manager 2022: Enhanced Cloud Integration and Management Capabilities

System Center Virtual Machine Manager (SCVMM) 2022 represents a transformative advancement in private cloud management, offering enhanced capabilities across virtualization, deployment, and cloud integration domains. This comprehensive platform introduces sophisticated hardware-level security protocols, dynamic resource allocation mechanisms, and intelligent orchestration capabilities that significantly improve operational efficiency. The integration with Azure Arc and support for Azure Kubernetes Service demonstrates SCVMM's evolution in hybrid cloud management, while enhanced data protection solutions ensure robust security and recovery capabilities. The platform's implementation of energy-aware management protocols and low-carbon operational methodologies showcases Microsoft's commitment to environmental sustainability without compromising performance. Through advanced predictive analytics, automated workflow management, and streamlined deployment architectures, SCVMM 2022 addresses the growing demands of modern enterprise environments. This article examines the platform's core enhancements, deployment methodologies, cloud integration capabilities, and impact on enterprise operations while providing implementation best practices derived from extensive research and real-world deployments.

Subwavelength broadband light-harvesting metacoating for infrared camouflage and anti-counterfeiting empowered by inverse design

Broadband mid-infrared (MIR) light harvesting is critical for a wide range of applications, including thermophotovoltaic conversion, thermal sensing and imaging, infrared camouflage and anti-counterfeiting technologies. In this study, we present the design and experimental validation of a deep-subwavelength broadband MIR light-harvesting metacoating (MMC), optimized through a genetic algorithm (GA)-based inverse design approach. The strength of this approach lies in its ability to automate and optimize the complex multilayer structure, encompassing both material selection and structural thickness, thereby achieving unparalleled performance in broadband MIR light absorption, with an average absorbance of approximately 0.85 across the 3–13 μm spectral range and nearly perfect absorption within the 4–12 μm range. This exceptional performance is attributed to strong electromagnetic localization within its multilayer configuration, facilitating efficient energy dissipation via high-loss materials such as bismuth and titanium. Notably, the MMC exhibits robust performance with respect to angle and polarization variations, maintaining high absorbance even at incident angles up to 70°. Its large-area fabrication capabilities and compatibility with various substrates further enhance its practical applicability. Two specific applications, long-wavelength infrared camouflage and anti-counterfeiting, highlight its potential for real-world deployment. In these applications, the MMC seamlessly integrates into high-emission environments and enables the modulation of patterned infrared emission, providing a lithography-free, cost-effective solution compared to conventional methods relying on artificially engineered structures. This work underscores the versatility of the developed MMC for a diverse array of MIR applications, ranging from camouflage technologies to advanced security measures.

Optimal gait design for a soft quadruped robot via multi-fidelity Bayesian optimization

This study focuses on the locomotion capability improvement in a tendon-driven soft quadruped robot through an online adaptive learning approach. Leveraging the inverse kinematics model of the soft quadruped robot, we employ a central pattern generator to design a parametric gait pattern, and use Bayesian optimization (BO) to find the optimal parameters. Further, to address the challenges of modeling discrepancies, we implement a multi-fidelity BO approach, combining data from both simulation and physical experiments throughout training and optimization. This strategy enables the adaptive refinement of the gait pattern and ensures a smooth transition from simulation to real-world deployment for the controller. Compared to previous result using a fixed gait pattern, the multi-fidelity BO approach improves the robot’s average walking speed from 0.14 m/s to 0.214 m/s, an increase of 52.7%. Moreover, we integrate a computational task off-loading architecture by edge computing, which reduces the onboard computational and memory overhead, to improve real-time control performance and facilitate an effective online learning process. The proposed approach successfully achieves optimal walking gait design for physical deployment with high efficiency, effectively addressing challenges related to the reality gap in soft robotics.

Unsupervised evaluation for out-of-distribution detection

We need to acquire labels for test sets to evaluate the performance of existing out-of-distribution (OOD) detection methods. In real-world deployment, it is laborious to label each new test set as there are various OOD data with different difficulties. However, we need to use different OOD data to evaluate OOD detection methods as their performance varies widely. Thus, we propose evaluating OOD detection methods on unlabeled test sets, which can free us from labeling each new OOD test set. It is a non-trivial task as we do not know which sample is correctly detected without OOD labels, and the evaluation metric like AUROC cannot be calculated. In this paper, we address this important yet untouched task for the first time. Inspired by the bimodal distribution of OOD detection test sets, we propose an unsupervised indicator named Gscore that has a certain relationship with the OOD detection performance; thus, we could use neural networks to learn that relationship to predict OOD detection performance without OOD labels. Through extensive experiments, we validate that there does exist a strong quantitative correlation, which is almost linear, between Gscore and the OOD detection performance. Additionally, we introduce Gbench, a new benchmark consisting of 200 different real-world OOD datasets, to test the performance of Gscore. Our results show that Gscore achieves state-of-the-art performance compared with other unsupervised evaluation methods and generalizes well with different in-distribution (ID)/OOD datasets, OOD detection methods, backbones, and ID:OOD ratios. Furthermore, we conduct analyses on Gbench to study the effects of backbones and ID/OOD datasets on OOD detection performance. The dataset and code will be available.

Lightweight, Post-Quantum Secure Cryptography Based on Ascon: Hardware Implementation in Automotive Applications

With the rapid growth of connected vehicles and the vulnerability of embedded systems against cyber attacks in an era where quantum computers are becoming a reality, post-quantum cryptography (PQC) is a crucial solution. Yet, by nature, automotive sensors are limited in power, processing capability, memory in implementing secure measures. This study presents a pioneering approach to securing automotive systems against post-quantum threats by integrating the Ascon cipher suite—a lightweight cryptographic protocol—into embedded automotive environments. By combining Ascon with the Controller Area Network (CAN) protocol on an Artix-7 Field Programmable Gate Array (FPGA), we achieve low power consumption while ensuring high performance in post-quantum-resistant cryptographic tasks. The Ascon module is designed to optimize computational efficiency through bitwise Boolean operations and logic gates, avoiding resource-intensive look-up tables and achieving superior processing speed. Our hardware design delivers significant speed improvements of 100 times over software implementations and operates effectively within a 100 MHz clock while demonstrating low resource usage. Furthermore, a custom digital signal processing block supports CAN protocol integration, handling message alignment and synchronization to maintain signal integrity under automotive environmental noise. Our work provides a power-efficient, robust cryptographic solution that prepares automotive systems for quantum-era security challenges, emphasizing lightweight cryptography’s readiness for real-world deployment in automotive industries.

A dual-tier adaptive one-class classification IDS for emerging cyberthreats

In today’s digital age, our dependence on IoT (Internet of Things) and IIoT (Industrial IoT) systems has grown immensely, which facilitates sensitive activities such as banking transactions and personal, enterprise data, and legal document exchanges. Cyberattackers consistently exploit weak security measures and tools. The Network Intrusion Detection System (IDS) acts as a primary tool against such cyber threats. However, machine learning-based IDSs, when trained on specific attack patterns, often misclassify new emerging cyberattacks. Further, the limited availability of attack instances for training a supervised learner and the ever-evolving nature of cyber threats further complicate the matter. This emphasizes the need for an adaptable IDS framework capable of recognizing and learning from unfamiliar/unseen attacks over time. In this research, we propose a one-class classification-driven IDS system structured on two tiers. The first tier distinguishes between normal activities and attacks/threats, while the second tier determines if the detected attack is known or unknown. Within this second tier, we also embed a multi-classification mechanism coupled with a clustering algorithm. This model not only identifies unseen attacks but also uses them for retraining them by clustering unseen attacks. This enables our model to be future-proofed, capable of evolving with emerging threat patterns. Leveraging one-class classifiers (OCC) at the first level, our approach bypasses the need for attack samples, addressing data imbalance and zero-day attack concerns and OCC at the second level can effectively separate unknown attacks from the known attacks. Our methodology and evaluations indicate that the presented framework exhibits promising potential for real-world deployments.

A fuzzy-based frame transformation to mitigate the impact of adversarial attacks in deep learning-based real-time video surveillance systems

Deep learning (DL) techniques have become integral to smart city projects, including video surveillance systems (VSS). These advanced technologies offer significant benefits, such as enhanced accuracy and efficiency in monitoring and managing urban environments. However, despite their advantages, these systems are not without vulnerabilities. One of the most pressing challenges is their susceptibility to adversarial attacks, which can lead to critical misclassifications during inference. To address these challenges, our research focuses on developing a more robust smart city VSS. Our research unfolds across two pivotal initiatives. In our initial exploration, we introduce a pioneering framework that extends the reach of adversarial attacks to real-time VSS. A practical manifestation involved implementing a real-time face mask surveillance system based on Multi-Task Cascaded Convolutional Networks (MTCNN) for face detection and MobileNet-v2 for face mask classification, subjecting it to the Fast Gradient Sign Method (FGSM) adversarial attack in real-time. In our subsequent endeavor, we propose a sophisticated defense mechanism deploying Fuzzy Image Transformation as a pre-processing unit (FITP). This strategic defense fortification significantly reinforces our real-time VSS against adversarial intrusions. Experimental findings highlight the effectiveness of the proposed adversarial attack framework in real-time, resulting in a marked reduction in the model's performance from a precision (P) of 93 %, recall (R) of 93 %, F1 score (F) of 93 %, and accuracy (A) of 93–22 %, 21 %, 22 %, and 22 %, respectively. However, the post-implementation efficacy of our defense mechanism is striking, enhancing the model's average performance to a noteworthy improvement, with P, R, F, and A ascending to 91 %, 90 %, 91 %, and 91 %. This research illuminates the vulnerabilities intrinsic to VSS in the face of adversarial threats, underscoring the critical need for heightened awareness and the development of robust defense mechanisms before real-world deployment.

Cloud-Based Machine Learning : Opportunities and Challenges

This comprehensive article explores the transformative impact of cloud-based machine learning (ML) on modern enterprises, examining both opportunities and challenges in implementation. The article investigates the rapidly growing cloud computing market and its ML segment, revolutionizing how organizations approach data analytics and business intelligence. Through detailed analysis of enterprise implementations, the article demonstrates how cloud ML solutions have democratized access to advanced analytics, significantly reducing operational costs while improving data processing efficiency. The article examines key aspects, including scalability advantages, cost efficiencies, and technical complexities, while providing evidence-based best practices for successful implementation. Drawing from multiple industry studies and real-world deployments, the article presents a framework for organizations to navigate challenges in data privacy, vendor dependencies, and skill requirements while maximizing the benefits of cloud-based ML solutions.

A blockchain based secure authentication technique for ensuring user privacy in edge based smart city networks

In the past decade, modernization of Information and Communication Technology (ICT), Edge Computing (EC), and Smart Cities has attracted significant academic interest due to its diverse applications in the fields of healthcare, transportation, agriculture, and defense. EC offers numerous advantages, including faster and more efficient services, lower latency, improved data processing, managed bandwidth consumption, scalable, real-time decision-making, security, reduced network congestion, and increased resilience. Despite these benefits, EC networks face persistent challenges, particularly related to security and privacy concerns. Addressing these security challenges requires strong authentication mechanisms, which demand extra resources like processing power and memory, often surpassing the limited capabilities of lightweight edge devices compared to cloud systems. This highlights the critical need for securing edge nodes and ensuring user privacy before real-world deployment and data transfer. User and edge device authentication is vital to prevent external and internal Impersonation and Reflection attacks that threaten system integrity and confidentiality. This paper presents a BlockChain based Authentication technique for Edge Networks (BCAuthEN) that utilizes a Consortium Blockchain (CB) with key agreements for biometric authentication, incorporating a Fuzzy Extractor (FE) to secure user biometrics and passwords. In addition, BCAuthEN offers multifactor and continuous authentication by monitoring user behavior and biometrics. BCAuthEN has been formally verified through Real-Or-Random (RoR) modeling and AVISPA tool, proving its effectiveness in enhancing privacy, and security. The proposed technique ensures robust security by preventing attackers at the potential entry points (edge nodes). In addition, BCAuthEN reduces computation cost, communication overhead and improves throughput. BCAuthEN provides strong resilience by achieving high detection accuracy and reduces false positives against impersonation and reflection attacks. Results have shown that BCAuthEN improves communication costs and reduces overhead by 10% and 7%, respectively, as compared to the recent biometric and key-based user authentication techniques.

Heuristic dense reward shaping for learning-based map-free navigation of industrial automatic mobile robots

This paper presents a map-free navigation approach for industrial automatic mobile robots (AMRs), designed to ensure computational efficiency, cost-effectiveness, and adaptability. Utilizing deep reinforcement learning (DRL), the system enables real-time decision-making without fixed markers or frequent map updates. The central contribution is the Heuristic Dense Reward Shaping (HDRS), inspired by potential field methods, which integrates domain knowledge to improve learning efficiency and minimize suboptimal actions. To address the simulation-to-reality gap, data augmentation with controlled sensor noise is applied during training, ensuring robustness and generalization for real-world deployment without fine-tuning. Training results underscore HDRS’s superior convergence speed, training stability, and policy learning efficiency compared to baselines. Simulation and real-world evaluations establish HDRS-DRL as a competitive alternative, outperforming traditional approaches, and offering practical applicability in industrial settings.

Hyperdimensional Brain-Inspired Learning for Phoneme Recognition With Large-Scale Inferior Colliculus Neural Activities.

Develop a novel and highly efficient framework that decodes Inferior Colliculus (IC) neural activities for phoneme recognition. We propose using Hyperdimensional Computing (HDC) to support an efficient phoneme recognition algorithm, in contrast to widely applied Deep Neural Networks (DNN). The high-dimensional representation and operations in HDC are rooted in human brain functionalities and naturally parallelizable, showing the potential for efficient neural activity analysis. Our proposed method includes a spatial and temporal-aware HDC encoder that effectively captures global and local patterns. As part of our framework, we deploy the lightweight HDC-based algorithm on a highly customizable and flexible hardware platform, i.e., Field Programmable Gate Arrays (FPGA), for optimal algorithm speedup. To evaluate our method, we record IC neural activities on gerbils while playing the sound of different phonemes. We compare our proposed method with multiple baseline machine learning algorithms in recognition quality and learning efficiency, across different hardware platforms. The results show that our method generally achieves better classification quality than the best-performing baseline. Compared to the Deep Residual Neural Network (i.e., ResNet), our method shows a speedup up to 74×, 67×, 210× on CPU, GPU, and FPGA respectively. We achieve up to 15% (10%) higher accuracy in consonant (vowel) classification than ResNet. By leveraging brain-inspired HDC for IC neural activity encoding and phoneme classification, we achieve orders of magnitude runtime speedup while improving accuracy in various challenging task settings. Decoding IC neural activities is an important step to enhance understanding about human auditory system. However, these responses from the central auditory system are noisy and contain high variance, demanding large-scale datasets and iterative model fine-tuning. The proposed HDC-based framework is more scalable and viable for future real-world deployment thanks to its fast training and overall better quality.

Workshop summaries from the 2024 voice AI symposium, presented by the Bridge2AI-voice consortium.

The 2024 Voice AI Symposium, presented by the Bridge2AI-Voice Consortium, featured deep-dive educational workshops conducted by experts from diverse fields to explore the latest advancements in voice biomarkers and artificial intelligence (AI) applications in healthcare. Through five workshops, attendees learned about topics including international standardization of vocal biomarker data, real-world deployment of AI solutions, assistive technologies for voice disorders, best practices for voice data collection, and deep learning applications in voice analysis. These workshops aimed to foster collaboration between academia, industry, and healthcare to advance the development and implementation of voice-based AI tools. Each workshop featured a combination of lectures, case studies, and interactive discussions. Transcripts of audio recordings were generated using Whisper (Version 7.13.1) and summarized by ChatGPT (Version 4.0), then reviewed by the authors. The workshops covered various methodologies, from signal processing and machine learning operations (MLOps) to ethical concerns surrounding AI-powered voice data collection. Practical demonstrations of AI-driven tools for voice disorder management and technical discussions on implementing voice AI models in clinical and non-clinical settings provided attendees with hands-on experience. Key outcomes included the discussion of international standards to unify stakeholders in vocal biomarker research, practical challenges in deploying AI solutions outside the laboratory, review of Bridge2AI-Voice data collection processes, and the potential of AI to empower individuals with voice disorders. Additionally, presenters shared innovations in ethical AI practices, scalable machine learning frameworks, and advanced data collection techniques using diverse voice datasets. The symposium highlighted the successful integration of AI in detecting and analyzing voice signals for various health applications, with significant advancements in standardization, privacy, and clinical validation processes. The symposium underscored the importance of interdisciplinary collaboration to address the technical, ethical, and clinical challenges in the field of voice biomarkers. While AI models have shown promise in analyzing voice data, challenges such as data variability, security, and scalability remain. Future efforts must focus on refining data collection standards, advancing ethical AI practices, and ensuring diverse dataset inclusion to improve model robustness. By fostering collaboration among researchers, clinicians, and technologists, the symposium laid a foundation for future innovations in AI-driven voice analysis for healthcare diagnostics and treatment.

Accurate detection of gait events using neural networks and IMU data mimicking real-world smartphone usage

Wearable technologies such as inertial measurement units (IMUs) can be used to evaluate human gait and improve mobility, but sensor fixation is still a limitation that needs to be addressed. Therefore, aim of this study was to create a machine learning algorithm to predict gait events using a single IMU mimicking the carrying of a smartphone. Fifty-two healthy adults (35 males/17 females) walked on a treadmill at various speeds while carrying a surrogate smartphone in the right hand, front right trouser pocket, and right jacket pocket. Ground-truth gait events (e.g. heel strikes and toe-offs) were determined bilaterally using a gold standard optical motion capture system. The tri-dimensional accelerometer and gyroscope data were segmented in 20-ms windows, which were labelled as containing or not the gait events. A long-short term memory neural network (LSTM-NN) was used to classify the 20-ms windows as containing the heel strike or toe-off for the right or left legs, using 80% of the data for training and 20% of the data for testing. The results demonstrated an overall accuracy of 92% across all phone positions and walking speeds, with a slightly higher accuracy for the right-side predictions (∼94%) when compared to the left side (∼91%). Moreover, we found a median time error <3% of the gait cycle duration across all speeds and positions (∼77 ms). Our results represent a promising first step towards using smartphones for remote gait analysis without requiring IMU fixation, but further research is needed to enhance generalizability and explore real-world deployment.

An estimation method for vision-based autonomous landing system for fixed wing aircraft

In this paper, we propose a vision-based estimation method for autonomous landing of fixed-wing aircraft for Advanced Air Mobility. The concept of autonomous flight with minimal human intervention has gained significant interest with a particular focus on autonomous landing. The goal is to overcome the limitations of existing instrument landing systems and reduce reliance on GNSS during aircraft landing. The proposed system leverages the following techniques for high-performance and real-time operations in various real-world environments and during all stages of landing. A deep learning segmentation model was directly learned, created, and used for robust runway recognition performance against environmental changes around the runway. Algorithms were designed to adapt to different flight stages considering the varying information offered by image data when the aircraft is in mid-air and on the ground. The relative lateral position from the aircraft to the runway was estimated using bird’s-eye-view conversion and inverse projection techniques instead of conventional perspective-n-point methods for reducing the recognition error occurring from the conversion between 2D image and 3D world. Finally, the mixed-precision technique was used for the segmentation model to improve inference speed and ensure real-time operation in real-world deployment. Estimation stability and reliability were improved by using a Kalman Filter to cope with sensor uncertainties caused by the real-world flight environment. Consequently, we show that the average error in the lateral position estimation by the proposed method is comparable to the accuracy of a single GNSS and demonstrate successful autonomous landing of our test aircraft with a set of flight tests.

Enhancing IoT Security through an Artificial Neural Network Approach

This study aims to fortify Internet of Things (IoT) security through the strategic implementation of Artificial Neural Networks (ANNs). With the rapid expansion of IoT devices, traditional security measures have struggled to cope with the dynamic and complex nature of these environments. ANNs, known for their adaptability, are explored as a promising solution to enhance security. The central objective is to significantly improve the accuracy of IoT security measures by optimizing ANN architectures. Using a curated dataset with key environmental parameters, the study evaluates three ANN models—Backpropagation Neural Network (BPNN), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM). The evaluation metrics include accuracy, precision, recall, and F1-score across different train-test splits. Results show that LSTM consistently outperforms BPNN and MLP, demonstrating superior accuracy and the ability to capture temporal dependencies within IoT security data. Implications stress the importance of aligning model selection with specific application goals, considering factors like computational efficiency. In conclusion, this research contributes valuable insights into the practical implementation of ANNs for IoT security, guiding future optimization efforts and addressing real-world deployment challenges to safeguard sensitive data and ensure system resilience in the evolving IoT landscape.

Navigating Trust and Safety in Multi-Agent Reinforcement Learning: Attacks, Defenses, and Future Directions

Multi-Agent Reinforcement Learning (MARL) is a key framework for building intelligent systems where multiple agents operate within a shared environment, with applications spanning autonomous driving, robotics, and distributed control systems. However, real-world deployment of MARL brings significant trust and safety challenges, as these systems are susceptible to a range of attacks that can compromise their robustness and reliability. This paper provides a comprehensive review of trust and safety attacks in MARL, categorizing various types of attacks and their implications. We explore existing defense mechanisms designed to mitigate these threats, highlighting their strengths and limitations. Additionally, we identify open challenges that remain unaddressed and propose potential future research directions to enhance the robustness and security of MARL systems.