Open Challenges Research Articles

Hybrid learning based service migration for cost minimization with deadlines in multi-user mobile edge computing systems

Mobile edge computing, a new computing model, aims to reduce network latency and improve user experience by placing computing resources closer to the users. However, when users move away from the current service areas, the quality of services will decline. To guarantee the quality of services, service migration technique is proposed and studied. Due to the wireless resource contention among users, there is service migration decision-making coupling among multiple users. Meanwhile, making real-time service migration decisions for multiple users to minimize service cost with application deadlines remains an open challenge because of the huge state space. In this paper, we formalize the service migration problem with deadlines as a Markov decision process (MDP) and propose a hybrid learning based service migration strategy. The proposed approach integrates Monte Carlo method and DQN learning, which adopts online training without Q-values and neural network approximation to generate service migration decisions for multiple users. Experimental results demonstrate that the proposed hybrid learning based service migration strategy outperforms the existing migration strategies in terms of service success ratio and service cost.

Artificial Intelligence-Based Algorithms in Medical Image Scan Segmentation and Intelligent Visual Content Generation—A Concise Overview

Recently, artificial intelligence (AI)-based algorithms have revolutionized the medical image segmentation processes. Thus, the precise segmentation of organs and their lesions may contribute to an efficient diagnostics process and a more effective selection of targeted therapies, as well as increasing the effectiveness of the training process. In this context, AI may contribute to the automatization of the image scan segmentation process and increase the quality of the resulting 3D objects, which may lead to the generation of more realistic virtual objects. In this paper, we focus on the AI-based solutions applied in medical image scan segmentation and intelligent visual content generation, i.e., computer-generated three-dimensional (3D) images in the context of extended reality (XR). We consider different types of neural networks used with a special emphasis on the learning rules applied, taking into account algorithm accuracy and performance, as well as open data availability. This paper attempts to summarize the current development of AI-based segmentation methods in medical imaging and intelligent visual content generation that are applied in XR. It concludes with possible developments and open challenges in AI applications in extended reality-based solutions. Finally, future lines of research and development directions of artificial intelligence applications, both in medical image segmentation and extended reality-based medical solutions, are discussed.

A Comprehensive Survey on Feature Selection with Grasshopper Optimization Algorithm

Recent growth in data dimensions presents challenges to data mining and machine learning. A high-dimensional dataset consists of several features. Data may include irrelevant or additional features. By removing these redundant and unwanted features, the dimensions of the data can be reduced. The feature selection process eliminates a small set of relevant and important features from a large data set, reducing the size of the dataset. Multiple optimization problems can be solved using metaheuristic algorithms. Recently, the Grasshopper Optimization Algorithm (GOA) has attracted the attention of researchers as a swarm intelligence algorithm based on metaheuristics. An extensive review of papers on GOA-based feature selection algorithms in the years 2018–2023 is presented based on extensive research in the area of feature selection and GOA. A comparison of GOA-based feature selection methods is presented, along with evaluation strategies and simulation environments in this paper. Furthermore, this study summarizes and classifies GOA in several areas. Although many researchers have introduced their novelty in the feature selection problem, many open challenges and enhancements remain. The survey concludes with a discussion about some open research challenges and problems that require further attention.

Simulation study of electron beam optics for a distributed X-ray source toward stationary CT architecture

For computed tomography (CT) imaging to be considered “real time”, one set of tomographic projections are to be acquired in less than 30 ms. Current conventional CT systems are limited to approximately 300 ms because of mechanical and material limitations. To bypass the mechanical limitations of a conventional gantry system, there is an open design challenge to develop a distributed X-ray source that is tightly packed and bright. The work presented here reports a design for a distributed X-ray source based on a rotating cylindrical anode. In particular, this work focuses on designing the electron beam optics for said X-ray source and refining these optics via multi-physics simulation studies. We designed these studies to investigate the electron beam behavior for switching, steering, and focusing. We demonstrated that the high-energy electron beam could be turned off and on via the grid-switching technique, could be steered, and could be dynamically focused for distinct positions along the cylindrical anode. We also report the optimal set of parameters that result in the desired electronic focal spot size (1 mm × 7 mm) and shape at each source position for our system.

Integrated Photonics for Quantum Communications and Metrology

Over the last two decades, integrated photonics has profoundly revolutionized the domain of quantum technologies. The ongoing second quantum revolution stands as a timely opportunity for a state-of-the-art review and, most important, an exploration of the directions undertaken by integrated quantum photonics. Within this perspective, based on the recent advances, we discuss the current challenges and future trends related to different technological platforms. Key examples will be considered across various subfields, including quantum communication, quantum metrology, and quantum memories. Our discussion encompasses disruptive concepts, progress, and potential limitations. The main objective of this Perspective is to provide the reader with a forward-looking discussion ranging from state-of-the-art developments to open challenges of the field. Published by the American Physical Society 2024

ZrO2 Holographic Metasurfaces for Efficient Optical Trapping in The Visible Range

AbstractHolographic Metasurfaces (HMs) in the visible range enable advanced imaging applications in compact, planarized systems. The ability to control and structure light with high accuracy and a high degree of freedom is particularly relevant in lab‐on‐chip biophotonic applications. Pushing the operation wavelength into the blue region and below is an open challenge. Here, it is demonstrated that Zirconium dioxide (ZrO2) metasurfaces (MSs) are particularly well‐suited to satisfy these requirements. Specifically, MSs are designed for optical trapping applications with a high numerical aperture (NA = 1.2) at a wavelength as low as 488 nm, with trap stiffness >200 pN (µmW)−1.

An Improved Detection Method for Crop & Fruit Leaf Disease under Real-Field Conditions

Using deep learning-based tools in the field of agriculture for the automatic detection of plant leaf diseases has been in place for many years. However, optimizing their use in the specific background of the agriculture field, in the presence of other leaves and the soil, is still an open challenge. This work presents a deep learning model based on YOLOv6s that incorporates (1) Gaussian error linear unit in the backbone, (2) efficient channel attention in the basic RepBlock, and (3) SCYLLA-Intersection Over Union (SIOU) loss function to improve the detection accuracy of the base model in real-field background conditions. Experiments were carried out on a self-collected dataset containing 3305 real-field images of cotton, wheat, and mango (healthy and diseased) leaves. The results show that the proposed model outperformed many state-of-the-art and recent models, including the base YOLOv6s, in terms of detection accuracy. It was also found that this improvement was achieved without any significant increase in the computational cost. Hence, the proposed model stood out as an effective technique to detect plant leaf diseases in real-field conditions without any increased computational burden.

Severe floods predictive ability: A proxy based probabilistic assessment of the Italian early warning system

AbstractIn compliance with the national legal framework, the regional offices (CFDs) of the Italian Civil Protection Department have the daily duty to issue warnings to the local population on the account of the weather and hydrology‐related impacts, predicted by forecast models and refined through their expertise and experience: this composite of objective (model) and subjective (analyst) assessments are both contributing to the actual colour‐coded warning system. Given its hybrid nature, it is of paramount importance to evaluate the predictive ability of the warning decision‐making process as a whole. To this end, this study compares the return period T of the occurred flood (estimated through an hydrological model fed with observations) to the warning level that was issued. The novelty of this approach is that, by applying this methodology extensively in space and time, the probability curves of the variable T for each warning level are computed, allowing to evaluate the consistency between the warnings and the actual (estimated) severity of the event. As results suggest, the national early warning system is proven to be overall reliable for most cases, though very fine scale events (e.g., severe, localised, short‐lived thunderstorms) are still an open challenge.

Scaled local gate controller for optically addressed qubits

Scalable classical controllers are a key component of future fault-tolerant quantum computers. Neutral atom quantum computers leverage commercially available optoelectronic devices for generating large-scale tweezer arrays and performing parallel readout, but implementing massively parallel, locally addressed gate operations is an open challenge. In this work, we demonstrate an optical modulator system based on off-the-shelf components, which can generate a two-dimensional array of over 10,000 focused spots with uniform frequency and amplitude, and switching them on and off individually in arbitrary configurations at rates of up to 43 kHz. Through careful control of aberrations, the modulator achieves an extinction ratio of 46 dB, and nearest-neighbor crosstalk of −44dB with a beam spacing of 4.6 waists. The underlying components can operate at wavelengths from the UV to the NIR, and sustain high laser intensities. This approach is suitable for local addressing of gates with low cross-talk error rates in any optically addressed qubit platform, including neutral atoms, trapped ions, or solid-state atomic defects.

Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance

Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security, privacy, and fairness issues in AI systems. In this paper, we review representative techniques, algorithms, and theoretical foundations for trustworthy distributed AI through robustness guarantee, privacy protection, and fairness awareness in distributed learning. We first provide a brief overview of alternative architectures for distributed learning, discuss inherent vulnerabilities for security, privacy, and fairness of AI algorithms in distributed learning, and analyze why these problems are present in distributed learning regardless of specific architectures. Then we provide a unique taxonomy of countermeasures for trustworthy distributed AI, covering (1) robustness to evasion attacks and irregular queries at inference, and robustness to poisoning attacks, Byzantine attacks, and irregular data distribution during training; (2) privacy protection during distributed learning and model inference at deployment; and (3) AI fairness and governance with respect to both data and models. We conclude with a discussion on open challenges and future research directions toward trustworthy distributed AI, such as the need for trustworthy AI policy guidelines, the AI responsibility-utility co-design, and incentives and compliance.

Standardizing digital biobanks: integrating imaging, genomic, and clinical data for precision medicine.

Advancements in data acquisition and computational methods are generating a large amount of heterogeneous biomedical data from diagnostic domains such as clinical imaging, pathology, and next-generation sequencing (NGS), which help characterize individual differences in patients. However, this information needs to be available and suitable to promote and support scientific research and technological development, supporting the effective adoption of the precision medicine approach in clinical practice.Digital biobanks can catalyze this process, facilitating the sharing of curated and standardized imaging data, clinical, pathological and molecular data, crucial to enable the development of a comprehensive and personalized data-driven diagnostic approach in disease management and fostering the development of computational predictive models.This work aims to frame this perspective, first by evaluating the state of standardization of individual diagnostic domains and then by identifying challenges and proposing a possible solution towards an integrative approach that can guarantee the suitability of information that can be shared through a digital biobank.Our analysis of the state of the art shows the presence and use of reference standards in biobanks and, generally, digital repositories for each specific domain. Despite this, standardization to guarantee the integration and reproducibility of the numerical descriptors generated by each domain, e.g. radiomic, pathomic and -omic features, is still an open challenge. Based on specific use cases and scenarios, an integration model, based on the JSON format, is proposed that can help address this problem.Ultimately, this work shows how, with specific standardization and promotion efforts, the digital biobank model can become an enabling technology for the comprehensive study of diseases and the effective development of data-driven technologies at the service of precision medicine.

OEBench: Investigating Open Environment Challenges in Real-World Relational Data Streams

How to get insights from relational data streams in a timely manner is a hot research topic. Data streams can present unique challenges, such as distribution drifts, outliers, emerging classes, and changing features, which have recently been described as open environment challenges for machine learning. While existing studies have been done on incremental learning for data streams, their evaluations are mostly conducted with synthetic datasets. Thus, a natural question is how those open environment challenges look like and how existing incremental learning algorithms perform on real-world relational data streams. To fill this gap, we develop an Open Environment Benchmark named OEBench to evaluate open environment challenges in real-world relational data streams. Specifically, we investigate 55 real-world relational data streams and establish that open environment scenarios are indeed widespread, which presents significant challenges for stream learning algorithms. Through benchmarks with existing incremental learning algorithms, we find that increased data quantity may not consistently enhance the model accuracy when applied in open environment scenarios, where machine learning models can be significantly compromised by missing values, distribution drifts, or anomalies in real-world data streams. The current techniques are insufficient in effectively mitigating these challenges brought by open environments. More researches are needed to address real-world open environment challenges. All datasets and code are open-sourced in https://github.com/Xtra-Computing/OEBench.

NADOL: Neuromorphic Architecture for Spike-Driven Online Learning by Dendrites.

Biologically plausible learning with neuronal dendrites is a promising perspective to improve the spike-driven learning capability by introducing dendritic processing as an additional hyperparameter. Neuromorphic computing is an effective and essential solution towards spike-based machine intelligence and neural learning systems. However, on-line learning capability for neuromorphic models is still an open challenge. In this study a novel neuromorphic architecture with dendritic on-line learning (NADOL) is presented, which is a novel efficient methodology for brain-inspired intelligence on embedded hardware. With the feature of distributed processing using spiking neural network, NADOL can cut down the power consumption and enhance the learning efficiency and convergence speed. A detailed analysis for NADOL is presented, which demonstrates the effects of different conditions on learning capabilities, including neuron number in hidden layer, dendritic segregation parameters, feedback connection, and connection sparseness with various levels of amplification. Piecewise linear approximation approach is used to cut down the computational resource cost. The experimental results demonstrate a remarkable learning capability that surpasses other solutions, with NADOL exhibiting superior performance over the GPU platform in dendritic learning. This study's applicability extends across diverse domains, including the Internet of Things, robotic control, and brain-machine interfaces. Moreover, it signifies a pivotal step in bridging the gap between artificial intelligence and neuroscience through the introduction of an innovative neuromorphic paradigm.

Toward Zero-Trust Security for the Metaverse

By focusing on immersive interaction among users, the burgeoning Metaverse can be viewed as a natural extension of existing social media. Similar to traditional online social networks, there are numerous security and privacy issues in the Metaverse (e.g., attacks on user authentication and impersonation). In this paper, we develop a holistic research agenda for zero-trust user authentication in social virtual reality (VR), an early prototype of the Metaverse. Our proposed research includes four concrete steps: investigating biometrics-based authentication that is suitable for continuously authenticating VR users, leveraging federated learning (FL) for protecting user privacy in biometric data, improving the accuracy of continuous VR authentication with multimodal data, and boosting the usability of zero-trust security with adaptive VR authentication. Our preliminary study demonstrates that conventional FL algorithms are not well suited for biometrics-based authentication of VR users, leading to an accuracy of less than 10%. We discuss the root cause of this problem, the associated open challenges, and several future directions for realizing our research vision.

Pose Control of Millimeter-Scale Objects in a Laser-Powered Thermocapillary Manipulation Platform

The miniaturization of technological components requires tools capable of manipulating them. Noncontact micromanipulation has recently gained popularity since it minimizes component damage and adhesion problems. However, the simultaneous position and orientation (pose) control using noncontact tools remains an open challenge. In this work, we propose the pose control of millimeter-scale structures at the air–water interface using laser-powered thermocapillary flows. We achieve autonomous pose control by steering two laser spots around the structure in a closed-loop manner. The controller consists of a linear pose controller and a model inversion. The pose controller defines the required force and torque to reach the target. The model inversion defines the required laser positions to obtain said force and torque. This inversion is performed with an optimization algorithm, without any prescribed strategy. The pose stabilization was validated experimentally, obtaining a position and orientation precision of 0.15 body lengths and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$2^{\circ }$</tex-math></inline-formula> , respectively. Additionally, we show the experimental path-following with independent orientation control, obtaining a similar position precision.

Resource allocation problem and artificial intelligence: the state-of-the-art review (2009–2023) and open research challenges

Resource allocation problem and artificial intelligence: the state-of-the-art review (2009–2023) and open research challenges

Real-Time Semantic Data Integration and Reasoning in Life- and Time-Critical Decision Support Systems

Natural disasters such as earthquakes, floods, and forest fires involve critical situations in which human lives and infrastructures are in jeopardy. People are often injured and/or trapped without being able to be assisted by first responders on time. Moreover, in most cases, the harsh environment jeopardizes first responders by significantly increasing the difficulty of their mission. In such scenarios, time is crucial and often of vital importance. First responders must have a clear and complete view of the current situation every few seconds/minutes to efficiently and timely tackle emerging challenges, ensuring the safety of both victims and personnel. Advances in related technology including robots, drones, and Internet of Things (IoT)-enabled equipment have increased their usability and importance in life- and time-critical decision support systems such as the ones designed and developed for Search and Rescue (SAR) missions. Such systems depend on efficiency in their ability to integrate large volumes of heterogeneous and streaming data and reason with this data in (near) real time. In addition, real-time critical data integration and reasoning need to be performed on edge devices that reside near the missions, instead of using cloud infrastructure. The aim of this paper is twofold: (a) to review technologies and approaches related to real-time semantic data integration and reasoning on IoT-enabled collaborative entities and edge devices in life- and time-critical decision support systems, with a focus on systems designed for SAR missions and (b) to identify open issues and challenges focusing on the specific topic. In addition, this paper proposes a novel approach that will go beyond the state-of-the-art in efficiently recognizing time-critical high-level events, supporting commanders and first responders with meaningful and life-critical insights about the current and predicted state of the environment in which they operate.

A Review on Sensor‐Integrating Machine Elements

AbstractThis contribution summarizes the current state of research regarding so‐called sensor‐integrating machine elements as an enabler of digitalization in mechanical engineering and——if available—their application in industry. The focus is on the methodical aspects of the development of these machine elements in general as well as specific sensor‐integrating machine elements that are either already in use or currently under development. Developmental aspects include the robust design of initially evaluated concepts for sensor‐integrating machine elements as well as their modularization. Smart materials with sensory functions are included in the analysis as well as the differentiation with regard to add‐on sensors. The aim of the authors interlinked by a special research program funded by the German Research Foundation (DFG) is to facilitate the exchange with other researchers with the help of the comprehensive overview given in this contribution. The contribution concludes with a brief discussion of open challenges, such as the energy supply and data transfer in rotating systems and also data security.

Privacy-preserving association rule mining: a survey of techniques for sensitive rule identification and enhanced data protection

Over the past few decades, pervasive computing has generated increasing amounts of data. Data mining (DM) technology is becoming more widely used. Due to the potential threats to the confidentiality of people and organizations, the massive collecting and analysis of data might raise privacy issues. A new research area termed privacy-preserving association rule mining (PPARM), which has attracted the interest of many researchers, has emerged to prevent privacy disclosure during DM. The research field PPARM, aims to prevent association rule mining privacy infractions from happening. The study uses a systematic survey to understand the literature on PPARM techniques for sensitive rule identification and enhanced data protection. Here, the application area of PPARM has been explored, summarized, and concluded with some open challenges and future directions.

Sparse species interactions reproduce abundance correlation patterns in microbial communities

During the last decades, macroecology has identified broad-scale patterns of abundances and diversity of microbial communities and put forward some potential explanations for them. However, these advances are not paralleled by a full understanding of the dynamical processes behind them. In particular, abundance fluctuations of different species are found to be correlated, both across time and across communities in metagenomic samples. Reproducing such correlations through appropriate population models remains an open challenge. The present paper tackles this problem and points to sparse species interactions as a necessary mechanism to account for them. Specifically, we discuss several possibilities to include interactions in population models and recognize Lotka-Volterra constants as a successful ansatz. For this, we design a Bayesian inference algorithm to extract sets of interaction constants able to reproduce empirical probability distributions of pairwise correlations for diverse biomes. Importantly, the inferred models still reproduce well-known single-species macroecological patterns concerning abundance fluctuations across both species and communities. Endorsed by the agreement with the empirically observed phenomenology, our analyses provide insights into the properties of the networks of microbial interactions, revealing that sparsity is a crucial feature.