Search

Artificial Intelligence (AI) and Machine Learning (ML) approaches have emerged in the networking domain with great expectation. They can be broadly divided into AI/ML techniques for network engineering and management, network designs for AI/ML applications, and system concepts. AI/ML techniques for networking and management improve the way we address networking. They support efficient, rapid, and trustworthy engineering, operations, and management. As such, they meet the current interest in softwarization and network programmability that fuels the need for improved network automation in agile infrastructures, including edge and fog environments. Network design and optimization for AI/ML applications addresses the complementary topic of supporting AI/ML-based systems through novel networking techniques, including new architectures and algorithms. The third topic area is system implementation and open-source software development. [ABSTRACT FROM AUTHOR]

The papers in this special section present the state-of-the-art technologies and the challenges of parallel and distributed computing techniques for artificial intelligence (AI), machine learning (ML), and deep learning (DL). AI, ML, and DL have established themselves in a multitude of domains because of their ability to process and model unstructured input data. [ABSTRACT FROM AUTHOR]

The IEEE Transactions on Semiconductor Manufacturing congratulates Yonghwi Kwon and Youngsoo Shin whose paper Optical Proximity Correction Using Bidirectional Recurrent Neural Network With Attention Mechanism was selected as the Best paper for 2021. The paper was selected from all the papers that appeared in 2021 by a team of Associate Editors. This paper applied recurrent neural networks to optical proximity correction for lithographic processing for integrated circuits. The challenge in determining a correction value comes from correlation: correction of one segment affects the correction value of other segments due to the optical proximity effect. This paper broke new ground by showing that Recurrent Neural Networks, which has been mainly applied to time series data, can be effectively applied to spatial data. Clearly, Machine Learning is rapidly moving from R&D into full flow manufacturing where the interplay between each aspect of a single process step has exponential increased in complexity requiring new approaches. Three additional papers were recognized with an Honorable Mention: [ABSTRACT FROM AUTHOR]

Innovations in digital health and machine learning are changing the path of clinical health and care. People from different geographical locations and cultural backgrounds can benefit from the mobility of wearable devices and smartphones to monitor their health ubiquitously. This paper focuses on reviewing the digital health and machine learning technologies used in gestational diabetes – a subtype of diabetes that occurs during pregnancy. This paper reviews sensor technologies used in blood glucose monitoring devices, digital health innovations and machine learning models for gestational diabetes monitoring and management, in clinical and commercial settings, and discusses future directions. Despite one in six mothers having gestational diabetes, digital health applications were underdeveloped, especially the techniques that can be deployed in clinical practice. There is an urgent need to (1) develop clinically interpretable machine learning methods for patients with gestational diabetes, assisting health professionals with treatment, monitoring, and risk stratification before, during and after their pregnancies; (2) adapt and develop clinically-proven devices for patient self-management of health and well-being at home settings (“virtual ward” and virtual consultation), thereby improving clinical outcomes by facilitating timely intervention; and (3) ensure innovations are affordable and sustainable for all women with different socioeconomic backgrounds and clinical resources. [ABSTRACT FROM AUTHOR]

Scenario identification plays an important role in improving communication system performance. Considering that the scenarios of vehicle communications are dynamic due to movements of vehicles, and there are obvious differences in channel characteristics, vehicle speeds, traffic densities between various scenarios, the requirement for real-time scenario identification of vehicular communications is increasingly urgent. Vehicular communication systems can select appropriate channel models and transmission mode by correctly identifying the current scenarios to maintain an effective and reliable operating state. This paper presents a machine-learning-based scenario identification model for intelligent vehicular communications. Channel characteristics extracted from channel measurements in different scenarios form the datasets used to training, then a back-propagation neural network (BPNN) is trained, and a scenario identification model is obtained. Furthermore, the model configuration scheme is explored and presented which can make the proposed identification model achieves optimal performance. Subsequently, identification accuracy is verified by using validation data of the corresponding scenarios. The results show that the identification accuracies are all above 98 % in four typical scenarios of urban areas, highways, tunnels, and vehicle obstructions, which indicates that the model proposed in this paper shows good performance in scenario identification for intelligent vehicular communications. [ABSTRACT FROM AUTHOR]

In this paper, we propose to use commercial off-the-shelf (COTS) monostatic RFID devices (i.e. which use a single antenna at a time for both transmitting and receiving RFID signals to and from the tags) to monitor browsing activity of customers in front of display items in places such as retail stores. To this end, we propose TagSee, a multi-person imaging system based on monostatic RFID imaging. TagSee is based on the insight that when customers are browsing the items on a shelf, they stand between the tags deployed along the boundaries of the shelf and the reader, which changes the multi-paths that the RFID signals travel along, and both the RSS and phase values of the RFID signals that the reader receives change. Based on these variations observed by the reader, TagSee constructs a coarse grained image of the customers. Afterwards, TagSee identifies the items that are being browsed by the customers by analyzing the constructed images. The key novelty of this paper is on achieving browsing behavior monitoring of multiple customers in front of display items by constructing coarse grained images via robust, analytical model-driven deep learning based, RFID imaging. To achieve this, we first mathematically formulate the problem of imaging humans using monostatic RFID devices and derive an approximate analytical imaging model that correlates the variations caused by human obstructions in the RFID signals. Based on this model, we then develop a deep learning framework to robustly image customers with high accuracy. We implement TagSee scheme using a Impinj Speedway R420 reader and SMARTRAC DogBone RFID tags. TagSee can achieve a TPR of more than ${\sim }90\%$ ∼ 90 % and a FPR of less than ${\sim }10\%$ ∼ 10 % in multi-person scenarios using training data from just 3-4 users. [ABSTRACT FROM AUTHOR]

This paper presents an asset health index (HI) prediction methodology for high voltage transmission overhead lines (OHLs) using supervised machine learning and structured, unambiguous visual inspections. We propose a framework for asset HI predictions to determine the technical condition of individual OHL towers to improve grid reliability in a cost-effective manner. The paper focuses on asset HI prediction and the selection of the most parsimonious model. Based on the technical specifications and HI data, our methodology allows for the prediction of a HI for OHLs without HI data, and models asset aging behaviour. Technical specifications and the HI as defined in this paper are taken from the Estonian TSO periodical visual inspections implemented in 2018. The case study successfully demonstrates that the proposed methodology can predict tower HI values for a single OHL with nearly 80 percent accuracy without the need for additional measurements. [ABSTRACT FROM AUTHOR]

In a recent Special Section published in IEEE Transactions on Consumer Electronics we introduced smart electronics. We presented a set of papers which were selected after rigorous review with a scope of artificial intelligence (AI) or machine learning (ML) approaches used for various levels of system abstractions, from device-level to system-level. In one school of thought energy-smart, security-smart, and response-smart are 3 dimensions of smart electronic systems. [ABSTRACT FROM AUTHOR]

Due to the advancement of camera hardware and machine learning techniques, video object tracking for surveillance has received noticeable attention from the computer vision research community. Object tracking and trajectory modeling have important applications in surveillance video analysis. For example, trajectory clustering, summarization or synopsis generation, and detection of anomalous or abnormal events in videos are mainly being exploited by the research community. However, barring one research work (which is almost a decade old), there is no recent review that emphasizes the use of video object trajectories, particularly in the perspective of visual surveillance. This paper presents a survey of trajectory-based surveillance applications with a focus on clustering, anomaly detection, summarization, and synopsis generation. The methods reviewed in this paper broadly summarize the abovementioned applications. The main purpose of this survey is to summarize the state-of-the-art video object trajectory analysis techniques used in the indoor and outdoor surveillance. [ABSTRACT FROM AUTHOR]

This paper reports the development of a manipulation system for electric wires, implemented by means of a commercial gripper installed on an industrial manipulator and equipped with cameras and suitably designed tactile sensors. The purpose of this system is the execution of wire insertion on commercial electromechanical components. The synergy between computer vision and tactile sensing is necessary because, in a real environment, the tight spaces very often prevent the possibility to use the vision system, also when the same task is performed by a human being. A novel technique to speed up the generation of training data sets for convolutional neural networks (CNNs) is proposed. Therefore, this technique is used to train a CNN in order to detect small objects (such as wire terminals). Moreover, aiming to prevent faults during the task and to interact with the environment safely, several machine learning approaches are used to produce an affordable output from the tactile sensor. The proposed approach shows how a cheap sensor embedded with suitable intelligence can provide information comparable to a more expensive force sensor. Note to Practitioners—This paper was motivated by the lack of commercial solution for the automatic cabling of switchgears. Existing approaches to this problem are in some way limited to specific large-scale products or simple layouts. This paper investigated a robust and flexible solution, based on the exploitation of multiple sensors and machine learning algorithms, for wire detection, grasping, and connection. The proposed approach is characterized by simple design and self-tuning capabilities, and it can be easily employed on a wide range of switchgear layouts thanks to the large workspace of the manipulator. Experimental results show that the proposed system is able to achieve a 95% success rate within a realistic admissible region. In the future research, we will integrate the proposed solution with an electromechanical component localization module and a terminal fastening system to evaluate the performance on the real production line. [ABSTRACT FROM AUTHOR]

Web-based appointment systems are emerging in healthcare industry providing patients with convenient and diversiform services, among which physician recommendation is becoming more and more popular tool to make assignments of physicians to patients. Motivated by a popular physician recommendation application on a web-based appointment system in China, this paper gives a pioneer work in modeling and solving the physician recommendation problem. The application delivers personalized recommendations of physician assortments to patients with heterogeneous illness conditions, and then, patients would select one physician for appointment according to their preferences. Capturing patient preferences is essential for physician recommendation delivery; however, it is also challenging due to the lack of data on patient preferences. In this paper, we formulate the physician recommendation problem based on which the preference learning algorithm is proposed that optimizes the recommendations and learns patient preferences at the same time. Since the illness conditions of patients are heterogeneous, the algorithm aims to make personalized recommendation for each patient. Besides demonstrating the effectiveness of algorithm performance in terms of regret bound, we also provide extensive numerical experiments to show the expected algorithm performance under heterogeneous reward scenarios and performance comparison with algorithms in the literature under fixed reward scenarios. We introduce the flexibility of adjusting preference estimate update interval into our algorithm and conclude that short update interval contributes to short-term performance while long update interval leads to good results in the long run. Furthermore, we analyze how preference bound helps the algorithm to make explorations, which constitute two major contributions of our algorithm. Finally, we discuss the relevance between patient preferences and physician utilization and present a utilization-balancing approach that is effective in numerical experiments. Note to Practitioners—This paper aims at addressing the challenge of recommending physicians to patients on web-based appointment systems, so as to achieve efficient and effective utilization of physician resources. Currently, the recommendations are delivered manually by a huge number of general practitioners hired by the platforms based on their expertise and experiences. Upon each arrival of patient, they upload symptom statements of their own illness, and then, general practitioners will give a score or a rating on how well these patients are matched to physicians on the basis of symptom descriptions. With the development of artificial intelligence and information technology, these works might be done efficiently and effectively by algorithms automatically. To accomplish that, challenges will be presented: 1) physicians with adequate expertise might conflict with patient preferences, i.e., patients have strong preference toward senior specialists but their illness should be taken care of by a junior physician. This conflict indicates the importance of capturing patient preferences and choices in web-based appointment system operations and 2) the lack of patient preferences information makes the problem even harder. For newly developed web-based system, there are no available historical data to infer the preference parameters. On the other hand, the historical data in the web-based appointment system might not be able to reveal full information on patient preferences, because the system did not conduct effective and comprehensive explorations over all possible operations in the past. We capture the heterogeneous illness conditions in terms of rewards to imply the potential health improvement of patients. This paper assumes complete information of patient illness descriptions, and therefore, we focus on the operations management of appointment system, i.e., how to deliver the optimized physician assortment. [ABSTRACT FROM AUTHOR]

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. A list of important papers discussed in this survey, corresponding codes, and additional resources on BLOs are publicly available at: https://github.com/vis-opt-group/BLO. [ABSTRACT FROM AUTHOR]

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) and Kernel principal component analysis (KPCA) are fundamental methods in machine learning for dimensionality reduction. The former is a technique for finding this approximation in finite dimensions and the latter is often in an infinite dimensional reproducing Kernel Hilbert-space (RKHS). In this paper, we present a geometric framework for computing the principal linear subspaces in both (finite and infinite) situations as well as for the robust PCA case, that amounts to computing the intrinsic average on the space of all subspaces: the Grassmann manifold. Points on this manifold are defined as the subspaces spanned by $K$ K -tuples of observations. The intrinsic Grassmann average of these subspaces are shown to coincide with the principal components of the observations when they are drawn from a Gaussian distribution. We show similar results in the RKHS case and provide an efficient algorithm for computing the projection onto the this average subspace. The result is a method akin to KPCA which is substantially faster. Further, we present a novel online version of the KPCA using our geometric framework. Competitive performance of all our algorithms are demonstrated on a variety of real and synthetic data sets. [ABSTRACT FROM AUTHOR]

Data quality plays an important role during the training stage of machine/deep learning models. The annotation hinges on the experiences of domain experts. To acquire the expert’s knowledge in the context of machine learning, manual data labeling, a tedious and time-consuming task in supervised learning, should be given a top priority. However, the domain experts in the line of plentiful manual annotation may easily get distracted or fatigued after long-time work, causing judgment errors, mislabeling, etc. The pattern recognition of wafer defect map is investigated in this paper, the primary goal of which is to train the convolutional neural network (CNN) model through a very limited number of manually labeled data so that the trained model is capable of performing pseudo labeling. Subsequently, a self-assured adaptive ensemble learner in terms of a series of shallow neural networks is proposed to filter wafer map samples with untrusted pseudo-labels. In the result, the amount of human annotations is significantly reduced by 61% for training a highly accurate classifier. A minimum number of manually labeled data is suggested while the equally high classification performance of wafer defect pattern is maintained. For the evaluation purpose, the proposed self-assured learning is compared with the confidence learning. [ABSTRACT FROM AUTHOR]

The papers in this special section is to broadly engage the machine learning and multimedia communities on the emerging yet challenging interpretable machine learning. Multimedia is increasingly becoming the "biggest big data," among the most important and valuable source for insight and information. Many powerful machine learning algorithms, especially deep learning models such as convolutional neural networks (CNNs), have recently achieved outstanding predictive performance in a wide range of multimedia applications, including visual object classification, scene understanding, speech recognition, and activity prediction. Nevertheless, most deep learning algorithms are generally conceived as blackbox methods, and it is difficult to intuitively and quantitatively understand the results of their prediction and inference. Since this lack of interpretability is a major bottleneck in designing more successful predictive models and exploring wider-range useful applications, there has been an explosion of interest in interpreting the representations learned by these models, with profound implications for research into interpretable machine learning in the multimedia community. [ABSTRACT FROM AUTHOR]

Few of the challenges with development of a single on–board motor for direct–drive electric vehicles include high torque density and low torque ripple. Therefore, in this paper, a 36–slot, 34–pole consequent pole six–phase permanent magnet synchronous machine (PMSM) has been optimized to address the aforementioned challenges for direct–drive application. Existing literature on optimization processes that rely solely on finite element models are restricted to three–phase machines only and also take longer computation time. Therefore, this paper proposes a novel optimization approach based on supervised machine learning for six–phase PMSM. In this approach, a non–conventional extended dual dq–frame model that accounts for higher order space harmonics in inductances and flux linkages has been developed and used for accurate computation of average torque and torque ripple of six–phase PMSM. Using the performance characteristics obtained from the extended dual dq–frame model for a set of initial design candidates, support vector regression algorithm is employed for supervised machine learning and increasing solutions in the design space. Furthermore, pareto front is used for selecting optimal machine models with maximum torque density and reduced torque ripple. Multi–objective trade–offs and comparison of initial and optimized designs based on average torque, torque ripple, efficiency and cost are performed. [ABSTRACT FROM AUTHOR]

This paper introduces a supervised machine learning (ML) approach to predict and schedule the real-time operation mode of the next operation interval for residential PV/battery systems controlled by mode-based controllers. The performance of the mode-based economic model-predictive control approach is used as the benchmark. The residential load and PV data used in this paper are 1-min data downloaded from the Pecan Street Project website. The optimal operation mode for each control interval is first derived from the historical data used as the training set. Then, four ML algorithms (i.e., neural network, support vector machine, logistic regression, and random forest algorithms) are applied. We compared the performance of the four algorithms when using different number of features and length of the training sets extracted from different months of the year. Simulation results show that using the ML approach can effectively improve the performance of the mode-based control system and reduce the computation effort of local controllers because the training can be completed on a cloud-based ML engine. The work presented in this paper paves the way for using a shared-learning platform to design controllers of residential PV/storage systems. This may significantly reduce the cost for implementing such systems. [ABSTRACT FROM AUTHOR]

It is an annual tradition ever from the start of the IEEE Journal of Solid-State Circuits (JSSC) in 1966 to publish extended manuscripts of a selected set of papers presented at the annual International Solid-State Circuits Conference (ISSCC). In this November issue, you will find selected papers from the Imagers, Medical, MEMS, and Displays (IMMD) and the Technology Directions (TD) sessions. Most of the bio-related papers are covered in these topics. Next month, the sessions of Analog, Power Management, Data Converters, RF, and Wireless will be covered, and in January, you will find the selected papers from the Wireline, Digital Circuits, Digital Architectures and Systems, Memory, and Machine Learning subcommittees. [ABSTRACT FROM AUTHOR]

In this paper, we present an improved framework for the instance-aware semantic segmentation of road furniture in mobile laser scanning data. In our framework, we first detect road furniture from mobile laser scanning point clouds. Then we decompose the detected pieces of road furniture into poles and their attached components, and extract the instance information of the components with different features. Most importantly, we classify the components into different categories by combining a classifier and a probabilistic graphic model named DenseCRF, which is the major contribution of this paper. For the classification of the components using DenseCRF, the unary potentials and the pairwise potentials are first obtained. The unary potentials are obtained from the classifier which takes the instance information of components as the input. The pairwise potentials are calculated considering contextual relations between components. By utilising DenseCRF, the contextual consistency of components is preserved, and the performance is significantly improved compared to our previous work. We collect three datasets to test our framework, and compare the classification performances of six different classifiers with and without DenseCRF. The combination of random forest with DenseCRF outperforms the other methods and achieves high overall accuracies of 83.7%, 96.4% and 95.3% in these three datasets. Experimental results demonstrate that our framework reliably assigns both semantic information and instance information for mobile laser scanning point clouds of road furniture. [ABSTRACT FROM AUTHOR]

Due to high biological adaptability and flexibility, pneumatic artificial muscle (PAM) systems are widely employed in exoskeleton robots to accomplish rehabilitation training with repetitive motions. However, some intrinsic characteristics of PAMs and inevitable practical factors, e.g., high nonlinearity, hysteresis, uncertain dynamics, and limited working space, may badly degrade tracking performance and safety. Hence, this paper designs a new learning-based motion controller for PAMs, to simultaneously compensate for model uncertainties, eliminate tracking errors, and satisfy preset motion constraints. Particularly, when PAMs suffer from periodically non-parametric uncertainties, the elaborately designed continuous update algorithm can repetitively learn them online to enhance tracking accuracy, without employing upper/lower bounds of unknown parts for controller design and gain selections. Meanwhile, some non-periodic uncertainties are handled by a robust term, whose value is only related to the initial states of PAMs, instead of exact upper bounds of unknown dynamics. From safety concerns, we introduce error-related saturation terms to limit initial amplitudes of control inputs within saturation constraints and avoid overlarge errors inducing overlarge acceleration. Meanwhile, the constraint-related auxiliary term is utilized to keep tracking errors within allowable ranges. To the best of our knowledge, this paper presents the first learning-based error-constrained controller for uncertain PAM-actuated exoskeleton robots, to realize high-precision tracking control and improve safety without additional gain conditions. Moreover, the asymptotic convergence of tracking errors is strictly proven by Lyapunov-based stability analysis. Finally, based on a self-built exoskeleton robot, the effectiveness of the proposed controller is verified by hardware experiments. Note to Practitioners—This work is motivated by the practical requirements of exoskeleton robots in rehabilitation training and exploration fields. Currently, PAM systems, as a kind of new flexible actuator equipment, are playing increasingly important roles in the development of exoskeleton robot control. However, uncertain (or time-varying) parameters/structures and highly nonlinear dynamics, such as creep and hysteresis, may badly increase the control difficulty of PAMs. Moreover, higher and higher tracking accuracy and safety requirements also induce urgently solved problems to practical PAM-actuated exoskeleton robots, e.g., smooth start, motion constraints, and rapid error elimination. To this end, this paper proposes a new learning-based adaptive controller, which realizes accurate tracking control for PAM-actuated exoskeleton robots by utilizing an elaborately designed repetitive learning algorithm and a robust term to handle periodic and non-periodic uncertainties, respectively. More importantly, the proposed controller simultaneously enhances transient performance of PAMs, including gradually improved tracking accuracy, effective constraints for startup acceleration and tracking errors. Additionally, it is not required to consider the upper bounds of unknown dynamics and additional gain selection conditions, which is theoretically and practically important for PAM systems. Some hardware experiments further verify the effectiveness and robustness of the suggested controller. In our future work, we intend to design more effective methods for PAMs with unmeasurable states and time-delay. [ABSTRACT FROM AUTHOR]

With the abundance of data, machine learning applications engaged increased attention in the last decade. An attractive approach to robustify the statistical analysis is to preprocess the data through clustering. This paper develops a low-complexity Riemannian optimization framework for solving optimization problems on the set of positive semidefinite stochastic matrices. The low-complexity feature of the proposed algorithms stems from the factorization of the optimization variable $\mathbf {X}=\mathbf {Y}\mathbf {Y}^{\mathrm{T}}$ X = Y Y T and deriving conditions on the number of columns of $\mathbf {Y}$ Y under which the factorization yields a satisfactory solution. The paper further investigates the embedded and quotient geometries of the resulting Riemannian manifolds. In particular, the paper explicitly derives the tangent space, Riemannian gradients and Hessians, and a retraction operator allowing the design of efficient first and second-order optimization methods for the graph-based clustering applications of interest. The numerical results reveal that the resulting algorithms present a clear complexity advantage as compared with state-of-the-art euclidean and Riemannian approaches for graph clustering applications. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) is becoming pervasive in most engineering domains, and railway transport is no exception. However, due to the plethora of different new terms and meanings associated with them, there is a risk that railway practitioners, as several other categories, will get lost in those ambiguities and fuzzy boundaries, and hence fail to catch the real opportunities and potential of machine learning, artificial vision, and big data analytics, just to name a few of the most promising approaches connected to AI. The scope of this paper is to introduce the basic concepts and possible applications of AI to railway academics and practitioners. To that aim, this paper presents a structured taxonomy to guide researchers and practitioners to understand AI techniques, research fields, disciplines, and applications, both in general terms and in close connection with railway applications such as autonomous driving, maintenance, and traffic management. The important aspects of ethics and explainability of AI in railways are also introduced. The connection between AI concepts and railway subdomains has been supported by relevant research addressing existing and planned applications in order to provide some pointers to promising directions. [ABSTRACT FROM AUTHOR]

In 2016, Google introduced the concept of Federated Learning (FL), enabling collaborative Machine Learning (ML). FL does not share local data but ML models, offering applications in diverse domains. This paper focuses on the application of FL to Intrusion Detection Systems (IDSs). There, common criteria to compare existing solutions are missing. In particular, this survey shows: (i) how FL-based IDSs are used in different domains; (ii) what differences exist between architectures; (iii) the state of the art of FL-based IDS. With a structured literature survey, this work identifies the relevant state of the art in FL–based intrusion detection from its creation in 2016 until 2021. It provides a reference architecture and a taxonomy to serve as guidelines to compare and design FL-based IDSs. Both are validated with the existing works. Finally, it identifies research directions for the application of FL to intrusion detection systems. [ABSTRACT FROM AUTHOR]

In-home health monitoring has attracted great attention for the ageing population worldwide. With the abundant user health data accessed by Internet of Things (IoT) devices and recent development in machine learning, smart healthcare has seen many successful stories. However, existing approaches for in-home health monitoring do not pay sufficient attention to user data privacy and thus are far from being ready for large-scale practical deployment. In this paper, we propose FedHome, a novel cloud-edge based federated learning framework for in-home health monitoring, which learns a shared global model in the cloud from multiple homes at the network edges and achieves data privacy protection by keeping user data locally. To cope with the imbalanced and non-IID distribution inherent in user’s monitoring data, we design a generative convolutional autoencoder (GCAE), which aims to achieve accurate and personalized health monitoring by refining the model with a generated class-balanced dataset from user’s personal data. Besides, GCAE is lightweight to transfer between the cloud and edges, which is useful to reduce the communication cost of federated learning in FedHome. Extensive experiments based on realistic human activity recognition data traces corroborate that FedHome significantly outperforms existing widely-adopted methods. [ABSTRACT FROM AUTHOR]

To solve the information explosion problem and enhance user experience in various online applications, recommender systems have been developed to model users’ preferences. Although numerous efforts have been made toward more personalized recommendations, recommender systems still suffer from several challenges, such as data sparsity and cold-start problems. In recent years, generating recommendations with the knowledge graph as side information has attracted considerable interest. Such an approach can not only alleviate the above mentioned issues for a more accurate recommendation, but also provide explanations for recommended items. In this paper, we conduct a systematical survey of knowledge graph-based recommender systems. We collect recently published papers in this field, and group them into three categories, i.e., embedding-based methods, connection-based methods, and propagation-based methods. Also, we further subdivide each category according to the characteristics of these approaches. Moreover, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation. Finally, we propose several potential research directions in this field. [ABSTRACT FROM AUTHOR]

Training an accurate classifier for EEG-based brain-computer interface (BCI) requires EEG data from a large number of users, whereas protecting their data privacy is a critical consideration. Federated learning (FL) is a promising solution to this challenge. This paper proposes Federated classification with local Batch-specific batch normalization and Sharpness-aware minimization (FedBS) for privacy protection in EEG-based motor imagery (MI) classification. FedBS utilizes local batch-specific batch normalization to reduce data discrepancies among different clients, and sharpness-aware minimization optimizer in local training to improve model generalization. Experiments on three public MI datasets using three popular deep learning models demonstrated that FedBS outperformed six state-of-the-art FL approaches. Remarkably, it also outperformed centralized training, which does not consider privacy protection at all. In summary, FedBS protects user EEG data privacy, enabling multiple BCI users to participate in large-scale machine learning model training, which in turn improves the BCI decoding accuracy.

Advancements in machine learning offer promising avenues for the identification of ADHD symptoms in adults, an endeavour traditionally encumbered by the intricacies of human behavioural patterns. In this paper, we introduce three innovative dual-stream models. The proposed approach utilises a novel multi-modal dataset recorded for ADHD symptoms detection, leveraging RGB video alongside facial, body posture and hand landmark data. The fusion of these different sub-modalities within video enhances the discriminative capability of the ADHD symptoms detection system. A primary objective was to maintain minimal model depth while achieving competitive performance. Through randomised search cross-validation and a rigorous leave-one-out validation scheme, the proposed model achieves high generalisability and robust symptom identification, suggesting strong potential for application in clinical environments. Evaluation boasts the state-of-the-art performance of the proposed model, demonstrating an accuracy of 98.67%, a precision of 98.01%, and a recall of 98.88%. These metrics attest to the model's ability to consistently identify ADHD symptoms while maintaining a minimal parameter footprint. This delicate balance provides a significant step forward in behavioural health analytics.

Robot-assisted motor training is applied for neurorehabilitation in stroke patients, using motor imagery (MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing movement challenges. However, the effectiveness of training with MI may vary depending on the location of the stroke lesion, which should be considered. This paper introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature extraction, and the features according to stroke lesions are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used as classifiers. Nine patients with chronic ischemic stroke participated, engaging in MI and motor execution (ME) paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways, taking into account the characteristics of stroke patients. In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270) in ME. The second task focused on motor assessment for lesion location, resulting in a performance of 0.7457 (±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing the specific-subject session, except for ME on the motor assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore, classification performance was similar to or statistically higher in cross-subject sessions compared to baseline models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings and facilitating the detection of lesions.

Various measures have been proposed to quantify upper-limb use through wrist-worn inertial measurement units. The two most popular traditional measures of upper-limb use - thresholded activity counts (TAC) and the gross movement (GM) score suffer from high sensitivity and low specificity, and vice versa. We previously proposed a hybrid version of these two measures - the GMAC - that showed better overall detection performance than TAC and GM. In this paper, we answer two critical questions to improve the GMAC measure's usefulness: (a) can it be implemented using only the accelerometer data? (b) what are its optimal parameter values? Here, we propose a modified GMAC using only the accelerometer data and optimize its parameters to develop: (a) a generic measure that is both limb- and subject-independent, and (b) limb-specific measures that were only subject-independent. The optimized GMAC showed better detection performance than the previous GMAC and surprisingly had comparable performance to the best-performing machine learning-based measure (random forest inter-subject model). In hemiparetic data, its performance was similar to the previous GMAC and the random forest inter-subject model; the limb-specific GMAC measure, however, had a better performance than the generic measure. The optimized limb-specific GMAC is a simple, interpretable alternative to a machine learning-based inter-subject model. The optimized GMAC can be a valuable measure for offline or real-time detection and feedback of upper limb use. The preliminary results of this study, based on a small dataset, need to be validated on a larger dataset to evaluate its generalizability.

The steady-state visual evoked potential (SSVEP) has become one of the most prominent BCI paradigms with high information transfer rate, and has been widely applied in rehabilitation and assistive applications. This paper proposes a least-square (LS) unified framework to summarize the correlation analysis (CA)-based SSVEP spatial filtering methods from a machine learning perspective. Within this framework, the commonalities and differences between various spatial filtering methods appear apparent, the interpretation of computational factors becomes intuitive, and spatial filters can be determined by solving a generalized optimization problem with non-linear and regularization items. Moreover, the proposed LS framework provides the foundation of utilizing the knowledge behind these spatial filtering methods in further classification/regression model designs. Through a comparative analysis of existing representative spatial filtering methods, recommendations are made for the superior and robust design strategies. These recommended strategies are further integrated to fill the research gaps and demonstrate the ability of the proposed LS framework to promote algorithmic improvements, resulting in five new spatial filtering methods. This study could offer significant insights in understanding the relationships between various design strategies in the spatial filtering methods from the machine learning perspective, and would also contribute to the development of the SSVEP recognition methods with high performance.

This study presents a novel method to assess the learning effectiveness using Electroencephalography (EEG)-based deep learning model. It is difficult to assess the learning effectiveness of professional courses in cultivating students' ability objectively by questionnaire or other assessment methods. Research in the field of brain has shown that innovation ability can be reflected from cognitive ability which can be embodied by EEG signal features. Three navigation tasks of increasing cognitive difficulty were designed and a total of 41 subjects participated in the experiment. For the classification and tracking of the subjects' EEG signals, a convolutional neural network (CNN)-based Multi-Time Scale Spatiotemporal Compound Model (MTSC) is proposed in this paper to extract and classify the features of the subjects' EEG signals. Furthermore, Spiking neural networks (SNN) -based NeuCube is used to assess the learning effectiveness and demonstrate cognitive processes, acknowledging that NeuCube is an excellent method to display the spatiotemporal differences between spikes emitted by neurons. The results of the classification experiment show that the cognitive training traces of different students in solving three navigational problems can be effectively distinguished. More importantly, new information about navigation is revealed through the analysis of feature vector visualization and model dynamics. This work provides a foundation for future research on cognitive navigation and the training of students' navigational skills.

Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers. [ABSTRACT FROM AUTHOR]

Systems thinking characterizes the paradigm needed to effectively design, maintain, and utilize systems. Prior work has shown that there is a language of systems thinking and that its presence can be quantified within text using supervised learning methods. Building on this foundation, we present a human-in-the-loop methodology that utilizes topic models to facilitate the identification of systems thinking within a corpus of documents. Though explorative, it requires no manual grading of documents, which makes it significantly faster than previous methods. The methodology uses each document's topic proportion within a systems thinking topic as a proxy measure for the potential of strong systems thinking. The novel aspect of the methodology is in the seeding of the corpus; the user encourages the emergence of the systems thinking topic by adding several documents that demonstrate strong systems thinking to the corpus. Additionally, seeding could be used with concepts other than systems thinking. A Tukey test on a graded corpus reveals that the top echelons of strong systems thinking papers have significantly higher mean topic proportions in the systems thinking topic than lower graded papers. Additionally, a case study on a corpus of Army documents related to the development, character, and management of soldiers demonstrates the methodology's effectiveness in overviewing a system and in providing research direction. The definition of strong systems thinking and the interpretation of topics are subjective, but the methodology overcomes this hurdle by leveraging human intuition and keeping a human in the loop. [ABSTRACT FROM AUTHOR]

In this paper, a radically new anticipatory perspective is taken into account when designing the user-to-access point (AP) associations for indoor visible light communications (VLC) networks, in the presence of users’ mobility and wireless-traffic dynamics. In its simplest guise, by considering the users’ future locations and their predicted traffic dynamics, the novel anticipatory association prepares the APs for users in advance, resulting in an enhanced location- and delay-awareness. This is technically realized by our contrived design of an efficient approximate dynamic programming algorithm. More importantly, this paper is in contrast to most of the current research in the area of indoor VLC networks, where a static network environment was mainly considered. Hence, this paper is able to draw insights on the performance trade-off between delay and throughput in dynamic indoor VLC networks. It is shown that the novel anticipatory design is capable of significantly outperforming the conventional benchmarking designs, striking an attractive performance trade-off between delay and throughput. Quantitatively, the average system queue backlog is reduced from 15 to 8 [ms], when comparing the design advocated to the conventional benchmark at the per-user throughput of 100 [Mbps], in a 15\times 15\times 5 [ \text{m}^{3} ] indoor environment associated with 8\times 8$ APs and 20 users walking at 1 [m/s]. [ABSTRACT FROM PUBLISHER]

With the rapid development of Internet-of-Things and big data, health assessment of equipment is receiving more attention in recent years. It is critical to bridge the gap between real-time production data and health status evaluation, which helps maintenance team understand the health status of equipment exactly, and then make rational maintenance plans. For this purpose, this paper proposes a framework to realize real-time equipment health assessment with health status quantitatively characterized by health degree (HD). The proposed framework begins with removing redundant features using a principal component analysis (PCA) method. Then, to represent the optimal operation status, a support vector data description (SVDD) algorithm is employed for extracting normal observations in the offline part. Thereafter, HD is introduced based on the Euclidean distance between current observation and the normal sample set. In order to achieve online updating of the normal sample set, and promote accuracy and computational efficiency of the offline part, an improved incremental SVDD algorithm based on adaptive threshold N (NISVDD) is proposed. A case study is used to demonstrate the effectiveness of the proposed framework and model using a benchmark dataset of rolling bearing. Results suggest that the proposed framework is effective, and PCA shows good potential to extract features and keep most of the original information. The proposed NISVDD model is able to trace the dynamics of equipment health status for whole run-to-failure process, and outperforms other models in both accuracy and computational efficiency. [ABSTRACT FROM AUTHOR]

The papers in this special section focus on increasing interests in the development and implementation of advanced artificial intelligence (AI) and machine learning (ML) methods for tackling the reliability and system health prognostics challenges in various industrial applications. [ABSTRACT FROM AUTHOR]

A safe and versatile interaction between humans and objects is based on tactile and visual information. In literature, visual sensing is widely explored compared to tactile sensing, despite showing significant limitations in environments with an obstructed view. Tactile perception does not depend on those factors. In this paper, a Machine Learning-based tactile object classification approach is presented. The hardware setup is composed of a 3-finger-gripper of a robotic manipulator mounted on the Doro robot of the Robot-Era project. This paper’s main contribution is the augmentation of the custom 20 class 2000 sample tactile time-series dataset using random jitter noise, scaling, magnitude, time warping, and cropping. The effect on the object recognition performance of the dataset expansion is investigated for the neural network architectures MLP, LSTM, CNN, CNNLSTM, ConvLSTM, and deep CNN (D-CNN). The data augmentation methods brought a statistically significant object classification accuracy increase compared to models trained on the original dataset. The best tactile object classification success rate of 72.58% is achieved for the D-CNN trained on an augmented dataset derived from scaling and time warping augmentation. [ABSTRACT FROM AUTHOR]

Coded caching is a promising technique to smooth out network traffic by storing part of the library content at the users’ local caches. The seminal work on coded caching for single file retrieval by Maddah-Ali and Niesen (MAN) showed the existence of a global caching gain that scales with the total memory in the system, in addition to the known local caching gain in uncoded systems. This paper formulates a novel cache-aided matrix multiplication retrieval problem, relevant for data analytics and machine learning applications. In the considered problem, each cache-aided user requests the product of two matrices from the library. A structure-agnostic solution is to treat each possible matrix product as an independent file and use the MAN coded caching scheme for single file retrieval. This paper proposes two structure-aware schemes, which partition each matrix in the library by either rows or columns and let a subset of users cache some sub-matrices, that improve on the structure-agnostic scheme. For the case where the library matrices are “fat” matrices, the structure-aware row-partition scheme is shown to be order optimal under some constraint. [ABSTRACT FROM AUTHOR]

Trends in the automotive industry confirm that the demand for testing of embedded systems, especially advanced driver assistance systems (ADAS), will grow dramatically in the near future. This paper proposes a new solution that automates the detection of software defects in embedded systems. The solution consists of a data-driven sampling algorithm to intelligently sample the testing space by sequentially generating test cases. Moreover, it segregates different defects from each other and identifies the signals that trigger each. The results are compared against other automated methods for defect identification and analysis, and it is found that this novel solution is able to identify defects more rapidly. In addition, it correctly separates defects and reliably reproduces each distinct defect. [ABSTRACT FROM AUTHOR]

Traffic control optimization is a challenging task for various traffic centers around the world and the majority of existing approaches focus only on developing adaptive methods for normal (recurrent) traffic conditions. Optimizing the control plans when severe incidents occur still remains an open problem, especially when a high number of lanes or entire intersections are affected. This paper presents a novel methodology for optimizing the traffic signal timings in signalized urban intersections, under non-recurrent traffic incidents. With the purpose of producing fast and reliable decisions, we combine the fast running Machine Learning (ML) algorithms and the reliable Genetic Algorithms (GA) into a single optimization framework. Firstly, we deploy a typical GA algorithm by considering the phase duration as the decision variable and the objective function as the total travel time in the network. We fine tune the GA for crossover, mutation, fitness calculation and obtain the optimal parameters. Secondly, we train several regression models to predict the total travel time in the studied traffic network, and select the best performing model which we further hyper-tune. Lastly, we propose a new algorithm BGA-ML combining the GA algorithm and the extreme-gradient decision-tree (XGBT), which is the best performing regression model, together in a single optimization framework. Comparison and results are generated by two experiments (one synthetic and one from real urban traffic network) and show that the new BGA-ML is much faster than the original GA algorithm and can reduce the total travel time by almost half when used under incident conditions. [ABSTRACT FROM AUTHOR]

Objective: Long-term monitoring of epilepsy patients outside of hospital settings is impractical due to the complexity and costs associated with electroencephalogram (EEG) systems. Alternative sensing modalities that can acquire, and automatically interpret signals through easy-to-use wearable devices, are needed to help with at-home management of the disease. In this paper, a novel machine learning algorithm is presented for detecting epileptic seizures using acoustic physiological signals acquired from the neck using a wearable device. Methods: Acoustic signals from an existing database, were processed, to extract their Mel-frequency Cepstral Coefficients (MFCCs) which were used to train RUSBoost classifiers to identify ictal and non-ictal acoustic segments. A postprocessing stage was then applied to the segment classification results to identify seizures episodes. Results: Tested on 667 hours of acoustic data acquired from 15 patients with at least one seizure, the algorithm achieved a detection sensitivity of 88.1% (95% CI: 79%–97%) from a total of 36 seizures, out of which 24 had no motor manifestations, with a FPR of 0.83/h, and a median detection latency of −42 s. Conclusion: The results demonstrated for the first time the ability to identify seizures using acoustic internal body signals acquired on the neck. Significance: The results of this paper validate the feasibility of using internal physiological sounds for seizure detection, which could potentially be of use for the development of novel, wearable, very simple to use, long term monitoring, or seizure detection systems; circumventing the practical limitations of EEG monitoring outside hospital settings, or systems based on sensing modalities that work on convulsive seizures only. [ABSTRACT FROM AUTHOR]

This paper proposes a Principal Component Analysis (PCA)-based method to construct composite indices to rapidly assess power system transient stability. By assigning appropriate weights to a few selected sub-indicators, a composite index can be constructed to guarantee a better coverage of worst-case stability scenarios of the power system. This paper provides an automatic method to construct a composite index with four sub-indicators calculated by the integral of acceleration, speed deviation and rotor angle of generators over a certain integration period using PCA. The effectiveness of the sub-indicators is validated first, followed by a comprehensive example of process of composite index construction, and the assessment of the influence of the effect of integration period on the performance of the composite index. High accuracy of classification has been demonstrated using composite index with appropriate settings of the integration periods of the sub-indicators. [ABSTRACT FROM AUTHOR]

In this paper, we study an automatic hypothesis generation (HG) problem, which refers to the discovery of meaningful implicit connections between scientific terms, including but not limited to diseases, chemicals, drugs, and genes extracted from databases of biomedical publications. Most prior studies of this problem focused on the use of static information of terms and largely ignored the temporal dynamics of scientific term relations. Even when the dynamics were considered in a few recent studies, they learned the representations for the scientific terms, rather than focusing on the term-pair relations. Since the HG problem is to predict term-pair connections, it is not enough to know with whom the terms are connected, it is more important to know how the connections have been formed (in a dynamic process). We formulate this HG problem as a future connectivity prediction in a dynamic attributed graph. The key is to capture the temporal evolution of node-pair (term-pair) relations. We propose an inductive edge (node-pair) embedding method named T-PAIR, utilizing both the graphical structure and node attribute to encode the temporal node-pair relationship. We demonstrate the efficiency of the proposed model on three real-world datasets, which are three graphs constructed from Pubmed papers published until 2019 in Neurology, Immunotherapy, and Virology, respectively. Evaluations were conducted on predicting future term-pair relations between millions of seen terms (in the transductive setting), as well as on the relations involving unseen terms (in the inductive setting). Experiment results and case study analyses show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing plays a crucial role in the world’s economic growth and technology development and is the backbone of the high value-added electronic device manufacturing industry. In this paper, a new anomaly detection framework by means of data visualization is proposed for semiconductor manufacturing. Firstly, t-Distributed Stochastic Neighbor Embedding (t-SNE) in unsupervised learning is used to transform the high-dimensional raw trace data, corresponding to normal wafers, into a two-dimensional map, with the purpose of visually observing the distribution of normal wafers. The t-SNE algorithm cannot be used at run time for a new test sample since it requires the whole dataset for the embedding transformation, and is computationally very expensive. The Multilayer Perceptron (MLP) neural network is then applied as a regressor for the real-time t-SNE embedding of a new test data. The envelope of t-SNE score estimates for a set of normal wafers is circumscribed and used as the 2D control boundary based on the Delaunay Triangulation (D.T.). A new test sample with its MLP estimated embedding points outside the D.T boundary is identified as defective. Lastly, a real-world dataset in semiconductor manufacturing is used to illustrate the proposed data visualization tool for anomaly detection. The experimental results show that a multilayer perceptron in combination with t-SNE and Delaunay Triangulation performs very well for data visualization and automated detection of anomalies. [ABSTRACT FROM AUTHOR]