Centered Learning Research Articles

Utility Analysis about Log Data Anomaly Detection Based on Federated Learning

Logs that record system information are managed in anomaly detection, and more efficient anomaly detection methods have been proposed due to their increase in complexity and scale. Accordingly, deep learning models that automatically detect system anomalies through log data learning have been proposed. However, in existing log anomaly detection models, user logs are collected from the central server system, exposing the data collection process to the risk of leaking sensitive information. A distributed learning method, federated learning, is a trend proposed for artificial intelligence learning regarding sensitive information because it guarantees the anonymity of the collected user data and collects only weights learned from each local server in the central server. In this paper, we executed an experiment regarding system log anomaly detection using federated learning. The results demonstrate the feasibility of applying federated learning in deep-learning-based system-log anomaly detection compared to the existing centralized learning method. Moreover, we present an efficient deep-learning model based on federated learning for system log anomaly detection.

Instruction of Spanish Direct and Indirect Object Pronouns through Task-Supported Videoconferencing Instruction

Task-supported videoconferencing instruction emphasizes learner centeredness and experientiallearning in Second Language Acquisition (SLA). Still, relatively few studies have addressed the useof specific linguistic structures in online courses from a task-based perspective. The present studyexamines the effects of an online task-supported module on the acquisition of direct and indirect objectpronouns in Spanish. These pronouns are used very frequently by proficient Spanish speakers,but are less used by Spanish learners because of their morphological and syntactic complexity. Theresults of this study demonstrate the benefits of using an online task-supported module speciallydesigned to promote the use of direct and indirect object pronouns in Spanish through videoconference.Participants used the target structures on many occasions without being prompted to doso. The results suggest that the task-supported module is a promising approach to the teaching ofgrammar.

GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models

Generative adversarial networks (GANs) learn the distribution of observed samples through a zero-sum game between two machine players, a generator and a discriminator. While GANs achieve great success in learning the complex distribution of image, sound, and text data, they perform suboptimally in learning multimodal distribution-learning benchmarks such as Gaussian mixture models (GMMs). In this paper, we propose Generative Adversarial Training for Gaussian Mixture Models (GAT-GMM), a minimax GAN framework for learning GMMs. Motivated by optimal transport theory, we design the zero-sum game in GAT-GMM using a random linear generator and a softmax-based quadratic discriminator architecture, which leads to a nonconvex concave minimax optimization problem. We show that a gradient descent ascent (GDA) method converges to an approximate stationary minimax point of the GAT-GMM optimization problem. In the benchmark case of a mixture of two symmetric, well-separated Gaussians, we further show that this stationary point recovers the true parameters of the underlying GMM. We discuss the application of the proposed GAT-GMM framework for learning GMMs in the distributed federated learning setting, where the widely used expectation-maximization (EM) algorithm can incur great computational and communication costs. On the other hand, we show that GAT-GMM provides a scalable learning approach and a distributed GDA algorithm can still solve the GAT-GMM minimax problem without incurring extra computation costs. We numerically support our theoretical results by performing experiments which show that our minimax framework is successful in centralized learning tasks and can outperform standard EM-type algorithms in the federated setting.

Misbehavior detection system with semi-supervised federated learning

V2X communications can enhance transportation safety by exchanging safety information between vehicles, road infrastructures, networks, and pedestrians. However, the safety messages are vulnerable to disruption from faulty components or an attack that can cause misinformation. Recently, a machine learning-based misbehavior detection system (MDS) has been widely investigated to detect the misbehaving vehicles to secure the V2X communications. Nonetheless, machine learning models need sufficient labeled data for learning purposes. However, the volume of unlabeled data is usually larger than that of labeled data in practice. Moreover, transferring the large dataset to a centralized learning model will consume much bandwidth. Thus, we propose a semi-supervised federated learning MDS to overcome the limitations of unlabeled data and bring the training close to the data sources to reduce the bandwidth to the core network. Overall, our model with only limited labeled data training (5%–30%) can achieve the F1-score up to 0.96 and the recall up to 0.95. The F1-score is up to 0.26 higher and the recall is up to 0.29 higher than the performance of centralized supervised learning. The federated learning model can reduce the core network bandwidth utilization by up to 95%.

A federated learning-enabled predictive analysis to forecast stock market trends

This article proposes a federated learning framework to build Random Forest, Support Vector Machine, and Linear Regression models for stock market prediction. The performance of the federated learning is compared against centralised and decentralised learning frameworks to figure out the best fitting approach for stock market prediction. According to the results, federated learning outperforms both centralised and decentralised frameworks in terms of Mean Square Error if Random Forest (MSE = 0.021) and Support Vector Machine techniques (MSE = 37.596) are used, while centralised learning (MSE = 0.011) outperforms federated and decentralised frameworks if a linear regression model is used. Moreover, federated learning gives a better model training delay as compared to the benchmarks if Linear Regression (time = 9.7 s) and Random Forest models (time = 515 s) are used, whereas decentralised learning gives a minimised model training delay (time = 3847 s) for Support Vector Machine.

Latency-aware blockage prediction in vision-aided federated wireless networks

Introduction: The future wireless landscape is evolving rapidly to meet ever-increasing data requirements, which can be enabled using higher-frequency spectrums like millimetre waves (mmWaves) and terahertz (THz). However, mmWave and THztechnologies rely on line-of-sight (LOS) communication, making them sensitive to sudden environmental changes and higher mobility of users, especially in urban areas.Methods: Therefore, beam blockage prediction is a critical challenge for sixth-generation (6G) wireless networks. One possible solution is to anticipate the potential change in the wireless network surroundings using multi-sensor data (wireless, vision, lidar, and GPS) with advanced deep learning (DL) and computer vision (CV) techniques. Despite numerous advantages, the fusion of deep learning,computer vision, and multi-modal data in centralised training introduces many challenges, including higher communication costs for raw data transfer, inefficient bandwidth usage and unacceptable latency. This work proposes latency-aware vision-aided federated wireless networks (VFWN) for beam blockage prediction using bimodal vision and wireless sensing data. The proposed framework usesdistributed learning on the edge nodes (EN) for data processing and model training.Results and Discussion: This involves federated learning for global model aggregation that minimizes latency and data communication cost as compared to centralised learning while achieving comparable predictive accuracy. For instance, the VFWN achieves a predictive accuracy of 98.5%, which is comparable to centralised learning with overall predictive accuracy 99%, considering that no data sharing is done. Furthermore, the proposed framework significantly reduces the communication cost by 81.31% and latency by 6.77% using real-time on device processing and inference.

Multiworking Conditions Anomaly Detection of Mechanical System Based on Conditional Variational Auto-Encoder

Existing anomaly detection models of mechanical systems often face challenges for the equipment under multiple working conditions: the learning model under a single working condition is challenging to adapt to new working conditions, and centralized learning of multicondition samples leads to too low detection accuracy. A multiworking condition variational auto-encoder (MW-CVAE) is proposed to solve the problem. Based on the variational auto-encoder model, the working conditions of the equipment are regarded as the input. The anomaly evaluation threshold of each independent working condition is established by the centralized learning of normal multiworking condition samples. At the same time, it is found that the representation of each working condition sample in the space of the hidden layer forms a distribution close to the prior probability, providing a theoretical basis for the separation and evaluation of working conditions. By comparing and verifying the CWRU, JNU, and PU datasets, the new method significantly improves anomaly detection (the F1-score value is increased by 18-19%) and can be widely used in anomaly detection mechanical systems with various discrete working conditions.

Striking a Balance Between Researchers’ and Learners’ Voices in L2/FL Empirical Studies: A Guide to the Group Repertory Grid Approach

ABSTRACT Against the backdrop of greater emphasis on learner centredness and growing attention to learners’ voices in recent decades, concerns have been raised over researchers’ dominance in shaping research scope and findings. Whether it be quantitative, qualitative, or mixed-methods research, learners’ voices are mostly absent at the methodological design stage. In this article, we discuss the imbalance between researchers’ and learners’ voices in L2/FL empirical studies and why this deserves our attention. We then introduce personal construct theory and delineate the repertory grid approach, with which many language researchers are unlikely to be familiar. With a step-by-step illustration, we endeavour to exemplify how an adapted version of this approach can be applied to mid/large-scale studies. The article ends with a conclusion of how this approach potentially complements and supplements the use of common quantitative (e.g., questionnaires) and qualitative (e.g., interviews) instruments, and calls for a wider adoption of this approach in L2/FL studies.

Full Data-Processing Power Load Forecasting Based on Vertical Federated Learning

Power load forecasting (PLF) has a positive impact on the stability of power systems and can reduce the cost of power generation enterprises. To improve the forecasting accuracy, more information besides load data is necessary. In recent years, a novel privacy-preserving paradigm vertical federated learning (FL) has been applied to PLF to improve forecasting accuracy while keeping different organizations’ data locally. However, two problems are still not well solved in vertical FL. The first problem is a lack of a full data-processing procedure, and the second is a lack of enhanced privacy protection for data processing. To address it, according to the procedure in a practical scenario, we propose a vertical FL XGBoost-based PLF, where multiparty secure computation is used to enhance the privacy protection of FL. Concretely, we design a full data-processing PLF, including data cleaning, private set intersection, feature selection, federated XGBoost training, and inference. Furthermore, we further use RSA encryption in the private set intersection and Paillier homomorphic encryption in the training and inference phases. To validate the proposed method, we conducted experiments to compare centralized learning and vertical FL on several real-world datasets. The proposed method can also be directly applied to other practical vertical FL tasks.

2DF-IDS: Decentralized and differentially private federated learning-based intrusion detection system for industrial IoT

Advanced technologies, such as the Internet of Things (IoT) and Artificial Intelligence (AI), underpin many of the innovations in Industry 4.0. However, the interconnectivity and open nature of such systems in smart industrial facilities can also be targeted and abused by malicious actors, which reinforces the importance of cyber security. In this paper, we present a secure, decentralized, and Differentially Private (DP) Federated Learning (FL)-based IDS (2DF-IDS), for securing smart industrial facilities. The proposed 2DF-IDS comprises three building blocks, namely: a key exchange protocol (for securing the communicated weights among all peers in the system), a differentially private gradient exchange scheme (achieve improved privacy of the FL approach), and a decentralized FL approach (that mitigates the single point of failure/attack risk associated with the aggregation server in the conventional FL approach). We evaluate our proposed system through detailed experiments using a real-world IoT/IIoT dataset, and the results show that the proposed 2DF-IDS system can identify different types of cyber attacks in an Industrial IoT system with high performance. For instance, the proposed system achieves comparable performance (94.37%) with the centralized learning approach (94.37%) and outperforms the FL-based approach (93.91%) in terms of accuracy. The proposed system is also shown to improve the overall performance by 12%, 13%, and 9% in terms of F1-score, recall, and precision, respectively, under strict privacy settings when compared to other competing FL-based IDS solutions.

Fair detection of poisoning attacks in federated learning on non-i.i.d. data.

Reconciling machine learning with individual privacy is one of the main motivations behind federated learning (FL), a decentralized machine learning technique that aggregates partial models trained by clients on their own private data to obtain a global deep learning model. Even if FL provides stronger privacy guarantees to the participating clients than centralized learning collecting the clients' data in a central server, FL is vulnerable to some attacks whereby malicious clients submit bad updates in order to prevent the model from converging or, more subtly, to introduce artificial bias in the classification (poisoning). Poisoning detection techniques compute statistics on the updates to identify malicious clients. A downside of anti-poisoning techniques is that they might lead to discriminate minority groups whose data are significantly and legitimately different from those of the majority of clients. This would not only be unfair, but would yield poorer models that would fail to capture the knowledge in the training data, especially when data are not independent and identically distributed (non-i.i.d.). In this work, we strive to strike a balance between fighting poisoning and accommodating diversity to help learning fairer and less discriminatory federated learning models. In this way, we forestall the exclusion of diverse clients while still ensuring detection of poisoning attacks. Empirical work on three data sets shows that employing our approach to tell legitimate from malicious updates produces models that are more accurate than those obtained with state-of-the-art poisoning detection techniques. Additionally, we explore the impact of our proposal on the performance of models on non-i.i.d local training data.

A Transfer Learning Approach to Breast Cancer Classification in a Federated Learning Framework

Artificial intelligence (AI) technologies have seen strong development. Many applications now use AI to diagnose breast cancer. However, most new research has only been conducted in centralized learning (CL) environments, which entails the risk of privacy breaches. Moreover, the accurate identification and localization of lesions and tumor prediction using AI technologies is expected to increase patients’ likelihood of survival. To address these difficulties, we developed a federated learning (FL) facility that extracts features from participating environments rather than a CL facility. This study’s novel contributions include (i) the application of transfer learning to extract data features from the region of interest (ROI) in an image, which aims to enable careful pre-processing and data enhancement for data training purposes; (ii) the use of synthetic minority oversampling technique (SMOTE) to process data, which aims to more uniformly classify data and improve diagnostic prediction performance for diseases; (iii) the application of FeAvg-CNN + MobileNet in an FL framework to ensure customer privacy and personal security; and (iv) the presentation of experimental results from different deep learning, transfer learning and FL models with balanced and imbalanced mammography datasets, which demonstrate that our solution leads to much higher classification performance than other approaches and is viable for use in AI healthcare applications.

Gossiped and Quantized Online Multi-Kernel Learning

In instances of online kernel learning where little prior information is available and centralized learning is unfeasible, past research has shown that distributed and online multi-kernel learning provides sub-linear regret as long as every pair of nodes in the network can communicate (i.e., the communications network is a complete graph). In addition, to manage the communication load, which is often a performance bottleneck, communications between nodes can be quantized. This letter expands on these results to non-fully connected graphs, which is often the case in wireless sensor networks. To address this challenge, we propose a gossip algorithm and provide a proof that it achieves sub-linear regret. Experiments with real datasets confirm our findings.

Automatic Detection of Congestive Heart Failure Based on Multiscale Residual UNet++: From Centralized Learning to Federated Learning

Congestive heart failure (CHF) is a progressive and complex syndrome resulted from ventricular dysfunction, which is difficult to detect at early stages. Heart rate variability (HRV) has been identified as a prognostic indicator for CHF. The traditional diagnosis methods based on analyzing the electrocardiogram (ECG) are time-consuming and laborious, and the interpretation of the results is subjective. Inspired by the outstanding performance of U-shaped networks in medical image segmentation, in this article, we propose a novel end-to-end classification model based on 2000 intervals between successive R-peaks of ECG signals. The proposed model integrates the outputs of encoders, decoders, and intermediate units through a unified scale operation, which can not only preserve low-level details from the input signals but also extract the high-level pathology-related information. We further employ a variant of residual module with group convolution and squeeze-and-excitation (SE) block, enhancing the network’s expression capability. In addition, considering the challenge of collecting large and diverse samples by individual institutions, we decentralize the data across different clients and extend the proposed model with a federated version, which is able to facilitate multi-institutional collaborations while maintaining data anonymity. A total of 29 CHF patients and 177 non-CHF subjects (i.e., 54 normal sinus rhythm (NSR) subjects, 84 atrial fibrillation (AF), and 39 Apnea subjects) from PhysioBank are included in this article. The experimental results show that the proposed model outperforms the state of the art both in centralized and decentralized learning, with an accuracy of 89.83% and 87.54%, respectively. The diagnosis model trained in federated framework provides competitive performance to that in centralized learning, which demonstrates its potential of utilizing multisite data to improve CHF detection performance without sharing patient privacy.

Policy Analysis: An Analysis of National Education Policy 2020

This paper analyses the National Education Policy 2020 (pages 1-32), the official policy document issued by the Ministry of Human Resource Development (India). This paper is written in light of five peda-gogical theories: a). Human Capital; b). Traditional Academic; c). Learner Centred; d). Social Efficiency; e). Social Reconstruction. By identifying the presence of the five theories in the policy and analysing the domi-nant ideologies of education across the whole text, the paper aims to explore the influence of pedagogical philosophies and the relevant factors on educational policy formation and upgrading in India. It discovers that although all five theories exist in the policy, Learner Centred theory is the most dominant. In addition, it also discusses political and socio-economic factors that impact the formation of the Indian educational policy.

Competency Evaluation using Graduate Attributes – A comparative study

The reformation in the education system is inevitable with the growth and advancement in the society. Thus, towards the end of the 20th century, there is a pedagogical transformation from the output-based education system to the outcome-based education system. Outcome based education is a student centric learning approach in which learning is set around specified goals (outcomes). It gives importance to the knowledge and skills acquired by students than what or how something is taught. The role of the faculty is as facilitator to help students in achieving desired outcomes. In this method, the purpose of any program is clearly specified in terms of Course Outcomes, Program Outcomes, Program Specific Outcomes, and Program Educational Objectives. The attainment of these outcomes is a measure of effectiveness of the program and the assessment of the same is monitored by various accreditation agencies in different parts of the world. After a series of discussions among these agencies, a set of graduate attributes are set forth as parameters for the assessment of the quality of education. In India, the accreditation agency is known as the National Board of Accreditation and the graduate attributes are named as program outcomes. A student graduating from an accredited program is considered a competent graduate. In this study, the competency of Civil Engineering graduates of selected institutes in Kerala state is compared in terms of these graduate attributes. The opinion of academicians and industry professionals regarding the preparedness of the current undergraduate civil engineering curriculum to develop “industry-ready engineers” is also discussed in the study. Keywords—attainment; competency; civil engineering curriculum; graduate attributes

OBE Framework for Assessing Laboratory / Practical Courses in Engineering Programmes

Abstract : Irrespective of the branch of study, practical/laboratory courses are integral parts of engineering curriculum. These courses develop the knowledge, skill and attitude of the graduates. It is thus necessary to frame the laboratory experiments, to create a student centric learning environment and to have suitable assessment methodologies to enhance the cognitive, affective and psychomotor skills of the engineering students. This paper proposes a framework of the above three from the authors' perspective for a software laboratory. The proposed framework can be extended to the laboratory/practical with suitable modifications in the Course Outcomes. Also in this paper, a methodology is proposed for converting the scales into marks and also the formula for calculating the marks under various heads (record, viva voce and experiment) is given. Rubrics are defined for the Performance Indicators (PIs) as specified in the Examination Reform Policy of AICTE for the Program Outcomes (POs defined by National Board of Accreditation (NBA), India). Keywords : Laboratory/practical courses, OBE, Rubrics, Course Outcomes (COs), Program Outcomes (Pos)

The application of machine learning techniques in prediction of quality of life features for cancer patients

Quality of life (QoL) is one of the major issues for cancer patients.With the advent of medical databases containing large amounts of relevant QoL information it becomes possible to train predictive QoL models by machine learning (ML) techniques. However, the training of predictive QoL models poses several challenges mostly due to data privacy concerns and missing values in patient data. In this paper, we analyze several classification and regression ML models predicting QoL indicators for breast and prostate cancer patients. Three different approaches are employed for imputing missing values, and several settings for data privacy preserving are tested. The examined ML models are trained on datasets formed from two databases containing a large number of anonymized medical records of cancer patients from Sweden. Two learning scenarios are considered: centralized and federated learning. In the centralized learning scenario all patient data coming from different data sources is collected at a central location prior to model training. On the other hand, federated learning enables collective training of machine learning models without data sharing. The results of our experimental evaluation show that the predictive power of federated models is comparable to that of centrally trained models for short-term QoL predictions, whereas for long-term periods centralized models provide more accurate QoL predictions. Furthermore, we provide insights into the quality of data preprocessing tasks (missing value imputation and differential privacy).

Revolutionizing Disease Diagnosis: A Microservices-Based Architecture for Privacy-Preserving and Efficient IoT Data Analytics Using Federated Learning

Deep learning-based disease diagnosis applications are essential for accurate diagnosis at various disease stages. However, using personal data exposes traditional centralized learning systems to privacy concerns. On the other hand, by positioning processing resources closer to the device and enabling more effective data analyses, a distributed computing paradigm has the potential to revolutionize disease diagnosis. Scalable architectures for data analytics are also crucial in healthcare, where data analytics results must have low latency and high dependability and reliability. This study proposes a microservices-based approach for IoT data analytics systems to satisfy privacy and performance requirements by arranging entities into fine-grained, loosely connected, and reusable collections. Our approach relies on federated learning, which can increase disease diagnosis accuracy while protecting data privacy. Additionally, we employ transfer learning to obtain more efficient models. Using more than 5800 chest X-ray images for pneumonia detection from a publically available dataset, we ran experiments to assess the effectiveness of our approach. Our experiments reveal that our approach performs better in identifying pneumonia than other cutting-edge technologies, demonstrating our approach's promising potential detection performance.

Distributed Intelligence in Wireless Networks

The cloud-based solutions are becoming inefficient due to considerably large time delays, high power consumption, and security and privacy concerns caused by billions of connected wireless devices and typically zillions of bytes of data they produce at the network edge. A blend of edge computing and Artificial Intelligence (AI) techniques could optimally shift the resourceful computation servers closer to the network edge, which provides the support for advanced AI applications (e.g., video/audio surveillance and personal recommendation system) by enabling intelligent decision making on computing at the point of data generation as and when it is needed, and distributed Machine Learning (ML) with its potential to avoid the transmission of the large dataset and possible compromise of privacy that may exist in cloud-based centralized learning. Besides, the deployment of AI techniques to redesign end-to-end communication is attracting attention to improve communication performance. Therefore, the interaction of AI and wireless communications generates a new concept, named native AI wireless networks. In this paper, we conduct a comprehensive overview of recent advances in distributed intelligence in wireless networks under the umbrella of native AI wireless networks, with a focus on the design of distributed learning architectures for heterogeneous networks, on AI-enabled edge computing, on the communication-efficient technologies to support distributed learning, and on the AI-empowered end-to-end communications. We highlight the advantages of hybrid distributed learning architectures compared to state-of-the-art distributed learning techniques. We summarize the challenges of existing research contributions in distributed intelligence in wireless networks and identify potential future opportunities.