Papers by Mahardhika Adhi Pratama

Proceedings of the 31st ACM International Conference on Information & Knowledge Management
Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs ... more Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs and similar topological data structures. While many works have been established in domains related to node and graph classification/regression tasks, they mostly deal with a single task. Continual learning on graphs is largely unexplored and existing graph continual learning approaches are limited to the task-incremental learning scenarios. This paper proposes a graph continual learning strategy that combines the architecturebased and memory-based approaches. The structural learning strategy is driven by reinforcement learning, where a controller network is trained in such a way to determine an optimal number of nodes to be added/pruned from the base network when new tasks are observed, thus assuring sufficient network capacities. The parameter learning strategy is underpinned by the concept of Dark Experience replay method to cope with the catastrophic forgetting problem. Our approach is numerically validated with several graph continual learning benchmark problems in both task-incremental learning and class-incremental learning settings. Compared to recently published works, our approach demonstrates improved performance in both the settings. The implementation code can be found at https://github.com/codexhammer/gcl. CCS CONCEPTS • Computing methodologies → Artificial intelligence.

Complexity
Data-driven quality monitoring is highly demanded in practice since it enables relieving manual q... more Data-driven quality monitoring is highly demanded in practice since it enables relieving manual quality inspection of the product quality. Conventional data-driven quality monitoring is constrained by its offline characteristic thus being unable to handle streaming nature of sensory data and nonstationary environments of machine operations. Recently, there have been pioneering works of online quality monitoring taking advantage of online learning concepts in the literature, but it is still far from realization of minimum operator intervention in the quality monitoring because it calls for full supervision in labelling data samples. This paper proposes Parsimonious Network++ (ParsNet++) as an online semisupervised learning approach being able to handle extreme label scarcity in the quality monitoring task. That is, it is capable of coping with varieties of semisupervised learning conditions including random access of ground truth and infinitely delayed access of ground truth. ParsNet...

Continual Semi-Supervised Learning
Unsupervised continual learning remains a relatively uncharted territory in the existing literatu... more Unsupervised continual learning remains a relatively uncharted territory in the existing literature because the vast majority of existing works call for unlimited access of ground truth incurring expensive labelling cost. Another issue lies in the problem of task boundaries and task IDs which must be known for model's updates or model's predictions hindering feasibility for real-time deployment. Knowledge Retention in Self-Adaptive Deep Continual Learner, (KIERA), is proposed in this paper. KIERA is developed from the notion of flexible deep clustering approach possessing an elastic network structure to cope with changing environments in the timely manner. The centroidbased experience replay is put forward to overcome the catastrophic forgetting problem. KIERA does not exploit any labelled samples for model updates while featuring a task-agnostic merit. The advantage of KIERA has been numerically validated in popular continual learning problems where it shows highly competitive performance compared to stateof-the art approaches. Our implementation is available in https:// github.com/ ContinualAL/ KIERA.

2017 International Joint Conference on Neural Networks (IJCNN), 2017
Randomized neural network (RNN) is a highly feasible solution in the era of big data because it o... more Randomized neural network (RNN) is a highly feasible solution in the era of big data because it offers a simple and fast working principle in processing dynamic and evolving data streams. This paper proposes a novel RNN, namely recurrent type-2 random vector functional link network (RT2McRVFLN), which provides a highly scalable solution for data streams in a strictly online and integrated framework. It is built upon the psychologically inspired concept of metacognitive learning, which covers three basic components of human learning: what-to-learn, how-to-learn, and when-to-learn. The what-to-learn selects important samples on the fly with the use of online active learning scenario, which renders our algorithm an online semi-supervised algorithm. The how-to-learn process combines an open structure of evolving concept and a randomized learning algorithm of random vector functional link network (RVFLN). The efficacy of the RT2McRVFLN has been numerically validated through two real-world case studies and comparisons with its counterparts, which arrive at a conclusive finding that our algorithm delivers a tradeoff between accuracy and simplicity. KeywordsEvolving Fuzzy Systems, Fuzzy Neural Networks, Type-2 Fuzzy Systems, Sequential Learning. I.

Pengaruh Index Card Match Bergambar Terhadap Motivasi Dan Hasil Belajar Kognitif Pada Materi Struktur Dan Fungsi Sel
Journal of Biology Education, 2016
Materi struktur dan fungsi sel merupakan materi yang sangat penting namun banyak peserta didik ya... more Materi struktur dan fungsi sel merupakan materi yang sangat penting namun banyak peserta didik yang tidak mendapatkan hasil belajar kognitif maksimal dikarenakan strategi belajar dan media pembelajaran yang kurang efektif. Index card match bergambar diprediksi sesuai untuk mengatasi masalah-masalah dalam pembelajaran materi struktur dan fungsi sel. Penelitian ini bertujuan untuk menguji pengaruh penggunaan index card match bergambar terhadap motivasi belajar dan hasil belajar kognitif peserta didik. Penelitian ini menggunakan rancangan quasi experimental dengan desain non equivalent control group. Subjek penelitan adalah kelas XI MIA 1 (kelas eksperimen) dan MIA 2 (kelas kontrol) SMA Negeri 1 Purwodadi. Data motivasi belajar diperoleh dari lembar observasi dan data kognitif diperoleh dari nilai posttest, LKPD, dan laporan praktikum. Teknik analisis data menggunakan uji independent t test. Nilai motivasi belajar kelas eksperimen berada pada kriteria tinggi, sedangkan kelas kontrol be...

Pengaruh Penggunaanindex Card Match Bergambarterhadap Hasil Belajar Kognitifpada Materi Struktur Dan Fungsi Sel
Observasi yang dilakukan pada tiga SMA Negeri di Purwodadi menunjukan bahwa materi struktur dan f... more Observasi yang dilakukan pada tiga SMA Negeri di Purwodadi menunjukan bahwa materi struktur dan fungsi sel merupakan materi yang sangat penting karena menjadi dasar pemahaman materi selanjutnya, namun banyak peserta didik yang tidak mendapatkan hasil belajar kognitif yang maksimal dikarenakan strategi belajar dan media pembelajaran yang kurang efektif . Strategi belajar yang sesuai dengan struktur dan fungsi sel adalah strategi yang merangsang motivasi belajar peserta didik, membuat peserta didik aktif dalam pembelajaran, mempermudah peserta didik untuk memahami, dan membuat peserta didik hafal kata-kata baru dalam materi. Oleh sebab itu dibutuhkan strategi index card match bergambar untuk mengatasi permasalahan hasil belajar kognitif peserta didik. Pernyataan tersebut sejalan dengan penelitian Chen et al (2009) yang menyatakan bahwa index card match dapat meningkatkan motivasi dan hasil belajar peserta didik.Penelitian ini bertujuan untuk menguji pengaruh penggunaan index card matc...

Complexity, 2020
Real-world complex systems inevitably suffer from perturbations. When some system components brea... more Real-world complex systems inevitably suffer from perturbations. When some system components break down and trigger cascading failures on a system, the system will be out of control. In order to assess the tolerance of complex systems to perturbations, an effective way is to model a system as a network composed of nodes and edges and then carry out network robustness analysis. Percolation theories have proven as one of the most effective ways for assessing the robustness of complex systems. However, existing percolation theories are mainly for multilayer or interdependent networked systems, while little attention is paid to complex systems that are modeled as multipartite networks. This paper fills this void by establishing the percolation theories for multipartite networked systems under random failures. To achieve this goal, this paper first establishes two network models to describe how cascading failures propagate on multipartite networks subject to random node failures. Afterwa...

Complexity, 2019
Complex networks in reality may suffer from target attacks which can trigger the breakdown of the... more Complex networks in reality may suffer from target attacks which can trigger the breakdown of the entire network. It is therefore pivotal to evaluate the extent to which a network could withstand perturbations. The research on network robustness has proven as a potent instrument towards that purpose. The last two decades have witnessed the enthusiasm on the studies of network robustness. However, existing studies on network robustness mainly focus on multilayer networks while little attention is paid to multipartite networks which are an indispensable part of complex networks. In this study, we investigate the robustness of multipartite networks under intentional node attacks. We develop two network models based on the largest connected component theory to depict the cascading failures on multipartite networks under target attacks. We then investigate the robustness of computer-generated multipartite networks with respect to eight node centrality metrics. We discover that the robust...

IEEE transactions on cybernetics, Jan 12, 2018
Existing methodologies for tool condition monitoring (TCM) still rely on batch approaches which c... more Existing methodologies for tool condition monitoring (TCM) still rely on batch approaches which cannot cope with a fast sampling rate of a metal cutting process. Furthermore, they require a retraining process to be completed from scratch when dealing with a new set of machining parameters. This paper presents an online TCM approach based on Parsimonious Ensemble+ (pENsemble+). The unique feature of pENsemble+ lies in its highly flexible principle where both the ensemble structure and base-classifier structure can automatically grow and shrink on the fly based on the characteristics of data streams. Moreover, the online feature selection scenario is integrated to actively sample relevant input attributes. This paper presents advancement of a newly developed ensemble learning algorithm, pENsemble, where the online active learning scenario is incorporated to reduce the operator's labeling effort. The ensemble merging scenario is proposed which allows reduction of ensemble complexit...

IEEE Transactions on Fuzzy Systems, 2018
the concept of ensemble learning offers a promising avenue in learning from data streams under co... more the concept of ensemble learning offers a promising avenue in learning from data streams under complex environments because it better addresses the bias and variance dilemma than its single-model counterpart and features a reconfigurable structure, which is well-suited to the given context. While various extensions of ensemble learning for mining nonstationary data streams can be found in the literature, most of them are crafted under static base-classifier and revisit preceding samples in the sliding window for a retraining step. This feature causes computationally prohibitive complexity and is not flexible enough to cope with rapidly changing environments. Their complexities are often demanding because they involve a large collection of offline classifiers due to the absence of structural complexities reduction mechanisms and lack of an online feature selection mechanism. A novel evolving ensemble classifier, namely Parsimonious Ensemble (pENsemble), is proposed in this paper. pENsemble differs from existing architectures in the fact that it is built upon an evolving classifier from data streams, termed Parsimonious Classifier (pClass). pENsemble is equipped by an ensemble pruning mechanism, which estimates a localized generalization error of a base-classifier. A dynamic online feature selection scenario is integrated into the pENsemble. This method allows for dynamic selection and deselection of input features on the fly. pENsemble adopts a dynamic ensemble structure to output a final classification decision where it features a novel drift detection scenario to grow the ensemble's structure. The efficacy of the pENsemble has been numerically demonstrated through rigorous numerical studies with dynamic and evolving data streams where it delivers the most encouraging performance in attaining a tradeoff between accuracy and complexity.

Journal of Intelligent Manufacturing, 2017
As manufacturing processes become increasingly automated, so should tool condition monitoring (TC... more As manufacturing processes become increasingly automated, so should tool condition monitoring (TCM) as it is impractical to have human workers monitor the state of the tools continuously. Tool condition is crucial to ensure the good quality of products-Worn tools affect not only the surface quality but also the dimensional accuracy, which means higher reject rate of the products. Therefore, there is an urgent need to identify tool failures before it occurs on the fly. While various versions of intelligent tool condition monitoring have been proposed, most of them suffer from a cognitive nature of traditional machine learning algorithms. They focus on the how-to-learn process without paying attention to other two crucial issueswhat-to-learn, and when-to-learn. The what-to-learn and the when-to-learn provide self-regulating mechanisms to select the training samples and to determine time instants to train a model. A novel tool condition monitoring approach based on a psychologically plausible concept, namely the metacognitive scaffolding theory, is proposed and built upon a recently published algorithm recurrent classifier (rClass). The learning process consists of three phases: what-to-learn, how-to-learn, whento-learn and makes use of a generalized recurrent network structure as a cognitive component. Experimental studies with real-world manufacturing data streams were conducted where rClass demonstrated the highest accuracy while retaining the lowest complexity over its counterparts.

2016 International Joint Conference on Neural Networks (IJCNN), 2016
In this paper, a novel extreme learning machine based online multi-label classifier for real-time... more In this paper, a novel extreme learning machine based online multi-label classifier for real-time data streams is proposed. Multi-label classification is one of the actively researched machine learning paradigm that has gained much attention in the recent years due to its rapidly increasing real world applications. In contrast to traditional binary and multiclass classification, multi-label classification involves association of each of the input samples with a set of target labels simultaneously. There are no real-time online neural network based multi-label classifier available in the literature. In this paper, we exploit the inherent nature of high speed exhibited by the extreme learning machines to develop a novel online realtime classifier for multi-label data streams. The developed classifier is experimented with datasets from different application domains for consistency, performance and speed. The experimental studies show that the proposed method outperforms the existing state-of-the-art techniques in terms of speed and accuracy and can classify multi-label data streams in real-time.

International Journal of Fuzzy Systems, 2016
A novel evolving semi-supervised classifier, namely Parsimonious Classifier? (pClass?), is propos... more A novel evolving semi-supervised classifier, namely Parsimonious Classifier? (pClass?), is proposed in this paper. pClass? enhances a recently developed classifier, namely pClass, for a semi-supervised learning scenario. As with its predecessor, pClass? is capable of initiating its learning process from scratch with an empty rule base and adopts an open network structure, where fuzzy rules are evolved, pruned, and recalled automatically on demands. The novelty of pClass? lies in an online active learning technique, which decreases operator's annotation efforts and expedites its training process. pClass? is also equipped with a new parameter identification strategy to cope with the class overlapping situation. The efficacy of pClass? has been experimentally validated with numerous synthetic and real-world study cases, confirmed by thorough statistical tests and comparisons against state-of-the art classifiers, where pClass? outperforms its counterparts in achieving the best trade-off between accuracy and complexity.
Genetic Based Optimization of ANFIS Controller for DC Servo Velocity Control Using Static Identification
Experimental Comparison of Anti Wind Up Fuzzy Method for Velocity DC Servo Controllers

2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2015
Most real world classification problems involve a high degree of uncertainty, unsolved by a tradi... more Most real world classification problems involve a high degree of uncertainty, unsolved by a traditional type-1 fuzzy classifier. In this paper, a novel interval type-2 classifier, namely Evolving Type-2 Classifier (eT2Class), is proposed. The eT2Class features a flexible working principle built upon a fully sequential and local working principle. This learning notion allows eT2Class to automatically grow, adapt, prune, recall its knowledge from data streams in the single-pass learning fashion, while employing loosely coupled fuzzy sub-models. In addition, eT2Class introduces a generalized interval type-2 fuzzy neural network architecture, where a multivariate Gaussian function with uncertain non-diagonal covariance matrixes constructs the rule premise, while the rule consequent is crafted by a local non-linear Chebyshev polynomial. The efficacy of eT2Class is numerically validated by numerical studies with four data streams characterizing non-stationary behaviors, where eT2Class demonstrates the most encouraging learning performance in achieving a tradeoff between accuracy and complexity.
Fuzzy Modulation for Networked Control System with Multiple Plants
Evolving Systems, 2015
newly developed re-scaled Mahalanobis distance measure for assuring monotonicity between feature ... more newly developed re-scaled Mahalanobis distance measure for assuring monotonicity between feature weights and distance values. Gen-Smart-EFS will be evaluated based on high-dimensional real-world data (streaming) sets and compared with other well-known (evolving) fuzzy systems approaches. The results show improved accuracy with lower rule base complexity as well as smaller rule length when using Gen-Smart-EFS.

A recurrent meta-cognitive-based Scaffolding classifier from data streams
2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS), 2014
ABSTRACT a novel incremental meta-cognitive-based Scaffolding algorithm is proposed in this paper... more ABSTRACT a novel incremental meta-cognitive-based Scaffolding algorithm is proposed in this paper crafted in a recurrent network based on fuzzy inference system termed recurrent classifier (rClass). rClass features a synergy between schema and scaffolding theories in the how-to-learn part, which constitute prominent learning theories of the cognitive psychology. In what-to-learn component, rClass amalgamates the new online active learning concept by virtue of the Bayesian conflict measure and dynamic sampling strategy, whereas the standard sample reserved strategy is incorporated in the when-to-learn constituent. The inference scheme of rClass is managed by the local recurrent network, sustained by the generalized fuzzy rule. Our thorough empirical study has ascertained the efficacy of rClass, which is capable of producing reliable classification accuracies, while retaining the amenable computational and memory burdens.

A novel meta-cognitive-based scaffolding classifier to sequential non-stationary classification problems
2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2014
ABSTRACT a novel meta-cognitive-based scaffolding classifier, namely Generic-Classifier (gClass),... more ABSTRACT a novel meta-cognitive-based scaffolding classifier, namely Generic-Classifier (gClass), is proposed in this paper to handle non-stationary classification problems in the single-pass learning mode. Meta-cognitive learning is a breakthrough in the machine learning where the learning process is not only directed to craft learning strategies to exacerbate the classification rates , i.e., how-to-learn aspect, but also is focused to accommodate the emotional reasoning and commonsense of human being in terms of what-to-learn and when-to-learn facets. The crux of gClass is to synergize the scaffolding learning concept, which constitutes a well-known tutoring theory in the psychological literatures, in the how-to-learn context of meta-cognitive learning, in order to boost the learner’s performance in dealing with complex data. A comprehensive empirical studies in time-varying datasets is carried out, where gClass numerical results are benchmarked with other state-of-the-art classifiers. gClass is, generally speaking, capable of delivering the most encouraging numerical results where a trade-off between predictive accuracy and classifier’s complexity can be achieved.
Uploads
Papers by Mahardhika Adhi Pratama