A5029534696- Optimization and Search Problems
- Machine Learning and Algorithms
- Acoustic Wave Phenomena Research
- Speech and Audio Processing
- Music and Audio Processing
- Fire Detection and Safety Systems
- Ferroelectric and Negative Capacitance Devices
- Advanced Neural Network Applications
- Evacuation and Crowd Dynamics
- Visual Attention and Saliency Detection
- Reinforcement Learning in Robotics
- Anomaly Detection Techniques and Applications
- semigroups and automata theory
- Machine Learning and ELM
- Metaheuristic Optimization Algorithms Research
- Water resources management and optimization
- Water Systems and Optimization
- Biomedical Text Mining and Ontologies
- Generative Adversarial Networks and Image Synthesis
- Noise Effects and Management
- Topic Modeling
- DNA and Biological Computing
- Hydraulic flow and structures
- Advanced Bandit Algorithms Research
- Face and Expression Recognition
University of Agder
2017-2024
NILU
2024
Sørlandet Sykehus
2023
Maulana Azad National Institute of Technology
2015
Govind Ballabh Pant University of Agriculture and Technology
1994
Deep reinforcement learning (RL) is achieving significant success in various applications like control, robotics, games, resource management, and scheduling. However, the important problem of emergency evacuation, which clearly could benefit from RL, has been largely unaddressed. Indeed, evacuation a complex task that difficult to solve with RL. An situation highly dynamic, lot changing variables constraints make it challenging solve. Also, there no standard benchmark environment available...
Abstract Background Natural language processing (NLP) based clinical decision support systems (CDSSs) have demonstrated the ability to extract vital information from patient electronic health records (EHRs) facilitate important tasks. While obtaining accurate, medical domain interpretable results is crucial, it demanding because real-world EHRs contain many inconsistencies and inaccuracies. Further, testing of such machine learning-based in practice has received limited attention are yet be...
Abstract Recent advances in intrusion detection systems based on machine learning have indeed outperformed other techniques, but struggle with detecting multiple classes of attacks high accuracy. We propose a method that works three stages. First, the ExtraTrees classifier is used to select relevant features for each type attack individually (ELM). Then, an ensemble ELMs detect separately. Finally, results all are combined using softmax layer refine and increase accuracy further. The...
In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to Deep Convolutional Neural Network (CNN) with Attention mechanism.The novelty paper lies in using consisting Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency (GFCC), Constant Q-transform (CQT) and Chromagram.And, employ deeper CNN (DCNN) compared previous models, spatially separable convolutions working on time domain...
Abstract Background Data mining of electronic health records (EHRs) has a huge potential for improving clinical decision support and to help healthcare deliver precision medicine. Unfortunately, the rule-based machine learning-based approaches used natural language processing (NLP) in today all struggle with various shortcomings related performance, efficiency, or transparency. Methods In this paper, we address these issues by presenting novel method NLP that implements unsupervised learning...
Tsetlin Machines (TMs) have garnered increasing interest for their ability to learn concepts via propositional formulas and proven efficiency across various application domains. Despite this, the convergence proof TMs, particularly AND operator (conjunction of literals), in generalized case (inputs greater than two bits) remains an open problem. This paper aims fill this gap by presenting a comprehensive analysis automaton-based Machine Learning algorithms. We introduce novel framework,...
Fault detection in ball bearing has attracted attention of various researchers. Several Statistical features have been proposed and used by researchers for fault bearing. This work analyzes the importance available statistical different methods which includes graphical analysis, feature ranking using information gain ratio. The results show that some can be individually to distinguish between healthy faulty bearings, i.e. we just need use one distinguishing bearings instead an ensemble...
Embedding words in vector space is a fundamental first step state-of-the-art natural language processing (NLP). Typical NLP solutions employ pre-defined representations to improve generalization by co-locating similar space. For instance, Word2Vec self-supervised predictive model that captures the context of using neural network. Similarly, GLoVe popular unsupervised incorporating corpus-wide word co-occurrence statistics. Such embedding has significantly boosted important tasks, including...
Logic-based machine learning has the crucial advantage of transparency. However, despite significant recent progress, further research is needed to close accuracy gap between logic-based architectures and deep neural network ones. This paper introduces a novel variant Tsetlin (TM) that randomly drops clauses, logical element TMs. In effect, TM with Drop Clause ignores random selection clauses in each epoch, selected according predefined probability. this way, phase becomes more diverse. To...
Recommendation Systems (RSs) are ubiquitous in modern society and one of the largest points interaction between humans AI. Modern RSs often implemented using deep learning models, which infamously difficult to interpret. This problem is particularly exasperated context recommendation scenarios, as it erodes user's trust RS. In contrast, newly introduced Tsetlin Machines (TM) possess some valuable properties due their inherent interpretability. TMs still fairly young a technology. As no RS...
Tsetlin Machine (TM) is a logic-based machine learning approach with the crucial advantages of being transparent and hardware-friendly. While TMs match or surpass deep accuracy for an increasing number applications, large clause pools tend to produce clauses many literals (long clauses). As such, they become less interpretable. Further, longer increase switching activity logic in hardware, consuming more power. This paper introduces novel variant TM -- Clause Size Constrained (CSC-TMs) where...
This paper introduces an interpretable contextual bandit algorithm using Tsetlin Machines, which solves complex pattern recognition tasks propositional logic. The proposed learning relies on straightforward bit manipulation, thus simplifying computation and interpretation. We then present a mechanism for performing Thompson sampling with Machine, given its non-parametric nature. Our empirical analysis shows that Machine as base learner outperforms other popular learners eight out of nine...
Tsetlin Machines learn from input data by creating patterns in propositional logical, using the literals available data. These vote for classes a classification task. Despite their simplistic premise, machine (TM)s have been performing at with other popular learning methods across various benchmarks. Not only accuracy, TMs also perform well terms of energy efficiency and speed. The general TM scheme works best when there is sufficient discriminatory information between two classes. In this...
In response to the escalating ecological challenges that threaten global sustainability, there's a need investigate alternative methods of commerce, such as rental economies. Like most online or otherwise, functioning recommender system is crucial for their success. Yet domain has, until this point, been largely neglected by research community.