Search results for "learning."
showing 10 items of 6527 documents
Safer Reinforcement Learning for Agents in Industrial Grid-Warehousing
2020
In mission-critical, real-world environments, there is typically a low threshold for failure, which makes interaction with learning algorithms particularly challenging. Here, current state-of-the-art reinforcement learning algorithms struggle to learn optimal control policies safely. Loss of control follows, which could result in equipment breakages and even personal injuries.
Support Tool for the Combined Software/Hardware Design of On-Chip ELM Training for SLFF Neural Networks
2016
Typically, hardware implemented neural networks are trained before implementation. Extreme learning machine (ELM) is a noniterative training method for single-layer feed-forward (SLFF) neural networks well suited for hardware implementation. It provides fixed-time learning and simplifies retraining of a neural network once implemented, which is very important in applications demanding on-chip training. This study proposes the data flow of a software support tool in the design process of a hardware implementation of on-chip ELM learning for SLFF neural networks. The software tool allows the user to obtain the optimal definition of functional and hardware parameters for any application, and e…
Preamble Transmission Prediction for mMTC Bursty Traffic : A Machine Learning based Approach
2020
The evolution of Internet of things (IoT) towards massive IoT in recent years has stimulated a surge of traffic volume among which a huge amount of traffic is generated in the form of massive machine type communications. Consequently, existing network infrastructure is facing challenges when handling rapidly growing traffic load, especially under bursty traffic conditions which may more often lead to congestion. By proactively predicting the occurrence of congestion, we can implement necessary means and conceivably avoid congestion. In this paper, we propose a machine learning (ML) based model for predicting successful preamble transmissions at a base station and subsequently forecasting th…
Tabu and Scatter Search for Artificial Neural Networks
2003
In this paper we address the problem of training multilayer feed-forward neural networks. These networks have been widely used for both prediction and classification in many different areas. Although the most popular method for training these networks is back propagation, other optimization methods such as tabu search or scatter search have been applied to solve this problem. This paper presents a new training algorithm based on the tabu search methodology that incorporates elements for search intensification and diversification by utilizing strategic designs where other previous approaches resort to randomization. Our method considers context and search information, as it is provided by th…
Fall Detection Based on the Instantaneous Doppler Frequency : A Machine Learning Approach
2019
Modern societies are facing an ageing problem which comes with increased cost of healthcare. A major share of this ever-increasing cost is due to fall related injuries, which urges the development of fall detection systems. In this context, this paper paves the way for building of a radio-frequency-based fall detection system. This paper presents an activity simulator that generates the complex channel gain of indoor channels in the presence of one person performing three different activities, namely, slow fall, fast fall, and walking. We built a machine learning framework for activity recognition based on the complex channel gain. We assess the recognition accuracy of three different class…
Constructing Interpretable Classifiers to Diagnose Gastric Cancer Based on Breath Tests
2017
Quick, inexpensive and accurate diagnosis of gastric cancer is a necessity, but at this moment the available methods do not hold up. One of the most promising possibilities is breath test analysis, which is quick, relatively inexpensive and comfortable to the person tested. However, this method has not yet been well explored. Therefore in this article the authors propose using transparent classification models to explain diagnostic patterns and knowledge, which is acquired in the process. The models are induced using decision tree classification algorithms and RIPPER algorithm for decision rule induction. The accuracy of these models is compared to neural network accuracy.
Adaptive Continuous Feature Binarization for Tsetlin Machines Applied to Forecasting Dengue Incidences in the Philippines
2020
The Tsetlin Machine (TM) is a recent interpretable machine learning algorithm that requires relatively modest computational power, yet attains competitive accuracy in several benchmarks. TMs are inherently binary; however, many machine learning problems are continuous. While binarization of continuous data through brute-force thresholding has yielded promising accuracy, such an approach is computationally expensive and hinders extrapolation. In this paper, we address these limitations by standardizing features to support scale shifts in the transition from training data to real-world operation, typical for e.g. forecasting. For scalability, we employ sampling to reduce the number of binariz…
Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI Using Deep Convolutional Networks
2021
In this paper, we propose a new deep learning framework for an automatic myocardial infarction evaluation from clinical information and delayed enhancement-MRI (DE-MRI). The proposed framework addresses two tasks. The first task is automatic detection of myocardial contours, the infarcted area, the no-reflow area, and the left ventricular cavity from a short-axis DE-MRI series. It employs two segmentation neural networks. The first network is used to segment the anatomical structures such as the myocardium and left ventricular cavity. The second network is used to segment the pathological areas such as myocardial infarction, myocardial no-reflow, and normal myocardial region. The segmented …
A Review of Kernel Methods in Remote Sensing Data Analysis
2011
Kernel methods have proven effective in the analysis of images of the Earth acquired by airborne and satellite sensors. Kernel methods provide a consistent and well-founded theoretical framework for developing nonlinear techniques and have useful properties when dealing with low number of (potentially high dimensional) training samples, the presence of heterogenous multimodalities, and different noise sources in the data. These properties are particularly appropriate for remote sensing data analysis. In fact, kernel methods have improved results of parametric linear methods and neural networks in applications such as natural resource control, detection and monitoring of anthropic infrastruc…
Integrating genomic binding site predictions using real-valued meta classifiers
2008
Currently the best algorithms for predicting transcription factor binding sites in DNA sequences are severely limited in accuracy. There is good reason to believe that predictions from different classes of algorithms could be used in conjunction to improve the quality of predictions. In this paper, we apply single layer networks, rules sets, support vector machines and the Adaboost algorithm to predictions from 12 key real valued algorithms. Furthermore, we use a ‘window’ of consecutive results as the input vector in order to contextualise the neighbouring results. We improve the classification result with the aid of under- and over-sampling techniques. We find that support vector machines …