| 1. |
- Abdukalikova, Anara, et al.
(författare)
-
Detection of Atrial Fibrillation from Short ECGs : Minimalistic Complexity Analysis for Feature-Based Classifiers
- 2018
-
Ingår i: Computing in Cardiology 2018. - : IEEE.
-
Konferensbidrag (refereegranskat)abstract
- In order to facilitate data-driven solutions for early detection of atrial fibrillation (AF), the 2017 CinC conference challenge was devoted to automatic AF classification based on short ECG recordings. The proposed solutions concentrated on maximizing the classifiers F 1 score, whereas the complexity of the classifiers was not considered. However, we argue that this must be addressed as complexity places restrictions on the applicability of inexpensive devices for AF monitoring outside hospitals. Therefore, this study investigates the feasibility of complexity reduction by analyzing one of the solutions presented for the challenge.
|
|
| 2. |
- Bandaragoda, Tharindu, et al.
(författare)
-
Trajectory clustering of road traffic in urban environments using incremental machine learning in combination with hyperdimensional computing
- 2019
-
Ingår i: The 2019 IEEE Intelligent Transportation Systems Conference - ITSC. - : IEEE. - 9781538670248 - 9781538670255 ; , s. 1664-1670
-
Konferensbidrag (refereegranskat)abstract
- Road traffic congestion in urban environments poses an increasingly complex challenge of detection, profiling and prediction. Although public policy promotes transport alternatives and new infrastructure, traffic congestion is highly prevalent and continues to be the lead cause for numerous social, economic and environmental issues. Although a significant volume of research has been reported on road traffic prediction, profiling of traffic has received much less attention. In this paper we address two key problems in traffic profiling by proposing a novel unsupervised incremental learning approach for road traffic congestion detection and profiling, dynamically over time. This approach uses (a) hyperdimensional computing to enable capture variable-length trajectories of commuter trips represented as vehicular movement across intersections, and (b) transforms these into feature vectors that can be incrementally learned over time by the Incremental Knowledge Acquiring Self-Learning (IKASL) algorithm. The proposed approach was tested and evaluated on a dataset consisting of approximately 190 million vehicular movement records obtained from 1,400 Bluetooth identifiers placed at the intersections of the arterial road network in the State of Victoria, Australia.
|
|
| 3. |
|
|
| 4. |
- Hernandez, Sinuhe
(författare)
-
Friction and Wear Phenomena in Steels at Elevated Temperatures
- 2016
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Different grades of steels are often exposed to high temperatures whether during their shaping/forming or during their use in several applications. This exposure to high temperature has a great bearing on the resulting friction and wear phenomena in steels due to changes in their surface and near-surface properties. This means that the wear and frictional behaviour will be no longer controlled nor determined by the original properties of steels but rather by the changes in steels surfaces brought about by high temperatures. A thorough understanding of friction and wear phenomena in steels under these conditions is crucial in terms of control as well as prediction of friction and wear. This thesis has focussed on friction and wear phenomena in some selected steels suitable for working at high temperatures.The initial part of this work concentrated on investigating the effect of load and temperature on the friction and wear behaviour of tool steel sliding against boron steel in a pin-on-disc (POD) test configuration. This investigation revealed the formation of oxidised protective layers and their role in reducing wear and friction at elevated temperatures.Experimental studies in a specially designed high temperature tribometer for simulating tool-workpiece interaction in hot sheet metal forming were also carried out using similar conditions to those used in the POD tests. These studies corroborated the presence and importance of oxidised layers at elevated temperatures. However, the thickness of oxidised layers was lower compared to those on the POD specimens. The results showed a good correlation between mechanisms of wear and friction especially at 400 °C. As in the case of the POD studies, the main wear mechanisms were adhesion and three body abrasion.Further, three-body abrasive wear behaviour of different tool steels, heat treated high-Si steels and boron steel at different temperatures was also investigated. The two main wear mechanisms identified were microploughing and microcutting. The results revealed near surface modifications in steel surfaces such as work hardened layers, mechanically mixed layers and recrystallization of ferrite grains. The wear behaviour of different steels was strongly influenced by the occurrence of these transformations as well as changes in mechanical properties like hardness and toughness.Nanoindentation and multiple-pass nanoscratch tests were carried out using a high temperature nanoindenter with a view to investigate the relationship between mechanical properties measured (hardness, fracture toughness, plasticity index) and the tribological behaviour of different tool steels. Higher volume losses were obtained for tool steels with low hardness and high plasticity index values.
|
|
| 5. |
- Holmberg, Jonas, 1976-, et al.
(författare)
-
Machining of additively manufactured alloy 718 in as-built and heat-treated condition: surface integrity and cutting tool wear
- 2024
-
Ingår i: The International Journal of Advanced Manufacturing Technology. - : Springer Nature. - 0268-3768 .- 1433-3015. ; 130:3-4, s. 1823-1842
-
Tidskriftsartikel (refereegranskat)abstract
- Additive manufacturing (AM) using powder bed fusion is becoming a mature technology that offers great possibilities and design freedom for manufacturing of near net shape components. However, for many gas turbine and aerospace applications, machining is still required, which motivates further research on the machinability and work piece integrity of additive-manufactured superalloys. In this work, turning tests have been performed on components made with both Powder Bed Fusion for Laser Beam (PBF-LB) and Electron Beam (PBF-EB) in as-built and heat-treated conditions. The two AM processes and the respective heat-treatments have generated different microstructural features that have a great impact on both the tool wear and the work piece surface integrity. The results show that the PBF-EB components have relatively lower geometrical accuracy, a rough surface topography, a coarse microstructure with hard precipitates and low residual stresses after printing. Turning of the PBF-EB material results in high cutting tool wear, which induces moderate tensile surface stresses that are balanced by deep compressive stresses and a superficial deformed surface that is greater for the heat-treated material. In comparison, the PBF-LB components have a higher geometrical accuracy, a relatively smooth topography and a fine microstructure, but with high tensile stresses after printing. Machining of PBF-LB material resulted in higher tool wear for the heat-treated material, increase of 49%, and significantly higher tensile surface stresses followed by shallower compressive stresses below the surface compared to the PBF-EB materials, but with no superficially deformed surface. It is further observed an 87% higher tool wear for PBF-EB in as-built condition and 43% in the heat-treated condition compared to the PBF-LB material. These results show that the selection of cutting tools and cutting settings are critical, which requires the development of suitable machining parameters that are designed for the microstructure of the material.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Kleyko, Denis, 1990-, et al.
(författare)
-
A Comprehensive Study of Complexity and Performance of Automatic Detection of Atrial Fibrillation : Classification of Long ECG Recordings Based on the PhysioNet Computing in Cardiology Challenge 2017
- 2020
-
Ingår i: Biomedical Engineering & Physics Express. - : Institute of Physics Publishing (IOPP). - 2057-1976. ; 6:2
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: The 2017 PhysioNet/CinC Challenge focused on automatic classification of atrial fibrillation (AF) in short ECGs. This study aimed to evaluate the use of the data and results from the challenge for detection of AF in longer ECGs, taken from three other PhysioNet datasets.Approach: The used data-driven models were based on features extracted from ECG recordings, calculated according to three solutions from the challenge. A Random Forest classifier was trained with the data from the challenge. The performance was evaluated on all non-overlapping 30 s segments in all recordings from three MIT-BIH datasets. Fifty-six models were trained using different feature sets, both before and after applying three feature reduction techniques.Main Results: Based on rhythm annotations, the AF proportion was 0.00 in the MIT-BIH Normal Sinus Rhythm (N = 46083 segments), 0.10 in the MIT-BIH Arrhythmia (N = 2880), and 0.41 in the MIT-BIH Atrial Fibrillation (N = 28104) dataset. For the best performing model, the corresponding detected proportions of AF were 0.00, 0.11 and 0.36 using all features, and 0.01, 0.10 and 0.38 when using the 15 best performing features.Significance: The results obtained on the MIT-BIH datasets indicate that the training data and solutions from the 2017 Physionet/Cinc Challenge can be useful tools for developing robust AF detectors also in longer ECG recordings, even when using a low number of carefully selected features. The use of feature selection allows significantly reducing the number of features while preserving the classification performance, which can be important when building low-complexity AF classifiers on ECG devices with constrained computational and energy resources.
|
|
| 9. |
- Kleyko, Denis, 1990-, et al.
(författare)
-
A Hyperdimensional Computing Framework for Analysis of Cardiorespiratory Synchronization during Paced Deep Breathing
- 2019
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 7, s. 34403-34415
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: Autonomic function during deep breathing (DB) is normally scored based on the assumption that the heart rate is synchronized with the breathing. We have observed individuals with subtle arrhythmias during DB where autonomic function cannot be evaluated. This study presents a novel method for analyzing cardiorespiratory synchronization: feature-based analysis of the similarity between heart rate and respiration using principles of hyperdimensional computing. Methods: Heart rate and respiration signals were modeled using Fourier series analysis. Three feature variables were derived and mapped to binary vectors in a high-dimensional space. Using both synthesized data and recordings from patients/healthy subjects, the similarity between the feature vectors was assessed using Hamming distance (high-dimensional space), Euclidean distance (original space), and with a coherence-based index. Methods were evaluated via classification of the similarity indices into three groups. Results: The distance-based methods achieved good separation of signals into classes with different degree of cardiorespiratory synchronization, also providing identification of patients with low cardiorespiratory synchronization but high values of conventional DB scores. Moreover, binary high-dimensional vectors allowed an additional analysis of the obtained Hamming distance. Conclusions: Feature-based similarity analysis using hyperdimensional computing is capable of identifying signals with low cardiorespiratory synchronization during DB due to arrhythmias. Vector-based similarity analysis could be applied to other types of feature variables than based on spectral analysis. Significance: The proposed methods for robustly assessing cardiorespiratory synchronization during DB facilitate the identification of individuals where the evaluation of autonomic function is problematic or even impossible, thus, increasing the correctness of the conventional DB scores.
|
|
| 10. |
- Kleyko, Denis, et al.
(författare)
-
Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks
- 2021
-
Ingår i: IEEE Transactions on Neural Networks and Learning Systems. - : Institute of Electrical and Electronics Engineers Inc.. - 2162-237X .- 2162-2388. ; 32:8, s. 3777-3783
-
Tidskriftsartikel (refereegranskat)abstract
- The deployment of machine learning algorithms on resource-constrained edge devices is an important challenge from both theoretical and applied points of view. In this brief, we focus on resource-efficient randomly connected neural networks known as random vector functional link (RVFL) networks since their simple design and extremely fast training time make them very attractive for solving many applied classification tasks. We propose to represent input features via the density-based encoding known in the area of stochastic computing and use the operations of binding and bundling from the area of hyperdimensional computing for obtaining the activations of the hidden neurons. Using a collection of 121 real-world data sets from the UCI machine learning repository, we empirically show that the proposed approach demonstrates higher average accuracy than the conventional RVFL. We also demonstrate that it is possible to represent the readout matrix using only integers in a limited range with minimal loss in the accuracy. In this case, the proposed approach operates only on small ${n}$ -bits integers, which results in a computationally efficient architecture. Finally, through hardware field-programmable gate array (FPGA) implementations, we show that such an approach consumes approximately 11 times less energy than that of the conventional RVFL.
|
|
