Generalized adaptive resonance theory (GART) is a neural network model that is capable of online learning and is effective in tackling pattern classification tasks. In this paper, we propose an improved GART model (IGART), and demonstrate its applicability to power systems. IGART enhances the dynamics of GART in several aspects, which include the use of the Laplacian likelihood function, a new vigilance function, a new match-tracking mechanism, an ordering algorithm for determining the sequence of training data, and a rule extraction capability to elicit if-then rules from the network. To assess the effectiveness of IGART and to compare its performances with those from other methods, three datasets that are related to power systems are employed. The experimental results demonstrate the usefulness of IGART with the rule extraction capability in undertaking classification problems in power systems engineering.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNN.2011.2173502 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Tasers, a form of police weaponry causing neuromuscular incapacitation and extreme pain, were confirmed in 2010 to be used in New Zealand inpatient mental health units. Their use on patients, or tāngata whai ora (persons seeking wellbeing), raises ethical concerns about harm prevention, moral duties, and human rights in healthcare. The New Zealand healthcare system, grounded in principles and rights, regulates procedures to uphold fundamental rights.
View Article and Find Full Text PDFChanges in muscle performance among older adults with myeloid malignancies engaging in a mobile health (mHealth) exercise intervention: a single arm pilot study.
BMC Geriatr
January 2025
James P. Wilmot Cancer Institute, Rochester, New York, USA.
Background: Older adults with cancer are vulnerable to declines in muscle performance (e.g., strength, speed, duration of muscular contraction), which are associated with worse cancer-related outcomes.
View Article and Find Full Text PDFResistive memory-based zero-shot liquid state machine for multimodal event data learning.
Nat Comput Sci
January 2025
Key Lab of Fabrication Technologies for Integrated Circuits and Key Laboratory of Microelectronic Devices and Integrated Technology, Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China.
The human brain is a complex spiking neural network (SNN) capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal propagation. However, replicating the human brain in neuromorphic hardware presents both hardware and software challenges.
View Article and Find Full Text PDFWireless power-up and readout from a label-free biosensor.
Biomed Microdevices
January 2025
Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ, 08854, USA.
Wearable and implantable biosensors have rapidly entered the fields of health and biomedicine to diagnose diseases and physiological monitoring. The use of wired medical devices causes surgical complications, which can occur when wires break, become infected, generate electrical noise, and are incompatible with implantable applications. In contrast, wireless power transfer is ideal for biosensing applications since it does not necessitate direct connections between measurement tools and sensing systems, enabling remote use of the biosensors.
View Article and Find Full Text PDFAn optimized LSTM-based deep learning model for anomaly network intrusion detection.
Sci Rep
January 2025
Department of Electrical and Electronics Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India.
The increasing prevalence of network connections is driving a continuous surge in the requirement for network security and safeguarding against cyberattacks. This has triggered the need to develop and implement intrusion detection systems (IDS), one of the key components of network perimeter aimed at thwarting and alleviating the issues presented by network invaders. Over time, intrusion detection systems have been instrumental in identifying network breaches and deviations.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!