Transfer Learning: Survey and Classification

Agarwal, Nidhi; Sondhi, Akanksha; Chopra, Khyati; Singh, Ghanapriya

doi:10.1007/978-981-15-5345-5_13

Cited by 56 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The model training time should be reduced so that FPFE can react to changes in the environment in less time. In the future, we plan to employ the transfer learning concept [ 42 ] to train models for a target domain (i.e., a new environment) by leveraging the models for the source domain (i.e., the old environment) with only a few training data. By deep learning, we only need to collect fingerprint data of a few PRs for training AE or PCA models.…”

Section: Discussionmentioning

confidence: 99%

Fingerprint Feature Extraction for Indoor Localization

Jiang

Subakti

Liang

2021

Sensors

View full text Add to dashboard Cite

This paper proposes a fingerprint-based indoor localization method, named FPFE (fingerprint feature extraction), to locate a target device (TD) whose location is unknown. Bluetooth low energy (BLE) beacon nodes (BNs) are deployed in the localization area to emit beacon packets periodically. The received signal strength indication (RSSI) values of beacon packets sent by various BNs are measured at different reference points (RPs) and saved as RPs’ fingerprints in a database. For the purpose of localization, the TD also obtains its fingerprint by measuring the beacon packet RSSI values for various BNs. FPFE then applies either the autoencoder (AE) or principal component analysis (PCA) to extract fingerprint features. It then measures the similarity between the features of PRs and the TD with the Minkowski distance. Afterwards, k RPs associated with the k smallest Minkowski distances are selected to estimate the TD’s location. Experiments are conducted to evaluate the localization error of FPFE. The experimental results show that FPFE achieves an average error of 0.68 m, which is better than those of other related BLE fingerprint-based indoor localization methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Fingerprint Feature Extraction for Indoor Localization

Jiang

Subakti

Liang

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…There are many types of transfer learning [9] in the literature that use different approaches to solve this problem. To better understand how to classify our proposal, we can say that it can be included in inductive transfer learning [9] because we use teachers trained on the same domain or on a different one but we only use supervised data. We are also in the sub-category of self-taught learning [9] because we only train the student and not other models.…”

Section: Related Workmentioning

confidence: 99%

“…To better understand how to classify our proposal, we can say that it can be included in inductive transfer learning [9] because we use teachers trained on the same domain or on a different one but we only use supervised data. We are also in the sub-category of self-taught learning [9] because we only train the student and not other models.…”

Section: Related Workmentioning

confidence: 99%

Is One Teacher Model Enough to Transfer Knowledge to a Student Model?

2021

View full text Add to dashboard Cite

Nowadays, the transfer learning technique can be successfully applied in the deep learning field through techniques that fine-tune the CNN’s starting point so it may learn over a huge dataset such as ImageNet and continue to learn on a fixed dataset to achieve better performance. In this paper, we designed a transfer learning methodology that combines the learned features of different teachers to a student network in an end-to-end model, improving the performance of the student network in classification tasks over different datasets. In addition to this, we tried to answer the following questions which are in any case directly related to the transfer learning problem addressed here. Is it possible to improve the performance of a small neural network by using the knowledge gained from a more powerful neural network? Can a deep neural network outperform the teacher using transfer learning? Experimental results suggest that neural networks can transfer their learning to student networks using our proposed architecture, designed to bring to light a new interesting approach for transfer learning techniques. Finally, we provide details of the code and the experimental settings.

show abstract

“…A drawback of polls lies in their dependence on abstract evaluations of members or relatives and, consequently, subject to inclination and mistakes connected to intellectual weakness or absence of knowledge into hindrances. Additionally, several patients live alone and are supported for a couple of hours weekly; it is hard to get a consistent and exhaustive clinical image of the patient's ADL status [3,6]. Sensor-based advancements for measuring ADL can add new measurements to existing clinical evaluation.…”

Section: Introduction and Necessity Of The Workmentioning

confidence: 99%

“…The utilization of sensorbased estimation creates much information, which requires acknowledgment strategies to deduce an action. ADL detection from ambient information is customarily done utilizing training datasets or early learning-based methodologies, for example, probabilistic based, rule based, Naïve Bayes, K-Means grouping, and Random Forest [6]. Another general way to deal with action acknowledgment is to plan and utilize machine learning techniques to outline sensor occasions' succession to compare movement names [7].…”

Section: Introduction and Necessity Of The Workmentioning

confidence: 99%

Smart aging monitoring and early dementia recognition (SAMEDR): uncovering the hidden wellness parameter for preventive well-being monitoring to categorize cognitive impairment and dementia in community-dwelling elderly subjects through AI

Ghayvat

Gope

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Reasoning weakening because of dementia degrades the performance in activities of daily living (ADL). Present research work distinguishes care needs, dangers and monitors the effect of dementia on an individual. This research contrasts in ADL design execution between dementia-affected people and other healthy elderly with heterogeneous sensors. More than 300,000 sensors associated activation data were collected from the dementia patients and healthy controls with wellness sensors networks. Generated ADLs were envisioned and understood through the activity maps, diversity and other wellness parameters to categorize wellness healthy, and dementia affected the elderly. Diversity was significant between diseased and healthy subjects. Heterogeneous unobtrusive sensor data evaluate behavioral patterns associated with ADL, helpful to reveal the impact of cognitive degradation, to measure ADL variation throughout dementia. The primary focus of activity recognition in the current research is to transfer dementia subject occupied homes models to generalized age-matched healthy subject data models to utilize new services, label classified datasets and produce limited datasets due to less training. Current research proposes a novel Smart Aging Monitoring and Early Dementia Recognition system that provides the exchange of data models between dementia subject occupied homes (DSOH) to healthy subject occupied homes (HSOH) in a move to resolve the deficiency of training data. At that point, the key attributes are mapped onto each other utilizing a sensor data fusion that assures to retain the diversities between various HSOH & DSOH by diminishing the divergence between them. Moreover, additional tests have been conducted to quantify the excellence of the offered framework: primary, in contradiction of the precision of feature mapping techniques; next, computing the merit of categorizing data at DSOH; and, the last, the aptitude of the projected structure to function thriving due to noise data. The outcomes show encouraging pointers and highlight the boundaries of the projected approach.

show abstract

Transfer Learning: Survey and Classification

Cited by 56 publications

References 28 publications

Fingerprint Feature Extraction for Indoor Localization

Fingerprint Feature Extraction for Indoor Localization

Is One Teacher Model Enough to Transfer Knowledge to a Student Model?

Smart aging monitoring and early dementia recognition (SAMEDR): uncovering the hidden wellness parameter for preventive well-being monitoring to categorize cognitive impairment and dementia in community-dwelling elderly subjects through AI

Contact Info

Product

Resources

About