Heterogeneous Transfer Learning Research Articles

Heterogeneous transfer learning considering feature representation and environmental consistency for landslide spatial prediction

ABSTRACT The difficult, time-consuming, and imbalanced acquisition of landslide inventories in complex and heterogeneous large areas often results in limited predictive performance for most statistical landslide spatial prediction methods. Although partial transfer learning methods have produced reliable predictive results and successfully implemented knowledge transfer between data-rich and data-scarce areas, most of these methods generally only extract inadequate environmental features and lack the ability to interpret when, what, and how to effectively transfer knowledge to other regions with limited data. In this paper, a heterogeneous transfer learning method considering feature representations and environmental consistency, which features robustness, similarity, and transferability, is proposed for landslide spatial prediction. Specifically, we trained a stacked autoencoder (SAE) to extract more nonlinear features among environmental factors, and added an environmental similarity criterion to the transfer adaptation boosting (TrAdaBoost) algorithm to minimize feature dissimilarities and avoid negative transfer in different scenarios. To evaluate the robustness of the proposed method, we first selected two target areas (Lushan County and Luding County, China) and a source area (Wenchuan County, China) as case study areas. Then, we directly combined the source area and target area as an additional dataset without considering transfer learning to validate the significance and necessity of the proposed method. The area under the receiver operating characteristic curve (AUC) of the two target regions for the proposed method were 0.920 and 0.972, respectively, which were greater than those of the traditional TrAdaBoost (0.909 and 0.969, respectively), SAE (0.790 and 0.937, respectively), and random forest (0.915 and 0.966, respectively) methods. Furthermore, the AUC values of the SAE (0.851 and 0.900) and random forest (0.890 and 0.935) models based on the expanded datasets were also lower than those of the proposed method. Therefore, the experimental results show that the proposed method can be generalized well due to its efficient utilization and high adaptability. Moreover, the proposed method can not only be applied to emergency rescue and disaster prevention but can also offer a promising way to improve landslide predictions of models with incomplete landslide inventories.

Distributed Heterogeneous Transfer Learning

Transfer learning has proved to be effective for building predictive models even in complex conditions with a low amount of available labeled data, by constructing a predictive model for a target domain also using the knowledge coming from a separate domain, called source domain. However, several existing transfer learning methods assume identical feature spaces between the source and the target domains. This assumption limits the possible real-world applications of such methods, since two separate, although related, domains could be described by totally different feature spaces. Heterogeneous transfer learning methods aim to overcome this limitation, but they usually i) make other assumptions on the features, such as requiring the same number of features, ii) are not generally able to distribute the workload over multiple computational nodes, iii) cannot work in the Positive-Unlabeled (PU) learning setting, which we also considered in this study, or iv) their applicability is limited to specific application domains, i.e., they are not general-purpose methods.In this manuscript, we present a novel distributed heterogeneous transfer learning method, implemented in Apache Spark, that overcomes all the above-mentioned limitations. Specifically, it is able to work also in the PU learning setting by resorting to a clustering-based approach, and can align totally heterogeneous feature spaces, without exploiting peculiarities of specific application domains. Moreover, our distributed approach allows us to process large source and target datasets.Our experimental evaluation was performed in three different application domains that can benefit from transfer learning approaches, namely the reconstruction of the human gene regulatory network, the prediction of cerebral stroke in hospital patients, and the prediction of customer energy consumption in power grids. The results show that the proposed approach is able to outperform 4 state-of-the-art heterogeneous transfer learning approaches and 3 baselines, and exhibits ideal performances in terms of scalability.

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

AbstractDeep Reinforcement Learning (DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers (RBCs), but it still lacks scalability and generalisation due to the necessity of using tailored models for the training process. Transfer Learning (TL) is a potential solution to address this limitation. However, existing TL applications in building control have been mostly tested among buildings with similar features, not addressing the need to scale up advanced control in real-world scenarios with diverse energy systems. This paper assesses the performance of an online heterogeneous TL strategy, comparing it with RBC and offline and online DRL controllers in a simulation setup using EnergyPlus and Python. The study tests the transfer in both transductive and inductive settings of a DRL policy designed to manage a chiller coupled with a Thermal Energy Storage (TES). The control policy is pre-trained on a source building and transferred to various target buildings characterised by an integrated energy system including photovoltaic and battery energy storage systems, different building envelope features, occupancy schedule and boundary conditions (e.g., weather and price signal). The TL approach incorporates model slicing, imitation learning and fine-tuning to handle diverse state spaces and reward functions between source and target buildings. Results show that the proposed methodology leads to a reduction of 10% in electricity cost and between 10% and 40% in the mean value of the daily average temperature violation rate compared to RBC and online DRL controllers. Moreover, online TL maximises self-sufficiency and self-consumption by 9% and 11% with respect to RBC. Conversely, online TL achieves worse performance compared to offline DRL in either transductive or inductive settings. However, offline Deep Reinforcement Learning (DRL) agents should be trained at least for 15 episodes to reach the same level of performance as the online TL. Therefore, the proposed online TL methodology is effective, completely model-free and it can be directly implemented in real buildings with satisfying performance.

Heterogeneous transfer learning: recent developments, applications, and challenges

Heterogeneous transfer learning: recent developments, applications, and challenges

Video Abnormal Action Recognition Based on Multimodal Heterogeneous Transfer Learning

Human abnormal action recognition is crucial for video understanding and intelligent surveillance. However, the scarcity of labeled data for abnormal human actions often hinders the development of high-performance models. Inspired by the multimodal approach, this paper proposes a novel approach that leverages text descriptions associated with abnormal human action videos. Our method exploits the correlation between the text domain and the video domain in the semantic feature space and introduces a multimodal heterogeneous transfer learning framework from the text domain to the video domain. The text of the videos is used for feature encoding and knowledge extraction, and knowledge transfer and sharing are realized in the feature space, which is used to assist in the training of the abnormal action recognition model. The proposed method reduces the reliance on labeled video data, improves the performance of the abnormal human action recognition algorithm, and outperforms the popular video-based models, particularly in scenarios with sparse data. Moreover, our framework contributes to the advancement of automatic video analysis and abnormal action recognition, providing insights for the application of multimodal methods in a broader context.

Innovation and Informatization of Civics Teaching Mode in Colleges and Universities under Integrated Transfer Learning Strategies

Abstract This study addresses the problem of predicting student performance by proposing a heterogeneous transfer learning method based on FMBCC-FT, which aims to accurately predict students’ Civics knowledge mastery. The study achieves effective knowledge transfer by defining university Civics teaching as the source domain and considering the university’s demand for students’ Civics dynamics as the target domain. After collecting and standardizing students’ Civics education data, this study constructed a knowledge base model of Civics teaching based on the source domain data and migrated it to the target domain. To compensate for the bias in the migration, the study designed a three-stage iterative optimization migration weight learning method, which significantly improved the quality of Civics teaching by updating the parameter weights of the source domain model. The process was verified through the experimental control group pre and post-tests. The results showed that the total score of critical thinking ability pre and post-tests was −3.39. The students’ innovative consciousness score in the experimental group was 3.96, which was significantly higher than that of the control group, which was 0.18. In addition, the scores of the quality dimensions of the students in the control group and the experimental group ranged from 3.22 to 3.40 and 3.43 to 3.68, respectively. This empirical result effectively confirms that the Civics teaching model proposed in this paper can effectively improve students’ critical thinking ability, innovation consciousness and overall quality, which is of great guiding significance to the current practice of Civics teaching in colleges and universities.

Deep Learning-Enabled Heterogeneous Transfer Learning for Improved Network Attack Detection in Internal Networks

Cybersecurity faces constant challenges from increasingly sophisticated network attacks. Recent research shows machine learning can improve attack detection by training models on large labeled datasets. However, obtaining sufficient labeled data is difficult for internal networks. We propose a deep transfer learning model to learn common knowledge from domains with different features and distributions. The model has two feature projection networks to transform heterogeneous features into a common space, and a classification network then predicts transformed features into labels. To align probability distributions for two domains, maximum mean discrepancy (MMD) is used to compute distribution distance alongside classification loss. Though the target domain only has a few labeled samples, unlabeled samples are adequate for computing MMD to align unconditional distributions. In addition, we apply a soft classification scheme on unlabeled data to compute MMD over classes to further align conditional distributions. Experiments between NSL-KDD, UNSW-NB15, and CICIDS2017 validate that the method substantially improves cross-domain network attack detection accuracy.

Domain‐invariant attention network for transfer learning between cross‐scene hyperspectral images

AbstractSmall‐sample‐size problem is always a challenge for hyperspectral image (HSI) classification. Considering the co‐occurrence of land‐cover classes between similar scenes, transfer learning can be performed, and cross‐scene classification is deemed a feasible approach proposed in recent years. In cross‐scene classification, the source scene which possesses sufficient labelled samples is used for assisting the classification of the target scene that has a few labelled samples. In most situations, different HSI scenes are imaged by different sensors resulting in their various input feature dimensions (i.e. number of bands), hence heterogeneous transfer learning is desired. An end‐to‐end heterogeneous transfer learning algorithm namely domain‐invariant attention network (DIAN) is proposed to solve the cross‐scene classification problem. The DIAN mainly contains two modules. (1) A feature‐alignment CNN (FACNN) is applied to extract features from source and target scenes, respectively, aiming at projecting the heterogeneous features from two scenes into a shared low‐dimensional subspace. (2) A domain‐invariant attention block is developed to gain cross‐domain consistency with a specially designed class‐specific domain‐invariance loss, thus further eliminating the domain shift. The experiments on two different cross‐scene HSI datasets show that the proposed DIAN achieves satisfying classification results.

Automatic Classification of Histopathology Images across Multiple Cancers Based on Heterogeneous Transfer Learning.

Current artificial intelligence (AI) in histopathology typically specializes on a single task, resulting in a heavy workload of collecting and labeling a sufficient number of images for each type of cancer. Heterogeneous transfer learning (HTL) is expected to alleviate the data bottlenecks and establish models with performance comparable to supervised learning (SL). An accurate source domain model was trained using 28,634 colorectal patches. Additionally, 1000 sentinel lymph node patches and 1008 breast patches were used to train two target domain models. The feature distribution difference between sentinel lymph node metastasis or breast cancer and CRC was reduced by heterogeneous domain adaptation, and the maximum mean difference between subdomains was used for knowledge transfer to achieve accurate classification across multiple cancers. HTL on 1000 sentinel lymph node patches (L-HTL-1000) outperforms SL on 1000 sentinel lymph node patches (L-SL-1-1000) (average area under the curve (AUC) and standard deviation of L-HTL-1000 vs. L-SL-1-1000: 0.949 ± 0.004 vs. 0.931 ± 0.008, p value = 0.008). There is no significant difference between L-HTL-1000 and SL on 7104 patches (L-SL-2-7104) (0.949 ± 0.004 vs. 0.948 ± 0.008, p value = 0.742). Similar results are observed for breast cancer. B-HTL-1008 vs. B-SL-1-1008: 0.962 ± 0.017 vs. 0.943 ± 0.018, p value = 0.008; B-HTL-1008 vs. B-SL-2-5232: 0.962 ± 0.017 vs. 0.951 ± 0.023, p value = 0.148. HTL is capable of building accurate AI models for similar cancers using a small amount of data based on a large dataset for a certain type of cancer. HTL holds great promise for accelerating the development of AI in histopathology.

Cross-domain network attack detection enabled by heterogeneous transfer learning

In recent years, cybersecurity has been endlessly challenged by more and more sophisticated network attacks, due to lacking the ability to detect unknown attacks in time. Recent researches show that machine learning helps to improve the efficacy of network attack detection, by training network attack classification models with huge amount labeled data. However in internal networks, due to the scarcity of attack instances and lacking expert labor force to label the data, it is always difficult to obtain sufficient labeled data to train such models. To uncover unknown attacks with machine learning techniques in internal networks, we propose to exploit transfer learning to utilize public datasets that contains attack instances to train a prediction model that will be used for un-labeled internal datasets. The main problem is to address the heterogeneity between datasets. Specifically, we project two heterogeneous datasets into a common latent space and formulate an optimization problem to minimize the distance of two distributions in the common space. Then we apply MLP classifier to the projected data to identify attack instances in internal networks. We conduct experiments that perform transfer learning between the NSLKDD to UNSW-NB15 datasets. The results validate that the proposed method notably improves the cross-domain attack detection accuracy in learning scenarios, such as “DoS to DoS” and “R2L to Exploits”.

Cross-modal multi-label image classification modeling and recognition based on nonlinear

Abstract Recently, it has become a popular strategy in multi-label image recognition to predict those labels that co-occur in a picture. Previous work has concentrated on capturing label correlation but has neglected to correctly fuse picture features and label embeddings, which has a substantial influence on the model’s convergence efficiency and restricts future multi-label image recognition accuracy improvement. In order to better classify labeled training samples of corresponding categories in the field of image classification, a cross-modal multi-label image classification modeling and recognition method based on nonlinear is proposed. Multi-label classification models based on deep convolutional neural networks are constructed respectively. The visual classification model uses natural images and simple biomedical images with single labels to achieve heterogeneous transfer learning and homogeneous transfer learning, capturing the general features of the general field and the proprietary features of the biomedical field, while the text classification model uses the description text of simple biomedical images to achieve homogeneous transfer learning. The experimental results show that the multi-label classification model combining the two modes can obtain a hamming loss similar to the best performance of the evaluation task, and the macro average F1 value increases from 0.20 to 0.488, which is about 52.5% higher. The cross-modal multi-label image classification algorithm can better alleviate the problem of overfitting in most classes and has better cross-modal retrieval performance. In addition, the effectiveness and rationality of the two cross-modal mapping techniques are verified.

MDEV Model: A Novel Ensemble-Based Transfer Learning Approach for Pneumonia Classification Using CXR Images

Pneumonia is a dangerous respiratory disease due to which breathing becomes incredibly difficult and painful; thus, catching it early is crucial. Medical physicians’ time is limited in outdoor situations due to many patients; therefore, automated systems can be a rescue. The input images from the X-ray equipment are also highly unpredictable due to variances in radiologists’ experience. Therefore, radiologists require an automated system that can swiftly and accurately detect pneumonic lungs from chest x-rays. In medical classifications, deep convolution neural networks are commonly used. This research aims to use deep pre-trained transfer learning models to accurately categorize CXR images into binary classes, i.e., Normal and Pneumonia. The MDEV is a proposed novel ensemble approach that concatenates four heterogeneous transfer learning models: MobileNet, DenseNet-201, EfficientNet-B0, and VGG-16, which have been finetuned and trained on 5,856 CXR images. The evaluation matrices used in this research to contrast different deep transfer learning architectures include precision, accuracy, recall, AUC-roc, and f1-score. The model effectively decreases training loss while increasing accuracy. The findings conclude that the proposed MDEV model outperformed cutting-edge deep transfer learning models and obtains an overall precision of 92.26%, an accuracy of 92.15%, a recall of 90.90%, an auc-roc score of 90.9%, and f-score of 91.49% with minimal data pre-processing, data augmentation, finetuning and hyperparameter adjustment in classifying Normal and Pneumonia chests.

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification

Funnelling(Fun) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL). In this ensemble method, 1st-tier classifiers, each working on a different and language-dependent feature space, return a vector of calibrated posterior probabilities (with one dimension for each class) for each document, and the final classification decision is taken by a meta-classifier that uses this vector as its input. The meta-classifier can thus exploit class-class correlations, and this (among other things) givesFunan edge over CLTC systems in which these correlations cannot be brought to bear. In this article, we describeGeneralized Funnelling(gFun), a generalization ofFunconsisting of an HTL architecture in which 1st-tier components can be arbitraryview-generating functions, i.e., language-dependent functions that each produce a language-independent representation (“view”) of the (monolingual) document. We describe an instance ofgFunin which the meta-classifier receives as input a vector of calibrated posterior probabilities (as inFun) aggregated to other embedded representations that embody other types of correlations, such as word-class correlations (as encoded byWord-Class Embeddings), word-word correlations (as encoded byMultilingual Unsupervised or Supervised Embeddings), and word-context correlations (as encoded bymultilingual BERT). We show that this instance ofgFunsubstantially improves overFunand over state-of-the-art baselines by reporting experimental results obtained on two large, standard datasets for multilingual multilabel text classification. Our code that implementsgFunis publicly available.

Adaptively heterogeneous transfer learning for hyperspectral image classification

ABSTRACT Convolutional Neural Network (CNN) has been proved excellent for hyperspectral image(HSI) classification on the basis of large training set. However, the lack of available samples degrades the performance of CNNs in practical HSI classification. Although transfer learning is a typical strategy to address the issue of limited training samples, such methods tend to reload source model’s feature extractors directly ignoring their generalization. Furthermore, most existing adaptive transfer learning algorithms pay attention to spectral features of HSI while the obvious difference between RGB image and HSI’s spatial features is overlooked. In this paper, the proposed method can solve the mentioned problems to some extent. Firstly, the proposed adaptive heterogeneous transfer (AHT) can measure their transferability and find appropriate solution to transfer knowledge. It computes feature extractors’ transferability based on feature maps and influences the learning process of target model through backpropagation, therefore, target model is prone to receive knowledge from feature extractors with high generalization. Secondly, the proposed method lays emphasis on HSI’s spatial features. It adopts the methodology of spatial attention and calculates the regularization loss based on spatial features. Experiments were conducted on two widely used HSI datasets. The results demonstrate the method’s effectiveness when few samples are available.

Co-Occurrence Fingerprint Data-Based Heterogeneous Transfer Learning Framework for Indoor Positioning

Distribution discrepancy is an intrinsic challenge in existing fingerprint-based indoor positioning system(s) (FIPS) due to real-time environmental variations; thus, the positioning model needs to be reconstructed frequently based on newly collected training data. However, it is expensive or impossible to collect adequate training samples to reconstruct the fingerprint database. Fortunately, transfer learning has proven to be an effective solution to mitigate the distribution discrepancy, enabling us to update the positioning model using newly collected training data in real time. However, in practical applications, traditional transfer learning algorithms no longer act well to feature space heterogeneity caused by different types or holding postures of fingerprint collection devices (such as smartphones). Moreover, current heterogeneous transfer methods typically require enough accurately labeled samples in the target domain, which is practically expensive and even unavailable. Aiming to solve these problems, a heterogeneous transfer learning framework based on co-occurrence data (HTL-CD) is proposed for FIPS, which can realize higher positioning accuracy and robustness against environmental changes without reconstructing the fingerprint database repeatedly. Specifically, the source domain samples are mapped into the feature space in the target domain, then the marginal and conditional distributions of the source and target samples are aligned in order to minimize the distribution divergence caused by collection device heterogeneity and environmental changes. Moreover, the utilized co-occurrence fingerprint data enables us to calculate correlation coefficients between heterogeneous samples without accurately labeled target samples. Furthermore, by resorting to the adopted correlation restriction mechanism, more valuable knowledge will be transferred to the target domain if the source samples are related to the target ones, which remarkably relieves the "negative transfer" issue. Real-world experimental performance implies that, even without accurately labeled samples in the target domain, the proposed HTL-CD can obtain at least 17.15% smaller average localization errors (ALEs) than existing transfer learning-based positioning methods, which further validates the effectiveness and superiority of our algorithm.

OHetTLAL: An Online Transfer Learning Method for Fingerprint-Based Indoor Positioning.

In an indoor positioning system (IPS), transfer learning (TL) methods are commonly used to predict the location of mobile devices under the assumption that all training instances of the target domain are given in advance. However, this assumption has been criticized for its shortcomings in dealing with the problem of signal distribution variations, especially in a dynamic indoor environment. The reasons are: collecting a sufficient number of training instances is costly, the training instances may arrive online, the feature spaces of the target and source domains may be different, and negative knowledge may be transferred in the case of a redundant source domain. In this work, we proposed an online heterogeneous transfer learning (OHetTLAL) algorithm for IPS-based RSS fingerprinting to improve the positioning performance in the target domain by fusing both source and target domain knowledge. The source domain was refined based on the target domain to avoid negative knowledge transfer. The co-occurrence measure of the feature spaces (Cmip) was used to derive the homogeneous new feature spaces, and the features with higher weight values were selected for training the classifier because they could positively affect the location prediction of the target. Thus, the objective function was minimized over the new feature spaces. Extensive experiments were conducted on two real-world scenarios of datasets, and the predictive power of the different modeling techniques were evaluated for predicting the location of a mobile device. The results have revealed that the proposed algorithm outperforms the state-of-the-art methods for fingerprint-based indoor positioning and is found robust to changing environments. Moreover, the proposed algorithm is not only resilient to fluctuating environments but also mitigates the model's overfitting problem.

An improved method for predicting soluble solids content in apples by heterogeneous transfer learning and near-infrared spectroscopy

Predicting fruit soluble solids content (SSC) is a hot topic in non-destructive detection. Biological variability of fruit decreases the accuracy of the prediction model. Therefore, modeling methods that can reduce the negative effect of biological variability are necessary. In this paper, an improved modeling method based on the partial least squares (PLS) regression was proposed, using convolutional autoencoder and heterogeneous transfer learning for feature extraction. The dataset used for calibration and prediction contains spectra and corresponding SSC values of apples collected from 2012 to 2018. In comparison with the traditional PLS method, the proposed method performed better for long-term SSC prediction of apples with biological variability. The correlation coefficients calculated on validation set were 0.934, 0.940, 0.915, 0.899, 0.901, respectively. The root mean square errors calculated on validation set were 0.736 °Brix, 0.694 °Brix, 0.674 °Brix, 0.571 °Brix, 0.620 °Brix, respectively. Besides, the proposed method could still achieve relatively satisfactory results when the quantity of calibration samples was less.

A novel heterogeneous transfer learning method based on data stitching for the sequential coding brain computer interface

ObjectiveFor the brain computer interface (BCI), it is necessary to collect enough electroencephalography (EEG) signals to train the classification model. When the operation dimension of BCI is large, it will bring great burden to data acquisition. Fortunately, this problem can be solved by our proposed transfer learning method. MethodFor the sequential coding experimental paradigm, the multi-band data stitching with label alignment and tangent space mapping (MDSLATSM) algorithm is proposed as a novel heterogeneous transfer learning method. After filtering by multi-band filtering, the artificial signals can be obtained by data stitching from the source domain, which build a bridge between the source domain and target domain. To make the distribution of two domains closer, their covariance matrices are aligned by label alignment. After mapping to the tangent space, the features are extracted from the Riemannian manifold. Finally, the classification results are obtained with feature selection and classification. ResultsOur data set includes the EEG signals from 16 subjects. For the heterogeneous transfer learning of cross-label, the average classification accuracy is 78.28%. MDSLATSM is also tested for cross-subject, and the average classification accuracy is 64.01%, which is better than existing methods. SignificanceCombining multi-band filtering, data stitching, label alignment and tangent space mapping, a novel heterogeneous transfer learning method can be achieved with superior performance, which promotes the practical application of the BCI systems.

A brain-like classification method for computed tomography images based on adaptive feature matching dual-source domain heterogeneous transfer learning.

Transfer learning can improve the robustness of deep learning in the case of small samples. However, when the semantic difference between the source domain data and the target domain data is large, transfer learning easily introduces redundant features and leads to negative transfer. According the mechanism of the human brain focusing on effective features while ignoring redundant features in recognition tasks, a brain-like classification method based on adaptive feature matching dual-source domain heterogeneous transfer learning is proposed for the preoperative aided diagnosis of lung granuloma and lung adenocarcinoma for patients with solitary pulmonary solid nodule in the case of small samples. The method includes two parts: (1) feature extraction and (2) feature classification. In the feature extraction part, first, By simulating the feature selection mechanism of the human brain in the process of drawing inferences about other cases from one instance, an adaptive selected-based dual-source domain feature matching network is proposed to determine the matching weight of each pair of feature maps and each pair of convolution layers between the two source networks and the target network, respectively. These two weights can, respectively, adaptive select the features in the source network that are conducive to the learning of the target task, and the destination of feature transfer to improve the robustness of the target network. Meanwhile, a target network based on diverse branch block is proposed, which made the target network have different receptive fields and complex paths to further improve the feature expression ability of the target network. Second, the convolution kernel of the target network is used as the feature extractor to extract features. In the feature classification part, an ensemble classifier based on sparse Bayesian extreme learning machine is proposed that can automatically decide how to combine the output of base classifiers to improve the classification performance. Finally, the experimental results (the AUCs were 0.9542 and 0.9356, respectively) on the data of two center data show that this method can provide a better diagnostic reference for doctors.

Heterogeneous Transfer Learning for Wi-Fi Indoor Positioning Based Hybrid Feature Selection.

This paper presents the application of heterogeneous transfer learning (HetTL) methods which consider hybrid feature selection to reduce the training calibration effort and the noise generated by fingerprint duplicates obtained from multiple Wi-Fi access points. The Cramer–Rao Lower Bound analysis (CRLB) was also applied to evaluate and estimate a lower limit for the variance of a parameter estimator used to analyze positioning performance. We developed two novel algorithms for feature selection in fingerprint-based indoor positioning problems (IPP) to enhance positioning performance in the target domain with the HetTL. The algorithms comprised two scenarios: (i) a principal component analysis-based approach (PCA-based) and (ii) a hybrid approach that takes both PCA and correlation effect analysis into account (hybrid scenario). Accordingly, a new feature vector was constructed by retaining only the most significant predictors, and the most efficient feature dimensions were also determined by using a hybrid-based approach. Experimental results showed that the hybrid-based proposed algorithm has the minimum mean absolute error. The CRLB analysis also showed that the number of Wi-Fi access points could affect the lower bound location estimation error; however, identifying the most significant predictors is an effective approach to improve positioning performance.