A Review on the Drawbacks and Enhancement Opportunities of the Feature Selective Validation

Azpúrua, Marco A.; Páez, Eduardo; Rojas-Mora, Julio; Ventosa, Oriol; Silva, Ferran; Zhang, Gang; Duffy, Alistair; Jauregui, Ricardo

doi:10.1109/temc.2014.2304622

Cited by 15 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ADM, FDM and GDM provide quantitative visual interpretations for data similarity and map a quality interpretation on six intervals, as shown in Table 1 . FSV has its advantages and limitations, as do all other statistics methods [ 62 ]. In contrast to classical statistical and algebraic toolsets, this method is relatively new and there has been active research conducted to eliminate its limitations and extend its applicability to two-dimensional (2D) and three-dimensional (3D) data sets [ 63 ].…”

Section: Preparation Experimental Setup and Methodologymentioning

confidence: 99%

Impact of Li-Ion Battery on System’s Overall Impedance and Received Signal Strength for Power Line Communication (PLC)

Marsic

Amietszajew

Gardner

et al. 2022

Sensors

View full text Add to dashboard Cite

In anticipation of the hybrid utilisation of the radio frequency (RF) wireless transceiver technology embedded in future smart Li-ion battery cells to deliver hybrid links based on power line communication (PLC) and wireless connections, herein we present an empirical high-frequency investigation of the direct current (DC) bus. The focus is to determine, via statistical tools including correlation coefficient (CC), root mean squared error (RMSE) and feature selective validation (FSV) method, the impedance and signal change impact on a possible communication link when fully charged cells are present or completely missing from the bus. Moreover, to establish if technological differences may be accounted for during the empirical experiments, Li-ion cells from two different manufacturers were selected and connected via three subsequent capacitive couplings of 1 µF, 1 nF and 1 pF. According to a methodical comparison by employing CC, RMSE, and FSV over the measured impedance and signal attenuation, this study has shown that the physical DC network is the dominant impedance at high frequencies and that the signal attenuation on the DC line supports communication in the investigated spectrum. The reported findings are critical for in situ hybrid PLC and wireless communication implementation of BMS for Li-ion systems supported through only one RF transceiver.

show abstract

Section: Preparation Experimental Setup and Methodologymentioning

confidence: 99%

Impact of Li-Ion Battery on System’s Overall Impedance and Received Signal Strength for Power Line Communication (PLC)

Marsic

Amietszajew

Gardner

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…1597.1 and 1597.2 [11]. For example, to solve the problem applying FSV to the validation of transient datasets, [12], [13] proposed a modification to FSV method to give reasonable assessment results.…”

Section: Fsv Methodsmentioning

confidence: 99%

Applying the Analytic Hierarchy Process (AHP) to an FSV-Based Comparison of Multiple Datasets

Zhang

Wang

Duffy

et al. 2015

IEEE Trans. Electromagn. Compat.

Self Cite

View full text Add to dashboard Cite

This paper presents research extending the feature selective validation (FSV) method to quantitatively compare multiple datasets. The analytic hierarchy process is introduced to weight different FSV results when comparison is conducted by comparing multiple numerical results with their referencing counterparts. Only pairwise comparisons are required which simplify the process of comprehensive validation. The efficiency of this approach is demonstrated by the validation of a simplified crosstalk model. Index Terms-Analytic hierarchy process, comprehensive validation, crosstalk, equivalent cable bundle method, feature selective validation. 0018-9375

show abstract

“…On contrary to most existing literature, no feature engineering has been used for generating predictions. Feature engineering often proves to be a very costly process as it involves manual extraction of significant features from the dataset which becomes a tiresome job [16] when the dataset is huge. Furthermore, getting the relevant features involve a deep understanding of the relevant domain [17] for which classification is to be made.…”

Section: Literature Reviewmentioning

confidence: 99%

An Efficient SMOTE-Based Deep Learning Model for Heart Attack Prediction

Waqar

Dawood

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

Cardiac disease treatments are often being subjected to the acquisition and analysis of vast quantity of digital cardiac data. These data can be utilized for various beneficial purposes. These data’s utilization becomes more important when we are dealing with critical diseases like a heart attack where patient life is often at stake. Machine learning and deep learning are two famous techniques that are helping in making the raw data useful. Some of the biggest problems that arise from the usage of the aforementioned techniques are massive resource utilization, extensive data preprocessing, need for features engineering, and ensuring reliability in classification results. The proposed research work presents a cost-effective solution to predict heart attack with high accuracy and reliability. It uses a UCI dataset to predict the heart attack via various machine learning algorithms without the involvement of any feature engineering. Moreover, the given dataset has an unequal distribution of positive and negative classes which can reduce performance. The proposed work uses a synthetic minority oversampling technique (SMOTE) to handle given imbalance data. The proposed system discarded the need of feature engineering for the classification of the given dataset. This led to an efficient solution as feature engineering often proves to be a costly process. The results show that among all machine learning algorithms, SMOTE-based artificial neural network when tuned properly outperformed all other models and many existing systems. The high reliability of the proposed system ensures that it can be effectively used in the prediction of the heart attack.

show abstract

A Review on the Drawbacks and Enhancement Opportunities of the Feature Selective Validation

Cited by 15 publications

References 17 publications

Impact of Li-Ion Battery on System’s Overall Impedance and Received Signal Strength for Power Line Communication (PLC)

Impact of Li-Ion Battery on System’s Overall Impedance and Received Signal Strength for Power Line Communication (PLC)

Applying the Analytic Hierarchy Process (AHP) to an FSV-Based Comparison of Multiple Datasets

An Efficient SMOTE-Based Deep Learning Model for Heart Attack Prediction

Contact Info

Product

Resources

About