Feature Generation Techniques Research Articles

A novel multi-model feature generation technique for suicide detection

Automated expert systems (AES) analyzing depression-related content on social media have piqued the interest of researchers. Depression, often linked to suicide, requires early prediction for potential life-saving interventions. In the conventional approach, psychologists conduct patient interviews or administer questionnaires to assess depression levels. However, this traditional method is plagued by limitations. Patients might not feel comfortable disclosing their true feelings to psychologists, and counselors may struggle to accurately predict situations due to limited data. In this context, social media emerges as a potentially valuable resource. Given the widespread use of social media in daily life, individuals often express their nature and mental state through their online posts. AES can efficiently analyze vast amounts of social media content to predict depression levels in individuals at an early stage. This study contributes to this endeavor by proposing an innovative approach for predicting suicide risks using social media content and machine learning techniques. A novel multi-model feature generation technique is employed to enhance the performance of machine learning models. This technique involves the use of a feature extraction method known as term frequency-inverse document frequency (TF-IDF), combined with two machine learning models: logistic regression (LR) and support vector machine (SVM). The proposed technique calculates probabilities for each sample in the dataset, resulting in a new feature set referred to as the probability-based feature set (ProBFS). This ProBFS is compact yet highly correlated with the target classes in the dataset. The utilization of concise and correlated features yields significant outcomes. The SVM model achieves an impressive accuracy score of 0.96 using ProBFS while maintaining a low computational time of 5.63 seconds even when dealing with extensive datasets. Furthermore, a comparison with state-of-the-art approaches is conducted to demonstrate the significance of the proposed method.

Online_XKD: An online knowledge distillation model for underwater object detection

Underwater object detection in the field of computer vision faces unique challenges such as color distortion, reduced visibility, and blurred edges caused by aquatic conditions, which decrease the efficiency of traditional methods. Furthermore, the limited memory and computational power of underwater equipment necessitate the development of lightweight and efficient real-time monitoring algorithms. To address these issues, this paper designs an online knowledge distillation(KD) framework based on mutual knowledge transfer, named Online-XKD, which aims to enhance the efficiency and generalizability of knowledge distillation through mutual knowledge exchange while maintaining model lightweightness. The core idea of Online-XKD is an internally designed mutual knowledge transfer structure for online distillation within the detection head, which enhances learning outcomes by optimizing distillation efficiency and broadening generalizability. Additionally, we introduce a mask generation feature knowledge distillation architecture based on the backbone network, which significantly enhances the feature extraction capability of the student model by integrating mask masking and feature generation techniques. Moreover, by incorporating PSA and AUGFPN attention modules, the feature extraction capability in complex underwater environments is further enhanced without adding extra parameters, thereby improving detection accuracy. Experimental results on the URPC2020 dataset demonstrate that Online-XKD enhances the detection accuracy of the student model by 3.6 mAP, exceeding initial KD models by 3.3 mAP, and outperforming most existing KD methods in underwater detection tasks. These results confirm the effectiveness and superiority of Online-XKD in applications of underwater object detection, proving its practical significance and effectiveness in enhancing the feature extraction and generalization abilities of lightweight models.

Effectiveness of ELMo embeddings, and semantic models in predicting review helpfulness

Online product reviews (OPR) are a commonly used medium for consumers to communicate their experiences with products during online shopping. Previous studies have investigated the helpfulness of OPRs using frequency-based, linguistic, meta-data, readability, and reviewer attributes. In this study, we explored the impact of robust contextual word embeddings, topic, and language models in predicting the helpfulness of OPRs. In addition, the wrapper-based feature selection technique is employed to select effective subsets from each type of features. Five feature generation techniques including word2vec, FastText, Global Vectors for Word Representation (GloVe), Latent Dirichlet Allocation (LDA), and Embeddings from Language Models (ELMo), were employed. The proposed framework is evaluated on two Amazon datasets (Video games and Health & personal care). The results showed that the ELMo model outperformed the six standard baselines, including the fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model. In addition, ELMo achieved Mean Square Error (MSE) of 0.0887 and 0.0786 respectively on two datasets and MSE of 0.0791 and 0.0708 with the wrapper method. This results in the reduction of 1.43% and 1.63% in MSE as compared to the fine-tuned BERT model on respective datasets. However, the LDA model has a comparable performance with the fine-tuned BERT model but outperforms the other five baselines. The proposed framework demonstrated good generalization abilities by uncovering important factors of product reviews and can be evaluated on other voting platforms.

Feature Engineering for a MIL-STD-1553B LSTM Autoencoder Anomaly Detector

The MIL-STD-1553B data bus protocol is used in both civilian and military aircraft to enable communications between subsystems. These interconnected subsystems are responsible for core services such as communications, flow of instrument data and aircraft control. With aircraft modernization, threat vectors are introduced through increased inter-connectivity internal and external to the aircraft. The resulting potential for exploitation introduces a requirement for an intrusion detection capability in order to maintain the integrity, availability and reliability of data transmitted using the MIL-STD-1553B protocol, safety of the aircraft and overall, to achieve mission assurance. Research in recent years has investigated signature, statistical and machine learning based solutions to detect attacks on MIL-STD-1553B buses. Of the different techniques, those based on machine learning have shown extremely good results. The aim of this research is to improve the performance of an existing Long Short-Term Memory Auto-Encoder by refining the feature engineering phase of its pipeline. The improvement in the detector’s overall effectiveness was accomplished through feature engineering focused on feature generation and selection. Five different attack datasets were used as the starting point, consisting of four different denial of service attacks and one data integrity attack. From initial feature extraction of 155 features, two feature generation techniques were employed to create over 38,000 features as a starting point. Using five different MIL-STD-1553B datasets and three feature selection techniques, fifteen different Long Short-Term Memory Auto-Encoder models were created, trained and evaluated using common performance metrics and compared to those of the original anomaly detector. This research demonstrated marked performance improvement achieved by the feature engineering refinements made in comparison to those of the original model. Equally important, this research also showed a significant reduction in the number of features required to achieve this performance gain. In the context of miliary air operations, the ability to improve detection capabilities with less data is important to the technical solutions that contribute to the achievement of cyber mission assurance.

Correction to: Automated facial expression recognition using exemplar hybrid deep feature generation technique

Correction to: Automated facial expression recognition using exemplar hybrid deep feature generation technique

Automatic detection of Feature Envy and Data Class code smells using machine learning

Code smells in software indicate poor design and implementation choices. Detecting and removing them is critical for sustainable software development. Machine learning (ML) can automate code smell detection. Most ML solutions train models from scratch on code smell datasets, using handcrafted source code metrics as features. Pretrained language models, like BERT, fueled a paradigm shift in natural language processing: from handcrafted features to automatically inferred features and from training models from scratch to using pretrained models. Code embeddings offer the potential to bring a similar paradigm shift to code analysis. Nevertheless, the potential of using pretrained neural code embeddings for code smell detection has yet to be fully explored. To this end, we evaluated ML models trained using different code representations: code metrics and state-of-the-art neural code embeddings (CodeT5 and CuBERT). We experimented with CodeT5 variants (base and small) and explored multiple ways of embedding code snippets (by combining line-level embeddings or passing the entire code snippet as input). We tested our approaches on the tasks of detecting Data Class and Feature Envy on the MLCQ dataset. Considering the results of this study and our previous research, performance-wise, there is no clear winner between using code metrics or code embeddings for different code smell types and programming languages. However, given that, in contrast to code metrics, code embeddings can automatically adapt to new programming constructs and are expected to scale better with dataset size, these models are likely to become the future state-of-the-art feature generation technique for code smell detection.

Human activity recognition for analyzing stress behavior based on Bi-LSTM.

Stress is one of the critical health factors that could be detected by Human Activity Recognition (HAR) which consists of physical and mental health. HAR can raise awareness of self-care and prevent critical situations. Recently, HAR used non-invasive wearable physiological sensors. Moreover, deep learning techniques are becoming a significant tool for analyzing health data. In this paper, we propose a human lifelog monitoring model for stress behavior recognition based on deep learning, which analyses stress levels during activity. The proposed approach considers activity and physiological data for recognizing physical activity and stress levels. To tackle these issues, we proposed a model that utilizes hand-crafted feature generation techniques compatible with a Bidirectional Long Short-Term Memory (Bi-LSTM) based method for physical activity and stress level recognition. We have used a dataset called WESAD, collected using wearable sensors for model evaluation. This dataset presented four levels of stress emotion, including baseline, amusement, stress, and meditation. The following results are from the hand-crafted feature approaches compatible with the bidirectional LSTM model. The proposed model achieves an accuracy of 95.6% and an F1-score of 96.6%. The proposed HAR model efficiently recognizes stress levels and contributes to maintaining physical and mental well-being.

A virtual sample generation method based on manifold learning and a generative adversarial network for soft sensor models with limited data

BackgroundIn the modern industrial process, data-driven-based soft sensor technology plays a key role in intelligent measurement. However, due to the strong dependence of the prediction accuracy on the training data, it can be challenging to apply this technology to particular industrial processes for which obtaining enough training samples is difficult. MethodsTo solve the problem of insufficient training data for soft sensor models, this paper proposes the Potential of Heat-diffusion for Affinity-based Trajectory Embedding and generative adversarial network based virtual sample generation (PGAN-VSG) method, which combines Potential of Heat-diffusion for Affinity-based Trajectory Embedding (PHATE) based feature extraction, virtual feature generation (VFG) techniques, and PHATE based generative adversarial network (PGAN) to generate virtual samples. The methodology of the work consists of several phases. First, the PHATE is deployed to embed the original data into a low-dimensional space to obtain the original feature set, which preserves the local and global structure of the original data. Second, a number of candidate features are randomly generated in the neighborhood space of each original feature, and the features located in the sparse feature region are selected as virtual features. Furthermore, the PGAN with L1 distance loss is used to map the virtual features to the corresponding high-dimensional space to obtain virtual samples. To validate the performance of the proposed PGAN-VSG method, a multilayer perceptron (MLP) model was employed as a soft sensor model to showcase the effectiveness of the proposed approach. This was achieved through both a numerical example and an industrial case study involving the penicillin fermentation process. Significant findingsBy filling the sample scarcity region while ensuring the distribution of generated samples, the virtual sample generation (VSG) method proposed in this paper improves the prediction accuracy of the soft sensor model while also outperforming the classical VSG method.

Automated facial expression recognition using exemplar hybrid deep feature generation technique

Automated facial expression recognition using exemplar hybrid deep feature generation technique

Academic performance warning system based on data driven for higher education.

Academic probation at universities has become a matter of pressing concern in recent years, as many students face severe consequences of academic probation. We carried out research to find solutions to decrease the situation mentioned above. Our research used the power of massive data sources from the education sector and the modernity of machine learning techniques to build an academic warning system. Our system is based on academic performance that directly reflects students' academic probation status at the university. Through the research process, we provided a dataset that has been extracted and developed from raw data sources, including a wealth of information about students, subjects, and scores. We build a dataset with many features that are extremely useful in predicting students' academic warning status via feature generation techniques and feature selection strategies. Remarkably, the dataset contributed is flexible and scalable because we provided detailed calculation formulas that its materials are found in any university or college in Vietnam. That allows any university to reuse or reconstruct another similar dataset based on their raw academic database. Moreover, we variously combined data, unbalanced data handling techniques, model selection techniques, and research to propose suitable machine learning algorithms to build the best possible warning system. As a result, a two-stage academic performance warning system for higher education was proposed, with the F2-score measure of more than 74% at the beginning of the semester using the algorithm Support Vector Machine and more than 92% before the final examination using the algorithm LightGBM.

Exemplar Darknet19 feature generation technique for automated kidney stone detection with coronal CT images

Kidney stone is a commonly seen ailment and is usually detected by urologists using computed tomography (CT) images. It is difficult and time-consuming to detect small stones in CT images. Hence, an automated system can help clinicians to detect kidney stones accurately. In this work, a novel transfer learning-based image classification method (ExDark19) has been proposed to detect kidney stones using CT images. The iterative neighborhood component analysis (INCA) is employed to select the most informative feature vectors and these selected features vectors are fed to the k nearest neighbor (kNN) classifier to detect kidney stones with a ten-fold cross-validation (CV) strategy. The proposed ExDark19 model yielded an accuracy of 99.22% with 10-fold CV and 99.71% using the hold-out validation method. Our results demonstrate that the proposed ExDark19 detect kidney stones over 99% accuracies for two validation techniques. This developed automated system can assist the urologists to validate their manual screening of kidney stones and hence reduce the possible human error.

Shallow Deep Learning using Space-filling Curves for Malware Classification

The incidents of malware attacks are continually increasing at a rapid rate, thanks to the lucrative potential in schemes such as ransomware, credential stealing Trojans and cryptominers. Their explosive growth is compounded by the ease with which variants can be created from original strains. As a result, anti-virus organisations are struggling to keep up, with some reporting upwards of 14 million samples processed per month. These sheer volumes have caused a shift towards machine learning and artificial intelligence in an effort to alleviate the manual burden of analysis and classification. This research presents a novel framework for the classification of malware into distinct family classes through computer vision and deep learning. In the proposed framework, malware binaries are represented in an abstract form as images mapped through mathematical constructs known as space-filling curves. Convolutional neural networks were constructed and applied to the malware images to build predictive models for classification. The models were optimised using an auto-tuning function for the hyper parameters, which included Bayesian Optimisation, Random search and HyperBand, providing an exhaustive search on the hyper parameters. On a training dataset of 13k malware samples from 23 distinct families, the models yielded an average score of 95% for precision, recall and f1-score. The final deep learning model was validated for robustness against a dataset of more recent variants, comprising 12,816 samples from 16 malware families, returning classification scores of 95%, 86% and 90% for precision, recall and f1-score. The final model was demonstrated to outperform a similar benchmark model considerably. The results show the potential of the deep learning framework as a viable solution to the classification of malware, without the need for manually intensive feature generation or invasive processing techniques.

Artificial Intelligence-Based Breast Cancer Diagnosis Using Ultrasound Images and Grid-Based Deep Feature Generator

PurposeBreast cancer is a prominent cancer type with high mortality. Early detection of breast cancer could serve to improve clinical outcomes. Ultrasonography is a digital imaging technique used to differentiate benign and malignant tumors. Several artificial intelligence techniques have been suggested in the literature for breast cancer detection using breast ultrasonography (BUS). Nowadays, particularly deep learning methods have been applied to biomedical images to achieve high classification performances.Patients and MethodsThis work presents a new deep feature generation technique for breast cancer detection using BUS images. The widely known 16 pre-trained CNN models have been used in this framework as feature generators. In the feature generation phase, the used input image is divided into rows and columns, and these deep feature generators (pre-trained models) have applied to each row and column. Therefore, this method is called a grid-based deep feature generator. The proposed grid-based deep feature generator can calculate the error value of each deep feature generator, and then it selects the best three feature vectors as a final feature vector. In the feature selection phase, iterative neighborhood component analysis (INCA) chooses 980 features as an optimal number of features. Finally, these features are classified by using a deep neural network (DNN).ResultsThe developed grid-based deep feature generation-based image classification model reached 97.18% classification accuracy on the ultrasonic images for three classes, namely malignant, benign, and normal.ConclusionThe findings obviously denoted that the proposed grid deep feature generator and INCA-based feature selection model successfully classified breast ultrasonic images.

A Novel Local Feature Generation Technique Based Sound Classification Method for Covid-19 Detection using Lung Breathing Sound

Lung breathing sounds have been used to diagnose many diseases, including Covid-19. Nowadays, Covid-19 has affected daily life worldwide, and it has caused a global pandemic. Generally, computer vision methods have been presented to classify healthy, pneumonia, and Covid-19. They achieved high classification rates on datasets with a limited number of classes without taking into consideration other lung diseases. Our main hypothesis is to detect Covid-19 automatically among other lung diseases by using lung breathing sounds. Therefore, a dataset of lung breathing sound with ten classes has been collected, and a novel lung sounds classification method has been proposed in this paper. This method presents a novel local feature generation technique, and Substitution Box (S-Box) of the present lightweight encryption method is utilized as a pattern. A novel nonlinear pattern is presented based on S-Box, named Present-SBox-Pat (present S-Box pattern). A new pooling-based transformation (maximum tent pooling (MaTP)) is proposed to generate high, middle, and low levels features. It is considered as a preprocessing method of this work. ReliefF and iterative neighbourhood component analysis (RFINCA) selector is used to select the most discriminative and informative features. Two shallow classifiers are used to obtain results. The proposed Present-SBox-Pat and MaTP feature generation network and RFINCA feature selector-based method achieved 95.43% classification accuracy using the SVM classifier. These results demonstrated the success of techniques in generating and selecting features that facilitate the task of classifiers.

An automated COVID-19 detection based on fused dynamic exemplar pyramid feature extraction and hybrid feature selection using deep learning

The new coronavirus disease known as COVID-19 is currently a pandemic that is spread out the whole world. Several methods have been presented to detect COVID-19 disease. Computer vision methods have been widely utilized to detect COVID-19 by using chest X-ray and computed tomography (CT) images. This work introduces a model for the automatic detection of COVID-19 using CT images. A novel handcrafted feature generation technique and a hybrid feature selector are used together to achieve better performance. The primary goal of the proposed framework is to achieve a higher classification accuracy than convolutional neural networks (CNN) using handcrafted features of the CT images. In the proposed framework, there are four fundamental phases, which are preprocessing, fused dynamic sized exemplars based pyramid feature generation, ReliefF, and iterative neighborhood component analysis based feature selection and deep neural network classifier. In the preprocessing phase, CT images are converted into 2D matrices and resized to 256 × 256 sized images. The proposed feature generation network uses dynamic-sized exemplars and pyramid structures together. Two basic feature generation functions are used to extract statistical and textural features. The selected most informative features are forwarded to artificial neural networks (ANN) and deep neural network (DNN) for classification. ANN and DNN models achieved 94.10% and 95.84% classification accuracies respectively. The proposed fused feature generator and iterative hybrid feature selector achieved the best success rate, according to the results obtained by using CT images.

An Extensive Study on Traditional-to-Recent Transformation on Face Recognition System

The face is the most visible biometric feature considered in manual and automated systems to identify individuals. In recent years, the inventions of low-cost high-resolution mobile cameras and surveillance systems have increased the usage and popularity of facial recognition systems. Today, various mobile apps, ICT systems, electronic devices, and cloud-based systems are using facial verification to gain access and authorization based security. Now, the facial recognition system has become a generalized authentication system instead of a specialized capability of specialized applications. This increasing scope and applications are reflected as the challenges and criticalities that exist in the real environment. The technological transformation was investigated by the researchers in image types, facial capturing, facial rectification, feature generation, and classification methods and techniques of face recognition systems. This paper has provided an extensive study on each stage of standard FRS (Face Recognition System). The methods and measures provided by researchers for improving and optimizing face normalization, segmentation, feature generation, and face recognition are provided in this paper. Each of the methods is also defined along with the performance, accuracy, and robustness against various addressed challenges. The paper has provided a map between the traditional and recent methods to explore the advancement in facial verification systems.

Review on Fault Detection and Diagnosis Feature Engineering in Building Heating, Ventilation, Air Conditioning and Refrigeration Systems

Faults are inevitable in building energy systems, such as heating, ventilation, air conditioning and refrigeration systems. With the increasing utilization of these systems, their fault detection and diagnosis has become more significant for maintaining their operation and performance. The rapid development of data analytics has led to fault detection and diagnosis using data-based algorithms considering building intelligence. Feature engineering, which focuses on generating near minimum and optimal model inputs from the original dataset, is a fundamental technique to balance efficiency and accuracy of fault detection and diagnosis models. The generated inputs are fault features which ensures a better description of fault operations owing to their stronger fault indicative capability than original data. However, since most feature engineering research has been implemented alongside the development of data-based algorithms, most studies fail to effectively distinguish and understand their roles in fault detection and diagnosis models. To fill this research gap, this study presented the problems and mechanisms associated with feature engineering, comprehensively reviewed about 200 papers on the topic of feature engineering for heating, ventilation, air conditioning and refrigeration system fault detection and diagnosis tasks over the past 15 years. Firstly, feature engineering studies are divided according to their feature-generation technique, into manual and automated techniques. Next, feature engineering studies are analysed in terms of data type, system type, fault type, operation statue, methods and fault features. The desirable characteristics of feature engineering works are then discussed in terms of their capability of rapidly generating indicative, decoupled, interpretable and new fault features to enhance fault detection and diagnosis accuracy; the efficiency, reliability and robustness of feature engineering process; the mutual adaptability between feature engineering and fault detection and diagnosis; and their widespread applicability for more fault types and system operations. The challenges affecting feature engineering studies are discussed in terms of data volume, data diversity and quality, along with the performance evaluation of feature engineering with respect to feature engineering algorithms, fault detection and diagnosis models, fault features and online application constraints. Future work should aim to design a hybrid, heuristic, robust and automated feature engineering strategy under the guidance of expert knowledge and practical application constraints that consider the relationships between fault-related features and real-time fault impacts with energy consumption, occupants' thermal comfort, etc.

Voxel Weight Matrix-Based Feature Extraction for Biomedical Applications

Functional Magnetic Resonance Imaging (fMRI) is an emerging medical tool used to measure brain activities that were induced normally such as cognitive states (e.g., reading a sentence or viewing a picture) or abnormally (e.g., brain activity occurs after a stroke or brain injury). These measured data can be used to construct a model via machine learning techniques to predict the occurrence of a certain cognitive behavior or brain disease. The difficulty of this prediction problem can be summarized in two points: first, the size of the dataset is very small due to the small number of subjects (i.e., patients) who can contribute to these research-based experiments. Second, the size of the feature vector resulted from these medical tools is very large compared to the few number of samples that were collected. One possible way to overcome these obstacles is to develop a feature generation methodology that can produce a small-sized and descriptive feature vector that may improve the overall prediction performance. Motivated by these considerations, this paper proposes a novel feature generation methodology termed Voxel Weight Matrix (VWM) method. This feature generation technique can transform the original high-dimensional feature vector to a two-dimensional discriminative feature domain. The main contribution of this feature generation technique is its ability to represent the statistical measures of the original feature vector via two-dimensional feature vector. After generating the VWM-based feature set, various classification tools such as logistic regression (LR) models and Support Vector Machine (SVM) are used for cognitive state prediction based on publicly available fMRI dataset called state/plus dataset. The classification models with the proposed VWM features outperformed the best two reported prediction models associated with the star/plus dataset with an average accuracy of 99.8%. To further illustrate the effectiveness of the proposed feature generation methodology, another publicly available Electroencephalography (EEG) dataset are used for Epileptic Seizure Prediction.

Cross-Domain Deep Visual Feature Generation for Mandarin Audio–Visual Speech Recognition

There has been a long term interest in using visual information to improve automatic speech recognition (ASR) system performance. Both audio and visual information are required in conventional audio visual speech recognition (AVSR) systems. This limits their wider applications when visual modality is not present. To this end, one possible solution is to use acoustic-to-visual (A2V) inversion techniques to generate visual features. Previous research in this direction used synthetic acoustic-articulatory parallel data in inversion model training. The acoustic mismatch between the audio-visual (AV) parallel data and target data was not considered. In addition, the target language to apply these technologies has been focused on English. In this article, a real 3D Audio-Visual Mandarin Continuous Speech (3DAV-MCS) corpus was used to train deep neural network based A2V inversion models. Cross-domain adaptation of the inversion models allows suitable visual features to be generated from acoustic data of mismatched domains. The proposed cross-domain deep visual feature generation techniques were evaluated on two state-of-the-art Mandarin speech recognition tasks: DAPRA GALE broadcast transcription and BOLT conversational telephone speech recognition. The AVSR systems constructed using the cross-domain generated visual features consistently outperformed the baseline convolutional neural network (CNN) ASR systems by up to 3.3% absolute (9.1% relative) character error rate (CER) reductions after both speaker adaptive training and sequence discriminative training were performed.

Improving IoT Predictions through the Identification of Graphical Features.

IoT sensor networks have an inherent graph structure that can be used to extract graphical features for improving performance in a variety of prediction tasks. We propose a framework that represents IoT sensor network data as a graph, extracts graphical features, and applies feature selection methods to identify the most useful features that are to be used by a classifier for prediction tasks. We show that a set of generic graph-based features can improve performance of sensor network predictions without the need for application-specific and task-specific feature engineering. We apply this approach to three different prediction tasks: activity recognition from motion sensors in a smart home, demographic prediction from GPS sensor data in a smart phone, and activity recognition from GPS sensor data in a smart phone. Our approach produced comparable results with most of the state-of-the-art methods, while maintaining the additional advantage of general applicability to IoT sensor networks without using sophisticated and application-specific feature generation techniques or background knowledge. We further investigate the impact of using edge-transition times, categorical features, different sensor window sizes, and normalization in the smart home domain. We also consider deep learning approaches, including the Graph Convolutional Network (GCN), for the elimination of feature engineering in the smart home domain, but our approach provided better performance in most cases. We conclude that the graphical feature-based framework that is based on IoT sensor categorization, nodes and edges as features, and feature selection techniques provides superior results when compared to the non-graph-based features.