Manual Feature Extraction Research Articles

Optimizing Curriculum Vitae Concordance: A Comparative Examination of Classical Machine Learning Algorithms and Large Language Model Architectures

Digital recruitment systems have revolutionized the hiring paradigm, imparting exceptional efficiencies and extending the reach for both employers and job seekers. This investigation scrutinized the efficacy of classical machine learning methodologies alongside advanced large language models (LLMs) in aligning resumes with job categories. Traditional matching techniques, such as Logistic Regression, Decision Trees, Naïve Bayes, and Support Vector Machines, are constrained by the necessity of manual feature extraction, limited feature representation, and performance degradation, particularly as dataset size escalates, rendering them less suitable for large-scale applications. Conversely, LLMs such as GPT-4, GPT-3, and LLAMA adeptly process unstructured textual content, capturing nuanced language and context with greater precision. We evaluated these methodologies utilizing two datasets comprising resumes and job descriptions to ascertain their accuracy, efficiency, and scalability. Our results revealed that while conventional models excel at processing structured data, LLMs significantly enhance the interpretation and matching of intricate textual information. This study highlights the transformative potential of LLMs in recruitment, offering insights into their application and future research avenues.

An Effective Deep Learning Framework for Fall Detection: Model Development and Study Design.

Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors-based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning-based FDSs using manual feature extraction, and deep learning (DL)-based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy. This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities. Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model. The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%). This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.

Decoding micro-electrocorticographic signals by using explainable 3D convolutional neural network to predict finger movements

BackgroundElectroencephalography (EEG) and electrocorticography (ECoG) recordings have been used to decode finger movements by analyzing brain activity. Traditional methods focused on single bandpass power changes for movement decoding, utilizing machine learning models requiring manual feature extraction. New methodThis study introduces a 3D convolutional neural network (3D-CNN) model to decode finger movements using ECoG data. The model employs adaptive, explainable AI (xAI) techniques to interpret the physiological relevance of brain signals. ECoG signals from epilepsy patients during awake craniotomy were processed to extract power spectral density across multiple frequency bands. These data formed a 3D matrix used to train the 3D-CNN to predict finger trajectories. ResultsThe 3D-CNN model showed significant accuracy in predicting finger movements, with root-mean-square error (RMSE) values of 0.26–0.38 for single finger movements and 0.20–0.24 for combined movements. Explainable AI techniques, Grad-CAM and SHAP, identified the high gamma (HG) band as crucial for movement prediction, showing specific cortical regions involved in different finger movements. These findings highlighted the physiological significance of the HG band in motor control. Comparison with existing methodsThe 3D-CNN model outperformed traditional machine learning approaches by effectively capturing spatial and temporal patterns in ECoG data. The use of xAI techniques provided clearer insights into the model's decision-making process, unlike the "black box" nature of standard deep learning models. ConclusionsThe proposed 3D-CNN model, combined with xAI methods, enhances the decoding accuracy of finger movements from ECoG data. This approach offers a more efficient and interpretable solution for brain-computer interface (BCI) applications, emphasizing the HG band's role in motor control.

Puppet Dynasty Recognition System Based on MobileNetV2.

Traditional image classification usually relies on manual feature extraction; however, with the rapid development of artificial intelligence and intelligent vision technology, deep learning models such as CNNs can automatically extract key features from input images to achieve efficient classification. This study focuses on the application of lightweight separable convolutional neural networks in domain-specific image classification tasks. In this paper, we discuss how to use the SSDLite object detection algorithm combined with the MobileNetV2 lightweight convolutional architecture for puppet dynasty recognition from images-a novel and challenging task. By constructing a system that combines object detection and image classification, we aimed to solve the problem of automatic puppet dynasty recognition to reduce manual intervention and improve recognition efficiency and accuracy. We hope that this will have significant implications in the fields of cultural protection and art history research.

An improved 3D-SwinT-CNN network to evaluate the fermentation degree of black tea

Fermentation is a key process in forming the flavor quality of black tea. Evaluating the degree of fermentation during black tea processing is difficult. This paper proposes an improved 3D-SwinT-CNN network for the end-to-end processing of black tea's hyperspectral images to evaluate the degree of fermentation. The model incorporates dilated convolution and a shifted window self-attention mechanism, expanding the network's receptive field and capturing both local spatial-spectral and global features of black tea hyperspectral images. The accuracy is 98.13% on the test set. Compared to manual feature extraction methods, the accuracy improved by 3.45%. Compared to baseline 3D-CNNs, 3D-SwinT-CNN demonstrates superior spatial-spectral feature extraction, achieving an average accuracy improvement of 10.17%. Ablation experiments were conducted to further verify the effectiveness of the introduced modules. The proposed 3D-SwinT-CNN aims to establish a research foundation for online evaluation of black tea's fermentation degree.

Network traffic classification based‐ masked language regression model using CNN

SummaryNetwork traffic classification task has become increasingly challenging. The objective behind this classification is to effectively handle bandwidth, prioritize certain types of traffic, enhance application performance, and more. In recent times, there has been a surge in exploring deep learning approaches for network traffic categorization. However, these models demand substantial volumes of training data. Additionally, many classification methods necessitate manual feature extraction, a process that is not only time‐consuming but also laborious. Addressing the challenge of identifying optimal features to enhance classification accuracy, this work introduces a deep learning model designed for effective classification of network traffic. The model comprises the following key stages: (a) The dataset involves TCP flows captured from running different network stress and web crawling tools, (b) Pre‐processing for removal of anomalies and noises using Label Encoder and OneHotEncoder, (c) The utilization of K‐BERT for feature extraction aims to retrieve local spatial–temporal features, (d) feature selection using linear regression model (LASSO) and finally, and (e) The classification of network traffic involves neural network. The model serves to enhance the precision and efficiency of the classification mission. Through comprehensive experimental analysis, it was observed that the Masked Language‐based Regression model surpassed other referenced models, achieving an exceptional accuracy of 0.97.

Enhancing Hypotension Prediction in Real-time Patient Monitoring Through Deep Learning: A Novel Application of XResNet with Contrastive Learning and Value Attention Mechanisms.

The precise prediction of hypotension is vital for advancing preemptive patient care strategies. Traditional machine learning approaches, while instrumental in this field, are hampered by their dependence on structured historical data and manual feature extraction techniques. These methods often fall short of recognizing the intricate patterns present in physiological signals. Addressing this limitation, our study introduces an innovative application of deep learning technologies, utilizing a sophisticated end-to-end architecture grounded in XResNet. This architecture is further enhanced by the integration of contrastive learning and a value attention mechanism, specifically tailored to analyze arterial blood pressure (ABP) waveform signals. Our approach improves the performance of hypotension prediction over the existing state-of-theart ABP model [7]. This research represents a step towards optimizing patient care, embodying the next generation of AI-driven healthcare solutions. Through our findings, we demonstrate the promise of deep learning in overcoming the limitations of conventional prediction models, thereby offering an avenue for enhancing patient outcomes in clinical settings.

Multiclass Text Classification of Indonesian Short Message Service (SMS) Spam using Deep Learning Method and Easy Data Augmentation

The ease of using Short Message Service (SMS) has brought the issue of SMS spam, characterized by unsolicited and unwanted. Many studies have been conducted utilizing machine learning methods to build models capable of classifying SMS Spam to overcome this problem. However, most of these studies still rely on traditional methods, with limited exploration of deep learning-based approaches. Whereas traditional methods have a limitation compared to deep learning, which performs manual feature extraction. Moreover, many of these studies only focus on binary classification rather than multiclass SMS classification which can provide more detailed classification results. The aim of this research is to analyze deep learning model for multiclass Indonesian SMS spam classification with six categories and to assess the effectiveness of the text augmentation method in addressing data imbalace issues arising from the increased number of SMS categories. The research method used were Indonesian version of Bidirectional Encoder Representations from Transformers (IndoBERT) model and exploratory data analysis (EDA) augmentation technique to address imbalance dataset issue. The evaluation is conducted by comparing the performance of the IndoBERT model on the dataset and applying EDA techniques to enhance the representation of minority classes. The result of this research shows that IndoBERT achieves 91% accuracy rate in classifying SMS spam. Furthermore, the use of EDA technique results in significant improvement in f1-score, with an average 12% increase in minority classes. Overall model accuracy also improves to 93% after EDA implementation. This research concludes that IndoBERT is effective for multiclass SMS spam classification, and the EDA is beneficial in handling imbalanced data, contributing to the enhancement of model performances.

Radio frequency fingerprint authentication based on feature fusion and contrastive learning

Radio frequency fingerprints (RFFs) are inherent attributes of wireless devices caused by differences in electronic components, which can serve as unique device identifiers and effective means of achieving physical layer authentication. However, traditional RFF approaches predominantly depend on manual feature extraction, which struggles to effectively distinguish devices due to its limited generalization capability as the number of devices grows. Additionally, current machine learning-based methods are designed for scenarios with a fixed set of trained devices while they fail to handle unknown devices. In this paper, we propose a novel contrastive learning-based RFF authentication framework to address the above challenges. The proposed framework integrates both manual feature extraction and deep learning-based techniques to enhance the generalization ability of RFFs, thereby enabling efficient differentiation among a vast number of devices. To further address the limitations of traditional machine learning approaches in dealing with unknown devices, we incorporate contrastive learning techniques into RFF authentication. By employing an input construction strategy, we generate positive and negative sample pairs of the RFFs to train an RFF compression network, allowing it to learn pivotal features within the fused RFFs. This process results in highly discriminative representations of the fused RFFs, ensuring effective authentication of open-set devices. The experimental results demonstrate that our method achieves an accuracy of 98% in open-set device classification even in the most complex experimental scenario, significantly outperforming other benchmark methods.

Mental fatigue recognition study based on 1D convolutional neural network and short-term ECG signals.

Mental fatigue has become a non-negligible health problem in modern life, as well as one of the important causes of social transportation, production and life accidents. Fatigue detection based on traditional machine learning requires manual and tedious feature extraction and feature selection engineering, which is inefficient, poor in real-time, and the recognition accuracy needs to be improved. In order to recognize daily mental fatigue level more accurately and in real time, this paper proposes a mental fatigue recognition model based on 1D Convolutional Neural Network (1D-CNN), which inputs 1D raw ECG sequences of 5s duration into the model, and can directly output the predicted fatigue level labels. The fatigue dataset was constructed by collecting the ECG signals of 22 subjects at three time periods: 9:00-11:00 a.m., 14:00-16:00 p.m., and 19:00-21:00 p.m., and then inputted into the 19-layer 1D-CNN model constructed in the present study for the classification of mental fatigue in three grades. The results showed that the model was able to recognize the fatigue levels effectively, and its accuracy, precision, recall, and F1 score reached 98.44%, 98.47%, 98.41%, and 98.44%, respectively. This study further improves the accuracy and real-time performance of recognizing multi-level mental fatigue based on electrocardiography, and provides theoretical support for real-time fatigue monitoring in daily life.

Unsupervised autoencoders with features in the electromechanical impedance domain for early damage assessment in FRP-strengthened concrete elements

This paper presents the development of a robust automatic diagnosis technique that uses raw Electro-Mechanical Impedance (EMI) signals and deep autoencoder models to detect damage in fiber-reinforced-polymers (FRP) strengthened reinforced concrete (RC) elements, for which the most common failure modes occur in a sudden and brittle way by debonding. The contribution of this work is threefold: First, for the first time, two autoencoder models, convolutional and fully connected, based on an unsupervised learning framework supplemented by appropriate pre-processing techniques, are proposed for effective tracking of FRP-strengthened RC elements from raw EMI response variations in different locations of the auscultated structure; their implementation is also extensively investigated. The proposed framework consists of two main components, namely, dimensionality reduction and relationship learning. The first component is to reduce the dimensionality of the raw EMI signal while preserving the necessary information required, and the second component is to perform the relationship learning between the features with the reduced dimensionality and the stiffness reduction parameters of the structure. The approach is beneficial as only the EMI spectrum from the healthy structure state is considered for the training of the autoencoders. Second, the superior performance of the proposed framework is demonstrated. The results show that the proposed technique can accurately detect minor damage in its earliest stages for this kind of strengthened structures, while removing the need for manual or signal processing-based damage sensitive feature extraction from EMI signals for damage diagnosis. Finally, research presented in this work can potentially open up new opportunities for successful condition monitoring of this type of strengthened structures.

A Benchmark for Morphological Segmentation in Uyghur and Kazakh

Morphological segmentation and stemming are foundational tasks in natural language processing. They have become effective ways to alleviate data sparsity in agglutinative languages because of the nature of agglutinative language word formation. Uyghur and Kazakh, as typical agglutinative languages, have made significant progress in morphological segmentation and stemming in recent years. However, the evaluation metrics used in previous work are character-level based, which may not comprehensively reflect the performance of models in morphological segmentation or stemming. Moreover, existing methods avoid manual feature extraction, but the model’s ability to learn features is inadequate in complex scenarios, and the correlation between different features has not been considered. Consequently, these models lack representation in complex contexts, affecting their effective generalization in practical scenarios. To address these issues, this paper redefines the morphological-level evaluation metrics: F1-score and accuracy (ACC) for morphological segmentation and stemming tasks. In addition, two models are proposed for morpheme segmentation and stem extraction tasks: supervised model and unsupervised model. The supervised model learns character and contextual features simultaneously, then feature embeddings are input into a Transformer encoder to study the correlation between character and context embeddings. The last layer of the model uses a CRF or softmax layer to determine morphological boundaries. In unsupervised learning, an encoder–decoder structure introduces n-gram correlation assumptions and masked attention mechanisms, enhancing the correlation between characters within n-grams and reducing the impact of characters outside n-grams on boundaries. Finally, comprehensive comparative analyses of the performance of different models are conducted from various points of view. Experimental results demonstrate that: (1) The proposed evaluation method effectively reflects the differences in morphological segmentation and stemming for Uyghur and Kazakh; (2) Learning different features and their correlation can enhance the model’s generalization ability in complex contexts. The proposed models achieve state-of-the-art performance on Uyghur and Kazakh datasets.

Interpretable End-to-End heart sound classification

Heart sound analysis is a non-invasive and economical technique that can aid in diagnosing cardiovascular disease. A novel End-to-End heart sound classification method was proposed in this paper, in which a combination of multi-scale dense network and multi-head recurrent neural network technology was used. It can be used to diagnose congenital heart disease (CHD) without using the manual extraction of features. An Fβ score of 94.33% and an accuracy of 94.41% were achieved by the method on dataset A, which consisted of 1,000 individuals and 5,000 signals. Similarly, the widely used dataset B (Physio Net/CinC 2016 dataset), comprising 764 individuals and 3,240 signals, resulted in an Fβ score of 93.75% and an accuracy of 92.97%. The results show the proposed method had a significant potential to assist in diagnosing CHD. The SHAP algorithm which is a kind of Interpretable method was applied in this study to interpret the prediction results of model. It was shown that the model’s prediction process is similar to a doctor’s diagnosing mode.

An intelligent biosensing platform using phase space reconstruction‐assisted convolutional neural network for drug‐induced cardiotoxicity assessment

AbstractDrug‐induced cardiotoxicity often leads to patient deaths and drug recalls. Interdigitated electrode (IDE)‐based cellular impedance detection instrument has been integrated with intelligent algorithms to screen cardiotoxicity based on cardiomyocytes. These intelligent biosensing systems generally employ traditional machine learning methods to assess drug‐induced cardiotoxicity by analyzing cardiomyocytes mechanical beating signals. However, modern deep learning methods with robustness and flexibility have not been integrated in IDE‐based platform to screen cardiotoxicity. Here, for the first time, we implemented deep convolutional neural network (CNN) to analyze cardiomyocytes mechanical beating signals for cardiotoxicity assessment. This method can eliminate the feature engineering procedures, such as manual design and extraction of signal features required by traditional machine learning methods. To facilitate two‐dimensional (2‐D) CNN analysis, we utilized phase space reconstruction to convert one‐dimensional beating signals into 2‐D image representations as well as take into account nonlinear dynamic information. The phase space reconstruction‐assisted convolutional neural network (PSRCNN) is capable of accurately categorizing drug‐induced cardiotoxicities and predicting cardiotoxicity levels. It obtains accuracies ranging from 0.82 to 0.99 when recognizing the cardiotoxicity of newly developed drugs, which are represented by drugs that are not used during model training. Furthermore, we explore in depth to compare the performance of CNN with other traditional machine learning methods. The PSRCNN method can achieve higher accuracies when compared to other methods. The PSRCNN‐based biosensing platform is highly potential in improving the efficiency and accuracy of high‐throughput screening of newly developed drugs for cardiotoxicity during drug discovery.

The Prediction of Incremental Damage on Optics from the Final Optic Assembly in an ICF High-Power Laser Facility

High-power laser facilities necessitate predicting incremental damage to final optics to identify evolving damage trends. In this study, we propose a surface damage detection method utilizing image segmentation employing ResNet-18 and a damage area estimation network employing U-Net++. Paired sets of online and offline images of optics obtained from a large laser facility are used to train the network. The trends of varying damage could be identified by incorporating additional experimental parameters. A key advantage of the proposed method is that the network can be trained end to end on small samples, eliminating the need for manual labeling or feature extraction. The software developed based on these models can facilitate the daily inspection and maintenance of optics in large laser facilities. By effectively applying deep learning techniques, we successfully addressed the challenges faced by traditional methods in handling complex environments, achieving the accurate identification and prediction of damages on optics.

Utilizing a CNN-RNN machine learning approach for forecasting time-series outlet fluid temperature monitoring by long-term operation of BHEs system

The Borehole Heat Exchanger (BHE) plays a pivotal role in enhancing heat exchange efficiency within Ground Source Heat Pump (GSHP) systems. The accurate prediction of the BHE's outlet fluid temperature is crucial for optimizing GSHP performance, energy storage, and resource conservation. However, conventional machine learning methods encounter challenges in manual feature extraction, learning complex nonlinear relationships, and adapting to real-world scenarios. To address these limitations, this research proposes a crossbreed model integrating Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) architectures to forecast long-term outlet fluid temperature in BHE systems. The model framework encompasses data preprocessing, utilizing refined data in the CNN module for temporal feature extraction, subsequently passed to the RNN module to capture sequential and temporal patterns from each dataset. Specifically, the advanced CNN-RNN architecture is designed to establish a comprehensive input-output mapping, leveraging essential input features such as inlet fluid, ambient air, and subsurface temperatures at varying depths (0, 10, and 20 m). Performance evaluation metrics, including R2, RMSE, MAE, and AARE, are employed to compare and assess prediction accuracy across various models, including LSTM, CNN, and SimpleRNN. The obtained results demonstrate the superior performance of the proposed model, achieving an RSME of 0.818, MAE of 0.642, AARE of 0.0305, and an R2 value of 98.75 %. This surpasses the performance of traditional prediction models (LSTM, CNN, and SimpleRNN) by 3.01 %, 5.80 %, and 19.52 %, respectively. Notably, the remarkably low MAE of 0.642 exhibited by a CNN-RNN model underscores its capability to outperform traditional approaches, especially when handling large datasets. These findings emphasize the significance of the developed model in facilitating efficient operation, positioning it as a valuable tool for advancing the long-term sustainability of BHE systems.

Classification of Driver Cognitive Load in Conditionally Automated Driving: Utilizing Electrocardiogram-Based Spectrogram with Lightweight Neural Network

With the development of conditionally automated driving, drivers will be allowed to perform non-driving-related tasks. Under such circumstances, continuous monitoring of driver cognitive load will play an increasingly important role in ensuring that drivers have sufficient mental resources to take over control of the vehicle should the driving automation fail. However, estimation of cognitive load is challenging because of the difficulties in identifying high-level feature representation and accounting for interindividual differences. Physiological measures are believed to be promising candidates for cognitive load estimation in partially automated vehicles. However, current estimation methods are mainly based on the manual feature extraction of time- or frequency-domain indicators from physiological signals, which may not adapt to dynamic driving conditions. With the development of deep learning, the neural network has shown good performance in automatically capturing high-level features from input data. Inspired by this, we adopted a novel approach to classify driver cognitive load based on electrocardiogram (ECG) spectrograms, in which the driver’s ECG signal was collected and transformed into a 2D spectrogram by a short-time Fourier transform. A squeeze-and-excitation network-based deep-learning framework that can capture high-level features and pays more attention to the cognition-related features of the spectrogram was proposed for classification. Experiments on a publicly available dataset demonstrated that our model achieved an accuracy of 96.76% in differentiating two levels of cognitive load for a within-subject evaluation and 71.50% accuracy with an across-subjects evaluation. The results demonstrated the feasibility of detecting drivers’ cognitive load through deep learning using ECG spectrogram alone.

Motor Imagery EEG Signal Classification Using Distinctive Feature Fusion with Adaptive Structural LASSO

A motor imagery brain–computer interface connects the human brain and computers via electroencephalography (EEG). However, individual differences in the frequency ranges of brain activity during motor imagery tasks pose a challenge, limiting the manual feature extraction for motor imagery classification. To extract features that match specific subjects, we proposed a novel motor imagery classification model using distinctive feature fusion with adaptive structural LASSO. Specifically, we extracted spatial domain features from overlapping and multi-scale sub-bands of EEG signals and mined discriminative features by fusing the task relevance of features with spatial information into the adaptive LASSO-based feature selection. We evaluated the proposed model on public motor imagery EEG datasets, demonstrating that the model has excellent performance. Meanwhile, ablation studies and feature selection visualization of the proposed model further verified the great potential of EEG analysis.

Development of a machine vision-based weight prediction system of butterhead lettuce (Lactuca sativa L.) using deep learning models for industrial plant factory.

Indoor agriculture, especially plant factories, becomes essential because of the advantages of cultivating crops yearly to address global food shortages. Plant factories have been growing in scale as commercialized. Developing an on-site system that estimates the fresh weight of crops non-destructively for decision-making on harvest time is necessary to maximize yield and profits. However, a multi-layer growing environment with on-site workers is too confined and crowded to develop a high-performance system.This research developed a machine vision-based fresh weight estimation system to monitor crops from the transplant stage to harvest with less physical labor in an on-site industrial plant factory. A linear motion guide with a camera rail moving in both the x-axis and y-axis directions was produced and mounted on a cultivating rack with a height under 35 cm to get consistent images of crops from the top view. Raspberry Pi4 controlled its operation to capture images automatically every hour. The fresh weight was manually measured eleven times for four months to use as the ground-truth weight of the models. The attained images were preprocessed and used to develop weight prediction models based on manual and automatic feature extraction. The performance of models was compared, and the best performance among them was the automatic feature extraction-based model using convolutional neural networks (CNN; ResNet18). The CNN-based model on automatic feature extraction from images performed much better than any other manual feature extraction-based models with 0.95 of the coefficients of determination (R2) and 8.06 g of root mean square error (RMSE). However, another multiplayer perceptron model (MLP_2) was more appropriate to be adopted on-site since it showed around nine times faster inference time than CNN with a little less R2 (0.93). Through this study, field workers in a confined indoor farming environment can measure the fresh weight of crops non-destructively and easily. In addition, it would help to decide when to harvest on the spot.

An end-to-end gait recognition system for covariate conditions using custom kernel CNN

Gait recognition is the identification of individuals based on how they walk. It can identify an individual of interest without their intervention, making it better suited for surveillance from afar. Computer-aided silhouette-based gait analysis is frequently employed due to its efficiency and effectiveness. However, covariate conditions have a significant influence on individual recognition because they conceal essential features that are helpful in recognizing individuals from their walking style. To address such issues, we proposed a novel deep-learning framework to tackle covariate conditions in gait by proposing regions subject to covariate conditions. The features extracted from those regions will be neglected to keep the model's performance effective with custom kernels. The proposed technique sets aside static and dynamic areas of interest, where static areas contain covariates, and then features are learnt from the dynamic regions unaffected by covariates to effectively recognize individuals. The features were extracted using three customized kernels, and the results were concatenated to produce a fused feature map. Afterward, CNN learns and extracts the features from the proposed regions to recognize an individual. The suggested approach is an end-to-end system that eliminates the requirement for manual region proposal and feature extraction, which would improve gait-based identification of individuals in real-world scenarios. The experimentation is performed on publicly available dataset i.e. CASIA A, and CASIA C. The findings indicate that subjects wearing bags produced 90 % accuracy, and subjects wearing coats produced 58 % accuracy. Likewise, recognizing individuals with different walking speeds also exhibited excellent results, with an accuracy of 94 % for fast and 96 % for slow-paced walk patterns, which shows improvement compared to previous deep learning methods.© 2017 Elsevier Inc. All rights reserved.