Traditional Feature-based Approaches Research Articles

Weed Detection and Classification with Computer Vision Using a Limited Image Dataset

In agriculture, as precision farming increasingly employs robots to monitor crops, the use of weeding and harvesting robots is expanding the need for computer vision. Currently, most researchers and companies address these computer vision tasks with CNN-based deep learning. This technology requires large datasets of plant and weed images labeled by experts, as well as substantial computational resources. However, traditional feature-based approaches to computer vision can extract meaningful parameters and achieve comparably good classification results with only a tenth of the dataset size. This study presents these methods and seeks to determine the minimum number of training images required to achieve reliable classification. We tested the classification results with 5, 10, 20, 40, 80, and 160 images per weed type in a four-class classification system. We extracted shape features, distance transformation features, color histograms, and texture features. Each type of feature was tested individually and in various combinations to determine the best results. Using six types of classifiers, we achieved a 94.56% recall rate with 160 images per weed. Better results were obtained with more training images and a greater variety of features.

Using explainable AI to investigate electrocardiogram changes during healthy aging-From expert features to raw signals.

Cardiovascular diseases remain the leading global cause of mortality. Age is an important covariate whose effect is most easily investigated in a healthy cohort to properly distinguish the former from disease-related changes. Traditionally, most of such insights have been drawn from the analysis of electrocardiogram (ECG) feature changes in individuals as they age. However, these features, while informative, may potentially obscure underlying data relationships. In this paper we present the following contributions: (1) We employ a deep-learning model and a tree-based model to analyze ECG data from a robust dataset of healthy individuals across varying ages in both raw signals and ECG feature format. (2) We use explainable AI methods to identify the most discriminative ECG features across age groups.(3) Our analysis with tree-based classifiers reveals age-related declines in inferred breathing rates and identifies notably high SDANN values as indicative of elderly individuals, distinguishing them from younger adults. (4) Furthermore, the deep-learning model underscores the pivotal role of the P-wave in age predictions across all age groups, suggesting potential changes in the distribution of different P-wave types with age. These findings shed new light on age-related ECG changes, offering insights that transcend traditional feature-based approaches.

Integrated Analysis of Machine Learning and Deep Learning in Silkworm Pupae (Bombyx mori) Species and Sex Identification

Hybrid pairing of the corresponding silkworm species is a pivotal link in sericulture, ensuring egg quality and directly influencing silk quantity and quality. Considering the potential of image recognition and the impact of varying pupal postures, this study used machine learning and deep learning for global modeling to identify pupae species and sex separately or simultaneously. The performance of traditional feature-based approaches, deep learning feature-based approaches, and their fusion approaches were compared. First, 3600 images of the back, abdomen, and side postures of 5 species of male and female pupae were captured. Next, six traditional descriptors, including the histogram of oriented gradients (HOG), and six deep learning descriptors, including ConvNeXt-S, were utilized to extract significant species and sex features. Finally, classification models were constructed using the multilayer perceptron (MLP), support vector machine, and random forest. The results indicate that the {HOG + ConvNeXt-S + MLP} model excelled, achieving 99.09% accuracy for separate species and sex recognition and 98.40% for simultaneous recognition, with precision–recall and receiver operating characteristic curves ranging from 0.984 to 1.0 and 0.996 to 1.0, respectively. In conclusion, it can capture subtle distinctions between pupal species and sexes and shows promise for extensive application in sericulture.

Deployment of the deep learning fusion method to emotional semantic evaluation of natural language

The emotional semantic evaluation of natural language plays a crucial role in sentiment analysis. Deep learning methods have shown great potential in capturing the complex relationships between words and emotions. This paper proposes a deep learning fusion method for deploying emotional semantic evaluation. The technique combines multiple deep learning architectures to capture local and global contextual information, including Bidirectional Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) networks, and Self-Attention mechanisms. Pretrained GloVe word embedding’s utilized to enhance word representation. A novel fusion layer combines the outputs of individual models; employing self-attention means to assign weights dynamically. This allows the model to weigh the importance of different representations in the final prediction. Benchmark movie review (MR) for sentiment analysis and emotion classification tasks are used to evaluate the proposed method. Experimental results demonstrate superior performance compared to individual deep learning models and traditional feature-based approaches. The proposed fusion method effectively captures the nuances of emotional semantics in natural language, leading to more accurate and nuanced evaluations.

Cross-Modal Image Registration via Rasterized Parameter Prediction for Object Tracking

Object tracking requires heterogeneous images that are well registered in advance, with cross-modal image registration used to transform images of the same scene generated by different sensors into the same coordinate system. Infrared and visible light sensors are the most widely used in environmental perception; however, misaligned pixel coordinates in cross-modal images remain a challenge in practical applications of the object tracking task. Traditional feature-based approaches can only be applied in single-mode scenarios, and cannot be well extended to cross-modal scenarios. Recent deep learning technology employs neural networks with large parameter scales for prediction of feature points for image registration. However, supervised learning methods require numerous manually aligned images for model training, leading to the scalability and adaptivity problems. The Unsupervised Deep Homography Network (UDHN) applies Mean Absolute Error (MAE) metrics for cost function computation without labelled images; however, it is currently inapplicable for cross-modal image registration. In this paper, we propose aligning infrared and visible images using a rasterized parameter prediction algorithm with similarity measurement evaluation. Specifically, we use Cost Volume (CV) to predict registration parameters from coarse-grained to fine-grained layers with a raster constraint for multimodal feature fusion. In addition, motivated by the utilization of mutual information in contrastive learning, we apply a cross-modal similarity measurement algorithm for semi-supervised image registration. Our proposed method achieves state-of-the-art performance on the MS-COCO and FLIR datasets.

Fusing feature engineering and deep learning: A case study for malware classification

Machine learning has become an appealing signature-less approach to detect and classify malware because of its ability to generalize to never-before-seen samples and to handle large volumes of data. While traditional feature-based approaches rely on the manual design of hand-crafted features based on experts’ knowledge of the domain, deep learning approaches replace the manual feature engineering process by an underlying system, typically consisting of a neural network with multiple layers, that perform both feature learning and classification altogether. However, the combination of both approaches could substantially enhance detection systems. In this paper we present an hybrid approach to address the task of malware classification by fusing multiple types of features defined by experts and features learned through deep learning from raw data. In particular, our approach relies on deep learning to extract N-gram like features from the assembly language instructions and the bytes of malware, and texture patterns and shapelet-based features from malware’s grayscale image representation and structural entropy, respectively. These deep features are later passed as input to a gradient boosting model that combines the deep features and the hand-crafted features using an early-fusion mechanism. The suitability of our approach has been evaluated on the Microsoft Malware Classification Challenge benchmark and results show that the proposed solution achieves state-of-the-art performance and outperforms gradient boosting and deep learning methods in the literature.

Boosting Social Spam Detection via Attention Mechanisms on Twitter

Twitter is one of the largest social networking platforms, which allows users to make friends, read the latest news, share personal ideas, and discuss social issues. The huge popularity of Twitter mean it attracts a lot of online spammers. Traditional spam detection approaches have shown the effectiveness for identifying Twitter spammers by extracting handcrafted features and training machine learning models. However, such models need knowledge from domain experts. Moreover, the behaviors of spammers can change according to the defense strategies of Twitter. These result in the ineffectiveness of the traditional feature-based approaches. Although deep-learning-based approaches have been proposed for detecting Twitter spammers, they all treat each tweet equally, and ignore the differences among them. To solve these issues, in this paper, we propose a new attention-based deep learning model to detect social spammers in Twitter. In particular, we first introduce the state-of-the-art pretraining model BERTweet for learning the representation of each tweet, and then use the proposed novel attention-based mechanism to learn the user representations by distinguishing the differences among tweets posted by each user. Moreover, we take social interactions into consideration and propose that a graph attention network is used to update the learned user representations, to further improve the accuracy of identifying spammers. Experiments on a publicly available, real-world Twitter dataset show the effectiveness of the proposed model, which is able to significantly enhance the performance.

Uncovering the structure of clinical EEG signals with self-supervised learning

Objective. Supervised learning paradigms are often limited by the amount of labeled data that is available. This phenomenon is particularly problematic in clinically-relevant data, such as electroencephalography (EEG), where labeling can be costly in terms of specialized expertise and human processing time. Consequently, deep learning architectures designed to learn on EEG data have yielded relatively shallow models and performances at best similar to those of traditional feature-based approaches. However, in most situations, unlabeled data is available in abundance. By extracting information from this unlabeled data, it might be possible to reach competitive performance with deep neural networks despite limited access to labels. Approach. We investigated self-supervised learning (SSL), a promising technique for discovering structure in unlabeled data, to learn representations of EEG signals. Specifically, we explored two tasks based on temporal context prediction as well as contrastive predictive coding on two clinically-relevant problems: EEG-based sleep staging and pathology detection. We conducted experiments on two large public datasets with thousands of recordings and performed baseline comparisons with purely supervised and hand-engineered approaches. Main results. Linear classifiers trained on SSL-learned features consistently outperformed purely supervised deep neural networks in low-labeled data regimes while reaching competitive performance when all labels were available. Additionally, the embeddings learned with each method revealed clear latent structures related to physiological and clinical phenomena, such as age effects. Significance. We demonstrate the benefit of SSL approaches on EEG data. Our results suggest that self-supervision may pave the way to a wider use of deep learning models on EEG data.

Enhancing Aspect-Based Sentiment Analysis With Capsule Network

Existing feature-based neural approaches for aspect-based sentiment analysis (ABSA) try to improve their performance with pre-trained word embeddings and by modeling the relations between the text sequence and the aspect (or category), thus heavily depending on the quality of word embeddings and task-specific architectures. Although the recently pre-trained language models, i.e., BERT and XLNet, have achieved state-of-the-art performance in a variety of natural language processing (NLP) tasks, they still subject to the aspect-specific, local feature-aware and task-agnostic challenges. To address these challenges, this paper proposes a XLNet and capsule network based model XLNetCN for ABSA. XLNetCN firstly constructs auxiliary sentence to model the sequence-aspect relation and generate global aspect-specific representations, which enables to enhance aspect-awareness and ensure the full pre-training of XLNet for improving task-agnostic capability. After that, XLNetCN also employs a capsule network with the dynamic routing algorithm to extract the local and spatial hierarchical relations of the text sequence, and yield its local feature representations, which are then merged with the global aspect-related representations for downstream classification via a softmax classifier. Experimental results show that XLNetCN outperforms significantly than the classical BERT, XLNet and traditional feature-based approaches on the two benchmark datasets of SemEval 2014, Laptop and Restaurant, and achieves new state-of-the-art results.

Automatic Wireless Signal Classification: A Neural-Induced Support Vector Machine-Based Approach

Automatic Classification of Wireless Signals (ACWS), which is an intermediate step between signal detection and demodulation, is investigated in this paper. ACWS plays a crucial role in several military and non-military applications, by identifying interference sources and adversary attacks, to achieve efficient radio spectrum management. The performance of traditional feature-based (FB) classification approaches is limited due to their specific input feature set, which in turn results in poor generalization under unknown conditions. Therefore, in this paper, a novel feature-based classifier Neural-Induced Support Vector Machine (NSVM) is proposed, in which the features are learned automatically from raw input signals using Convolutional Neural Networks (CNN). The output of NSVM is given by a Gaussian Support Vector Machine (SVM), which takes the features learned by CNN as its input. The proposed scheme NSVM is trained as a single architecture, and in this way, it learns to minimize a margin-based loss instead of cross-entropy loss. The proposed scheme NSVM outperforms the traditional softmax-based CNN modulation classifier by managing faster convergence of accuracy and loss curves during training. Furthermore, the robustness of the NSVM classifier is verified by extensive simulation experiments under the presence of several non-ideal real-world channel impairments over a range of signal-to-noise ratio (SNR) values. The performance of NSVM is remarkable in classifying wireless signals, such as at low signal-to-noise ratio (SNR), the overall averaged classification accuracy is > 97% at SNR = −2 dB and at higher SNR it achieves overall classification accuracy at > 99%, when SNR = 10 dB. In addition to that, the analytical comparison with other studies shows the performance of NSVM is superior over a range of settings.

Automatic Wireless Signal Classification in Multimedia Internet of Things: An Adaptive Boosting Enabled Approach

Provision of multimedia contents over the Internet of things (IoT) presents significant challenges to wireless networks owing to nodes diversity. Therefore, efficient utilization of resources is required to meet the growing diversity in user's behavior and wireless services that mark the future of wireless communication. Automatic classification of wireless signals based on their modulation schemes is a crucial technology that enables wireless transceivers to utilize the resources efficiently. Traditional feature-based approaches lack generalization, and versatility by relying on single classifier predictions. In this paper, two adaptive boosting (Adaboost) based wireless signal classifiers called SigmaBoost and KNNAdaboost are proposed. Adaboost generates an optimal prediction rule by combining the prediction of many weak component classifiers (CCs). However, sometimes it overfits on real-world scenarios with noisy data. That makes the choice of CC vital for its success in classifying wireless signals. Therefore, two well-known classifiers support vector machine (SVM) and k-nearest neighbor (KNN) are used as CCs in proposed schemes respectively. In SigmaBoost an adaptive decrementing mechanism is introduced, which decreases the value of Gaussian radial function (RBF) of SVM kernel as boosting progresses. It not only ensures the generation of weak RBFSVM component classifiers but also improves diversity across the ensemble. Signal spectral features and higher-order cumulants are used as input features. The experimental results demonstrate significant gain in the performance of SigmaBoost, as compared to KNNAdaboost and other single classifier-based approaches. Hence, SigmaBoost can be used in multimedia-enabled IoT for quick discrimination of wireless signals to ensure better radio spectrum management.

Convolutional neural networks for time series classification

Time series classification is an important task in time series data mining, and has attracted great interests and tremendous efforts during last decades. However, it remains a challenging problem due to the nature of time series data: high dimensionality, large in data size and updating continuously. The deep learning techniques are explored to improve the performance of traditional feature-based approaches. Specifically, a novel convolutional neural network (CNN) framework is proposed for time series classification. Different from other feature-based classification approaches, CNN can discover and extract the suitable internal structure to generate deep features of the input time series automatically by using convolution and pooling operations. Two groups of experiments are conducted on simulated data sets and eight groups of experiments are conducted on real-world data sets from different application domains. The final experimental results show that the proposed method outperforms state-of-the-art methods for time series classification in terms of the classification accuracy and noise tolerance.

Exploiting multi-channels deep convolutional neural networks for multivariate time series classification

Time series classification is related to many different domains, such as health informatics, finance, and bioinformatics. Due to its broad applications, researchers have developed many algorithms for this kind of tasks, e.g., multivariate time series classification. Among the classification algorithms, k-nearest neighbor (k-NN) classification (particularly 1-NN) combined with dynamic time warping (DTW) achieves the state of the art performance. The deficiency is that when the data set grows large, the time consumption of 1-NN with DTWwill be very expensive. In contrast to 1-NN with DTW, it is more efficient but less effective for feature-based classification methods since their performance usually depends on the quality of hand-crafted features. In this paper, we aim to improve the performance of traditional feature-based approaches through the feature learning techniques. Specifically, we propose a novel deep learning framework, multi-channels deep convolutional neural networks (MC-DCNN), for multivariate time series classification. This model first learns features from individual univariate time series in each channel, and combines information from all channels as feature representation at the final layer. Then, the learnt features are applied into a multilayer perceptron (MLP) for classification. Finally, the extensive experiments on real-world data sets show that our model is not only more efficient than the state of the art but also competitive in accuracy. This study implies that feature learning is worth to be investigated for the problem of time series classification.

Dense Structure from a Dense Optical Flow Sequence

This paper presents a structure-from-motion system which deliversdensestructure information from a sequence of dense optical flows. Most traditional feature-based approaches cannot be extended to compute dense structure due to impractical computational complexity. We demonstrate that by decomposing uncertainty information into independent and correlated parts and employing an eigen-based uncertainty representation, we can decrease these complexities fromO(N2) toO(N) for every frame, whereNis the number of pixels in the images. We also show that our new representation of structural information makes it easy to merge over a long image sequence even when no specific feature is tracked over multiple frames.

Phase‐based measurement of object velocity in image sequences using the Hough transform

An alternative to traditional spatiotemporal gradient and feature-based approaches to measuring object velocity in images is in- troduced. Here, the velocity is computed by treating each object as a distinct intensity wave profile, with Fourier components, and by identify- ing the Fourier components that exhibit the magnitude and phase changes that are consistent with anticipated velocity wave motion. This detection is accomplished using an appropriate Hough transform. The two major advantages of this technique are that because the analysis takes place in the Fourier domain, the spatial organization and the visual appearance of the moving object are not significant and, second, the formulation presented in this paper lends itself to direct extension for more complex motion. Consequently, objects that are visually or spatially complex and that would be difficult to analyze using either of the tradi- tional spatiotemporal differentiation or feature-based approaches can be effectively treated. The proposed approach is demonstrated for scenes of varying complexity. © 1996 Society of Photo-Optical Instrumentation Engineers. Subject terms: velocity measurements; object motion; Fourier transforms; fre- quency phases; wave models; Hough transforms.