Combined Feature Extraction Research Articles

Steel plate surface defect classification technology based on image enhancement and combination feature extraction

PurposeIn the process of continuous casting and rolling of steel plate, due to the influence of rolling equipment and process, there are scratches, inclusions, patches, scabs and pitted surfaces on the surface of steel plate, which will not only affect the corrosion resistance, wear resistance and fatigue strength of steel plate but also may cause production accidents. Therefore, the detection of steel plate surface defect must be strengthened to ensure the production quality of steel plate and the smooth development of industrial construction.Design/methodology/approach(1) A steel plate surface defect detection technology based on small datasets is proposed, which can detect multiple surface defects and fill in the blank of scab defect detection. (2) A detection system based on intelligent recognition technology is built. The steel plate images are collected by the front-end monitoring device, then transmitted to the back-end monitoring center and processed by the embedded intelligent algorithms. (3) In order to reduce the impact of external light on the image, an improved Multi-Scale Retinex (MSR) enhancement algorithm based on adaptive weight calculation is proposed, which lays the foundation for subsequent object segmentation and feature extraction. (4) According to the different factors such as the cause and shape, the texture and shape features are combined to classify different defects on the steel plate surface. The defect classification model is constructed and the classification results are recorded and stored, which has certain application value in the field of steel plate surface defect detection. (5) The practicability and effectiveness of the proposed method are verified by comparison with other methods, and the field running tests are conducted based on the equipment commissioning field of China Heavy Machinery Institute.FindingsWhen applied to small dataset, the precision of the proposed method is 94.5% and the time is 23.7 ms. In order to compare with deep learning technology, after expanding the image dataset, the precision and detection time of this paper are 0.948 and 24.2 ms, respectively. The proposed method is superior to other traditional image processing and deep learning methods. And the field recognition precision is 91.7%.Originality/valueIn brief, the steel plate surface defect detection technology based on computer vision is effective, but the previous attempts and methods are not comprehensive and the accuracy and detection speed need to be improved. Therefore, a more practical and comprehensive technology is developed in this paper. The main contributions are as follows: (1) A steel plate surface defect detection technology based on small datasets is proposed, which can detect multiple surface defects and fill in the blank of scab defect detection. (2) A detection system based on intelligent recognition technology is built. The steel plate images are collected by the front-end monitoring device, then transmitted to the back-end monitoring center and processed by the embedded intelligent algorithms. (3) In order to reduce the impact of external light on the image, an improved MSR enhancement algorithm based on adaptive weight calculation is proposed, which lays the foundation for subsequent object segmentation and feature extraction. (4) According to the different factors such as the cause and shape, the texture and shape features are combined to classify different defects on the steel plate surface. The defect classification model is constructed and the classification results are recorded and stored, which has certain application value in the field of steel plate surface defect detection. (5) The practicability and effectiveness of the proposed method are verified by comparison with other methods, and the field running tests are conducted based on the equipment commissioning field of China Heavy Machinery Institute.

Identification of multiple symptoms of huanglongbing by electronic nose based on the variability of volatile organic compounds

AbstractHuanglongbing (HLB) is highly contagious and cannot be cured, resulting in a decrease in the commercial value of citrus. Timely detection and removal of diseased trees is an effective way to reduce losses. Complex symptoms of HLB, such as nutrient deficiencies often accompany HLB; as a result effective and accurate identification of HLB remains a challenge. In this study, 175 volatile organic compounds (VOCs) were detected in three categories (healthy, HLB, and Zn‐deficiency) of samples using headspace solid‐phase microextraction gas chromatography–mass spectrometry (HS‐SPME‐GC/MS), highlighting the variability of VOCs present in different categories of samples. In order to simplify the testing steps and reduce the cost in practical agricultural production, a method based on electronic nose technology to collect VOCs from citrus leaves for HLB detection was proposed. Among them, limiting value features and linear discriminant analysis were identified as the best combination of feature extraction and pattern recognition methods. Multiple sets of comparison experiments were set up and the collection conditions of VOCs were optimized. The results showed that the best classification performance was achieved for a 0.2 g sample at a collection time of 20 min when the collection temperature was 40°C and the headspace volume was 200 mL. Four types of samples (healthy, HLB‐positive, Zn‐deficiency, Zn‐deficiency and HLB‐positive) were used for model reliability validation, with an accuracy of 97.79% for HLB samples for multiple symptoms (including HLB‐positive and Zn‐deficiency and HLB‐positive) identification. In addition, the accuracy of samples with a combined effect of Zn‐deficiency and HLB was 96.43%. The results show that the E‐nose‐based HLB detection method is conducive to suppressing the spread of HLB, which can ensure the quality of citrus products and reduce the economic loss to horticulturists, and has good practical value.

A hybrid approach for face recognition using a convolutional neural network combined with feature extraction techniques

Facial recognition technology has been used in many fields such as security, biometric identification, robotics, video surveillance, health, and commerce due to its ease of implementation and minimal data processing time. However, this technology is influenced by the presence of variations such as pose, lighting, or occlusion. In this paper, we propose a new approach to improve the accuracy rate of face recognition in the presence of variation or occlusion, by combining feature extraction with a histogram of oriented gradient (HOG), scale invariant feature transform (SIFT), Gabor, and the Canny contour detector techniques, as well as a convolutional neural network (CNN) architecture, tested with several combinations of the activation function used (Softmax and Segmoïd) and the optimization algorithm used during training (adam, Adamax, RMSprop, and stochastic gradient descent (SGD)). For this, a preprocessing was performed on two databases of our database of faces (ORL) and Sheffield faces used, then we perform a feature extraction operation with the mentioned techniques and then pass them to our used CNN architecture. The results of our simulations show a high performance of the SIFT+CNN combination, in the case of the presence of variations with an accuracy rate up to 100%.

A deep learning algorithm-based visual strategy intervention study for children with autism spectrum disorders - extraction and detection of children's behavioral features.

Autism spectrum disorder is a group of neurodevelopmental disorders. The disease's etiology is unclear, and there is no specific drug treatment for the core symptoms of autism spectrum disease. The study aims to explore effective intervention methods for children with autism spectrum disorders.This paper proposes a visual strategy intervention method for children with autism spectrum disorders. This method combines feature extraction and abnormal behavior detection and can use a visual cue strategy to integrate children into social groups. Firstly, the spatial-temporal feature fusion structure is added to extract behavioral features from children, and the spatial information contained in MotionNet is fused with temporal features. Optical Flow Feature (OFF) subnetwork is added to the optical flow extraction feature network. Each layer feature is input to the OFF subnet to extract the time feature further. Then, a behavior detection method based on the sequential pool is proposed. This method combines attention mechanism and clustering pool to effectively describe human behavior dynamics in the long, redundant video under complex background. Finally, feature extraction and behavior detection experiments are carried out on SDUFall, Weizmann, and HMDB51 data sets.The model's accuracy is still slightly higher than others in that only the video Red-Green-Blue (RGB) frame is used as input. Compared with OFF, SDUFall can reach 88.64%, and HMDB51 can only reach 63.81%. In contrast, the proposed model can reach 72.09%, higher than others. The descriptor obtained the best result of 92.57%, which is 3.64%, 2.58%, and 1.73% higher than the other three comparison descriptors. The data show that the method presented here is effective and has advantages in detecting children's abnormal behavior.This method and visual intervention for children with autism spectrum disorders can help them to overcome social barriers.

A Hybridized Feature Extraction Model for Offline Yorùbá Document Recognition

Document recognition is required to convert handwritten and text documents into digital equivalents, making them more easily accessible and convenient to store. This study combined feature extraction techniques for recognizing Yorùbá documents in an effort to preserve the cultural values and heritages of the Yorùbá people. Ten Yorùbá documents were acquired from Kwara State University’s Library, and ten indigenous literate writers wrote the handwritten version of the documents. These were digitized using HP Scanjet300 and pre-processed. The pre-processed image served as input to the Local Binary Pattern, Speeded-Up-Robust-Features and Histogram of Gradient. The combined extracted feature vectors were input into the Genetic Algorithm. The reduced feature vector was fed into Support Vector Machine. A 10-folds cross-validation was used to train the model: LBP-GA, SURF-GA, HOG-GA, LBP-SURF-GA, HOG-SURF-GA, LBP-HOG-GA and LBP-HOG-SURF-GA. LBP-HOG-SURF-GA for Yorùbá printed text gave 90.0% precision, 90.3% accuracy and 15.5% FPR. LBP-HOG-SURF-GA for Handwritten Yorùbá document showed 80.9% precision, 82.6% accuracy and 20.4% (FPR) LBP-HOG-SURF-GA for CEDAR gave 98.0% precision, 98.4% accuracy and 2.6% FPR. LBP-HOG-SURF-GA for MNIST gave 99% precision, 99.5% accuracy, 99.0% and 1.1% FPR. The results of the hybridized feature extractions (LBP-HOG-SURF) demonstrated that the proposed work improves significantly on the various classification metrics.

Image recognition of sports dance teaching and auxiliary function data verification based on neural network algorithm

Nowadays, physical dance is widely spread in the society as an emerging sport. Dance movement is favored by people because of its unique social function and fitness effect. For dance teaching, dance movement analysis can help optimize and improve the existing dance movements and the understanding and inheritance of traditional dance movements. With the rise of online teaching, intelligent identification and analysis of dance movements can promote the better development of sports dance teaching. However, the relevant research in this area is still very scarce. As the basis of this kind of research, there is an urgent need for dance motion recognition technology. Based on this background, this paper by introducing neural network algorithm for dance teaching sports image special recognition design, the algorithm can combine feature extraction technology to process video, extract the dance movements in the target data set, then for the extraction of cumulative feature extraction operation, in order to accumulate all the collected target features, so as to further complete the gradient histogram acquisition. Through the design experimental test, the cumulative feature image extraction results obtained through the algorithm are obviously better than the traditional image recognition results, so the design rationality and effectiveness of the algorithm are proved, and the sports dance teaching can be specially assisted. This paper designs an effective auxiliary image recognition algorithm by introducing the neural network algorithm into the field of sports dance teaching.

Internal short circuit fault diagnosis based on 1DVCNN in lithium battery storage system

Because LiFePO4 batteries are widely used in the energy storage system, their safety has received a great deal of research. If an internal short circuit (ISC) in a Li-ion battery energy storage system leads to thermal runaway, it will pose an uncontrollable hazard. Therefore, there is a proposed method in this study that is a one-dimensional voltage-correlated convolutional neural network (1DVCNN) to detect and localize ISC faults in time, which is a combination of feature extraction, correlation analysis, and convolutional neural networks. First, the voltage signal of the LiFePO4 battery collected in the energy storage system is then converted into a Pearson Correlation Coefficient (PCC) by correlation analysis of the data. Specific PCCs are then selected as features of a one-dimensional convolutional neural network (1DCNN) to diagnose faults. Finally, the fault dataset is used to train the model and the results are then validated against the untrained fault data. In this paper, the ISC faults are modeled by both building an actual training platform for lithium batteries and MATLAB simulations to obtain the dataset used to train the proposed model. By comparing the accuracy of the training results of the models using different features, it is found that 1DVCNN is able to detect the ISC fault in the energy storage system in a more timely and effective manner than in other studies.

Wavelet-based Parametric Feature Subset Selection for Speaker and Accent Recognition using Genetic Algorithm

Research on speaker and accent recognition studies using the Malay language in the field of Automatic Speech Recognition (ASR) is limited, with most studies focusing on speech recognition. This study proposes to increase the performance Malaysian speakers and accent recognition using wavelets transform, namely Wavelet Packet Transform (WPT) and Dual-Tree Complex Wavelet Packet Transform (DT-CWPT). A variety of feature extraction combinations, including conventional Mel Frequency Cepstral Coefficients (MFCC), Linear Predictive Coding (LPC) and wavelets transform, were implemented to compare the effectiveness of the proposed method. Although the proposed approach resulted in improved detection rate, it faced challenges in terms of high feature dimensionality and increased computation time. To address these issues, the Genetic Algorithm (GA) approach has been adopted to reduce the number of irrelevant features, accelerate the learning system and achieve better performance. The extracted features were trained using various classifiers, including k-Nearest Neighbors (k-NN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM). The experimental results showed that the best speaker recognition accuracy was 97.33% for English numbers using SVM classifier and 96.02% for Malay words using the ELM classifier with a combination of wavelets, LPC and MFCC features. For accent recognition, the ELM classifier yielded the best performance, achieving 95.28% accuracy for English numbers with a combination of wavelets and MFCC features and 96.72% for Malay words using combined feature extraction of wavelets, LPC and MFCC feature extraction. It can be concluded that Malay words yielded better recognition rates than English numbers. Furthermore, use of GA effectively reduced the overall number of features while maintaining high accuracy level.

Graph Convolutional Network Using Adaptive Neighborhood Laplacian Matrix for Hyperspectral Images with Application to Rice Seed Image Classification

Graph convolutional neural network architectures combine feature extraction and convolutional layers for hyperspectral image classification. An adaptive neighborhood aggregation method based on statistical variance integrating the spatial information along with the spectral signature of the pixels is proposed for improving graph convolutional network classification of hyperspectral images. The spatial-spectral information is integrated into the adjacency matrix and processed by a single-layer graph convolutional network. The algorithm employs an adaptive neighborhood selection criteria conditioned by the class it belongs to. Compared to fixed window-based feature extraction, this method proves effective in capturing the spectral and spatial features with variable pixel neighborhood sizes. The experimental results from the Indian Pines, Houston University, and Botswana Hyperion hyperspectral image datasets show that the proposed AN-GCN can significantly improve classification accuracy. For example, the overall accuracy for Houston University data increases from 81.71% (MiniGCN) to 97.88% (AN-GCN). Furthermore, the AN-GCN can classify hyperspectral images of rice seeds exposed to high day and night temperatures, proving its efficacy in discriminating the seeds under increased ambient temperature treatments.

An efficient feature selection method for arabic and english speech emotion recognition using Grey Wolf Optimizer

Nowadays, analyzing and interpreting emotions through human speech communication have drawn a great attention in the field of human-computer interaction. Therefore, many speech recognition systems have been suggested to recognize the emotional states of the speaker utilizing the speech recordings of their spoken utterances. Feature extraction is an important step in building an emotion recognition system in which it is used to extract emotional features from speech data. However, not all extracted features are relevant to classify the emotion states of the speaker. The existence of irrelevant and redundant features generates unmeaningful patterns that lead to inaccurate and undesirable emotion classification performance. Therefore, this study proposes an intelligent feature selection method based on a novel bio-inspired optimization algorithm that mimics the hunting mechanism of wolves in the nature, called Grey Wolf Optimizer (GWO) and K-nearest neighbor (KNN) classifier, to find the most relevant subset of features to enhance the classification performance of an emotion recognition systems. The proposed method is called GWO-KNN. Emotion classification is performed on three distinct databases including Arabic Emirati-accented speech database, Ryerson Audio-Visual Database of Emotional Speech and Song dataset (RAVDESS), and Surrey Audio-Visual Expressed Emotion dataset (SAVEE). A combined or single feature extraction method is applied to extract the features from each dataset. The proposed method provides better classification performance for speech emotion recognition system compared to classical methods such as bat algorithm (BAT), cuckoo search (CS), White Shark Optimizer (WSH), and arithmetic optimization algorithm (AOA). Our proposed method also surpasses several state-of-the-art recent approaches that use the same datasets.

Hyperspectral Image Classification via Information Theoretic Dimension Reduction

Hyperspectral images (HSIs) are one of the most successfully used tools for precisely and potentially detecting key ground surfaces, vegetation, and minerals. HSIs contain a large amount of information about the ground scene; therefore, object classification becomes the most difficult task for such a high-dimensional HSI data cube. Additionally, the HSI’s spectral bands exhibit a high correlation, and a large amount of spectral data creates high dimensionality issues as well. Dimensionality reduction is, therefore, a crucial step in the HSI classification pipeline. In order to identify a pertinent subset of features for effective HSI classification, this study proposes a dimension reduction method that combines feature extraction and feature selection. In particular, we exploited the widely used denoising method minimum noise fraction (MNF) for feature extraction and an information theoretic-based strategy, cross-cumulative residual entropy (CCRE), for feature selection. Using the normalized CCRE, minimum redundancy maximum relevance (mRMR)-driven feature selection criteria were used to enhance the quality of the selected feature. To assess the effectiveness of the extracted features’ subsets, the kernel support vector machine (KSVM) classifier was applied to three publicly available HSIs. The experimental findings manifest a discernible improvement in classification accuracy and the qualities of the selected features. Specifically, the proposed method outperforms the traditional methods investigated, with overall classification accuracies on Indian Pines, Washington DC Mall, and Pavia University HSIs of 97.44%, 99.71%, and 98.35%, respectively.

Identification method for subgrade settlement of ballastless track based on vehicle vibration signals and machine learning

High-frequency train loads and complex environmental factors over a long period will inevitably cause subgrade settlement, an issue that adversely affects line smoothness. The existing monitoring methods are inefficient, manpower consuming and small in scope. This paper takes the subgrade settlement disease of the double-block ballastless track as the research object and proposes a subgrade settlement identification method based on vehicle vibration signals. In addition, it establishes a vehicle-track-subgrade vertical coupling model that combines feature extraction with algorithms such as support vector machines (SVMs) and convolutional neural networks (CNNs) to accurately identify subgrade settlement diseases on ballastless tracks. The results show: I) the subgrade settlement is far more impactful than fastener failure and debonding of the supporting layer on the vehicle vibration, with the main frequency band concentrated in 0 to 10 Hz, and the vertical vibration acceleration of the vehicle body and bogie can be used as a sensitive feature to identify ballastless track subgrade settlement, II) both the particle swarm optimization (PSO)-SVM and CNN-SVM algorithms can effectively determine the existence of subgrade settlement and the values of the settlement wavelength and amplitude. Both algorithms run a 100 % identification of subgrade settlement, with the lowest identification rates of settlement wavelength being 97.56 % and 100 %, respectively and the lowest identification rates of amplitude being 84.78 % and 97.56 %, respectively. In general, the overall accuracy of the CNN-SVM always outperforms PSO-SVM, and III) changes to the vehicle passing speed will create a more obvious interference effect on the identification of the settlement amplitude. For the PSO-SVM algorithm, the identification rate for the amplitude has a difference of up to 8.70 %, while this is 2.44 % for the CNN-SVM algorithm, indicating the CNN-SVM algorithm is more robust than the PSO-SVM algorithm.

PCEP: Few-Shot Model-Based Source Camera Identification

Source camera identification is an important branch in the field of digital forensics. Most existing works are based on the assumption that the number of training samples is sufficient. However, in practice, it is unrealistic to obtain a large amount of labeled samples. Therefore, in order to solve the problem of low accuracy for existing methods in a few-shot scenario, we propose a novel identification method called prototype construction with ensemble projection (PCEP). In this work, we extract a variety of features from few-shot datasets to obtain rich prior information. Then, we introduce semi-supervised learning to complete the construction of prototype sets. Subsequently, we use the prototype sets to retrain SVM classifiers, and take the posterior probability of each image sample belonging to each class as the final projection vector. Finally, we obtain classification results through ensemble learning voting. The PCEP method combines feature extraction, feature projection, classifier training and ensemble learning into a unified framework, which makes full use of image information of few-shot datasets. We conduct comprehensive experiments on multiple benchmark databases (i.e., Dresden, VISION and SOCRatES), and empirically show that our method achieves satisfactory performance and outperforms many recent methods in a few-shot scenario.

Introducing the Effective Features Using the Particle Swarm Optimization Algorithm to Increase Accuracy in Determining the Volume Percentages of Three-Phase Flows

What is presented in this research is an intelligent system for detecting the volume percentage of three-phase fluids passing through oil pipes. The structure of the detection system consists of an X-ray tube, a Pyrex galss pipe, and two sodium iodide detectors. A three-phase fluid of water, gas, and oil has been simulated inside the pipe in two flow regimes, annular and stratified. Different volume percentages from 10 to 80% are considered for each phase. After producing and emitting X-rays from the source and passing through the pipe containing a three-phase fluid, the intensity of photons is recorded by two detectors. The simulation is introduced by a Monte Carlo N-Particle (MCNP) code. After the implementation of all flow regimes in different volume percentages, the signals recorded by the detectors were recorded and labeled. Three frequency characteristics and five wavelet transform characteristics were extracted from the received signals of each detector, which were collected in a total of 16 characteristics from each test. The feature selection system based on the particle swarm optimization (PSO) algorithm was applied to determine the best combination of extracted features. The result was the introduction of seven features as the best features to determine volume percentages. The introduced characteristics were considered as the input of a Multilayer Perceptron (MLP) neural network, whose structure had seven input neurons (selected characteristics) and two output neurons (volume percentage of gas and water). The highest error obtained in determining volume percentages was equal to 0.13 as MSE, a low error compared with previous works. Using the PSO algorithm to select the most optimal features, the current research’s accuracy in determining volume percentages has significantly increased.

Feature Extraction for Image Analysis and Detection using Machine Learning Techniques

Feature extraction is the most vital step in image classification to produce high-quality and good content images for further analysis, image detection, segmentation, and object recognition. Using machine learning algorithms, profound learning like convolutional neural network CNN became necessary to train, classify, and recognize images and objects like humans. Combined feature extraction and machine learning classification to locate and identify objects on images can then be an input of automatic recognition systems ATR such as surveillance systems CCTV, to enhance these systems and reduce time and effort for object detection and recognition in images based on digital image processing techniques especially image segmentation that differentiate from computer vision approach. This article will use machine learning and deep learning algorithms to facilitate and achieve the study's objectives.

Deep Non-Parallel Hyperplane Support Vector Machine for Classification

In the last few decades, deep learning based on neural networks has become popular for the classification tasks, which combines feature extraction with the classification tasks and always achieves the satisfactory performance. Non-parallel hyperplane support vector machine (NPHSVM) aims at constructing two non-parallel hyperplanes to classify data and extracted features are always used to be input data for NPHSVM. As for NPHSVM, extracted features will greatly influence the performance of the model to some extent. Therefore, in this paper, we propose a novel DNHSVM for classification, which combines deep feature extraction with the generation of hyperplanes seamlessly. Each hyperplane is close to its own class and as far as possible to other classes, and deep features are friendly for classification and samples are easy to be classified. Experiments on UCI datasets show the effectiveness of our proposed method, which outperforms other compared state-of-the-art algorithms.

A Spectral–Spatial Feature Rotation-Based Ensemble Method for Imbalanced Hyperspectral Image Classification

Hyperspectral image classification has two key characteristics: spatial dependency and class imbalance. The synthetic oversampling methods for solving the between-class imbalance has the problem of spatial information loss to some extent. However, the feature space optimization methods for solving data within-class complex distribution problems have not been studied extensively. To remedy such issue, we propose in this paper an improved spectral-spatial feature rotation based SVM ensemble method (SSFRoF). More precisely, in the data preprocessing stage and from the perspective of sample space optimization, we devise a spectral-spatial neighborhood based adaptive synthetic sampling algorithm (SSAS) that focuses adaptively on hard-to-learn samples, with artificial samples interpolated in the spectral-spatial neighborhood to further utilize the spatial information. In feature rotation stage and from the perspective of feature space optimization, we innovatively discover that the class overlapping problem can be handled by combining feature extraction, so as to achieve the goal of reducing the difficulty of imbalanced classification. Besides, the SVM and voting procedure are used in the ensembled classification stage. We then conduct a series of experiments to compare the proposed SSFRoS with several baselines in terms of seven metrics. The results show that SSFRoS has significant advantages in dealing with imbalanced hyperspectral image classification problem. In addition, a detailed ablation study shows that the lowest class recall can be improved by 46.67% and 5.26% on Indian Pines and Pavia University respectively, which demonstrates that using SSAS can enhance the recognition of hard-to-learn classes.

FE-TAC: an effective document classification method combining feature extraction and feature selection

FE-TAC: an effective document classification method combining feature extraction and feature selection

FE-TAC: An Effective Document Classification Method Combining Feature Extraction and Feature Selection

FE-TAC: An Effective Document Classification Method Combining Feature Extraction and Feature Selection

Sequence Modeling of Passive Sensing Data for Treatment Response Prediction in Major Depressive Disorder.

Major depressive disorder (MDD) is a prevalent mental health condition and has become a pressing societal challenge. Early prediction of treatment response may aid in the rehabilitation engineering of depression, which is of great practical significance for the relief of suffering and burden of MDD. In this paper, we present a sequence modeling approach that uses data collected by passive sensing techniques to predict patients with an outcome of treatment responded defined by the reduction in clinical administrated scales. Hundreds of patients with MDD have been recruited from outpatient clinics at 4 psychiatric sites. Each has been delivered with a self-developed app to passively record their daily phone usage and physical data with minimal human action. An unavoidable dilemma in passive sensing is missing values. To overcome that, the proposed approach combined feature extraction and sequence modeling methods to fully utilize the pattern of missing values from longitudinal data. With no treatment constraints, it enables us to predict the treatment response of MDD 8-10 weeks before the completion of the treatment course, leaving time for preventative measures. Our work explored the feasibility of treatment response prediction using longitudinal passive sensing data and sparse ground truth, and also has the potential for preventing depression by forecasting treatment outcomes weeks in advance.