AlexNet Architecture Research Articles

An improved AlexNet deep learning method for limb tumor cancer prediction and detection.

Synovial sarcoma (SS) is a rare cancer that forms in the soft tissues around joints, where early detection is crucial for improving patient survival rates. This study introduces a convolutional neural network (CNN) using an improved AlexNet deep learning classifier to enhance the diagnosis of SS from digital pathological images. Key preprocessing steps such as dataset augmentation and noise reduction techniques like adaptive median filtering (AMF) and histogram equalization were employed to improve image quality. Feature extraction was conducted using the Gray-Level Co-occurrence Matrix (GLCM) and Improved Linear Discriminant Analysis (ILDA), while image segmentation targeted spindle-shaped cells using repetitive phase-level set segmentation (RPLSS). The improved AlexNet architecture features additional convolutional layers and resized input images, leading to superior performance. The model demonstrated significant improvements in accuracy, sensitivity, specificity, and AUC, outperforming existing methods by 3%, 1.70%, 6.08%, and 8.86%, respectively, in predicting SS.

Development of a city-level surface ozone forecasting system using deep learning techniques and air quality model: Application in eastern China

Utilizing regional air quality models to accurately forecast surface ozone (O3) concentrations, particularly high concentrations, is essential for protecting public health. However, forecasts of air quality model often deviate from site observations due to the limitation of grid resolution and uncertainties from emission sources, meteorological conditions, and chemical reaction mechanisms. Especially, the underestimation is significant under condition of high O3 concentrations. Moreover, such deviations tend to accumulate as forecast lead time increases, compounding the challenges associated with reliable air quality forecast. In this study, we employed AlexNet architecture, a classical convolutional neural network, combined with multiple variables related to meteorology, chemistry, emission and geography to establish a non-linear relationship between grid-scale input variables and site-scale hourly O3 forecast biases in Eastern China, aiming to realize accurate city-level ozone forecast based on a regional air quality prediction model (i.e., Nested Air Quality Prediction Model System, NAQPMS). By assigning weights to high-bias samples and high-concentration samples within the loss function, the proposed Weighted AlexNet model (W_AlexNet) effectively reduced forecast biases and enhanced its capability to predict O3 pollution levels. Compared to NAQPMS, W_AlexNet model demonstrated a 25.71% improvement in RMSE and a 7.17% increase in IOA averagely for hourly O3 (O3-1h) forecasts across four different lead times (24-h, 48-h, 72-h, and 96-h). Notably, W_AlexNet model alleviated the tendency of NAQPMS to underestimate high concentrations and showed a superior performance in improving O3-1h pollution level forecasts, particularly for the 72-h and 96-h lead times. W_AlexNet model can effectively mitigate the bias accumulation effect over increasing lead times, thereby enhancing the reliability of longer-term forecasts. Thus, the W_AlexNet model serves as a post-processing model that can calibrate forecast biases in air quality prediction models, significantly improving the accuracy of O3 high concentration forecasts and providing more precise early warnings of O3 pollution. This underscores its utility in air quality management.

Modified Alexnet Architecture for Classification of Cassava Based on Leaf Images

The objective of this study is to address the drawbacks of conventional classification approaches through the implementation of deep learning, specifically a modified AlexNet. The primary aim of this study is to precisely categorize the four distinct varieties of cassava, namely Manggu, Gajah, Beracun, and Kapok. The cassava dataset was obtained from farmers in Lamongan, Indonesia, and was used as a source of information. Data collection on cassava leaves was carried out with agricultural research specialists. A total of 1,400 images are included in the dataset, with 350 images corresponding to each variety of cassava produced. The central focus of this research lies in a comprehensive evaluation of the modified AlexNet architecture's performance compared to the original AlexNet architecture for cassava classification. Multiple scenarios were examined, involving diverse combinations of learning rates and epochs, to thoroughly assess the robustness and adaptability of the proposed approach. Among the evaluation criteria that were rigorously examined were accuracy, recall, F1 score, and precision. These metrics were used to determine the predictive capabilities of the model as well as its potential utilization in the actual world. The results show that the modified AlexNet design has better performance than the original AlexNet for recall, accuracy, precision, and F-1 score, all achieving a rate of 87%. In situations where a learning rate of 0.0001 and an epoch count of 150 are utilized, the performance of the approach stands out significantly, displaying an excellent level of competency. Nevertheless, it is crucial to recognize that distinct fluctuations in performance were noted within particular contexts and with diverse learning rates.

MRI Brain Tumor Classification and Extraction using Deep Learning-Based Decision Level Image Fusion Technique

Objectives: The proposed work emphasizes the tumor region extracted from the multimodal MRI brain scan by deep learning-based decision-level image fusion technique. Methods: Convolutional Neural Network (CNN) architectures such as AlexNet, ResNet50, and VGG16 perform brain tumor classification with multimodal MRI images Flair, T2, and T1c respectively. Flair images are fed to the AlexNet architecture, T2 images are fed to the ResNet50 architecture, and T1c images are fed to the VGG16 architecture to classify brain tumor images. The classification results from these architectures are fused together to perform the decision on the given inputs. If the inputs come under the decision of the tumor affected then the tumor portion will be extracted using the fusion of three images as a post-processing operation. Findings: The experiments are done using BraTS datasets an open-access brain tumor image analysis research repository. The three CNN architectures' performance is measured by accuracy and gives 0.87 for AlexNet, 0.91 for ResNet50, and 0.99 for VGG16. The extracted tumor region from the fused output image is compared with the ground truth image by metrics such as SSIM with 0.93, DC 0.96, and PSNR with 66.57. Better results are received for the proposed work in the evaluation analysis than the existing works. Novelty: Decision level image fusion limitedly experimented with Deep Learning techniques in state-of-art methods. In this proposed method, the decisions made based on the classification result of three CNN architectures. Keywords: MRI, Brain tumor, Deep Learning, Convolutional Neural Network Architectures, Image Fusion, AlexNet, ResNet50, VGG16

Deteksi Kesegaran Telur Ayam pada Citra Cangkang Menggunakan Metode Convolutional Neural Network (CNN)

This research developed an egg freshness detection system using the Convolutional Neural Network (CNN) method to analyze egg shell images. A dataset consisting of 1,898 images of fresh and stale egg shells was used in this study. The pre-processing stage included resizing and labeling data, followed by training the CNN model using the SqueezeNet and AlexNet architectures. The results showed an accuracy of 90% in classifying egg freshness. The use of CNN proved to be more effective than conventional methods such as thresholding and K-Nearest Neighbor (KNN). This research makes a significant contribution to improving the efficiency and accuracy of egg sorting in Indonesia, reducing reliance on manual methods, and speeding up the sorting process.

Efficient image classification through collaborative knowledge distillation: A novel AlexNet modification approach

This paper introduces an innovative image classification technique utilizing knowledge distillation, tailored for a lightweight model structure. The core of the approach is a modified version of the AlexNet architecture, enhanced with depthwise-separable convolution layers. A unique aspect of this work is the Teacher-Student Collaborative Knowledge Distillation (TSKD) method. Unlike conventional knowledge distillation techniques, TSKD employs a dual-layered learning strategy, where the student model learns from both the final output and the intermediate layers of the teacher model. This collaborative learning approach enables the student model to actively engage in the learning process, resulting in more efficient knowledge transfer. The paper emphasizes the model suitability for scenarios with limited computational resources. This is achieved through architectural optimizations and the introduction of specialized loss functions, which balance the trade-off between model complexity and computational efficiency. The study demonstrates that despite its lightweight nature, the model maintains high accuracy and robustness in image classification tasks. Key contributions of the paper include the innovative use of depthwise-separable convolution in AlexNet, the TSKD approach for enhanced knowledge transfer, and the development of unique loss functions. These advancements collectively contribute to the model effectiveness in environments with computational constraints, making it a valuable contribution to the field of image classification.

Energy-Efficient Secure Routing for a Sustainable Heterogeneous IoT Network Management

The Heterogeneous Internet of Things (H-IoT) is considered as the upcoming industrial and academic revolution in the technological world, having billions of things and devices connected to the Internet. This H-IoT has a major issue of energy consumption during data transmission which leads to low scalability. Additionally, anomalies in the data create a serious threat to energy in H-IoT. To overcome these issues, a novel approach has been proposed in this study termed as the Energy-Efficient Memetic Clustering Method (EEMCM), which combines the Parallelized Memetic Algorithm (PMA) with the AlexNet architecture to improve anomaly detection efficiency in IoT WSNs. Initially, cluster formation and CH selection are carried out using PMA. This is followed by routing path generation, and the data are prepared for high-level feature extraction. The extracted features are classified to identify anomalies. For anomaly detection, high-level features were collected that contain data relevant to the model given as input into the AlexNet architecture, which detects anomalies and identifies normal or potential attacks within the IoT WSNs. The proposed EEMCM model has been implemented in the MATLAB platform and obtained an accuracy of 99.11%. As a result, the overall performance of the network is improved.

Prediction of paroxysmal atrial fibrillation using a convolutional neural network and electrocardiogram signals

Atrial fibrillation (AF) is the most clinically diagnosed arrhythmia in cardiac pathology. The incidence of AF begins at a very early age and its initial state is paroxysmal atrial fibrillation (PAF). This type of heart disease can be detected and predicted by analyzing the spectrogram of a surface electrocardiogram (ECG) signal. In many studies, different ECG signal formats and convolutional neural network (CNN) architectures have been used. However, the lack of good signal preprocessing or signal adequacy may have affected the accuracy, especially on short-term ECG signals. In this study, we analyzed a preprocessed ECG signal, determined the optimal set to predict PAF, and evaluated the accuracy using ECG signals of different durations. The PAF Prediction Challenge–PhysioNet database was used to extract spectrograms in 30-sec and 5-sec windows for two classes (Normal, PAF) and 3 classes (Normal, Close-AF, Distant-AF). Then, the AlexNet architecture was used. The proposed method achieved a two-class accuracy of 99.92% with a 30-sec window and 99.42% with a 5-sec window, improving the PAF prediction performance compared with similar works. In addition, the three-class accuracies were 96.92% and 97.43% with windows of 30-sec, and 5-sec, respectively. These results prove the efficacy of the method for the early diagnosis of PAF, even based on short-term ECG signals.

Image Classification of Traditional Indonesian Cakes Using Convolutional Neural Network (CNN)

Indonesia is one of the countries famous for its traditional culinary. Traditional cakes in Indonesia are traditional snacks typical of the archipelago's culture which have a variety of textures, shapes, colors that vary and some are similar so that there are still many people who do not know the name of the cake from the many types of traditional Indonesian cakes. The problem can be solved by creating a traditional cake image recognition system that can be programmed and trained to classify various types of traditional Indonesian cakes. The Convolutional Neural Network method with the AlexNet architecture model is used in this research to predict various kinds of traditional Indonesian cakes. The dataset used in this research is 1846 datasets with 8 classes of cake images. This study trained the AlexNet model with several optimizers, namely, Adam optimizer, SGD, and RMSprop. The best parameters from the model testing results are at batchsize 16, epoch 50, learning rate 0.01 for SGD optimizer and learning rate 0.001 for Adam and RMSprop optimizers. Each optimizer tested produces different accuracy, precision, recall, and f1_score values. The highest test results that have been carried out on the image dataset of typical Indonesian traditional cakes are obtained by the Adam optimizer with an accuracy value of 79%.

SEMANTIC SEGMENTATION AND CONTENT-BASED RETRIEVAL IN MULTIMEDIA IMAGE DATABASES

Brain tumors, particularly gliomas, pose a significant threat to global health, necessitating accurate and efficient diagnostic methods. Magnetic Resonance Imaging (MRI) serves as a crucial tool for diagnosing glioma grades, but interpretation is subject to variability, hindering treatment planning. Intra and inter-observer variability in radiological image interpretation impede effective therapeutic strategies for brain tumor patients. Accessing relevant images from vast medical databases for comparison and treatment planning is cumbersome and time-consuming. This paper proposes a Content-Based Medical Image Retrieval (CBIR) system utilizing Convolutional Neural Network (CNN)-based feature extraction, specifically employing the AlexNet architecture. The system employs KNN clustering for indexing the feature map database and implements Gain-based feature selection to reduce feature vector dimensionality. The proposed system underwent evaluation using BraTS 2018 and 2020 datasets with five-fold cross-validation. Achieving state-of-the-art performance, the system demonstrated a mean Average Precision of 98% and Precision of 97%, showcasing its efficacy in accurately retrieving similar pathological MRI brain images.

Innovative Framework for Thyroid Disease Detection by Leveraging Hybrid AGTEO Feature Selection and GRU Classification Model

Thyroid disease remains a significant health concern, necessitating advanced diagnostic tools for swift and accurate identification. The initial step involves preprocessing datasets, employing an Outlier Detection Method with Isolated Forest in conjunction with data normalization techniques to eliminate noise and standardize the data, laying a robust groundwork for subsequent analysis. Subsequently, feature extraction is conducted utilizing an Enhanced AlexNet architecture augmented by a more intricate Chameleon Swarm Algorithm (CSA) model to discern finer patterns within the data, enhancing the discriminative nature of the extracted features. Following this, a feature selection strategy employing hybrid optimization is deployed, amalgamating the strengths of Equilibrium Optimizer and Artificial Gorilla Troops Optimizer (AGTO) into a hybrid model named HAGTEO, aiming to identify the most informative features, thus reducing dimensionality and enhancing classifier efficiency. Ultimately, the Gated Recurrent Unit (GRU) classifier is employed for thyroid disease classification based on the extracted and selected features. Renowned for its capability to capture temporal dependencies, the GRU model further enhances classification accuracy. The proposed framework is subjected to testing on two distinct datasets, demonstrating its efficacy in thyroid disease detection. Experimental outcomes reveal superior performance compared to conventional methods, achieving accuracies of 98.07% and 98.00% for dataset 1 and dataset 2, respectively. As an advanced diagnostic solution for thyroid disease, it holds promising potential.

Research on inter-shaft bearing fault diagnosis method based on STFT-CNN modeling

Inter-shaft bearings are an essential component of aircraft engines, and their operational status determines the safety of aircraft engine operation. Therefore, to improve the accuracy of fault type prediction and enrich the feature information in vibration signals of aircraft engine inter-shaft bearings, this paper proposes an STFT-CNN model based on the AlexNet architecture, extending its application to the research of aircraft engine inter-shaft bearing fault diagnosis. This approach addresses the common reliance on personnel experience for fault type diagnosis in traditional aircraft engine inter-shaft bearing fault diagnosis. Firstly, real vibration fault signals from inter-shaft bearings are collected through experiments to enrich feature information in non-stationary signals using STFT time-frequency methods. Secondly, utilizing the high interpretability of the STFT-CNN model, fault feature data from inter-shaft bearings under various operating conditions are extracted to refine our understanding of fault feature information. Finally, leveraging the robustness of the STFT-CNN model, fault types are classified and predicted. The training process involves comparative analysis using different pooling algorithms, time-frequency analysis methods, and various deep learning network models. The results demonstrate that the STFT-CNN model, employing the maximum pooling algorithm, outperforms other models in predicting inter-shaft bearing faults, achieving an average fault prediction accuracy of 98.8% .

Car Parking Occupancy Detection Using Deep Learning

It can be difficult to find a parking space in a busy neighborhood because you never know when one will become available. Due to the rise of automobiles and fall in parking spots, this task even more challenging. To increase the dependability of smart parking systems, numerous researchers have sought to improve them. In smart parking systems, computer vision is a more advantageous method for detecting parking spaces than sensors. Many parking spots may be monitored by a single smart camera, which is also reasonably easy to install and maintain. To identify parking occupancy in camera-captured photos, a CNN model is employed. The CNN model will be trained using the CNRpark+Ext and PKLot datasets, which contain 4081 and 12,416 parking lot photos under various weather scenarios, respectively. The CNN architectures, CmAlexNet and mAlexNet, are five-layer designs built on the eight-layer AlexNet architecture, in which processing speed is increased by removing the completely connected layer and the third and fourth convolutional layers. To increase accuracy, the first convolutional layer of CmAlexNet's filter is resized from 11x11 to 13x13, and batch normalization [1] is used instead of the original method. Three key performance metrics are evaluated between CmAlexNet and mAlexNet: recall, precision, and accuracy in classification. Keywords: Car Parking , Computer Vision , Deep learning , CNN, mAlexnet , cmAlexnet , CNRpark dataset , PKLot dataset.

Efficient Model on Corp Disease and Pest Detection with Deep Learning

Agricultural production faces significant challenges due to pests and diseases, causing substantial losses in crop yield globally. Traditional methods of pest and disease management are often manual, time-consuming, and prone to errors. In recent years, the integration of artificial intelligence (AI) techniques, particularly deep learning algorithms, with modern information and communication technology has shown promising results in addressing these challenges. This paper presents a comprehensive review of recent advancements in applying deep learning for detecting and classifying agricultural pests, diseases, and weeds. Various deep learning models, including convolutional neural networks (CNNs) such as Faster R-CNN, InceptionV3, DenseNet, and AlexNet, have been explored for their efficacy in identifying pests, diseases, and weeds in crops. While models like Faster R-CNN, InceptionV3, and DenseNet have demonstrated high accuracy rates ranging from 78.71% to 99.62% in classification tasks across different datasets and crops, the AlexNet architecture has also shown promising results in certain applications within agricultural image analysis. Additionally, the development of lightweight CNN architectures and the fusion of deep features with traditional handcrafted features have further enhanced the accuracy and efficiency of detection systems. Furthermore, the review discusses challenges and future research directions in the field, emphasizing the importance of large-scale datasets, model optimization, and real-time applications for practical implementation in agriculture. Overall, the findings highlight the potential of deep learning technologies, including models like AlexNet, in revolutionizing pest and disease management practices, leading to improved crop yield, food security, and sustainable agriculture. Keywords: Agricultural pests, plant diseases, deep learning, convolutional neural networks (CNNs), AlexNet, classification

Preliminary Study Based on Myocardial Infarction Classification of 12-Lead Electrocardiography Images with Deep Learning Methods

In contemporary medicine, the development of computer-aided diagnostic systems using Electrocardiography (ECG) signals has gained significance for the diagnosis of heart diseases. Myocardial infarction (MI) is recognized as the condition where blood flow to the heart muscle is obstructed due to blockages in coronary vessels. In this study, four deep learning approaches were employed to automatically identify different MI conditions (STEMI, NSTEMI, USAP) using images generated from 12-lead ECG signals. The utilized architectures include deep neural networks such as Visual Geometry Group-16 (VGG-16), AlexNet, Residual Neural Network (ResNet), SqueezeNet and an ensemble model composed of these networks. With the proposed method, classification was performed based on 10-second grayscale images of 12-lead ECG signals for HC-STEMI, HC-NSTEMI, HC-USAP, and NSTEMI-STEMI conditions. According to the obtained results, the HC-STEMI group achieved the highest performance with a cross-validated 0.8237 F1 score using the AlexNet architecture. Among the novel contributions of this study is the image-based ECG classification method that can be more easily adapted to clinical applications and the analysis of the potential use of detecting different MI conditions in clinical practices. In conclusion, this study sheds light on future research by demonstrating the significant potential of using multi-channel ECG signals in image format for MI diagnosis, paving the way for advancements in this field.

Enhancing Pneumonia Diagnosis Through Chest Imaging and Machine Learning A Comprehensive Ensemble Approach with Diverse CNN Architectures

Abstract: This research presents a novel approach for pneumonia diagnosis in chest X-ray images utilizing an ensemble of convolutional neural networks (CNNs). The proposed system integrates state-of-the-art architectures such as ResNet, DenseNet, InceptionV3, MobileNet, and AlexNet, helping transfer learning to fine-tune these models on a curated chest X-ray dataset obtained from Kaggle. The dataset comprises two classes: normal and pneumonia. The ensemble methodology combines the predictive strengths of individual CNN models, harnessing their diverse feature extraction capabilities. A key innovation lies in the incorporation of the AlexNet architecture into the ensemble, aiming to further enhance the ensemble's discriminative power. The system undergoes a comprehensive training, validation, and testing pipeline, culminating in real-time predictions on new chest X-ray images. The experimental results showcase the effectiveness of the ensemble approach, demonstrating improved accuracy and robustness in pneumonia detection compared to individual models. The incorporation of AlexNet contributes unique features to the ensemble, ighlighting the potential of diverse model architectures in enhancing diagnostic performance

Evaluation of AI tools for healthcare networks at the cloud-edge interaction to diagnose autism in educational environments

Physical, social, and routine environments can be challenging for learners with autism spectrum disorder (ASD). ASD is a developmental disorder caused by neurological problems. In schools and educational environments, this disorder may not only hinder a child’s learning, but also lead to more crises and mental convulsions. In order to teach students with ASD, it is essential to understand the impact of their learning environment on their interaction and behavior. Different methods have been used to diagnose ASD in the past, each with their own strengths and weaknesses. Research into ASD diagnostics has largely focused on machine learning algorithms and strategies rather than diagnostic methods. This article discusses many diagnostic techniques used in the ASD literature, such as neuroimaging, speech recordings, facial features, and EEG signals. This has led us to conclude that in schools and educational settings, autism can be diagnosed cheaply, quickly, and accurately through face analysis. To facilitate and speed up the processing of facial information among children in educational settings, we applied the AlexNet architecture designed for edge computing. A fast method for detecting autism spectrum disorders from the face can be applied to educational settings using this structure. While we have investigated a variety of methods, the face can provide us with appropriate information about the disorder. In addition, it can produce more interpretive features. In order to help students in schools who are suffering from this disease, key factors must be considered: potential clinical and therapeutic situations, efficiency, predictability, privacy protection, accuracy, cost-effectiveness, and lack of methodological intervention. The diseases are troublesome, so they should be identified and treated.

Yogyakarta Batik Image Classification Based on Convolutional Neural Network

This paper studies the efficiency of identifying motifs and patterns in Yogyakarta batik using the Convolutional Neural Network (CNN) algorithm. This research uses the AlexNet architecture on CNN to increase the accuracy of batik image classification. Apart from that, it also involves the use of Canny edge detection techniques and feature extraction using the Gray Level Co-occurrence Matrix (GLCM) to improve the feature extraction process in batik images. There are 6 folders representing 6 types of motifs containing -+20 to 25 data that have been prepared for the training session. Next, the data is processed with 20% of the data used for training and 80% for testing. The accuracy of this research using the SGDM optimizer reached 100%. The evaluation results provide insight into the extent to which edge emphasis can improve the model's ability to recognize and classify batik patterns. It also presents classification test results and evaluation metrics such as precision, recall, and F1 score.

Car make and model recognition using convolutional neural network: fine-tune AlexNet architecture

Artificial intelligence (AI) has significantly contributed to car make and model recognition in this current era of intelligent technology. By using AI, it is much easier to identify car models from any picture or video. This paper introduces a new model by fine-tuning the AlexNet architecture to determine the car model from images. First of all, our car image dataset has been created. Some of these images were taken by us, and others were taken from the website of the car connection. Then we cleaned all the unwanted images for better performance. Our dataset has ten classes containing 5,000 car images split into train and test data. After that, we augmented our data with random flip, rotation, and zoom to reduce overfitting. Finally, we used a pre-trained convolutional neural network (CNN) model AlexNet architecture. We fine-tuned AlexNet (FT-AlexNet) by adding three extra layers for better classification and compared it with the original AlexNet. To measure the performance of these models, accuracy, precision, recall, and F1-score were used. The results show that fine-tune AlexNet architecture outperforms the original AlexNet architecture. The results prove that recognition accuracy has increased due to our improvement approach.

Face-based Gender Classification Using Deep Learning Model

Gender classification is a critical task in computer vision. This task holds substantial importance in various domains, including surveillance, marketing, and human-computer interaction. In this work, the face gender classification model proposed consists of three main phases: the first phase involves applying the Viola-Jones algorithm to detect facial images, which includes four steps: 1) Haar-like features, 2) Integral Image, 3) Adaboost Learning, and 4) Cascade Classifier. In the second phase, four pre-processing operations are employed, namely cropping, resizing, converting the image from(RGB) Color Space to (LAB) color space, and enhancing the images using (HE, CLAHE). The final phase involves utilizing Transfer learning, a powerful deep learning technique that can be effectively employed to Face gender classification using the Alex-Net architecture. The performance evaluation of the proposed gender classification model encompassed three datasets: the LFW dataset, which contained 1,200 facial images. The Faces94 dataset contained 400 facial images, and the family dataset had 400. The Transfer Learning with the Alex-Net model achieved an accuracy of 98.77% on the LFW dataset. Furthermore, the model attained an accuracy rate of 100% on both the Faces94 and family datasets. Thus, the proposed system emphasizes the significance of employing pre-processing techniques and transfer learning with the Alex-Net model. These methods contribute to more accurate results in gender classification. Where, the results achieved by applying image contrast enhancement techniques, such as HE and CLAHE, were compared. CLAHE achieved the best facial classification accuracy compared to HE.