Cancerous and Non-Cancerous MRI Classification Using Dual DCNN Approach.

Brain cancer is a life-threatening disease requiring close attention. Early and accurate diagnosis using non-invasive medical imaging is critical for successful treatment and patient survival. However, manual diagnosis by radiologist experts is time-consuming and has limitations in processing large datasets efficiently. Therefore, efficient systems capable of analyzing vast amounts of medical data for early tumor detection are urgently needed. Deep learning (DL) with deep convolutional neural networks (DCNNs) emerges as a promising tool for understanding diseases like brain cancer through medical imaging modalities, especially MRI, which provides detailed soft tissue contrast for visualizing tumors and organs. DL techniques have become more and more popular in current research on brain tumor detection. Unlike traditional machine learning methods requiring manual feature extraction, DL models are adept at handling complex data like MRIs and excel in classification tasks, making them well-suited for medical image analysis applications. This study presents a novel Dual DCNN model that can accurately classify cancerous and non-cancerous MRI samples. Our Dual DCNN model uses two well-performed DL models, i.e., inceptionV3 and denseNet121. Features are extracted from these models by appending a global max pooling layer. The extracted features are then utilized to train the model with the addition of five fully connected layers and finally accurately classify MRI samples as cancerous or non-cancerous. The fully connected layers are retrained to learn the extracted features for better accuracy. The technique achieves 99%, 99%, 98%, and 99% of accuracy, precision, recall, and f1-scores, respectively. Furthermore, this study compares the Dual DCNN's performance against various well-known DL models, including DenseNet121, InceptionV3, ResNet architectures, EfficientNetB2, SqueezeNet, VGG16, AlexNet, and LeNet-5, with different learning rates. This study indicates that our proposed approach outperforms these established models in terms of performance.

PEMFC model identification using a squeezenet developed by modified transient search optimization algorithm.

Proton Exchange Membrane Fuel Cells (PEMFCs) are promising sources of clean and renewable energy, but their performance and efficiency depend on an accurate modeling and identification of their system parameters. However, existing methods for PEMFC modeling suffer from drawbacks, such as slow convergence, high computational cost, and low accuracy. To address these challenges, this research work proposes an enhanced approach that combines a modified version of the SqueezeNet model, a deep learning architecture that reduces the number of parameters and computations, and a new optimization algorithm called the Modified Transient Search Optimization (MTSO) Algorithm, which improves the exploration and exploitation abilities of the search process. The proposed approach is applied to model the output voltage of the PEMFC under different operating conditions, and the results are compared with empirical data and two other state-of-the-art methods: Gated Recurrent Unit and Improved Manta Ray Foraging Optimization (GRU/IMRFO) and Grey Neural Network Model integrated with Particle Swarm Optimization (GNNM/PSO). The comparison shows that the proposed approach achieves the lowest Sum of Squared Errors (SSE) and the highest accuracy, demonstrating its superiority and effectiveness in PEMFC modeling. The proposed approach can facilitate the optimal design, control, and monitoring of PEMFC systems in various applications.

An Optimal Model Combining SqueezeNet and Machine Learning Methods for Lung Disease Diagnosis.

BACKGROUND: Artificial intelligence (AI) is rapidly evolving in healthcare, with transformative potential. AI revolutionizes medical imaging by enabling online self-diagnosis for patients and improving diagnostic accuracy for healthcare professionals. While valuable datasets aid machine learning in disease detection, challenges persist in diagnosing similar lung conditions from chest X-rays. Integrating AI into healthcare holds promise for enhanced outcomes and efficiency. OBJECTIVE: In this article, we aim to present a new AI model that solves this challenge by allowing the differentiation, diagnosis and classification of three distinct diseases, whose symptoms are very similar. The fundamental contribution is to reduce the number of parameters used while maintaining the same level of precision for use in embedded systems. METHODS: Our proposed model combines the power of the neural network using the SqueezeNet architecture with a set of machine learning algorithms as classifiers, including logistic regression, support vector machine (SVM), k-nearest neighbors (KNN), decision tree, and naive Bayes. The chest Xray dataset used in the proposed model consists of CXR images that are classified into four categories: pneumonia, tuberculosis, COVID-19, and normal cases. RESULTS: Our proposed model demonstrated remarkable accuracy (97,32%), precision (97,33), F1 score (97,31%), recall (97,30%), and AUC (99,40), which is close to the best model. Whereas, the number of parameters used by our model (4,6 M) is very small compared to the best model in the literature (47M). CONCLUSION: The model demonstrated good classification accuracy. In addition, the proposed model has the ability to use fewer parameters, which means it requires less internal memory and computing resources.

SCSLnO-SqueezeNet: Sine Cosine-Sea Lion Optimization enabled SqueezeNet for intrusion detection in IoT.

Security and privacy are regarded as the greatest priority in any real-world smart ecosystem built on the Internet of Things (IoT) paradigm. In this study, a SqueezeNet model for IoT threat detection is built using Sine Cosine Sea Lion Optimization (SCSLnO). The Base Station (BS) carries out intrusion detection. The Hausdorff distance is used to determine which features are important. Using the SqueezeNet model, attack detection is carried out, and the network classifier is trained using SCSLnO, which is developed by combining the Sine Cosine Algorithm (SCA) with Sea Lion Optimization (SLnO). BoT-IoT and NSL-KDD datasets are used for the analysis. In comparison to existing approaches, PSO-KNN/SVM, Voting Ensemble Classifier, Deep NN, and Deep learning, the accuracy value produced by devised method for the BoT-IoT dataset is 10.75%, 8.45%, 6.36%, and 3.51% higher when the training percentage is 90.

Assist-Dermo: A Lightweight Separable Vision Transformer Model for Multiclass Skin Lesion Classification.

A dermatologist-like automatic classification system is developed in this paper to recognize nine different classes of pigmented skin lesions (PSLs), using a separable vision transformer (SVT) technique to assist clinical experts in early skin cancer detection. In the past, researchers have developed a few systems to recognize nine classes of PSLs. However, they often require enormous computations to achieve high performance, which is burdensome to deploy on resource-constrained devices. In this paper, a new approach to designing SVT architecture is developed based on SqueezeNet and depthwise separable CNN models. The primary goal is to find a deep learning architecture with few parameters that has comparable accuracy to state-of-the-art (SOTA) architectures. This paper modifies the SqueezeNet design for improved runtime performance by utilizing depthwise separable convolutions rather than simple conventional units. To develop this Assist-Dermo system, a data augmentation technique is applied to control the PSL imbalance problem. Next, a pre-processing step is integrated to select the most dominant region and then enhance the lesion patterns in a perceptual-oriented color space. Afterwards, the Assist-Dermo system is designed to improve efficacy and performance with several layers and multiple filter sizes but fewer filters and parameters. For the training and evaluation of Assist-Dermo models, a set of PSL images is collected from different online data sources such as Ph2, ISBI-2017, HAM10000, and ISIC to recognize nine classes of PSLs. On the chosen dataset, it achieves an accuracy (ACC) of 95.6%, a sensitivity (SE) of 96.7%, a specificity (SP) of 95%, and an area under the curve (AUC) of 0.95. The experimental results show that the suggested Assist-Dermo technique outperformed SOTA algorithms when recognizing nine classes of PSLs. The Assist-Dermo system performed better than other competitive systems and can support dermatologists in the diagnosis of a wide variety of PSLs through dermoscopy. The Assist-Dermo model code is freely available on GitHub for the scientific community.

SqueezeNet for the forecasting of the energy demand using a combined version of the sewing training-based optimization algorithm.

With the introduction of various loads and dispersed production units to the system in recent years, the significance of precise forecasting for short, long, and medium loads have already been recognized. It is important to analyze the power system's performance in real-time and the appropriate response to changes in the electric load to make the best use of energy systems. Electric load forecasting for a long period in the time domain enables energy producers to increase grid stability, reduce equipment failures and production unit outages, and guarantee the dependability of electricity output. In this study, SqueezeNet is first used to obtain the required power demand forecast at the user end. The structure of the SqueezeNet is then enhanced using a customized version of the Sewing Training-Based Optimizer. A comparison between the results of the suggested method and those of some other published techniques is then implemented after the method has been applied to a typical case study with three different types of demands-short, long, and medium-term. A time window has been set up to collect the objective and input data from the customer at intervals of 20 min, allowing for highly effective neural network training. The results showed that the proposed method with 0.48, 0.49, and 0.53 MSE for Forecasting the short-term, medium-term, and long-term electricity provided the best results with the highest accuracy. The outcomes show that employing the suggested technique is a viable option for energy consumption forecasting.

Research on Small Sample Multi-Target Grasping Technology Based on Transfer Learning.

This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved.

Crystal search - feasibility study of a real-time deep learning process for crystallization well images.

To avoid the time-consuming and often monotonous task of manual inspection of crystallization plates, a Python-based program to automatically detect crystals in crystallization wells employing deep learning techniques was developed. The program uses manually scored crystallization trials deposited in a database of an in-house crystallization robot as a training set. Since the success rate of such a system is able to catch up with manual inspection by trained persons, it will become an important tool for crystallographers working on biological samples. Four network architectures were compared and the SqueezeNet architecture performed best. In detecting crystals AlexNet accomplished a better result, but with a lower threshold the mean value for crystal detection was improved for SqueezeNet. Two assumptions were made about the imaging rate. With these two extremes it was found that an image processing rate of at least two times, but up to 58 times in the worst case, would be needed to reach the maximum imaging rate according to the deep learning network architecture employed for real-time classification. To avoid high workloads for the control computer of the CrystalMation system, the computing is distributed over several workstations, participating voluntarily, by the grid programming system from the Berkeley Open Infrastructure for Network Computing (BOINC). The outcome of the program is redistributed into the database as automatic real-time scores (ARTscore). These are immediately visible as colored frames around each crystallization well image of the inspection program. In addition, regions of droplets with the highest scoring probability found by the system are also available as images.

Optimized deep learning vision system for human action recognition from drone images.

There are several benefits to constructing a lightweight vision system that is implemented directly on limited hardware devices. Most deep learning-based computer vision systems, such as YOLO (You Only Look Once), use computationally expensive backbone feature extractor networks, such as ResNet and Inception network. To address the issue of network complexity, researchers created SqueezeNet, an alternative compressed and diminutive network. However, SqueezeNet was trained to recognize 1000 unique objects as a broad classification system. This work integrates a two-layer particle swarm optimizer (TLPSO) into YOLO to reduce the contribution of SqueezeNet convolutional filters that have contributed less to human action recognition. In short, this work introduces a lightweight vision system with an optimized SqueezeNet backbone feature extraction network. Secondly, it does so without sacrificing accuracy. This is because that the high-dimensional SqueezeNet convolutional filter selection is supported by the efficient TLPSO algorithm. The proposed vision system has been used to the recognition of human behaviors from drone-mounted camera images. This study focused on two separate motions, namely walking and running. As a consequence, a total of 300 pictures were taken at various places, angles, and weather conditions, with 100 shots capturing running and 200 images capturing walking. The TLPSO technique lowered SqueezeNet's convolutional filters by 52%, resulting in a sevenfold boost in detection speed. With an F1 score of 94.65% and an inference time of 0.061 milliseconds, the suggested system beat earlier vision systems in terms of human recognition from drone-based photographs. In addition, the performance assessment of TLPSO in comparison to other related optimizers found that TLPSO had a better convergence curve and achieved a higher fitness value. In statistical comparisons, TLPSO surpassed PSO and RLMPSO by a wide margin.

SNELM: SqueezeNet-Guided ELM for COVID-19 Recognition.

(Aim) The COVID-19 has caused 6.26 million deaths and 522.06 million confirmed cases till 17/May/2022. Chest computed tomography is a precise way to help clinicians diagnose COVID-19 patients. (Method) Two datasets are chosen for this study. The multiple-way data augmentation, including speckle noise, random translation, scaling, salt-and-pepper noise, vertical shear, Gamma correction, rotation, Gaussian noise, and horizontal shear, is harnessed to increase the size of the training set. Then, the SqueezeNet (SN) with complex bypass is used to generate SN features. Finally, the extreme learning machine (ELM) is used to serve as the classifier due to its simplicity of usage, quick learning speed, and great generalization performances. The number of hidden neurons in ELM is set to 2000. Ten runs of 10-fold cross-validation are implemented to generate impartial results. (Result) For the 296-image dataset, our SNELM model attains a sensitivity of 96.35 ± 1.50%, a specificity of 96.08 ± 1.05%, a precision of 96.10 ± 1.00%, and an accuracy of 96.22 ± 0.94%. For the 640-image dataset, the SNELM attains a sensitivity of 96.00 ± 1.25%, a specificity of 96.28 ± 1.16%, a precision of 96.28 ± 1.13%, and an accuracy of 96.14 ± 0.96%. (Conclusion) The proposed SNELM model is successful in diagnosing COVID-19. The performances of our model are higher than seven state-of-the-art COVID-19 recognition models.

SNSVM: SqueezeNet-Guided SVM for Breast Cancer Diagnosis.

Breast cancer is a major public health concern that affects women worldwide. It is a leading cause of cancer-related deaths among women, and early detection is crucial for successful treatment. Unfortunately, breast cancer can often go undetected until it has reached advanced stages, making it more difficult to treat. Therefore, there is a pressing need for accurate and efficient diagnostic tools to detect breast cancer at an early stage. The proposed approach utilizes SqueezeNet with fire modules and complex bypass to extract informative features from mammography images. The extracted features are then utilized to train a support vector machine (SVM) for mammography image classification. The SqueezeNet-guided SVM model, known as SNSVM, achieved promising results, with an accuracy of 94.10% and a sensitivity of 94.30%. A 10-fold cross-validation was performed to ensure the robustness of the results, and the mean and standard deviation of various performance indicators were calculated across multiple runs. This model also outperforms state-of-the-art models in all performance indicators, indicating its superior performance. This demonstrates the effectiveness of the proposed approach for breast cancer diagnosis using mammography images. The superior performance of the proposed model across all indicators makes it a promising tool for early breast cancer diagnosis. This may have significant implications for reducing breast cancer mortality rates.

Internet of Medical Things-Based COVID-19 Detection in CT Images Fused with Fuzzy Ensemble and Transfer Learning Models.

One of the most difficult research areas in today's healthcare industry to combat the coronavirus pandemic is accurate COVID-19 detection. Because of its low infection miss rate and high sensitivity, chest computed tomography (CT) imaging has been recommended as a viable technique for COVID-19 diagnosis in a number of recent clinical investigations. This article presents an Internet of Medical Things (IoMT)-based platform for improving and speeding up COVID-19 identification. Clinical devices are connected to network resources in the suggested IoMT platform using cloud computing. The method enables patients and healthcare experts to work together in real time to diagnose and treat COVID-19, potentially saving time and effort for both patients and physicians. In this paper, we introduce a technique for classifying chest CT scan images into COVID, pneumonia, and normal classes that use a Sugeno fuzzy integral ensemble across three transfer learning models, namely SqueezeNet, DenseNet-201, and MobileNetV2. The suggested fuzzy ensemble techniques outperform each individual transfer learning methodology as well as trainable ensemble strategies in terms of accuracy. The suggested MobileNetV2 fused with Sugeno fuzzy integral ensemble model has a 99.15% accuracy rate. In the present research, this framework was utilized to identify COVID-19, but it may also be implemented and used for medical imaging analyses of other disorders.

Computer-aided diagnosis system for retinal disorder classification using optical coherence tomography images.

The incidence of vision impairment is rapidly increasing. Diagnosis and classifying retinal abnormalities in ophthalmological applications is a significant challenge. Using Optical Coherence Tomography (OCT), the study aims to develop a computer aided diagnosis system for detecting and classifying retinal disorders. Choroidal neovascularization, diabetic macular edema, drusen, and normal cases are the investigated groups. Both deep learning and machine learning are combined to build the system. The SqueezeNet neural network was modified to extract features. The Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Decision Tree (DT), and Ensemble Model (EM) algorithms were used for disorder classification. The Bayesian optimization technique was also used to determine the best hyperparameters for each model. The model' performance was evaluated through nine criteria using 12,000 OCT images. The results have demonstrated accuracies of 97.39, 97.47, 96.98, and 95.25% for the SVM, K-NN, DT, and EM, respectively. When results are compared to relevant studies in terms of accuracy and tested samples, they show superior performance. As a result, a novel computer-aided diagnosis system for detecting and classifying retinal diseases has been developed, reducing human error while also saving time.

Deep Transfer Learning Based Unified Framework for COVID19 Classification and Infection Detection from Chest X-Ray Images.

The presentation of the COVID19 has endangered several million lives worldwide causing thousands of deaths every day. Evolution of COVID19 as a pandemic calls for automated solutions for initial screening and treatment management. In addition to the thermal scanning mechanisms, findings from chest X-ray imaging examinations are reliable predictors in COVID19 detection, long-term monitoring and severity evaluation. This paper presents a novel deep transfer learning based framework for COVID19 detection and segmentation of infections from chest X-ray images. It is realized as a two-stage cascaded framework with classifier and segmentation subnetwork models. The classifier is modeled as a fine-tuned residual SqueezeNet network, and the segmentation network is implemented as a fine-tuned SegNet semantic segmentation network. The segmentation task is enhanced with a bioinspired Gaussian Mixture Model-based super pixel segmentation. This framework is trained and tested with two public datasets for binary and multiclass classifications and infection segmentation. It achieves accuracies of 99.69% and 99.48% for binary and three class classifications, and a mean accuracy of 83.437% for segmentation. Experimental results and comparative evaluations demonstrate the superiority of this unified model and signify potential extensions for biomarker definition and severity quantization.

Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation.

The evolution the novel corona virus disease (COVID-19) as a pandemic has inflicted several thousand deaths per day endangering the lives of millions of people across the globe. In addition to thermal scanning mechanisms, chest imaging examinations provide valuable insights to the detection of this virus, diagnosis and prognosis of the infections. Though Chest CT and Chest X-ray imaging are common in the clinical protocols of COVID-19 management, the latter is highly preferred, attributed to its simple image acquisition procedure and mobility of the imaging mechanism. However, Chest X-ray images are found to be less sensitive compared to Chest CT images in detecting infections in the early stages. In this paper, we propose a deep learning based framework to enhance the diagnostic values of these images for improved clinical outcomes. It is realized as a variant of the conventional SqueezeNet classifier with segmentation capabilities, which is trained with deep features extracted from the Chest X-ray images of a standard dataset for binary and multi class classification. The binary classifier achieves an accuracy of 99.53% in the discrimination of COVID-19 and Non COVID-19 images. Similarly, the multi class classifier performs classification of COVID-19, Viral Pneumonia and Normal cases with an accuracy of 99.79%. This model called the COVID-19 Super pixel SqueezNet (COVID-SSNet) performs super pixel segmentation of the activation maps to extract the regions of interest which carry perceptual image features and constructs an overlay of the Chest X-ray images with these regions. The proposed classifier model adds significant value to the Chest X-rays for an integral examination of the image features and the image regions influencing the classifier decisions to expedite the COVID-19 treatment regimen.

LeanNet: An Efficient Convolutional Neural Network for Digital Number Recognition in Industrial Products.

The remarkable success of convolutional neural networks (CNNs) in computer vision tasks is shown in large-scale datasets and high-performance computing platforms. However, it is infeasible to deploy large CNNs on resource constrained platforms, such as embedded devices, on account of the huge overhead. To recognize the label numbers of industrial black material product and deploy deep CNNs in real-world applications, this research uses an efficient method to simultaneously (a) reduce the network model size and (b) lower the amount of calculation without compromising accuracy. More specifically, the method is implemented by pruning channels and corresponding filters that are identified as having a trivial effect on the output accuracy. In this paper, we prune VGG-16 to obtain a compact network called LeanNet, which gives a 25× reduction in model size and a 4.5× reduction in float point operations (FLOPs), while the accuracy on our dataset is close to the original accuracy by retraining the network. Besides, we also find that LeanNet could achieve better performance on reductions in model size and computation compared to some lightweight networks like MobileNet and SqueezeNet, which are widely used in engineering applications. This research has good application value in the field of industrial production.

[Classification of Fetal Heart Rate Based on Poincare Plot and LSTM].

Fetal heart rate plays an essential role in maternal and fetal monitoring and fetal health detection. In this study, a method based on Poincare Plot and LSTM is proposed to realize the high performance classification of abnormal fetal heart rate. Firstly, the original fetal heart rate signal of CTU-UHB database is preprocessed via interpolation, then the sequential fetal heart rate signal is converted into Poincare Plot to obtain nonlinear characteristics of the signals, and then SquenzeNet is used to extract the features of Poincare Plot. Finally, the features extracted by SqueezeNet are classified by LSTM. And the accuracy, the true positive rate and the false positive rate are 98.00%, 100.00%, 92.30% respectively on 2 000 test set data. Compared with the traditional fetal heart rate classification method, all respects are improved. The method proposed in this study has good performance in CTU-UHB fetal monitoring database and has certain practical value in the clinical diagnosis of auxiliary fetal heart rate detection.

Classification of Fetal Heart Rate Based on Poincare Plot and LSTM / 中国医疗器械杂志

Fetal heart rate plays an essential role in maternal and fetal monitoring and fetal health detection. In this study, a method based on Poincare Plot and LSTM is proposed to realize the high performance classification of abnormal fetal heart rate. Firstly, the original fetal heart rate signal of CTU-UHB database is preprocessed via interpolation, then the sequential fetal heart rate signal is converted into Poincare Plot to obtain nonlinear characteristics of the signals, and then SquenzeNet is used to extract the features of Poincare Plot. Finally, the features extracted by SqueezeNet are classified by LSTM. And the accuracy, the true positive rate and the false positive rate are 98.00%, 100.00%, 92.30% respectively on 2 000 test set data. Compared with the traditional fetal heart rate classification method, all respects are improved. The method proposed in this study has good performance in CTU-UHB fetal monitoring database and has certain practical value in the clinical diagnosis of auxiliary fetal heart rate detection.

An expert system for brain tumor detection: Fuzzy C-means with super resolution and convolutional neural network with extreme learning machine.

Super-resolution, which is one of the trend issues of recent times, increases the resolution of the images to higher levels. Increasing the resolution of a vital image in terms of the information it contains such as brain magnetic resonance image (MRI), makes the important information in the MRI image more visible and clearer. Thus, it is provided that the borders of the tumors in the related image are found more successfully. In this study, brain tumor detection based on fuzzy C-means with super-resolution and convolutional neural networks with extreme learning machine algorithms (SR-FCM-CNN) approach has been proposed. The aim of this study has been segmented the tumors in high performance by using Super Resolution Fuzzy-C-Means (SR-FCM) approach for tumor detection from brain MR images. Afterward, feature extraction and pretrained SqueezeNet architecture from convolutional neural network (CNN) architectures and classification process with extreme learning machine (ELM) were performed. In the experimental studies, it has been determined that brain tumors have been better segmented and removed using SR-FCM method. Using the SquezeeNet architecture, features were extracted from a smaller neural network model with fewer parameters. In the proposed method, 98.33% accuracy rate has been detected in the diagnosis of segmented brain tumors using SR-FCM. This rate is greater 10% than the rate of recognition of brain tumors segmented with fuzzy C-means (FCM) without SR.

A Dual Neural Architecture Combined SqueezeNet with OctConv for LiDAR Data Classification.

Light detection and ranging (LiDAR) is a frequently used technique of data acquisition and it is widely used in diverse practical applications. In recent years, deep convolutional neural networks (CNNs) have shown their effectiveness for LiDAR-derived rasterized digital surface models (LiDAR-DSM) data classification. However, many excellent CNNs have too many parameters due to depth and complexity. Meanwhile, traditional CNNs have spatial redundancy because different convolution kernels scan and store information independently. SqueezeNet replaces a part of 3 × 3 convolution kernels in CNNs with 1 × 1 convolution kernels, decomposes the original one convolution layer into two layers, and encapsulates them into a Fire module. This structure can reduce the parameters of network. Octave Convolution (OctConv) pools some feature maps firstly and stores them separately from the feature maps with the original size. It can reduce spatial redundancy by sharing information between the two groups. In this article, in order to improve the accuracy and efficiency of the network simultaneously, Fire modules of SqueezeNet are used to replace the traditional convolution layers in OctConv to form a new dual neural architecture: OctSqueezeNet. Our experiments, conducted using two well-known LiDAR datasets and several classical state-of-the-art classification methods, revealed that our proposed classification approach based on OctSqueezeNet is able to provide competitive advantages in terms of both classification accuracy and computational amount.