Inception ResNet Research Articles

A fine-tuned adaptive weight deep dense meta stacked transfer learning model for effective cervical cancer prediction

Abstract In the digital world of remarkable technological advancements, the detection of cervical cancer at early stages is of important clinical significance as it can vastly improve the survival rate during treatment. Cervical cytopathology, often known as a Pap test is the frequently adopted screening method for cervical cancer. However, the test seems to be effective but investigation of images containing Pap smear with the help of a microscope is a difficult as well as laborious exercise. The procedure for the same demands an expert in the area and is often time-consuming. The serious pitfalls in subjective clinical evaluation evoke the need of developing an automated system for more reliable cervical cancer diagnosis. Therefore, the goal of this study primarily focuses on designing a Deep learning model to process the Pap smear images and correctly classify the cervical cells. For this purpose, firstly, a publically available dataset namely SIPaKMeD is utilized. Then, different data pre-processing methods are applied to intensify the data quality for effective analysis. Next, a novel stacking model is proposed that leverages a Support Vector Classifier (SVC) as a Meta model over a combination of different Transfer Learning Models including VGG16, ResNet101, InceptionV3, Xception, DenseNet169, and Inception ResNet. Furthermore, the dense layers are added to tune the underlying base transfer learning models to learn fine-tuned adaptive weights. The results obtained from experimental evaluation demonstrate the efficacy of the proposed stacking model by yielding the highest accuracy rate of 95.66% in comparison to other employed methods and existing state-of-the-art techniques.

Novel coronavirus pneumonia CT image classification based on inception ResNet

Novel coronavirus pneumonia CT image classification based on inception ResNet

XAIEnsembleTL-IoV: A new eXplainable Artificial Intelligence ensemble transfer learning for zero-day botnet attack detection in the Internet of Vehicles

The Internet of Vehicles (IoV) is a network of interconnected vehicles that use modern communication technologies to communicate with each other and the surrounding infrastructure. The IoV is a novel network that experiences a continuous emergence and evolution of various forms of attacks. This research addresses the growing challenge of detecting zero-day botnet attacks within the IoV, a complex network that enhances real-time communication among vehicles and surrounding infrastructure to improve traffic management, safety, and driving experiences. Traditional machine learning-based intrusion detection systems (IDS) for IoV face two key limitations: the requirement for large labeled datasets and the “black box” issue, where the reasoning behind model decisions is not transparent, reducing user and stakeholder confidence. To solve these problems, this research proposes an eXplainable Artificial Intelligence (XAI) Ensemble Transfer Learning (TL) model specifically for detecting zero-day attacks in IoV. The proposed model integrates deep Shapley Additive Explanations (SHAP), providing transparency and making decisions understandable to cybersecurity professionals. Additionally, the model employs hybrid bidirectional long-short-term memory with autoencoders (BiLAE) to reduce the dimensionality of IoV network traffic, improving computational efficiency. It also uses Barnacle Mating Optimizer (BMO) to optimize the hyper-parameters of deep learning models such as ResNet, Inception, Inception ResNet, and MobileNet Convolution neural network-transfer learning architecture (CNN-TL), enhancing detection capabilities without needing vast amounts of labeled data. Experimental results showed that the model performed with an accuracy of 100 %, precision of 100 %, recall of 100 %, F1-score of 100 %, and Matthew Correlation Coefficient of 100 % in binary-class situations for internal vehicular (CAN) networks and achieved 99.88 % accuracy and similarly high metrics in multi-class scenarios for external vehicular networks(N-BaIoT). Compared to state-of-the-art techniques, the model proved to be more effective in detecting zero-day botnet attacks, reducing reliance on large datasets. Unlike traditional black-box models, the XAI component of the ensemble model offers insight into the decision-making process. It allows network administrators and security experts to understand how specific patterns in the data contribute to detection, making the system more transparent. The solution is highly adaptable and scalable for real-time application, designed to operate efficiently even on IoV gateway electronic control units with limited computational power.

Prediction of combustion pressure with deep learning using flame images

Deep learning methods provide data-driven techniques for handling large amounts of combustion data, thus finding the hidden patterns underlying these data. This study aims to predict combustion pressure from flame images, which provide more comprehensive information about the combustion process than traditional pressure sensors. The flame images were captured from a single-cylinder 4-stroke optical gasoline direct injection (GDI) engine at 1000 rpm, 5.7 bar IMEP, and stoichiometric combustion conditions using a high-speed camera. To achieve this prediction, we employed five different models: EfficientNetB4, ResNet50, Ensemble Adversarial Inception ResNet, convolutional neural network (CNN), and CNN-XGBoost. The training dataset comprised 1350 flame images captured from a single-cylinder optical GDI engine across different combustion stages. To ensure robustness, 150 images were used for validation. The models were subjected to a testing set of 4500 flame images obtained from different cycles, to evaluate how well they could perform on new, unseen data. The results showed that EfficientNetB4 achieved an impressive R2 of 0.94 and a low RMSE of 0.70 compared to other tested models. Saliency analysis revealed that the model focuses on subtle flame characteristics and areas without intense flames, which suggests that it detects features invisible to the human eye. Additionally, the proposed deep learning approach is applied for the sake of monitoring cycle-to-cycle variations based on in-cylinder flame propagation where it is found that it produces high accuracy compared to those obtained through pressure sensors. Our findings are intended to advance the adoption of machine learning approaches for assisting in engine design and optimization.

Comparing Mask R-CNN backbone architectures for human detection using thermal imaging

We introduce a method for detecting humans in thermal imaging using an end-to-end deep learning model. Our objective is to optimize the human detection process in thermal imaging by investigating the mask region-based convolutional neural network (Mask R-CNN). The model, an advancement of the faster region-based convolutional neural network (Faster R-CNN), not only captures bounding boxes encompassing human subjects but also delineates segmentation masks around them. Our investigation extends to the evaluation and comparison of various convolutional neural networks for feature learning, like residual network (ResNet) and Inception ResNet, all integrated into the Mask R-CNN framework. Furthermore, the experimental results show that our proposed technique achieves high accuracy. Specifically, the Mask R-CNN model using ResNet50-V1 achieved the best results, with an F-value of 87.85%, a recall of 79.33%, and a precision of 98.41%.

A framework for classifying breast cancer via heterogenetic attention mechanism and optimized feature selection

Breast cancer poses a significant threat to women’s health, emphasizing the crucial role of timely detection. Traditional pathology reports, though widely used, face challenges prompting the development of automated Deep Learning (DL) tools. DL models, gaining traction in radiology, offer precise diagnoses; however, issues with generalization on varying dataset sizes persist. This paper introduces a computationally efficient DL framework, addressing dataset imbalance through a hybrid model design, ensuring both accuracy and speed in breast cancer image classification. Proposed model novel design excels in accuracy and generalization across medical imaging datasets, providing a robust tool for precise diagnostics. The proposed model integrates features from two classifiers, Inception ResNet V2 and Vision Transformers (ViT), to enhance the classification of breast cancer. This synergistic blend enhances adaptability, ensuring consistent performance across diverse dataset scales. A key contribution is the introduction of an Efficient Attention Mechanism within one of the classifiers, optimizing focus on critical features for improved accuracy and computational efficiency. Further, a Resource-Efficient Optimization model through feature selection is proposed, streamlining computational usage without compromising accuracy. Addressing the inherent heterogeneity within classifiers, our framework integrates high dimensional features comprehensively, leading to more accurate tumor class predictions. This consideration of heterogeneity marks a significant leap forward in precision for breast cancer diagnosis. An extensive analysis on datasets, BreakHis and BACH, that are imbalanced in nature is conducted by evaluating complexity, performance, and resource usage. Comprehensive evaluation using the datasets and standard performance metrics accuracy, precision, Recall, F1-score, MCC reveals the model’s high efficacy, achieving a testing accuracy of 0.9936 and 0.994, with precision, recall, F1-score and MCC scores of 0.9919, 0.987, 0.9898, 0.9852 and 0.989, 1.0, 0.993, 0.988 on the BreakHis and BACH datasets, respectively. Our proposed model outperforms state-of-the-art techniques, demonstrating superior accuracy across different datasets, with improvements ranging from 0.25% to 15% on the BACH dataset and from 0.36% to 15.02% on the BreakHis dataset. Our results position the framework as a promising solution for advancing breast cancer prediction in both clinical and research applications. The collective contributions, from framework and hybrid model design to feature selection and classifier heterogeneity consideration, establish a holistic and state-of-the-art approach, significantly improving accuracy and establishing optimization in breast cancer classification from MRI images. Future research for the DL framework in breast cancer image classification includes enhancing interpretability, integrating multi-modal data, and developing personalized treatments.

Result and Analysis of Soft Computing Techniques for Diagnosis of Skin Diseases

Abstract: A prevalent bodily issue that has a significant impact on people's lives is skin disease. An early and precise identification of the condition can assist patients in receiving proper care, hastening their recovery. Convolutional neural networks (CNN) powered by deep learning have recently made major advancements that have greatly increased the accuracy of illness categorization. This led to the motivation for this work, which used deep CNN architectures to identify two different skin conditions—eczema and psoriasis. Ten fold cross validation has been utilized to examine the performance of five distinct cutting-edge CNN architectures. With the Adam optimizer, the Inception ResNet v2 architecture achieves a maximum validation accuracy of 97.1%. The results of the performance matrices suggest that the model performs remarkably well in terms of diagnosing skin disorders. Additionally, the study demonstrates two approaches for the practical application of the implemented model. (i) CNN Approach ii) PCA Approach.

Inception ResNet v2 for Early Detection of Breast Cancer in Ultrasound Images

Breast cancer is one of the leading causes of death in women. Early detection through breast ultrasound images is important and can be improved using machine learning models, which are more accurate and faster than manual methods. Previous research has shown that the use of the CNN (Convolutional Neural Network) algorithm in breast cancer detection still does not achieve high accuracy. This study aims to improve the accuracy of breast cancer detection using the Inception ResNet v2 transfer learning method and data augmentation. The data is divided into training, validation and testing data consisting of 3 classes, namely Benign, Malignant and Normal. The augmentation process includes rotation, zoom, and rescale. The model trained using CNN and Inception ResNet v2 showed good performance by producing the highest accuracy of 89.72% in the training data evaluation data and getting 90% accuracy in the prediction test stage with data testing. This study shows that the combination of data augmentation and the Inception ResNet v2 architecture can improve the accuracy of breast cancer detection in CNN models.

Enhancing image watermarking efficiency through advanced deep learning: A novel approach with modified Res-Ception blocks and practical applications in modern scenarios

In recent years, digital media has become a prevalent form of information exchange, necessitating robust measures for privacy, data safety, and copyright protection. Image watermarking is one of the tools that can be employed for these tasks. Research on blind image watermarking techniques is lacking, and there is a gap between theoretical findings and practical implementations to address contemporary issues such as photo metadata privacy, AI generated image recognition, etc. The proposed research introduces a revolutionary deep learning-based image watermarking approach in order to address these issues. This scheme is designed to overcome the contemporary challenges related to image watermarking by being blind, efficient and robust. It also has an improved PSNR and beats state-of-the-art in various attacks. The model outperforms existing deep learning frameworks in terms of fidelity. All these are achieved by creating a modified and much more efficient form of Inception Resnet block, coined ResCeption Block, for use in effective learning of watermarking networks. The research also presents an application of watermarking in the identification of AI generated images and proposes a novel and robust algorithm for metadata encryption of digital images and enforce digital media security. Rigorous testing has been performed on benchmark datasets, and comparisons have been done against state-of-the-art and a PSNR of 43.12 dB has been achieved.

MEDI-NET: CLOUD-BASED FRAMEWORK FOR MEDICAL DATA RETRIEVAL SYSTEM USING DEEP LEARNING

Medical data retrieval is becoming increasingly crucial, aiding physicians and domain experts in more effectively accessing knowledge and information related to medicine and facilitating informed decision-making. The centralized architectures need help with scalability and real-time indexing, leading to extended retrieval times and decreased efficiency. To address these issues, a novel MEdical Data retrieval using Inception resNET (MEDI-NET) has been proposed to retrieve medical data efficiently. The proposed system introduces a deep learning network for a dynamic poly-indexing model and concurrent indexing, ensuring the real-time retrieval of the latest medical records. EMRBots and MIMIC-III are the two datasets used to compare the performance of the proposed MEDI-NET approach with existing MRCG, HCAC-EHR, and FedCBMIR method, which is implemented using Python. The effectiveness of the proposed MEDI-NET approach has been determined using evaluation metrics such as precision, accuracy, recall, F1-score, indexing time, and retrieval time. Comparative analysis with existing methods demonstrates superior precision, accuracy, recall, and F1 score for the proposed method. Additionally, the proposed system exhibits reduced indexing and retrieval times, showcasing its efficiency in handling large-scale medical data. The proposed MEDI-NET approach's accuracy is 0.60 %, 9.87 %, and 21.1 % higher than the existing MRCG, HCAC-EHR, and FedCBMIR techniques, respectively.

Model‐driven neural network based for HPO‐MIMO channel estimation

AbstractIntegrated Sensing and Communications (ISAC) need to process data streams in high‐speed sensor data acquisition or high‐speed wireless communications. To process the data can require more computing and communication resources, resulting in higher power consumption. Halved‐Phase Only Multiple Input Multiple Output (HPO‐MIMO) communication technology can solve this problem by using low‐power nonlinear detection devices. In ISAC, Channel Estimation (CE) technology can provide key channel characteristics and state information for sensing and collaborative work of perception and communication tasks. However, HPO‐MIMO system cannot realize CE using traditional receiver schemes because of the missing amplitude. In order to solve this problem, two HPO‐MIMO CE schemes based on model‐driven deep learning are proposed in this paper. The proposed schemes include a Densely Residual Network (DRN) and a Inception‐Resnet (IR), which is suitable for the case of sufficient data and insufficient data, respectively. The simulation results show that the performance of DRN based scheme is better than that of IR based scheme when the data amount is sufficient, and the performance of IR based scheme is better when the dataset is small. In addition, the proposed CE schemes work well with a range of antenna sizes and distances.

Improved Diagnostic Accuracy of Thyroid Fine-Needle Aspiration Cytology with Artificial Intelligence Technology.

Background: Artificial intelligence (AI) is increasingly being applied in pathology and cytology, showing promising results. We collected a large dataset of whole slide images (WSIs) of thyroid fine-needle aspiration cytology (FNA), incorporating z-stacking, from institutions across the nation to develop an AI model. Methods: We conducted a multicenter retrospective diagnostic accuracy study using thyroid FNA dataset from the Open AI Dataset Project that consists of digitalized images samples collected from 3 university hospitals and 215 Korean institutions through extensive quality check during the case selection, scanning, labeling, and reviewing process. Multiple z-layer images were captured using three different scanners and image patches were extracted from WSIs and resized after focus fusion and color normalization. We pretested six AI models, determining Inception ResNet v2 as the best model using a subset of dataset, and subsequently tested the final model with total datasets. Additionally, we compared the performance of AI and cytopathologists using randomly selected 1031 image patches and reevaluated the cytopathologists' performance after reference to AI results. Results: A total of 10,332 image patches from 306 thyroid FNAs, comprising 78 malignant (papillary thyroid carcinoma) and 228 benign from 86 institutions were used for the AI training. Inception ResNet v2 achieved highest accuracy of 99.7%, 97.7%, and 94.9% for training, validation, and test dataset, respectively (sensitivity 99.9%, 99.6%, and 100% and specificity 99.6%, 96.4%, and 90.4% for training, validation, and test dataset, respectively). In the comparison between AI and human, AI model showed higher accuracy and specificity than the average expert cytopathologists beyond the two-standard deviation (accuracy 99.71% [95% confidence interval (CI), 99.38-100.00%] vs. 88.91% [95% CI, 86.99-90.83%], sensitivity 99.81% [95% CI, 99.54-100.00%] vs. 87.26% [95% CI, 85.22-89.30%], and specificity 99.61% [95% CI, 99.23-99.99%] vs. 90.58% [95% CI, 88.80-92.36%]). Moreover, after referring to the AI results, the performance of all the experts (accuracy 96%, 95%, and 96%, respectively) and the diagnostic agreement (from 0.64 to 0.84) increased. Conclusions: These results suggest that the application of AI technology to thyroid FNA cytology may improve the diagnostic accuracy as well as intra- and inter-observer variability among pathologists. Further confirmatory research is needed.

A Stereovision-based Approach for Retrieving Variable Force Feedback in Robotic-Assisted Surgery Using Modified Inception ResNet V2 Networks

The surge of haptic technology has greatly impacted Robotic-assisted surgery in recent years due to its inspirational advancement in the field. Delivering tactile feedback to the surgeon has a significant role in improving the user experience in RAMIS. This work proposes a Modified inception ResNet network along with dimensionality reduction to regenerate the variable force produced during the surgical intervention. This work collects the relevant dataset from two ex vivo porcine skins and one ex vivo artificial skin for the validation of the results. The proposed framework is used to model both spatial and temporal data collected from the sensors, tissue, manipulators, and surgical tools. The evaluations are based on three distinct datasets with modest variations in tissue properties. The results of the proposed framework show an improvement of force prediction accuracy by 10.81% over RNN, 6.02% over RNN + LSTM, and 3.81% over the CNN + LSTM framework, and torque prediction accuracy by 12.41% over RNN, 5.75% over RNN + LSTM, and 3.75% over CNN + LSTM. The sensitivity study demonstrates that features such as torque (96.93%), deformation (94.02%), position (93.98%), vision (92.12%), stiffness (87.95%), tool diameter (89.24%), rotation (65.10%), and orientation (62.51%) have respective influences on the anticipated force. It was observed that the quality of the predicted force improved by 2.18% when performing feature selection and dimensionality reduction on features collected from tool, manipulator, tissue, and vision data and processing them simultaneously in all four architectures. The method has potential applications for online surgical tasks and surgeon training.

A supervised learning algorithm based on the quasi-Bayesian method for the probability density functions and application for medical data

This study proposes a new supervised learning algorithm for probability density functions (PDFs) and effectively applies it to medical images. The proposed algorithm is demonstrated step by step, illustrated with a numerical example, and proofed the convergence. This algorithm contributes significantly to the field of recognition in four key areas. The first contribution is the improvement of determining prior probabilities by establishing a method based on the fuzzy relationship between each classified PDF and groups within the training set through cluster analysis technique. The next contribution involves developing a new measure to evaluate the level of similarity between the classified PDFs and the considered groups. Another contribution is the establishment of a new classification principle, quasi-Bayes, for PDFs. The final contribution of this study is the application of the proposed algorithm to both numerical and image data, where objects are represented as representative PDFs. Practical applications on various medical datasets with different characteristics have demonstrated the outstanding advantages of the proposed algorithm over other methods, including traditional statistics, machine learning, and deep learning approaches, based on metrics such as ACC, AUC, F1-Score, and One-way ANOVA test. Specifically, experimental results of the Skin cancer data show that the proposed algorithm achieved an ACC index of 98.024%, higher than other methods, including ResNet-50, Inception ResNet V2, and CNN with 97.33%, 97.815%, and 80.702%, respectively. Similarly, the proposed algorithm also obtained notable results for other indices such as AUC and F1-Score. Additionally, we also obtained similar results for the Brain tumour dataset.

ENHANCING DEEPFAKE DETECTION: LEVERAGING MTCNN AND INCEPTION RESNET

In response to the escalating threat posed by manipulated facial imagery in the digital age, our research project is dedicated to developing an advanced framework for the detection and classification of such content, augmented by a proactive user reporting mechanism. Leveraging state-of-the-art deep learning models like Multi-Task Cascaded Convolutional Networks (MTCNN) and InceptionResnetV1, our framework achieves an impressive accuracy rate of 92% in distinguishing between genuine and manipulated faces. The integration of explainability methods such as Grad-CAM enhances model interpretability, empowering users to understand model predictions. Additionally, our user-centric reporting interface enables active user participation in identifying and flagging potentially manipulated content, fostering transparency and accountability in digital media platforms. With the continued proliferation of deepfake technology, our research endeavors not only advance facial image analysis techniques but also uphold principles of trust and integrity in the digital realm, aiming to safeguard the credibility of information dissemination through vigilance, innovation, and collaborative action. Keywords: Deepfake detection, Facial image manipulation, Deep learning models, User reporting mechanism, Model interpretability, Transparency in digital media, Trust and integrity, Information dissemination, Vigilance, Collaborative action.

Mobilenet, inception ResNet and GoogleNet for epilepsy detection using spectrogram images

Epilepsy is considered the most common cerebral disorder, around 1% of the worldwide population suffer from it. Recently, detection of epilepsy has attracted more and more attention. It has become a hastily increasing problem that can worsen their conditions which necessitate a specific and crucial attention where the symptoms can be an impaired awareness or motor symptoms. Besides that, the difficult process of manual inspection of electroencephalography electroencephalogram (EEG). This paper proposes using transfer learning models to detect both normal and epileptic brain activity and auto-classify signals from the brain. The models considered for this study are GoogleNet, MobileNet, and inception residual neural network inception ResNet. These models were associated with seven different classifiers such as discriminant. These classifiers were tested, analyzed and compared with each other. The efficiency of models is comparatively evaluated through result using multiple metrics. We therefore attained an accuracy of 96.53%, a precision of 97.18%, a false positive rate of 2.78% and an F1-score of 96.50%. Finally, comparison of the suggested approach with existing research shows that the performance of epilepsy classification has been markedly enhanced.

Estimating Acceleration from a Single Uniform Linear Motion-Blurred Image using Homomorphic Mapping and Machine Learning

Context: Vision-based measurement (VBM) systems are becoming popular as an affordable and suitable alternative for scientific and engineering applications. When cameras are used as instruments, motion blur usually emerges as a recurrent and undesirable image degradation, which in fact contains kinematic information that is usually dismissed. Method: This paper introduces an alternative approach to measure relative acceleration from a real invariant uniformly accelerated linear motion-blurred image. This is done by using homomorphic mapping to extract the characteristic Point Spread Function (PSF) of the blurred image, as well as machine learning regression. A total of 125 uniformly accelerated motion-blurred pictures were taken in a light- and distance-controlled environment, at five different accelerations ranging between 0,64 and 2,4 m/s2. This study evaluated 19 variants such as tree ensembles, Gaussian processes (GPR), and linear, support vector machine (SVM), and tree regression. Results: The best RMSE result corresponds to GPR (Matern 5/2), with 0,2547 m/s2 and a prediction speed of 530 observations per second (obs/s). Additionally, some novel deep learning methods were used to obtain the best RMSE value (0,4639 m/s2 for Inception ResNet v2, with a prediction speed of 11 obs/s. Conclusions: The proposed method (homomorphic mapping and machine learning) is a valid alternative for calculating acceleration from invariant motion blur in real-time applications when additive noise is not dominant, even surpassing the deep learning techniques evaluated.

A multiclass deep learning algorithm for healthy lung, Covid-19 and pneumonia disease detection from chest X-ray images

A crucial step in the battle against the coronavirus disease 2019 (Covid-19) pandemic is efficient screening of the Covid affected patients. Deep learning models are used to improve the manual judgements made by healthcare professionals in classifying Chest X-Ray (CXR) images into Covid pneumonia, other viral/bacterial pneumonia, and normal images. This work uses two open source CXR image dataset having a total of 15,153 (dataset 1), and 4575 (dataset 2) images respectively. We trained three neural network models with a balanced subset of dataset 1 (1345 images per class), balanced dataset 2 (1525 images per class), and an unbalanced full dataset 1. The models used are VGG16 and Inception Resnet (IR) using transfer learning and a tailor made Convolutional Neural Network (CNN). The first model, VGG16 gives an accuracy, sensitivity, specificity, and F1 score of 96%, 97.8%, 95.92%, 97% respectively. The second model, IR gives an accuracy, sensitivity, specificity and F1 score of 97%, 98.51%, 97.28%, 99% respectively. The third and best proposed model, CNN gives an accuracy, sensitivity, specificity, and F1 score of 97%, 98.21%, 96.62%, 98% respectively. These performance metrics were obtained for the balanced dataset 1 and all models used 80:10:10 cross validation technique. The highest accuracy using CNN for all the three datasets are 97%, 96%, and 93% respectively. Gradient-weighted Class Activation Mapping (Grad-CAM) is used to ensure that the model uses genuine pathology markers to generalize.

Human Skin Disease Detection Using Machine Learning

Abstract: In this research, I want to improve deep convolution neural networks that have been successful with the ImageNet dataset at categorizing seven different types of skin lesions using the HAM10000 dataset, which has 10,000 dermatoscopic pictures. With VGG16, Inception V3, Inception ResNet V2, and Dense Net 201, the top layers were fine-tuned.

A cross-domain intelligent fault diagnosis method based on feature transfer with improved Inception ResNet for rolling bearings under varying working condition

A cross-domain intelligent fault diagnosis method based on feature transfer with improved Inception ResNet for rolling bearings under varying working condition