Sensitivity And Specificity Research Articles

Label flipping attacks in hierarchical federated learning for intrusion detection in IoT

ABSTRACT Federated learning (FL) is a promising approach for distributed training of deep neural networks within Internet of Things (IoT) environments, where the data generated by IoT devices stays local, and only model updates are communicated to a central server. This methodology is particularly relevant for intrusion detection systems in IoT networks, where security is paramount. However, the decentralized nature of FL introduces vulnerabilities, such as the risk of data poisoning by malicious participants. In this paper, we propose a hierarchical federated learning to reduce communication overhead and improve privacy by limiting data spread. We further explore the impact of label-flipping attacks on hierarchical FL systems used in IoT-based intrusion detection. We focus on scenarios where a subset of malicious participants attempts to degrade the global model’s performance by submitting corrupted model updates based on intentionally mislabeled data. Our findings reveal significant decreases in classification accuracy by 10.53% and recall rates, even with a minimal number of compromised participants, primarily affecting the specific classes targeted by the attackers. We further examine how the availability of these malicious nodes influences the attack’s success. To counteract these threats, we introduce a defense mechanism that successfully identifies all malicious clients and mitigates their impact. As a result, the global model’s accuracy is maintained at the original 95% level found during training without the presence of malicious clients, thereby enhancing the resilience of federated learning models in IoT security applications.

Radiation Pneumonitis Prediction Using Dual-Modal Data Fusion Based on Med3D Transfer Network.

Radiation pneumonitis (RP) is an inflammatory reaction in the lungs caused by radiation therapy. The etiology of RP is complex and varied, making it challenging to establish accurate predictive models for RP. The aim of this study is to develop a dual-modal prediction model for RP using pre-radiotherapy CT images of the patient's lungs, along with clinical and dose data. In this paper, an RP prediction model utilizing dual-modal data is proposed. Firstly, for CT image data, the Med3D transfer network, trained on a large-scale medical dataset, is employed to extract CT image features. To adapt the transfer network for the RP task, the last convolutional block, which incorporates the 3D channel attention mechanism, is trained and saved as the optimal model for extracting deep features once training stabilizes. Subsequently, an autoencoder (AE) is employed to compress the deep features to reduce their dimensionality. Secondly, for clinical and dose features, univariate analysis and lasso regression are used to screen the features. Finally, the two groups of features are multiplied by their respective adaptive rates to achieve data fusion, and then input into the binary classification model for training and prediction. The KAN classifier with adaptive feature fusion demonstrates superior performance, achieving precision rates of 74% and 76%, a recall rate of 73%, and an AUC of 86%. These results surpass those obtained from single-modality approaches. The experimental results on a dataset of 117 chest cancer patients receiving radiotherapy show that the dual-modal data fusion model can predict RP more effectively than single-modality models.

Puzzle sine cosine optimization-based secure communication and brain tumor classification in IoT‐healthcare system

A brain tumor (BT) refers to an irregular accumulation of cells within the brain that proliferates uncontrollably, resulting in the formation of a mass. The accurate classification and early detection are important for effective treatment. In previous researches, the BT exhibited diverse features in terms of size, shape, and location. Moreover, the images used for segmentation, which suffered from image noise, low contrast, and shifting intensities within tissues. These issues are overcome by developing an effective method in this paper named Puzzle Sine Cosine Optimization enabled Deep Kronecker Network (PSCO-DKN) for classifying BT in the Internet of Things (IoT) healthcare system. Firstly, an IoT network is simulated, where the IoT device is used to capture the patient’s Magnetic Resonance Imaging (MRI) images. Further, the images are routed to the Base Station (BS) by employing PSCO. The routing is accomplished by contemplating several fitness parameters including delay, energy, and distance. At the BS, the process for BT classification is implemented as follows. Initially, the pre-processing is done by utilizing the median filter. Afterwards, the segmentation process is done by applying Spatial Attention U-Net (SA-Unet). After that, Statistical features and Shape Local Binary Texture (SLBT) are extracted. At last, BT classification is performed by utilizing the DKN, which is structurally optimized by using PSCO developed by the hybridization of Puzzle Optimization Algorithm (POA) and Sine Cosine Algorithm (SCA). Finally, PSCO-DKN attained superior outcomes of True Negative Rate (TNR) at 90.9 %, True Positive Rate (TPR) at 92.6 %, and accuracy at 87.7 %.

CRH-YOLO for precise and efficient detection of gastrointestinal polyps

Gastrointestinal polyps are early indicators of many significant diseases within the digestive system, and timely detection of these polyps is crucial for preventing them. Although clinical gastrointestinal endoscopy and interventions help reduce the risk of malignancy, most current methods fail to adequately address the uncertainties and scale issues associated with the presence of polyps, posing a threat to patients’ health. Therefore, this paper proposes a novel single-stage method for polyp detection. Specifically, by designing the CRFEM, the network’s ability to perceive contextual information about polyp targets is enhanced. Additionally, the RSPPF is designed to assist the network in more meticulously completing the fusion of multi-scale polyp features. Finally, one detection head is removed from the original model to reduce a substantial number of parameters, and a high-dimensional feature compensation structure is designed to address the decline in recall rate caused by the absence of the detection head. Experiments were conducted using public datasets such as Kvasir-seg, which includes gastric and intestinal polyps. The results indicate that CRH-YOLO achieves 88.8%, 86.0%, and 90.7% on three key metrics: Precision (P), Recall (R), and mean average precision at 0.5 (map@.5), significantly outperforming current mainstream detection models like YOLOv8n. Notably, CRH-YOLO improves the map@.5 metric by 2.4% compared to YOLOv8n. Furthermore, the model demonstrates excellent performance in detecting smaller or less obvious polyps, providing an effective solution for the early detection and prediction of polyps.

Hybrid deep learning-based skin cancer classification with RPO-SegNet for skin lesion segmentation

ABSTRACT Skin melanin lesions are typically identified as tiny patches on the skin, which are impacted by melanocyte cell overgrowth. The number of people with skin cancer is increasing worldwide. Accurate and timely skin cancer identification is critical to reduce the mortality rates. An incorrect diagnosis can be fatal to the patient. To tackle these issues, this article proposes the Recurrent Prototypical Object Segmentation Network (RPO-SegNet) for the segmentation of skin lesions and a hybrid Deep Learning (DL) – based skin cancer classification. The RPO-SegNet is formed by integrating the Recurrent Prototypical Networks (RP-Net), and Object Segmentation Networks (O-SegNet). At first, the input image is taken from a database and forwarded to image pre-processing. Then, the segmentation of skin lesions is accomplished using the proposed RPO-SegNet. After the segmentation, feature extraction is accomplished. Finally, skin cancer classification and detection are accomplished by employing the Fuzzy-based Shepard Convolutional Maxout Network (FSCMN) by combining the Deep Maxout Network (DMN), and Shepard Convolutional Neural Network (ShCNN). The established RPO-SegNet+FSCMN attained improved accuracy, True Negative Rate (TNR), True Positive Rate (TPR), dice coefficient, Jaccard coefficient, and segmentation analysis of 91.985%, 92.735%, 93.485%, 90.902%, 90.164%, and 91.734%.

Enhancing pancreatic tumor delineation using dual-energy CT-derived extracellular volume fraction map

Precise identification of pancreatic tumors is challenging for radiotherapy planning due to the anatomical variability of the tumor and poor visualization of the tumor on 3D cross-sectional imaging. Low extracellular volume fraction (ECVf) correlates with poor vasculature uptake and possible necrosis or hypoxia in pancreatic tumors. This work investigates the feasibility of delineating pancreatic tumors using ECVf spatial distribution maps derived from contrast enhanced dual-energy CT (DECT). Data acquired from radiotherapy simulation of 12 pancreatic cancer patients, using a dual source DECT scanner, were analyzed. For each patient, an ECVf distribution of the pancreas was computed from the simultaneously acquired low and high energy DECT series during the late arterial contrast phase combined with the patient's hematocrit level. Volume of interest (VECVf) maps in ECVf distribution of pancreas were identified by applying an appropriate threshold condition and a connected components clustering algorithm. The obtained VECVf was compared with the clinical gross tumor volume (GTV) using the positive predictive value (PPV), Dice similarity coefficient (DSC), mean distance to agreement (MDA) and true positive rate (TPR). As a proof of concept, our hypothetical threshold condition based on the first quartile separation of the ECVf distribution to find VECVf of the pancreas elucidates the tumor volume within the pancreas. Notably, 7 out of 12 cases studied for VECVf matched well with the GTV and the mean PPV of 0.83±0.12. The mean MDA (2.83±1.0) of the cases confirms that VECVf lies within the tolerance for comparing to the pancreatic GTV. For the remaining 5 cases, the VECVf is substantially affected by other compounding factors, e.g., large cysts, dilate ducts, and thus did not align with the GTVs. This work demonstrated the promising application of the ECVf map, derived from contrast enhanced DECT, to help delineate tumor target for RT planning of pancreatic cancer.

Hybrid similarity based feature selection and Cascade deep maxout fuzzy network for Autism Spectrum Disorder detection using EEG signal

Autism Spectrum Disorder (ASD) is a neurological disorder that influences a person’s comprehension and way of behaving. It is a lifetime disability that cannot be completely treated using any therapy up to date. Nevertheless, in time identification and continuous therapies have a huge effect on autism patients. The existing models took a long time to confirm the diagnosis process and also, it is highly complex to differentiate autism from various developmental disorders. To facilitate early diagnosis by providing timely intervention, saving healthcare costs and reducing stress for the family in the long run, this research introduces an affordable and straightforward diagnostic model to detect ASD using EEG and deep learning models. Here, a hybrid deep learning model called Cascade deep maxout fuzzy network (Cascade DMFN) is proposed to identify ASD and it is achieved by the integration of Deep Maxout Network (DMN) and hybrid cascade neuro-fuzzy. Moreover, hybrid similarity measures like Canberra distance and Kumar-hassebrook is employed to conduct the feature selection technique. Also, the EEG dataset and BCIAUT_P300 dataset are used for analyzing the designed Cascade DMFN for detecting Autism Spectrum disorder. The designed Cascade DMFN has outperformed other classical models by yielding a high accuracy of 0.930, Negative Predictive Value (NPV) of 0.919, Positive Predictive Value (PPV) of 0.923, True Negative Rate (TNR) of 0.926, and True Positive Rate (TPR) of 0.934.

Automated blood cancer detection models based on EfficientNet-B3 architecture and transfer learning

In blood smear images, there are difficulties in diagnosing blood cancer diseases like leukemia and lymphoma because of their various forms that appear in the human body. In this paper, a method for automatic detection of blood cancer is suggested that uses the EfficientNet-B3 architecture along with transfer learning techniques to improve accuracy and efficiency. We first fine-tuned the EfficientNet-B3 model, which was pre-trained on a large dataset consisting of annotated blood smear images, to capture pertinent features linked with blood malignant cells. To expedite the training process and adapt the model to our task, we use transfer learning. The proposed approach’s results from our experiments show that it outperforms traditional deep learning models and state-of-the-art methods in blood cancer detection. Additionally, with high precision and recall rates, this model also detects different types of blood cancers with robustness in its performance since its accuracy is over 99%. This means that when used together with the EfficientNet-B3 architecture, transfer learning can help the developed methods generalize among different types of blood cancers and conditions.

Multi-spectral Remote Sensing Image Fusion Method Based on Gradient Moment Matching

Image fusion is a popular research direction in the field of computer vision. Traditional image fusion algorithms can achieve good results in fusing grayscale images, but it is difficult to achieve ideal results in processing multi-spectral images. To address the shortcomings of multi-spectral image fusion, this study proposes a low computational complexity and low latency multi-spectral image fusion model by utilizing a multi-step degree moment matching algorithm and a generative adversarial network for fusion. Through experiments, it was found that the F1 score of the GAN-MMN model on the TinyPerson dataset was 89.79%, with an average recall rate of 89.76%. The GAN-MMN performance was higher than that of the control model. Meanwhile, the GAN-MMN model also exhibited superior performance in high-frequency feature extraction and time delay compared to the control model. According to the experimental results, the proposed multi-spectral remote sensing image fusion model had a high feature extraction effect, and its recall rate and F1 score were better than the control model, so the research model had a certain progressiveness. The proposal of this model gives a new approach for the processing of multi-spectral remote sensing images, effectively promoting the development of the computer vision industry.

HOLISMOKES

While supervised neural networks have become state of the art for identifying the rare strong gravitational lenses from large imaging data sets, their selection remains significantly affected by the large number and diversity of non-lens contaminants. This work evaluates and compares systematically the performance of neural networks in order to move towards a rapid selection of galaxy-scale strong lenses with minimal human input in the era of deep, wide-scale surveys. We used multiband images from PDR2 of the Hyper-Suprime Cam (HSC) Wide survey to build test sets mimicking an actual classification experiment, with 189 securely-identified strong lenses from the literature over the HSC footprint and 70 910 non-lens galaxies in COSMOS covering representative lens-like morphologies. Multiple networks were trained on different sets of realistic strong-lens simulations and non-lens galaxies, with various architectures and data preprocessing, mainly using the deepest gri-bands. Most networks reached excellent area under the Receiver Operating Characteristic (ROC) curves on the test set of 71 099 objects, and we determined the ingredients to optimize the true positive rate for a total number of false positives equal to zero or 10 (TPR0 and TPR10). The overall performances strongly depend on the construction of the ground-truth training data and they typically, but not systematically, improve using our baseline residual network architecture presented in Paper VI (Cañameras et al., A&A, 653, L6). TPR0 tends to be higher for ResNets (≃ 10–40%) compared to AlexNet-like networks or G-CNNs. Improvements are found when (1) applying random shifts to the image centroids, (2) using square-root scaled images to enhance faint arcs, (3) adding z-band to the otherwise used gri-bands, or (4) using random viewpoints of the original images. In contrast, we find no improvement when adding g – αi difference images (where α is a tuned constant) to subtract emission from the central galaxy. The most significant gain is obtained with committees of networks trained on different data sets, with a moderate overlap between populations of false positives. Nearly-perfect invariance to image quality can be achieved by using realistic PSF models in our lens simulation pipeline, and by training networks either with large number of bands, or jointly with the PSF and science frames. Overall, we show the possibility to reach a TPR0 as high as 60% for the test sets under consideration, which opens promising perspectives for pure selection of strong lenses without human input using the Rubin Observatory and other forthcoming ground-based surveys.

Cybersecurity on social media platforms: The use of deep learning methodologies for detecting anomalous user behavior

The exponential growth of social media platforms has brought unprecedented opportunities for global communication, networking, and information exchange. However, this expansion has also given rise to significant challenges, particularly in identifying and mitigating anomalous or malicious user behaviors such as spamming, cyberbullying, and misinformation dissemination. Traditional anomaly detection methods, which often rely on rule-based systems or basic statistical models, have proven inadequate in addressing the complex, dynamic, and evolving nature of user behavior on these platforms. In response, this paper explores the application of deep learning methodologies—specifically Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTMs), Autoencoders, and Generative Adversarial Networks (GANs)—for detecting anomalous behavior in social media environments. We present a novel deep learning architecture that integrates these models to enhance the detection accuracy of behavioral anomalies. By leveraging large-scale datasets and advanced feature extraction techniques, our approach demonstrates significant improvements over traditional methods, with higher precision, recall, and overall detection rates. The proposed model's ability to adapt to new and emerging patterns of behavior underscores its potential for real-world application in monitoring social media platforms. This research contributes to the growing body of literature on deep learning for cybersecurity and digital trust, offering a robust solution for maintaining the integrity of online social spaces. Our findings suggest that the implementation of these advanced methodologies can provide a more secure and reliable social media environment, benefiting both users and platform providers alike.

Emerging Trends in Real-time Recommendation Systems: A Deep Dive into Multi-behavior Streaming Processing and Recommendation for E-commerce Platforms

This paper aims to assess the effectiveness of recommendation systems, focusing on multi-behavior streaming processing to enhance accuracy. It studies recommendation system performance using AI and data science, focusing on user behaviour, algorithm refinement, and satisfaction. E-commerce, streaming, and social media datasets with 93 anonymous participants were employed in experiments. These files from 93 anonymized users show typical internet use. Data anonymization and strict data management ensured anonymity. These databases track clicks, views, purchases, and ratings for empirical research and model evaluation. Collaborative filtering, matrix factorization, and TensorFlow/Keras train and assess application-specific recommendation models. Multi-behavior streaming processing and recommendation accounts assess each method's pros and downsides, system correctness, efficacy, and user involvement. The outcome compares domain-wide recommendation system precision, recall, NDCG, and conversion rate. Multi-behavior streaming processing adapts to user preferences and interactions to improve model accuracy and adaptability. Multi-behavior streaming processing improved model accuracy and flexibility by reacting to user inputs and choices. With error margins for all significant metrics, statistical significance was confirmed. The findings suggest that recommendation systems with real-time adaptation and multi-behavior streaming processing can improve user satisfaction and engagement in the changing digital landscape. It encourages algorithm advancement, model interpretation, user-centric evaluation, and ethics to improve information retrieval and personalisation. The study concluded that algorithm refinement, transparent model interpretation, user-centric evaluation, and ethical problems including data protection and bias mitigation increase information retrieval and personalisation. For durable and flexible recommendation systems, research should improve multi-behavior processing and sectoral applications.

A Cost-Effective Blind Spot Detection System with High Recall Rate using Deep Learning and a Comparative Analysis of Implementation Hardware Platforms

A Cost-Effective Blind Spot Detection System with High Recall Rate using Deep Learning and a Comparative Analysis of Implementation Hardware Platforms

Fast Quality Detection of Astragalus Slices Using FA-SD-YOLO

Quality inspection is a pivotal component in the intelligent sorting of Astragalus membranaceus (Huangqi), a medicinal plant of significant pharmacological importance. To improve the precision and efficiency of assessing the quality of Astragalus slices, we present the FA-SD-YOLO model, an innovative advancement over the YOLOv8n architecture. This model introduces several novel modifications to enhance feature extraction and fusion while reducing computational complexity. The FA-SD-YOLO model replaces the conventional C2f module with the C2F-F module, developed using the FasterNet architecture, and substitutes the SPPF module with the Adaptive Inverted Fusion (AIFI) module. These changes markedly enhance the model’s feature fusion capabilities. Additionally, the integration of the SD module into the detection head optimizes parameter efficiency while improving detection performance. Performance evaluation highlights the superiority of the FA-SD-YOLO model. It achieves accuracy and recall rates of 88.6% and 89.6%, outperforming the YOLOv8n model by 1.8% and 1.3%, respectively. The model’s F1 score reaches 89.1%, and the mean average precision (mAP) improves to 93.2%, reflecting increases of 1.6% and 2.4% over YOLOv8n. These enhancements are accompanied by significant reductions in model size and computational cost: the parameter count is reduced to 1.58 million (a 47.3% reduction), and the FLOPS drops to 4.6 G (a 43.2% reduction). When compared with other state-of-the-art models, including YOLOv5s, YOLOv6s, YOLOv9t, and YOLOv11n, the FA-SD-YOLO model demonstrates superior performance across key metrics such as accuracy, F1 score, mAP, and FLOPS. Notably, it achieves a remarkable recognition speed of 13.8 ms per image, underscoring its efficiency and suitability for real-time applications. The FA-SD-YOLO model represents a robust and effective solution for the quality inspection of Astragalus membranaceus slices, providing reliable technical support for intelligent sorting machinery in the processing of this important medicinal herb.

Fuzzy-ER Net: Fuzzy-based Efficient Residual Network-based lung cancer classification

Globally, Lung Cancer (LC) continues to be the primary cause of cancer-related death. Effective diagnosis is essential to save the lives of people. Nevertheless, manual Computed Tomography (CT) scan analysis takes more time and is inaccurate. The principal intention of this paper is to establish a hybrid Fuzzy-based Efficient Residual Network (Fuzzy-ER Net) for LC classification. The prime phase is the acquisition of input CT images from the database and the obtained CT image is sent to the pre-processing stage where noise is eradicated utilizing a Double bilateral filter. Thereafter, segmentation of the lung lobe is done by using a Dual-Attention V-network (DAV-Net). Moreover, feature extraction is performed, where features that are extracted include area, irregularity index, Local Vector Pattern (LVP), Local Gabor XOR Pattern (LGXP), and Statistical Fuzzy Local Binary Pattern (SFLBP). Eventually, LC classification is done by utilizing the proposed hybrid Fuzzy-ER Net. Here, the proposed Fuzzy-ER Net is newly devised by assimilating fuzzy concepts, EfficientNet, and Deep Residual Network (DRN). Additionally, the evaluation of the Fuzzy-ER Net on the basis of various metrics shows that it achieved maximum accuracy, True Positive Rate (TPR), of 93.2 % and 94.8 %, minimum False Positive Rate (FPR) is 5.7 %, maximum precision of 92.6 %, and maximum F-measure of 93.7 %.

Minimal Defect Detection on End Face of Lithium Battery Shells

Lithium batteries represent a pivotal technology in the advancement of renewable energy, and their enhanced performance and safety are vital to the attainment of sustainable development goals. To solve the issue of the high missed detection rate of minimal defects on end face of lithium battery shells, a novel YOLO-based Minimal Defect Detection algorithm, named YOLO-MDD, is proposed. Firstly, aimed at the problem of insufficient data, a dataset of defects on the end face of lithium battery shells is constructed and annotated. Secondly, a YOLO-MDD network which includes a feature extraction module and a four-scale detection head for detecting defects of various scales is improved. Here, deformable convolution and an attention module are ingeniously embedded into the backbone of YOLO to capture more detailed and accurate information on object defects, and the four-scale head is used to handle the significant differences in the size and shape of defects on lithium battery shells. Finally, a hybrid loss including localization loss with normalized Wasserstein distance (NWD), classification loss, and confidence loss is designed to optimize our model to further enhance its sensitivity to minimal defects. The experimental results show that the proposed YOLO-MDD has a mean average precision of 80% for the defect detection of the lithium battery shells, especially with a minimal defect rust spots mean average precision of 74.1% and a recall rate of 71.5%, which is superior compared with other mainstream detection algorithms and provides the technical support necessary to achieve the goals of energy and environmental sustainability.

HawkEye: An end-host method to detect the Low-rate Denial-of-Service attack of cross-traffic over bottleneck links

The adaptive mechanisms of the Transmission Control Protocol (TCP) address network congestion and other unpredictable network conditions. They ensure the reliability of data transmission and the stability of the network. Unfortunately, the vulnerabilities in these adaptive mechanisms are targeted explicitly by low-rate denial-of-service (LDoS) attacks, which severely degrade network service quality. Only by modifying these protocols and addressing their vulnerabilities can one entirely prevent LDoS attacks. Although various improved TCP algorithms exist, they often fail to identify LDoS attacks accurately and, in some cases, may even reduce TCP performance. Furthermore, traditional LDoS attack detection methods rely on intermediate devices, which do not meet TCP’s end-to-end performance optimization needs. We introduce HawkEye, which moves the detection mechanism to the end hosts to address this issue. HawkEye uses an improved genetic algorithm to fine-tune the parameters of the LightGBM on the sending host, integrating multiple network traffic features to detect LDoS attacks. Experimental results show that our proposed method achieves the high accuracy, high true positive rate, and low false positive rate, successfully addressing the limitations of end-host detection of LDoS attacks and providing an innovative and effective solution for enhancing LDoS attack detection.

Using Short Molecular Dynamics Simulations to Determine the Important Features of Interactions in Antibody-Protein Complexes.

The last few years have seen the rapid proliferation of machine learning methods to design binding proteins. Although these methods have shown large increases in experimental success rates compared to prior approaches, the majority of their predictions fail when they are experimentally tested. It is evident that computational methods still struggle to distinguish the features of real protein binding interfaces from false predictions. Short molecular dynamics simulations of 20 antibody-protein complexes were conducted to identify features of interactions that should occur in binding interfaces. Intermolecular salt bridges, hydrogen bonds, and hydrophobic interactions were evaluated for their persistences, energies, and stabilities during the simulations. It was found that only the hydrogen bonds where both residues are stabilized in the bound complex are expected to persist and meaningfully contribute to binding between the proteins. In contrast, stabilization was not a requirement for salt bridges and hydrophobic interactions to persist. Still, interactions where both residues are stabilized in the bound complex persist significantly longer and have significantly stronger energies than other interactions. Two hundred and twenty real antibody-protein complexes and 8194 decoy complexes were used to train and test a random forest classifier using the features of expected persistent interactions identified in this study and the macromolecular features of interaction energy (IE), buried surface area (BSA), IE/BSA, and shape complementarity. It was compared to a classifier trained only on the expected persistent interaction features and another trained only on the macromolecular features. Inclusion of the expected persistent interaction features reduced the false positive rate of the classifier by two- to five-fold across a range of true positive classification rates.

Brain Tumour Detection Using Deep Learning and Image Processing

Abstract —Brain tumor detection is a critical aspect of neurooncology, where timely and accurate diagnosis significantly impacts patient outcomes. Traditional imaging techniques, while useful, are often limited by variations in image quality, illumination inconsistencies, and the complex nature of brain tumors themselves, which vary widely in size, shape, and texture. This paper presents a deep learning- based approach to brain tumor detection using Convolutional Neural Networks (CNNs) combined with advanced image processing methods. Our methodology involves preprocessing brain MRI scans using histogram equalization, morphological operations, and data augmentation to address illumination issues and enhance the tumor region. Following preprocessing, the images are fed into a CNN, where transfer learning from the Sequential model is applied to improve classification accuracy. Experimental results demonstrate high recall and precision rates, affirming the model’s robustness in detecting brain tumors in MRI images. This approach not only addresses the challenge of inconsistent MRI scan quality but also reduces the risk of misclassification, showing promise for clinical application. Keywords— Brain Tumor Detection, Computer-aided Diagnosis, Computer Vision, Convolutional Neural Networks, Deep Learning, Image Processing, Transfer Learning.

QuIDS: A Quantum Support Vector machine-based Intrusion Detection System for IoT networks

With the increasing popularity of IoT, there has been a noticeable surge in security breaches associated with vulnerable IoT devices. To identify and counter such attacks. Intrusion Detection Systems (IDS) are deployed. However, these IoT devices use device-specific application layer protocols like MQTT and CoAP, which pose an additional burden to the traditional IDS. Several Machine Learning (ML) and Deep Learning (DL) based IDS are developed to detect malicious IoT network traffic. However, in recent times, a variety of IoT devices have been available on the market, resulting in the frequent installation and uninstallation of IoT devices based on users’ needs. Moreover, ML and DL-based IDS must train with sufficient device-specific attack training data for each IoT device, consuming a noticeable amount of training time. To solve these problems, we propose QuIDS, which utilizes a Quantum Support Vector Classifier to classify attacks in an IoT network. QuIDS requires very little training data compared to ML or DL to train and accurately identify attacks in the IoT network. QuIDS extracts eight flow-level features from IoT network traffic and utilizes them over four quantum bits for training. We experimented with QuIDS on two publicly available datasets and found the average recall rate, precision, and f1-score of the QuIDS as 91.1%, 84.3%, and 86.4%, respectively. Moreover, comparing QuIDS with the ML and DL methods, we found that QuIDS outperformed by 37.7%, 24.4.6%, and 36.9% more average recall and precision rates than the ML and DL methods, respectively.