Multiple Architectures Research Articles

Diagnosis of Permanent Magnet Assisted Synchronous Reluctance Motor Winding Fault by Convolutional Neural Network

In recent years, the use of machine learning models for fault detection has become commonplace. Its goal is to identify and fix problems with permanent magnet synchronous reluctance motors. This research’s primary goal is to identify and categorize errors in their early stages. We classified winding faults using machine learning approaches, such as Independent Component Analysis and Deep Learning models. We could distinguish between vibration and current signals from the engine signals by using Independent Component Analysis (ICA). We experimented on multiple architectures using the convolutional neural network (CNN) architecture we designed from scratch and the Transfer Learning technique, testing two distinct datasets we generated using the signals we got. According to experimental findings, the suggested scratch CNN model performed exceptionally well in classification, achieving 98.6% with current signals and 99.4% with vibration signals.

Phenotypic and genetic characterization of a near-isogenic line pair: insights into flowering time in chickpea

BackgroundCicer arietinum is a significant legume crop cultivated mainly in short-season environments, where early-flowering is a desirable trait to overcome terminal constraints. Despite its agricultural significance, the genetic control of flowering time in chickpea is not fully understood. In this study, we developed, phenotyped, re-sequenced and genetically characterized a pair of near-isogenic lines (NILs) with contrasting days to flowering to identify candidate gene variants potentially associated with flowering time.ResultsIn addition to days to flowering, noticeable differences in multiple shoot architecture traits were observed between the NILs. The resequencing data confirms that the NILs developed in this study serve as appropriate plant materials, effectively constraining genetic variation to specific regions and thereby establishing a valuable resource for future genetic and functional investigations in chickpea research. Leveraging bioinformatics tools and public genomic datasets, we identified homologs of flowering-related genes from Arabidopsis thaliana, including ELF3 and, for the first time in chickpea, MED16 and STO/BBX24, with variants among the NILs. Analysis of the allelic distribution of these genes revealed their preservation within chickpea diversity and their potential association with flowering time. Variants were also identified in members of the ERF and ARF gene families. Furthermore, in silico expression analysis was conducted elucidating their putative roles in flowering.ConclusionsWhile the gene CaELF3a is identified as a prominent candidate, this study also exposes new targets in chickpea, such as CaMED16b and LOC101499101 (BBX24-like), homologs of flowering-related genes in Arabidopsis, as well as ERF12 and ARF2. The in silico expression characterization and genetic variability analysis performed could contribute to their use as specific markers for chickpea breeding programs. This study lays the groundwork for future investigations utilizing this plant material, promising further insights into the complex mechanisms governing flowering time in chickpea.

Prediction of Frequency-Dependent Optical Spectrum for Solid Materials: A Multioutput and Multifidelity Machine Learning Approach.

The frequency-dependent optical spectrum is pivotal for a broad range of applications from material characterization to optoelectronics and energy harvesting. Data-driven surrogate models, trained on density functional theory (DFT) data, have effectively alleviated the scalability limitations of DFT while preserving its chemical accuracy, expediting material discovery. However, prevailing machine learning (ML) efforts often focus on scalar properties such as the band gap, overlooking the complexities of optical spectra. In this work, we employ deep graph neural networks (GNNs) to predict the frequency-dependent complex-valued dielectric function across the infrared, visible, and ultraviolet spectra directly from the crystal structures. We explore multiple architectures for the spectral multioutput representation of the dielectric function and utilize various multifidelity learning strategies, such as transfer learning and fidelity embedding, to address the challenges associated with the scarcity of high-fidelity DFT data. Additionally, we model key solar cell absorption efficiency metrics, demonstrating that learning these parameters is enhanced when integrated through a learning bias within the learning of the frequency-dependent absorption coefficient. This study demonstrates that leveraging multioutput and multifidelity ML techniques enables accurate predictions of optical spectra from crystal structures, providing a versatile tool for rapidly screening materials for optoelectronics, optical sensing, and solar energy applications across an extensive frequency spectrum.

Deep learning and feature fusion-based lung sound recognition model to diagnoses the respiratory diseases

This paper proposed a novel approach for detecting lung sound disorders using deep learning feature fusion. The lung sound dataset are oversampled and converted into spectrogram images. Then, extracting deep features from CNN architectures, which are pre-trained on large-scale image datasets. These deep features capture rich representations of spectrogram images from the input signals, allowing for a comprehensive analysis of lung disorders. Next, a fusion technique is employed to combine the extracted features from multiple CNN architectures totlaly 8064 feature. This fusion process enhances the discriminative power of the features, facilitating more accurate and robust detection of lung disorders. To further improve the detection performance, an improved CNN Architecture is employed. To evaluate the effectiveness of the proposed approach, an experiments conducted on a large dataset of lung disorder signals. The results demonstrate that the deep feature fusion from different CNN architectures, combined with different CNN Layers, achieves superior performance in lung disorder detection. Compared to individual CNN architectures, the proposed approach achieves higher accuracy, sensitivity, and specificity, effectively reducing false negatives and false positives. The proposed model achieves 96.03% accuracy, 96.53% Sensitivity, 99.424% specificity, 96.52% precision, and 96.50% F1 Score when predicting lung diseases from sound files. This approach has the potential to assist healthcare professionals in the early detection and diagnosis of lung disorders, ultimately leading to improved patient outcomes and enhanced healthcare practices.

Operational Amplifiers Defect Detection and Localization Using Digital Injectors and Observer Circuits

Operational amplifiers (op amps) are fundamental blocks that find wide application both as stand-alone devices and as crucial blocks embedded in various Systems on Chips (SoCs). Achieving high defect coverage, as well as performing defect localization in these circuits, has proven to be a difficult/expensive task, even with sophisticated testing circuitry. The ISO 26262 standard for functional safety (FuSa) includes the stringent requirement that an automotive IC must have a very high defect coverage. This reinforces the need to ensure the functionality of analog and mixed (AMS) circuits, especially in mission critical applications. This paper presents an all-digital op amp defect detection, diagnosis, and localization method that can be used both for production and in-field tests and discusses various implementation of the proposed method. We validated our results using extensive transistor-level simulations of multiple op amp architectures using TSMC 180 nm technology. Across op amp architectures and multiple implementation approaches, we achieved a worst-case and best-case defect coverage of 94.5% and 99%, respectively. Furthermore, in this work, we also propose a defect diagnosis and localization strategy using recorded bit streams from states of digital injectors and detectors.

A new subcarrier‐index modulation schemes for downlink NOMA systems

SummaryIn this paper, we propose two downlink multiple access architectures for networks where human‐type communication users (HTCUs) and machine‐type communication devices (MTCDs) coexist. The proposed schemes combine non‐orthogonal multiple access (NOMA), orthogonal frequency division multiplexing (OFDM), and index modulation (OFDM‐IM) concepts. In the first scheme, the base station (BS) transmits bits of HTCUs using modulated symbols and bits of MTCDs by the subcarrier activation pattern (SAP). This approach called IM‐NOMA with null subcarriers (IM‐NOMA‐NS) ensures that inactive subcarriers are always null, which improves the system bit error rate (BER) performance. To improve the spectral efficiency (SE), we propose a second approach, termed IM‐NOMA with dual‐mode modulation (IM‐NOMA‐DM), in which the HTCUs' bits are transmitted using two‐dimensional modulation and the MTCDs' bits are transmitted using one‐dimensional modulation and the SAP. For each proposed system, a near‐optimal low‐complexity detector, based on the energy‐detection (ED) and the log‐likelihood ratio (LLR) criterion, is provided to mitigate the detection burden of the optimal maximum‐likelihood (ML) detector. The BER performances and SE of the proposed schemes are investigated. The average BERs of IM‐NOMA‐NS and IM‐NOMA‐DM are derived in closed‐form expressions corroborated by the simulation results. We have proved numerically that the proposed schemes achieve a good trade‐off between BER performance, SE, and the number of supported users, making them more suitable for Internet of Things (IoT) applications.

A high speed pipelined radix-16 Booth multiplier architecture for FPGA implementation

Since multiplication is a complex and resource-consuming operation, it is very effective on the speed performance of a processor. In this regard, fast multiplication unit design is important in digital system architectures. FPGA hardware, which is efficient for the implementation and rapid prototyping of today’s digital system architectures, is becoming widespread. Therefore, in this study it aimed to design a fast radix-16 Booth multiplier based on the FPGA architecture. Booth multiplier implementation is preferred because it is relatively simple and efficient. The sizes of the multiplexers, which have an impact on the operating period in the encoder part of the proposed multiplier, reduced in the designed architecture by using a simple algorithm. To increase the speed performance of the system, the pipeline technique is used and parallelization is preferred in the tree structure in addition of the partial products. The effects of different multiplexer sizes, bit lengths and pipeline stages on the operating period of the system and other performance metrics examined. Different designs and the results obtained presented. According to the results, the multiplier hardware architectures designed in this study exhibit effective results in terms of speed performance.

Specific Investigations Concerning the Improveable Multiplier Architecture of High-Speed and Area-Efficient Adders

Over the past few decades, the growth of portable devices such as laptops, mobile phone and personal digital assistant has resulted in increasing demand for complex functionality with effective computation. The present day technology is known for digital systems with very high computing capabilities. The demand for high speed, low power integrated circuits for portable devices has become crucial. The never ending growing complexities of integrated circuit for future devices pose a challenging task for integrated circuit designer. Cost effective integrated circuits requires the design meeting out the challenging task to optimize power, area with high performance. Hence this research focuses on the optimization of area, power and speed of Arithmetic circuits, Very Large Scale Integrated circuits (VLSI) are widely used in Arithmetic circuits, Digital Signal Processing (DSP), Image and Video Processing applications

GMC-crypto: Low latency implementation of ECC point multiplication for generic Montgomery curves over GF(p)

Elliptic Curve Cryptography (ECC) is the front-runner among available public key cryptography (PKC) schemes due to its potential to offer higher security per key bit. All ECC-based cryptosystems heavily rely on point multiplication operation where its efficient realization has attained notable focus in the research community. Low latency implementation of the point multiplication operation is frequently required in high-speed applications such as online authentication and web server certification. This paper presents a low latency ECC point multiplication architecture for Montgomery curves over generic prime filed GF(p). The proposed architecture is able to operate for a general prime modulus without any constraints on its structure. It is based on a new novel pipelined modular multiplier developed using the Montgomery multiplication and the Karatsuba-Offman technique with a four-part splitting methodology. The Montgomery ladder approach is adopted on a system level, where a high-speed scheduling strategy to efficiently execute GF(p) operations is also presented. Due to these circuit and system-level optimizations, the proposed design delivers low-latency results without a significant increase in resource consumption. The proposed architecture is described in Verilog-HDL for 256-bit key lengths and implemented on Virtex-7 and Virtex-6 FPGA platforms using Xilinx ISE Design Suite. On the Virtex-7 FPGA platform, it performs a 256-bit point multiplication operation in just 110.9 us with a throughput of almost 9017 operations per second. The implementation results demonstrate that despite its generic nature, it produces low latency as compared to the state-of-the-art. Therefore, it has prominent prospects to be used in high-speed authentication and certification applications.

Reweighted Alternating Direction Method of Multipliers for DNN weight pruning

As Deep Neural Networks (DNNs) continue to grow in complexity and size, leading to a substantial computational burden, weight pruning techniques have emerged as an effective solution. This paper presents a novel method for dynamic regularization-based pruning, which incorporates the Alternating Direction Method of Multipliers (ADMM). Unlike conventional methods that employ simple and abrupt threshold processing, the proposed method introduces a reweighting mechanism to assign importance to the weights in DNNs. Compared to other ADMM-based methods, the new method not only achieves higher accuracy but also saves considerable time thanks to the reduced number of necessary hyperparameters. The method is evaluated on multiple architectures, including LeNet-5, ResNet-32, ResNet-56, and ResNet-50, using the MNIST, CIFAR-10, and ImageNet datasets, respectively. Experimental results demonstrate its superior performance in terms of compression ratios and accuracy compared to state-of-the-art pruning methods. In particular, on the LeNet-5 model for the MNIST dataset, it achieves compression ratios of 355.9× with a slight improvement in accuracy; on the ResNet-50 model trained with the ImageNet dataset, it achieves compression ratios of 4.24× without sacrificing accuracy.

PhiHER2: phenotype-informed weakly supervised model for HER2 status prediction from pathological images.

Human epidermal growth factor receptor 2 (HER2) status identification enables physicians to assess the prognosis risk and determine the treatment schedule for patients. In clinical practice, pathological slides serve as the gold standard, offering morphological information on cellular structure and tumoral regions. Computational analysis of pathological images has the potential to discover morphological patterns associated with HER2 molecular targets and achieve precise status prediction. However, pathological images are typically equipped with high-resolution attributes, and HER2 expression in breast cancer (BC) images often manifests the intratumoral heterogeneity. We present a phenotype-informed weakly supervised multiple instance learning architecture (PhiHER2) for the prediction of the HER2 status from pathological images of BC. Specifically, a hierarchical prototype clustering module is designed to identify representative phenotypes across whole slide images. These phenotype embeddings are then integrated into a cross-attention module, enhancing feature interaction and aggregation on instances. This yields a phenotype-based feature space that leverages the intratumoral morphological heterogeneity for HER2 status prediction. Extensive results demonstrate that PhiHER2 captures a better WSI-level representation by the typical phenotype guidance and significantly outperforms existing methods on real-world datasets. Additionally, interpretability analyses of both phenotypes and WSIs provide explicit insights into the heterogeneity of morphological patterns associated with molecular HER2 status. Our model is available at https://github.com/lyotvincent/PhiHER2.

NeoGx: Machine-Recommended Rapid Genome Sequencing for Neonates.

Genetic disease is common in the Level IV Neonatal Intensive Care Unit (NICU), but neonatology providers are not always able to identify the need for genetic evaluation. We trained a machine learning (ML) algorithm to predict the need for genetic testing within the first 18 months of life using health record phenotypes. For a decade of NICU patients, we extracted Human Phenotype Ontology (HPO) terms from clinical text with Natural Language Processing tools. Considering multiple feature sets, classifier architectures, and hyperparameters, we selected a classifier and made predictions on a validation cohort of 2,241 Level IV NICU admits born 2020-2021. Our classifier had ROC AUC of 0.87 and PR AUC of 0.73 when making predictions during the first week in the Level IV NICU. We simulated testing policies under which subjects begin testing at the time of first ML prediction, estimating diagnostic odyssey length both with and without the additional benefit of pursuing rGS at this time. Just by using ML to accelerate initial genetic testing (without changing the tests ordered), the median time to first genetic test dropped from 10 days to 1 day, and the number of diagnostic odysseys resolved within 14 days of NICU admission increased by a factor of 1.8. By additionally requiring rGS at the time of positive ML prediction, the number of diagnostic odysseys resolved within 14 days was 3.8 times higher than the baseline. ML predictions of genetic testing need, together with the application of the right rapid testing modality, can help providers accelerate genetics evaluation and bring about earlier and better outcomes for patients.

Digital Aided Analog Data Acquisition for Telemetry

This paper tackles the limitations in the current data acquisition system through the integration of a equiripple Finite Impulse Response (FIR) filter. The inclusion of this digital filter eliminates the necessity for physical component alterations, thereby increasing the system’s adaptability and versatility in telemetry applications. The FIR filter’s ability to adjust passband, stopband, and sampling frequencies allows for seamless reconfiguration without the need for hardware modifications, representing a substantial enhancement compared to the constraints of the previous system. Additionally, the equiripple design guarantees minimal variations in passband and stopband ripples, thereby optimizing overall filter performance. An important aspect of the proposed solution is the implementation of shift-and-add multiplier architecture for the FIR filter, which contributes to a reduction in hardware complexity and resource requirements, ultimately leading to a more efficient system. The adoption of MATLAB’s robust filter design tools, coupled with subsequent verification through SIMULINK simulations, has played a pivotal role in successfully realizing the proposed design. To sum up, this project has efficiently addressed the identified issues by introducing a reconfigurable FIR filter solution that not only enhances the flexibility, performance, and user friendliness of the data acquisition system in telemetry applications but also showcases the potential for broader applications in various signal processing domain.

Area and Power Optimized VLSI Architecture of Approximate Multiplier

When it comes to error-resistant applications, approximation computing offers the ability to reduce design complexity while increasing performance in terms of size, latency, and power efficiency. This brief discusses an innovative design technique for approximating multipliers. When it comes to error-resistant applications, approximation computing offers the ability to reduce design complexity while increasing performance in terms of size, latency, and power efficiency. Within the scope of this short, a unique 4-2 approximate compressor is presented. This compressor is complimentary to existing compressors that have been developed in previous work. Additionally, A proposed multiplier is built using the compressors, a constant approximation, and error correction. The simulation results show that the designed approximation multiplier performs satisfactorily. Within the Xilinx-Vivado environment, the implementation, synthesis, and simulation are carried out and recorded using the verilog HDL programming language. Key Words: approximate multiplier, exact compressor, approximate compressor and Verilog HDL.

Sex classification of 3D skull images using deep neural networks

Determining the fundamental characteristics that define a face as "feminine" or "masculine" has long fascinated anatomists and plastic surgeons, particularly those involved in aesthetic and gender-affirming surgery. Previous studies in this area have relied on manual measurements, comparative anatomy, and heuristic landmark-based feature extraction. In this study, we collected retrospectively at Cedars Sinai Medical Center (CSMC) a dataset of 98 skull samples, which is the first dataset of this kind of 3D medical imaging. We then evaluated the accuracy of multiple deep learning neural network architectures on sex classification with this dataset. Specifically, we evaluated methods representing three different 3D data modeling approaches: Resnet3D, PointNet++, and MeshNet. Despite the limited number of imaging samples, our testing results show that all three approaches achieve AUC scores above 0.9 after convergence. PointNet++ exhibits the highest accuracy, while MeshNet has the lowest. Our findings suggest that accuracy is not solely dependent on the sparsity of data representation but also on the architecture design, with MeshNet's lower accuracy likely due to the lack of a hierarchical structure for progressive data abstraction. Furthermore, we studied a problem related to sex determination, which is the analysis of the various morphological features that affect sex classification. We proposed and developed a new method based on morphological gradients to visualize features that influence model decision making. The method based on morphological gradients is an alternative to the standard saliency map, and the new method provides better visualization of feature importance. Our study is the first to develop and evaluate deep learning models for analyzing 3D facial skull images to identify imaging feature differences between individuals assigned male or female at birth. These findings may be useful for planning and evaluating craniofacial surgery, particularly gender-affirming procedures, such as facial feminization surgery.

Unrefreshing naps and sleep architecture during the multiple sleep latency test in idiopathic hypersomnia

SummaryPatients with idiopathic hypersomnia frequently report having unrefreshing naps. However, whether they have abnormal sleep architecture during naps that may explain their unrefreshing aspect is unknown. We compared sleep architecture during short daytime naps in patients with idiopathic hypersomnia reporting unrefreshing and refreshing naps. One‐hundred and thirty‐four patients tested with one‐night polysomnography, followed by an adapted version of the Multiple Sleep Latency Test with four naps, were included. They were asked about the refreshing aspect of their habitual naps during a clinical interview. They were classified as having objective (Multiple Sleep Latency Test ≤ 8 min) or subjective idiopathic hypersomnia (Multiple Sleep Latency Test > 8 min), and as presenting refreshing or unrefreshing naps. We tested Group differences (refreshing versus unrefreshing naps) on nap sleep architecture in the whole sample and for subjective and objective idiopathic hypersomnia subgroups separately using ANCOVAs. No Group effects were observed in the Multiple Sleep Latency Test architecture in the whole sample and in objective and subjective idiopathic hypersomnia subgroups. This study provides preliminary evidence that reporting unrefreshing naps is not associated with clinically significant findings in Multiple Sleep Latency Test sleep architecture in patients with idiopathic hypersomnia. Given that naps taken by patients with idiopathic hypersomnia are typically long, future studies should investigate longer daytime sleep episodes.

Audio-based event detection in the operating room.

Even though workflow analysis in the operating room has come a long way, current systems are still limited to research. In the quest for a robust, universal setup, hardly any attention has been given to the dimension of audio despite its numerous advantages, such as low costs, location, and sight independence, or little required processing power. We present an approach for audio-based event detection that solely relies on two microphones capturing the sound in the operating room. Therefore, a new data set was created with over 63h of audio recorded and annotated at the University Hospital rechts der Isar. Sound files were labeled, preprocessed, augmented, and subsequently converted to log-mel-spectrograms that served as a visual input for an event classification using pretrained convolutional neural networks. Comparing multiple architectures, we were able to show that even lightweight models, such as MobileNet, can already provide promising results. Data augmentation additionally improved the classification of 11 defined classes, including inter alia different types of coagulation, operating table movements as well as an idle class. With the newly created audio data set, an overall accuracy of 90%, a precision of 91% and a F1-score of 91% were achieved, demonstrating the feasibility of an audio-based event recognition in the operating room. With this first proof of concept, we demonstrated that audio events can serve as a meaningful source of information that goes beyond spoken language and can easily be integrated into future workflow recognition pipelines using computational inexpensive architectures.

Methodology for Severe Convective Cloud Identification Using Lightweight Neural Network Model Ensembling

This study introduces an advanced ensemble methodology employing lightweight neural network models for identifying severe convective clouds from FY-4B geostationary meteorological satellite imagery. We have constructed a FY-4B based severe convective cloud dataset by a combination of algorithms and expert judgment. Through the ablation study of a model ensembling combination of multiple specialized lightweight architectures—ENet, ESPNet, Fast-SCNN, ICNet, and MobileNetV2—the optimal EFNet (ENet- and Fast-SCNN-based network) not only achieves real-time processing capabilities but also ensures high accuracy in severe weather detection. EFNet consistently outperformed traditional, heavier models across several key performance indicators: achieving an accuracy of 0.9941, precision of 0.9391, recall of 0.9201, F1 score of 0.9295, and computing time of 18.65 s over the test dataset of 300 images (~0.06 s per 512 × 512 pic). ENet shows high precision but misses subtle clouds, while Fast-SCNN has high sensitivity but lower precision, leading to misclassifications. EFNet’s ensemble approach balances these traits, enhancing overall predictive accuracy. The ensemble method of lightweight models effectively aggregates the diverse strengths of the individual models, optimizing both speed and predictive performance.

Decreasing incidence and mortality of lung cancer in Hungary between 2011 and 2021 revealed by robust estimates reconciling multiple data sources.

Hungary has repeatedly been shown to have the highest cancer-related mortality and incidence in Europe. Despite lung cancer being the most abundant malignant diagnosis in Hungary, numerous concerns have been raised recently regarding the bias inherent to reported incidence estimates. Re-analysis of reimbursement claims has been suggested previously by our group as an alternative approach, offering revised figures of lung cancer incidence between 2011 and 2016. Leveraging on this methodology, we aimed at updating Hungarian lung cancer incidence estimates with an additional 5years (2017-2021), including years affected by the COVID-19 pandemic. Additionally, we also attempted to improve the robustness of estimates by taking additional characteristics of the patient pathway into account. Lung cancer patients between 2011 and 2021 were identified based on reimbursement-associated ICD-10 codes, histology codes and time patterns. Multiple query architectures were tested for sensitivity and compared to official estimates of the Hungarian National Cancer Registry (HNCR). Epidemiological trends were estimated by Poisson-regression, corrected for age and sex. A total of 89,948 lung cancer patients diagnosed in Hungary between 2011 and 2021 have been identified by our study. In 2019 alone, 7,887 patients were diagnosed according to our optimized query. ESP2013 standardized rate was estimated between 92.5/100,000 (2011) and 78.4/100,000 (2019). In 2019, standardized incidence was 106.8/100,000 for men and 59.7/100,000 for women. Up until the COVID-19 pandemic, lung cancer incidence was decreasing by 3.18% (2.1%-4.3%) yearly in men, while there was no significant decrease in women. Young age groups (40-49 and 50-59) featured the largest improvement, but women aged 60-79 are at an increasing risk for developing lung cancer. The COVID-19 pandemic resulted in a statistically significant decrease in lung cancer incidence, especially in the 50-59 age group (both sexes). Our results show that using an optimized approach, re-analysis of reimbursement claims yields robust estimates of lung cancer incidence. According to this approach, the incidence rate of male lung cancer is declining in Hungary, in concordance with the trend observed for lung cancer mortality. Among women aged 60-79, the incidence of lung cancer has risen, requiring more attention in the near future.

Enhanced deep learning based decision support system for kidney tumour detection

This study presents a high-accuracy deep learning-based decision support system for kidney cancer detection. The research utilizes a relatively large dataset of 10,000 CT images, including both healthy and tumour-detected kidney scans. After data preprocessing and optimization, various deep learning models were evaluated, with DenseNet-201 emerging as the top performer, achieving an accuracy of 99.75 %. The study compares multiple deep learning architectures, including AlexNet, EfficientNet, Darknet-53, Xception, and DenseNet-201, across different learning rates. Performance metrics such as accuracy, precision, sensitivity, F1-score, and specificity are analysed using confusion matrices. The proposed system outperforms different deep learning networks, demonstrating superior accuracy in kidney cancer detection. The improvement is attributed to effective data engineering and hyperparameter optimization of the deep learning networks. This research contributes to the field of medical image analysis by providing a robust decision support tool for early and rapid diagnosis of kidney cancer. The high accuracy and efficiency of the proposed system make it a promising aid for healthcare professionals in clinical settings.