Limited Accuracy Research Articles

Deep Learning-Based Network Intrusion Detection Systems

With the rapid growth of the internet, the security threats to computer networks have escalated significantly, making the reduction and prevention of cybercrime a top priority in the digital age. Traditional Network Intrusion Detection Systems (NIDS) struggle with limitations in detection accuracy and real-time performance as attackers employ increasingly sophisticated techniques. In recent years, deep learning has emerged as a prominent solution in the NIDS field due to its powerful capabilities in feature extraction and classification. This paper reviews the application of deep learning in NIDS, with a focus on Convolutional Neural Networks (CNN), Long Short-Term Memory Networks (LSTM), and their hybrid models. The paper discusses the strengths of these models in capturing spatial and temporal features and examines their performance on key datasets such as KDD Cup 99 and UNSW-NB15. Additionally, the paper addresses challenges related to computational complexity, real-time performance, and model interpretability, while suggesting future research directions, including model optimization, lightweight architectures, and improved interpretability. Finally, the potential of Automated Machine Learning (AutoML) in advancing NIDS design and enhancing response capabilities is explored. This study offers valuable insights for further research and development in NIDS.

A Wavelet Decomposition Method for Estimating Soybean Seed Composition with Hyperspectral Data

Soybean seed composition, particularly protein and oil content, plays a critical role in agricultural practices, influencing crop value, nutritional quality, and marketability. Accurate and efficient methods for predicting seed composition are essential for optimizing crop management and breeding strategies. This study assesses the effectiveness of combining handheld spectroradiometers with the Mexican Hat wavelet transformation to predict soybean seed composition at both seed and canopy levels. Initial analyses using raw spectral data from these devices showed limited predictive accuracy. However, by using the Mexican Hat wavelet transformation, meaningful features were extracted from the spectral data, significantly enhancing prediction performance. Results showed improvements: for seed-level data, Partial Least Squares Regression (PLSR), a method used to reduce spectral data complexity while retaining critical information, showed R2 values increasing from 0.57 to 0.61 for protein content and from 0.58 to 0.74 for oil content post-transformation. Canopy-level data analyzed with Random Forest Regression (RFR), an ensemble method designed to capture non-linear relationships, also demonstrated substantial improvements, with R2 increasing from 0.07 to 0.44 for protein and from 0.02 to 0.39 for oil content post-transformation. These findings demonstrate that integrating handheld spectroradiometer data with wavelet transformation bridges the gap between high-end spectral imaging and practical, accessible solutions for field applications. This approach not only improves the accuracy of seed composition prediction at both seed and canopy levels but also supports more informed decision-making in crop management. This work represents a significant step towards making advanced crop assessment tools more accessible, potentially improving crop management strategies and yield optimization across various farming scales.

A Review of Liquid Chromatography-Mass Spectrometry and its Applications in Chemical Analysis

Liquid Chromatography-Mass Spectrometry (LC-MS) has emerged as a powerful analytical technique combining the separation capabilities of liquid chromatography with the high sensitivity and selectivity of mass spectrometry. This sophisticated instrumentation enables precise identification and quantification of complex chemical mixtures across diverse fields including pharmaceuticals, environmental monitoring, food safety, and biological research. Modern LC-MS systems offer enhanced resolution, improved ionization methods, and sophisticated mass analyzers that facilitate accurate molecular weight determination and structural elucidation of compounds. Recent technological advancements have led to the development of ultra-high-performance liquid chromatography (UHPLC) systems coupled with high-resolution mass spectrometers, enabling faster analysis times and improved detection limits. The versatility of LC-MS is demonstrated through its applications in proteomics, metabolomics, drug development, and quality control processes. Integration of artificial intelligence and machine learning algorithms has further enhanced data processing capabilities, allowing for automated peak identification and complex mixture analysis. The continuous evolution of LC-MS technology has addressed previous limitations in ionization efficiency, matrix effects, and quantification accuracy. This analytical technique has revolutionized chemical analysis by providing comprehensive molecular information, making it an indispensable tool in modern analytical laboratories.

Flexural capacity prediction of reinforced UHPC beams using an interpretable machine learning model

Addressing the issues of inconsistency and limited accuracy in the current prediction models for the flexural capacity of reinforced ultrahigh-performance concrete (UHPC) beams, this paper proposes a machine-learning prediction model for the flexural capacity of reinforced UHPC beams based on interpretable Extreme Gradient Boosting (XGBoost) model. Firstly, a database containing 221 sets of experimental UHPC beam data is established, and the database quality is evaluated by Pearson correlation coefficient and Mahalanobis distance. Then, ten-fold cross-validation and the whale optimization algorithm (WOA) are employed to find the optimal hyperparameter combination for XGBoost. Different indices are used to evaluate the prediction accuracy of the XGBoost model with four typical machine learning models and other computational methods. The Shapley additive explanations (SHAP) method is used to provide interpretations of the prediction results. The results indicate that the XGBoost model outperforms the four other machine learning models and related standards. Compared with the existing formulas, the proposed prediction model demonstrates higher accuracy in predicting the flexural capacity of UHPC beams. The SHAP method effectively explains the prediction results of the XGBoost model, providing insights into accurately assessing the factors influencing the flexural capacity of UHPC beams. SHAP analysis reveals that the most significant factors affecting the flexural capacity of UHPC beams are the cross-sectional height and reinforcement ratio, while the least significant factors are the aspect ratio of steel fibers and volume fraction of steel fibers.

Paired autoencoders for likelihood-free estimation in inverse problems

Abstract We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. Such problems are notoriously difficult to solve in practice and require minimizing a combination of a data-fit term and a regularization term. The main computational bottleneck of typical algorithms is the direct estimation of the data misfit. Therefore, likelihood-free approaches have become appealing alternatives. Nonetheless, difficulties in generalization and limitations in accuracy have hindered their broader utility and applicability. In this work, we use a paired autoencoder framework as a likelihood-free estimator (LFE) for inverse problems. We show that the use of such an architecture allows us to construct a solution efficiently and to overcome some known open problems when using LFEs. In particular, our framework can assess the quality of the solution and improve on it if needed. We demonstrate the viability of our approach using examples from full waveform inversion and inverse electromagnetic imaging.

Identification and Validation of Serum Biomarkers to Improve Colorectal Cancer Diagnosis.

The pressing need for reliable biomarkers in colorectal cancer (CRC) diagnosis and prognosis is a major global health concern. Current diagnostic methods rely heavily on invasive procedures like colonoscopy, and existing biomarkers such as Carbohydrate Antigen 19-9 (CA19-9) and Carcinoembryonic Antigen (CEA) exhibit limitations in accuracy and specificity. This study aims to identify and validate novel biomarkers that can enhance the early detection and diagnostic precision of CRC while overcoming the shortcomings of conventional biomarkers. Leveraging advancements in genomic and proteomic technologies, gene expression datasets were obtained from the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA). We identified differentially expressed genes (DEGs) and conducted further analyses, including Gene Ontology (GO) enrichment and Protein-Protein Interaction (PPI) network construction. Five promising biomarkers-INHBA, MMP7, PSAT1, SLC7A5, and TGFBI-were selected based on their robust performance in Receiver Operating Characteristic (ROC) curve analysis. Serum concentrations of these biomarkers were measured in 200 CRC patients and 100 healthy controls. The study revealed significantly elevated expression levels of the selected biomarkers in CRC tissues compared to normal tissues. Additionally, serum concentrations of INHBA, MMP7, PSAT1, SLC7A5, and TGFBI were notably higher in CRC patients than in healthy individuals, with Area Under the Curve (AUC) values ranging from 0.8361 to 0.9869 indicating high diagnostic accuracy. Optimal cutoff values for diagnosis ranged from 38.9 pg/mL to 280.7 pg/mL, yielding sensitivity and specificity values between 74.5% and 92.9%. The findings underscore the potential of INHBA, MMP7, PSAT1, SLC7A5, and TGFBI as effective non-invasive biomarkers for CRC detection. Their elevated serum concentrations and robust discriminatory abilities highlight their promise in improving diagnostic accuracy and patient outcomes compared to traditional biomarkers. The identification and validation of these novel biomarkers represent a significant advancement in CRC diagnosis and management. Further studies are required to validate their clinical applicability in larger cohorts and to elucidate their functional roles in CRC pathogenesis, ultimately enhancing diagnostic strategies and personalized treatment approaches.

Predicting compressive strength of grouted masonry using machine learning models with feature importance analysis

Grouted masonry, a technique employing grout-filled hollow concrete blocks, offers superior strength to conventional hollow blocks. Existing methods rely on empirical equations that incorporate the strengths of individual components (blocks, mortar, grout) and geometrical properties. However, these equations often suffer from limitations in accuracy. The present study uses machine learning models to predict the compressive strength of grouted masonry. It utilizes a comprehensive dataset encompassing the compressive strength of various components (blocks, mortar, grout), geometrical properties (height-to-thickness and length-to-thickness ratios), and the net-to-gross area ratio of the blocks. Statistical analysis revealed a significant influence of individual component strengths and the height-to-thickness ratio on the overall compressive strength. Furthermore, the study demonstrates that machine learning models outperform existing prediction methods, particularly the Artificial Neural Network (ANN). The ANN model effectively captures the complex relationships between various factors, leading to superior prediction accuracy compared to traditional empirical equations. This novel approach offers significant potential benefits for the construction industry. It can streamline the design process by reducing reliance on time-consuming physical testing, leading to cost savings through optimized material use. Additionally, engineers gain the advantage of designing with greater confidence due to the availability of reliable strength predictions.

MM-DRPNet: A Multimodal Dynamic Radial Partitioning Network for Enhanced Protein–Ligand Binding Affinity Prediction

Accurate prediction of drug-target binding affinity remains a fundamental challenge in contemporary drug discovery. Despite significant advances in computational methods for protein-ligand binding affinity prediction, current approaches still face substantial limitations in prediction accuracy. Moreover, the prevalent methodologies often overlook critical three-dimensional (3D) structural information, thereby constraining their practical utility in computer-aided drug design (CADD). Here we present MM-DRPNet, a multimodal deep learning framework that enhances binding affinity prediction by integrating protein-ligand structural information with interaction features and physicochemical properties. The core innovation lies in our dynamic radial partitioning (DRP) algorithm, which adaptively segments 3D space based on complex-specific interaction patterns, surpassing traditional fixed partitioning methods in capturing spatial interactions. MM-DRPNet further incorporates molecular topological features to comprehensively model both structural and spatial relationships. Extensive evaluations on benchmark datasets demonstrate that MM-DRPNet significantly outperforms state-of-the-art methods across multiple metrics, with ablation studies confirming the substantial contribution of each architectural component. Source code for MM-DRPNet is freely available for download at https://github.com/Bigrock-dd/MMDRPv1.

Temperature extraction from Brillouin sensing based on temporal convolutional networks

The Brillouin optical time-domain sensing system has become a hot spot of research due to its ability to seamlessly monitor the temperature and strain variations in optical fibers along the line. Given its current limitations of low accuracy and inadequate real-time performance in long-distance monitoring, the Brillouin gain extraction temperature method based on temporal convolutional networks is proposed. On this basis, we established a Brillouin optical time-domain experimental system where comprehensive simulations and tests were conducted to assess the temperature extraction performance under different conditions. Besides, a comparison was made between the system and traditional methods like Lorentz fitting method and extreme learning machine method. The results have suggested that the temporal convolutional network exhibits remarkable measurement accuracy, even in scenarios with low signal-to-noise ratios and large sweep frequency steps.

Effect of water-to-quick setting cement ratio and aggregate size on mechanical properties and dimensional accuracy of binder jetting 3D-printed bodies

Quick setting cement-based materials were produced in the present work using the binder jetting 3D printing (BJ3DP) technique with the aim at investigating how processing parameters like water-to-cement ratio and aggregate size affect the final properties of the products. Commercially available quick-setting cement and siliceous sand were utilized. Dimensional accuracy, compressive and flexural strength were measured for variable processing conditions and their individual effect was analysed. The results showed that the properties of printed parts are significantly influenced by the considered processing variables and, in particular, a larger water-to-cement ratio has a beneficial effect on the mechanical performances, the improvement being higher when coarser siliceous sand is used. It was also shown that the employment of finer sand results in more limited dimensional accuracy.

Machine learning algorithms for breast cancer analysis: performance and accuracy comparison

Breast cancer, a leading cause of cancer mortality among women, necessitates early detection to improve survival rates. Traditional diagnostics face accuracy and speed limitations, prompting this study to explore machine learning for enhanced diagnostics. We applied bidirectional encoder representations from transformers (BERT), long short-term memory (LSTM), naive Bayes, support vector machine (SVM), and random forest to the Breast Cancer Wisconsin dataset, implementing a thorough methodology involving data preprocessing, feature extraction, and model validation. BERT led in accuracy at 92.5%, showcasing advanced algorithms' potential in medical diagnostics, with random forest 90.6%, SVM 89.3%, LSTM 88.7%, and naive Bayes 85.2%; also showing promising results. The study underscores the importance of incorporating machine learning, especially BERT, into clinical decision-making, potentially revolutionizing breast cancer diagnostics by improving accuracy and efficiency. We recommend healthcare practitioners integrate these algorithms into their diagnostic processes. Future research should reeefine these algorithms and extend their application to enhance patient care further.

Diagnostic Efficacy of Multimodal Ultrasound for Mass and Non-Mass Enhancements in Dynamic Contrast-Enhanced MRI of Idiopathic Granulomatous Mastitis and Breast Cancer

PurposeIdiopathic granulomatous mastitis (IGM) poses diagnostic challenges due to its diverse clinical and radiological presentations, often mimicking malignancies. This study aimed to assess the diagnostic efficacy of multimodal ultrasound for mass and non-mass enhancements in Dynamic Contrast-Enhanced MRI (DCE-MRI) of IGM and breast cancer. MethodsA retrospective analysis involved patients confirmed histopathologically with IGM and BC. All patients underwent conventional ultrasound (C-US), ultrasound elastography (UE), contrast-enhanced ultrasound (CEUS), and DCE-MR examinations. Blind experienced radiologists assessed imaging findings. Diagnostic accuracy, sensitivity, and specificity were calculated for mass and non-mass enhancements. ResultsFor mass enhancements (ME), multimodal ultrasound demonstrated strong efficacy (AUC = 0.8651, 95% CI: 0.7431 to 0.9871), exhibiting high sensitivity (83.3%) and specificity (92.4%) in differentiating IGM from breast cancer. However, for non-mass enhancements (NME), multimodal ultrasound showed limited accuracy (AUC = 0.6306) with lower sensitivity (65.6%) and specificity (81.2%) in distinguishing between IGM and breast cancer. ConclusionMultimodal ultrasound displayed good diagnostic efficacy for mass enhancements in DCE-MRI for idiopathic granulomatous mastitis and breast cancer, while for non-mass enhancement patterns, DCE-MRI remains the most valuable radiological modality for comprehensively assessing this condition's complexities.

Research Progress on Medical Imaging and New Ultrasound Techniques for Assessing the Degree of Carotid Artery Stenosis

The paper summarizes the imaging evaluation methods for assessing the degree of carotid artery stenosis and analyzes the unique advantages and limitations of various imaging techniques in vascular imaging based on existing guidelines and consensus. The paper focuses on reviewing the clinical applications of several novel ultrasound technologies, including the use of advanced hemodynamic parameters such as blood flow dispersion (Tur index) and wall shear stress (WSS). Carotid artery stenosis is closely associated with cardiovascular disease. Although non-invasive and radiation-free ultrasound technology has certain limitations in diagnostic accuracy to a certain extent, with the continuous emergence of advanced functions such as ultrasound hemodynamics and vascular elasticity, the combination of multi-modality and multi-parameter ultrasound is expected to become an important method for efficient diagnosis of arterial stenosis in the future.

Big data and machine learning in digital forensics: Predictive technology for proactive crime prevention

The integration of big data analytics and machine learning [ML] has transformed digital forensics, enabling predictive technologies that proactively prevent cybercrimes and enhance crime investigation processes. As cyber threats grow in scale and complexity, traditional forensic methods face limitations in scalability, efficiency, and accuracy. Big data platforms, such as Hadoop and Spark, combined with advanced ML techniques, offer revolutionary approaches to address these challenges. By analysing vast datasets—including network traces, file metadata, and logs—big data enables the identification of hidden patterns and trends in criminal activities. Simultaneously, ML models, such as supervised and unsupervised learning algorithms, facilitate anomaly detection, predictive risk assessment, and real-time analysis. This article explores how the synergy of big data and ML advances digital forensics by automating large-scale forensic processes, identifying potential cyber threats, and predicting high-risk scenarios. It also discusses the integration of predictive technologies into forensic frameworks, examining the role of automation and real-time analytics in strengthening investigations. The challenges of implementing big data and ML, including issues of data quality, ethical concerns, and legal compliance, are critically analysed. Finally, the article highlights future trends, such as the role of quantum computing and explainable AI, in shaping the future of digital forensics. By providing a comprehensive overview of the field, this study emphasizes the transformative potential of big data and ML in proactive crime prevention, offering insights for researchers, regulators, and industry stakeholders.

Molecular Ultrasound Imaging With Clinically Translatable cRGD-Coated Microbubbles to Assess αvβ3-Integrin Expression in Inflammatory Bowel Disease.

Inflammatory bowel disease (IBD) subdivides into Crohn disease (CD) and ulcerative colitis (UC), and is characterized by unpredictable periods of inflammation and results in significant patient suffering and even death. Conventional diagnostic methods, for example, colonoscopy, computed tomography, or magnetic resonance imaging, have limitations such as invasiveness, patient discomfort, and limited sensitivity and accuracy. Therefore, we propose ultrasound molecular imaging (USMI) to detect and characterize IBD. First, we evaluated integrin-αvβ3 as a biomarker of IBD in human samples and then used clinically translatable cyclic Arg-Gly-Asp-D-Phe-Lys (cRGDfK)-coupled poly(butyl)cyanoacrylate microbubbles (cRGD-MB) to assess IBD in mice. Vascular integrin-αvβ3 expression in human colon tissue samples (healthy, CD and UC, n = 10 per group) was analyzed by immunofluorescence staining. In mice, acute colitis was induced by administration of 4% dextran sodium sulfate in drinking water for 5 days. On day 7, USMI with cRGD-MB was performed in colitis (n = 6) and healthy (n = 5) mice. The signal of bound cRGD-MB was assessed by the destruction-replenishment method. Ex vivo analysis of mouse colon tissue was performed to assess the degree of colitis by hematoxylin-eosin staining and the vascular expression of integrin-αv by immunofluorescence. Human samples showed a significantly higher vascular integrin-αvβ3 expression in CD and UC tissue, when compared with healthy samples (P < 0.005). In mice, a higher binding of cRGD-MB to inflamed colon was detected by USMI compared with healthy controls (P < 0.005). Immunofluorescence staining confirmed these findings, showing stronger integrin-αv expression in acute colitis, with a good correlation between USMI signal intensity and integrin-αv expression (r = 0.8, P = 0.0016). Integrin-αvβ3 on vessels is a suitable marker for IBD. USMI using cRGD-MB accurately detects this marker and correlates well with histology. These encouraging results support clinical translation of this imaging method as a noninvasive and cost-effective monitoring tool.

Conditional neural field latent diffusion model for generating spatiotemporal turbulence

Eddy-resolving turbulence simulations are essential for understanding and controlling complex unsteady fluid dynamics, with significant implications for engineering and scientific applications. Traditional numerical methods, such as direct numerical simulations (DNS) and large eddy simulations (LES), provide high accuracy but face severe computational limitations, restricting their use in high-Reynolds number or real-time scenarios. Recent advances in deep learning-based surrogate models offer a promising alternative by providing efficient, data-driven approximations. However, these models often rely on deterministic frameworks, which struggle to capture the chaotic and stochastic nature of turbulence, especially under varying physical conditions and complex, irregular geometries. Here, we introduce the Conditional Neural Field Latent Diffusion (CoNFiLD) model, a generative learning framework for efficient high-fidelity stochastic generation of spatiotemporal turbulent flows in complex, three-dimensional domains. CoNFiLD synergistically integrates conditional neural field encoding with latent diffusion processes, enabling memory-efficient and robust generation of turbulence under diverse conditions. Leveraging Bayesian conditional sampling, CoNFiLD flexibly adapts to various turbulence generation scenarios without retraining. This capability supports applications such as zero-shot full-field flow reconstruction from sparse sensor data, super-resolution generation, and spatiotemporal data restoration. Extensive numerical experiments demonstrate CoNFiLD’s capability to accurately generate inhomogeneous, anisotropic turbulent flows within complex domains. These findings underscore CoNFiLD’s potential as a versatile, computationally efficient tool for real-time unsteady turbulence simulation, paving the way for advancements in digital twin technology for fluid dynamics. By enabling rapid, adaptive high-fidelity simulations, CoNFiLD can bridge the gap between physical and virtual systems, allowing real-time monitoring, predictive analysis, and optimization of complex fluid processes.

The effects of soy protein and soy isoflavones intake on chronic kidney disease: a systematic review and meta-analysis.

Existing literatures on the potential impact of soy protein consumption on kidney function present conflicting findings. In this study, a meta-analysis has been conducted to assess the impact of soy protein consumption in comparison to animal protein consumption among individuals with chronic kidney disease (CKD). A structured electronic search was conducted on Medline, EMBASE, and Cochrane Library for randomized controlled trials published up to March 2024. The outcome measures were serum creatinine (SCR), triglyceride (TG), total cholesterol (TC), calcium (Ca), C-reactive protein, proteinuria, high-density lipoprotein (HDL), low-density lipoprotein (LDL), uric acid (UA) and phosphorus concentrations. Mean differences were calculated for net changes using random-effects models. Eighteen trials with a total of 522 participants were included in this systematic review. The results showed that consumption of soy protein led to a significant decrease in total cholesterol, LDL, and proteinuria levels. The average reduction was - 20.55mg/dL (95% CI - 38.25, - 2.85mg/dL) for total cholesterol (P = 0.02), - 8.26mg/dL (95% CI - 13.35, - 3.17mg/dL; P = 0.001) for LDL and - 140.53 (95% CI - 205.83, - 75.23mg/day) for proteinuria. No statistically significant impact was observed on serum creatinine, triglycerides, calcium, C-reactive protein, HDL, uric acid, or phosphorus levels. The findings of the meta-analysis showed a potential protective impact of soy protein intake on hyperlipidemia and proteinuria inCKD patients. It is important to note that the evidence presented may be of limited accuracy due to relatively small number of trials and participants.

Validation of Analytical Performance Limits for Accuracy with High-Sensitivity Cardiac Troponin Assays.

Validation of Analytical Performance Limits for Accuracy with High-Sensitivity Cardiac Troponin Assays.

3D-printed model for resection of positive surgical margins in robot-assisted prostatectomy.

To improve precision of secondary resection (SR) after positive surgical margin (PSM) detection by frozen section (FS) during nerve-sparing (NS) robot-assisted radical prostatectomy (RARP) by employing a personalised three-dimensional (3D)-printed prostate model derived from pelvic magnetic resonance imaging (MRI). This model was used to mark positive surgical margins (PSM) and guide intraoperative SR during NS-RARP. Prospective multicentre cohort study with 100 patients undergoing NS-RARP between September 2018 and August 2021. Primary and secondary endpoints were the conversion rate of FS-identified PSM to a tumour-free margin and functional/oncological parameters within a 12-month follow-up, respectively. A PSM was identified in 23% of cases during FS, with a conversion to negative surgical margins (NSM) in 83% (19/23 cases) by model-guided SR. The tumour detection rate in SR specimens was 39% (nine of 23 cases). Among the 19 patients with converted margins, 18 (95%) achieved undetectable prostate-specific antigen levels 2 months postoperatively, with six (32%) having subsequent biochemical recurrence within 12 months. prostate-specific-membrane-antigen positron emission tomography computed tomography found one local recurrence, and five cases of metastatic disease. In converted patients, the baseline median five-item version of the International Index of Erectile Function score decreased by 16% after 1 year, with no significant difference compared to patients with primarily NSM. Limitations include the absence of a control group, the potential for false-negative FS results and limited accuracy of MRI. The integration of 3D-printed prostate models into NS-RARP has the potential to positively impact surgical outcomes by improving the precision of SR and optimising pathosurgical communication.

Review on Multisensor SLAM Datasets for Advanced Perception and Mapping Technologies

Abstract. SLAM (Simultaneous Localization and Mapping) is a technique in robotics and computer vision used to build a map of an unknown environment while simultaneously tracking the location of a robot or vehicle within that environment. The primary goal is to enable autonomous systems to navigate and understand their surroundings without prior knowledge of the environment. It has evolved significantly with the integration of diverse sensor modalities which initially used either a single LIDAR (light detection and ranging, or laser imaging, detection, and ranging) or visual sensor to perform the dual tasks of mapping an environment and localizing the device within it. These systems had limitations in accuracy and robustness due to their reliance on a single type of data input. Over time, the field has advanced to incorporate multiple sensor modalities, including LIDAR, visual cameras, Inertial Measurement Units (IMUs), ultrasonic sensors, and GPS. This multi-sensor fusion approach has dramatically enhanced the precision and reliability of SLAM systems. This paper reviews the state-of-the-art datasets that combine data from infrared cameras, depth cameras, LiDAR, and 4D millimeter-wave radar, focusing on their contributions to advancing SLAM technologies. The study analyzes the advantages and limitations of each sensor type, the challenges associated with data fusion, and the impact on perception and mapping accuracy. This review aims to provide a comprehensive understanding of how these multisensor datasets enhance SLAM systems and highlight areas for future research.