Current Algorithms Research Articles

Public Health Initiatives of Wearable Sensors for Health Monitoring and Early Heart Disease Detection

The science of preserving and enhancing individual and community health is known as public health. In order to accomplish this task, healthy lifestyle promotion, disease and injury prevention research, and the detection, prevention, and management of infectious diseases are used. Early detection and treatment of health disease can improve the prognosis for the condition worldwide. However, the massive volume of data needed poses a problem to the current automatic algorithms for diagnosing health illness. This study presents a medical gadget that uses the Internet of Things to gather cardiac data from individuals both before and after of heart illness. Technology is developing at a quick pace, leading to the establishment of many methodologies and ongoing research into solutions for problems that arise in a variety of industries. Preprocessing techniques are employed to effectively classify collected health data because the human body generates enormous amounts of data all the time. Furthermore, the most important phase is accurately classifying health data, which is necessary for diagnosis. The Deep Convolutional Neural Network (DCNN) is among the greatest and most efficient methods for categorising medical data. The results of the simulation in experimental research demonstrate that following this advise improves classification accuracy.

Investigating amplitude amplification in optimization-based control for a continuous stirred tank reactor

Quantum computers, which utilize quantum states called ‘qubits’ to process information, are becoming of increased interest in a variety of fields because they have the potential to outperform classical computers in certain situations. However, many challenges and hurdles remain, including the development of quantum algorithms that offer a speedup and can be applied to practical problems (some quantum algorithms that offer a speedup may only be applicable in specific and sometimes contrived circumstances). Our previous works have studied the use of quantum computers and quantum algorithms for process control applications. Our prior work evaluated the use of a gate-based quantum amplitude amplification algorithm when applied to a model predictive control optimization problem, specifically evaluating a linear systems example. The results suggested that the algorithm may be suited for the specific linear problem studied (meaning that there is a high probability of obtaining the desired result when measuring the quantum state after the algorithm has been applied). However, the results cannot be generalized to a wider class of systems or to systems containing nonlinearities. To begin to gain an understanding of how the amplitude amplification algorithm might be generalized, this work evaluates the use of the algorithm for the optimization-based control of a nonlinear dynamic system (specifically, a continuous stirred tank reactor). We seek to understand aspects of the problem, such as the development of a solution space, the effects of changing process and control parameters, and the operation of the amplitude amplification algorithm itself. The results demonstrate the challenges that still exist, and demonstrate a method involving inverse sampling transformations to potentially aid in addressing these issues.

Research on improved YOLOV7-SSWD digital meter reading recognition algorithms.

Meter reading recognition is an important link for robots to complete inspection tasks. To solve the problems of low detection accuracy and inaccurate localization of current meter reading recognition algorithms, the YOLOV7-SSWD (YOLOV7-SiLU-SimAM-Wise-IoU-DyHeads) model is proposed, a novel detection model based on the multi-head attention mechanism, which is improved on the YOLOV7-Tiny model. First, the Wise-IoU loss function is used to solve the problem of sample quality imbalance and improve the model's detection accuracy. Second, a new convolutional block is constructed using the SiLU activation function and applied to the YOLOV7-Tiny model to enhance the model's generalization ability. The dynamic detection header is then built as the header of YOLOV7-Tiny, which realizes the fusion of multi-scale feature information and improves the target recognition performance. Finally, we introduce SimAM to improve the feature extraction capability of the network. In this paper, the importance of each component is fully verified by ablation experiments and comparative analysis. The experiments showed that the mAP and F1-scores of the YOLOV7-SSWD model reached 89.8% and 0.84. Compared with the original network, the mAP increased by 8.1% and the F1-scores increased by 0.1. The YOLOV7-SSWD algorithm has better localization and recognition accuracy and provides a reference for deploying inspection robots to perform automatic inspections.

The cooperative algorithm with auxiliary objectives for the truck and trailer routing problem

<p>In this paper, a cooperative algorithm with auxiliary objectives is proposed to resolve the truck and trailer routing problem. In this proposal, each member of the population does not represent a complete solution as in almost any evolutionary algorithm. In addition, for each member, an aptitude is not possible to compute based only on its codification, because the member has only partial information of the solution. All the members of the population have partial information of the solution. Therefore, these members need to cooperate to obtain an aptitude for the entire population. This way of computing fitness is clearly a gap in the literature, and must be investigated. Moreover, the multi-objectivization approach incorporates an important feature to the proposed algorithm in order to improve its performance, i.e., the multi-objectivization approach permits to identify the best trips using the auxiliary objectives. Enough experimental results are shown that the cooperative algorithm is competitive against other current evolutionary algorithms. There no exist statistically significant difference between the cooperative algorithm and the others.</p>

Polygenic Risk Scores: The Next Step for Improved Risk Stratification in Coronary Artery Disease?

Despite significant advances in the management of coronary artery disease (CAD) and reductions in annual mortality rates in recent decades, this disease remains the leading cause of death worldwide. Consequently, there is an ongoing need for efforts to address this situation. Current clinical algorithms to identify at-risk patients are particularly inaccurate in moderate-risk individuals. For this reason, the need for ancillary tests has been suggested, including predictive genetic screening. As genetic studies rapidly expand and genomic data becomes more accessible, numerous genetic risk scores have been proposed to identify and evaluate an individual's susceptibility to developing diseases, including CAD. The field of genetics has indeed made substantial contributions to risk prediction, particularly in cases where children have parents with premature CAD, resulting in an increased risk of up to 75%. The polygenic risk scores (PRSs) have emerged as a potentially valuable tool for understanding and stratifying an individual's genetic risk. The PRS is calculated as a weighted sum of single-nucleotide variants present throughout the human genome, identifiable through genome-wide association studies, and associated with various cardiometabolic diseases. The use of PRSs holds promise, as it enables the development of personalized strategies for preventing or diagnosing specific pathologies early. Furthermore, it can complement existing clinical scores, increasing the accuracy of individual risk prediction. Consequently, the application of PRSs has the potential to impact the costs and adverse outcomes associated with CAD positively. This narrative review provides an overview of the role of PRSs in the context of CAD.

Determining Clinicopathologic Factors That Influence Treatment in Advanced Breast Cancer in Argentina After CDK4/6 Inhibitors.

The optimal treatment sequence for hormone receptor-positive (HR+)/human epidermal growth factor receptor 2-negative (HER2-) advanced breast cancer (ABC) after progression on first-line cyclin-dependent kinase 4/6 inhibitor (CDKi) and endocrine therapy is unclear. Clinical and biological factors influencing treatment choices and outcomes in the second-line setting need to be elucidated. This is a retrospective analysis of a real-world cohort including patients with HR+/HER2- ABC who received CDKi and endocrine therapy in the first-line setting and progressed, requiring second-line treatment. Clinical and biological factors were analyzed to evaluate their association with daily treatment decisions and the prognostic role of progression-free survival (PFS) in the second-line setting. Two hundred thirty-five patients were included. Second-line treatments were hormone therapy (HT) based in 60% and chemotherapy based in 40% of patients. The second-line median PFS was 6.6 months, with no difference between treatment types. In multivariable analysis, postmenopausal status, lower Ki-67 expression, and non-de novo stage IV disease were associated with improved second-line (2L) PFS. Menopausal status significantly interacted with treatment type, with reduced PFS in premenopausal patients receiving HT-based treatments (4.7 v 8.7 months, P = .00045). In our study, treatment decisions reflected the current algorithm incorporated in our clinical guidelines, and prior treatment response was the most relevant factor to determine 2L treatment decision. Menopausal status interacted with the subsequent therapy efficacy in this setting. Hence, we consider that menopausal status should be routinely evaluated in the subgroup analysis of clinical trials.

Revision Hip Arthroscopy: Getting It Right the Second Time

Hip arthroscopy procedures have become increasingly common in the last few decades for treating both intra- and extra-articular hip pathologies. Despite advancements in the field, some patients may not experience improvement and may eventually require revision hip arthroscopy. The multifactorial causes for failure, unknown impacts of the primary procedure and previous iatrogenic considerations can create added complexity for the revision. Given that revision hip arthroscopy has had more variation in patient outcomes and higher rates of subsequent conversion to hip arthroplasty, compared with primary hip arthroscopy, it is imperative to have a good algorithm for patient selection and to understand the various surgical options available to address different pathologies. In this review, we explore the current diagnostic algorithms, etiologies, surgical procedures, outcomes, and provide insights into future directions in the field of revision hip arthroscopy.

BBM: A novel beta-binomial-distribution-based biclustering algorithm for mining m6A co-methylation patterns

Studies have indicated that mining co-methylation patterns of N6-methyladenosine (m6A) can aid in understanding its functional mechanism. However, current algorithms require the conversion of IP and input data matrices into a single methylation level matrix for co-methylation pattern mining. This conversion introduces additional noise and leads to inaccurate results. To address this issue, we propose a novel biclustering algorithm, BBM, based on the beta-binomial distribution. BBM can perform biclustering analysis directly on IP and input matrices without the need for data matrix conversion. The Gibbs sampling method is used to infer parameters in BBM. Simulation studies show that BBM can accurately reproduce the three pre-planted patterns and their overlap. On real data, BBM identify two patterns. Gene Ontology enrichment analysis reveal that the sites remaining in the two patterns are enriched in different biological processes. One pattern is associated with RNA splicing, translation, transport, and localization, while the other is related to histone modification and histone H3 acetylation. These findings suggest that the two patterns are effective co-methylation patterns. In addition, GOE_Score scoring demonstrate that these two patterns are more biologically relevant than patterns mined by other current mainstream algorithms. BBM is freely available at https://github.com/cumtlzhy/BBM.

A novel positive end-expiratory pressure titration using electrical impedance tomography in spontaneously breathing acute respiratory distress syndrome patients on mechanical ventilation: an observational study from the MaastrICCht cohort.

There is no universally accepted method for positive end expiratory pressure (PEEP) titration approach for patients on spontaneous mechanical ventilation (SMV). Electrical impedance tomography (EIT) guided PEEP-titration has shown promising results in controlled mechanical ventilation (CMV), current implemented algorithm for PEEP titration (based on regional compliance measurements) is not applicable in SMV. Regional peak flow (RPF, defined as the highest inspiratory flow rate based on EIT at a certain PEEP level) is a new method for quantifying regional lung mechanics designed for SMV. The objective is to study whether RPF by EIT is a feasible method for PEEP titration during SMV. Single EIT measurements were performed in COVID-19 ARDS patients on SMV. Clinical (i.e., tidal volume, airway occlusion pressure, end-tidal CO2) and mechanical (cyclic alveolar recruitment, recruitment, cumulative overdistension (OD), cumulative collapse (CL), pendelluft, and PEEP) outcomes were determined by EIT at several pre-defined PEEP thresholds (1-10% CL and the intersection of the OD and CL curves) and outcomes at all thresholds were compared to the outcomes at baseline PEEP. In total, 25 patients were included. No significant and clinically relevant differences were found between thresholds for tidal volume, end-tidal CO2, and P0.1 compared to baseline PEEP; cyclic alveolar recruitment rates changed by -3.9% to -37.9% across thresholds; recruitment rates ranged from - 49.4% to + 79.2%; cumulative overdistension changed from - 75.9% to + 373.4% across thresholds; cumulative collapse changed from 0% to -94.3%; PEEP levels from 10 up to 14 cmH2O were observed across thresholds compared to baseline PEEP of 10 cmH2O. A threshold of approximately 5% cumulative collapse yields the optimum compromise between all clinical and mechanical outcomes. EIT-guided PEEP titration by the RPF approach is feasible and is linked to improved overall lung mechanics) during SMV using a threshold of approximately 5% CL. However, the long-term clinical safety and effect of this approach remain to be determined.

Study on the impact of camera ISP algorithms on stripe structured light 3D reconstruction and the improvement of 3D reconstruction accuracy by photon input

This paper investigates the impact of camera image signal processing (ISP) algorithms on stripe structured light 3D reconstruction and explores the improvement of 3D reconstruction accuracy by photon input. Existing 3D reconstruction technologies have broad applications in fields such as intelligent manufacturing, healthcare, and consumer electronics, but their high precision requirements often cannot be met by current ISP algorithms. By using handheld devices to capture images and combining key techniques such as the multi-step phase shifting method, multi-frequency phase unwrapping method, and triangulation method, this paper conducts an in-depth study on the application of photon input in 3D reconstruction. The study demonstrates that using non-visual information (RAW images) as input can significantly improve reconstruction accuracy, producing more accurate results compared to images processed by ISP. The paper also quantifies the impact of ISP processing on 3D reconstruction results by comparing the depth information and point cloud data of two sets of images. Experimental results show that disabling certain ISP algorithms, such as bilateral noise filtering (BNF), edge enhancement (EEH), and non-local means denoising (NLM), can further improve reconstruction accuracy and reduce errors. In conclusion, this paper proposes a photon image-based 3D reconstruction method that, combined with artificial intelligence technology and differentiable point cloud rendering techniques, holds promise for achieving higher precision and faster 3D reconstruction. This technology is of great significance in practical applications, particularly in the field of industrial close-range 3D reconstruction.

Dynamic Assessment of Drain Fluid Amylase Estimates the Risk of CR-POPF Following Pancreatoduodenectomy.

To evaluate whether drain fluid amylase levels on day-1 (DFA1) and day-3 (DFA3) can reliably estimate the risk of clinically relevant-postoperative pancreatic fistula (CR-POPF) following pancreatoduodenectomy (PD) compared to either value alone or in combination with clinicopathologic variables. CR-POPF is a major source of morbidity and mortality following PD. Current drain management algorithms are variable and are mostly dependent on DFA1, while the DFA3 is seldom utilized to guide clinical decision making. Between 2015-2020, patients who underwent PD at two high-volume pancreas centers and had intraoperative drain placement with measurement of DFA1 and DFA3 were retrospectively reviewed. Models to predict CR-POPF were constructed using DFA1, DFA3, fistula risk score (FRS) and other patient or treatment-related parameters. The fittest and more parsimonious model was used to construct a CR-POPF risk calculator. Nine-hundred-twenty-three patients were included in the analysis. The FRS was high in 100(10.9%), intermediate in 524(57.3%), low in 211(23.1%) and negligible in 79(8.6%) patients. The overall rate of CR-POPF was 9.2%. Five logistic regression models were constructed using variables known to be implicated in CR-POPF. A model based solely on DFA1 and DFA3 with a cross-validated area under the curve of 0.846 was selected. A calculator using DFA1 and DFA3 was created based on this model to estimate the risk of CR-POPF. Risk of CR-POPF following pancreatoduodenectomy can be accurately estimated based on measurement of DFA1 and DFA3. Our CR-POPF kinetics calculator can facilitate postoperative risk stratification and guide drain management algorithms.

Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

GLU-YOLOv8: An Improved Pest and Disease Target Detection Algorithm Based on YOLOv8

In the contemporary context, pest detection is progressively moving toward automation and intelligence. However, current pest detection algorithms still face challenges, such as lower accuracy and slower operation speed in detecting small objects. To address this issue, this study presents a crop pest target detection algorithm, GLU-YOLOv8, designed for complex scenes based on an enhanced version of You Only Look Once version 8 (YOLOv8). The algorithm introduces the SCYLLA-IOU (SIOU) loss function, which enhances the model generalization to various pest sizes and shapes by ensuring smoothness and reducing oscillations during training. Additionally, the algorithm incorporates the Convolutional Block Attention Module (CBAM) and Locality Sensitive Kernel (LSK) attention mechanisms to boost the pest target features. A novel Gated Linear Unit CONV (GLU-CONV) is also introduced to enhance the model’s perceptual and generalization capabilities while maintaining performance. Furthermore, GLU-YOLOv8 includes a small-object detection layer with a feature map size of 160 × 160 to extract more features of small-target pests, thereby improving detection accuracy and enabling more precise localization and identification of small-target pests. The study conducted a comparative analysis between the GLU-YOLOv8 model and other models, such as YOLOv8, Faster RCNN, and RetinaNet, to evaluate detection accuracy and precision. In the Scolytidae forestry pest dataset, GLU-YOLOv8 demonstrated an improvement of 8.2% in mAP@0.50 for small-target detection compared to the YOLOv8 model, with a resulting mAP@0.50 score of 97.4%. Specifically, on the IP102 dataset, GLU-YOLOv8 outperforms the YOLOv8 model with a 7.1% increase in mAP@0.50 and a 5% increase in mAP@0.50:0.95, reaching 58.7% for mAP@0.50. These findings highlight the significant enhancement in the accuracy and recognition rate of small-target detection achieved by GLU-YOLOv8, along with its efficient operational performance. This research provides valuable insights for optimizing small-target detection models for various pests and diseases.

Algorithm of surgical treatment for diaphyseal defects of the forearm bones due to gunshot injuries

Introduction In the current system of providing medical aid to wounded servicemen, along with the conservative primary surgical treatment and minimally invasive extrafocal fixation, high-tech surgical interventions of considerable complexity with the use of additive and tissue-engineering technologies have been coming to the forefront. It is necessary to determine their place in the current algorithm of limb bone defect management, which was the substantiation of our study.The purpose of the study was to improve the algorithm for selecting a treatment method for patients with associated gunshot defects of the forearm based on the literature and clinical observations.Materials and Methods We analyzed scientific articles in PubMed and Scientific Electronic Library (eLIBRARY.ru) platforms, published from 2004 to 2024, on the basis of which we could refine the algorithm of treatment method selection for patients with associated gunshot defects of the forearm. The developed algorithm was used to treat 178 patients with gunshot fractures of the forearm.Results The review of the literature established the main provisions and principles that are applied in the reconstruction of the forearm with an associated defect. When choosing the method of bone defect management, a great number of authors tend to build a “reconstructive ladder”, moving from less severe (one bone) and extended defects (small defect up to 2 cm) to more complex (both bones) and massive defect (more than 10 cm). Upon having considered the revealed regularities, we improved the algorithm of surgical treatment of the latter, which is based on two classification principles: defect extention and location. Reconstruction of the forearm as a dynamic system after diaphyseal fractures requires consider the state of the radioulnar joint. The function of the latter depends on the length ratio of the radius and ulna bones. Therefore, we substantiated small (up to 2 cm) forearm bone defects that can be managed by simple surgical methods. Another fundamental addition to the algorithm was the allocation of a patients’ group with a defect of one forearm bone and a fracture of the other bone (defect-fracture); this combination allows avoiding complex surgical methods for reconstruction and use segment shortening.Discussion The treatment of associated forearm defects is challenging, the choice of reconstruction technique remains uncertain, and the required consensus is lacking. Several forearm reconstruction techniques are available, yet there is no reliable evidence of their effectiveness in terms of treatment time, complications, reoperations, and functional recovery.Conclusion The algorithm proposed for the treatment of extensive gunshot-associated defects of the forearm allows us to consider the change in the anatomy, make a surgical plan based on the reconstruction vector, and select optimal surgical techniques.

Towards reliable domain generalization: Insights from the PF2HC benchmark and dynamic evaluations

Deep neural networks (DNNs) are easily biased towards the training set, which causes substantial performance degradation for out-of-distribution data. Many methods are studied to generalize under various distribution shifts in the literature of domain generalization (DG). To facilitate practical DG research, we construct a large-scale non-independent and identically distributed Chinese characters dataset called PaHCC (Printed and Handwritten Chinese Characters) for a real application scenario (generalization from Printed Fonts to Handwritten Characters, PF2HC) of DG methods. We evaluate eighteen DG methods on the proposed PaHCC dataset and demonstrate that the performance of the current algorithms on this dataset remains inadequate. To improve the performance, we propose a radical-based multi-label learning method by integrating structure learning into statistical methods. Moreover, in the dynamic evaluation settings, we discover additional properties of DG methods and demonstrate that many algorithms suffer from unstable performances. We advocate that researchers in the DG community pay attention not only to accuracy under the fixed leave-one-domain-out protocol but also to algorithmic stability across variable training domains in future studies. Our dataset, method, and evaluations bring valuable insights to the DG community and could promote the development of realistic and stable algorithms.

An Enhanced SL-YOLOv8-Based Lightweight Remote Sensing Detection Algorithm for Identifying Broken Strands in Transmission Lines

Power transmission lines frequently face threats from lightning strikes, severe storms, and chemical corrosion, which can lead to damage in steel–aluminum-stranded wires, thereby seriously affecting the stability of the power system. Currently, manual inspections are relatively inefficient and high risk, while drone inspections are often limited by complex environments and obstacles. Existing detection algorithms still face difficulties in identifying broken strands. To address these issues, this paper proposes a new method called SL-YOLOv8. This method incorporates an improved You Only Look Once version 8 (YOLOv8) algorithm, specifically designed for online intelligent inspection robots to detect broken strands in transmission lines. Transmission lines are susceptible to lightning strikes, storms, and chemical corrosion, which is leading to the potential failure of steel- and aluminum-stranded lines, and significantly impacting the stability of the power system. Currently, manual inspections come with relatively low efficiency and high risk, and Unmanned Aerial Vehicle (UAV) inspections are hindered by complex situations and obstacles, with current algorithms making it difficult to detect the broken strand lines. This paper proposes SL-YOLOv8, which is a broken transmission line strand detection method for an online intelligent inspection robot combined with an improved You Only Look Once version 8 (YOLOv8). By incorporating the Squeeze-and-Excitation Network version 2 (SENet_v2) into the feature fusion network, the method effectively enhances adaptive feature representation by focusing on and amplifying key information, thereby improving the network’s capability to detect small objects. Additionally, the introduction of the LSKblockAttention module, which combines Large Selective Kernels (LSKs) and the attention mechanism, allows the model to dynamically select and enhance critical features, significantly enhancing detection accuracy and robustness while maintaining model precision. Compared with the original YOLOv8 algorithm, SL-YOLOv8 demonstrates improved precision recognition accuracy in Break-ID-1632 and cable damage datasets. The precision is increased by 3.9% and 2.7%, and the recall is increased by 12.2% and 2.3%, respectively, for the two datasets. The mean average precision (mAP) at the Intersection over Union (IoU) threshold of 0.5 is also increased by 4.9% and 1.2%, showing the SL-YOLOv8’s effectiveness in accurately identifying small objects in complex situations.

Reversible data hiding in encrypted images based on secret sharing and hierarchical embedding

With the increasing emphasis on information security, reversible data hiding technology in encrypted images (RDH-EI) has been widely applied in cloud storage privacy protection in recent years. However, once the data hider is leaked or compromised, the current algorithm of RDH-EI will encounter the challenge of effectiveness and security. In order to tackle this issue, this paper proposes an RDH-EI scheme based on secret sharing and hierarchical embedding. First, an image secret sharing based on (4, 6)-threshold algorithm is proposed. This algorithm aims to combine image encryption and sharing processes to generate six different encrypted images with vertical correlation. Sending them in encrypted form to cloud storage is beneficial for protecting the semantics of cover image. Then, the hierarchical embedding method is suggested to attain a high embedding payload. In this approach, by analyzing the vertical correlation of adjacent pixels, we have designed three mapping rules based on multi-MSB prediction. Among them, case 1 reserves the highest embedding capacity, case 2 follows, and case 3 has no embedding space. Based on this, the paper can adaptively embed secret data. Finally, fully authorized users can extract secret data and restore the original image by decrypting four or more marked encrypted images. Experimental results indicate that our approach surpass some existing RDH-EI approaches in payload, which average payloads in the best case on the BOSSbase and BOWS-2 datasets reach 4.466 bpp and 4.152 bpp, respectively. Additionally, the proposed RDH-EI method transfers and stores image data in a distributed manner, which helps prevent excessive concentration of power by data hiders and misuse of data. Compared to traditional end-to-end RDH-EI schemes, the proposed approach offers higher security.

SLG-SLAM: An integrated SLAM framework to improve accuracy using semantic information, laser and GNSS data

Visual Simultaneous Localization and Mapping (V-SLAM) is pivotal for precise positioning and mapping. However, visual data from crowd-sourced datasets often contains deficiencies that may lead to positioning errors. Despite existing optimization techniques, current algorithms do not adequately adapt to varied data in vehicle driving scenarios. To address this gap, this study introduces a novel SLAM framework (SLG-SLAM). This framework refines trajectories by integrating semantic information, laser point cloud, and global navigation satellite system (GNSS) data into V-SLAM. Initial trajectory estimates are made after filtering out dynamic targets and are subsequently refined with matched laser point clouds, then corrected for scale and direction using GNSS. The efficacy of this approach is assessed using four public datasets and one self-collected dataset, showing significant enhancements across all datasets. The proposed method reduces the mean absolute trajectory error by 43.50% on the KITTI dataset and 14.91% on the MVE dataset compared to the baseline. Unlike the baseline, which fails on three other datasets, the proposed method successfully performs localization and mapping. Additionally, compared to three other single-source methods (DynaSLAM, MCL, MVSLAM), the proposed method consistently outperforms, demonstrating its superior adaptability and effectiveness.

AI-based detection and identification of low-level nuclear waste: a comparative analysis

Ensuring environmental safety and regulatory compliance at Department of Energy (DOE) sites demands an efficient and reliable detection system for low-level nuclear waste (LLW). Unlike existing methods that rely on human effort, this paper explores the integration of computer vision algorithms to automate the identification of such waste across DOE facilities. We evaluate the effectiveness of multiple algorithms in classifying nuclear waste materials and their adaptability to newly emerging LLW. Our research introduces and implements five state-of-the-art computer vision models, each representing a different approach to the problem. Through rigorous experimentation and validation, we evaluate these algorithms based on performance, speed, and adaptability. The results reveal a noteworthy trade-off between detection performance and adaptability. YOLOv7 shows the best performance and requires the highest effort to detect new LLW. Conversely, OWL-ViT has lower performance than YOLOv7 and requires minimal effort to detect new LLW. The inference speed does not strongly correlate with performance or adaptability. These findings offer valuable insights into the strengths and limitations of current computer vision algorithms for LLW detection. Each developed model provides a specialized solution with distinct advantages and disadvantages, empowering DOE stakeholders to select the algorithm that aligns best with their specific needs.

Optimal Searching-Based Reference Current Computation Algorithm for IPMSM Drives Considering Iron Loss

Optimal Searching-Based Reference Current Computation Algorithm for IPMSM Drives Considering Iron Loss