We develop an interactive likelihood (ILH) for sequential Monte-Carlo (SMC) methods for image-based multiple target tracking applications. The purpose of the ILH is to improve tracking accuracy by reducing the need for data association. In addition, we integrate a recently developed deep neural network for pedestrian detection along with the ILH with a multi-Bernoulli filter. We evaluate the performance of the multi-Bernoulli filter with the ILH and the pedestrian detector in a number of publicly available datasets (2003 PETS INMOVE, AFL, and TUD-Stadtmitte) using standard, well-known multi-target tracking metrics (OSPA and CLEAR MOT). In all datasets, the ILH term increases the tracking accuracy of the multi-Bernoulli filter.

: The radar multi target tracking (MTT) technique requires prior knowledge of a number of parameters about the sensor, the target and backgrounds. The Integrated Track Splitting (ITS) is a fully automatic track-while-scan (TWS) target tracking algorithm capable of extracting and tracking a target in a dense clutter environment using quality false track discrimination (FTD) methodology. The computational complexity in ITS algorithm is limited, compared to other algorithms they use statistical methods to discriminate between false and true tracks, such as multiple hypothesis tracking (MHT), mainly due to the FTD performed. The paper provides an analysis of tracking parameters that allows determining the limit of the possibility of successful target tracking. Extensive experiments have confirmed that the recursive determination of the probability of the existence of a track during tracking can confirm a true track and reject a false track. The clutter density, number of random occurred targets, targets load during the maneuver and the target detection probability were varied. The results of experiments, carried out via Monte Carlo simulations, shown over representative confirmed true tracks (CTT) diagrams, root mean square error position and normalized tracking efficiency parametric diagrams allow the user to select optimal multi-target tracking parameters for different scenarios and clutter densities.

In this paper, a framework for simultaneous tracking and recognizing drone targets using a low-cost and small-sized millimeter-wave radar is presented. The radar collects the reflected signals of multiple targets in the field of view including drone and non-drone targets. The analysis of the received signals allows multiple targets to be distinguished because of the different reflection patterns. The proposed framework consists of four processes including signal processing, cloud points clustering, target tracking, and target recognition. Signal processing translates the raw signals into spare cloud points. These points are merged into several clusters, each representing a single target. Target tracking estimates the new locations of each detected target. A novel convolutional neural network model is developed for drone and/or non-drone targets feature extraction and recognition. For performance evaluation, a dataset collected with an IWR6843ISK mmWave sensor by Texas Instruments is used for training and testing the convolutional neural network. The proposed recognition model achieves an accuracy of 98.4% for one target and 98.1% for two targets.

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one is designed using a Jetson TX or AGX Xavier, and the other is based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-art deep-learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep-learning-based association metric approach (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep-learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

Pedestrian multi-target tracking technology plays an important role in artificial intelligence, driverless, virtual reality and other fields. The pedestrian multi-target tracking algorithm DeepSORT based on detection is widely used in industry. It mainly tracks multiple pedestrian targets continuously and keeps their ID unchanged. In order to improve the applicability and tracking accuracy of DeepSORT algorithm, this paper improved the IOU distance measurement in the matching process. At the same time, ResNet50 is used as the feature extraction backbone network, and combined with FPN (Feature Pyramid Network), the appearance features of multi-layer pedestrians are fused to improve the tracking accuracy of DeepSORT algorithm. The proposed algorithm is verified on the public data set MOT-16 and it’s tracking accuracy is enhanced to 4.1%.

Abstract: Rationale. Object tracking has significance in many applications ranging from control of unmanned vehicles to autonomous monitoring of specific situations and events, especially when providing safety for patients with certain adverse conditions such as epileptic seizures. Conventional tracking methods face many challenges, such as the need for dedicated attached devices or tags, influence by high image noise, complex object movements, and intensive com-putational requirements. We have developed earlier computationally efficient algorithms for global optical flow reconstruction of group velocities that provide means for convulsive seizure detection and have potential applications in fall and apnea detection. Here, we address the chal-lenge of using the same calculated group velocities for object tracking in parallel. Methods. We propose a novel optical flow-based method for object tracking. It utilizes real-time image se-quences from the camera and directly reconstructs global motion-group parameters of the con-tent. These parameters can steer a rectangular region of interest surrounding the moving object to follow the target. The method successfully applies to multi-spectral data, further improving its effectiveness. Results. Experimental results on simulated tests and complex real-world data demonstrate the method's capabilities. The proposed optical flow reconstruction can provide accurate, robust, and faster results compared to current state-of-the-art approaches.

The world's growing population is highly dependent on animal agriculture. Animal products provide nutrient-packed meals that help to sustain individuals of all ages in communities across the globe. As the human demand for animal proteins grows, the agricultural industry must continue to advance its efficiency and quality of production. One of the most commonly farmed livestock is poultry and their significance is felt on a global scale. Current poultry farming practices result in the premature death and rejection of billions of chickens on an annual basis before they are processed for meat. This loss of life is concerning regarding animal welfare, agricultural efficiency, and economic impacts. The best way to prevent these losses is through the individualistic and/or group level assessment of animal on a continuous basis. On large-scale farms, such attention to detail was generally considered to be inaccurate and inefficient, but with the integration of Artificial Intelligence (AI) assisted technology individualized and per-herd assessments of livestock are possible and accurate. Various studies have shown cameras linked with specialized systems of AI can properly analyze flocks for health concerns, thus improving the survival rate and product quality of farmed poultry. Building on the recent advancements, this review explores the aspects of AI in the detection, counting and tracking of the poultry in commercial and research-based applications.

This paper proposes a multi-terminal adaptive collaborative operation method to solve the problem of unstable internal force tracking in clamping and handling unknown objects by multi-terminal robots. In the proposed method, the internal command force changes the complex internal force control problem into an internal force tracking problem from multi-slave to master. Moreover, we develop an algorithm for multi-slave setups to estimate object stiffness and motion uncertainty in the direction of the internal command force according to Lyapunov theory. Finally, the impedance control generates a reference trajectory for the multi-slave to maintain the desired internal force and track the master’s motion. Several experiments are conducted on a self-made robot equipped. The experimental results show that the oscillation amplitude of each slave end is less than 1 mm, the directional oscillation amplitude is less than 1 degree during the tracking of the desired commanded internal force. For objects with low stiffness, the error of the commanded internal force is less than 1 N (6%) per slave. The error in tracking the commanded internal force for objects with high stiffness is less than 2 N (8%). The results prove the feasibility and effectiveness of the proposed method.

Owing to the upsurge in the number of endangered species and understanding animal patterns in general as well as population demographics; the monitoring of wildlife species is an essential for the conservation and safety of animals. In order to organize and manage the reserves, the nature bequeaths to us, we need to have hands-on information of their population and food trends, conditions where they survive and other species in the ecosystem. The paper presents a vision-based approach to monitor wildlife using an aerial platform. A quad-rotor based aerial platform is used for the very first time for this purpose. Field imaging is done using a digital cellphone camera mounted on the platform to acquire video of horses in the field. Two techniques, Lucas-Kanade and Horn-Schunck methods are applied on the acquired set of images and the results are compared. Noise due to fluctuations and light conditions are minimized using Gaussian and HSV filters. Experiments show results with an absolute mean difference of 2.84 pixels and 8.50 pixels for changes in X and Y directions respectively for the two approaches.

The safe and reliable operation of autonomous vehicles in complex and dynamic environments is heavily dependent upon exteroceptive and proprioceptive sensors. A LiDAR system generates accurate 3D point clouds, which are crucial for the detection, classification, and tracking of multiple targets. LiDAR data, however, presents significant challenges due to its density, noise, and varying sampling rates. In this study, various clustering and MTT techniques for LiDAR point clouds will be identified and classified within the context of autonomous driving to assess the state-of-the-art methods’ key challenges and their performances. We have categorized clustering and MTT methods used in AV applications, identified research gaps and challenges and analyzed existing algorithms and their challenges in detail. Researchers and practitioners in the field of autonomous driving will find this review to be a valuable resource.

For improving the tracking accuracy and model switching speed of maneuvering target tracking in nonlinear systems, a new algorithm named interacting multiple model fifth-degree spherical simplex-radial cubature filter (IMM5thSSRCKF) is proposed in this paper. The new algorithm is a combination of the interacting multiple model (IMM) filter and fifth-degree spherical simplex-radial cubature filter (5thSSRCKF). The proposed algorithm makes use of Markov process to describe the switching probability among the models, and uses 5thSSRCKF to deal with the state estimation of each model. The 5thSSRCKF is an improved filter algorithm, which utilizes the fifth-degree spherical simplex-radial rule to improve the filtering accuracy. Finally, the tracking performance of the IMM5thSSRCKF is evaluated by simulation in a typical maneuvering target tracking scenario. Simulation results show that the proposed algorithm has better tracking performance and quicker model switching speed when disposing maneuver models compared with IMMUKF, IMMCKF and IMM5thCKF.

The prediction of drug-target interactions plays a fundamental role in facilitating drug discovery, where the goal is to find prospective drug candidates. With the increase in the number of drug-protein interactions, machine learning techniques, especially deep learning methods, have become applicable for drug-target interaction discovery because they significantly reduce the required experimental workload. In this paper, we present a spontaneous formulation of the drug-target interaction prediction problem as an instance of multi-instance learning. We address the problem in three stages, first organizing given drug and target sequences into instances via a private-public mechanism, then identifying the predicted scores of all instances in the same bag, and finally combining all the predicted scores as the output prediction. A comprehensive evaluation demonstrates that the proposed method outperforms other state-of-the-art methods on three benchmark datasets.

This paper investigates the problem of cooperative standoff tracking using multiple fixed-wing unmanned aerial vehicles (UAVs) with control input constraints. In order to achieve accurate target tracking in the presence of unknown background wind and target motion, a coordinated standoff target tracking algorithm is proposed. The objective of the research is to steer multiple UAVs to fly a circular orbit around a moving target with prescribed intervehicle angular spacing. To achieve this goal, two control laws are proposed, including relative range regulation and space phase separation. On one hand, a heading rate control law based on Lyapunov guidance vector field is proposed. The convergence analysis show that the UAVs can asymptotically converge to a desired circular orbit around the target, regardless of their initial position and heading. Through rigorous theoretical proof, it is concluded that the command signal of the proposed heading rate controller will not violate the boundary constraint on heading rate. On the other hand, a temporal phase is introduced to represent the phase separation and avoid discontinuity of the wrapped space phase angle. On this basis, a speed controller is developed to achieve equal phase separation. The proposed airspeed controller met the requirement of airspeed constraint. In addition, to improve the robustness of the aircraft during target tracking, an estimator is developed to estimate the composition velocity of the unknown wind and target motion. The proposed estimator uses the offset vector between the UAV’s actual flight path and the desired orbit which is defined by Lyapunov guidance vector field to estimate the composition velocity. The stability of the estimator is proved. Simulations are conducted under different scenarios to demonstrate the effectiveness of the proposed cooperative standoff target tracking algorithm. The simulation results of indicate that, the temporal-phase-based speed controller can achieve fast convergence speed and small phase separation error. Additionally, the composition velocity estimator exhibits fast response speed and high estimation accuracy.

The dynamic factors in the environment violate the static environment assumption of the SLAM algorithm, leading to a decrease in the accuracy of camera positioning. In recent years, many studies have attempted to address dynamic objects by combining semantic constraints and geometric constraints, but issues such as poor real-time performance, the potential for mistakenly treating humans as rigid objects, and subpar performance in high-dynamic scenes still persist. This paper proposes a dynamic scene visual SLAM algorithm called Dynamic SLAM based on target tracking and multi-view geometry (TKG-SLAM), based on object detection, Kalman filters, and multi-view geometry. This algorithm takes into consideration both real-time performance and algorithm accuracy. It combines semantic constraints and multi-view geometry constraints, selectively running the algorithm in different scenarios, filtering and preserving static points for camera pose estimation. Experimental results demonstrate that, compared to current state-of-the-art dynamic SLAM methods, our approach achieves optimal performance in some scenarios and exhibits stronger real-time capabilities.

Current effort with light field displays is mainly concentrated on the widest possible viewing angle, while a single viewer only needs to view the display in a specific viewing direction. To make light field display a practical practice, a super multi-view light field display is proposed to compress the information in the viewing zone of a single user by reducing the redundant viewpoints. A quasi-directional backlight is proposed and a lenticular lens array is applied to achieve the restricted viewing zone. Eye-tracking technique is applied to extend the viewing area. Experimental results show that the proposed scheme can present vivid 3D scene with smooth motion parallax. Only 16.7% conventional light field display data are required to achieve 3D display. Furthermore, an illumination power of 3.5 watt is sufficient to lighten a 31.5-inch light field display，which takes up 1.5% of the illumination power required for planar display of similar configuration.

The multi-UAV target search problem is crucial in the field of autonomous Unmanned Aerial Vehicle (UAV) decision-making. The algorithm design of Multi-agent Reinforcement Learning (MARL) methods has become integral to research on multi-UAV target search, due to its adaptability to the rapid online decision-making required by UAVs in complex, uncertain environments. In non-cooperative target search scenarios, targets may have the ability to escape, complicating UAVs' search efforts and hindering the convergence of the MARL algorithm training. This paper investigates the multi-UAV target search problem in scenarios involving static obstacles and dynamic escape targets, modeling the problem within the framework of Decentralized Partially Observable Markov Decision Process. Based on this model, a Spatio-Temporal Efficient Exploration network and a Global Convolutional Local Ascent mechanism are proposed. Subsequently,we introduce a Multi-UAV Escape Target Search Algorithm Based on MAPPO(ETS-MAPPO) for addressing the escape target search difficulty problem. Simulation results demonstrate that the ETS-MAPPO algorithm outperforms five classical MARL algorithms in terms of the number of target searches,the area coverage rate, and other metrics.

Multi-Object Tracking (MOT) is a key technology for Unmanned Aerial Vehicles (UAVs). Traditional tracking-by-detection methods firstly employ an object detector to retrieve targets in each image and then track them based on a matching algorithm. Recently, the popular multi-task learning methods has been dominating this area since they can detect targets and extract Re-Identification (Re-ID) features in a computationally efficient way. However, the detection task and the tracking task have conflicting requirements on image features, leading to the poor performance of the joint learning model compared to separate detection and tracking methods. The problem is more severe when it comes to UAV images due to the presence of irregular motion of large number of small targets. In this paper, we propose a balanced Joint Detection and Re-ID learning (JDR) network to address the MOT problem in UAV vision. To better handle the non-uniform motion of objects in UAV videos, the Set-Member Filter is applied which describes object state as a bounded set. An appearance matching cascade is then proposed based on target state set. Furthermore, a Motion-Mutation module is designed to address the challenges posed by the abrupt motion of UAV. Extensive experiments on the VisDrone-MOT2019 dataset demonstrate that our proposed model, termed as SMFMOT, outperforms state-of-the-arts by a large margin and achieves superior performance on the MOT tasks in UAV videos.

Compared to wide-field telescopes, small-field detection systems have higher spatial resolution, resulting in stronger detection capabilities and higher positioning accuracy. When detecting by small-field in synchronous orbit, both space debris and fixed stars are imaged as point targets, making it difficult to distinguish them. In addition, with the improvement of detection capabilities, the number of stars in the background rapidly increases, which puts higher requirements on recognition algorithms. Therefore, star detection is indispensable for identifying and locating space debris in complex backgrounds. To address these difficulties, this paper proposes a real-time star extraction method based on adaptive filtering and multi frame projection. We use bad point repair and background suppression algorithms to preprocess star image. Afterwards, we analyze and enhance the target signal-to-noise ratio(SNR). Then, we use multi frame projection to fuse information. Subsequently, adaptive filtering, adaptive morphology, and adaptive median filtering algorithms are proposed to detect trajectories. Finally, the projection is released to locate the target. Our recognition algorithm has been verified by real star images, and the images were captured using small-field telescope. The experimental results demonstrate the effectiveness of the algorithm proposed in this paper. We successfully extracted hip-27066 star, which has magnitudes about 12 and SNR about 1.5. Compared with existing methods, our algorithm has advantages in both recognition rate and false-alarm rate, and can be used as real time target recognition algorithm for space-based synchronous orbit detection payload.

Drones have been used in a variety of scenarios such as atmospheric monitoring, fire rescue, agricultural irrigation, etc., in which accurate environmental perception is of crucial importance for both decision-making and control. Among the drone sensors, the RGB camera is indispensable for capturing rich visual information for vehicle navigation but encounters a grand challenge in high-dynamic-range scenes that occur frequently in real applications. Specifically, the recorded frames suffer from under-exposure and over-exposure simultaneously and degenerate the successive vision tasks. To solve the problem, we take object tracking as an example and leverage the superior response of event cameras over a large intensity range to propose an event-assisted object tracking algorithm that can achieve reliable tracking under large intensity variations. Specifically, we propose to pursue feature matching from dense event signals, and based on which to (i) design a UNet-based image enhancement algorithm to balance the RGB intensity with the help of neighboring frames in the time domain, and then (ii) construct a dual-input tracking model to track the moving objects from intensity balanced RGB video and event sequence. The proposed approach is comprehensively validated in both simulation and real experiments.

We present information theoretic search strategies for single and multi-robot teams to localize the source of biochemical contaminants in turbulent flows. The robots synthesize the information provided by sporadic and intermittent sensor readings to optimize their exploration strategy. By leveraging the spatio-temporal sensing capabilities of a mobile sensing network, our strategies result in control actions that maximize the information gained by the team while optimizing the time spent localizing the position of the biochemical source. By leveraging the team's ability to obtain simultaneous measurements at different locations, we show how a multi-robot team is able to speed up the search process resulting in a collaborative information theoretic search strategy. We validate our proposed strategies in both simulations and experiments.

Non-polio enteroviruses (NPEVs), namely coxsackieviruses (CV), echoviruses (E), enteroviruses (EV), and rhinoviruses (RV), are responsible for a wide variety of illnesses. Some infections can progress to life-threatening complications in children or immunocompromised patients. To date, no treatments have been approved. Several molecules have been evaluated through clinical trials without success. To overcome these failures, the multi-target directed ligand (MTDL) strategy can be applied to tackle enterovirus infections. This work analyzes clinical trials to highlight the best candidates and develops filters to apply to a selection for MTDL synthesis. We explicitly stated the methods used to answer the question: Which solution can fight NPEVs effectively? We note the originality and relevance of this proposal in relation to the state of the art in the enterovirus-inhibitors field. Several combinations are possible to broaden the antiviral spectrum and potency. We discuss data related to the virus and data related to each LEAD compound identified. Overall, this study proposes a perspective on different strategies to overcome issues identified in clinical trials and evaluate the “MTDL” potential to improve the efficiency of drugs synergistically, broaden the targeted, and reduce the adverse effects and drug design cost as well as limit the opportunity of drug-resistant viruses.

Visual Sensor Networks (VSNs) have been the focus of numerous studies, emphasizing the quality of the information they generate. The primary goal of these networks is to capture data from an area, extract the pertinent information from the visual scene, and facilitate communication. However, the presence of objects in the study area can impacted the network's efficiency, linking the quality of acquired data directly to the positioning of the cameras. Strategically positioning multiple cameras in a potentially complex area, while ensuring effective communication between nodes, presents a challenging issue in VSNs applications. This paper introduces a specific method to enhance the deployment of visual sensors in indoor environments. The research addresses the theme of multi-objective optimization of VSN deployment, integrating various criteria: maximizing overall visual coverage, maximizing the observation of zones of interest, maximizing observation redundancy of zones of interest and ensuring communication connectivity for data transfers. To tackle this problem, we simulate the observed environment incorporating cameras, obstacles, and considering zones of interest. Camera positioning is performed while considering visual constraints and the scene's characteristics. The quality of positioning is evaluated based on the defined objective functions. Initially, a comparative study is conducted with a state-of-the-art approach, integrating the first three objective functions. Subsequently, we incorporate the fourth objective function to ensure data transfers. The proposed method demonstrates efficient camera network deployments in indoor areas, considering global coverage and observation redundancy. In contrast to the state-of-the-art, these results are achieved in areas with visual obstacles while ensuring communication connectivity between the different cameras.

Ability of quantitative structure – property / activity relationships (QSPRs/QSARs) to serve for epistemological processes in natural sciences is discussed. Some weirdness of QSPR/QSAR state-of-art are listed. There are some contradictions in the research results in this area. Sometimes, these should be classified as paradoxes or weirdness. These points often are ignored. Here these are listed and briefly commented. In addition, hypothesises on the future evolution of the QSPR/QSAR theory and practice are suggested.

This paper focuses on improving the tracking accuracy for servo systems and increasing the contouring performance of precision machining. The dynamic friction during precision machining is analyzed using the LuGre model. The dynamic and static parameters in the friction model are efficiently and accurately identified using the improved Drosophila Swarm Algorithm based on cross-mutation. The friction tracking error can be deduced by the friction state space and an expression is derived. To compensate for the tracking error caused by friction, a feedforward compensation control is designed to avoid signal lag in traditional friction controllers. Furthermore, the factors of multi-axis parameter mismatching that impact the machining profile accuracy are analyzed for multi-axis control. An adaptive cross-coupled control-based pre-compensation strategy of contour error is designed to reduce both the tracking error and the contour error. The effectiveness of the proposed method is validated through several experiments, which demonstrate a remarkable improvement in tracking performance and contour accuracy.

The study sought to investigate the effect of Multi-choice Goal programming in project Portfolio Analysis, using Lagos State Project Portfolio from between 2017-2021 as a study case. Specifically, the objectives examined the effectiveness of multi-choice goal programming in analyzing the project Portfolio of Lagos State Government and investigated the possible lapses in the use of Multi-choice Goal programming in analyzing the project Portfolio of Lagos State Government. Data were gathered from the State financial Statements and analyzed using Lingo-17 Software. Based on the analysis, the study discovered that the goals formulated can be optimally and minimally attained as the positive deviational and negative deviational variables depict zero. This indicates that the cost incurred on the project portfolio was absolutely minimized during the period and at the same time; Lagos State Government derived the most preferred benefits from it. The study therefore concluded that the State minimized the project costs and at the same time maximized benefits while meeting its overall objectives.

Ship detection in large-scene offshore synthetic aperture radar (SAR) images is crucial in civil and military fields, such as maritime management and wartime reconnaissance. However, the problems of low detection rates, high false alarm rates, and high missed detection rates of offshore ship targets in large-scene SAR images are due to the occlusion of objects or mutual occlusion among targets, especially for small ship targets. To solve this problem, this study proposes a target detection model (TAC_CSAC_Net) that incorporates a multi-attention mechanism for detecting marine vessels in large-scene SAR images. Experiments were conducted on two public datasets, the SAR-Ship-Dataset and high-resolution SAR image dataset (HRSID), with multi-scene and multi-size, and the results showed that the proposed TAC_CSAC_Net model achieves good performance for both small and occluded target detection. Experiments were conducted on a real large-scene dataset, LS-SSDD, to obtain the detection results of subgraphs of the same scene. Quantitative comparisons were made with classical and recently developed deep learning models, and the experiments demonstrated that the proposed model outperformed other models for large-scene SAR image target detection.

The presence of fog in the background can prevent small and distant objects from being detected, let alone tracked. Under safety-critical conditions, multi-object tracking models require faster-tracking speed while maintaining high object-tracking accuracy. The original DeepSORT algorithm used YOLOv4 for the detection phase, and a simple neural network for deep appearance descriptor. Consequently, the feature map generated loses relevant details about the track being matched with a given detection in fog. Targets with a high degree of appearance similarity on the detection frame are more likely to be mismatched, resulting in identity switches or track failures in heavy fog. We propose an improved multi-object tracking model based on the DeepSORT algorithm to im-prove tracking accuracy and speed under foggy weather conditions. First, we employed our camera-radar fusion network (CR-YOLOnet) in the detection phase for faster and more accurate object detection. We proposed an appearance feature network to replace the basic convolutional neural network. We incorporated GhostNet to take the place of the traditional convolutional layers to generate more features and reduce computational complexities and cost. We adopted a segmentation module and fed the semantic labels of the corresponding input frame to add rich semantic information to the low-level appearance feature maps. Our proposed method outperformed YOLOv5 + DeepSORT with a 35.15% increase in multi-object tracking accuracy, a 32.65% increase in multi-object tracking precision, the speed increased by 37.56%, and identity switches decreased by 46.81%.

In modern security situations, tracking multiple human objects in real-time within challenging urban environments is a critical capability for enhancing situational awareness, minimizing response time, and increasing overall operational effectiveness. Tracking multiple entities enables informed decision-making, risk mitigation, and the safeguarding of civil-military operations to ensure safety and mission success. This paper presents a multi-modal electro-optical/infrared (EO/IR) and radio frequency (RF) fused sensing (MEIRFS) platform for real-time human object detection, recognition, classification, and tracking in challenging environments. By utilizing different sensors in a complementary manner, the robustness of the sensing system is enhanced, enabling reliable detection and recognition results across various situations. Specifically designed Radar tag and thermal tag can be used to discriminate friendly and non-friendly objects. The system incorporates deep learning-based image fusion and human object recognition and tracking (HORT) algorithms to ensure accurate situation assessment. After integrating into an all-terrain robot, multiple ground tests were conducted to verify the consistent HORT in various environments. The MEIRFS sensor system has been designed to meet the Size, Weight, Power, and Cost (SWaP-C) requirements for installation on autonomous ground and aerial vehicles.

Underwater robotics equipped with visual detection systems have the function of detecting un-derwater artifacts, which is of great significance to deep-sea archaeology. Underwater artifacts are located in complex environments with poor imaging conditions, and the targets have chal-lenging problems such as breakage, stacking, and sediment burial, which causes the marine cul-tural target detection failures. To solve these problems, this paper proposes an underwater cul-tural target detection algorithm based on the deformable deep aggregation network model for underwater robotics exploration. To fully extract the target feature information of underwater targets in complex environments, this paper designs a multi-scale deep aggregation network with deformable convolutional layers. Besides, the BAM attention module is designed for fea-ture optimization, which enhances the potential feature information of the target while weak-ening the background interference information. Finally, the target prediction is achieved through feature fusion at different scales. The proposed algorithm has been extensively validat-ed and analyzed on the collected underwater artifact datasets, and the precision, recall, and mAP of the algorithm have reached 93.1%, 91.4%, and 92.8%, respectively. In addition, the present al-gorithm has been practically deployed on the underwater robotics. In the deep-sea tests, the ar-tifact detection frame rate reaches up to 19 fps, which satisfies the real-time target detection。

Atrial fibrillation (AF) is the most common cardiac arrhythmia. Its treatment includes antiarrhythmic drugs (AADs) to modulate the function of cardiac ion channels. However, AADs have been limited by proarrhythmic effects, non-cardiovascular toxicities as well as often modest antiarrhythmic efficacy. Theoretical models showed that combined blockade of Nav1.5 (and its current INa) and Kv1.5 (and its current, IKur) ion channels yield a synergistic anti-arrhythmic effect without effect on ventricles. We focused on Kv1.5 and Nav1.5 to search for structural similarities in their binding site (BS) for flecainide (a common blocker and widely prescribed AAD), as a first step for prospective rational multi-target directed ligand (MTDL) design strategies. We presented a computational workflow for flecainide BS comparison in a flecainide-Kv1.5 docking model and a solved structure of flecainide-Nav1.5 complex. The workflow includes docking, molecular dynamics, BS characterization and pattern matching. We identified a common structural pattern in flecainide BS for these channels. The latter belongs to the inner cavity and consist of a hydrophobic patch and a polar region, involving residues from S6 helix and P-loop. Since the rational MTDL design for AF is still incipient, our findings could advance multi-target atrial-selective strategies for AF treatment.

The integration of bioinformatics in drug discovery has revolutionized the field of pharmaceutical research. The use of computational tools and techniques has enabled researchers to analyze vast amounts of data, identify potential drug targets, and design new drugs with greater precision and efficiency. The integration of bioinformatics has also facilitated the development of personalized medicine, where drugs can be tailored to individual patients based on their genetic makeup. However, there are still challenges that need to be addressed, such as the need for more accurate predictive models and the ethical considerations surrounding the use of patient data. Overall, the integration of bioinformatics in drug discovery holds great promise for improving human health and advancing our understanding of disease mechanisms. In this mini-review, we discuss how Bioinformatics plays a crucial role in each step of drug discovery by providing tools and techniques to analyze large amounts of data generated from various sources, as well as the challenges and the opportunities offered by bioinformatics.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has resulted in the current COVID-19 pandemic. Worldwide this disease has infected around 1.5 million individuals with a mortality rate ranging from 5 to 10%. It has also imposed extreme challenges on global health, economy, and social behavior. Due to the unavailability of therapeutics, several efforts are going on in the drug discovery to control the SARS-CoV-2 viral infection. The main protease (M^Pro) plays a critical role in viral replication and maturation, thus can serve as the primary drug target. To understand the structural evolution of M^Pro, we have performed phylogenetic and SSN analysis, that depicted divergence of Coronaviridae M^Pro in five clusters specific to viral hosts. This clustering was also corroborated with the comparison of M^Pro structures. Furthermore, it has been observed that backbone and binding site conformations are conserved despite variation in some of the residues. This conservation can be exploited to repurpose available viral protease inhibitors against SARS-CoV-2 M^Pro. In agreement with this, we performed screening of the custom-made library of ~7100 molecules including active ingredients present in the Ayurvedic anti-tussive medicines, anti-viral phytochemicals and synthetic anti-virals against SARS-CoV-2 M^Pro as the primary target. We identified several natural molecules that strongly binds to SARS-CoV-2 M^Pro among which top seven molecules are d-Viniferin, Myricitrin, Taiwanhomoflavone A, Lactucopicrin 15-oxalate, Nympholide A, Biorobin and Phyllaemblicin B. Most of the predicted lead molecules are from Vitis vinifera, also reported for anti-tussive and/or antiviral activities. These molecules also showed strong binding with other main targets RdRp and hACE-2. We anticipate that our approach for identification of multi-target-directed ligand will provide new avenues for drug discovery against SARS-CoV-2 infection.

The development of biosensors for target detection plays a crucial role in advancing various fields of bioscience. This work presents the development of a genosensor that exploits the colorimetric phenol-sulfuric acid sugar reaction for the detection of DNA, and RNA as specific targets, and DNA intercalator molecules. The biosensor combines simplicity and reliability to create a novel bio-assay for accurate and rapid analysis. A 96-well microplate based on polystyrene polymer was used as the platform for an unmodified capture DNA immobilization via a silanization process and with (3-Aminopropyl) triethoxysilane (APTES). After that, a hybridization step was carried out to catch the target molecule, followed by adding phenol and sulfuric acid to quantify the amount of DNA or RNA sugar backbone. This reaction generates a yellow-orange color on the wells measured at 490 nm that was proportional to the target concentration. Under the optimum conditions, a calibration curve was obtained for each target. The developed biosensor demonstrated high sensitivity, good selectivity, and linear response over a wide concentration range for DNA and RNA targets. Additionally, the biosensor was successfully employed for the detection of DNA intercalator agents that inhibit the hybridization of DNA complementary to the immobilized capture DNA. The developed biosensor offers a potential tool for sensitive and selective detection in various applications, including virus diagnosis, genetic analysis, pathogenic bacteria monitoring, and drug discovery.

The COVID-19 was described as a respiratory illness, however further studies recognize it as a complex heterogeneous multisystemic disorder. Global efforts have been proposed to combat COVID-19, emerging diverse therapeutic options, in which discovering new drug therapies, development of vaccines and drug repurposing have been considered the most promising approaches to fight the virus. This study aimed to repurpose known drugs for use against the COVID-19, finding better therapeutic options. Seventeen biological databases were used in this study. The genetic algorithm (GA) was performed for a set of drug target classes and COVID-19 proteins as input, whose drug candidates are obtained according to the target similarities found in the target-target similarity predictive network, resulting in a drug-target interaction network. Thus, recommended drugs correspond to the union of the drug subsets found during each GA execution. Twenty-eight drugs were indicated to be the best therapeutic targets for the virus, in special, the Cyclosporine drug was administered as adjuvant to steroid treatment for COVID-19 patients which showed positive outcomes, reducing mortality in moderate and severe cases. The drugs found have used to treat other diseases, evidencing that the COVID-19 is a multisystemic disorder and suggests that the viruses’ mechanism of action presents some comorbidity with other human diseases. Evidence shows that the drugs found in this research might act together to fight the virus in a broader fashion, however further studies including in vitro and in vivo experiments are needed to find the best combination of these drugs.

Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest. This large-scene data-intensive technology puts a high value on automatic target recognition (ATR) which can free the utilizers and boost the efficiency. Recent advances in artificial intelligence have made it possible to create a deep learning-based SAR ATR that can automatically identify target features from massive input data. In the last 6 years, intensive research has been conducted in this area, however, most papers in the current SAR ATR field used recurrent neural network (RNN) and convolutional neural network (CNN)-varied models to deepen the regime’s understanding of the SAR images. To equip SAR ATR with updated deep learning technology, this paper tries to apply a lightweight vision transformer (LViT)-based model to classify SAR images. The entire structure was verified by an open- accessed SAR data set and recognition results show that the final classification outcomes are robust and more accurate in comparison with referred traditional network structures without even using any convolutional layers.

Lung cancer represents the most common form of cancer accounting for 1.8 million deaths globally in 2020.The 5-year relative survival rate for lung cancer is lower than many other leading cancer types. Over the last decade the treatment for advanced and metastatic non small cell lung cancer have dramatically improved due to the development of immune checkpoint inhibitors and the identification of targetable driver mutations. Recently, potentially effective inhibitors of a hitherto untargetable oncogenic driver mutation in NSCLC, Kirsten Rat Sarcoma (KRAS) have been developed. KRAS mutations are found in 20-25% of NSCLC and represent the most frequent mutation. The mutation is almost exclusively detected in adenocarcinoma and is found among smokers 90% of the time. Along with the development of new drugs that have been showing promising activity, resistance mechanisms have begun to be clarified. The aim of this review is to unwrap the biology of KRAS in NSCLC with a specific focus on primary and secondary resistance mechanisms and their possible clinical implications.

The increasing emergence of multidrug resistant (MDR) pathogens, due to antibiotics misuse, translates in obstinate infections, with high morbidity and high-cost hospitalizations. To oppose these MDR superbugs, new antimicrobial options are necessary. Although both quaternary ammonium (QASs) and phosphonium salts (QPSs) possess antimicrobial effects, QPSs have been studied at lesser extent. Recently, we have successfully reported on the bacteriostatic and cytotoxic effects of a triphenyl phosphonium salt against MDR isolates of Enterococcus and Staphylococcus genus. Here, aiming at finding new antibacterial devices possibly bactericidal towards a broader spectrum of clinically relevant bacteria, responsible for severe human infections, we synthesized a water-soluble, sterically hindered quaternary phosphonium salt (BPPB). It encompasses two triphenyl phosphonium groups linked by a C12 alkyl chain, thus embodying the characteristics of molecules known as bola-amphiphiles. BPPB was characterized by ATR-FTIR, NMR and UV spectroscopy, FIA-MS (ESI), elemental analysis and potentiometric titrations. Optical and DLS analyses evidenced BPPB tendency to self-forming spherical vesicles in solution (45 nm by DLS), having a positive zeta potential (+18 mV). The antibacterial effects of BPPB were for the first time assessed against fifty clinical isolates of both Gram-positive and Gram-negative species. Excellent antibacterial effects were observed on all strains tested, involving all the most worrying species included in ESKAPE bacteria. The lowest MICs were 0.250 µg/mL, while the highest ones (32 µg/mL) were observed on MDR Gram-negative metallo-β-lactamase-producing bacteria and/or species resistant also to colistin, carbapenems, cefiderocol, so that intractable with current available antibiotics. Moreover, when administered to HepG2 human hepatic and Cos-7 monkey kidney cell lines, BPPB showed selectivity indices > 10 for all Gram-positive isolated and for clinically relevant Gram-negative superbugs such as those of E. coli species, thus being very promising to be clinically developed.

Unmanned surface vehicles have the advantages of maneuverability, concealment, wide activity area and low cost of use. Therefore, they have broad application prospects. This makes unmanned surface vehicles a research hotspot at home and abroad, and the sensing technology is the basis for the unmanned surface vehicles to perform tasks. The perception technology based on optical vision has the advantages of convenient application, relatively low cost, easy data acquisition and large amount of information, and has been widely studied by scholars at home and abroad. This paper mainly discusses the research of optical vision in unmanned surface vehicles from five aspects: Firstly, the water surface image preprocessing based on unmanned surface vehicles, mainly including water surface image stabilization research and defogging enhancement research; two water boundary detection; It is the use of light vision target detection; the fourth is the surface target tracking method. Finally, the light vision research of unmanned surface vehicles is summarized and forecasted.

The delineation of the clinical target volumes (CTVs) for radiation therapy is time-consuming, requires intensive training and shows high inter-observer variability. Supervised deep learning methods depend heavily on consistent training data, thus state-of-the-art research focuses on making CTV labels more homogeneous and strictly bounding them to current standards. International consensus expert guidelines standardize CTV delineation by conditioning the extension of the clinical target volume on surrounding anatomical structures. Training strategies that directly following the construction rules given in the expert guidelines or the possibility to quantify the conformance of manually drawn contours with the guidelines are still missing. 71 anatomical structures that are relevant for CTV delineation in head and neck cancer patients according to the expert guidelines were segmented on 104 CT scans to assess the possibility to automate their segmentation by state-of-the-art deep learning methods. nnU-Net models were trained to automatically segment those 71 structures on planning CT scans. We report the DICE, HD and sDICE for 71 + 5 anatomical structures for most of which no previous segmentation accuracies have been reported. For those structures, for that prediction values have been reported, our segmentation accuracy matched or exceeded the reported values. The predictions from our models were always better than those predicted by the TotalSegmentator. The sDICE with 2mm margin was larger than 80% for almost all structures. Individual structures with decreased segmentation accuracy are analyzed and discussed with respect to their impact on the CTV delineation following the expert guidelines. No deviation is expected to affect the rule-based automation of the CTV delineation.

This paper considers the detection of fluctuating target in heavy-tailed clutter through the use of dynamic programming based on track-before-detect (DP-TBD) in radar systems. The clutter is modeled in terms of K-distribution, which can be widely used to describe non-Gaussian clutter received from high-resolution radars and radars working at small grazing angle. Swerling type 1 is considered to describe the target fluctuation between scans. Conventional TBD techniques suffer from significant performance loss in heavy-tailed environments due to the more frequent occurrences of target-like outliers. In this paper, we resort to DP-TBD algorithm based on prior information, which can enhance the detection performance by using the environment and target fluctuating information during the integration process of TBD. Under non-Gaussian background, the expressions of the likelihood ratio merit function for Swerling type 1 target are derived first. However, the closed analytical form of the merit function is difficult to be obtained. In order to reduce the complexity of evaluating the merit function and the computational load, an efficient approximation method as well as a two-stage detection approach is proposed and used in the integration process. Finally, several numerical simulations of the new strategy and the comparisons are presented to verify that the proposed algorithm can improve the detection performance, especially for fluctuating target in heavy-tailed clutter.

Infection with the malaria parasite Plasmodium, remains a major cause of illness and death world-wide. The development of evasion strategies by the parasite from host immunity and its adaptability to antimalarial drugs has raised the urgency for developing new strategies to combat this disease. One promising avenue is targeting telomeres – sequences found at chromosome termini– and telomerase – the enzyme that catalysis synthesis of telomeres using an intrinsic RNA template. As telomeres shorten critically, cells undergo replicative senescence or apoptosis. Plasmodium, lacking telomerase activity in its human stages, exploits alternative mechanisms, accelerating telomere shortening, aging, and immune evasion. Chemical telomerase inhibitors show promise as antimalarials. In this review, we examine the potential of targeting this system in malaria therapy, with telomerase inhibitors offering a novel approach. A systematic search on PubMed using Boolean techniques identified 246 relevant articles from 1985 to March 31, 2024. After filtering, 43 articles met inclusion criteria, supplemented by snowball sampling. The telomerase inhibitor drug strategy is widely applicable against cancer. However, given the drugability of telomerase and the absolute requirement for active telomere maintenance in the vast majority of parasites including plasmodium, telomerase and telomere maintenance could well represent the Achilles heel of the parasite

Currently, ovarian cancer (OC) is a target of intense biomarkers research because of its frequent late diagnosis and poor prognosis. Serum determination of Human epididymis protein 4 (HE4) is a very important early detection test. Most interestingly, HE4 plays a unique role in OC as it has been implicated not only in OC diagnosis but also in the prognosis and recurrence of this lethal neoplasm, actually acting as a clinical biomarker. There are several evidence about the predictive power of HE4 clinically, conversely less has been described concerning its role in OC oncogenesis. Based on these considerations, the main goal of this review is to clarify the role of HE4 in OC proliferation, angiogenesis, metastatization, immune response and also in the development of targeted therapy. Through a deeper understanding of its functions as a key molecule in the oncogenetic processes underlying OC, HE4 could be possibly considered as an essential resource not only for diagnosis but also for prognosis and therapy choice.

MicroRNAs act as the cardinal post-transcriptional monitors of gene regulatory networks sculpturing the developmental plasticity and stress responses in plants. Single miRNA target several genes and how the transcriptional regulation of miRNA impacts its pool of targets in different tissues and stress conditions is still elusive. The present study investigated the highly conserved and evolving MIR408 family comprehensively by redefining its evolutionary conservation and diversification in plants followed by detailed functional analysis in rice. MIR408 family comprises three dominant mature forms (21 nt) including a distinct monocot variant. Plant MIR408 family can be divided into six groups. miR408 majorly cleave genes belonging to blue copper protein in addition to several other species-specific targets in plants. Screening of 4726 rice accessions identified 22 sequence variants in 1 Kb upstream (15) and MIR408 region leading to the identification of 8 haplotypes (3: Japonica-specific and 5: Indica-specific). miR408-3p follows flag leaf preferential and drought upregulated expression profile in flag leaf and roots of N22 which seems to be regulated by differential fraction of mCs in the precursor region. The active pool of miR408 regulated targets under control and drought conditions is impacted by the tissue type. Comparative expression analysis of miR408/target module under different sets of conditions features 83 targets exhibiting antagonistic expression in rice. Twelve high confidence targets including 4 plantacyanins (OsUCL6, 7, 9 and 30), pirin, OsLPR1, OsCHUP1, OsDOF12, OsBGLU1, glycine rich cell wall, deoxyuridine 5-triphosphate nucleotidohydrolaseand OsERF7 with antagonistic expression under most conditions. Further, over-expression of osa-MIR408 in drought sensitive rice cultivar leads to the massive enhancement of vegetative growth in rice with improved ETR and Y(II) and enhanced the dehydration stress tolerance at seedling stage.

Mesothelin is a protein that is expressed in the mesothelial cell lining in the pleura, peritoneum and pericardium. The gene of mesothelin encodes a precursor protein that is processed to yield mesothelin, which is attached to the cell membrane by a glycophosphatidylinositol linkage and a shred fragment named the megakaryocytic-potentiating factor. The biological functions of this substance in normal cells are still unknown. Experimental studies on knockout mice suggest that this substance does not play an important role in development and reproduction. In contrast, it has been observed that mesothelin is produced in abnormal amounts in several malignant neoplasms such as mesotheliomas and pancreatic adenocarcinomas. Given that mesothelin is overexpressed in many solid tumours and has antigenic properties, this molecule could be considered a tumour marker or an antigenic target for many malignancies. Many molecular studies also have demonstrated that mesothelin is overexpressed in serous ovarian carcinomas and may bind to ovarian cancer antigen Ca-125, favouring the spread of the tumour in the abdominal cavity. Here, we discuss the current knowledge of mesothelin and focus on its role in clinical and pathological diagnoses as well as its impact on the prognosis in serous ovarian carcinomas. We also briefly discuss the latest progress of mesothelin-targeting therapies for this aggressive and lethal neoplasm.

MicroRNAs (miRNAs) are small and non-coding RNAs displaying aberrant expression in the tissue and plasma of cancer patients in comparison to healthy individuals. In past decades, accumulating data proposed that miRNAs could be diagnostic and prognostic biomarkers in cancer patients. It has been identified that miRNAs can act either as oncogenes through silencing of tumor inhibitors or tumor suppressor via targeting oncoproteins. MiR-144 is located in chromosomal region 17q11.2 that was widely destroyed in many types of cancers. Several studies revealed that miR-144 has different target genes including rapamycin, zonula occludens1, SFRP1, and ANO1. MiR-144 acts as a tumor suppressor or oncogene by targeting specific genes. In this review, we define the role of miR‐144 and its targets in different cancers and provide understanding in tumor proliferation, migration, and apoptosis.

Pristimerin (PM) is a naturally occurring quinonemethide triterpenoid compound that isolated from the Celastraceae and Hippocrateaceae families. Its anticancer effects have attracted a great deal of attention, but the mechanisms of action remain obscure. In this study, we screened for the active compounds of Pristimerin using a drug-likeness approach. Potential protein targets of Pristimerin were predicted by PharmMapper and Coremine database. Candidate protein targets were then uploaded to GeneMANIA and GO pathway analysis. Finally, compound-target, target-pathway, and compound-target-pathway networks were constructed using Cytoscape 3.3. The results showed that Pristimerin had good drug ability and identified 13 putative protein targets. Network analysis revealed that these targets are associated with cancer, inflammation and other physiological processes. In summary, Pristimerin is predicted to target a variety of proteins and pathways to form a network that exerts systemic pharmacological effects.

Bistatic scattering coefficient have important application of ocean active microwave remote sensing. In this paper, a general expression of the composite scattering coefficient for multiple dielectric targets of one-dimensional fractal sea surface is derived by MOM method. Secondly, the bistatic scattering coefficient is computed, there are two class missile targets and one class ship target of one-dimensional fractal sea surface, and the influence of the water dielectric constant, fractal dimension, wind speed, the target dielectric constant and spatial position is discussed, and the corresponding conclusions are given. The proposed algorithm is able to solve some composite scattering problems, such as “dielectric or conductive object + rough surface”, “dielectric or conductive floating object +rough ”and it has certain generalization and reference.

Although natural products are an important source of drugs and drug leads, identification and validation of their target proteins have proven difficult. Here, we report the development of a systematic strategy for target identification and validation employing drug affinity responsive target stability (DARTS) and mass spectrometry imaging (MSI) without modifying or labeling natural compounds. Through a validation step using curcumin, which targets aminopeptidase N (APN), we successfully standardized the systematic strategy. Using label-free voacangine, an antiangiogenic alkaloid molecule as the model natural compound, DARTS analysis revealed vascular endothelial growth factor receptor 2 (VEGFR2) as a target protein. Voacangine inhibits VEGFR2 kinase activity and its downstream signaling by binding to the kinase domain of VEGFR2, as was revealed by docking simulation. Through cell culture assays, voacangine was found to inhibit the growth of glioblastoma cells expressing high levels of VEGFR2. Specific localization of voacangine to tumor compartments in a glioblastoma xenograft mouse was revealed by MSI analysis. The overlap of histological images with the MSI signals for voacangine was intense in the tumor regions and showed colocalization of voacangine and VEGFR2 in the tumor tissues by immunofluorescence analysis of VEGFR2. The strategy employing DARTS and MSI to identify and validate the targets of a natural compound as demonstrated for voacangine in this study is expected to streamline the general approach of drug discovery and validation using other biomolecules including natural products.

In daily travel and activities, pathfinding is a significant process. They are often used in transportation routes calculation. They have now evolved to be able to solve most situations of the pathfinding and its related problems. This review describes previous and recent studies on the pathfinding algorithms. It reviews the development of pathfinding algorithms in a classification base on their usage. The aim is to summarize the application of the pathfinding algorithms for the readers interested in the subject that can be used as a supplement.

Multi-Faith Spaces (MFS) are a relatively recent invention that quickly gained in significance. On the one hand, they offer a convenient solution for satisfying needs of people with diverse beliefs in the institutional context of hospitals, schools, airports, etc. On the other hand, as Andrew Crompton pointed out, they are politically significant because the multi-faith paradigm “is replacing Christianity as the face of public religion in Europe” (2012, p. 493). Due to their ideological entanglement, MFS are often used as the means to promote either a more privatised version of religion, or a certain denominational preference. Two distinct designs are used to achieve these means: negative in the case of the former, and positive in the latter. Neither is without problems, and neither adequately fulfils its primary purpose of serving diverse groups of believers. Both, however, seem to follow the biases and main problems of secularism. In this paper, I analyse recent developments of MFS to detail their main problems and answer the question, whether the MFS, and the underlying Multi-Faith Paradigm, can be classified as a continuation of secularism.

In the industrial field, the 3D target detection algorithm PointPillars has gained popularity. Improving target detection accuracy while maintaining high efficiency has been a significant challenge. To address the issue of low target detection accuracy in the PointPillars 3D target detection algorithm, this paper proposes an algorithm based on feature enhancement to improve the backbone network. The algorithm enhances preliminary feature information of the Backbone network by modifying it based on PointPillars with the aid of channel attention and spatial attention mechanisms. To address the inefficiency caused by the excessive number of subsampled parameters in PointPillars, FasterNet (a lightweight and efficient feature extraction network) is utilized for downsampling and forming different scale feature maps. To prevent the loss and blurring of extracted features resulting from the use of inverse convolution, we utilize the lightweight and efficient up-sampling modules Carafe and Dysample for adjusting resolution. Experimental results indicate improved accuracy under all difficulties of the KITTI dataset, demonstrating the superiority of the algorithm over PointPillars.

Online speech enhancement is of great interest, because of its diverse areas of application. The Demucs architecture has been recently shown to achieve a high level of performance, even with small audio segments, while requiring a relatively small amount of computational resources. However, an issue that it bears, as well as most of state-of-the-art speech enhancement techniques, is that of target speech selection: it is assumed that only one speech source is present. However, in real-life scenarios, more than one speech source may be present, in it is uncertain which speech source within the fed mixture should be enhanced. Thus, it is of interest to complement speech enhancement techniques (such as Demucs-based) with a target selection scheme, so as to ensure that only the source of interest is enhanced. In this work, two target selection strategies are explored: 1) an embedding-based strategy, using a codified sample of the target speech, and 2) a location-based strategy, using a beamforming-based pre-filter to select the target that is in front of a 2-microphone array. It is shown that while both strategies improve the performance of the Demucs-based technique when one or more speech interferences are present, they both have their pros and cons. Specifically, while the beamforming-based strategy achieves overall a better performance compared to the embedding-based strategy, it is sensitive against the location variation of the target speech source which the embedding-based strategy does not suffer from.

Pancreatic cancer leads the most common lethal tumor in America. This lethality is related to limited treatment options. Conventional treatments involve a non-specific use of chemotherapeutical agents like 5-FU, capecitabine, gemcitabine, cisplatine, oxaliplatine, or irinotecan, that produce several side effects. This review we focus on the use of targeted nanoparticles as an alternative to the standard treatment for the pancreatic cancer. The principal objective of the use of nanoparticles is the reduction in side effects that conventional treatments produce, mostly because of their nonspecificity. Currently, several molecular markets of pancreatic cancer cells have been studied to target nanoparticles and improve the actual treatment. Therefore, properly functionalizated nanoparticles with specific aptamers or antibodies can be used to recognize pancreatic cancer cells and once cancer is recognized, these nanoparticles can attack the tumor by drug delivery, hyperthermia, or gene therapy.

Amyotrophic Lateral Sclerosis (ALS) is a prototypical neurodegenerative disease characterized by progressive degeneration of motor neurons to severely effect the functionality to control voluntary muscle movement. Most of the non additive genetic aberrations responsible for ALS make its molecular classification very challenging along with limited sample size, curse of dimensionality, class imbalance and noise in the data. Deep learning methods have been successful in many other related areas but have low minority class accuracy and suffer from the lack of explainailbilty when used directly with RNA expression features for ALS molecular classification. In this paper we propose a deep learning based molecular ALS classification and interpretation framework. Our framework is based on training a convolution neural network (CNN) on images obtained from converting RNA expression values into pixels based on DeepInsight similarity technique. Then we employed Shapley Additive Explanations (SHAP) to extract pixels with higher relevance to ALS classifications. These pixels were mapped back to the genes which made them up. This enabled us to classify ALS samples with high accuracy for a minority class along with identifying genes that might be playing an important role in ALS molecular classifications. Taken together with RNA expression images classified with CNN, our preliminary analysis of the genes identified by SHAP interpretation demonstrate the value of utilising Machine Learning to perform molecular classification of ALS and uncover disease-associated genes.

Nanoscale imaging with the ability to identify cellular organelles and protein complexes has been a highly challenging subject in secondary ion mass spectrometry (SIMS) of biological samples. This is because only a few isotopic tags can be used successfully to target specific proteins or organelles. To address this, we have generated gold-nanoprobes, in which gold nanoparticles are conjugated to nanobodies. The nanoprobes were well suited for specific molecular imaging using NanoSIMS at subcellular resolution. They demonstrated to be highly selective to different proteins of interest, and sufficiently sensitive for SIMS detection. The nanoprobes offer the possibility of correlating the investigation of cellular isotopic turnover to the positions of specific proteins and organelles, thereby enabling an understanding of functional and structural relations that are currently obscure.

In order to meet the national energy saving goals set in the Vietnam National Energy Efficiency Program in the period of 2019 – 2030 (VNEEP), the Vietnamese government has adopted a series solutions and policies to improve energy efficiency. The Vietnam’s 63 provinces will be as main actor for the national achievement in energy efficiency. Thus, understanding the province’s potentiality of energy efficiency is useful for the harmonious and sustainable development between the economy and energy systems. In this study, provincial and national data from General Statistic Office are analyzed in terms of the energy efficiency levels. With the trends of economic development and energy consumption in both national and regional levels, the Lorenz curve between Vietnamese energy consumption and GDP is investigated. The Lorenz coefficient shows the energy allocation is nether reasonable nor balanced. By using clustering method, the 63 provinces of Vietnam clustered into 7 groups that the provinces in the cluster has the similar indexes of energy efficiency i.e. ability, responsibility, potential and difficulty. The energy consumption and GDP are predicted in the period of 2019 – 2025. Based on the difference of GDP development and energy consumption levels, the target of energy efficiency for each province through clustering is set. The results show that 33 provinces included in the cluster 1, 2, 3, 4 and 6 are heavy contribution. Among them, the provinces in the cluster 2 and 3 need to focus on the industry sector in their energy saving policy. The cluster 7 included the under-developed provinces can learn development’s experiences of the provinces in the cluster 1, 2, 3 and 4 to find the best way of their future development.

Multi-channel and multi-parameter near-infrared spectrometers (NIRS) have gradually become a new research direction and hot spot due to their ability to provide real-time, continuous, comprehensive indicators of multiple parameters. However, multi-channel and multi-parameter detection may lead to crosstalk between signals. There is still a lack of benchmarks on the evaluation of reliability, sensitivity, stability and response consistency of the NIRS instrument. In this study, a set of test methods (the ink drop test, multi-channel crosstalk test and multi-parameter crosstalk test) for analysis crosstalk and verifying the reliability of NIRS were conducted to test experimental verification on a multi-channel (8-channel), multi-parameter (4-parameter) NIRS instrument independently developed by our team. Results show that these tests can be used to analyze the signal crosstalk and verify the reliability, sensitivity, stability and response consistency in the NIRS instrument. This study contributes to the establishment of benchmarks for the NIRS instrument crosstalk and reliability testing. These novel tests have the potential to become the benchmark for the NIRS instrument reliability testing.

Manipulating autophagy is a promising strategy for treating cancer as several autophagy inhibitors shown to induce autophagic cell death. One of these, autophagonizer (APZ), induces apoptosis-independent cell death by binding an unknown target via an unknown mechanism. To identify APZ targets we used a label-free drug affinity responsive target stability (DARTS) approach with a liquid chromatography/tandem mass spectrometry (LC-MS/MS) readout. Of 35 protein interactors, we identified Hsp70 as a key target protein of unmodified APZ in autophagy. Either APZ treatment or Hsp70 inhibition attenuates integrity of lysosomes, which leads to autophagic cell death exhibiting an excellent synergism with a clinical drug, temozolomide, in vitro, in vivo, and orthotropic glioma xenograft model. These findings demonstrate the potential of APZ to induce autophagic cell death and its development to combinational chemotherapeutic agent for glioma treatment. Collectively, our study demonstrated that APZ, a new autophagy inhibitor, can be used as a potent antitumor drug candidate to get over unassailable glioma and revealed a novel function of Hsp70 in lysosomal integrity regulation of autophagy.

Although there are several access control systems in the literature for flexible policy management in multi-authority and multi-domain environments, achieving interoperability & scalability, without relying on strong trust assumptions, is still an open challenge. We present HMBAC, a distributed fine-grained access control model for shared and dynamic multi-authority and multi-domain environments, along with Janus, a practical system for HMBAC policy enforcement. The proposed HMBAC model supports: (a) dynamic trust management between different authorities; (b) flexible access control policy enforcement, defined at domain and cross-domain level; (c) a global source of truth for all entities, supported by an immutable, audit-friendly mechanism. Janus implements the HMBAC model and relies on the effective fusion of two core components. First, a Hierarchical Multi-Blockchain architecture that acts as a single access point that cannot be bypassed by users or authorities. Second, a Multi-Authority Attribute Based Encryption protocol that supports flexible shared multi-owner encryption, where attribute keys from different authorities are combined to decrypt data distributedly stored in different authorities. Our approach was implemented using Hyperledger Fabric as the underlying blockchain, with the system components placed in Kubernetes Docker container pods. We experimentally validated the effectiveness and efficiency of Janus, while fully reproducible artifacts of both our implementation and our measurements are provided.

Gastroesophageal cancers, are among the most prevalent cancers globally and represent the third leading cause of cancer-related mortality worldwide. Surgical resection remains the primary curative approach for localized and locally advanced stages, but its effectiveness is limited for locally advanced diseases, evidenced by a low 5-year survival rate of around 25%. High relapse rates post-surgery, particularly in western populations, necessitate the use of neoadjuvant, adjuvant, or perioperative strategies involving chemotherapy and radiation to improve surgical outcomes. Neoadjuvant chemoradiation therapy has demonstrated a significant improvement in overall survival. Recent advances have identified several target genes and pathways involved in the pathogenesis and progression of these cancers, leading to the development of targeted drugs, including immunotherapy, anti-HER-2 antibodies, and anti-VEGFR antibodies. These targeted therapies are emerging as promising interventions for better patient outcomes and personalized treatment approaches and therefore could eventually evolve into a novel therapeutic regimen for gastroesophageal cancer.

Chip pad alignment inspection is of great importance in the industrial field. However, due to the fact that chip pads are usually small, problems such as misdetection and missed detection often occur. When applying deep learning methods for chip pad detection, it is necessary to ensure accurate detection of small target chips while meeting the requirements of lightweight detection models for industrial needs. To solve the above problems, this paper proposes a lightweight model based on improved YOLOv5s. Firstly, the feature extraction part is improved to increase the network's focus on the target. Secondly, the feature fusion layer is improved to double the resolution of the prediction head, and the context-aware network is designed to enhance the context-capture ability of key features of small targets. Finally, SIoU is adopted as the loss function to improve the speed and accuracy of the regression frame. The experimental results show that the improved YOLOv5s algorithm improves the detection accuracy by 2.3% and reduces the network parameters by 81.8% compared to the original algorithm. The improved algorithm is combined with image processing techniques to design correction methods for alignment anomalies and realize real-time alignment anomaly correction in industry.

Lung cancer, including both non-small cell lung cancer and small cell lung cancer, remains the leading cause of cancer-related mortality worldwide representing 18% of the total cancer deaths in 2020. Many patients are identified already at an advanced stage with metastatic disease and have a worsening prognosis. Recent advances in the genetic understanding of lung cancer have opened new avenues for personalized treatments and targeted therapies. This review examines the latest discoveries in the genetics of lung cancer, discusses key biomarkers, and analyzes current clinical therapies based on this genetic information. It will conclude with a discussion of future prospects and potential research directions.

WHO reported an estimated 249 million malaria cases and 608,000 malaria deaths in 85 countries in 2022. A total of 94% of malaria deaths occurred in Africa, 80 % of which were children under 5. In other words, one child dies every minute from malaria. The RTS,S/AS01 malaria vaccine, that uses the Plasmodium falciparum circumsporozoite protein (CSP) to target sporozoite infection of the liver, achieved modest efficacy. The Malaria Vaccine Implementation Program (MVIP), coordinated by the WHO and completed at the end of 2023, found that immunization reduced mortality by only 13%. To further reduce malaria death, development of a more effective malaria vaccine is a high priority. Three major malaria vaccine targets being considered are the level of sporozoite liver infection, merozoite red blood cell (RBC) infection, and mosquito midgut infection. These targets involve specific ligand-receptor interactions. However, current malaria vaccine candidates that target two major parasite population bottlenecks, liver infection and mosquito midgut infection, do not focus on such parasite ligands. Here we evaluate the potential of newly identified parasite ligands as novel malaria vaccine antigens.

Tumor heterogeneity is a major obstacle in cancer therapy. We offer a novel perspective on tumor heterogeneity, informed by expanding upon the current view on tumor evolution. It is commonly known that in cancer, it is the advantageous genes and mutations that drive tumor capacities and the progression. We recognize an earlier, often overlooked, but necessary thus crucial step preceding the activation of advantageous genes functionality, namely, cellular response. We suggest that cancer is driven by an adaptive action taken by any organism when confronted with adversity - a cellular response to generate specific cancer capacities demanded to overcome survival threat - the responses that prompt the utilization of the functionality of advantageous genetic mutations and genes to attain these capacities and drive the disease. The ongoing development of cancer capabilities, as cells endeavor to obtain a competitive advantage, results in increased molecular chaos, observed as tumor heterogeneity. When the evolutionary drive for survival is impeded by therapeutic inhibition of critical genes, cell death occurs, a phenomenon thus termed oncogene addiction. We summarize the implications of this new framework for understanding tumor evolution and anti-cancer drug discovery, as well as understanding of basic cancer biology.

This article utilizes the Canny edge extraction algorithm based on contour curvature and the cross-correlation template matching algorithm to extensively study the impact of high-repetition-rate CO2 pulsed Laser on the target extraction and tracking performance of the infrared imaging detector. It establishes a quantified dazzling pattern for lasers on infrared imaging systems. By conducting laser dazzling and damage experiments, a detailed analysis of the normalized correlation between target and dazzling images is performed to quantitatively describe laser dazzling effects. Simultaneously, an evaluation system, including target distance and laser power evaluation factors, is established to determine the dazzling level and whether the target is recognizable. The research results reveal that laser power and target position are crucial factors affecting the detection performance of infrared imaging-guided weapon systems under laser dazzling. Different laser powers are required to successfully interfere with the recognition algorithm of infrared imaging-guided weapons at different distances. And laser dazzling will produce a lot of false edge information, which seriously affects the performance of pattern recognition algorithm. In laser damage experiments, the detector experienced functional damage, with a quarter of the image displaying as completely black. The energy density threshold required for functional damage to the detector is approximately 3 J/cm2. The dazzling assessment conclusions also apply to evaluating damage results. Finally, the proposed evaluation formula aligns with experimental results, objectively reflecting the actual impact of laser dazzling on the target extraction and tracking performance of infrared imaging systems. This study provides an in-depth and accurate analysis for understanding the influence of lasers on the performance of infrared imaging-guided weapons.

Background: Chronic Myeloid Leukemia (CML) is initiated in bone marrow due to chromosomal translocation t(22;9) leading to fusion oncogene BCR-ABL. Targeting BCR-ABL by tyrosine kinase inhibitors (TKI) have changed fatal CML into an almost curable disease. Despite that, TKIs lose their effectiveness due to disease progression. Unfortunately, mechanism of CML progression is poorly understood and common biomarkers for CML progression are unavailable. This study was conducted to find out novel biomarkers of CML progression by employing whole exome sequencing (WES).Materials and Methods: WES of accelerated phase (AP-) and blast crisis (BC-) CML patients was carried out, with chronic phase CML (CP-CML) patients as control. After DNA library preparation and exome enrichment, clustering and sequencing was carried out using Illumina platforms. Statistical analysis was carried out using [SAS/STAT] software version 9.4 and R package employed to find mutations shared exclusively by all AP-/BC-CML. Confirmation of mutations was carried out using Sanger sequencing and protein structure modelling using I-Tasser followed by mutant generation and visualization using PyMOL. Results: Three novel genes (ANKRD36, ANKRD36B and PRSS3) were mutated exclusively in all AP-/BC-CML patients. Only ANKRD36 gene mutations (c.1183_1184 delGC and c.1187_1185 dupTT) were confirmed by Sanger sequencing. Protein modelling studies showed that mutations induce structural changes in ANKRD36 protein. Conclusions: Our studies show that ANKRD36 is a potential common biomarker and drug target of early CML progression. ANKRD36 is yet uncharacterized in human. It has the highest expression in bone marrow, specifically myeloid cells. We recommend carrying out further studies to explore the role of ANKRD36 in biology and progression of CML.

Biofilm-associated proteins (BAPs) are important in the development and resilience of biofilms, which are intricate populations of microbes protected by extracellular matrix. All members of the BAP family are known to possess common characteristics such as high molecular weight and a signal sequence for extracellular secretion. It has been shown that BAPs are directly linked to the pathogenicity of many bacteria. This mini review highlights several potential strategies to target BAPs for drug development.

The microbiome is pivotal in maintaining health and influencing disease by modulating essential inflammatory and immune responses. Hepatocellular carcinoma (HCC), ranking as the third most common cause of cancer-related fatalities globally, is influenced by the gut microbiome through bidirectional interactions between the gut and liver, as evidenced in both mouse models and human studies. Consequently, biomarkers based on gut microbiota represent promising non-invasive tools for the early detection of HCC. There is a growing body of evidence suggesting that the composition of the gut microbiota may play a role in the efficacy of immunotherapy in different types of cancer, thus it could be used as a predictive biomarker. In this review, we will dissect the gut microbiome's role as a potential predictive and diagnostic marker in HCC and evaluate the latest progress in leveraging the gut microbiome as a novel therapeutic avenue for HCC patients, with a special emphasis on immunotherapy.

The aim of this study is to analyse problems related to thermal mapping obtained from thermal data acquired from Unmanned Aerial Systems (UAS) equipped with thermal cameras. We focused on an accurate analysis of uncertainties introduced by the PIX4D Mapper software used to obtain the surface temperature maps of thermal images acquired by the UAS. To achieve this aim, we used artificial thermal reference during the surveys, as well as natural hot targets, i.e. thermal anomalies in the Pisciarelli hydrothermal system in Campi Flegrei caldera (CFc). Artificial thermal targets, expressly created and designed for this goal, are a prototype here called “developed thermal target” (DTT) made by the drone Laboratory at Istituto Nazionale di Geofisica e Vulcanologia - Osservatorio Vesuviano (INGV-OV). We show the results obtained by three surveys during which thermal targets were positioned on land at different flight heights of the UAS. Different heights were also necessary to test spatial resolution of the DTT with the used thermal camera as well as possible temperature differences between the raw images acquired by UAS with the thermal mapping obtained from the PIX4D Mapper software. In this work we have estimated the uncertainty that may be introduced by the mosaic procedure and furthermore we find an attenuation of the measured temperatures introduced by the different distances between the thermal anomaly and sensor. These results appear to be of great importance for the subsequent calibration phase of the thermal maps especially in cases where these methodologies are applied for monitoring purposes of volcanic/geothermal areas.

Buffalo are silent breeders, therefore detecting estrus is a serious challenge. There is a rising need for sensitive and precise biomarkers in this scenario. Recent research on miRNA has demon-strated the importance of these molecules as biomarkers. Though there have been miRNA studies in saliva during the estrous cycle, there have been few miRNA research in blood samples. The current study was designed to look at blood miRNAs during the oestrous cycle in heifers (n=5) to address the issue of silent estrus. On the day of estrus and diestrus, blood samples from 60 heifers were obtained and pooled into (n=5) separate samples. Ultrasonography and progesterone assay was performed to confirm estrus. Then, employing particular miRNA adapters, small RNA se-quencing of miRNA was performed using the Illumina Miseq 2500. The UEA sRNA bioinfor-matics workbench identified 94 substantially differently expressed miRNAs (p>0.05) from these data. In estrus, 63 miRNA were upregulated and 31 miRNA were downregulated. When fold change was increased to (log2foldchange >1; q value less than 0.05), 25 miRNAs were elevated during estrus. miR-497, miR-582, miR-10174, miR-23, miR-223, miR-1296 were upregulated, whereas miR-10167, 671, 1246,122 were downregulated. miR-497 is unusually elevated (log2 foldchange>5) when compared to another miRNA (log2 foldchange >5) miRNet 2.0, Cytoscape, and MIENTURNET network software found that miR-497 has more degree centrality, above 60; it is associated with more than 60 nodes, followed by miR-93

When ground-penetrating radar is used to detect targets within concrete, the location of the targets, the identification of different shapes, properties and less obvious echoes all greatly increase the interpretation time of the staff and can easily cause misjudgment of the echo images. In this paper, the ground-penetrating radar echo images (B-scan) after processing are mean filtered to eliminate the direct waves that interfere greatly with the echoes. The RFB-s structure is added to the YOLOv3-SPP network structure, while the Anchor value is optimized and the EIOU loss function is introduced. For four types of data with different shapes and properties at random target locations, three models, YOLOv3, YOLOv3-SPP and the improved YOLOv3-SPP, are used for classification and identification, and the proposed algorithm models are comprehensively evaluated using model evaluation metrics. The experimental results show that the algorithm models proposed in this paper have good recognition effect in ground-penetrating radar echo image target detection.

Alfalfa primarily produces seeds through cross-pollination among different individuals. Self-pollination results in severe inbreeding depression, such as weak seedlings and termination of growth. Identifying the genetic loci associated with vigorous plant growth could enable the elimination of deleterious alleles and eventually develop inbred alfalfa lines for hybrid production. In this study, 215 alfalfa accessions were self-pollinated for three generations. Within accessions, pairs of weak and strong plants were sampled and bulked for exome sequencing. We extracted individual DNA from 534 plants that included parental clones, strong and weak pairs of plants, and plants selected based on the number of seeds produced. Among them, we formed 42 pools, including 16 with strong plants and 17 with weak plants, 3 top-seeded plants, 3 low-seeded plants, and 3 no-seeded plants. Along with 79 individuals, these pools were sequenced in the target regions covering 112,626 contigs across the entire alfalfa genome. From the 121 samples, (42+79) genotyped, 13.2 million SNPs including indels were generated. After filtering for MAF (>5%), depth (<20X), and no missing genotype and removing indels, a total of 588,136 SNPs were obtained which were used for final analysis. A genome-wide association study was performed and identified 11 genetic loci associated with alfalfa plant growth vigor. The GO analysis generated 12 significantly enriched GO terms. The associated SNPs were on, and near genes involved in stress response, defense responses against pathogens, and plant reproduction. These identified SNPs benefit the development of alfalfa inbred lines by purging the deleterious alleles and biomass improvement through marker-assisted selection.

Traditional camera sensors rely on human eyes for observation. However, the human eye 1 is prone to fatigue when observing targets of different sizes for a long time in complex scenes, and 2 human cognition is limited, which often leads to judgment errors and greatly reduces the efficiency. 3 Target recognition technology is an important technology to judge the target category in camera 4 sensor. In order to solve this problem, a small size target detection algorithm for special scenarios was 5 proposed by this paper. Its advantage is that this algorithm not only has higher precision for small 6 size target detection, but also can ensure that the detection accuracy of each size is not lower than the 7 existing algorithm. In this paper, a new down-sampling method was proposed, which could better 8 preserve the context feature information. The feature fusion network was improved to effectively 9 combine shallow information and deep information. A new network structure was proposed to 10 effectively improve the detection accuracy of the model. In terms of accuracy, it is better than: YOLOX, 11 YOLOXR, YOLOv3, scaled YOLOv5, YOLOv7-Tiny and YOLOv8.Three authoritative public data sets 12 were used in this experiment: a) On Visdron data sets (small size targets), DC-YOLOv8 is 2.5% more 13 accurate than YOLOv8. b) On Tinyperson data sets (minimal size targets), DC-YOLOv8 is 1% more 14 accurate than YOLOv8. c) On PASCAL VOC2007 data sets (Normal size target), DC-YOLOv8 is 0.5% 15 more accurate than YOLOv8.

MicroRNAs (miRNAs) are small non-coding RNAs that play a central role in the post-transcriptional regulation of biological processes. miRNAs regulate transcripts by direct binding involving the Argonaute protein family. The exact rules of binding are not known, and several in silico miRNA target prediction methods have been developed to date. Deep Learning has recently revolutionized miRNA target prediction. However, the higher predictive power comes with decreased ability to interpret increasingly complex models. Here, we present a novel interpretation technique, called attribution sequence alignment, for miRNA target site prediction models that can interpret such Deep Learning models on a two-dimensional representation of miRNA and putative target sequence. Our method produces a human readable visual representation of miRNA:target interactions and can be used as a proxy for further interpretation of biological concepts learned by the neural network. We demonstrate applications of this method in clustering of experimental data into binding classes, as well as using the method to narrow down predicted miRNA binding sites on long transcript sequences. Importantly, the presented method works with any neural network model trained on a two-dimensional representation of interactions and can be easily extended to further domains such as protein-protein interactions.

Global crop yields are estimated to be reduced by 30–40% per year on account of plant pests and pathogens. Agricultural insect pests raise concerns about constraining global food security and climate changes contributing to the rise of infestation. The current management relies on plant breeding, associated or not with transgenes and chemical pesticides. Both approaches face serious technology obsolescence on the field due to resistance breakdown or development of insecticide resistance. The need for new Modes of Action (MoA) approaches in managing crop health grows each year, driven by market demands to reduce economic losses and phytosanitary requirements to meet the consumer perception. Disabling pest genes by sequence-specific expression silencing is considered a promising tool in the development of environment and health respectful biopesticides. The specificity conferred by long dsRNA-base solutions give support to minimizing effects on off-targeted genes in the insect pest genome and the target gene in non-target organisms (NTOs). In this review, we summarize the current status of gene silencing by RNA interference (RNAi) for agricultural control. More specifically, we focus on the engineering, development and application of gene silencing to control Lepidoptera by the employment of non-transforming dsRNA technologies. Despite some delivery and stability drawbacks of topical applications, we reviewed works showing convincing proof-of-concept results that point to imminent innovative solutions. Considerations about the regulamentation of the ongoing research on dsRNA-based pesticides to produce commercialized products for exogenous application are discussed. Academic and industry initiatives reveal a worthy effort to accomplish controlling Lepidoptera pests with this new mode of action to provide more sustainable and reliable technologies to field management. New data on genomics of this taxon encourage the increment of a customized target genes portfolio. As a case of study, we illustrate how dsRNA and associated methodologies could be applied to control an important Lepidopteran coffee pest.

Inflammatory bowel disease (IBD) is a chronic and relapsing disease caused by a dysregulated immune response to host intestinal microbiota that occurs in genetically predisposed individuals. IBD encompasses two major clinical entities: ulcerative colitis (UC), which is limited to the colonic mucosa, and Crohn disease (CD), which might affect any segment of the gastrointestinal tract. Despite the prevalence of IBD is increasing worldwide, therapy remains suboptimal, largely because the variability of causative mechanisms, raising the need to develop individualized therapeutic approaches targeted to each individual patient. In this context, patients-derived intestinal organoids represent an effective tool for advancing our understanding on IBD’ s pathogenesis. Organoid 3D culture systems offer a unique model for dissecting epithelial mechanisms involved IBDs and test individualized therapy, although the lack of a functional immune system and a microbiota, two driving components of the IBD pathogenesis, represent a major barrier for their exploitation in clinical medicine. In this review we have examined how to improve the translational utility of intestinal organoids in IBD and how co-coltures of 3D or 2D organoids and immune cells and/or intestinal microbiota might help to overcome these limitations.

The advancement of precision medicine critically depends on the robustness and specificity of the carriers used for the targeted delivery of effector molecules in the human body. Numerous nanocarriers have been explored in vivo, to ensure the precise delivery of molecular cargos via tissue-specific targeting, including the endocrine part of the pancreas, thyroid, and adrenal glands. However, even after reaching the target organ, the cargo-carrying vehicle needs to enter the cell and then escape from lysosomal destruction. Most of artificial nanocarriers suffer from intrinsic limitations that either prevent them from completing the specific delivery of the cargo. In this respect, extracellular vesicles (EVs) seem to be the natural tool for payload delivery due to their versatility and low toxicity. However, EV-mediated delivery is not selective and usually short-ranged. By inserting the viral membrane fusion proteins into exosomes, it is possible to increase the efficiency of membrane recognition and also ease the process of membrane fusion. This review describes the molecular details of the viral-assisted interaction between the target cell and extracellular vesicles. We also discuss the question of the usability of viral fusion proteins in developing extracellular vesicle-based nanocarriers with higher efficacy of payload delivery. Finally, this review specifically highlights the role of Gag and RNA binding proteins in RNA sorting into extracellular vesicles.

Multiplex genome editing may induce genotoxicity and chromosomal rearrangements due to double-strand DNA breaks at multiple loci simultaneously induced by programmable nucleases, including CRISPR/Cas9. However, recently developed base-editing systems can directly substitute target sequences without double-strand breaks. Thus, the base-editing system is expected to be a safer method for multiplex genome-editing platforms for livestock. Target-AID is a base editing system composed of PmCDA1, a cytidine deaminase from sea lampreys, fused to Cas9 nickase. It can be used to substitute cytosine for thymine in 3-5 base editing windows, 18 bases upstream of the protospacer-adjacent motif site. In the current study, we demonstrated Target-AID-mediated base editing in porcine cells for the first time. We targeted multiple loci in the porcine genome using the Target-AID system and successfully induced target-specific base substitutions with up to 63.15% efficiency. This system can be used for the further production of various genome-engineered pigs.

In microwave imaging it is often of interest to inspect electrically large spatial regions. In these cases, data must be collected over a great deal of measurement points which entails long measurement time and/or costly, and often unfeasible, measurement configurations. In order to counteract such drawbacks, we have recently introduced a microwave imaging algorithm which looks for the scattering targets in terms of equivalent surface currents supported over a given reference plane. While this method is suited to detect shallowly buried targets, it allows to independently process each frequency data, hence the source and the receivers do not need to be synchronized. Moreover, spatial data can be reduced at large extent, without incurring in aliasing artefacts, by properly combining single-frequency reconstructions. In this paper, we validate such an approach by experimental measurements. In particular, the experimental test site consists of a sand box in open air where metallic plate targets are shallowly buried (few cm) under the air/soil interface. The investigated region is illuminated by a fixed transmitting horn antenna whereas the scattered field is collected over a planar measurement aperture at a fixed height from the air-sand interface. The transmitter and the receiver share only the working frequency information. Experimental results confirm the feasibility of the method.

Abstract: Molybdenum (Mo) thin films were sputtered from two kinds of Mo targets with different microstructures under the same sputtering process, and the effect of microstructure of Mo target on morphology, deposition rate and resistance of sputtered film were studied and discussed. The results show that morphological differences between Mo thin films sputtered by Mo targets with different microstructures are very small. The more uniform and finer the grain structures of Mo target, the better the uniformity on thickness and resistance of Mo sputtered film. Moreover, during sputtering process, when Mo target’s grain size is finer and the surface area of grain boundary is higher, the thickness reduction of the target is more homogeneous and the sputtering film has faster deposition velocity. The difference in microstructure of the Mo target has not obvious influence on the grain orientation of sputtering film.

We are in a new chapter of crop and livestock improvement with the emergence of genome editing. This latest generation of molecular tools can be used to make targeted changes in a genome including insertions, deletions, and mutations. With new advances comes new risks for unintended changes and impacts, thus the need for appropriate risk assessment for product development and to inform regulatory measures. Though CRISPR/Cas has arisen as the predominant technology, there are multiple types of genome editing tools each with pros and cons depending on the organism and desired outcome. Furthermore, each editing tool differs in specificity as they may edit non-intended sites, referred to as off-target edits. The consensus of the agricultural editing community is to avoid off-target editing through design and detection, instead of determining whether off-target editing in each case is detrimental. The design of a targeting component, the tool chosen, and the identification of the edit(s) made are the critical factors in avoiding off-target edits and confirming intended edits in final products that are released commercially. The limited amount of head-to-head comparisons of genome editing tools in diverse crops and livestock make it difficult to develop broad conclusions and best practices, which is further compounded by the diversity of techniques, targets, and processes. Developers and breeders should consult the literature and test as needed to determine which editing technology will be the most effective for their purposes, especially as more tools with altered efficiency and specificity become available. Yet, the lack of off-target edits in studies that employed careful design of targeting components followed by wide testing for on- and off-target edits bodes well for the use of genome editing with proper precautions of target selection and screening.

All countries are facing decisions about which groups to prioritise for COVID-19 vaccination after the first vaccine product has been licensed, at which time supply shortages are inevitable. Here we define the key target populations and their size in China for a phased introduction of COVID-19 vaccination with evolving goals, accounting for the risk of illness and transmission. Essential workers (47.2 million) like healthcare workers could be prioritized for vaccination to maintain essential services. Subsequently, older adults, individuals with underlying health conditions and pregnant women (616.0 million) could be targeted to reduce severe COVID-19 outcomes. Then it could be further extended to target adults without underlying health conditions and children (738.7 million) to reduce symptomatic infections and/or to stop virus transmission. The proposed framework could assist Chinese policy-makers in the design of a vaccination program, and could be generalized to inform other national and regional COVID-19 vaccination strategies.

The lean supply chain of construction engineering projects is to achieve the maximum satisfaction of the owners' needs in order to effectively achieve the goal of supply chain management. This paper explores an effective method of lean supply chain cost management for construction engineering projects with target cost management, so that each participating unit on the supply chain node can fully utilizes its core competencies to minimize internal consumption and waste, and achieve the optimal overall efficiency of the supply chain. According to the requirements of the goal planning theory of the construction project company, establish a lean supply chain cost planning system for the construction project, realize the basic model of the lean supply chain cost management of the construction project, and set the target cost from the lean project of the construction project. The technical decomposition is established by the process of cost decomposition and cost pressure transmission and sub-target cost planning.

Targeted enrichment of ultraconserved elements (UCE) has emerged as a promising tool for inferring evolutionary history in many taxa, with utility ranging from phylogenetic and phylogeographic questions at deep time scales to population level studies at shallow time scales. However, the methodology can be daunting for beginners. Our goal is to introduce UCE phylogenomics to a wider audience by summarizing recent advances in arthropod research, and to familiarize readers with background theory and steps involved. We define terminology used in association with the UCE approach, evaluate current laboratory and bioinformatic methods and limitations, and, finally, provide a roadmap of steps in the UCE pipeline to assist phylogeneticists in making informed decisions as they employ this powerful tool. By facilitating increased adoption of UCE in phylogenomics studies that deepen our comprehension of the function of these markers across widely divergent taxa, we aim to ultimately improve understanding of the arthropod tree of life.

Periodontitis is a chronic inflammatory disease affecting the tissues that surround and support the teeth. In the U. S., approximately 65 million people are affected by this condition. Its occurrence is also associated with many important systemic diseases such as cardiovascular disease, rheumatoid arthritis, and Alzheimer’s disease. Among the most important etiologies of periodontitis is Porphyromonas gingivalis, a keystone bacterial pathogen. Keystone pathogens can orchestrate inflammatory disease by remodeling a normally benign microbiota causing imbalance between normal and pathogenic microbiota (dysbiosis). The important characteristics of P. gingivalis causing dysbiosis are its virulence factors that cause effective subversion of host defenses to its advantage [1], allowing other pathogens to grow. However, the mechanisms involving these processes are poorly understood. However, various microbial strategies target host sialoglycoproteins for immune dysregulation. In addition, the enzymes that break down sialoglycoproteins/sialoglycans are the “sialoglycoproteases”, resulting in exposed terminal sialic acid. This process could lead to pathogen-toll like receptor (TLR) interactions mediated through sialic acid receptor–ligand mechanisms. By assessing the function of P. gingivalis sialoglycoproteases, could pave the way to designing carbohydrate analogues and sialic acid mimetics to serve as drug targets.

The development of new target stations for radioisotope production based on a dedicated 70~MeV commercial cyclotron is described. Currently known as the South African Isotope Facility (SAIF), this initiative will free the existing separated-sector cyclotron (SSC) at iThemba LABS (near Cape Town) to mainly pursue research activities in nuclear physics and radiobiology. It is foreseen that the completed SAIF facility will realize a three-fold increase in radioisotope production capacity compared to the current programme based on the SSC.

Portfolio weights solely based on risk avoid estimation error from the sample mean, but they are still affected from the misspecification in the sample covariance matrix. To solve this problem, we shrink the covariance matrix towards the Identity, the Variance Identity, the Single-index model, the Common Covariance, the Constant Correlation and the Exponential Weighted Moving Average target matrices. By an extensive Monte Carlo simulation, we offer a comparative study of these target estimators, testing their ability in reproducing the true portfolio weights. We control for the dataset dimensionality and the shrinkage intensity in the Minimum Variance, Inverse Volatility, Equal-risk-contribution and Maximum Diversification portfolios. We find out that the Identity and Variance Identity have very good statistical properties, being well-conditioned also in high-dimensional dataset. In addition, the these two models are the best target towards to shrink: they minimise the misspecification in risk-based portfolio weights, generating estimates very close to the population values. Overall, shrinking the sample covariance matrix helps reducing weights misspecification, especially in the Minimum Variance and the Maximum Diversification portfolios. The Inverse Volatility and the Equal-Risk-Contribution portfolios are less sensitive to covariance misspecification, hence they benefit less from shrinkage.

The vertebrate annexin superfamily (AnxA) consists of 12 calcium (Ca2+) and phospholipid binding proteins which share a high structural homology. In keeping with this hallmark feature, annexins have been implicated in the Ca2+-controlled regulation of membrane events. In this review, we discuss several themes of potential therapeutic value, namely the regulation of the immune response and the control of tissue homeostasis, that repeatedly surface in the annexin action profile. Our aim is to identify and discuss those annexin properties which might be exploited from a translational science and specifically clinical point of view.

To define the optimistic multiple-granulation (OMG) supra interior operator and the OMG-supra closure operator associated with a set A in a multiple-granulation approximation space, we used the concepts of the OMG-lower set OL (A) and the OMG-upper set OU (A). These operators create an approximate topological space known as optimistic multiple-granulation supratopological spaces. OMG-supra-open and OMG-supra-closed approximation sets are also defined, followed by OMG-supra-continuous approximation and OMG-irresolute approximation.

The paper proposes TOPSIS method for solving multi-objective multi-level programming problem (MO-MLPP) with fuzzy parameters via fuzzy goal programming (FGP). At first, - cut method is used to transform the fuzzily described MO-MLPP into deterministic MO-MLPP. Then, for specific , we construct the membership functions of distance functions from positive ideal solution (PIS) and negative ideal solution (NIS) of all level decision makers (DMs). Thereafter, FGP based multi-objective decision model is established for each level DM for obtaining individual optimal solution. A possible relaxation on decisions for all DMs is taken into account for satisfactory solution. Subsequently, two FGP models are developed and compromise optimal solutions are found by minimizing the sum of negative deviational variables. To recognize the better compromise optimal solution, the concept of distance functions is utilized. Finally, a novel algorithm for MO-MLPP involving fuzzy parameters is provided and an illustrative example is solved to verify the proposed procedure.

Large-scale deep learning models have produced significant results in underwater visual image target detection. However, deploying these models on underwater embedded devices poses a series of issues and challenges. Firstly, underwater devices have limited communication capabilities and carry relatively short supply of energy, resulting in constrained computing power for edge devices. Secondly, the large scale of deep neural networks creates a conflict in power demands with unmanned underwater equipment. Thirdly, insufficient underwater light and turbid water quality will lead to degradation problems in the images acquired by the device. In this paper, we build an offline system to complete the task of underwater scene target recognition. This paper introduces several innovations: 1) The new YOLO-TN model is developed by compressing the target recognition model based on YOLO-V5. The model use a model compression algorithm replace the YOLO-V5’s backbone network with a lightweight network, then perform parameter pruning on the model detection head, while reduce the size of the input image. The model uses a Teacher-guided Neural Architecture Search method based on YOLO-V5, named as YOLO-TN. 2)A method for constructing and processing real underwater environment data sets is designed. The datasets are all captured using underwater unmanned vehicles in real underwater environments, addressing issues present in existing underwater datasets, such as unbalanced target volume and single-image environment. Experimental results demonstrate that the YOLO-TN model significantly reduces the model size while maintaining the original recognition accuracy. Furthermore, it achieves 28.6 FPS on embedded devices, which is 12 times that of the original model.

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors and complexity of character interactions.Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy.To address the dataset complexity and multi-targeting problems, feature extraction is optimized and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students raising their hands, reading, writing, playing cell phones, looking down, and lying on the table in high-definition images. And the accuracy and robustness of this network are verified.Compared with small target detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network has better detection performance and can efficiently deal with the behavior recognition of multiple students.

Lactate, an important metabolic product, provides energy to neural cells during energy depletion or high demand and acts as a signaling molecule in the central nervous system. Recent studies revealed that lactate-mediated protein lactylation regulates gene transcription and influences cell fate, metabolic processes, inflammation, and immune responses. This review comprehensively examines the regulatory roles and mechanisms of lactylation in neurodevelopment, neuropsychiatric disorders, brain tumors, and cerebrovascular diseases. This analysis indicates that lactylation has multifaceted effects on central nervous system function and pathology, particularly in hypoxia-induced brain damage. Highlighting its potential as a novel therapeutic target, lactylation may play a significant role in treating neurological diseases. By summarizing current findings, this review aims to provide insights and guide future research and clinical strategies for central nervous system disorders.

With the global objectives of achieving a ‘carbon peak’ and ‘carbon neutrality’, along with the implementation of carbon reduction policies, China’s industrial structure has undergone significant adjustments, resulting in constraints on high-energy consumption and high-emission industries while promoting the rapid growth of green industries. Consequently, these changes have led to an increasingly complex power system structure and presented new challenges for electricity demand forecasting. To address this issue, this study proposes a 24-step multivariate time series short-term load forecasting algorithm model based on KNN data imputation and BiTCN bidirectional temporal convolutional networks combined with BiGRU bidirectional gated recurrent units and attention mechanism. The Kepler adaptive optimization algorithm (KOA) is employed for hyperparameter optimization to effectively enhance prediction accuracy. Furthermore, using real load data from a wind farm in Xinjiang as an example, this paper predicts the electricity load from January 1st to December 30th in 2019. Experimental results demonstrate that our comprehensive short-term load forecasting model exhibits lower prediction errors and superior performance compared to traditional methods, thus holding great value for practical applications.

Passive radar detection emerges as a pivotal method for environmental perception and target de-tection within radar applications. Leveraging its advantages, including minimal electromagnetic pollution and efficient spectrum utilization, passive radar methodologies have garnered increasing interest. In recent years, there has been an increasing selection of passive radar signal sources, and the emerging 5G has the characteristics of high frequency band, high bandwidth, and a large number of base stations, which make it have significant advantages in passive radar. Therefore, this paper introduces a passive radar target detection method based on 5G signals and designs a rotating target speed measurement experiment. In the experiment, this paper validated the method of de-tecting rotating targets using 5G signals and evaluated the measurement accuracy, providing a research foundation for passive radar target detection using 5G signals and detecting rotating targets such as drone rotors.

The present minireview assessed the benefits of using artificial intelligence applications in healthcare at predicting the targets of bioactive small molecules in human. Method. The tool is a tuned algorithm, with novel data in web interface. Results. We used tables to order the information of Swiss Target Prediction that allow predictions on combination of chemotherapies and probable side effects. This tool is useful to understand the molecular mechanisms underlying a given phenotype or bioactivity, to rationalize possible favorable or unfavorable side effects and to predict off-targets of known molecules as well as to clear the way for drug repurposing. Predictions are done using a ligand-based approach to compare the similarity between a query molecule and the known ligands of a large collection of protein targets. Conclusion. This study allowed us to formulate recommendations for the use of some of the chemotherapeutic agent groups in cancer patients at a low cost. It is very important and beneficial for patients that take medicine for a longer period and on whose lives depend on such treatment.

Despite UAV multi-target detection exhibits considerable developmental potential worldwide, it suffers distinct challenges compared with traditional tasks in this field. These challenges include insufficient feature extraction capabilities for small targets, limited capabilities for multi-dimensional feature fusion, as well as constraints on hardware computation parameters. Especially in mission scenarios such as disaster detection, these challenges will be further amplified. Consequently, this paper introduces SSE-YOLO, an innovative YOLO framework algorithm specially designed to address these challenges. To enhance the model's feature extraction capability, we employ the SPDConv module to replace the original Conv in the backbone section, utilizing depth-separable convolution instead of traditional convolution pooling. Concurrently, we eliminate the SPPF module at the bottom and address a new Separate Kernel Attention Pyramid Pooling (SKAPP) module, substantially enhancing the feature fusion capability at the model's core. Moreover, to address the challenge of multi-dimensional feature fusion, we replace the Concat module of the neck and head with E-BiFPN, transmitting feature information from the backbone to the lower network through four CBS blocks, which effectively resolves the issue of lost contextual information in the model. Meanwhile, SSE-YOLO undergoes ablation experiments on the VisDrone2019 dataset to evaluate its effectiveness against alternative methods, and experimental results illustrate the model's exceptional precision in detecting UAV targets. In comparison to models with comparable experimental accuracy, SSE-YOLO requires remarkably fewer parameters. On the VisDrone2019-DET-test-dev dataset, SSE-YOLO enhances mAP by 17.3%, with a 42.5% reduction in the parameter amounts. Therefore, the proposed method effectively tackles the challenge of reconciling low parameters and high accuracy, presenting a novel pathway for deep learning-based UAV multi-target detection.

To address the challenges associated with the difficult electromagnetic (EM) scattering computations of anisotropic dielectric-coated metallic composite targets, we proposed an efficient hybrid algorithm for simulating the EM scattering of complex targets with anisotropic dielectric coatings. This method, based on Impedance Boundary Condition (IBC), utilizes surface impedance vectors to describe the EM properties of the dielectric. It fully leverages the respective advantages of the low-frequency Method of Moments (MoM) and the high-frequency Physical Optics (PO) to achieve high-precision and rapid EM simulation of anisotropic dielectric-coated metallic composite targets. Employing boundary conditions and equivalent principles, we equivalently transform the EM scattering problem of targets with thin dielectric coatings into the radiation problem of equivalent EM current on impedance surfaces. This enables the high-precision and rapid calculation of Radar Cross Sections (RCS) for complex targets with anisotropic dielectric coatings. Using examples such as a square plate structure, a simplified aircraft, and a complex satellite model, the simulation results exhibit a high degree of agreement with full-wave numerical solutions and demonstrate a significant advantage in computational resources. This research convincingly demonstrates the accuracy and effectiveness of the proposed method.

Underwater target detection is widely used in various applications such as underwater search and rescue, underwater environment monitoring, and Marine resources survey. However, the visibility of the underwater environment and the accuracy of target detection can be affected by complex underwater light changes and unpredictable background noise. To address these issues, we propose an improved underwater target detection algorithm based on YOLOv8n. Our algorithm focuses on three aspects. Firstly, we replace the original C2f module with Deformable Convnets v2 to enhance the adaptive ability of the target region in the convolution check feature map and extract the target region's features more accurately. Secondly, we introduce SimAm, a non-parametric attention mechanism, which can deduce and assign three-dimensional attention weights without adding network parameters. Lastly, we optimize the loss function by replacing the CIOU loss function with the Wise-IOU loss function. To conduct our experiments, we create our own dataset of underwater target detection for experimentation. Meanwhile, we also utilized the Pascal VOC dataset to evaluate our approach. The mAP@0.5 and mAP@0.5:0.95 of the original YOLOv8n algorithm on the underwater target detection were 88.6% and 51.8%, respectively, and the improved algorithm mAP@0.5 and mAP@0.5:0.95 can reach 91.8% and 55.9%. The original YOLOV8n algorithm was 62.2% and 45.9% mAP@0.5 and mAP@0.5:0.95 on the Pascal VOC dataset, respectively. The improved YOLOV8n algorithm mAP@0.5 and mAP@0.5:0.95 were 65.7% and 48.3%, respectively. The floating-point computation volume of the model is reduced by about 6%. The above experimental results prove the effectiveness of our method.

This paper proposes a multimodal fusion 3D target detection algorithm based on the attention mechanism to improve the performance of 3D target detection. The algorithm utilizes point cloud data and information from camera. For image feature extraction, the ResNet50+FPN architecture extracts features at four levels. Point cloud feature extraction employs the voxel method and FCN to extract point and voxel features. The fusion of image and point cloud features is achieved through regional point fusion and regional voxel fusion methods. After information fusion, the Coordinate attention mechanism and SimAM attention mechanism extract fusion features at a deep level. The algorithm's performance is evaluated using the DAIR-V2X dataset. The results show that compared to the Part-A2 algorithm, the proposed algorithm improves the mAP value by 7.9% in BEV view and 7.8% in 3D view at IOU=0.5 (cars) and IOU=0.25 (pedestrians and cyclist). At IOU=0.7 (cars) and IOU=0.5 (pedestrians and cyclist), the mAP value of the SECOND algorithm is improved by 5.4% in the BEV view and 4.3% in the 3D view, compared to other comparison algorithms.