Weight Training Research Articles

Analysis of combinatory effects of free weight resistance training and a high-protein diet on body composition and strength capacity in postmenopausal women - A 12-week randomized controlled trial

BackgroundMenopause has a significant impact on the endocrine system of middle-aged women, resulting in a loss of skeletal muscle mass (SMM), changes in fat mass (FM) and a reduction in strength capacity. Resistance training (RT) and a high-protein diet (HPD) are effective methods for maintaining or increasing SMM. This study aims to determine the effects of HPD and RT on body composition, muscle thickness and strength capacity in postmenopausal women. MethodsIn total 55 healthy postmenopausal women (age: 58.2 ± 5.6 years, weight 69.1 ± 9.6 kg, height 166.5 ± 6.5 cm) successfully participated in the study. The women were randomly assigned to either group: training + protein (2.5 g/kg fat-free mass (FFM)) (n = 15; TP); only training (n = 12; T); only protein (2.5 g/kg FFM) (n = 14; CP) or control (n = 14; C). TP and T performed RT for 12 weeks with three training sessions and five exercises each. CP and C were prohibited from training during the period. The main parameters analysed for body composition were FFM, SMM, FM, muscle thickness of the M. rectus femoris, M. biceps femoris, M. triceps brachii and M. biceps brachii muscles. Strength was tested using a dynamometer for grip strength and 1-RM in the squat (BBS) and deadlift (DL). ResultsThe SMM significantly increased by RT (TP: (Δ+1.4 ± 0.9 kg; p < 0.05; d = 0.4; T: Δ+1.2 ± 1.3kg; p < 0.05; d = 0.3) and FM could be reduced only in T: (Δ−2.4 ± 2.9 kg; p < 0.05; d = 0.3). In muscle thickness a significant increase in the M. biceps brachii in both training groups (TP: (Δ+0.4 ± 0.3 cm; p < 0.05; d = 1.6; T: (Δ+0.3 ± 0.3 cm; p < 0.05; d = 0.9) and in M. biceps femoris only in TP (Δ+0.3 ± 0.4 cm; p < 0.05; d = 0.9) were observed. HPD without training does not affect body composition, A significant increase in grip strength (TP: Δ+4.7 ± 2.4 kg; (p < 0.05; d = 1.5; T: (Δ+3.6 ± 3.0 kg; p < 0.05; d = 0.8), in BBS (TP: (Δ+30.0 ± 14.2 kg; p < 0.05; d = 1.5; T: (Δ+34.0 ± 12.0 kg; p < 0.05; d = 2.4) and in DL (TP: (Δ+20.8 ± 10.3 kg; p < 0.05; d = 1.6; T: (Δ+22.1 ± 7.6 kg; p < 0.05; d = 2.0) was observed in both training groups. The CP also recorded a significant increase in the BBS (Δ+7.5 ± 5.4 kg; p < 0.05; d = 0.4) and in DL (Δ+5.5 ± 7.7 kg; p < 0.05; d = 0.5). No significant differences were detected for TP and T for any of the parameters. ConclusionThe results indicate that RT enhances body composition and strength capacity in postmenopausal women and is a preventive strategy against muscle atrophy. Besides HPD without training has a trivial significant effect on BBS and DL. HPD with RT has no clear additive effect on body composition and strength capacity. Further studies are needed to confirm these observations.

Implementation of Virtual Yoga Shared Medical Appointment (VYSMA) Pilot at an Academic Medical Center Within a Mixed-Diagnosis Oncology Population.

Yoga is highly sought after by people seeking oncology care, endorsed by clinical practice guidelines, and supported by leading cancer organizations, yet barriers related to access, time, cost, and availability of quality providers remain. Shared medical appointments (SMA), a group healthcare model where patients with similar medical conditions participate in a collective appointment with healthcare providers, are associated with increased access to quality care, patient satisfaction, and clinician satisfaction. We piloted a unique insurance-covered virtual yoga SMA series to assess feasibility and acceptability in a mixed-diagnosis population. In this prospective cohort pilot, a trauma-informed Hanna Somatic Yoga instructor and an integrative medicine physician co-led yoga SMAs via live web-based conferencing. SMA content included conscious self-regulation through mind-body practices including breathing, movement, visualization, meditation, chanting, and guided relaxation. Qualitative and quantitative data were gathered to assess satisfaction with the 88 sessions offered over 33 months. Sixty-nine participants with diverse demographics attended a total of 500 visits. Class attendance ranged from 2-11 participants (mean 6 participants). Participants attended a mean of 7 sessions (range 1-63 sessions), with 63% attending > 1 session. Participants' diagnoses/symptoms included cancer (77%), anxiety/depression (38%), and pain (38%). Preseries, participants reported pain, weakness, neuropathy, lymphedema, insomnia, and fatigue. Postseries survey results suggested improvements in anxiety/fear, pain, fatigue, poor sleep, neuropathy, brain fog, isolation, weakness, inflexibility, and poor balance. Postseries, participants also reported incorporating mindfulness, breathing techniques, somatic skills, weight training, and yoga into their daily routines, with 91% reporting that their goals had been met. Participants appreciated remote delivery, learning new skills, community, and the instructors. This virtual yoga SMA series in a diverse population with mixed diagnoses was feasible, acceptable to participants, and showed promising positive impact. A larger randomized controlled trial with longer follow-up is recommended.

Effectiveness of Weight Training Program on Maximal Muscular Power of the Arm, Some Biomechanical Properties and the Digital Record of 100m Freestyle Swimmers

Effectiveness of Weight Training Program on Maximal Muscular Power of the Arm, Some Biomechanical Properties and the Digital Record of 100m Freestyle Swimmers

Effect of thrower’s ten exercise along with plyometric weight training on throwing distance and hand grip strength among shot put players

Effect of thrower’s ten exercise along with plyometric weight training on throwing distance and hand grip strength among shot put players

Dynamic and Static Workout of In Vitro Skeletal Muscle Tissue through a Weight Training Device.

Enhancing muscle strength through workouts is a key factor inimproving physical activity and maintaining metabolic profiles. The controversial results concerning the impacts of weight training often arise from clinical experiments that require controlled experimental conditions. In this study, a weight training system for a muscle development model is presented, which is capable of performing weight training motions with adjustable weight loads. Through the implementation of cultured skeletal muscle tissue with floating structures and a flexible ribbon, both isotonic (dynamic change in muscle length) and isometric (static in muscle length) exercises can be performed without the deflection of the tissue. Quantitative analysis of contraction force, changes in metabolic processes, and muscle morphology under different weight training conditions demonstrates the effectiveness of the proposed system. Our proposed system holds potential for establishing effective muscle development and for further applications in rehabilitation training methods.

Effects of arginine intake during weight training on blood variables.

This experiment studied the effect of arginine intake on blood pressure and blood variables during weight training in 20 men in their 20s. The resistance exercise program was performed 3 times a week at 60% of one repetition maximum for 8 weeks. The arginine intake group consumed 1,000 mg of arginine 2 tablets per day before weight training for 8 weeks. The placebo group was instructed to consume two of placebo with water, the same as the arginine intake group. After 8 weeks, the day after the end of the resistance exercise program, systolic pressure, diastolic pressure, total cholesterol, triglyceride, high-density lipoprotein, low-density lipoprotein, muscle mass, and maximum muscle strength were measured. In changes in systolic blood pressure, the arginine intake group was 118.20±2.40 mmHg, showed a statistically significant decrease compared to the placebo group. Triglyceride in the arginine intake group was 112.62±2.40 mg/dL, showing a statistically significant decrease compared to the placebo group. Based on these results, arginine intake during resistance exercise is judged to have a positive effect on lowering blood pressure, and is also believed to reduce triglycerides, a blood lipid variable, so it is thought to function as a supplement during exercise.

Self-organizing hypercomplex-valued adaptive network

A novel, unsupervised, artificial intelligence system is presented, whose input signals and trainable weights consist of complex or hypercomplex values. The system uses the effect given by the complex multiplication that the multiplicand is not only scaled but also rotated. The more similar an input signal and the reference signal are, the more likely the input signal belongs to the corresponding class. The data assigned to a class during training is stored on a generic layer as well as on a layer extracting special features of the signal. As a result, the same cluster can hold a general description and the details of the signal. This property is vital for assigning a signal to an existing or a new class. To ensure that only valid new classes are opened, the system determines the variances by comparing each input signal component with the weights and adaptively adjusts its activation and threshold functions for an optimal classification decision. The presented system knows at any time all boundaries of its clusters. Experimentally, it is demonstrated that the system is able to cluster the data of multiple classes autonomously, fast, and with high accuracy.

Deep neural network homogenization of multiphysics behavior for periodic piezoelectric composites

We present a physically informed deep neural network homogenization theory for identifying homogenized moduli and local electromechanical fields of periodic piezoelectric composites. The theory employs a multi-network model to represent solutions to stress equilibrium and electrostatic partial differential equations in the inclusion and the matrix phases, leading to a more accurate depiction of field variables. Satisfaction of periodicity conditions for hexagonal and cubic symmetries are efficiently tackled using a series of sinusoidal functions with known periods and adjustable parameters. Additionally, the theory applies fully trainable weights to the collocation points. These trainable weights, trained concurrently with the neural network weights, compel the neural networks to enhance their performance when faced with large local stress/deformation gradients. The predictive capability of the proposed theory is illustrated by comparison with finite-element solutions for composites reinforced with unidirectional fiber, spherical particle, or weakened by an ellipsoidal cavity over a wide range of volume fractions.

Variational tensor neural networks for deep learning

Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN) into NN frameworks, combined with a variational DMRG-inspired training technique. This in turn, results in a scalable tensor neural network (TNN) architecture capable of efficient training over a large parameter space. Our variational algorithm utilizes a local gradient-descent technique, enabling manual or automatic computation of tensor gradients, facilitating design of hybrid TNN models with combined dense and tensor layers. Our training algorithm further provides insight on the entanglement structure of the tensorized trainable weights and correlation among the model parameters. We validate the accuracy and efficiency of our method by designing TNN models and providing benchmark results for linear and non-linear regressions, data classification and image recognition on MNIST handwritten digits.

Comparison of 8 Weeks of Selected TRX Training and Weight Training on Improving Motor Function and Chronic Nonspecific Back Pain in Women Aged 35 to 55

Comparison of 8 Weeks of Selected TRX Training and Weight Training on Improving Motor Function and Chronic Nonspecific Back Pain in Women Aged 35 to 55

Does Weight Training Impact People With Osteoarthritis- a Systematic Review and Meta-Analysis

Does Weight Training Impact People With Osteoarthritis- a Systematic Review and Meta-Analysis

The effect of plyometric training (hurddle jumps), body weight training (lunges) and speed on increasing leg muscle explosive power of futsal players: a factorial experimental design

Futsal games have high intensity and dynamics that require good skills and physical conditions, one of which is leg muscle explosiveness. By doing plyometric training (hurddle jump), body-weight training (lunges), and paying attention to explosive power factors including speed as a group determinant is believed to affect the explosive power of the player's leg muscles. However, despite recognizing the importance of both training methods in improving leg muscle explosive power, there is still a lack of a thorough understanding of their combined effect on players' leg muscle explosive power during futsal play. This study aims to analyze the differences in the effect of the intervention groups of plyometric training methods and body weight training by considering the level of running speed on explosive power results. Training groups include plyometric training groups and body weight training groups, while speed is categorized as high or low. Using an experimental approach with a 2 x 2 factorial design, this study randomly selected 20 players aged 17.1 ± 0.768 years. Training was conducted in three sessions per week for approximately six weeks. Training focused on fast/explosive movements. Speed data was collected using the 30m acceleration test and the leg muscle explosiveness standing broad jump test. The data were then statistically analyzed using a two-way ANOVA at the 0.05 level of significance. The results showed that both training methods can benefit individuals with high speed (P&lt;0.05). However, leg muscle explosive power training with plyometric exercise was more effective on individuals with high speed (P&lt;0.05). As for those with low speed, plyometric exercise can provide better results (P&lt;0.05). These findings provide valuable insights for futsal coaches and instructors in designing customized training programs to improve leg muscle explosiveness. Keywords: Plyometric, Body Weight, Speed, Power

An interpretable TFAFI-1DCNN-LSTM framework for UGW-based pre-stress identification of steel strands

Steel strands serve as the key load-bearing components of pre-stressed bridges, yet the identification of effective pre-stress for steel strands is a challenging task. In this study, a time and frequency adaptive fusion input-one dimensional convolutional neural network-long short-term memory (TFAFI-1DCNN-LSTM) framework was proposed for ultrasonic guided wave (UGW)-based effective pre-stress identification of steel strands. In this framework, the time and frequency domain signals of UGW were input into the network as two parallel branches, CNN and LSTM were utilized to extract spatial and serial-related features, and a trainable weight coefficient was introduced for adaptive fusion of time and frequency domain features. Firstly, ablation studies were conducted to investigate the influence of each key component in the proposed framework on the prediction results. Secondly, deep learning (DL) models of Res Net, Dense Net and Inception Net were introduced as comparisons, and the prediction results based on TFAFI-1DCNN-LSTM were compared with those based on the above DL models. Thirdly, the noise-robustness and performance under a few trainable samples of TFAFI-1DCNN-LSTM were also investigated. Finally, the outputs of various key layers of the proposed framework were subjected to dimensionality reduction and visualization to provide an intuitive demonstration of the feature extraction process, and the inherent mechanisms of the proposed framework were interpreted using local interpretable model-agnostic explanations (LIME). Results show that the architecture of TFAFI-1DCNN-LSTM is reasonably designed and all key components are necessary. The weights of features in time and frequency domain branches are rationally assigned due to the addition of an adaptive weight coefficient. Compared with other DL models, the proposed TFAFI-1DCNN-LSTM exhibits higher pre-stress identification accuracy, excellent noise-robustness, and superior performance under only a few trainable samples. The correlation between features extracted by the network and the pre-stress labels significantly increases with the deepening of the network, and the correlation between input UGW signals and predicted pre-stress values is effectively interpreted utilizing LIME, proving that the architecture of the proposed framework is reasonable and effective, the predicted results are reliable and credible.

Sign language video to text conversion via optimised LSTM with improved motion estimation

ABSTRACT A method of communication for the deaf and the dumb is sign language (SL). Knowing SL allows speakers and listeners to converse effectively with deaf and dumb people. Yet, while they can acquire sign language (SL) to communicate with the dumb and the deaf, untrained persons are unable to speak with them. For such individuals, an SL to text system is more beneficial in enabling them to communicate more effectively with everyday people. To interact with the deaf and dumb, SL is a tactile gesture that employs the hands and eyes. This proposes a new model for translating SL video to text conversion or generation. Frame Conversion is the initial step, where the given input video is converted into frames. Subsequently, features considered are hierarchy of skeleton and Improved Motion estimation (ME). For generating the text, this work uses an optimised LSTM model, where training of weights is done by hybrid Combined Pelican and BES algorithm (CP-BES). Moreover, the mean value for dataset ISL-CSLTR has achieved the proposed method is 27.3%, 31.6%, 28.7%, 33.4%, 29.8%, 24.5%, 36.2%, and 34.8% greater than the conventional schemes like CNN, FSU-CNN, ASL – CNN, RNN, LSTM +POA, LSTM +ARCHOA, LSTM +HGS, LSTM +PRO and LSTM +BES.

WI-TMLEGA: Weight Initialization and Training Method Based on Entropy Gain and Learning Rate Adjustment.

Addressing the issues of prolonged training times and low recognition rates in large model applications, this paper proposes a weight training method based on entropy gain for weight initialization and dynamic adjustment of the learning rate using the multilayer perceptron (MLP) model as an example. Initially, entropy gain was used to replace random initial values for weight initialization. Subsequently, an incremental learning rate strategy was employed for weight updates. The model was trained and validated using the MNIST handwritten digit dataset. The experimental results showed that, compared to random initialization, the proposed initialization method improves training effectiveness by 39.8% and increases the maximum recognition accuracy by 8.9%, demonstrating the feasibility of this method in large model applications.

Comparing the Effect of Isoinertial Flywheel Training and Traditional Resistance Training on Maximal Strength and Muscle Power in Healthy People: A Systematic Review and Meta-Analysis.

This systematic review and meta-analysis aimed to analyze whether isoinertial flywheel training (FWT) is superior to traditional resistance training (TRT) in enhancing maximal strength and muscle power in healthy individuals. Electronic searches were conducted in the Web of Science, PubMed, Cochrane Library, SPORTDiscus, and Scopus databases up to 21 April 2024. Outcomes were analyzed as continuous variables using either a random or fixed effects model to calculate the standardized mean difference (SMD) and 95% confidence intervals (CI). A total of sixteen articles, involving 341 subjects, met the inclusion criteria and were included in the statistical analyses. The pooled results indicate no statistically significant differences between FWT and TRT in developing maximal strength in healthy individuals (SMD = 0.24, 95% CI [-0.26, 0.74], p = 0.35). Additionally, the pooled outcomes showed a small-sized effect in muscle power with FWT (SMD = 0.47, 95% CI [0.10, 0.84]), which was significantly higher than that with TRT (p = 0.01) in healthy individuals. Subgroup analysis revealed that when the total number of FWT sessions is between 12 and 18 (1-3 times per week), it significantly improves muscle power (SMD = 0.61, 95% CI [0.12, 1.09]). Significant effects favoring FWT for muscle power were observed in both well-trained (SMD = 0.58, 95% CI [0.04, 1.13]) and untrained individuals (SMD = 1.40, 95% CI [0.23, 2.57]). In terms of exercise, performing flywheel training with squat and lunge exercises significantly enhances muscle power (SMD = 0.43; 95% CI: 0.02-0.84, and p = 0.04). Interestingly, FWT was superior to weight stack resistance training (SMD = 0.61, 95% CI [0.21, 1.00]) in enhancing muscle power, while no significant differences were found compared to barbell free weights training (SMD = 0.36, 95% CI [-0.22, 0.94]). This meta-analysis confirms the superiority of FWT compared to TRT in promoting muscle power in both healthy untrained and well-trained individuals. Squats and lunges for FWT are more suitable for improving lower limb explosive power. It is recommended that coaches and trainers implement FWT for six weeks, 2-3 times per week, with at least a 48 h interval between each session. Although FWT is not superior to free weights training, it is advisable to include FWT in sport periodization to diversify the training stimuli for healthy individuals.

A study of the effect of weight training on athletes' agility

The purpose of this research study was to study the effect of weight training on athletes' agility. This research study was limited to athletes from physical education and sports science disciplines. This research study was conducted for the age group of 18 to 22 years. Only brothers were selected as subjects in this research study. 60 players were selected in this research study. In this research study, 20 athletes were divided into three groups namely weight load, 20 athletes’ frequency and 20 athletes a control group. Standard of measurement Agility was measured by shuttle run test. Analysis of variance, covariance (ANCOVA) was applied to the data obtained from two experimental groups and one control group and differences between means were tested with LSD post hoc test at 0.05 level of significance. The conclusion of which was seen as follows. A significant improvement was observed in the agility test of subjects selected from the 08-week weight training and weight frequency training program of the methodology. Abstract in Gujarati Language: આ સંશોધન અભ્યાસનો હેતુ વજન તાલીમ દ્વારા ખેલાડીઓની ચપળતા પર થતી અસરનો અભ્યાસ કરવાનો હતો. આ સંશોધન અભ્યાસ શારીરિક શિક્ષણ અને રમત વિજ્ઞાન વિદ્યાશાખાના ખેલાડીઓ પુરતો હતો. આ સંશોધન અભ્યાસ 18 થી 22 વર્ષની વય જુથ પુરતો રાખવામાં આવ્યો હતો. આ સંશોધન અભ્યાસમાં વિષયપાત્રો તરીકે માત્ર ભાઈઓને જ પસંદ કરવામાં આવ્યા હતા. આ સંશોધન અભ્યાસમાં 60 ખેલાડીઓને પસંદ કરવામાં આવ્યા હતા. આ સંશોધન અભ્યાસમાં 20 ખેલાડીઓને વજન ભારણ, 20 ખેલાડીઓને આવર્તન અને 20 ખેલાડીઓને નિયંત્રિત જૂથમાં એમ ત્રણ જૂથમાં વિભાજીત કરવામાં આવ્યા હતા. માપનના ધોરણમાં ચપળતાનું માપન શટલ રન કસોટી દ્વારા કરવામાં આવ્યું હતું. બે પ્રાયોગિક જૂથો અને એક નિયંત્રિત જૂથની પ્રાપ્ત કરેલ માહિતી પર વિચરણ, સહવિચરણ પૃથક્કરણ (ANCOVA) લાગુ પાડી મધ્યકો વચ્ચેના તફાવતોને LSD પોસ્ટ હોક કસોટી લાગુ પાડી 0.05 કક્ષાએ સાર્થકતા ચકાસવામાં આવી હતી. જેનું તારણ આ પ્રમાણે જોવા મળ્યું હતું. પદ્ધત્તિસરના 08 અઠવાડિયાના વજન ભારણ તાલીમ અને વજન આવર્તન તાલીમ કાર્યક્રમથી પસંદ થતા વિષયપાત્રોના ચપળતા કસોટીમાં નોંધપાત્ર સુધારો જોવા મળ્યો હતો. Keywords: રમતવીરો, શારીરિક શિક્ષણ, રમત વિજ્ઞાન

Airborne acoustic assessment of impact-resistant fitness flooring systems

Fitness facilities in residential and mixed-used commercial buildings introduce important acoustic design challenges that must be considered in a building. Cardio activities such as running on treadmills, group classes for high intensity training, and weight training areas introduce high levels of unwanted noise and vibration into a building structure. Isolated floor constructions are generally coordinated and implemented during design but are not practical when buildings are completed and occupied. Impact-resistant fitness flooring systems are typically explored and installed as an alternate approach to reduce the transmission of impact noise and vibration. Non-standardized field airborne noise measurements of weight drops were conducted on an existing gym and on four possible impact-resistant fitness flooring upgrades to assess the reduction of impact noise levels in the offices located below the gym. The measurements were also compared to the HVAC background noise levels to observe the increase above background conditions and provide a subjective evaluation. The results of the measurements show that impact-resistant fitness flooring systems provide a noticeable reduction of impact noise, compared to standard fitness flooring systems. The results also show that impact-resistant fitness flooring systems that include specialty engineered shock pads as a base layer provide a significant reduction of impact noise levels.

A novel maternal thyroid disease prediction using multi-scale vision transformer architecture with improved linguistic hedges neural-fuzzy classifier.

Early pregnancy thyroid function assessment in mothers is covered. The benefits of using load-specific reference ranges are well-established. We pondered whether the categorization of maternal thyroid function would change if multiple blood samples obtained early in pregnancy were used. Even though binary classification is a common goal of current disease diagnosis techniques, the data sets are small, and the outcomes are not validated. Most current approaches concentrate on model optimization, focusing less on feature engineering. The suggested method can predict increased protein binding, non-thyroid syndrome (NTIS) (simultaneous non-thyroid disease), autoimmune thyroiditis (compensated hypothyroidism), and Hashimoto's thyroiditis (primary hypothyroidism). In this paper, we develop an automatic thyroid nodule classification system using a multi-scale vision transformer and image enhancement. Graph equalization is the chosen technique for image enhancement, and in our experiments, we used neural networks with four-layer network nodes. This work presents an enhanced linguistic coverage neuro-fuzzy classifier with chosen features for thyroid disease feature selection diagnosis. The training procedure is optimized, and a multi-scale vision transformer network is employed. Each hop connection in Dense Net now has trainable weight parameters, altering the architecture. Images of thyroid nodules from 508 patients make up the data set for this article. Sets of 80% training and 20% validation and 70% training and 30% validation are created from the data. Simultaneously, we take into account how the number of training iterations, network structure, activation function of network nodes, and other factors affect the classification outcomes. According to the experimental results, the best number of training iterations is 500, the logistic function is the best activation function, and the ideal network structure is 2500-40-2-1. K-fold validation and performance comparison with previous research validate the suggested methodology's enhanced effectiveness.

USVs Path Planning for Maritime Search and Rescue Based on POS-DQN: Probability of Success-Deep Q-Network

Efficient maritime search and rescue (SAR) is crucial for responding to maritime emergencies. In traditional SAR, fixed search path planning is inefficient and cannot prioritize high-probability regions, which has significant limitations. To solve the above problems, this paper proposes unmanned surface vehicles (USVs) path planning for maritime SAR based on POS-DQN so that USVs can perform SAR tasks reasonably and efficiently. Firstly, the search region is allocated as a whole using an improved task allocation algorithm so that the task region of each USV has priority and no duplication. Secondly, this paper considers the probability of success (POS) of the search environment and proposes a POS-DQN algorithm based on deep reinforcement learning. This algorithm can adapt to the complex and changing environment of SAR. It designs a probability weight reward function and trains USV agents to obtain the optimal search path. Finally, based on the simulation results, by considering the complete coverage of obstacle avoidance and collision avoidance, the search path using this algorithm can prioritize high-probability regions and improve the efficiency of SAR.