Experimental Results Research Articles

Cleft Grafting Propagation of Pome and Stone Fruit Trees during the Dormancy Period in a Hot Water System

Pome and stone fruit trees are heterozygous and cannot be propagated by seed. Various techniques are used for their vegetative propagation worldwide. The experiment's results are noteworthy, especially in the realm of fruit tree propagation. By utilizing a heated callus with a hot water system, combined with the cleft grafting method, successful propagation of both pome and stone fruit species has been accomplished. The experiment's results were intriguing, revealing varying success rates among different fruit species. The apple, pear, and plum fruit species achieved a higher percentage of callus-forming, adapted, and fruit-planting material compared to the sweet cherry. The highest success rate was observed in apples – 83.1%, followed by pears – 67.5% and plums 63.8%. The sweet cherry, a stone fruit species, had the lowest success rate at 20.6%. These findings open up new avenues for further research and experimentation. The use of a hot water system during the winter dormancy of apple, pear, and plum species has proven to be a successful propagation method. Therefore, we confidently recommend this method for these species, as it can greatly enhance fruit tree propagation practices. This recommendation is based on the solid results and advancements achieved in our experiment. Keywords: fruit tree, hot callus, grafting, planting material, cleft technique

Osmopriming with Polyethylene Glycol (PEG-6000) Improves the Action of Seed Germination, Growth, and Physiology in Carrot

In order to improve germination and vigour, the current study was conducted using three carrot varieties viz. Carrot Florence (G1), Deb Kuroda-1 (G2), and Deb Kuroda-3 (G3), and various concentrations and durations of PEG-6000, including 0.1 MPa for 24 hours (T2), 0.1 MPa for 48 hours (T3), 0.25 MPa for 24 hours(T4), 0.25 MPa for 48 hours (T5), 0.40 MPa for 24 hours (T6), and 0.40 MPa for 48 hours (T7), non-primed seeds (T1). A pre-sowing technique called seed priming produces a physiological environment that promotes more efficient seed germination. The experiment was carried out in the Department of Seed Science and Technology's seed testing lab at the BCKV, Mohanpur, Nadia, West Bengal, India. According to the experiment's results, seeds treated with 0.25 MPa PEG-6000 soaking for 48 hours produced the best results among treatments over genotype; these seeds showed notably greater potential than seeds treated with other priming concentrations and durations. Deb Kuroda-3 is the best from a germination perspective, and Deb Kuroda-1 is the best from a vigour perspective. The best results were clearly obtained with a 0.25 MPa PEG-6000 soaking duration of 48 hours for seed quality parameters like germination energy (47.273), seedling Vigour Index-I (639.032), and germination index (5.503). Therefore, to improve seedling establishment, PEG-6000 0.25 Mpa pre-sowing treatment for 48 hours is recommended for carrot.

A Review on High-speed Electric Spindle Dynamics Modeling and Vibration Response Research

Background: One of the main directions of modern technology in the field of precision machining is high-speed operation. The spindle system is commonly utilized in this kind of operation, and the electric spindle is the main preference among high-speed machine tool spindles. Objective: High-speed electric spindle vibration characteristics affect the machining accuracy of the machine tool and the quality of the workpiece, so the research on high-speed electric spindle vibration characteristics has important engineering practical significance. Methods: The research status of high-speed electrospindle at home and abroad has been summarized in this paper. Combined with the patents related to the dynamics modelling of electrospindle, the research on the dynamics modelling of high-speed electrospindle is analyzed. On this basis, the computational and analytical methods for the vibration modelling of the electrospindle, including the transfer matrix method and the finite element method, are investigated, the theoretical foundations of these methods are discussed in depth, and the advantages and disadvantages of the methods are evaluated. The applicability and limitations of the two methods are also compared. Results: The analysis has shown that the current research on the vibration characteristics of highspeed electrospindle is mainly based on mechanical modal analysis and electromagnetic analysis. At present, the dynamic modeling of the electrospindle mainly includes bearing modeling, shaft bearing modeling, spindle-case modeling, electrospindle electromechanical coupling modeling, electrospindle thermal coupling modeling, etc. The correctness of the modelling theory is verified through experimental and simulation results. Although these models tend to be perfected, they are still insufficient in the case of multiple influencing factors coupling and need further development. Conclusion: Finally, through the analysis of the patent and dynamic characteristics related to the high-speed electric spindle, thermal deformation, magnetic tension, material, and other factors should be considered comprehensively, and these factors should be coupled to establish an overall dynamics model for the vibration characteristics analysis. The dynamic modelling, vibration modelling method, and vibration characteristics of the high-speed electric spindle have been summarized in this study, and the outlook is presented.

Deterministic Weight Modification-based Extreme Learning Machine for Stock Price Prediction

Background: The prediction of the stock price is considered to be one of the most fascinating and important research and patent topics in the financial sector. Aims: Making more accurate predictions is a difficult and significant task because the financial industry supports investors and the national economy. Objectives: The DWM is used to adjust the connection weights and biases to enhance prediction precision and convergence rate. DWM was proposed as a method to reduce system error by changing the weights of various levels. The methods for predictable changes in weight were provided together with the computational difficulty. Methods: An extreme learning machine (ELM) is a fast-learning method for training a singlehidden layer neural network (SLFN). However, the model's learning process is ineffective or incomplete due to the randomly chosen weights and biases of the input's hidden layers. Hence, this article presents a deterministic weight modification (DWM) based ELM called DWM-ELM for predicting the stock price. Results: The calculated results showed that DWM-ELM had the best predictive performance, with RMSE (root mean square error) of 0.0096, MAE (mean absolute error) of 0.0563, 0.0428, MAPE (mean absolute percentage error) of 1.7045, and DS (Directional Symmetry) of 89.34. Conclusion: The experimental results showed that, in comparison to other well-known prediction algorithms, the suggested DWM+ELM prediction model offers better prediction performance.

A solar-powered electrocoagulation process with a novel CNT/silver nanowire coated basalt fabric cathode for effective oil/water separation: From fundamentals to application.

Electrocoagulation (EC) has proven its high efficiency and environmental sustainability for treating several types of wastewaters. However, the primary drawbacks of the conventional EC process are the suitable electrode materials and the relatively high cost due to the requirement for electric energy. To overcome these practical challenges, this study investigated effective oil/water separation by a solar-powered electrocoagulation (SPEC) process using a novel highly conductive basalt fabric (BF) cathode. The BF cathode was fabricated using a simple approach: dip-coating in carbon nanotubes (CNT) dispersion, followed by a bath exhaustion coating in a silver nanowires (AgNws) solution, and its successful preparation was confirmed through several advanced characterization techniques. The effect of the CNT-AgNws coating on the electrical conductivity of the BF-CNT/AgNws was investigated using the four-probe tester. The BF-CNT/AgNws cathode exhibited a high conductivity of 1.66×104S/m, which indicates its applicability in the SPEC system. Under the operating conditions of applied voltage (25V), SPEC time (30min), stirring rate (150rpm), and NaCl concentration (1g/L), the experiment's results showed a high COD removal of 90.2±0.03 %, a low energy consumption of 1.28±0.01 kWh/kgCOD, and electrode consumption of 0.35±0.06kg/m3. In addition, due to the use of solar-powered energy, the overall cost was reduced by eliminating the electricity fees. Moreover, the reusability test results proved that the BF cathode has potential reusability in successive SPEC experiments while maintaining its performance. In conclusion, the obtained findings are very encouraging in designing novel EC cathodes for effective oily wastewater treatment at an industrial scale.

Spatio-Temporal Joint Trajectory Planning for Autonomous Vehicles Based on Improved Constrained Iterative LQR.

With advancements in autonomous driving technology, the coupling of spatial paths and temporal speeds in complex scenarios becomes increasingly significant. Traditional sequential decoupling methods for trajectory planning are no longer sufficient, emphasizing the need for spatio-temporal joint trajectory planning. The Constrained Iterative LQR (CILQR), based on the Iterative LQR (ILQR) method, shows obvious potential but faces challenges in computational efficiency and scenario adaptability. This paper introduces three key improvements: a segmented barrier function truncation strategy with dynamic relaxation factors to enhance stability, an adaptive weight parameter adjustment method for acceleration and curvature planning, and the integration of the hybrid A* algorithm to optimize the initial reference trajectory and improve iterative efficiency. The improved CILQR method is validated through simulations and real-vehicle tests, demonstrating substantial improvements in human-like driving performance, traffic efficiency improvement, and real-time performance while maintaining comfortable driving. The experiment's results demonstrate a significant increase in human-like driving indicators by 16.35% and a 12.65% average increase in traffic efficiency, reducing computation time by 39.29%.

Exploring Asthma Mechanism of Belamcanda Chinensis by "Dose-effect Weighted Coefficient" Network Pharmacology and Experiment Validation.

Asthma is a chronic inflammatory disease of the airways that seriously endangers human health. Belamcanda chinensis (BC), a traditional Chinese medicine, has been used to counteract asthma as it has been shown to possess anti-inflammatory and regulatory immunity properties. The study aimed to investigate the mechanisms of action of BC in the treatment of asthma; a "dose-effect weighted coefficient" network pharmacology method was established to predict potential active compounds. Information on the components and content of BC was obtained by UPLC-QEOrbitrap- MS spectrometry. Based on BC content, oral bioavailability, and molecular docking binding energy, dose-effect weighting coefficients were constructed. With the degree greater than average as the index, a protein-protein interaction (PPI) database was used to obtain the core key targets for asthma under dose-effect weighting. GO function and KEGG pathway analyses of the core targets were performed using DAVID software. Finally, MTT and ELISA assays were used to assess the effects of active components on 16HBE cell proliferation. The experimental results using the 16HBE model demonstrated BC to have a potential protective effect on asthma. Network pharmacology showed SYK, AKT1, and ALOX5 to be the main key targets, and Fc epsilon RI as the promising signaling pathway. Eight components, such as tectoridin, mangiferin, luteolin, and isovitexin were the main active compounds, Finally, we analyzed the LPS-induced 16HBE proliferation of each active ingredient. Based on the activity verification study, all five predicted components promoted the proliferation of 16HBE cells. These five compounds can be used as potential quality markers for asthma. This study provides a virtual and practical method for the simple and rapid screening of active ingredients in natural products.

Developing intercultural competence and achieving B2 English proficiency level through using creative and interactive teaching methods and watching authentic TV series

Introduction. The increasing level of world’s globalization makes it necessary to be able to interact with representatives of other cultures. Since English is recognized as the language of international communication, students need to develop intercultural competence in order to interact with the international community based on mutual understanding and shared values. Incorporating creative interactive methods with the viewing of authentic TV series into education allows students to improve their skills in understanding the original language, which reflects the particularities of the culture. The purpose of the research is to develop a methodology for teaching English using video materials to enhance students' level of intercultural competence and language proficiency to independent mastery (B2). Materials and methods. To achieve the set goal, a pedagogical experiment was conducted involving 110 2nd year undergraduate students, 53 of whom were assigned to the control group and 57 to the experimental group. The experiment consisted of 3 stages: preliminary assessment of the level of intercultural competence among students in both groups; conducting classes in the experimental group with the viewing and discussion of TV series in the original language; final assessment of the level of intercultural competence and English language proficiency, followed by comparison of groups’ results. Mathematical processing of testing results was conducted using Fisher’s angular transformation, Student’s t-test for unrelated samples, and Pearson's chi-square test to determine changes between the two groups. Results. Analysis of the experiment's results revealed a statistically significant difference between the levels of intercultural competence formation among students in the experimental and control groups (χ 2 = 16.232, χ 2 = 15.425, χ 2 = 14.547 with t crit = 2.621, p < 0.01), indicating their differences. Evaluation of the abilities of students in the experimental group showed a substantial increase in the number of students at the Advanced level. Thus, the pedagogical experiment demonstrated the effectiveness of using authentic TV series as means to enhance the level of intercultural competence and English language proficiency up to the B2 level. Conclusion. The study showed that the development of students' intercultural competence requires reliance on authentic materials reflecting the cultural characteristics of the country whose language is being studied. The presented methodology can be used in combination with other interactive teaching methods for the effective education of students in various disciplines.

Fuzzy Modeling to Personalized Nutritional Menu

Background: While most healthy diets can help control the progression of disease, they can fail in the long term for many factors. Patients abandon the diet altogether after a while because it is too restrictive or the foods are unappealing; still, others engage in less physical activity because they consume fewer calories. What's more, almost all plans are based on optimization models. These models produce statistical diets offering limited choices to users, and a small substitution can call the whole diet into question. Objective: This article develops an intelligent system for generating flexible nutritional menus that each person can adopt to their environment and dietary preferences (food availability, price, patient eating habits, etc.). The system implements mathematical fuzzy optimization models and constraint satisfaction programming. Methods and Materials: First, the Moroccon foods were decomposed using fuzzy Cmeans. Next, the artificial foods, formed by the centers, were introduced into a fuzzy mathematical optimization diet model, which controlled the total glycemic load and met the World Health Organization (WHO) and Dietary Guidelines for Americans (GDA) recommendations (requirements for personalized menu). Then, we used a genetic algorithm strategy to generate optimal serving sizes and to build a nutritional menu based on the groups formed. To help patients choose customized diets, the menu was transformed into a constraint satisfaction programming model. Results: The proposed strategy was applied to Moroccan foods, experimental results show that all diets offer a wide range of choices to users and that substitutions comply with WHO and GDA recommendations. Conclusion: The suggested scheme has been applied to Moroccan foods; experimental findings demonstrate that all diets provide users with a wide variety of options that keeps consumers on their diet.

A phenological knowledge transfer-based fine grained land cover change sample collection method: a case study of coastal wetlands

ABSTRACT Methods for fine-grained sample collection are essential for detecting land cover changes at large scales. The complexity of wetland types increases the difficulty of obtaining training samples for high-precision wetland changes, while existing methods mainly focus on coarse-grained classification of urban areas, ignoring the physical growth cycle of vegetation. To solve the above problems, we propose a method for phenological knowledge transfer-based fine grained land cover change sample collection (PKT). Taking the Yellow River Delta as an example, the experimental results are shown as follows. (1) The overall accuracy of the results of the PKT method is 77.03%, and k is 0.42, which is better than the results of the other methods. (2) The PKT method is able to obtain the area of wetland change more accurately and can identify the wetland type changes in the area of change. (3) Making full use of multisource data and fine-grained category information can effectively improve the accuracy of change training samples. (4) Changes in coastal wetlands are the result of the interaction between natural factors and human activities. (5) Further restoration and management of wetlands can be carried out in terms of appropriate protective measures and restrictions on construction behavior.

ISOLATION, MOLECULAR CHARACTERIZATION AND APPLICATION OF PENICILLIUM CITRINUM AS BIOFERTILIZER POTENTIALS TO ENHANCE COWPEA GROWTH

Chemical fertilizers are linked to a persistent decline in soil fertility, posing health hazards. This study investigated P. citrinum as a biofertilizer for cowpea (Vigna unguiculata growth. The test fungus was identified using molecular techniques from alligator pepper. Using a pot experimental method, an in-situ experiment was conducted on cowpea (TVX-3236) in the greenhouse to screen for the isolate's mycofertilizer potential. For six weeks, the cowpea was planted in six replicates in loamy soil. P. citrinum treatment was applied to the cowpea leaves in the following amounts 20 ml, 35 ml, 50 ml, 65 ml and 80 ml per bucket at a concentration of 0.08 spores per milliliter (mL) with no inoculation on the control. P. citrinum was applied on the second week and data was collected for agronomic traits (plant height, leaf number, leaf area, and root length) and leaf color. The impact of P. citrinum on cowpea height, leaf number, leaf area, and root length revealed that these agronomic parameters rose with increasing P. citrinum concentration. The cowpea in the pot that received the 80 ml P. citrinum inoculation performed the best, indicating that the plant benefited from this treatment. The experiment's results suggest that the isolate can be utilized as a mycofertilizer to promote cowpea growth. For that reason, this study offers some initial data for further investigation into the application of P. citrinum as a biofertilizer in agriculture. This fungus strain's capacity to stimulate plant development may aid in the preservation and revegetation of some vegetations.

Experimental investigation of silica gel coated heat exchanger air conditioning system based on graphene nanofluid solar collector

ABSTRACT The solar driven desiccant air conditioning systems can play a vital role to decrease the dependency on conventional VCR system for air conditioning application. In present work, a solar-driven desiccant air conditioning system is developed. It consists of two silica gel coated fin tube heat exchangers (SGCHE) for continuous dehumidification and regeneration processes. A solar air heater based on parabolic trough collector integrated with heat pipe is used to regenerate the silica gel. A U-type heat exchanger is used for sensible cooling after dehumidification. The 0.1 vol. % concentration of graphene nanoparticle with ethylene glycol has been used in the heat pipe. The experimental results confirmed that use of graphene nanofluid instead of conventional fluid in heat pipe plays a vital role to supply hot air easily in short span of time and helps to reduce the cycle time. The present system performance has been analyzed in terms of moisture removal rate, regeneration rate, adsorption rate, and cooling capacity of system. The average regeneration and adsorption rate of SGCHE are 0.022 kg/hr and 0.033 kg/hr, respectively. The average cooling capacity of SGCHE and U-type heat exchanger are 117 W and 19 W, respectively.

An eco-friendly corrosion inhibitor for steel used in desalination systems during acid cleaning: Irish ivy extract.

Examining Irish ivy extract's (IIE) potential as a novel corrosion inhibitor to preserve C-steel in 2.0M H2SO4 solution under dynamic conditions is the main goal of this work. Investigations on weight loss, surface morphology, thermodynamics, electrochemistry (polarization and impedance), and adsorption isotherms all contributed to the achievement of this goal. The results demonstrated that the IIE extract's inhibitory effectiveness increases with concentration, reaching a maximum of 94.2% at 0.5g L-1. The approach that most nearly matched the experiment's results was the Langmuir adsorption isotherm. The activation energy rises to 61.4kJ mol-1 when IIE extract is added, compared to 46.9kJ mol-1 (2.0M H2SO4). The mixed type behavior of the IIE extract was confirmed by electrochemical method. The IIE extract effectively adsorbed on the C-steel, as confirmed by the FT-IR and SEM examinations. Many compounds, including α-hederin, hederacoside C, hederacoside D, and chlorogenic acid, which may operate as the main agents of corrosion control, were found by HPLC analysis of the IIE extract.

Evaluation Performance of Bloom Filter in Blockchain Network

A blockchain is a secret, scalability and decentralized p2p network in which all nodes follow similar protocols, preventing any single node from controlling the basic structure. In blockchain, Bloom filters are used to preserve the privacy of lightweight nodes. Bloom filter is a memory efficient randomized data structure to represent a set in order to support associate queries. Bloom filters offer a trade-off between (elements size in the network and bandwidth) and privacy metrics in untrusted environments. This paper proposes an analysis to evaluate the performance of Bloom filters. The evaluation results are based on the statistical distribution, standard deviation, entropy and y-deniability that are used by the attacker to analysis the leakage of the Bloom filter algorithm. Experimental results show that the degree of privacy in the network needs a large amount of elements and more bandwidth using the Bloom filter algorithm.

FACE DETECTION AND RECOGNITION USING GOOGLE-NET ARCHITECTURE

Using face detection to secure places is an important application merging with machine vision. This paper reposed a system to do face detection and recognition using existing architecture google-net and transfer learning to let the network learn images based on pre-trained architecture, The design of a network leads to an architecture that leads to maximizing the accuracy of the system and accurately detecting faces that are saved to the database and specifying the effect of weights used within the nodes of the hidden layer which consider the most time-consuming task within the architecture. The main characteristics are explained and the architecture used as well as the used data set in detail with the design of a network which provides an architecture that leads to maximizing the accuracy of the system and accurately detecting faces that are saved to the database and specifying the effect of weights used within the nodes of the hidden layer which consider the most time-consuming task within the architecture. Experimental results show using epochs 10 and 100 samples imply 98.37% training accuracy whereas other numbers of epochs either provide less accuracy or consume more time, and the number of epochs and training samples can be modified according to the system requirements. Other factors like illumination, the color of the background, and face rotation or scale were discussed as impact factors.

Public Leaderboard Feedback in Sampling Competition: An Experimental Investigation

Abstract We investigate the role of performance feedback, in the form of a public leaderboard, in a sequential-sampling contest with costly observations. We show theoretically that for contests with a fixed ending date (i.e., finite horizon), providing public performance feedback may result in fewer expected observations and a lower expected value of the winning observation. We conduct a controlled laboratory experiment to test the theoretical predictions and find that the experimental results largely support the theory. In addition, we investigate how individual characteristics affect competitive sequential-sampling activity.

Block pruning residual networks using Multi-Armed Bandits

ABSTRACT Recently, deep neural networks have been adopted in many application domains showing impressive performances that sometimes even exceed those of humans. However, the considerable size of deep learning models and their computational cost limits their use in mobile and embedded systems. Pruning is an important technique that has been used in the literature to compress a trained model by removing some of its elements (weights, neurons, filters, etc.) that do not notably contribute to its performance. In this paper, we propose a new block pruning method for residual networks that removes holes layers of the network based on the Multi-Armed Bandits (MAB) framework. The proposed method takes advantage of the existence of multiple trainable paths in residual models to identify and prune the less important residual blocks for inference. To evaluate our approach, we conducted extensive experiments using three different MAB algorithms, namely ε -greedy, Win Stay Lose Shift (WSLS), and the Upper Confidence Bound (UCB). The obtained results on different datasets show that our block pruning method can considerably reduce the model size and FLOPs with little to no impact on overall accuracy. We conducted a comparative analysis of our method with three existing techniques to demonstrate that our approach is highly competitive in terms of accuracy, while significantly reducing both model size and FLOPs. Moreover, our experimental results demonstrate that when our block pruning method is combined with a filter-level pruning technique, it leads to even greater reductions in model size and FLOPs while maintaining a relatively high accuracy.

Multiview Spectral Clustering Based on Consensus Neighbor Strategy.

Multiview spectral clustering, renowned for its spatial learning capability, has garnered significant attention in the data mining field. However, existing methods assume that the optimal consensus adjacency matrix is confined within the space spanned by each view's adjacency matrix. This constraint restricts the feasible domain of the algorithm and hinders the exploration of the optimal consensus adjacency matrix. To address this limitation, we propose a novel and convex strategy, termed the consensus neighbor strategy, for learning the optimal consensus adjacency matrix. This approach constructs the optimal consensus adjacency matrix by capturing the consensus local structure of each sample across all views, thereby expanding the search space and facilitating the discovery of the optimal consensus adjacency matrix. Furthermore, we introduce the concept of a correlation measuring matrix to prevent trivial solution. We develop an efficient iterative algorithm to solve the resulting optimization problem, benefitting from the convex nature of our model, which ensures convergence to a global optimum. Experimental results on 16 multiview datasets demonstrate that our proposed algorithm surpasses state-of-the-art methods in terms of its robust consensus representation learning capability. The code of this article is uploaded to https://github.com/PhdJiayiTang/Consensus-Neighbor-Strategy.git.

Propagation Structure Fusion for Rumor Detection Based on Node-Level Contrastive Learning.

With the rise of social media, the rapid spread of rumors online has resulted in numerous negative effects on society and the economy. The methods for rumor detection have attracted great interest from both academia and industry. Given the widespread effectiveness of contrastive learning, many graph contrastive learning models for rumor detection have been proposed by using the event propagation structure as graph data. However, the existing contrastive models usually treat the propagation structure of other events similar to the anchor events as negative samples. While this design choice allows for discriminative learning, on the other hand, it also inevitably pushes apart semantically similar samples and, thus, degrades model performance. In this article, we propose a novel propagation fusion model called propagation structure fusion model based on node-level contrastive learning (PFNC) for rumor detection based on node-level contrastive learning. PFNC first obtains three augmented propagation structures by masking the text of each node in the propagation structure randomly and perturbing some edges in the propagation structure based on the importance of edges. Then, PFNC applies the node-level contrastive learning method between every two augmented propagation structures to prevent the samples with similar propagation structure from far away. Finally, a convolutional neural network (CNN)-based model is proposed to capture the relevant information that is consistent and supplementary among three augmented propagation structures by regarding the propagation structure of the event as a color picture, three augmented propagation structures as color channels, and each node as a pixel. The experimental results on real datasets show that the PFNC significantly outperforms the state-of-the-art models for rumor detection.

Mild Policy Evaluation for Offline Actor-Critic.

In offline actor-critic (AC) algorithms, the distributional shift between the training data and target policy causes optimistic Q value estimates for out-of-distribution (OOD) actions. This leads to learned policies skewed toward OOD actions with falsely high Q values. The existing value-regularized offline AC algorithms address this issue by learning a conservative value function, leading to a performance drop. In this article, we propose a mild policy evaluation (MPE) by constraining the difference between the Q values of actions supported by the target policy and those of actions contained within the offline dataset. The convergence of the proposed MPE, the gap between the learned value function and the true one, and the suboptimality of the offline AC with MPE are analyzed, respectively. A mild offline AC (MOAC) algorithm is developed by integrating MPE into off-policy AC. Compared with existing offline AC algorithms, the value function gap of MOAC is bounded by the existence of sampling errors. Moreover, in the absence of sampling errors, the true state value function can be obtained. Experimental results on the D4RL benchmark dataset demonstrate the effectiveness of MPE and the performance superiority of MOAC compared to the state-of-the-art offline reinforcement learning (RL) algorithms.