System Response Time Research Articles

Deep Reinforcement Learning-based scheduling for optimizing system load and response time in edge and fog computing environments

Edge/fog computing, as a distributed computing paradigm, satisfies the low-latency requirements of ever-increasing number of IoT applications and has become the mainstream computing paradigm behind IoT applications. However, because large number of IoT applications require execution on the edge/fog resources, the servers may be overloaded. Hence, it may disrupt the edge/fog servers and also negatively affect IoT applications’ response time. Moreover, many IoT applications are composed of dependent components incurring extra constraints for their execution. Besides, edge/fog computing environments and IoT applications are inherently dynamic and stochastic. Thus, efficient and adaptive scheduling of IoT applications in heterogeneous edge/fog computing environments is of paramount importance. However, limited computational resources on edge/fog servers imposes an extra burden for applying optimal but computationally demanding techniques. To overcome these challenges, we propose a Deep Reinforcement Learning-based IoT application Scheduling algorithm, called DRLIS to adaptively and efficiently optimize the response time of heterogeneous IoT applications and balance the load of the edge/fog servers. We implemented DRLIS as a practical scheduler in the FogBus2 function-as-a-service framework for creating an edge–fog–cloud integrated serverless computing environment. Results obtained from extensive experiments show that DRLIS significantly reduces the execution cost of IoT applications by up to 55%, 37%, and 50% in terms of load balancing, response time, and weighted cost, respectively, compared with metaheuristic algorithms and other reinforcement learning techniques.

Route planning model based on multidimensional eigenvector processing in vehicular fog computing

With the rapid development of information technology, the informationization level of sport tourism has been improved in an all-around way, which makes a large number of data accumulated in the management system of road traffic. However, the traditional association rule algorithm cannot deal with huge data. To make up for the deficiency of predicting suitability from a single perspective, this paper, from the perspective of road daily travel planning, constructs a multi-dimensional characteristic model. Based on eigenvector processing as a research content, by carrying out a multi-dimensional prediction on the whole data set and considering the limitation problem of the influence of time, space, and items on daily travel routes, the invention provides a daily travel suitability road daily travel planning route prediction research method based on multiple dimensions. The invention also extracts the outstanding performance of a network model in a single variable problem based on deep interest and double characteristics. The combination of SVR and GBRT algorithm makes up for the one-sidedness of single perspective prediction. It uses the weighted fusion principle to fuse the results and establishes a multi-dimensional route suitability prediction model under this mode. Experiments verify that the prediction of multivariate dimensional data achieves the desired results. With the help of the dependence between the level and element dimension data, the future route planning trend can be judged. This algorithm compared to the ant colony algorithm and the traditional genetic algorithm increased by 15.6% and 15.1%. The system response time has been increased by more than 60%, which can effectively improve the accuracy of prediction. Therefore, in the VFC environment, the actual user needs can be improved, the planning and management of traffic routes can be guided, and the development of sport tourism systems of Taihang Mountain can be further promoted.

Development of Web-Based Teleoperation VOCAFE Service Robot

The design and implementation of a service robot that communicates effectively via the MQTT Protocol is presented in this research. This study focuses on creating a web-based application to control and monitor the movement of restaurant service robots in one of the university's cafes called VOCAFE. This research uses the MQTT communication protocol which allows smooth interaction between the robot and the operator. The design and construction of service robots, including their mechanical parts and communication systems, is described in the engineering section. The test results show the response time of the robot's navigation system, showing performance within a reasonable range. The conclusion highlights the importance of additional testing and research to improve the system. Overall, this research advances the creation of teleoperated restaurant service robots with reliable and effective communication using MQTT.

Efficiency and Accuracy of Scheduling Algorithms for Final Year Project Evaluation Management System

Scheduling algorithms play a crucial role in optimizing the efficiency and precision of scheduling tasks, finding applications across various domains to enhance work productivity, reduce costs, and save time. This research paper conducts a comparative analysis of three algorithms: genetic algorithm, hill climbing algorithm, and particle swarm optimization algorithm, with a focus on evaluating their performance in scheduling presentations. The primary goal of this study is to assess the effectiveness of these algorithms and identify the most efficient one for handling presentation scheduling tasks, thereby minimizing the system's response time for generating schedules. The research takes into account various constraints, including evaluator availability, student and evaluator affiliations within research groups, and student-evaluator relationships where a student cannot be supervised by one of the evaluators. Considering these critical parameters and constraints, the algorithm assigns presentation slots, venues, and two evaluators to each student without encountering scheduling conflicts, ultimately producing a schedule based on the allocated slots for both students and evaluators.

Design and research of MOOC teaching system based on TG-C4.5 algorithm

The emergence of Internet information technology has led to the development of MOOC-based online teaching methods. The study uses the traditional C4.5 algorithm for data mining to improve teaching quality and simplifies and quantifies it with the Taylor series and GINI index. The study also considers the uncertainty of data changes and the characteristics of MOOC teaching to design a parallel processing system of the HD-TG-C4.5 algorithm under the framework of the Hadoop platform. The experimental results show that the minimum data classification error of the algorithm is 2%, and the maximum recommendation accuracy of teaching resources is 92.6%. Moreover, the response time and resource search time of this algorithm system are significantly better than traditional algorithms in terms of system debugging. The average login response time is less than 0.87 s, and the success rate of system debugging reaches 90%. The probability value of students mastering teaching resource knowledge points is also above 0.7. The MOOC teaching system based on TG-C4.5 algorithm can effectively mine learner behavior data and reduce the complexity and consumption of C4.5 algorithm. The MOOC teaching system based on TG algorithm can provide technical support for the decision-making information of teaching participants and provide early warning information for predicting learning behavior.

Construction and application of a knowledge graph-based question answering system for Nanjing Yunjin digital resources

Nanjing Yunjin, one of China's traditional silk weaving techniques, is renowned for its unique local characteristics and exquisite craftsmanship, and was included in the Representative List of the Intangible Cultural Heritage of Humanity by UNESCO in 2009. However, with rapid development in weaving technology, ever-changing market demands, and shifting public aesthetics, Nanjing Yunjin, as an intangible cultural heritage, faces the challenge of survival and inheritance. Addressing this issue requires efficient storage, management, and utilization of Yunjin knowledge to enhance public understanding and recognition of Yunjin culture. In this study, we have constructed an intelligent question-answering system for Nanjing Yunjin digital resources based on knowledge graph, utilizing the Neo4j graph database for efficient organization, storage, and protection of Nanjing Yunjin knowledge, thereby revealing its profound cultural connotations. Furthermore, we adopted deep learning algorithms for natural language parsing. Specifically, we adopted BERT-based intent recognition technology to categorize user queries by intent, and we employed the BERT + BiGRU + CRF model for entity recognition. By comparing with BERT + BILSTM + CRF, BERT + CRF and BILSTM + CRF models, our model demonstrated superior performance in terms of precision, recall, and F1 score, substantiating the superiority and effectiveness of this model. Finally, based on the parsed results of the question, we constructed knowledge graph query statements, executed by the Cypher language, and the processed query results were fed back to the users in natural language. Through system implementation and testing, multiple indices including system response time, stability, load condition, accuracy, and scalability were evaluated. The experimental results indicated that the Nanjing Yunjin intelligent question-answering system, built on the knowledge graph, is able to efficiently and accurately generate answers to user’s natural language queries, greatly facilitating the retrieval and utilization of Yunjin knowledge. This not only reinforces the transmission, promotion, and application of Yunjin culture but also provides a paradigm for constructing other intangible cultural heritage question-answering systems based on knowledge graphs. This has substantial theoretical and practical significance for deeply exploring and uncovering the knowledge structure of human intangible heritage, promoting cultural inheritance and protection.

Design and experimentation of soil organic matter content detection system based on high-temperature excitation principle

With the continuous development of precision agriculture, the integration of sensor technology, control technology, and agricultural production activities has become increasingly tight. Soil organic matter (SOM) content is an important parameter in precision agriculture, closely related to the growth status of crops. Therefore, in-situ detection of SOM is an important part of variable seeding. Currently, most researchers use spectroscopy to detect SOM. However, the accuracy of spectroscopy is affected by factors such as soil texture, soil moisture content, soil iron oxide content, and soil particle size. Additionally, spectroscopic instruments are expensive and complex. To address these issues, this study designed and developed a real-time detection system for soil organic matter content based on the high-temperature excitation principle. The SOM detection system includes the selection and application of carbon dioxide sensor, the design of detection devices, the design of control systems, and the design of human–machine interface. Benchtop tests showed that the system's response time standard deviation was 0.252 s, indicating good stability. The filtering and cooling effects of the system met the requirements of the detection system. Five different natural soils were collected, and two of them, along with organic soil, were used to create artificially graded soil samples. Multiple linear regression was used for modeling, selecting six models with an R2 greater than 0.8 for accurate prediction of the remaining three different soil textures. The modeling results showed that a heating depth of 10 mm was susceptible to external interference, and the accuracy of the model with a heating depth of 15 mm was similar to that of the model with a heating depth of 20 mm. When the heating time exceeded 10 s, both models with different heating depths had an R2 greater than 0.8. The accuracy of the models increased with increasing heating time. Among them, the 15 mm-20 s model had the highest accuracy, with an average prediction accuracy of 91.4 %, a maximum accuracy of 94.1 %, and a minimum accuracy of 86.7 %. The experimental results showed that the SOM detection system designed in this study had good predictive capabilities for SOM in different soil textures and could achieve in-situ detection of SOM.

The Effect of Smartphone and Vehicle Distance on Vehicle Safety System Time Response Based on the Internet of Things

<p class="IndexTerms">This paper addresses the prevalent issue of increasing crimes in Indonesia, particularly vehicle thefts. To combat this challenge, we propose the development of an Internet of Things (IoT)-based vehicle security device capable of detecting intruders within the car and subsequently notifying the car owner through smartphone alerts. The implementation of this innovative technology holds the potential to enhance vehicle security and contribute to a safer environment for vehicle owners in the country. In this study, we conducted a series of tests in a rural mountain area to examine the impact of vehicle and smartphone distance variation, as well as internet provider variation, on the response time of a vehicle safety device under limited internet signal conditions. The experiment involved distance variations of 100m, 200m, 300m, 400m, 500m, and 600m, with the internet providers being the most expensive and the cheapest provider in Indonesia. By investigating these factors, we aimed to gain insights into optimizing the response time of the safety device, especially in areas with poor internet connectivity<span lang="IN">. </span>Utilizing the two-way ANOVA method, this experiment successfully demonstrates that variations in distances and internet providers significantly influence the notification response. The effective combination of the HC-SR501 passive infrared sensor and Nodemcu microcontroller is shown to detect movements inside the vehicle cabin and reliably notify the vehicle owner through their smartphone. These findings underscore the viability and efficiency of the proposed system in enhancing vehicle security and owner awareness.</p>

Design and Test of a Tractor Electro-Hydraulic-Suspension Tillage-Depth and Loading-Control System Test Bench

Electro-hydraulic suspension systems are one of the key working systems of tractors. Due to the complex and changeable working conditions in the field, it is of great significance to shorten the development cycle of the control strategy and reduce the development cost by using the indoor bench for test verification at the beginning of the study. Based on this, this paper has proposed a complete set of tractor hydraulic-suspension tillage-depth and loading-control test-bench designs. The system was mainly composed of three parts: an industrial computer, a suspension electro-hydraulic control system, and a loading electro-hydraulic control and data-acquisition system. The human–computer interaction interface of the test-bench measurement and control system was built, and the loading-force control system and suspension tillage-depth and loading integrated-control system were built based on PID and fuzzy PID control algorithms, respectively. The system can realize the control of suspension tillage depth and loading during the operation process and has the functions of the real-time acquisition, display, and data storage of related sensor signals during the working process. The test results showed that the response time of the loading-control system was less than 1.2 s, and the maximum steady-state error was less than 0.8%. The response time of the suspension control system was less than 2.3 s, and the maximum steady-state error was less than 1%. The system has good responsiveness and stability. These research results can provide platform and method of support for the development and test of tractor electro-hydraulic suspension systems.

Evaluation on big data sharing model and key mechanism based on blockchain technology

AbstractDue to the reliability and wide application of blockchain technology, it has attracted wide attention worldwide. Blockchain technology is widely used in finance, logistics, medicine, system management, and Bitcoin. This paper aimed to study how to analyze and study the sharing model and key mechanism of Big Data (BD) based on blockchain technology. This paper analyzed the impact of BD information resource sharing, then built an Ethernet‐based BD sharing system, and tested the performance of the system. This paper also analyzed the system response time, node mining speed test, transmission speed, security and stability of Inter Planetary File System (IPFS). IPFS and blockchain Ethernet are installed on 20 hosts in Ali Cloud and Tencent Cloud servers and laboratories, respectively. The consensus mining main grid consists of 4 Windows 7 systems. In the stability test data of relevant systems, when the number of users was 20 and 100, the system stability was 99.77% and 96.93% respectively. To sum up, the system designed in this paper has certain stability and security, and is worthy of further promotion and application.

Proton exchange membrane water electrolysis at high current densities: Response time and gas‐water distribution

AbstractUnderstanding the distribution of oxygen in proton exchange membrane water electrolysis (PEMWE) is crucial for improving electrolysis efficiency and gas removal. In this study, we developed a two‐dimensional (2D) transient model that couples the Euler–Euler multiphase model with electric potential equations to investigate two‐phase flow in PEMWE. Our simulation reveals that the system's response time initially decreases and then increases with current density, indicating longer response times at high current densities. Modifying the wetting properties of the porous transport layer (PTL) affects gas removal at low gas holdup, resulting in a maximum 15% decrease in gas holdup. However, at high gas holdup, the flow field in the channel predominantly governs bubble removal, making changes in PTL wetting properties less influential. With increasing gas production rate, an inverse gradient distribution of gas saturation appears, leading to uneven gas saturation and hindering efficient oxygen removal. This non‐uniform gas saturation adversely affects electrolysis performance.

Development and Performance Evaluation of a Pressure-Adjustable Waterjet Stubble-Cutting Device with Thickness Detection for No-Till Sowing

No-till maize (Zea mays L.) sowing is often affected by stubble. The high-pressure waterjet at a constant rate is powerless to precision applications of stubble cutting and causes water waste. In this study, a pressure-adjustable stubble-cutting device with a stubble-thickness detection device was designed. Through experiments, the quantitative analysis of the moisture content and electrical conductivity (EC) of the field soil and stubble during the spring sowing period was conducted, and the effect of soil moisture content (SMC), soil compaction (SC) and machine forward speed (V) on the stubble-thickness detection error (STDE) was explored. On this basis, the optimal parameters of the device were analyzed and evaluated, and a verification experiment was applied. The results showed that STDE decreased with the increase of SMC and SC and increased with the increase of V. The response time of the pressure adjustment system is 0.12 s. The stubble-cutting device with thickness detection for two-level pressure regulation reduced the water consumption (WC) by 13.22% under the condition that the stubble-cutting rate (SCR) remained unchanged. The WC increased with the increase of waterjet pressure (P) and decreased with the increase of V. The SCR increased first and then decreased with the increase of cutting angle (α). The response surface optimization analysis showed that when P was 26 MPa, α 90.45° and V was 3.36 km/h, the performance was optimal with a 3.03% STDE, a 95.49% stubble SCR and a 49.98 L/ha WC. The measured value of the field verification experiment had a 4.11% relative error existing in STDE, a 4.06% relative error existing in the SCR and a 1.81% relative error existing in WC compared with the predicted value of the regression model. In contrast to the constant rate waterjet cutting device, the application of this device can save WC by 13.22%. This study can provide a reference for the application of waterjet technology and conductivity detection technology in the agricultural field.

Mean-field fluctuations at diffusion scale in threshold-based randomized routing for processor sharing systems and applications

In this article, we study the fluctuations of the empirical occupation measures of servers around their mean-field limit in a large system of heterogeneous processor sharing servers. It is assumed that there are M different servers grouped by their speeds and that the total number of servers is N. In particular, we study the sensitivity of the fluctuations to arrival rate parameters at the diffusion scale. The job arrival process is assumed to be Poisson with rate N ( λ − β N ) and the job lengths are assumed to be exponentially distributed with unit mean. On arrival, a finite number of servers from each group are selected and the destination server depends on the server occupancy normalized to their speeds and pre-defined thresholds, referred to as the Join-Below-Threshold scheme. We derive Functional Central Limit Theorems (FCLTs) for the fluctuations that enable us to estimate the error of the mean-field approximations to the empirical measures associated with a system with N servers. We then use these results to show mean response time for finite systems can be approximated by the response time given by the mean-field limit and the error is O ( 1 N ) for which the constants can be precisely calculated.

Flux-Type versus Concentration-Type Sensors in Transdermal Measurements.

New transdermal biosensors measure analytes that diffuse from the bloodstream through the skin, making it important to reduce the system response time and understand measurement output. While highly customized models have been created for specific sensors, a generalized model for transdermal sensor systems is lacking. Here, a simple one-dimensional diffusion model was used to characterize the measurement system and classify biosensors as either flux types or concentration types. Results showed that flux-type sensors have significantly faster response times than concentration sensors. Furthermore, flux sensors do not measure concentration, but rather have an output measurement that is proportional to skin permeability. These findings should lead to an improved understanding of transdermal measurements and their relation to blood analyte concentration. In the realm of alcohol research, where the majority of commercially available sensors are flux types, our work advocates toward moving away from transdermal alcohol concentration as a metric, and instead suggests embracing transdermal alcohol flux as a more suitable alternative.

Optimization and thermo-economic performance of a solar-powered vapor absorption cooling system integrated with sensible thermal energy storage

Higher demand for refrigeration systems adversely affects power grids, causing blackouts, increased electricity expenses, and carbon emissions. However, using renewable energy thermally driven refrigeration absorption systems is a promising alternative. The higher initial cost and dependency on local weather, large space area for installation, and complex design are hurdles for the widespread of these systems compared to the conventional vapor compression refrigeration systems. This study uses response surface methodology to model a real vapor absorption machine (VAM) incorporated with the measured data. This VAM is the refrigeration machine of a solar-powered absorption cooling system (SPACS) integrated with thermal energy storage for milk chilling installed and operated in Jaipur (India). The weather data for 2022 is used in performance and productivity analysis in this study. The results show that most of the summer months, the system can produce desired cooling to take down the 1000 l of milk within 3 h as per standards ISO 5708 – 2 II. Moreover, the solar loop still has sufficient driving heat to charge the 1000 l cold storage tank/another milk tank. During winter days, it takes a significant system response time (SRT) to reach the thermal energy storage (TES) up to 95 °C; after that, VAM operates significantly underperforming due to weak solar insolation; even the system cannot provide cooling to the first milking. The system produces monthly cooling energy of up to 2356 kWh in summer and is reduced to 620 kWh during monsoon and winter. The maximum value of the coefficient of performance (COPVAM) is achieved as 0.55 with an average of 0.41–0.46 during summer months whereas 0.34–0.39 during monsoon and winter days. The system's energy efficiency ratio (EER) ranges from 2.5 to 6.5, with an overall average of 4.55, which is far better than the conventional vapor compression refrigeration systems. The LCOE for the SPACS has been estimated to be 0.177 $/kWh, whereas the simple payback period is 12.4 years, and the discounted payback period is 19.7 years.

A Lorentzian Adaptive Filter-Based Mechanism for Resilience Against Impulsive Disturbances Applied to a Grid-Tied Solar PV System

This paper demonstrates a solar photovoltaic (PV) system equipped with a Lorentzian adaptive filter (LAF) based mechanism, whose prominent capability is its ability to filter impulsive disturbances in the acquired sensor output. The primary motivation of this work is to achieve resiliency of load weight estimation against the adverse effects of impulsive disturbances in noisy environments, which present a unique difficulty for most filtering mechanisms. The swift and accurate information of the load weight assists the system to achieve an accelerated response at dynamic conditions. Moreover, on careful selection of the LAF gains using the procedure presented in this work, the effective resilience against impulsive disturbances is achieved without compromising the system response time. The detailed examination of the real time intermediate signals is presented to explain the filter functioning and abilities. The LAF equipped PV system behavior is compared experimentally against multiple other filters, to examine its improved behavior. The study considers the local loads to be non-ideal. The presented system inhibits the adverse effects of such loads from affecting the grid, via its power quality improvement actions. The system control also makes it robust against the grid voltage anomalies.

A system based on machine learning for improving sleep

Closed-loop auditory stimulation is one of the well-known and emerging sensory stimulation techniques, which achieves the purpose of sleep regulation by driving the EEG slow oscillation (SO, <1 Hz) through auditory stimulation. The main challenge is to accurately identify the stimulation timing and provide feedback in real-time, which has high requirements on the response time and recognition accuracy of the closed-loop auditory stimulation system. To reduce the impact of systematic errors on the regulation results, most traditional closed-loop auditory stimulation systems try to identify a single feature to determine the timing of stimulus delivery and reduce the system feedback delay by simplifying the calculation. Unlike existing closed-loop regulation systems that identify specific brain features, this paper proposes a closed-loop auditory stimulation sleep regulation system deploying machine learning. The process is: through online sleep real-time automatic staging, tracking the sleep stage to provide feedback quickly, and continuously offering external auditory stimulation at a specific SO phase. This paper uses this system to conduct sleep auditory stimulation regulation experiments on ten subjects. The experimental results show that the sleep closed-loop regulation system proposed in this paper can achieve consistency (effective for almost all subjects in the experiment) and immediate (taking effect immediately after stimulation) modulation effects on SOs. More importantly, the proposed method is superior to existing advanced methods. Therefore, the system designed in this paper has great potential to be more reliable and flexible in sleep regulation.

Small-Signal Stability Modeling, Sensitivity Analysis, and Parameter Optimization of Improved Virtual Synchronous Machine Based Standalone Inverter

The virtual synchronous machine (VSM) concept is emerging as a flexible approach for controlling power electronic converters in grid-connected and standalone applications. In this study, we have used the mathematical model of a Virtual machine with a virtual exciter and governor for the standalone inverter to optimize the parameter for small-signal stability. Firstly, the small-signal models of virtual synchronous generator with load have developed, and subsequently, the system eigenvalues were obtained by solving the state Jacobian matrix. Next, the sensitivity of the eigenvalue location on controller parameters has been studied. The parameters are optimized on the basis of the location of dominant eigenvalues using a genetic algorithm. Finally, the optimal controller parameters are used to test the system’s dynamics by solving the model equations with Ordinary Differential Equation (ODE) solver. Moreover, our conclusions were also tested using the actual switching devices on Matlab/Simulink. The results indicate that the frequency stability can be enhanced drastically by optimizing a wide range of VSM parameters. The frequency stability sensitivity with respect to load variation has been improved. The transient settling time of system response for optimized values is 0.25 sec which is only 5% of that for general values. The results of this work are relevant for the VSM-based microgrid small-signal stability analysis.

Delayed sedimentary response of the Huanghe alluvial plain to climate change inferred from source variations of the Xiashu loess since ∼1 Ma

Large river systems are reactive or buffered to large climate oscillations on orbital timescales, depending on whether their sedimentary response time is shorter or longer than the period of these climate oscillations. Estimating the sedimentary response time of large river systems is essential for understanding their sensitivity to climate change and their corresponding ability to reshape themselves, but few studies have estimated the sedimentary response time of real large river systems by geologic records. Provenance analysis of the Xiashu loess in China since ∼1 Ma provides the opportunity to estimate the sedimentary response time of the adjacent Huanghe (Yellow River). Here, we conducted the first provenance analysis of such a Xiashu loess section, using measured data of element contents, Nd isotopes, and grain-size compositions. The results reveal changes in loess provenance at ∼0.3 Ma and ∼0.07 Ma. The provenance changes were caused by the expansion of the Huanghe alluvial plain at ∼0.3 Ma and its contraction at ∼0.07 Ma. The expansion and contraction can be attributed to the delayed sedimentary response of the Huanghe alluvial plain to the Mid-Pleistocene Transition and the Mid-Brunhes Transition, respectively. Therefore, the sedimentary response time of the Huanghe alluvial plain is estimated to be ∼0.4 Ma, which is much longer than the duration of the high-amplitude Quaternary climate oscillations on orbital timescales. Our findings support that the Huanghe and similar large rivers are buffered to these climate oscillations. The alluvial plains of the Huanghe and similar rivers may play a key role in delaying and reducing the impacts of future climate change on the land surface.

Adaptive Sliding Mode Feedback Control Algorithm for a Nonlinear Knee Extension Model

Functional electrical stimulation (FES) has been widely used to treat spinal cord injury (SCI) patients. Many research studies employ a closed-loop FES system to monitor the stimulated muscle response and provide a precise amount of charge to the muscle. However, most closed-loop FES devices perform poorly and sometimes fail when muscle nonlinearity effects such as fatigue, time delay response, stiffness, spasticity, and subject change happen. The poor performance of the closed-loop FES device is mainly due to discrepancies in the feedback control algorithms. Most of the existing feedback control algorithms were not designed to adapt to new changes in patients with different nonlinearity effects, resulting in early muscle fatigue. Therefore, this research proposes an adaptive sliding mode (SM) feedback control algorithm that could adapt and fine-tune internal control settings in real-time according to the current subject’s nonlinear and time-varying muscle response during the rehabilitation (knee extension) exercise. The adaptive SM feedback controller consists mainly of system identification, direct torque control, and tunable feedback control settings. Employing the system identification unit in the feedback control algorithm enables real-time self-tuning and adjusting of the SM internal control settings according to the current patient’s condition. Initially, the patient’s knee trajectory response was identified by extracting meaningful information, which included time delay, rise time, overshoot, and steady-state error. The extracted information was used to fine-tune and update the internal SM control settings. Finally, the performance of the proposed adaptive SM feedback control algorithm in terms of system response time, stability, and rehabilitation time was analysed using a nonlinear knee model. The findings from the simulation results indicate that the adaptive SM feedback controller demonstrated the best control performance in accurately tracking the desired knee angle movement by having faster response times, smaller overshoots, and lower steady-state errors when compared with the conventional SM across four reference angle settings (20°, 30°, 40°, and 76°). The adaptive feedback SM controller was also observed to compensate for muscle nonlinearities, including fatigue, stiffness, spasticity, time delay, and other disturbances.