rss_2.0Journal of Automation, Mobile Robotics and Intelligent Systems FeedSciendo RSS Feed for Journal of Automation, Mobile Robotics and Intelligent Systemshttps://sciendo.com/journal/JAMRIShttps://www.sciendo.comJournal of Automation, Mobile Robotics and Intelligent Systems Feedhttps://sciendo-parsed.s3.eu-central-1.amazonaws.com/65ba0a7db81b0e1a1e5d17f5/cover-image.jpghttps://sciendo.com/journal/JAMRIS140216Simultaneous Localization and Mapping of a Mobile Robot With Stereo Camera Using ORB Featureshttps://sciendo.com/article/10.14313/jamris/2-2024/14<abstract> <title style='display:none'>Abstract</title> <p>Simultaneous Localization and Mapping (SLAM) is applied to robots for accurate navigation. The stereo cameras are suitable for visual SLAM as they can give the depth of the visual landmarks and more precise estimations of the robot’s pose. In this paper, we present a survey of SLAM methods, either Bayesian or bioinspired. Then we present a new method of SLAM, which we call stereo Extended Kalman Filter, improving the matching by computing the innovation matrices from the left and the right images. The landmarks are computed from Oriented FAST and Rotated BRIEF (ORB) features for detecting salient points and their descriptors. The covariance matrices of the state and the robot’s map are reduced during the robot’s motion. Experiments are done on the raw images of the Kitti dataset.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/142024-06-23T00:00:00.000+00:00A Numerical Analysis Based Internet of Things (IoT) and Big Data Analytics to Minimize Energy Consumption in Smart Buildingshttps://sciendo.com/article/10.14313/jamris/2-2024/12<abstract> <title style='display:none'>Abstract</title> <p>The new wave of performant technology devices generates massive amounts of data. These devices are used in cities, homes, buildings, companies, and more. One of the reasons for digitalizing their tasks is that over the past few years, there has been an interest in reducing carbon emissions and increasing energy efficiency to create a friendly ecosystem and protect nature. One of which granted the explosion of data. After deploying these new devices, a significant increase in the use of the other face of energy to implement the components of the new devices was noticed. Above all, the interconnection of these intelligent devices is the central concept of the Internet of Things (IoT). This domain has widened the possibilities for the interconnection of building management systems (also named Smart Grids) and devices for better energy management. Furthermore, its potential is realized only after organizing and analyzing a large amount of data. Real-time management and maintenance of big data are critical to improving energy management in buildings. The benefits of big data analytics go beyond savings on electricity bills. It can provide comfort for building users and extend the life of building equipment, enhancing the value of commercial buildings. Intelligent interconnection of a building’s technical installations (lighting, heating, hot water, photovoltaic installations, etc.) not only allows for connected management of this equipment but also meets high energy efficiency criteria that indicate an increase in comfort and energy savings. With building automation, the technical installations of a building interact optimally. In this article, we will simulate an intelligent building based on the Cisco packet tracer software. To better manage the energy consumption of our project, we will focus on the processing of data in real-time, especially since we will have a massive amount of data generated by the sensors, which makes the use of big data mandatory.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/122024-06-23T00:00:00.000+00:00Diagnostics Based Patient Classification for Clinical Decision Support Systemshttps://sciendo.com/article/10.14313/jamris/2-2024/16<abstract> <title style='display:none'>Abstract</title> <p>The widespread adoption of Electronic Healthcare Records has resulted in an abundance of healthcare data. This data holds significant potential for improving healthcare services by providing valuable clinical insights and enhancing clinical decision-making. This paper presents a patient classification methodology that utilizes a multiclass and multilabel diagnostic approach to predict the patient’s clinical class. The proposed model effectively handles comorbidities while maintaining a high level of accuracy. The implementation leverages the MIMIC III database as a data source to create a phenotyping dataset and train the models. Various machine learning models are employed in this study. Notably, the natural language processing-based One-Vs-Rest classifier achieves the best classification results, maintaining accuracy and F1 scores even with a large number of classes. The patient diagnostic class prediction model, based on the International Classification of Diseases 9, showcased in this paper, has broad applications in diagnostic support, treatment prediction, clinical assistance, recommender systems, clinical decision support systems, and clinical knowledge discovery engines.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/162024-06-23T00:00:00.000+00:00SOC-FPGA Based Concept of Hardware Aided Quantum Simulationhttps://sciendo.com/article/10.14313/jamris/2-2024/9<abstract> <title style='display:none'>Abstract</title> <p>Contemporary industry and science expectations towards technological solutions set the bar high. Current approaches to increasing the computing power of standard systems are reaching the limits of physics known to humankind. Fast, programmable systems with relatively low power consumption are a different concept for performing complex calculations. Highly parallel processing opens up a number of possibilities in the context of accelerating calculations. Application of SoC (System On Chip) with FPGA (Field-Programmable Gate Array) enables the delegating of a part of computations to the gates matrix, thereby expediting processing by using parallelization of hardware operations. This paper presents the general concept of using SoC FPGA systems to support the CPU (Central Processing Unit) in many modern tasks. While some tasks might be really hard to implement on an FPGA in a reasonable time, the SoC FPGA platform allows for easy low-level interconnections, and with such virtualized access to the hardware computing resources, it is seen as making FPGAs, or hardware in general, more accessible to engineers accustomed to high-level solutions. The concept presented in the article takes into account the limited resources of cheaper educational platforms, which, however, still provide an interesting and alternative hybrid solution to the problem of parallelization and acceleration of data processing. This allows encountered limitations to be overcome and the flexibility known from high-level solutions and high performance achieved with low-level programming to be maintained without the need for a high financial background.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/92024-06-23T00:00:00.000+00:00Improving Teaching Using Artificial Intelligence and Augmented Realityhttps://sciendo.com/article/10.14313/jamris/2-2024/13<abstract> <title style='display:none'>Abstract</title> <p>With the rapid advancements in technology, the educational landscape is witnessing significant transformations in pedagogy and classroom dynamics. Two prominent technologies, Artificial Intelligence (AI) and Augmented Reality (AR), are gaining prominence in the field of education, promising to revolutionize the way teaching and learning take place. This article explores the potential benefits, challenges, and practical applications of integrating AI and AR into the teaching process to enhance student engagement and learning outcomes.</p> <p>The integration of AI in education brings forth personalized learning experiences. AI-powered algorithms analyze vast amounts of student data, including learning patterns, strengths, and weaknesses, to create tailored learning paths. This individualized approach helps educators identify students’ unique needs and provide targeted support, ensuring that no student is left behind. Moreover, AI-based chatbots and virtual teaching assistants are increasingly being used to address student queries promptly, providing real-time support and fostering a more interactive learning environment.</p> <p>AR, on the other hand, enables the overlay of virtual objects and information in the real-world environment.. Students can explore complex concepts through visualizations, simulations, and interactive demonstrations, facilitating a deeper understanding of abstract topics. AR also fosters collaboration and teamwork among students, promoting active learning and peer-to-peer knowledge sharing.</p> <p>Combining AI and AR technologies offers a powerful synergy in the educational realm. AI can analyze ARgenerated data and adapt instructional strategies in real time, responding to individual students’ progress. This synergy not only enhances learning outcomes but also empowers teachers with data-driven insights, enabling them to make informed decisions about their teaching methodologies.</p> <p>However, successfully implementing AI and AR in education comes with its challenges. Issues related to data privacy, ethical considerations, and the need for effective teacher training in utilizing these technologies require careful attention. Additionally, the digital divide can exacerbate educational inequalities, as not all students have equal access to technology outside the classroom.</p> <p>Collaboration between educators, researchers, and technology developers is crucial to overcome these challenges. The development of user-friendly, accessible, and ethically sound AI and AR tools can ensure inclusivity and maximize the potential benefits of these technologies in education. The aim is to investigate whether the use of AR technology can enhance students’ understanding and mastery of physics concepts through visualizations and simulations. Spatial intelligence plays a crucial role in various subjects, including physics, as it enables students to create mental models and representations of objects and expressions. While spatial intelligence is not an innate skill, it can be developed through interactions with real and virtual objects. ARas a cutting-edge technology, has the potential to illustrate physical applications and significantly aid students in visualizing and comprehending complex physics concepts.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/132024-06-23T00:00:00.000+00:00Comparative Analysis of CNN-Based Smart Pre-Trained Models for Object Detection on Dotahttps://sciendo.com/article/10.14313/jamris/2-2024/11<abstract> <title style='display:none'>Abstract</title> <p>In this paper, we proposed a comparative research project on the classification of various objects in satellite images using some pre-trained models of CNN (VGG-19, ResNet-50, Inception-V3, EfficientNet-B7) and R-CNN. In this research work, we have used the DOTA dataset, which combines data from 14 classes. We have implemented above-mentioned pre-trained models of CNN and R-CNN to achieve optimal results for accuracy as well as productivity in detection of various objects such as ships, tennis courts, swimming pools, vehicles, and harbors from remotely accessed images. In this study, a convolutional neural network (CNN) is used as the base model. For complex computations and for speeding up results, transfer learning is used. With the help of experimental analysis, we have discovered that R-CNN and Inception-V3 performed best out of the five pre-trained models.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/112024-06-23T00:00:00.000+00:00Research to Simulate the Ship’s Vibration Regeneration System using A 6-Degree Freedom Gough-Stewart Parallel Robothttps://sciendo.com/article/10.14313/jamris/2-2024/10<abstract> <title style='display:none'>Abstract</title> <p>This article presents research results on building a model to reproduce ship vibrations based on a parallel robot with 6 degrees of freedom on the Gough-Stewart platform. Vibration data at the ship’s center of gravity, calculated by simulation software, will be inputted into the model. The regenerative control system uses a simple PID controller to control input trajectory tracking. Simulation results on Matlab/Simulink software have demonstrated the reproduction of ship vibrations within the allowable error.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/102024-06-23T00:00:00.000+00:00Design of Small-Phase Time-Variant Low-Pass Digital Fractional Differentiators and Integratorshttps://sciendo.com/article/10.14313/jamris/2-2024/15<abstract> <title style='display:none'>Abstract</title> <p>The design method and the time-variant finite impulse response (FIR) architecture for real-time estimation of fractional and integer differentials and integrals are presented in this paper. The proposed FIR architecture is divided into two parts. Small-phase filtering, integer differentiation, and fractional differential and integration on the local data are performed by the first part, which is time-invariant. The second part, which is time-variant, handles fractional and global differentiation and integration. The separation of the two parts is necessary because real-time matrix inversion or an extensive analytical solution, which can be computationally intensive for high-order FIR architectures, would be required by a single time-variant FIR architecture. However, matrix inversion is used in the design method to achieve negligible delay in the filtered, differentiated, and integrated signals. The optimum output obtained by the method of least squares results in the negligible delay. The experimental results show that fractional and integer differentiation and integration can be performed by the proposed solution, although the fractional differentiation and integration process is sensitive to the noise and limited resolution of the measurements. In systems that require closed-loop control, disturbance observation, and real-time identification of model parameters, this solution can be implemented.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/152024-06-23T00:00:00.000+00:00Effective nonlinear Predictive and CTC-PID Control of Rigid Manipulatorshttps://sciendo.com/article/10.14313/jamris/2-2024/8<abstract> <title style='display:none'>Abstract</title> <p>Effective nonlinear control of manipulators with dynamically coupled arms, like those with direct drives, is the subject of the paper. Model-based predictive control (MPC) algorithms with nonlinear state-space models and most recent disturbance attenuation technique are proposed. This technique makes controller design and online calculations simpler, avoiding necessity of dynamic modeling of disturbances or resorting to additional techniques like SMC. The core of the paper are computationally effective MPC-NPL (Nonlinear Prediction and Linearization) algorithms, where computations at every sample are divided into two parts: prediction of initial trajectories using nonlinear model, then optimization using simplified linearized model. For a comparison, a known CTC-PID algorithm, which is also model-based, is considered. It is applied in standard form and also proposed in more advanced CTC-PID2dof version. For all algorithms a comprehensive comparative simulation study is performed, for a direct drive manipulator under disturbances. Additional contribution of the paper is investigation of influence of sampling period and of computational delay time on performance of the algorithms, which is practically important when using model-based algorithms with fast sampling.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/2-2024/82024-06-23T00:00:00.000+00:00Comparison of Curvilinear Parametrization Methods and Avoidance of Orthogonal Singularities in the Path Following Taskhttps://sciendo.com/article/10.14313/jamris/3-2023/22<abstract> <title style='display:none'>Abstract</title> <p>In this paper applications of curvilinear parametrizations (Serret–Frenet, Bishop) in the path following task have been considered. The parametrizations allow one to derive manipulator’s equations with respect to a path. The full mathematical model of the path following task involves two groups of equations, i.e., the dynamics of the manipulator and the equations obtained from the parametrization method, connected in the cascaded system.</p> <p>Based on those relations two path following algorithms have been designed according to the backstepping integrator method (dedicated to the cascaded systems). Depending on the chosen parametrization method the algorithms differ in requirements and performance. In the paper an in-depth analysis comparing features of both considered methods has been presented.</p> <p>The parametric description of a path requires projection of a robot on the path. In this article the orthogonal projection has been taken into account. It introduces a singularity in the robot description. We have proposed a new form of the orthogonal projection constraint which allows a robot to not only approach the path, but also move along it. This novelty design is an important enhancement of the algorithms used so far.</p> <p>The problem of partially known dynamic parameters of a robot has also been addressed. In this paper, we have shown how to apply an adaptive controller to the path following task.</p> <p>Theoretical considerations have been verified with a simulation study conducted for a holonomic stationary manipulator. Achieved results emphasized why it is strongly recommended to use the algorithm version with the orthogonal singularity outside the path. Moreover, the comparative analysis results may be used to select the best curvilinear parametrization method according to the considered task requirements.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/222024-03-04T00:00:00.000+00:00Improved Competitive Neural Network for Classification of Human Postures Based on Data from RGB-D Sensorshttps://sciendo.com/article/10.14313/jamris/3-2023/19<abstract> <title style='display:none'>Abstract</title> <p>The cognitive goal of this paper is to assess whether marker-less motion capture systems provide sufficient data to recognize human postures in the side view. The research goal is to develop a new posture classification method that allows for analysing human activities using data recorded by RGB-D sensors. The method is insensitive to recorded activity duration and gives satisfactory results for the sagittal plane. An improved competitive Neural Network (cNN) was used. The method of preprocessing the data is first discussed. Then, a method for classifying human postures is presented. Finally, classification quality using various distance metrics is assessed. The data sets covering the selection of human activities have been created. Postures typical for these activities have been identified using the classifying neural network. The classification quality obtained using the proposed cNN network and two other popular neural networks were compared. The results confirmed the advantage of cNN network. The developed method makes it possible to recognize human postures by observing movement in the sagittal plane.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/192024-03-04T00:00:00.000+00:00Skeleton-based Human Action/Interaction Classification in Sparse Image Sequenceshttps://sciendo.com/article/10.14313/jamris/3-2023/18<abstract> <title style='display:none'>Abstract</title> <p>Research results on human activity classification in video are described, based on initial human skeleton estimation in selected video frames. Simple, homogeneous activities, limited to single person actions and two-person interactions, are considered. The initial skeleton data is estimated in selected video frames by software tools, like “OpenPose” or “HRNet”. Main contributions of presented work are the steps of “skeleton tracking and correcting” and “relational feature extraction”. It is shown that this feature engineering step significantly increases the classification accuracy compared to the case of raw skeleton data processing. Regarding the final neural network encoder-classifier, two different architectures are designed and evaluated. The first solution is a lightweight multilayer perceptron (MLP) network, implementing the idea of a “mixture of pose experts”. Several pose classifiers (experts) are trained on different time periods (snapshots) of visual actions/interactions, while the final classification is a time-related pooling of weighted expert classifications. All pose experts share a common deep encoding network. The second (middle weight) solution is based on a “long short-term memory” (LSTM) network. Both solutions are trained and tested on the well-known NTU RGB+D dataset, although only 2D data are used. Our results show comparable performance with some of the best reported LSTM-, Graph Convolutional Network-(GCN), and Convolutional Neural Network-based classifiers for this dataset. We conclude that, by reducing the noise of skeleton data, highly successful lightweight- and midweight-models for the recognition of brief activities in image sequences can be achieved.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/182024-03-04T00:00:00.000+00:00Adaptive and Robust Following of 3D Paths by a Holonomic Manipulatorhttps://sciendo.com/article/10.14313/jamris/3-2023/23<abstract> <title style='display:none'>Abstract</title> <p>This paper addresses the problem of the following three-dimensional path by holonomic manipulator with parametric or structural uncertainty in the dynamics. Description of the manipulator relative to a desired threedimensional path was presented. The path is parameterized orthogonally to the Serret-Frenet frame, which is moving along the curve. The adaptive and robust control laws for a stationary manipulator which ensures realization of the task were specified. Theoretical considerations are supported by the results of computer simulations conducted for an RTR manipulator.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/232024-03-04T00:00:00.000+00:00Multimodal Robot Programming Interface Based on RGB-D Perception and Neural Scene Understanding Moduleshttps://sciendo.com/article/10.14313/jamris/3-2023/20<abstract> <title style='display:none'>Abstract</title> <p>In this paper, we propose a system for natural and intuitive interaction with the robot. Its purpose is to allow a person with no specialized knowledge or training in robot programming to program a robotic arm. We utilize data from the RGB-D camera to segment the scene and detect objects. We also estimate the configuration of the operator’s hand and the position of the visual marker to determine the intentions of the operator and the actions of the robot. To this end, we utilize trained neural networks and operations on the input point clouds. Also, voice commands are used to define or trigger the execution of the motion. Finally, we performed a set of experiments to show the properties of the proposed system.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/202024-03-04T00:00:00.000+00:00Singularity-Robust Inverse Kinematics for Serial Manipulatorshttps://sciendo.com/article/10.14313/jamris/3-2023/21<abstract> <title style='display:none'>Abstract</title> <p>This paper is a practical guideline on how to analyze and evaluate the literature algorithms of singularity-robust inverse kinematics or to construct new ones. Additive, multiplicative, and based on the Singularity Value Decomposition (SVD) methods are examined to retrieve well-conditioning of a matrix to be inverted in the Newton algorithm of inverse kinematics. It is shown that singularity avoidance can be performed in two different, but equivalent, ways: either via properly modified manipulability matrix or not allowing the decrease of the minimal singular value below a given threshold. It is discussed which method can always be used and which can only be used when some pre-conditions are met. Selected methods are compared to with respect to the efficiency of coping with singularities based on a theoretical analysis as well as simulation results. Also, some questions important for mathematically and/or practically oriented roboticians are stated and answered.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/212024-03-04T00:00:00.000+00:00Parameter Identification of Space Manipulator’s Flexible Jointhttps://sciendo.com/article/10.14313/jamris/3-2023/24<abstract> <title style='display:none'>Abstract</title> <p>A manipulator mounted on a satellite is often used to perform active debris removal missions. The space manipulator control system needs to take the dynamic model of the satellite-manipulator system into account because of the influence of the manipulator motion on the position and attitude of the satellite. Therefore, precise modeling of the space manipulator dynamics as well as parameter identification are needed to improve the credibility of the simulation tools. In this paper, we presented the identification of the flexible-joint space manipulator model based on dynamic equations of motion. Experiments were performed in an emulated microgravity environment using planar air bearings. The arbitrarily selected joint-space trajectory was performed by the manipulator’s control system. The experiments were repeated multiple times in order to analyze the identification method sensitivity. The identification is based on the Simulink SimMechanics model. Thus, the procedure can be used for any space manipulator without the need to obtain analytical relations for dynamic equations each time. Including joint flexibility and spring viscous damping in the dynamic model allowed it to reflect the experimental measurements better than the reference model could. Identified parameters of the flexible joint have values of the same magnitude as corresponding real system parameters.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/3-2023/242024-03-04T00:00:00.000+00:00Extended State Observer Based Robust Feedback Linearization Control Applied to an Industrial CSTRhttps://sciendo.com/article/10.14313/jamris/4-2023/32<abstract> <title style='display:none'>Abstract</title> <p>In the chemical and petrochemical industry, the Continuous Stirred Tank Reactors (CSTR) are, without doubt, one of the most popular processes. From a control point of view, the mathematical model describing the temporal evolution of the CSTR has a strongly nonlinear crosscoupled character. Moreover, modeling errors such as external disturbances, neglected dynamics, and parameter variations or uncertainties make its control task a very difficult challenge. Even though this problem has been the subject of a wide number of control strategies, this article attempts to propose a viable, robust, nonlinear decoupling control scheme. The idea behind the proposed approach lies in the design of two nested control loops. The inner loop is responsible for the compensation of the nominal model nonlinear cross-coupled terms via static nonlinear feedback; whereas the outer loop, designed around an Extended State Observer (ESO) of which the additional state gathers the global effect of modeling errors, is charged to instantaneously estimate, and then to compensate the ESO extended state. This way, the CSTR complex dynamics are reduced to a series of decoupled linear subsystems easily controllable using a simple Proportional-Integral (PI) linear control to ensure the robust pursuit of reference signals respecting the desired performance. The presented control validation was performed numerically by an objective comparison to a classical PID controller. The obtained results clearly show the viability and the effectiveness of the proposed control strategy for dealing with such nonlinear, strongly crosscoupled plants subject to a wide range of disturbances despite the precision of their described mathematical model.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/4-2023/322024-03-14T00:00:00.000+00:00Lyapunov-L Lasalle Based Dynamic Stabilization for Fixedwing Droneshttps://sciendo.com/article/10.14313/jamris/4-2023/29<abstract> <title style='display:none'>Abstract</title> <p>The market of Unmanned Aerial Vehicles (UAVs) for civil applications is extensively growing. Indeed, these airplanes are now widely used in applications such as data gathering, agriculture monitoring and rescue. The UAVs are required to track a fixed or moving object; thus, tracking control algorithms that ensure the system stability and that have a quick time response must be developed. This paper tackles the problem of supervising a fixed target using a fixed wing UAV flying at a constant altitude and a constant speed. For that purpose, three control algorithms were developed. In all of the algorithms, the UAV is expected to hover around the target in a circular trajectory. Moreover, the three approaches are based upon a Lyapunov-LaSalle stabilization method. The first tracking algorithm ensures that the UAV circles around the target. However, the path that the UAV follows in order to join this pattern is not studied. In the second and third approach, two different techniques that allow the UAV to intercept its final circular pattern in the quickest possible time and thus follow the tangent to the circular pattern are presented. Simulation results that show and compare the performances of the proposed methods are presented.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/4-2023/292024-03-14T00:00:00.000+00:00Wimax Network Optimization Using Frame Period with Channel Allocation Techniqueshttps://sciendo.com/article/10.14313/jamris/4-2023/31<abstract> <title style='display:none'>Abstract</title> <p>Internet connectivity in WiMAX networks, along with various applications, is increasing rapidly, so the connectivity of internet and data transfer speed are always challenges for effective data transmission in wireless networks. Several factors affect the performance of networks. One important factor is to choose a suitable frame period for effective data transmissions. The performance of different frame periods with Round Robin and Strict Priority is evaluated in this work. A frame period in Round Robin performs better than a Strict Priority in terms of throughput, but a Strict Priority performs better in terms of drop rates. This paper also demonstrates that an effective frame period, when combined with a proper bandwidth allocation algorithm, yields better results. This work gives the analysis that Round Robin performs 83.8847% better while Strict Priority performs 86.0020% better than the earliest deadline first algorithms for 10 subscriber stations in terms of throughput. This work is helpful to researchers and industrialists for actual implementations in WiMAX networks.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/4-2023/312024-03-14T00:00:00.000+00:00Implementing Visual Assistant Using Yolo and SSD for Visually-Impaired Personshttps://sciendo.com/article/10.14313/jamris/4-2023/33<abstract> <title style='display:none'>Abstract</title> <p>Artificial Intelligence has been touted as the next big thing that is capable of altering the current landscape of the technological domain. Through the use of Artificial Intelligence and Machine Learning, pioneering work has been undertaken in the area of Visual and Object Detection. In this paper, we undertake the analysis of a Visual Assistant Application for Guiding Visually-Impaired Individuals. With recent breakthroughs in computer vision and supervised learning models, the problem at hand has been reduced significantly to the point where new models are easier to build and implement than the already existing models. Different object detection models exist now that provide object tracking and detection with great accuracy. These techniques have been widely used in automating detection tasks in different areas. A few newly discovered detection approaches, such as the YOLO (You Only Look Once) and SSD (Single Shot Detector) approaches, have proved to be consistent and quite accurate at detecting objects in real-time. This paper attempts to utilize the combination of these state-of-the-art, realtime object detection techniques to develop a good base model. This paper also implements a ’Visual Assistant’ for visually impaired people. The results obtained are improved and superior compared to existing algorithms.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.14313/jamris/4-2023/332024-03-14T00:00:00.000+00:00en-us-1