Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
224
Acumen: International Journal of Multidisciplinary Research
DEVELOPMENT OF A MODEL FOR RECOGNIZING VARIOUS OBJECTS
AND TOOLS IN A COLLABORATIVE ROBOT WORKSPACE
Vladyslav Yevsieiev1, Amer Abu-Jassar2, Svitlana Maksymova1, Nataliia
Demska1
1Department of Computer-Integrated Technologies, Automation and Robotics,
Kharkiv National University of Radio Electronics, Ukraine
2Department of Computer Science, College of Information Technology, Amman
Arab University, Amman, Jordan
Abstract
The article discusses the development of a model for recognizing objects and
tools in the robot's workspace, which is based on computer vision and machine learning
methods to ensure safe interaction within the framework of Industry 5.0. The model
allows increasing the accuracy and reliability of object recognition in complex
conditions, adapting robots to changing tasks. The results can be used for integration
into robotic platforms operating in flexible manufacturing environments, ensuring
flexible automation and a human-centric approach.
Keywords:
Object Recognition, Robotic Systems, Computer Vision, Machine
Learning, Robot Workspace, Industry 5.0.
Introduction
In the context of the rapid development of Industry 5.0, which is aimed at the
harmonious coexistence of humans and technologies, robotic systems are taking on
new roles, in particular in the field of safe and effective cooperation with people in
production [1]-[4]. Modern robotic platforms are no longer limited to automating
routine processes, but are beginning to perform more complex tasks that require
adaptation to rapidly changing conditions and accurate recognition of surrounding
objects [5]-[30]. Various methods and approaches can be used here [31]-[41].
Of particular importance is the ability of robots to distinguish between different
tools and objects in the work area, which allows them to make operational decisions
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
225
Acumen: International Journal of Multidisciplinary Research
about interacting with them based on their types and characteristics. This opens up
opportunities for flexible adaptation of the robot to new tasks, automation of complex
technological processes and increased safety in the workplace. However, existing
object recognition technologies often have low accuracy when processing complex or
noisy data, which requires the development of new methods to achieve high reliability.
Within the framework of the Industry 5.0 concept, a robot must be able not only to
recognize objects, but also to understand the context of tool use and act accordingly to
changing tasks. Such adaptability is achieved by combining artificial intelligence,
computer vision and machine learning algorithms, which together create new
possibilities for robotic systems. This research aims to develop a mathematical model
that will allow robots to effectively identify and classify objects in the work area,
ensuring their reliable interaction with the environment. The successful
implementation of such a model will contribute to the development of robotic platforms
that can support autonomous interaction with tools and objects, automatically choosing
the optimal paths to perform production tasks. In addition, such developments meet the
principles of human-centricity and sustainable development, which are key in the
Industry 5.0 concept. As a result, robotic systems will be able to provide higher
productivity, minimize risks to workers, and expand opportunities for integration into
new industries.
Related works
In the modern world, many scientists are engaged in the implementation of the
principles of the Industry 5.0 concept. They consider a wide variety of problems that
arise when solving the above-mentioned task. Let us consider several such works.
First of all, let us analyze the work [42]. There is noted the critical role and
implications of Cobotics in the context of Industry 5.0. The study addresses the
research problem of effectively integrating Cobots into industrial processes,
considering technical, economic, and social challenges.
Collaborative robotics, or “cobotics”, is a major enabling technology of Industry
5.0, which aspires at improving human dexterity by elevating robots to extensions of
human capabilities and, ultimately, even as team members. This fact is noted in [43].
A review [44] was performed aimed at investigating the effect of robot design
features on their human counterparts. Its results showcased the many to many
relationships between robot design features and effects on operators.
Doyle Kent, M., & Kopacek, P. in [45] arise next questions whether it is possible
to ensure that humans have a place in the highly automated workplace of the future
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
226
Acumen: International Journal of Multidisciplinary Research
(Industry 5.0) by optimizing human capital; and whether it is possible for traditional
educational provider supply the skills required to educate this modern worker or do we
require an innovative educational system?
Prassida, G. F., & Asfari, U. in [46] provide a holistic view of the acceptance of
collaborative robots (cobots) in the manufacturing context by adopting the socio-
technical perspective to the Industry 5.0 era. Grounding on the Unified Theory of
Acceptance and Use of Technology (UTAUT) and Socio-Technical Systems theory
(STS), this study proposes a conceptual model to better understanding critical factors
that influence the acceptance of cobots and how these factors can drive perceived work
performance improvement in the organizational level.
The scientists in [47] note that one relevant the most relevant challenges of
Industry 5.0 is the design of human-centered smart environments (i.e., that prioritize
human well-being while maintaining production performance).
Thus, we see a variety of issues arising during the implementation of Industry
5.0 technology. Our vision of a possible solution to the problem of recognizing objects
and tools is presented further in this article.
Mathematical model of various objects and tools recognition in a
collaborative robot workspace for making decisions about further actions
To create a mathematical model for recognizing various objects and tools in the
robot's working area and making decisions for interacting with them, a model based on
neural networks and image processing methods is used. As part of these studies, the
following mathematical model is proposed, which covers the main stages: processing
input data, classifying objects, determining position, calculating interaction parameters
and making decisions.
The first stage: The robot perceives the working area using sensors or a camera
that provide an image or a three-dimensional map. Let's assume that the image has a
resolution
W
H
(width and height) and is represented as a set of pixels. We make the
following variables
( , )
I x y
– intensity or color value for a pixel with coordinates
( , )
x y
and
( , )
D x y
– depth or distance to the object in the working area (for stereo images or
using LiDAR). Before starting recognition, smoothing, color normalization, noise
filtering and contrast equalization methods are applied.
The next step in the input data processing stage is the separation of objects using
segmentation. Segmentation consists of dividing an image into parts to highlight areas
that may be objects or tools.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
227
Acumen: International Journal of Multidisciplinary Research
To separate objects based on color or depth, it is proposed to use the threshold
segmentation method, which can be described by the following model:
min
[
min
max
1,if ( , ) [
,
]and ( , ) [
,
]
( , )
0, otherwise
ma
I x y
I
I
D x y
D
D
S x y
=
(1)
( , )
S x y
– segmentation mask;
min
I
and
max
I
– intensity range for segmentation;
min
D
and
max
D
– range for depth.
The convolution method will be used to calculate image gradients to determine
the contours of objects, which can be represented by the following expression:
( , )
(
,
)
( , )
k
k
i
k j
k
G x y
I x
i y
j
K i j
=−
=−
=
+
+
(2)
( , )
G x y
– result of convolution;
( , )
K i j
– convolution kernel (e.g., Sobel operator or other solution).
The second stage is object classification using a neural network. To classify
objects, a convolutional neural network (CNN) is used, which is trained on data
containing images and object labels. The CNN model can be rearranged as follows:
– input layer:
,
1,
1
{ ( , )}
W H
x
y
X
I x y
=
=
=
(3)
X
– input layer.
– convolutional layer:
(
,
)
1
1
N
N
l
ij
x i y j
i
j
F
K
X
b
+
+
=
=
=
+
(4)
l
F
– filtered image on
l
-th layer;
– activation function (e.g.ReLU);
K
– convolution kernels in CNN;
b
– displaced.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
228
Acumen: International Journal of Multidisciplinary Research
– max pooling layer for dimensionality reduction:
( , )
max(
), ( , )
area
ij
P x y
X
i j
=
.
(5)
– fully connected layer for object class output:
(
)
y
f W P
b
=
+
,
(6)
y
– probability vector for each class;
W
– weight matrix;
b
– bias;
f
– a nonlinear activation function that converts logits (values from the
intermediate layer) into probabilities.
The third stage is to determine the position of objects in the collaborative robot
workspace. If objects are recognized, their positions are determined taking into account
the depth and pixel coordinates, and can be described as follows:
(
,
,
)
( ( , )
( , ))
ob
ob
ob
x
y
d
O S x y
D x y
=
(7)
(
,
,
)
ob
ob
ob
x
y
d
– coordinates and depth of the center of mass (or center of gravity)
of the object, defined in the robot's working area;
O
– operator that calculates the coordinates of the center of mass of an object
by weighting the depth values according to the segmentation mask. This operator
calculates the average value of the coordinates
( , )
x y
taking into account the mask
( , )
S x y
and the depth
( , )
D x y
to obtain the position of the center of mass of the object
in the image and in space;
( , )
S x y
– a two-dimensional image segmentation function that determines
whether each point with coordinates
( , )
x y
belongs to an object;
( , )
D x y
– a function that represents the depth or distance to each point
( , )
x y
in
an image.
And there is the last stage of decision-making for interaction with objects in the
collaborative robot workspace. Based on the recognized objects and tools, the robot
makes a decision, in particular, selects appropriate actions:
– the decision to capture the object, can be represented by the following
expression:
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
229
Acumen: International Journal of Multidisciplinary Research
"capture", if
and
"tool"
"go around", if
"obstacle"
"continue", otherwise
ob
capture
ob
ob
d
d
C
R
C
=
=
=
(8)
ob
C
– object class (tool, obstacle, etc.).
– planning a trajectory to avoid or approach an object:
( , )
( , ,
,
)
ob
ob
T x y
f x y x
y
=
(9)
( , )
T x y
– trajectory built for interaction;
f
– scheduling algorithm (e.g., A* or D*).
Taking into account all stages, the mathematical model of decision-making based
on object recognition is described by the expression:
))
,
,
(
)),
,
(
(
(
)
,
(
ob
ob
ob
d
y
x
D
I
S
CNN
R
D
I
N
=
(10)
N
– decision-making function;
( ,
)
S I D
– segmentation result;
CNN
– classification function;
R
– solution for interacting with the object.
The developed general mathematical model of decision-making based on object
recognition
)
,
(
D
I
N
provides a number of advantages for the tasks of object recognition
in the robot’s workspace. The use of a convolutional neural network (CNN) in
combination with segmentation
( ,
)
S I D
, which takes into account both image intensity
I
and depth data
D
, allows the model to better distinguish objects, taking into account
their three-dimensional structure and position. This provides increased accuracy and
robustness in complex conditions, where objects may partially overlap or change their
orientation. The parameters of the center of mass of the object
(
,
,
)
ob
ob
ob
x
y
d
allow the
model to take into account the position and distance to objects, which facilitates
decision-making regarding interaction with them in real space. The component
R
combines the processed features and positional parameters, creating a holistic approach
to object recognition and response. Such a comprehensive model increases the
efficiency and reliability of robotic systems in a changing production environment,
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
230
Acumen: International Journal of Multidisciplinary Research
which meets the requirements of Industry 5.0 and contributes to flexible automation
and integration of human-centric technologies.
Software implementation of a program for recognizing various objects and
tools in the a collaborative robot workspace
The choice of the Python programming language for developing an object
recognition program in the collaborative robot workspace is justified by its powerful
capabilities in the field of machine learning and computer vision, as well as the
availability of numerous specialized libraries. Python has a simple and understandable
syntax, which makes it convenient for rapid development and maintenance of code,
especially in complex engineering projects. In combination with the TensorFlow
library, Python provides extensive capabilities for working with neural networks, in
particular convolutional (CNN), which are the basis for object recognition. Using
TensorFlow also allows you to use pre-trained models, such as MobileNetV2, to speed
up the development process and improve recognition accuracy. The integration of the
OpenCV library, which has image processing functions such as noise filtering,
smoothing, segmentation, and more, makes Python an ideal tool for processing video
streams in real time. The NumPy library provides efficient work with multidimensional
arrays, which is a key aspect when manipulating images and processing results,
especially during segmentation and classification. In addition, Python is a cross-
platform language, which allows you to run the program on different operating
systems, providing flexibility and portability. Thanks to an active community of
developers and a large number of open resources, Python offers stable support and
continuous improvement of the tools necessary for the development of modern
computer vision and artificial intelligence systems, which is critically important for
collaborative robotics. Let us describe the software implementation of the recognition
of various objects and tools in a collaborative robot workspace.
model = tf.saved_model.load(
r"C:\Users\Vladyslav\.cache\kagglehub\models\tensorflow\ssd-mobilenet-
v2\tensorFlow2\fpnlite-320x320\1")
This code snippet loads the pre-trained ssd-mobilenet-v2 model from the
TensorFlow library, saved in the SavedModel format, from the specified path. The
model is used to recognize objects in images or video streams, allowing the program
to automatically determine object classes and their coordinates in the frame.
def preprocess_image(image):
image = cv2.GaussianBlur(image, (5, 5), 0)
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
231
Acumen: International Journal of Multidisciplinary Research
image = cv2.normalize(image, None, 0, 255, cv2.NORM_MINMAX)
return image
This code snippet defines the `preprocess_image` function, which performs
preprocessing on the image to improve its quality before further analysis. The function
applies smoothing using a Gaussian filter to reduce noise and normalizes the pixel
intensity to a range of 0 to 255. This helps improve segmentation and object recognition
results.
def threshold_segmentation(image, low_intensity, high_intensity):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
_, thresholded = cv2.threshold(gray, low_intensity, high_intensity,
cv2.THRESH_BINARY)
return thresholded
This code snippet defines the `threshold_segmentation` function, which
performs threshold segmentation on an image to extract objects. First, the image is
converted to grayscale, and then a binary threshold is applied, which turns pixels into
black or white depending on their intensity. This simplifies further processing, making
it easier to identify objects in the image.
def calculate_center_of_mass(box, frame_shape):
y1, x1, y2, x2 = box
height, width = frame_shape[:2]
center_x = int((x1 + x2) / 2 * width)
center_y = int((y1 + y2) / 2 * height)
return center_x, center_y
This code snippet defines the function `calculate_center_of_mass`, which
calculates the coordinates of the center of mass of an object using the coordinates of
its bounding box `box`. Given the dimensions of the frame `frame_shape`, the function
returns the center coordinates `center_x` and `center_y`, which helps to more
accurately determine the position of the object for further interaction.
num_detections = int(detections['num_detections'][0])
detection_classes
detections['detection_classes'][0].numpy().astype(np.int64)
detection_boxes = detections['detection_boxes'][0].numpy()
detection_scores = detections['detection_scores'][0].numpy()
This code snippet extracts object recognition results from the model's detection
output. `num_detections` specifies the number of objects found, and
`detection_classes`, `detection_boxes`, and `detection_scores` contain the classes,
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
232
Acumen: International Journal of Multidisciplinary Research
bounding box coordinates, and probabilities for each object, respectively. This allows
the program to process and display information about the detected objects in the image.
if class_name in ['person', 'car', 'bicycle']:
print(f"Object avoidance: {class_name}")
else:
print(f"Capturing the object: {class_name}")
This code fragment checks the object class to determine whether it is an obstacle
to avoid or an object to capture. If the object class belongs to the obstacle list (`person`,
`car`, `bicycle`), avoidance is performed, otherwise — capture. This helps to decide on
the robot's further actions depending on the type of object.
An example of the developed program for recognizing various objects and tools
in the collaborative robot's workspace is shown in Figure 1.
a)
b)
a) recognition program window; b) decision terminal window.
Figure 1:
An example of the work of the developed program for recognizing various
objects and tools in a collaborative robot workspace
Let's conduct an experiment to test the developed program for recognizing
various objects and tools in a collaborative robot workspace, for example, to check the
model in situations where objects are partially covered or noise is superimposed on the
image (for example, by varying the lighting or adding background noise). This will
allow us to assess the model's resistance to real conditions, where errors may occur due
to complex background conditions. The results obtained during the experiment are
given in Table 1, and Figure 2 shows a graph
Table 1:
Results in different conditions
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
233
Acumen: International Journal of Multidisciplinary Research
Experimental conditions
Proportion of
objects
recognized
(%)
Precision
(%)
Recall
(%)
F1-
measure
(%)
No noise, normal lighting 98%
97%
95%
96%
Partial overlap (25%)
85%
83%
78%
80%
Partial overlap (50%)
65%
60%
55%
57%
Low lighting
70%
68%
66%
67%
High lighting
80%
75%
70%
72%
Added background noise
(10%)
90%
85%
83%
84%
Added background noise
(20%)
75%
70%
65%
67%
Added background noise
(30%)
60%
55%
50%
52%
Partial overlap + low light 50%
48%
45%
46%
Partial
overlap
+
background noise
55%
53%
50%
51%
Figure 2:
Model Performance under Different Experimental Conditions Graph
Analysis of the obtained experimental data shows that the object recognition
model demonstrates high accuracy (Precision 97%) and completeness (Recall 95%) in
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
234
Acumen: International Journal of Multidisciplinary Research
standard conditions without interference, which confirms its basic adequacy. With
partial overlap of objects, accuracy and completeness decrease (to 83% and 78%,
respectively, at 25% overlap), and at 50% overlap these indicators fall even more,
which indicates the vulnerability of the model to partial visibility of objects. In low-
light conditions, Precision and Recall indicators decrease to 68% and 66%, while with
additional background noise of 10% the model remains relatively stable (Precision
85%, Recall 83%). However, with an increase in noise to 30%, the indicators drop
significantly, especially Recall to 50%, which indicates a decrease in the model's ability
to correctly identify objects under strong interference. The F1-measures, which take
into account both Precision and Recall, show a similar trend, confirming the general
logic and stability of the model's quality degradation with increasing noise, decreasing
illumination, or partial overlap. Overall, the model performs well under optimal
conditions, but its robustness to noise and partial overlap needs improvement to ensure
reliability in real-world conditions.
Conclusion
The article presents a developed model for recognizing various objects and tools
in a collaborative robot workspace, which provides automatic determination of object
classes and positions for safe and effective interaction with them. The model
demonstrates high accuracy in standard conditions, however, experimental results
indicate the need for improvement in conditions of low illumination, partial
overlapping of objects and increased noise, where the recognition quality decreases.
This indicates the importance of additional image processing mechanisms, such as
adaptive segmentation, improved smoothing and methods that take into account the
three-dimensional structure of the workspace. Further research prospects include
expanding the functionality of the model using more complex neural networks, such as
deep convolutional networks and transformers, which can improve noise immunity and
ensure reliable operation in difficult conditions. Research can also focus on integrating
data from additional sensors, such as LiDAR and ultrasonic sensors, for more accurate
determination of the distance to objects. This will contribute to the creation of a
comprehensive detection and classification system that takes into account not only
visual characteristics, but also spatial parameters of objects. As a result, the proposed
model has the potential for further improvement, meeting the requirements of
Industry 5.0 and supporting the development of safe, reliable robotic systems focused
on collaborative work with humans.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
235
Acumen: International Journal of Multidisciplinary Research
References
1.
Samoilenko, H., & et al. (2024). Review for Collective Problem-Solving by a
Group of Robots. Journal of Universal Science Research, 2(6), 7-16.
2.
Yevsieiev, V., & et al. (2024). Research of Existing Methods of Representing a
Collaborative Robot-Manipulator Environment within the Framework of
Cyber-Physical Production Systems. Multidisciplinary Journal of Science and
Technology, 4(9), 112-120.
3.
Maksymova, S., Yevsieiev, V., Nevliudov, I., & Uluhan, N. (2024).
Constructing an Optimal Route for a Mobile Robot Using a Wave Algorithm.
Journal of Natural Sciences and Technologies, 3(1), 282-289.
4.
Gurin, D., & et al. (2024). Using Convolutional Neural Networks to Analyze
and Detect Key Points of Objects in Image. Multidisciplinary Journal of
Science and Technology, 4(9), 5-15.
5.
Basiuk, V., & et al. (2024). Command System for Movement Control
Development. Multidisciplinary Journal of Science and Technology, 4(6), 248-
255.
6.
Yevsieiev, V., & et al. (2024). The Sobel algorithm implementation for
detection an object contour in the mobile robot’s workspace in real time.
Technical Science Research in Uzbekistan, 2(3), 23-33.
7.
Maksymova, S., & et al. (2024). The Lucas-Kanade method implementation
for estimating the objects movement in the mobile robot’s workspace. Journal
of Universal Science Research, 2(3), 187-197.
8.
Abu-Jassar, A., & et al. (2024). The Optical Flow Method and Graham’s
Algorithm Implementation Features for Searching for the Object Contour in
the Mobile Robot’s Workspace. Journal of Universal Science Research, 2(3),
64-75.
9.
Maksymova, S., & et al. (2024). Comparative Analysis of methods for
Predicting the Trajectory of Object Movement in a Collaborative Robot-
Manipulator Working Area. Multidisciplinary Journal of Science and
Technology, 4(10), 38-48.
10.
Yevsieiev, V., & et al. (2024). Human Operator Identification in a Collaborative
Robot Workspace within the Industry 5.0 Concept. Multidisciplinary Journal
of Science and Technology, 4(9), 95-105.
11.
Sotnik, S., Mustafa, S. K., Ahmad, M. A., Lyashenko, V., & Zeleniy, O. (2020).
Some features of route planning as the basis in a mobile robot. International
Journal of Emerging Trends in Engineering Research, 8(5), 2074-2079.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
236
Acumen: International Journal of Multidisciplinary Research
12.
Lyashenko, V., Abu-Jassar, A. T., Yevsieiev, V., & Maksymova, S. (2023).
Automated Monitoring and Visualization System in Production. International
Research Journal of Multidisciplinary Technovation, 5(6), 9-18.
13.
Matarneh, R., Maksymova, S., Deineko, Z., & Lyashenko, V. (2017). Building
robot voice control training methodology using artificial neural net.
International Journal of Civil Engineering and Technology, 8(10), 523-532.
14.
Lyashenko, V., Kobylin, O., & Ahmad, M. A. (2014). General methodology for
implementation of image normalization procedure using its wavelet transform.
International Journal of Science and Research (IJSR), 3(11), 2870-2877.
15.
Sotnik, S., Matarneh, R., & Lyashenko, V. (2017). System model tooling for
injection molding. International Journal of Mechanical Engineering and
Technology, 8(9), 378-390.
16.
Maksymova, S., Matarneh, R., Lyashenko, V. V., & Belova, N. V. (2017). Voice
Control for an Industrial Robot as a Combination of Various Robotic Assembly
Process Models. Journal of Computer and Communications, 5, 1-15.
17.
Гиренко, А. В., Ляшенко, В. В., Машталир, В. П., & Путятин, Е. П. (1996).
Методы корреляционного обнаружения объектов. Харьков: АО
“БизнесИнформ, 112.
18.
Lyashenko, V. V., Babker, A. M. A. A., & Kobylin, O. A. (2016). The
methodology of wavelet analysis as a tool for cytology preparations image
processing. Cukurova Medical Journal, 41(3), 453-463.
19.
Lyashenko, V. V., Matarneh, R., & Deineko, Z. V. (2016). Using the Properties
of Wavelet Coefficients of Time Series for Image Analysis and Processing.
Journal of Computer Sciences and Applications, 4(2), 27-34.
20.
Lyashenko, V., Matarneh, R., & Kobylin, O. (2016). Contrast modification as
a tool to study the structure of blood components. Journal of Environmental
Science, Computer Science and Engineering & Technology, 5(3), 150-160.
21.
Lyubchenko, V., & et al.. (2016). Digital image processing techniques for
detection and diagnosis of fish diseases. International Journal of Advanced
Research in Computer Science and Software Engineering, 6(7), 79-83.
22.
Lyashenko, V. V., Matarneh, R., Kobylin, O., & Putyatin, Y. P. (2016). Contour
Detection and Allocation for Cytological Images Using Wavelet Analysis
Methodology. International Journal, 4(1), 85-94.
23.
Ahmad, M. A., Baker, J. H., Tvoroshenko, I., & Lyashenko, V. (2019).
Modeling the structure of intellectual means of decision-making using a
system-oriented NFO approach. International Journal of Emerging Trends in
Engineering Research, 7(11), 460-465.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
237
Acumen: International Journal of Multidisciplinary Research
24.
Lyashenko, V., Kobylin, O., & Selevko, O. (2020). Wavelet analysis and
contrast modification in the study of cell structures images. International
Journal of Advanced Trends in Computer Science and Engineering, 9(4), 4701-
4706.
25.
Lyashenko, V., & et al.. (2021). Wavelet ideology as a universal tool for data
processing and analysis: some application examples. International Journal of
Academic Information Systems Research (IJAISR), 5(9), 25-30.
26.
Ahmad, M. A., Baker, J. H., Tvoroshenko, I., Kochura, L., & Lyashenko, V.
(2020). Interactive Geoinformation Three-Dimensional Model of a Landscape
Park Using Geoinformatics Tools. International Journal on Advanced Science,
Engineering and Information Technology, 10(5), 2005-2013.
27.
Lyashenko, V. V., Matarneh, R., & Deineko, Z. V. (2016). Using the Properties
of Wavelet Coefficients of Time Series for Image Analysis and Processing.
Journal of Computer Sciences and Applications, 4(2), 27-34.
28.
Babker, A. M., Abd Elgadir, A. A., Tvoroshenko, I., & Lyashenko, V. (2019).
Information technologies of the processing of the spaces of the states of a
complex biophysical object in the intellectual medical system health.
International Journal of Advanced Trends in Computer Science and
Engineering, 8(6), 3221-3227.
29.
Khan, A., Joshi, S., Ahmad, M. A., & Lyashenko, V. (2015). Some effect of
Chemical treatment by Ferric Nitrate salts on the structure and morphology of
Coir Fibre Composites. Advances in Materials Physics and Chemistry, 5(1),
39-45.
30.
Abu-Jassar, A. T., Attar, H., Lyashenko, V., Amer, A., Sotnik, S., & Solyman,
A. (2023). Access control to robotic systems based on biometric: the
generalized model and its practical implementation. International Journal of
Intelligent Engineering and Systems, 16(5), 313-328.
31.
Al-Sharo, Y. M., Abu-Jassar, A. T., Sotnik, S., & Lyashenko, V. (2023).
Generalized Procedure for Determining the Collision-Free Trajectory for a
Robotic Arm. Tikrit Journal of Engineering Sciences, 30(2), 142-151.
32.
Ahmad, M. A., Sinelnikova, T., Lyashenko, V., & Mustafa, S. K. (2020).
Features of the construction and control of the navigation system of a mobile
robot. International Journal of Emerging Trends in Engineering Research, 8(4),
1445-1449.
33.
Lyashenko, V., Laariedh, F., Ayaz, A. M., & Sotnik, S. (2021). Recognition of
Voice Commands Based on Neural Network. TEM Journal: Technology,
Education, Management, Informatics, 10(2), 583-591.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
238
Acumen: International Journal of Multidisciplinary Research
34.
Tahseen A. J. A., & et al.. (2023). Binarization Methods in Multimedia Systems
when Recognizing License Plates of Cars. International Journal of Academic
Engineering Research (IJAER), 7(2), 1-9.
35.
Orobinskyi, P., Petrenko, D., & Lyashenko, V. (2019, February). Novel
approach to computer-aided detection of lung nodules of difficult location with
use of multifactorial models and deep neural networks. In 2019 IEEE 15th
International Conference on the Experience of Designing and Application of
CAD Systems (CADSM) (pp. 1-5). IEEE.
36.
Matarneh, R., Sotnik, S., Belova, N., & Lyashenko, V. (2018). Automated
modeling of shaft leading elements in the rear axle gear. International Journal
of Engineering and Technology (UAE), 7(3), 1468-1473.
37.
Abu-Jassar, A. T., Attar, H., Amer, A., Lyashenko, V., Yevsieiev, V., & Solyman,
A. (2024). Remote Monitoring System of Patient Status in Social IoT
Environments Using Amazon Web Services (AWS) Technologies and Smart
Health Care. International Journal of Crowd Science, 8.
38.
Lyubchenko, V., Veretelnyk, K., Kots, P., & Lyashenko, V. (2024). Digital
image segmentation procedure as an example of an NP-problem.
Multidisciplinary Journal of Science and Technology, 4(4), 170-177.
39.
Babker, A. M., Suliman, R. S., Elshaikh, R. H., Boboyorov, S., & Lyashenko,
V. (2024). Sequence of Simple Digital Technologies for Detection of Platelets
in Medical Images. Biomedical and Pharmacology Journal, 17(1), 141-152.
40.
Yevstratov, M., Lyubchenko, V., Amer, A. J., & Lyashenko, V. (2024). Color
correction of the input image as an element of improving the quality of its
visualization. Technical science research in Uzbekistan, 2(4), 79-88.
41.
Attar, H., Abu-Jassar, A. T., Lyashenko, V., Al-qerem, A., Sotnik, S., Alharbi,
N., & Solyman, A. A. (2023). Proposed synchronous electric motor simulation
with built-in permanent magnets for robotic systems. SN Applied Sciences,
5(6), 160.
42.
Rahman, M. M., & et al. (2024). Cobotics: The Evolving Roles and Prospects
of Next‐Generation Collaborative Robots in Industry 5.0. Journal of Robotics,
2024(1), 2918089.
43.
Zafar, M. H., & et al. (2024). Exploring the synergies between collaborative
robotics, digital twins, augmentation, and industry 5.0 for smart manufacturing:
A state-of-the-art review. Robotics and Computer-Integrated Manufacturing,
89, 102769.
Acumen:
International Journal of
Multidisciplinary Research
ISSN: 3060-4745
IF(Impact Factor)10.41 / 2024
Volume 2, Issue 1
239
Acumen: International Journal of Multidisciplinary Research
44.
Panagou, S., & et al. (2024). A scoping review of human robot interaction
research towards Industry 5.0 human-centric workplaces. International Journal
of Production Research, 62(3), 974-990.
45.
Doyle Kent, M., & Kopacek, P. (2021). Do we need synchronization of the
human and robotics to make industry 5.0 a success story?. In Digital
Conversion on the Way to Industry 4.0: Selected Papers from ISPR2020,
September 24-26, 2020 Online-Turkey, Springer International Publishing. 302-
311.
46.
Prassida, G. F., & Asfari, U. (2022). A conceptual model for the acceptance of
collaborative robots in industry 5.0. Procedia Computer Science, 197, 61-67.
47.
Coronado, E., & et al. (2022). Evaluating quality in human-robot interaction:
A systematic search and classification of performance and human-centered
factors, measures and metrics towards an industry 5.0. Journal of
Manufacturing Systems, 63, 392-410.
