Applying convolutional neural networks for limited-memory application

TELKOMNIKA Telecommunication, Computing, Electronics and Control
Vol. 19, No. 1, February 2021, pp. 244~251
ISSN: 1693-6930, accredited First Grade by Kemenristekdikti, Decree No: 21/E/KPT/2018
DOI: 10.12928/TELKOMNIKA.v19i1.16232  244
Journal homepage: http://journal.uad.ac.id/index.php/TELKOMNIKA
Applying convolutional neural networks for limited-memory
application
Xuan-Kien Dang1
, Huynh-Nhu Truong2
, Viet-Chinh Nguyen3
, Thi-Duyen-Anh Pham4
1,3,4
Ho Chi Minh City University of Transport, Vietnam
2
Ba Ria-Vung Tau College of Technology, Vietnam
Article Info ABSTRACT
Article history:
Received Apr 2, 2020
Revised Jun 12, 2020
Accepted Aug 29, 2020
Currently, convolutional neural networks (CNN) are considered as the most
effective tool in image diagnosis and processing techniques. In this paper, we
studied and applied the modified SSDLite_MobileNetV2 and proposed a
solution to always maintain the boundary of the total memory capacity in the
following robust bound and applied on the bridge navigational watch & alarm
system (BNWAS). The hardware was designed based on raspberry Pi-3, an
embedded single board computer with CPU smartphone level, limited RAM
without CUDA GPU. Experimental results showed that the deep learning
model on an embedded single board computer brings us high effectiveness in
application.
Keywords:
Convolutional neural networks
Image processing
Limited hardware devices
Maritime application
Object classification This is an open access article under the CC BY-SA license.
Corresponding Author:
Xuan-Kien Dang
Graduate School
Ho Chi Minh City University of Transport
Number 2, Vo Oanh Street, Ward 25, Binh Thanh District, Ho Chi Minh City, Vietnam
Email: dangxuankien@hcmutrans.edu.vn
1. INTRODUCTION
Object detection is a computer technology related to computer vision and image processing that deals
with a combination of object classification and object positioning. The advent of modern advances in deep
learning [1-3] has led to significant advances in object detection. Most recent research focused on designing a
complex network for object detection based on neural network to enhance accuracy, such as single shot detector
(SSD) [4] and faster R-CNN [5].
Many researchers are devoted to developing a computer technology and deep learning in the modern
life for ít outstanding advantages. Convolutional neural networks (CNNs) applied on the dataset of image data
(especially lung X-ray) [3] for classification of pneumonia disease and the result was obtained an accuracy rate
of 97%. The AlexNet’s deep convolutional neural network used as a pre-trained neural network with
1000 categories for image classification [6] to detect and geotag advertisement billboard in real-time condition,
and experimental results achieved 92.7% training accuracy for advertisement billboard detection. By using
convolutional neural networks, Z. Rustam, et al., [7] proposed the method to assist doctors in providing the
appropriate beliefs and predictions to patients, the results showed the capability of CNNs method to accurately
identify the patient's X-ray test images. According to the results published in [8], the CNNs model uses
64x64 input shape, 0.0001 learning rate, 3x3 filter size, epoch 100 count, data training 160, and data testing
40, the accuracy level of training and testing in classification of golek puppet image attained 100% accuracy.
This is an ideal result that demonstrates the effectiveness of using CNNs method in object classification. An

TELKOMNIKA Telecommun Comput El Control 
Applying convolutional neural networks for limited-memory application (Xuan-Kien Dang)
245
application of transfer learning by using CNNs method based on the inception-v3 architectural model [9] for
early detection of terry’s nail. The accuracy obtained with training data 90%, precision and memory, each of
which is worth 95.24%, 100%, and 90.91%. Specially, we introduce you only look once (YOLO), a unified
model for object detection. The YOLO model [10] is simple to construct and can be trained directly on full
images. Unlike classifier-based approaches, fast YOLO is the fastest general-purpose object detector in the
literature and YOLO pushes the state-of-the-art in real-time object detection, to do so YOLO generalizes well
to new domains making it ideal, fast, robust object detection for applications that rely on. However, all of the
algorithms require a large amount of resources of the system, and to put them on limited hardware devices
needs to be streamlined and compiled into limited hardware.
Related to ensure the maritime safety, the main objective constitutes the following two tasks as follow:
the first is ensuring the safety of life and property at sea from the geographic and operational hazards
(underwater obstacles, collision, harms and damages caused by the unfavorable weather conditions) and the
second is ensuring the safety of ship control throughout the journey by the sailer, if during an emergency
situation, a navigational officer is not capable of handling that situation, it can lead to maritime collision. For
the first task, there are many studies to improve, upgrade current systems that have shortcomings in regard to
availability, integrity, monitoring and system life expectancy as the global navigation satellite system [11] and
the regional satellite augmentation system for maritime applications [12], or the design of satellite constellation
for Indonesian maritime surveillance using the AIS data acquisition by LAPAN-A2 and LAPAN-A3
satellites [13] with the eight satellites in an equatorial orbit for near real-time AIS monitoring in Indonesia and
the other equatorial region make a better global maritime awareness and ensuring the maritime safety. The
second task, to design and manufacture systems serving ships to ensure safety in ship operation process by
using new computer technonogies as neural network, fuzzy-neural, or genetic algorithm.
In this paper, we aimed to apply the modified SSDLite_MobileNetV2 bounded CNN algorithm to
bridge navigational watch & alarm system (BNWAS), extensive experiments showed that the proposed method
can achieve the state-of-the-art results compared with the best current method based on hand crafted
features [14] and three other related CNN based methods [15-17] and our previous work [18] for image
analysis. Moreover, we have validated the rationality and robustness of the proposed model with more
supplementary results. The inverted residual bottleneck layers allow a particularly memory-efficient
implementation which is very important for mobile applications. A standard efficient implementation of
inference that were used for instance Tensor Flow [19] or Caffe [20] built a directed acyclic compute hyper
graph G. With a small hardware system, we used the SSD Lite MobileNetV2 structure because it was fast and
accurate. Not only were the requirements for image processing, object detection and classification met, the
system also abode by IMO [21, 22], IEC [23] and [24, 25] regulations which could be tested and directly
operated on board. We carefully designed a new CNN based method for detecting various typical
image-processing operations, the main contributions of this paper are given as follow:
− We first converted the input image into residuals to suppress the influence of image contents, and then used
a convolutional layer to increase the channel number.
− We employed six similar layer groups to obtain the high-level features of the input image.
− Finally, we applied the resulting features into the full connect layer for classification of the system, we
proposed a solution to always maintain the boundary of the total memory capacity in the following robust
bound and applied on the BNWAS.
The rest of the paper is organized as follows; section 2 shows some related works and proposed the
method reducing memory while ensuring image quality for object detection and section 3 describes the
structure of the proposed BNWAS based on convolutional neural networks, presents the experimental results
and discussions. Finally, the concluding remarks are given in section 4.
2. CNNs BASED SSD LITE-MOBILE NET METHOD FOR OBJECT DETECTION WITH
LIMITED-MEMORY
CNN models are highly accurate, but they all have a common drawback that is they are not suitable
for mobile applications or embedded systems with low power computing. In literature review, the authors
in [26] introduce resource-frugal quantized convolutional neural networks to reduce their size without
adversely affecting the classification capability for segmenting hyperspectral satellite images, especially
focusing on the memory savings of quantized CNNs. Moreover, an approach using object class clustering to
lower bit precision beyond quantization limits proposed by Prateeth Nayak, et al. [27] used 3 schemes, which
are uniform-ASYMM, uniform-SYMM, and power-of-2. The result is all of quantization scheme achieved near
original model accuracy for every tested model.
If you want to develop these models for real-time applications, you need an extremely powerful
configuration (GPU/CPU) for embedded systems (raspberry Pi, nano PC) or applications running on
smartphones. Therefore, we need to build a model like SSDLite-MobileNet hybrid. The main factor will help

 ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 19, No. 1, February 2021: 244 - 251
246
SSD Lite-Mobile Net achieve high accuracy while low computation time lies in the hybrid structure from SSD
and MobileNet structure. SSD (single shot multi box detector) is an object detector (Figure 1) that performs
two main steps: extract feature maps of features (feature maps) and apply convolution filters (convolution
filters) to detect objects.
Figure 1. Structure of single shot multi box detector used to detect a navigational officer
The loss function [3]:
𝐿(𝑥, 𝑐, 𝑙, 𝑔) =
1
𝑁
(𝐿𝑐𝑜𝑛𝑓(𝑥, 𝑐) + 𝛼𝐿𝑙𝑜𝑐(𝑥, 𝑙, 𝑔)) (1)
The loss function consists of two terms: 𝐿𝑐𝑜𝑛𝑓 and 𝐿𝑙𝑜𝑐where N is the matched default boxes. Matched default
boxes:
𝐿𝑙𝑜𝑐(𝑥, 𝑙, 𝑔) = ∑ ∑ 𝑥𝑖𝑗
𝑘
𝑚∈{𝑐𝑥,𝑐𝑦,𝑤,ℎ}
𝑁
𝑖∈𝑃𝑜𝑠 𝑠𝑚𝑜𝑜𝑡ℎ𝐿1(𝑙𝑖
𝑚
− 𝑔
̂𝑗
𝑚
) (2)
where 𝑔
̂𝑗
𝑐𝑥
= (𝑔𝑗
𝑐𝑥
− 𝑑𝑖
𝑐𝑥
)/𝑑𝑖
𝑤
,𝑔
̂𝑗
𝑐𝑦
= (𝑔𝑗
𝑐𝑦
− 𝑑𝑖
𝑐𝑦
)/𝑑𝑖
ℎ
, 𝑔
̂𝑗
𝑤
= 𝑙𝑜𝑔(
𝑔𝑗
𝑤
𝑑𝑖
𝑤) and 𝑔
̂𝑗
ℎ
= 𝑙𝑜𝑔(
𝑔𝑗
𝑤
𝑑𝑖
𝑤); 𝐿𝑙𝑜𝑐 is the
localization loss which is the smooth 𝐿 loss between the predicted box and the ground-truth box parameters.
This loss function is similar to the one in Faster R-CNN. 𝐿𝑐𝑜𝑛𝑓 is the confidence loss which is the softmax loss
over multiple classes confidences (c). (α is set to 1 by cross validation).
𝐿𝑐𝑜𝑛𝑓(𝑥, 𝑐) = − ∑ 𝑥𝑖𝑗
𝑝
𝑙𝑜𝑔( 𝑐̂𝑖
𝑝
) − ∑ 𝑙𝑜𝑔( 𝑐̂𝑖
0
)
𝑖∈𝑁𝑒𝑔
𝑁
𝑖∈𝑃𝑜𝑠 (3)
where: 𝑐̂𝑖
𝑝
=
𝑒𝑥𝑝(𝑐𝑖
𝑝
)
∑ 𝑒𝑥𝑝(𝑐𝑖
𝑝
)
𝑝
; 𝑥𝑖𝑗
𝑝
= {1,0} is an indicator for matching i-th default box to the j-th ground truth box
of category P. If m default maps are used for prediction, we suggest the form the scale of the default boxes
for each feature map is computed as:
max min
min ( 1), [1, ]
1
k
s s
s s k k m
m
−
= + − 
− (4)
Based on [24], we set parameter 𝑠𝑚𝑖𝑛 is 0.2 and 𝑠𝑚𝑎𝑥 is 0.9 (sk is 0.1, 0.2, 0.375, 0.55, 0.725. 0.9 means 30,
60, 112.5, 165, 217.5, 270 pixels input image (300x300)).
The structure contains a completely original convolution layer with 32 filters and 19 layers of
bottleneck. MobileNetV2 detailed structure is described by M. Sandler [25]. The inverted residual bottleneck
layers allow the system to have a particularly efficient memory, which is very important for applications. A
standard efficient implementation of inference is used in Tensor Flow [19] or Caffe [20]. The computation is
scheduled to minimize the total number of tensors that needs to be stored in memory. In most general cases, it
searches over all plausible computation orders Σ(G) and picks the minimum one.
𝑀(𝐺) = 𝑚𝑖𝑛
𝜋∈∑(𝐺)
𝑚𝑎𝑥
𝑖∈1..𝑛
[∑ |𝐴|
𝐴∈𝑅(𝑖,𝜋,𝐺) ] + 𝑠𝑖𝑧𝑒(𝜋𝑖) (5)

247
where: R(i, π, G) is the list of intermediate tensors that are connected to any of πi. . . πn nodes, |A| represents the size
of the tensor A, and size(πi) is the total amount of memory needed for internal storage during operation i. For graphs
that have only trivial parallel structure (such as residual connection), there is only one nontrivial feasible
computation order, and thus the total amount and a bound on the memory M(G) needed for inference on
compute graph G can be simplified:
𝑀(𝐺) = 𝑚𝑎𝑥
𝑜𝑝∈𝐺
[∑ |𝐴| + ∑ |𝐵| + |𝑂𝑃|
𝐴∈𝑂𝑃𝑜𝑢𝑡
𝐴∈𝑂𝑃𝑖𝑛𝑝
] (6)
Following [25], the amount of memory is simply the maximum total size of combined inputs and
outputs across all operations. It means we recognize that if we treat a bottleneck residual block as a single
operation (and treat inner convolution as a disposable tensor), the total amount of memory would be dominated
by the size of bottleneck tensors, rather than the size of tensors that are internal to bottleneck (and much larger).
In a Tensor Flow graph, each node has zero or more inputs and zero or more outputs, and represents the
instantiation of an operation. Values that flow along normal edges in the graph (from outputs to inputs) are
tensors, arbitrary dimensionality arrays where the underlying element type is specified or inferred at
graph-construction time. For small applications, reducing memory while ensuring image quality is great.
However, when we abuse this, it can easily lead to instability in image processing, such as reducing image
quality, which relates to the marginal limit of total memory capacity. In this paper, we proposed a solution to
always maintain the boundary of the total memory capacity in the following robust bound of OP as (7) as
follows:
𝑜𝑝∈𝐺
[∑ |𝐴| + ∑ |𝐵| + ‖𝑜𝑝‖∞
𝐵∈𝑜𝑝𝑜𝑢𝑡
𝐴∈𝑜𝑝𝑖𝑛𝑝
] (7)
Similar with
𝑜𝑝∈𝐺
[∑ |𝐴| + ∑ |𝐵|
𝐵∈𝑜𝑝𝑜𝑢𝑡
𝐴∈𝑜𝑝𝑖𝑛𝑝
] + ‖𝑜𝑝‖∞ (8)
Then, for hybrid SSD and MobileNetV2, we replaced all regular convolutions with separable
convolutions in the SSD network's predictive classes [2] to reduce the number of parameters and help the model
decrease the amount of total memory capacity as showed in (8) but still maintain the boundary of computing
steps. In particular, the output is labeled with the object and the confidence level is in percentage terms. In the
experiments of this paper, the improved SSD-Mobile Net V2 method also showed higher efficiency than the
method of [25] especially when applied to the BNWAS.
3. APPLYING CNNs TO DESIGN THE BRIDGE NAVIGATIONAL WATCH AND ALARM
SYSTEM
3.1. BNWAS design based on regulations of IMO MSC. 128 (75)
In recent years, it is known that ships usually perform under the complexity and vulnerability of
environment, so that the challenge of ship development remains an problem of significant advancements from
researchers. They have been paid attention to study of ship [27-30] to meet the IMO standards. Recently, the
authors [18] have studied and applied the modified SSDLite_MobileNetV2 hybrid algorithm to BNWAS by
using the hardware based on raspberry Pi-3 to meet the requirements of IMO MSC. 128 (75) and SOLAS
Chapter V, Reg.19 MSC. 282 (86) [23] revised on June 5, 2009 [20] valid for ships classified by size:
− July 2011: new vessels in excess of 150 tonnes.
− July 2011: all passenger vessels.
− July 2012: all vessels in excess of 3,000 tonnes.
− July 2013: all vessels between 500 and 3,000 tonnes.
− July 2014: all vessels between 150 and 500 tonnes.
BNWAS is a monitoring and Alarm system which notifies other officers or captains if the officer on
watch (OOW) does not respond or he/she is incapable of performing the watch duties efficiently which can
lead to maritime accidents. The system monitors the awareness of the officer of the watch (OOW) and
automatically alerts the Master or another qualified OOW if for any reason the OOW becomes incapable of
performing duties. This is achieved through a mix of alarms and indications which alert backup OOWs as well
as the Master. BNWAS warnings are given in the case of incapacity of the watchkeeping officer due to
accidents, sickness or in the event of a security breach, e.g. piracy and/or hijacking. Unless decided by the
Master only, the BNWAS shall remain operational at all times.

 ISSN: 1693-6930
248
Outputs of the system should be available for connection of additional bridge visual indications,
audible alarms and remote audible alarms as in [9]. The applied to the actual system design in Figure 2 (a) and
designing diagram is shown in Figure 2 (b). The connected computer works in tandem with raspberry Pi-3
(plays the role of the central processing board on Figure 2 (b) to collect input and output data of the testing
process. Hardware is designed to perform alarm functions.
To compare the effectiveness of the solution with other applications based on hardware and practical
conditions in the bridge of the Saigon Millennium Ship, we deployed four solutions to get results. In this work,
we focused on two factors, including processing speed and output reliability to apply object detectors on the
designed system by using the modified SSDLite_MobileNetV2 bounded CNN algorithm.
220V
AC
24V
DC
CAMERA BUTTONS COMPUTER
MOTION
SENSOR
HISTORY DATA ALARM DEVICES
TOUCH SCREEN
MAIN CONTROL SYSTEM
(RASPI 3B+ USING TENSORFLOW API)
CONTROL
VIA INTERNET
(a) (b)
Figure 2. The designed BNWAS GTS.V1 system tested on HCM City University of Transport;
(a) BNWAS-GTS.V1 system tested on HCM City University of Transport, and (b) Structure of designed BNWAS
3.2. Testing the designed BNWAS on Saigon Millennium Vessel in Saigon River
The image has been recorded from Saigon Millennium ship at Son Hai Shipyard, Ho Chi Minh City,
Vietnam. This image is captured through the logitech C270 camera and processed by hybrid network-based
object identification algorithms SSD-Mobile Net V2. The output is the processed image extracting the detected
object frame and the reliability calculated as a percentage. With the technique used in this paper, the system
can identify many officers in the bridge and the maximum number of accesses to the detection frame is 20
people at a time. When identifying officers in the bridge, the system allows customized functions via the touch
screen or push-button on the bridge. Testing the designed BNWAS on Saigon Millennium Vessel in Saigon
River as belows:
− Case 1: if the system determines that there is no officer in the bridge, a timer will be turned on and the
countdown time will wait for the officer to appear. During the active timer period, the function of switch
modes and countdown timer are disabled. If during the countdown, there is an officer in the bridge
(no physical impact is needed on the system), the timer is reset and the system returns to its normal state,
officers can operate and use the system function keys.
− Case 2: if no officer returns and the timer has counted to zero (timeout), a flash warning signal will be
activated in the bridge; this stage is called the primary alarm stage. This signal can be seen anywhere in the
bridge and in accordance with IMO standards. On the display screen, the alarm level will appear, and all
system parameters will be saved to the history file, then a next timer is started to move to the next alarm
stage. Subsequent alarm tests are tested and the final results are consistent with IMO requirements. Not
only did the system recognize the officer presence in the bridge, it also analyzed the officers' actions and
issued warnings when they found officers standing still for too long or sleeping while on duty. In
experiment, the test detected an officer who sat in silence for too long or showed signs of drowsiness as in
Figure 3.
The test was recorded when we asked an officer to sit silently on the driver's seat (at least 20 seconds)
to see whether the officer stands still for too long or has a drowsiness. At the same time, an underground
running counter will analyze the relative position of the officer and give a relative error. Based on the results
of each frame analysis, after 20 seconds, if the relative position error does not exceed 10%, the primary alarm
is set and the next alarm timer will start counting down.

249
(a) (b)
Figure 3. Testing the designed BNWAS on Saigon Millennium Vessel in Saigon River;
(a) testing no alarm stage, and (b) testing alarm stages
3.2. Summary experimental results
Highly configurable models running on TITAN X GPUs produced processing speeds between 17 and
37 frames per second. However, when experimenting on COCO data sets and mAP calculations on all object
classes, the results only reached 21-28%. Experimental results on processing speed on system were tested
directly on the bridge with normal working conditions and the results were shown high performance from
76-97% as in Table 1.
Table 1. Testing performance results of 4 models in experimental
Model name
Test on GPU TITAN X Test on Raspberry Pi 3B+
Speed (ms) COCO (mAP) Speed (FPS) Real time on bridge (mAP)
ssd_mobilenet_v1_coco 30 21 1.05 76
ssd_mobilenet_v2_coco 31 22 0.83 94
ssdlite_mobilenet_v2_coco 27 22 1.08 86
faster_rcnn_inception_v2_coco 58 28 0.08 97
This impressive result is achieved when installing the camera in the bridge in a convenient position
while the hardware is a mobile device with only ARM CPU and no integrated GPU. The highest processing
speed is only approximately 1 FPS. The discuss of the experimental results focus more detail in Table 1. The
result showed that 4 models tested on our hardware (raspberry Pi 3B+) using our method better than GPU
TITAN X hardware (difference hardware) about speed (ms) and mAP. So that, the FPS speed of the test
methods is indicated in Figure 4 and this is a good response rate for a monitoring system.
The output reliability is highest when tested with the faster RCNN detector, however with 0.08FPS
(about 12.5 seconds to process a frame) it is not possible to meet on a monitoring system. Object detectors
based on the SSD_MobileNet structure (in brown color) produce highly reliable results and meet processing
speed requirements. Meanwhile, the result of SSD_MobileNetV1 (yellow) and SSD_MobileNetV2 (green) sets
are almost equivalent, but the load time of the model is slow due to large capacity and actual output. There are
still certain deviations. Thus, the improved SSDLite_MobileNetV2 solution gives good results relating to
quality, processing speed, fast model load time (stable running on raspberry PI-3) and has higher accuracy than
the other solutions.
(a) (b)
Figure 4. The FPS speed of the test methods; (a) compare processing speed of object detectors on BNWAS
hardware and (b) compare the output reliability of object detectors on BNWAS hardware

 ISSN: 1693-6930
250
4. CONCLUSION
In this paper, we studied and applied the modified SSDLite_MobileNetV2 bounded CNN algorithm
to BNWAS-GTS.V1. The hardware was designed based on raspberry Pi-3, an embedded single board computer
with CPU smartphone level, limited RAM without CUDA GPU. Experimental results on processing speed on
BNWAS-GTS.V1 were tested directly on the bridge with normal working conditions. This impressive result
was achieved when installing the camera in the bridge in a convenient position while the hardware used a
mobile device. The improved SSD-Mobile Net V2 based on bounded CNN algorithm also showed higher
efficiency especially when applied to the BNWAS.
ACKNOWLEDGEMENTS
This study was supported by the Applied Basic Research Program of Ministry of Transport of Vietnam
DT18408 (2018), DT203036 (2020) and the Start up and Innovation Center of Ba Ria-Vung Tau, Viet Nam.
REFERENCES
[1] A. Krizhevsky, et al., “Imagenet classification with deep convolutional neural networks,” Communications of the
ACM, vol. 60, no. 6, pp. 1097-1105, 2012.
[2] W. Liu, et al., “Ssd: Single shot multibox detector,” Lecture Note in Computer Vision-ECCV, pp. 21-37, 2016.
[3] Zuherman Rustam, et al., “Pulmonary rontgen classification to detect pneumonia disease using convolutional neural
networks,”.TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 18, no. 3, pp. 1522-1528, 2020.
[4] Chengcheng Ning, et al., “Inception Single Shot Multibox Detector for Object Detection,” IEEE International
Conference on Multimedia & Expo Workshops (ICMEW), pp. 549-554, 2017.
[5] S. Ren, et al., “Faster r-cnn: To-wards real-time object detection with region proposal networks,” IEEE Transactions
on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 2017.
[6] R. Rahmat, et al., “Advertisement billboard detection and geotagging system with inductive transfer learning in deep
convolutional neural network,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 17,
no. 5, pp. 2659-2666, 2019.
[7] Z. Rustam, et al., “Pulmonary rontgen classification to detect pneumonia disease using convolutional neural networks,”
TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 18, no. 3, pp. 1522-1528, 2020.
[8] Tuti P., et al., “Image classification of golek puppet images using convolutional neural networks algorithm,”
International Journal of Advances, vol. 11, pp. 34-45, 2019.
[9] Muhamad. Y, et al., “Application of transfer learning using convolutional neural network method for early detection
of terry’s nail,” Journal of Physics: Conference Series, vol. 1201, pp. 1-9, 2019.
[10] Joseph Redmon, et al., “You Only Look Once: Uniﬁed, Real-Time Object Detection,” IEEE Conference on Computer
Vision and Pattern Recognition, pp. 779-788, 2015.
[11] Dimov Stojce Ilcev, “Architecture of the global navigation satellite system for maritime applications,”
TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 18, no. 3, pp. 1600-1609, June 2020.
[12] Dimov Stojce Ilcev, “Architecture of the regional satellite augmentation system for maritime applications,”
TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 18, no. 3, pp. 1610-1620, June 2020.
[13] M. Mukhayadi, et al., “ Designing a constellation for AIS mission based on data acquisition of LAPAN-A2 and
LAPAN-A3 satellite,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 17, no. 4,
pp.1774-1784, August 2019.
[14] Xian-Bao, et al., “Solar Cells Surface Defects Detection Based on Deep Learning,” Pattern Recognit. Artif. Intell.
vol. 27, pp. 517-523, 2014.
[15] Simonyan K., et al.,. “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Computer Vision
and Pattern Recognition, pp.1409-1556, 2014.
[16] Hong S., et al., “Lightweight Deep Neural Networks for Real-time Object Detection,” The 1st International
Workshop on Efficient Methods for Deep Neural Networks, pp. 1-7, 2016.
[17] Hunt M. A., et al., “Optimizing automatic defect classification feature and classifier performance for post,”
Proceedings of the 2000 IEEE/SEMI Advanced Semiconductor Manufacturing Conference and Workshop,
pp. 116-123, 2000.
[18] Dang Xuan Kien, et al., "Applying Hybrid Convolutional Neural Networks for Image Processing to Bridge
Navigational Watch & Alarm System," Journal of Transportation Science and Technology, pp. 47-53, no. 32, 2019.
[19] M. Abadi, et al., “TensorFlow: Large-scale machine learning on heterogeneous systems,” arXiv:1603.0446,
pp. 1-19, 2015.
[20] Yangqing Jia, et al., “ Caffe: Convolutional architecture for fast feature embedding,” Proceedings of the 22nd ACM
international conference on Multimedia, pp. 675-678, 2014.
[21] IMO MSC.128(75), “Performance Standards for a Bridge Navigational Watch Alarm System (BNWAS),” 2002.
[22] IMO A.1021(26), “Code on Alerts and Indicators,” 2009.
[23] IEC 62616, “Maritime Navigation and Radio Communication Equipment and Systems- Bridge Navigational Watch
Alarm System (BNWAS),” 2010.
[24] 19IMO MSC.282(86), “Chapter V, Reg,” 2009.

251
[25] Mark Sandler, et al., “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proc. IEEE Conference on
Computer Vision and Pattern Recognition, pp. 4510-4520, 2018.
[26] Jakub Nalepaa, et al., “Towards resource-frugal deep convolutional neural networks for hyperspectral image
segmentation,” Microprocessors and Microsystems, vol. 73, pp. 1-14, 2020 .
[27] Prateeth Nayak, et al., ” Bit Efficient Quantization for Deep Neural Networks” EMC2-NeurIPS Workshop, pp.1-5, 2019.
[28] Xuan Kien Dang, et al., “Analyzing the sea weather effects to the ship maneuvering in Viet Nam sea from Binh
Thuan province to Ca Mau province based on Fuzzy control method,” TELKOMNIKA Telecommunication
Computing Electronics and Control, vol. 16, no. 2, pp. 533-543, 2018.
[29] Viet Dung Do, et al.," Optimal control for dynamic positioning system based on Fuzzy-PSO advanced technical,"
TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 16, no. 6, pp. 2999-3007, 2018.
[30] Viet Dung Do, et al., "The fuzzy particle swarm optimization algorithm design for dynamic positioning system under
unexpected impacts," Journal of Mechanical Engineering and Sciences (JMES), vol. 13, pp. 5407-5423, 2019.
BIOGRAPHIES OF AUTHORS
Xuan-Kien Dang received Ph.D. degree in Control Science and Engineering, Huazhong
University of Science and Technology in June 2012. He is serving as the Director of Graduate
School, Ho Chi Minh City University of Transport, Vietnam. He has been awarded the Best
Paper Award in the 4th
Conference of Science and Technology, Ho Chi Minh City University
of Transport (2018), the President Prize for Award Winner of The Excellent Paper of the 17th
Asia Maritime & Fisheries Universities Forum (2018). His current research interests focus on
Control Theory, Automation, Maritime Technology, Underwater Vehicles, Optimal and
Robust Control, and Networked Control System. He has been serving as an Association
executive committee member of Vietnam Automation Association (VAA).
Huynh-Nhu Truong received Master's degree in Automation, Ho Chi Minh City University
of Transport, Viet Nam, 2011. She was recognized as a Ph.D. student of Automation and
Control Engineering, Ho Chi Minh City University of Transport, Vietnam, 2019. She is the
Principal of Ba Ria-Vung Tau College of Technology, Vietnam. Mrs. Nhu’s current research
focuses on the areas of Control Theory, Automation, and Underwater Robotic.
Viet-Chinh Nguyen received Bachelor's degree in Electrical and Electronic Engineering in
Ho Chi Minh City University of Technology, Viet Nam. He is studying the Master’s degree in
Automation and Control Engineering, Ho Chi Minh City University of Transport, Viet Nam.
His current research interests focus on Control Theory, Automation and Deep Learning.
Thi-Duyen-Anh Pham now is a Teacher of English at Ho Chi Minh University of Transport.
She graduated from University of Social Sciences and Humanities in 2012 with a degree in
English Linguistics and Literature and completed her Master’s Degree (MA) in Teaching
English to Speakers of Other Languages (TESOL), Victoria University, Australia, in 2016.
Her research has focused on English for Maritime and Maritime Safety.

Applying convolutional neural networks for limited-memory application

More Related Content

What's hot (18)

Similar to Applying convolutional neural networks for limited-memory application (20)

More from TELKOMNIKA JOURNAL (20)

Recently uploaded (20)

Applying convolutional neural networks for limited-memory application