IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING

Traffic incidents dont only cause various levels of traffic congestion but
often contribute to traffic accidents and secondary accidents, resulting in substantial loss of
life, economy, and productivity loss in terms of injuries and deaths, increased travel times
and delays, and excessive consumption of energy and air pollution. Therefore, it is essential
to accurately estimate the duration of the incident to mitigate these effects. Traffic
management center incident logs and traffic sensors data from Eastbound Interstate 70 (I-
70) in Missouri, United States collected during the period from January 2015 to January
2017, with a total of 352 incident records were used to develop incident duration estimation
models. This paper investigated different machine learning (ML) methods for traffic
incidents duration prediction. The attempted ML techniques include Support Vector
Machine (SVM), Random Forest (RF), and Neural Network Multi-Layer Perceptron (MLP).
Root mean squared error (RMSE) and Mean absolute error (MAE) were used to evaluate
the performance of these models. The results showed that the performance of the models
was comparable with SVM models slightly outperforms the RF, and MLP models in terms
of MAE index, where MAE was 14.23 min for the best-performing SVM models. Whereas,
in terms of the RMSE index, RF models slightly outperformed the other two models given
RMSE of 18.91 min for the best-performing RF model.

The technology has been growing rapidly in the form of portable wireless devices that
can perform multiple functions to cope with the state-of-the-art technology and synchronization. A
total device capacity must be increased to accommodate new wireless applications. This can be
achieved by leveraging new technologies, with higher data rates. Spectrum pooling has gained
immense popularity, with increased demand for frequency range and bandwidth availability
constraints. Statistics suggest that much of the spectrum licensed is not used all the time. Because of
the transmitter's nonlinearity nature, the large (peak to average power ratio (PAPR)) phenomenon is
a drawback in orthogonal frequency division multiplexing (OFDM). Several hybrid approaches have
recently been implemented to minimize PAPR's high value, at the expense of increasing the level of
computational complexity in the system. In this paper, a new hybrid approach has been introduced in
parallel to combine the selective mapping approach (SLM) with the partial transmit sequence (PTS)
approach to improve the efficiency of PAPR reduction with lower numerical method complexity. The
findings reveal that the OFDM systems with the proposed hybrid approach have better efficiency in
terms of PAPR elimination, side-information, and computational complexity compared to current
hybrid methods. Also, a hybrid approach proposed output could be maintained without degradation.

X-ray is electromagnetic wave pass through all human tissue and show tissue image by black and
white, and the explosion for x ray in short treatment may cause cancer, Photonic crystal fiber used
as detector for x- ray approximate effective radiation dose for human bone for spine x- ray 1.5 mSv
which need 6month to repeat the exposure and extremity (foot, hand and etc.) x-ray 0.001 mSv need
to 3 hours to repeat exposure , the change in x ray dose can be detected by measuring the change in
wavelength shifting of laser 450nm which pass through photonic crystal fiber and effected by the
emission of x-ray to record the small change in x-ray dose and save the human from radiation and
this sensor is small compact and easy to use and have high sensitivity for x -ray used to measure the
bone x-ray as its value lower than other x-ray used in others tissue.

The Microwave oven is a system used to convert the electromagnetic
energy to thermal energy when the microwave cavity is loaded with a dielectric
material. The ordinary microwave ovens are not supported with complex
features for detecting parameters such as temperature, weight, and loaded
material availability. Due to the lack of material availability, several laboratory
and industrial applications require these features to switch off the oven. The
reflections of electromagnetic radiation inside an empty microwave oven lead to
oven damage. An overview of the microwave oven characteristics and
emergence of electromagnetic radiation inside a microwave oven is presented
in this study. The parameters measured inside the microwave oven, methods for
power attenuation in a microwave oven, microwave power detector, and
microwave oven leakage are discussed as well. Moreover in the methodology of
this work, proposed a new technique based on the measurement of leaked
microwave power to control the microwave oven. The preliminary results
showed that the leakage measurement of electromagnetic power changes with
the state/phase of the material inside the microwave oven, which ensured the
possibility of the proposed promising technique. This work will be continued to
connect the microwave oven with a spectrum analyzer and computer via
hardware and software interfaces depending on the methodology of this article.
A computer code will be developed to read the measured power and
automatically switch off the microwave oven depending on materials state.

It is well known that the Wireless Sensor Network (WSN) is a part of different fields of
modern life (self-managing life). The automation of operating the WSN without any need for
human efforts develops the technique used in this network in terms of power consumption, costs,
and so on. In this paper, the WSN application that adopts the self-managing property is presented
as well as applying this property in a greenhouse as a case study. It uses remote controlling
technology for data exchanging in a multi-layer WSN. Different hardware and software
equipment have been employed in the application based on self-managing techniques. Such
hardware includes (NodeMCU ESP8266) as a microcontroller, Raspberry pi3 as a base station
that captures the sensor reading from the node. Additionally, it was utilized two types of sensors
(DS18B20, soil moisture) to sense the environmental parameters such as temperature and soil
moisture and two actuators (LED1, LED2). The results show the proper performance of the
presented WSN in terms of the self-managing side by checking the received data in real-time
mode. These results are achieved for the threshold values of 25ᵒC temperature and 500 soil
moisture as an upper level for operating the actuators.

Recently, video files and images have became the dominant media
material for transmitting or storing across different applications that are used by
different people. So, there was a serious need to find more effective and efficient
video compression techniques to reduce the large size of such multimedia files. This
paper proposes SIMD based FPGA lossless JPEG video compression system with the
facility of scalability. Generally, the proposed system consists of a software side and
a hardware side. The digital video file is prepared to be processed by the hardware
side frame by frame on the software side. The hardware side is proposed to consist of
two main processing circuits, which are the prediction circuit for calculating the
predicted value of each pixel in the certain frame and the encoding circuit that was
represented by a modified RLE (Run-Length-Encoder) to encode the result obtained
through subtracting the predicted value from the real value for each pixel to produce
the final compressed video file. The compression ratio obtained for the proposed
system is equal to 1.7493. The throughput improvement for the two and four
processing units basing on SIMD architecture was 100 MP/s and 200 MP/s,
respectively. The clock results showed that the number of clocks required had become
50% and 25% when using two processing units and four processing units,
respectively, from the number of clocks using single processing units.

Generally, pattern recognition considered a strong challenge in
many information processing research fields. The aim of this paper is to
propose a highly accurate model for recognizing a handwritten English
numeral through efficiently extracting the most valuable features of a certain
handwritten numeral or digit. The handwritten English Numerals Recognition
Model (HENRM) is proposed in this paper. The features extraction of the
proposal based on combining both statistical and structural features of the
certain numeral sample image. Mainly, the proposed HENCM has four phases
which are image acquisition, image preprocessing, features extraction, and
classification. In fact, four feature extraction approaches are utilized in this
paper, which are the number of intersection points, the number of open-end
points, calculation of density feature, and determining the chain code for each
of the English numerals. The latter phase gives a features vector of 26-element
size to be fed into the classifier that uses the Multi-class Support Vector
Machine (MSVM) for the classification process. The experimental results
showed that the proposed HENCM exhibits an average recognition rate equals
to 97%.