IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING

Air pollution is a common cause of health risks and also a cause of
climate change, one of the most threatening problems to humans. This problem
results from the abundance of automobiles, industrial production, and
combustion of transportation and electricity generation petroleum products.
Therefore, forecasting air pollution is necessary. In this paper, a system is
proposed to monitor the level of air pollution by integrating the Internet of
Things(IoT) with Wireless Sensor Networks (WSN), where pollution levels are
observed in three areas in Baghdad using different types of sensors connected
with ESP32 (It is the name of the chip developed by Espressif Systems) to detect
Particulate Matter (PM2.5 and PM10), Nitrogen Oxides (NOx), Carbon
monoxide (CO) as well as temperature and humidity to monitor indoor and
outdoor air quality. Observed results are monitored by ThingSpeak, an open-
source IoT platform. Success has been achieved using the ESP32
microcontroller, as the project is low-cost and uncomplicated, and pollutant
measurement is accurate compared to the natural proportions of pollutants.
Data display is easy and it can be monitored easily. This encourages the
improvement of the model and its use in other monitoring systems.

Due to the fact that the risk factor in the international border is very high, it
causes threats affecting soldiers’ lives, border military facility and state security. In fields
where there are difficulties for people to go or where human life may be endangered
(such as places that contain the harmful gases and explosive things). Human guards may
be substituted by a robot system that is designed for the purpose of taking care of the
dangerous tasks of surveillance. The main objective of this paper is to build an intelligent
surveillance robot with high accuracy to detect intrusions, easy to use and inexpensive.
This paper includes a new contribution by integrating intelligent algorithms into
monitoring systems and robotics technology, which is a strong addition to the research
through the accuracy of the system. The system provides a modern monitoring method for
detecting and recognizing faces using a robot equipped with a pi camera, sensors and a
control panel. The result of the proposal is a system that uses face detection and recognition by utilizing HAAR algorithm, and CNN algorithm, the system percentage accuracy becomes 99.87%.and the loss is 0.013. The proposed have high accuracy, effective, easy to use, with low cost, can be used to guard critical infrastructures, large facilities, and national borders.

The automation of medical systems is one of the most important topics and that takes
the highest priority in our time due to the COVID-19 pandemic, which has caused human
disasters without knowing the exact diagnosis of patients and other diseases. Therefore, it has
been recently started to rely on sensors to support medical results and monitor the patient
throughout the day, and this in itself is an application of Internet of Things (IoT) which is called
Internet of Medical Things (IoMT). The expansion and reliability of this type of systems need to
secure the systems, infrastructure, devices and used sensors. This paper focuses on the proposal
key to encrypt the data stored in the database by relying on artificial intelligence algorithms
and Bezier curves based on the dynamic number generated in the medical platform as an input
to it. The Particle Swarm Optimization (PSO) algorithm was chosen because it is fast to
implement and to support limited devices within the used network. Also, the logistic map
function was used to generate the randomness of the generated key. The proposed key has also
been examined and it has passed the five randomness tests and succeeded in 13 out of 16 tests
within the NIST tests.

Covid-19 is a deadly virus that has spread worldwide, causing millions of deaths. Chest X-ray is one of the most common methods of diagnosing the infection of Covid - 19. Therefore, this paper has presented an efficient method to detect Covid-19 through X-rays of the chest area through a Neural convolution network (CNN). the proposed system has used a convolution neural network to classify the extracted features. Since CNN needs a set of data defined for training and testing, the proposed method used a public dataset of 350 pneumonia x-ray images, 300 viral images, and 350 normal images for evaluation. Besides, the proposed work achieved a satisfactory accuracy of 95% based on the X-ray image.

Digitally, a large number of information was generated, stored and exchanged. This growth leads to problems that needed to solve. Digital watermarking has been one of the key terms to secure and authenticate the owner's information. The watermarking image technology is a procedure for embedding secret data into an original image. In this paper, encrypted holographic watermark image was proposed by using chaotic technique, which utilizing three distinct chaos maps: logistic, Arnold and Baker; to ensure the security to the system. Performance evaluation of embedding and decrypted Watermark image measured by Peak to signal ratio (PSNR), Structural Similarity (SSIM), Mean square error (MSE), Root mean square (RMSE), and Normalize Root mean square (NRMSE). Results and outcomes of measurements confirmed the robustness of the chaotic technique and also the Histogram showed the good distribution of the encrypted holographic image pixels and observed that the encrypted holographic image in bit are significantly uniform and different from that of the Watermark image that mean the encryption image in bit interleaver is change the level values and position of pixel and also good similarity SSIM about 0.9 for both test 1 and 2.

Lung cancer is one of the most fatal cancers in the world for both genders. It has a high mortality rate compared to other types of cancer. Early detection can save lives and enhance the treatment process. As a result, the demand for approaches to detect cancer at an early stage is growing. In this paper, an Artificial Neural Network (ANN) model is developed to identify the level of having lung cancer based on environmental, diagnostic, and statistical factors. The features that highly affect the risk level of lung cancer were identified. The model\'s performance was assessed using a variety of criteria, including accuracy, precision, recall, and f-measure. Experimental results show that the model attains a high accuracy rate of 91.79% and risk factors like obesity, alcohol use, genetic risk, and coughing of blood can lead to lung cancer.

Auto-Correction is the process of correcting a misspelled word typed by the user as an application of automated translation process. lip-reading is the process of recognizing the words through processing and observing the visual lip movement of a speaker's talking without any audio input. Although visual information itself cannot be considered as enough resource to provide normal speech as intelligibility, it may succeed with several cases especially when the words to be recognized are limited. Auto-correction is a trail to diminish the number of errors that can be generated by lip reading systems and to improve their accuracy, many error-correction techniques were visualized. In this paper an auto- correction model is proposed to correct the misspelled words recognized by a lip reading system, the output of a lip reading system is subjected to auto-correction model to enhance the accuracy of the system. The auto-correction model is based on levenshtien distance and dictionary lookup with a proposed dataset. The proposed model achieved accuracy of more than 67% enhancing the lip reading system by almost 30%.

Designing an efficient irrigation system is a crucial issue in agriculture, due to water scarcity problem around the world with the need of increasing agricultural production to satisfy the demands of the enlargement of population. Therefore, to design a smart irrigation system, a real monitoring of field's information that affects the watering status is required which can be achieved with Wireless Sensor Networks (WSN). In this paper, an irrigation system based WSN is proposed to save water, power, labor, and as a result, saving cost with production and profit increase. Sensor nodes collect field data to be sent to the Raspberry pi, as a main controller, to make optimal decisions about irrigation process. The field data includes the sensor readings of temperature and soil moisture. Crop evapotranspiration is also considered; thus, the required amount of water is estimated with a particular irrigation time to avoid over irrigation that hurts the plants growth and yields quality. The obtained results show the efficiency of the proposed system operation and controlling on the irrigation process. These results are taken for tomato plant as a case study. The monitoring tools are used to verify the suggested algorithm effectiveness in irrigation scheduling.

Task scheduling is one of the very crucial facets of cloud computing. The task scheduling method must assign jobs to virtual machines. In cloud computing, task scheduling includes a frontal influence on a system's resource utilization and operational costs. Diverse meta-heuristic algorithms, in addition to their modifications, have been developed to improve the efficiency of task executions in the cloud. In this paper, a multiobjective optimization model is applied using the metaheuristics cuckoo search optimization algorithm (MCSO) to enhance the performance of a cloud system with limited computing resources while minimizing the time and cost. Finally, we analyze the performance of the proposed MCSO with the existing methods, such as Bee Life Algorithm (BLA), A Time-Cost aware Scheduling (TCAS) algorithm, Modified Particle Swarm Optimization (MPSO), and Round Robin (RR), for the evaluation metrics makespan and cost. Based on the outcomes of the experiments, it can be inferred that the proposed MCSO provides essential schedule jobs with the shortest makespan and average cost.

Many companies recognize the importance of cloud computing all around the world. However, various worries keep businesses from adopting cloud computing. Data security, privacy, and trust difficulties are among them. Recently, there have been rapid developments in the progression of cloud computing services. This paper focuses on the design and implementation of the secure cloud services framework by providing secure and trusted storage for user data. Proposed framework generated an encryption key based on a chaotic map generator and encrypted user data. proposed work shows that integration of key with defensive options is more efficient than approaches from those categories of using external keys. A test has been applied on the frame work in cloud slime services and show the effectiveness of the proposed solution to provide secure cloud services. Our model of cloud services show valid ad promising performance with multiple users trail.

In the last few years, many applications have viewed great development, such as smart city applications, social media, smartphones, security systems, etc. In most of these applications, facial recognition played a major role. The work of these applications begins by locating the face within the image and then recognizing the face. The circumstances surrounding the person at the moment of taking the picture greatly affect the accuracy of these applications, especially the inappropriate lighting. Therefore, the stage of preparing the images is very important in the work. To solve this problem, we proposed a system that combines the use of gamma and Histogram Equalization algorithm (HE) to improve the images before starting to detect the face using the Viola-Jones. Then extract the facial features and identify the person using convolutional neural networks. The proposed system achieved a very small error rate and an accuracy during training that reached 100%.