Periodicals of Engineering and Natural Sciences (PEN - International University of Sarajevo)
Not a member yet
1290 research outputs found
Sort by
Enhancing artificial intelligence in advanced database systems for Baghdad\u27s urban transportation management
Get PDFThe issue of transportation in Iraqi cities, particularly Baghdad, is multifaceted and intricate, largely due to the horizontal expansion that puts pressure on services and exacerbates traffic congestion and bottlenecks. The ever-growing population and lack of regulation regarding vehicle imports further compound the situa-tion, making urban transportation in Iraq a challenging problem to address. The digital revolution has ush-ered in a new era of civilization, marked by significant advancements in communication technology and information systems. This transformation has led to the widespread adoption of communication and infor-mation technology in various sectors, including transportation management. However, the successful im-plementation of digital transportation initiatives requires the collection and organization of extensive data, which is then used to develop graphic and visual software technology, create communication networks, and define new functions for visual and audio files. In this digital age, transportation management has evolved into an interdisciplinary field that leverages the insights from various scientific domains to develop and pro-duce digital maps. The primary objective of digital organization is to recreate reality in a virtual environ-ment, enabling the manipulation of images and the seamless integration of locations beyond geographical boundaries.
 
Road conditions monitoring using semantic segmentation of smartphone motion sensor data
Get PDFMany studies and publications have been written about the use of moving object analysis to locate a specific item or replace a lost object in video sequences. Using semantic analysis, it could be challenging to pinpoint each meaning and follow the movement of moving objects. Some machine learning algorithms have turned to the right interpretation of photos or video recordings to communicate coherently. The technique converts visual patterns and features into visual language using dense and sparse optical flow algorithms. To semanti-cally partition smartphone motion sensor data for any video categorization, using integrated bidirectional Long Short-Term Memory layers, this paper proposes a redesigned U-Net architecture. Experiments show that the proposed technique outperforms several existing semantic segmentation algorithms using z-axis accelerometer and z-axis gyroscope properties. The video sequence\u27s numerous moving elements are syn-chronised with one another to follow the scenario. Also, the objective of this work is to assess the proposed model on roadways and other moving objects using five datasets (self-made dataset and the pothole600 da-taset). After looking at the map or tracking an object, the results should be given together with the diagnosis of the moving object and its synchronization with video clips. The suggested model\u27s goals were developed using a machine learning method that combines the validity of the results with the precision of finding the necessary moving parts. Python 3.7 platforms were used to complete the project since they are user-friendly and highly efficient platforms
Image hiding in audio file using chaotic method
Get PDFIn this paper, we propose an efficient image hiding method that combines image encryption and chaotic mapping to introduce adaptive data hiding for improving the security and robustness of image data hiding in cover audio. The feasibility of using chaotic maps to hide encrypted image in the high frequency band of the audio is investigated. The proposed method was based on hiding the image data in the noisiest part of the audio, which is the high frequency band that was extracted by the zero crossing filter. Six types of digital images were used, each of size fit the length of used audio, this to facilitate the process of hiding them among the audio samples. The input image was encrypted by a one-time pad method, then its bits were hid-den in the audio by the chaotic map. The process of retrieving the image from the audio was in the opposite way, where the image data was extracted from the high frequency band of the audio file, and then the ex-tracted image was decrypted to produce the retrieved image. Four qualitative metrics were used to evaluate the hiding method in two paths: the first depends on comparing the retrieved image with the original image, while the second depends on comparing the audio containing the image data with the original audio once, and another time by comparing the cover audio with the original audio. The results of the quality metrics proved the efficiency of the proposed method, and it showed a slight and unnoticed effect between the re-search materials, which indicates the success of the hiding process and the validity of the research path
Experimental and numerical analysis of the asymmetric flat rolling process of square section bars
Get PDFThis paper analyzed the asymmetric flat rolling process of square section bars by testing experiments and finite element simulation methods. The impacts of the rate of roll diameter, decrease in altitude, and rota-tional speeds of the rolls on the width of cross-section and the curl radii at the leaving point of deformation for the brass and aluminum bar materials were investigated. Furthermore, the asymmetric rolling process of square section bars was simulated using ABAQUS commercial software. A great convergence was demon-strated among the findings forecasted by the FEM simulation and the experimental findings. It was found that by increasing the rate of rolling diameter, the curl radius and the width of the bar cross-section at the exit have been increased, and the roll speed has a insignificant impact on the width and the curl radius of the rolled bar. 
The effect of independent audit quality on the quality of financial reporting in the listed companies in Tehran and Baghdad stock exchanges
Get PDFThe primary purpose of this research is to investigate the relationship between the quality of the external audit and the quality of the financial reporting done by companies that are traded on the Tehran and Bagh-dad Stock Exchanges. The experience of the auditor in the sector, the auditor\u27s reputation, and the auditor\u27s length of service were utilized as determining factors for the quality of the external audit. In order to deter-mine whether or not the reporting of financial data can be trusted, discretionary accruals are analyzed. The companies that are members of the Tehran Stock Exchange and the Baghdad Stock Exchange make up the statistical population for the current study. They were chosen using the process of systematic elimination, which was applied to 102 firms that were admitted to the Tehran Stock Exchange and 35 companies that were admitted to the Baghdad Stock Exchange. In order to examine the data, multiple regression analyses were performed. According to the findings of the study, the quality of financial reporting at the Baghdad Stock Exchange is not significantly impacted by the standard of external auditing. In addition, the independ-ence of the Tehran Stock Exchange\u27s financial reporting is directly and considerably impacted by the quality of the audits conducted by external parties. The findings, taken as a whole, suggested that in order for enter-prises to function properly in Iraq they need a secure and politically stable environment. This, in turn, has an effect on the accuracy of the reports they provide. On the other hand, the profession of auditing in Iraq is still in its formative stages, and auditors need to have a deeper understanding of their respective industries
Artificial intelligence: A review of the scientific literature in Scopus
Get PDFArtificial intelligence (AI) has revolutionized conventional work methods in all areas of knowledge. The aim of this study is to analyze the current state of research in this field. To this end, a systematic review was carried out with a bibliometric approach that included analysis of the distribution of scientific production by year, the most relevant sources, Bradford\u27s Law to identify the main sources, the most prominent authors, Lotka\u27s Law to analyze the productivity of authors and the author\u27s "h" index. Through the review of the scientific literature available in the Scopus database, 609 relevant results were identified, of which 414 were articles in Spanish. A total of 205 articles were selected as the final publication of the study and 113 of them were open access. The empirical studies demonstrate that AI presents both opportunities and ethical and social challenges, especially in areas such as health, communication, law and artistic practices. In healthcare, AI can improve patients\u27 quality of life. In journalism, AI streamlines the production of objective news and helps reduce misinformation, although it also poses ethical and professional challenges. In the field of law, AI offers opportunities to improve efficiency in judicial decision-making and legal work, but it also brings ethical and legal considerations. It is therefore essential to strike a balance between harnessing the benefits of AI and protecting rights, privacy and ethics in each of these fields, in order to maximize its potential for the benefit of society
FQMaP: Towards a framework quantitative management of processes in small software development organizations
Get PDFSoftware development organizations need to control and improve their practices, seeking to reduce variability when executing the necessary processes to elaborate software; therefore, these organizations implement improvement plans to identify factors that affect the processes. Quantitative Management deals with identification, tracing, and control of those incident factors, using data proactively to predict performance and the effect of possible changes in a process. Reference models in software processes development such as CMMI V2.0 and ISO/IEC 33061:2021 address Quantitative Management, but are aimed at big enterprises. Other models such as MoProSoft, COMPETISOFT, and MPS.BR are aimed at small enterprises, but do not include enough elements on Quantitative Management. Execution of a systematic literature review permitted searching for works on Quantitative Management intended for small software development enterprises, indicating necessary practices and how to perform them. This search showed that a proposal is not available that incorporates Quantitative Management practices for software processes aimed small software development enterprises. The referred aspects make it difficult to adopt a Quantitative Management culture within these organizations, it which has become a problem, consisting in that small software development enterprises that do not execute quantitative management practices will have difficulty identifying and focusing on the factors that impact the process performance and, therefore, on the results of their projects. This work sought to tackle this problem by proposing the “framework for quantitative management of processes in small software development organizations” (FQMaP), which allows incorporating practices and techniques that support Quantitative Management of software development processes in these kinds of enterprises. From the evaluation of FQMaP, carried out by following Focus Group technique guidelines, it can be demonstrated that it is a simple proposal and with elements that can serve a company to quantitatively manage software development processes. Also, it has clearly specified its components, showing that its structure is familiar with other process patterns, that would facilitate their interpretation
Exploring the relationship between knowledge management and core competencies to improve universities success in Jordan: Testing the mediating effect of employee engagement
Get PDFStrong job results require a lot of work and assistance from many people, particularly when it comes to aca-demic accomplishment. Therefore, the justification for this research is that success at universities involves knowledge, effort, and significant academic engagement. To encourage change and success in universities. Also, it is crucial to possess the necessary skills even when achieving this goal. Therefore, this research seeks to explain the relationship between knowledge management, core competencies, and university suc-cess with employee engagement as mediating. The data was gathered from ten Jordanian public universities. was also chose respondents were chosen using convenience sampling, and the data, which included respons-es from 365 respondents, were analyzed using the Partial Least Squares (PLS) modeling technique. The results of the research found that knowledge management and core competencies are significantly influ-enced by employee engagement and organizational success. Moreover, employee engagement has a signifi-cant relationship with organizational success. More importantly, the analysis revealed that employee en-gagement plays a mediating role between knowledge management, core competencies, and organizational success. Top management must begin planning the changes required to meet the demands of knowledge management and core competencies while also capitalizing on opportunities to improve organization success and employee engagement
Machine learning methods based on mammogram images to estimate survival times for breast cancer patients
Get PDFEstimating survival times based on medical images resulting from radiological imaging of some parts of the body affected by tumors and making a predictive system for them is considered one of the very important fields at the present time. This is because radiological imaging is one of the first and most important stages of medical diagnosis. Therefore the process of linking medical images including them within the work steps of the statistical analysis for estimating survival times is a modern and important topic. Its importance is helping doctors and medical specialists to determine the influencing factors and risk percentage associated with survival for each patient based on the medical image of the affected part.In this paper, the medical images extracted from the mammogram device for breast cancer patients in Iraq. These images were included in the machine learning method for estimating survival of patients. Based on two methods to extract features, The first one is the Fast independent component algorithm (Fast ICA algo-rithm) and the second one is Nonnegative Matrix Factorization (NMF algorithm). With two machine learn-ing algorithms, The first method is Random survival forests algorithm and the second method is support vector machine algorithm SVM (SVM).Through the application of the supervised machine learning method on mammogram images of patients with breast cancer, it was found that the best model for estimating survival according to the mean square error (MSE) and concordance index (C-Index) criterion is the model resulting from the use of the Fast ICA algo-rithm with the random survival forest algorithm compared with the other three models. Accordingly, It is recommended that interested medical agencies and institutions to adopt this model
Crowd counting using Yolov5 and KCF
Get PDFCrowd detection has various applications nowadays. However, detecting humans in crowded circumstances is difficult because the features of different objects conflict, making cross-state detection impossible. Detec-tors in the overlapping zone may therefore overreact. In this paper, real-time people counting is proposed using a proposed model of the YOLOv5 (You Only Look Once) algorithm and KCF (kernel correlation fil-ter) algorithm. The YOLOv5 algorithm was used because it is considered one of the most accurate algo-rithms for detecting people in real time. Despite the high accuracy of the YOLOv5 algorithm in detecting the people in the image, video or real-time camera capturing, it needs an increase in speed.For this reason, the YOLOv5 algorithm was combined with the KCF tracking algorithm. Where the YOLOv5 algorithm identifies people to be tracked by the KCF. The YOLOv5 algorithm was trained on a database of people, and the system\u27s accuracy reached 98%. The speed of the proposed system was in-creased after adding the KCF