Iraqi Journal of Information and communication technology

Managing crowded areas is an extremely and difficult task. Several people might be injured or lost their lives every year because of the mal organization of the crowded areas. There are many regular crowded events where this problem continues and create social and personal upheaval, namely, if not resolved, perhaps destroy the image of the administrators and organizers. One such event is the anniversary pilgrimage Hajj, where Millions visit the holy site Makkah (mecca) in Saudi Arabia. Besides, other regular events attract much more participants .During hajj events, some of the pilgrims get lost and are unable to reach back to their places. Many techniques are used to track users in crowded areas, like Wi-Fi, Mobile networks, and RFID. In this article, we proposed an integrated management model to solve this problem. The proposed model is based on the web system that uses maps and location service, furthermore, use the IoT tools, particularly RFID Reader and Tag to track and monitor persons. This architecture system can be utilized to solve various challenges related to the management of the crowd in general and the management of pilgrims in particular. This model can be adapted also to any crowded event

Traffic signs object detection has gained high interest in recent years, as one of the most significant object detector applications. Where the development of deep learning technologies gives support to traffic signs detector which it offers several advantages, including the benefit of high detection precision and the timely response to condition changes of traffic signs. Therefore, this paper shows an efficient method for detecting traffic signs in real-time. Hence, it implements a new Iraqi Traffic Sign Detection Benchmark (IQTSDB) dataset based on Mask Region-based Convolutional Neural Network (Mask R-CNN) algorithm. The experimental results show that the implementation of the IQTSDB dataset with Mask R-CNN has high efficiency in different conditions such as sunny ,cloudy, weak light, and rainy conditions. Besides, real images were captured for the traffic signs in Baghdad and then compared to the German traffic signs (GTSDB). In addition, the results show that the IQTSDB dataset has a better performance than the GTSDB dataset based on the performance parameters training loss and mean Average Precision (mAP)

Recently, algorithms of machine learning are widely used in the field of electroencephalography (EEG)-Brain-Computer interfaces (BCI). In this paper, a sign language software model based on the EEG brain signal was implemented, to help the speechless persons to communicate their thoughts to others. The preprocessing stage for the EEG signals was performed by applying the Principle Component Analysis (PCA) algorithm to extract the important features and reducing the data redundancy. A model for classifying ten classes of EEG signals, including Facial Expression (FE) and some Motor Execution(ME) processes, had been designed. A neural network of three hidden layers with a deep learning classifier had been used in this work. Data set from four different subjects were collected using a 14 channels Emotiv epoc+device. A classification results with an accuracy of 95.75% were obtained for the collected samples. An optimization process was performed on the predicted class with the aid of the user, and then the signing class will be connected to the specified sentence under a predesigned lock-up table

This paper aims to create infrastructure-free networking capabilities for people in need such as when inadequate infrastructure including mobile cell towers and power supplies are damaged or when all communication means are restricted. In general, this means finding a way to communicate without mobile cell towers, repeaters, or Wi-Fi hotspots on mobile devices. This paper focuses on introducing an ad-hoc network based on Bluetooth where users can communicate without barriers. The proposed network implementation uses Google’s API Nearby Connection which is one of Google Play Services that can provide high bandwidth, low latency, encrypted data transfers between nearby devices in a fully-offline P2P mode. Kotlin language was used to program an application called Blue Emergency installed on Android devices to broadcast data as bytes payloads in a form of text messages from one node to all nodes in proximity using Bluetooth only. The test and verification of the system are performed showed that successful communication is achieved with the latest versions of both the Android operating system and Bluetooth. Finally, the designed network can be extended to cover large geographical areas by multi-hopping the messages between devices to make the system more efficient to use in the time of need