The Air Traffic Management system is a complex issue that faces factors such as Aircraft Crash Prevention, air traffic controllers pressure, unpredictable weather conditions, flight emergency situations, airplane hijacking, and the need for autonomy on the fly. agent-based software engineering is a new aspect in software engineering that can provide autonomy. agent-based systems have some properties such: cooperation of agents with each other in order to meet their goals, autonomy in function, learning and Reliability that can be used for air traffic management systems. In this paper, we first study the agent-based software engineering and its methodologies, and then design a agent-based software model for air traffic management. The proposed model has five modules .this model is designed for aircraft ,air traffic control and navigations aids factors based on the Belief-Desire-Intention (BDI) architecture. The agent-based system was designed using the agent-tool under the multi-agent system engineering (MaSE) methodology, which was eventually developed by the agent-ATC toolkit. In this model, we consider agents for special occasions such as emergency flights’ and hijacking airplanes in airport air traffic management areas which is why the accuracy of the work increased. It also made the flight’s sequence arrangement in take-off and landing faster, which indicates a relative improvement in the parameters of the air traffic management پرونده مقاله

شبکه خودسازمانده پويا با يادگيري نيمه‌ناظر در بسياري از کاربردها نظیر خوشه‌بندی داده‌ها کاربرد دارد. محاسبه پارامترهاي شبکه خودسازمانده شامل شکل و ساختار لايه خوشه‌بندی، سطح فعال‌سازی و وزن‌هاي لايه طبقه‌بندی از جمله مسایل چالش‌برانگیز و مهم آن است. راهکارهای ارائه‌شده فعلی از روش‌های ابتکاری و با یک نگاه محلی سعی در تعیین این پارامترها دارند که در اثر آن، نتایج این الگوریتم‌ها وابستگی بالایی به شرایط دارد. این مقاله یک روش یادگیری نیمه‌ناظر مبتنی بر شبکه خودسازمانده پویا و يادگيري حداکثري را برای اولین بار مورد بررسی قرار می‌دهد. روش پیشنهادی، بدون محاسبه مستقیم پارامترهای شبکه خودسازمانده پویا و با استفاده از روش یادگیری حداکثری، کلاس هر داده را تعیین می‌کند. خطای حاصل از بازخورد سیستم، هم در یادگیری حداکثری و هم در بهینه‌سازی شبکه خودسازمانده پویا مورد استفاده قرار می‌گیرد. در این مقاله، علاوه بر بررسی تحلیلی همگرایی روش پیشنهادی، روش حداکثری ترتیبی برای شبکه نیمه‌ناظر خودسازمانده پویا ارائه شده است. آزمایش‌های انجام‌شده بر روی داده‌های برخط و با برچسب جزئی نشان می‌دهند که روش پیشنهادی از نظر دقت، نسبت به روش نیمه‌ناظر خودسازمانده پویا برتری نسبی دارد. پرونده مقاله

Over the last few years, online training courses have had a significant increase in the number of participants. However, most web-based educational systems have drawbacks compared to traditional classrooms. On the one hand, the structure and nature of the courses directly affect the number of active participants; on the other hand, it becomes difficult for teachers to guide students in choosing the appropriate learning resource due to the abundance of online learning resources. Students also find it challenging to decide which educational resources to choose according to their condition. The resource recommender system can be used as a Guide tool for educational resource recommendations to students so that these suggestions are tailored to the preferences and needs of each student. In this paper, it was presented a resource recommender system with the help of Bi-LSTM networks. Utilizing this type of structure involves both long-term and short-term interests of the user and, due to the gradual learning property of the system, supports the learners' behavioral changes. It has more appropriate recommendations with a mean accuracy of 0.95 and a loss of 0.19 compared to a similar article. پرونده مقاله