Border Trespasser Classification Using Artificial Intelligence تصنيف المتعدي على الحدود باستخدام الذكاء الاصطناعي Border Trespasser Classification Using Artificial Intelligence Border Trespasser Classification Using Artificial Intelligence Border Trespasser Classification Using Artificial Intelligence

Monitoring the border is a very important task for national security. Wireless sensor networks (WSN) appear well suited in this application. This work aims to monitor a large-scale geographical framework that represents the borders of countries. Researchers take the Tunisian Algerian border as an example. This border is labeled by the illegal passage of intruders between the two countries. The task is to identify the intruders and study their kinematics based on speed, acceleration, and bearing. The appropriate types of sensors are determined according to the nature of intruders. Six classification techniques are compared which are: Naïve Bayes, Support Vector Machine (SVM), Multilayer Perceptron, Best First Decision Tree (BF-Tree), Logistic Alternating Decision Tree (LAD-Tree), and J48. The comparison of the performance of the classification techniques is provided in terms of correct differentiation rates, confusion matrices, and the time taken to build each model. Four different levels of cross-validation are used to validate the classifiers. The results indicate that J48 has achieved the highest correct classification rate with a relatively low model-building time. مراقبة الحدود هي مهمة مهمة جدا للأمن القومي. تبدو شبكات المستشعرات اللاسلكية (WSN) مناسبة تمامًا في هذا التطبيق. يهدف هذا العمل إلى رصد إطار جغرافي واسع النطاق يمثل حدود الدول. يأخذ الباحثون الحدود التونسية الجزائرية كمثال. تم وضع علامة على هذه الحدود من خلال المرور غير القانوني للمتسللين بين البلدين. وتتمثل المهمة في تحديد المتسللين ودراسة حركيتهم على أساس السرعة والتسارع والحمل. يتم تحديد الأنواع المناسبة من أجهزة الاستشعار وفقًا لطبيعة الدخلاء. تتم مقارنة ست تقنيات تصنيف وهي: نايف بايز، آلة متجه الدعم (SVM)، بيرسبترون متعدد الطبقات، أفضل شجرة قرار أول (BF - Tree)، شجرة القرار المتناوب اللوجستي (LAD - Tree)، و J48. يتم توفير مقارنة أداء تقنيات التصنيف من حيث معدلات التمايز الصحيحة ومصفوفات الارتباك والوقت المستغرق لبناء كل نموذج. يتم استخدام أربعة مستويات مختلفة من التحقق المتبادل للتحقق من صحة المصنفات. تشير النتائج إلى أن J48 قد حققت أعلى معدل تصنيف صحيح مع وقت بناء نموذج منخفض نسبيًا. Monitoring the border is a very important task for national security. Wireless sensor networks (WSN) appear well suited in this application. This work aims to monitor a large-scale geographical framework that represents the borders of countries. Researchers take the Tunisian Algerian border as an example. This border is labeled by the illegal passage of intruders between the two countries. The task is to identify the intruders and study their kinematics based on speed, acceleration, and bearing. The appropriate types of sensors are determined according to the nature of intruders. Six classification techniques are compared which are: Naïve Bayes, Support Vector Machine (SVM), Multilayer Perceptron, Best First Decision Tree (BF-Tree), Logistic Alternating Decision Tree (LAD-Tree), and J48. The comparison of the performance of the classification techniques is provided in terms of correct differentiation rates, confusion matrices, and the time taken to build each model. Four different levels of cross-validation are used to validate the classifiers. The results indicate that J48 has achieved the highest correct classification rate with a relatively low model-building time. Surveiller le border is a very important task for national security. Wireless sensor networks (WSN) appear well suited in this application. This work aims to monitor a large-scale geographical framework that represents the borders of countries. Researchers take the Tunisian Algerian border as an example. This border is labeled by the illegal passage of intruders between the two countries. The task is to identify the intruders and study their kinematics based on speed, acceleration, and bearing. Les types appropriés de capteurs sont déterminés conformément à la nature des intruders. Six classification techniques are compared which are : Naïve Bayes, Support Vector Machine (SVM), Multilayer Perceptron, Best First Decision Tree (BF-Tree), Logistic Alternating Decision Tree (LAD-Tree), and J48. The comparison of the performance of the classification techniques is provided in terms of correct differentiation rates, confusion matrices, and the time taken to build each model. Four different levels of cross-validation are used to validate the classifiers. The results indicate that J48 has achieved the highest correct classification rate with a relatively low model-building time. Monitoring the border is a very important task for national security. Redes de sensores inalámbricos (WSN) appear well suited in this application. This work aims to monitor a large-scale geographical framework that represents the borders of countries. Researchers take the Tunisian Algerian border as an example. This border is labeled by the illegal passage of intruders between the two countries. The task is to identify the intruders and study their kinematics based on speed, acceleration, and bearing. The appropriate types of sensors are determined according to the nature of intruders. Six classification techniques are compared which are: Naïve Bayes, Support Vector Machine (SVM), Multilayer Perceptron, Best First Decision Tree (BF-Tree), Logistic Alternating Decision Tree (LAD-Tree), and J48. The comparison of the performance of the classification techniques is provided in terms of correct differentiation rates, confusion matrices, and the time taken to build each model. Los cuatro niveles diferenciales de validación cruzada se usan para validar a los clasificadores. The results indicate that J48 has achieved the highest correct classification rate with a relatively low model-building time.