The paper presents an innovative intrusion detection approach for Wireless Sensor Networks (WSNs) that integrates Machine Learning (ML) techniques with the Synthetic Minority Oversampling Technique Tomek Link (SMOTE-TomekLink) algorithm. This method addresses the challenges of low detection rates, computational overhead, and false alarms in existing intrusion detection methods for WSNs. By synthesizing minority instances and eliminating Tomek links, the proposed approach achieves a balanced dataset, significantly enhancing detection accuracy. The model also incorporates feature scaling through standardization to ensure input features are consistent and scalable, facilitating more precise training and detection. The effectiveness of the model is evaluated using the Wireless Sensor Network Dataset (WSN-DS) containing 374,661 records, achieving an accuracy rate of 99.78% in binary classification and 99.92% in multiclass classification. The research highlights the efficiency and superiority of the proposed model in WSN intrusion detection, making it a valuable tool for enhancing network security.The paper presents an innovative intrusion detection approach for Wireless Sensor Networks (WSNs) that integrates Machine Learning (ML) techniques with the Synthetic Minority Oversampling Technique Tomek Link (SMOTE-TomekLink) algorithm. This method addresses the challenges of low detection rates, computational overhead, and false alarms in existing intrusion detection methods for WSNs. By synthesizing minority instances and eliminating Tomek links, the proposed approach achieves a balanced dataset, significantly enhancing detection accuracy. The model also incorporates feature scaling through standardization to ensure input features are consistent and scalable, facilitating more precise training and detection. The effectiveness of the model is evaluated using the Wireless Sensor Network Dataset (WSN-DS) containing 374,661 records, achieving an accuracy rate of 99.78% in binary classification and 99.92% in multiclass classification. The research highlights the efficiency and superiority of the proposed model in WSN intrusion detection, making it a valuable tool for enhancing network security.