[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120579-en":3,"doc-seo-120579-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120579,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Anomaly Detection of Memory Leaks Using Machine Learning - Research-Based Thesis","This thesis applies machine learning to detect memory leaks in Linux-based software systems. Memory leaks cause programs to fail to release allocated memory, leading to gradual performance degradation and reduced stability, particularly in long-running and resource-constrained environments. An automated, lightweight, and scalable solution is designed for integration into industrial monitoring systems. Python-based simulations create time-series datasets of RAM usage, CPU load, and Resident Set Size (RSS), which train a neural network to recognize abnormal memory usage patterns from OS process-level metrics, enabling real-time non-intrusive detection.","Anomaly Detection of Memory Leaks Using Machine Learning  \nResearch-Based Thesis  \nRoman Kuznetcov  \nThesis  \nDegree Program Machine Learning and Data Engineering  \nBachelor of ICT  \nAuthor Supervisor Commissioned by Title of Thesis Number of pages  \nRoman Kuznetcov Year 2025  \nAnssi Ylinampa Wenzel Ingomar  \nAnomaly Detection of Memory Leaks Using Machine Learning 29  \nThis thesis focuses on using machine learning to detect memory leaks in Linux-based software systems. Memory leaks, which occur when programs fail to release allocated memory, gradually degrade performance and stability, especially in long-running or resource-limited environments. The goal was to design an automated, lightweight, and scalable solution suitable for integration into industrial monitoring systems such as those used at Festo.  \nTo achieve this, Python programs were written to simulate both normal and leaky memory behaviour in a controlled Linux environment. These programs generated time-series datasets containing key system parameters, including RAM usage, CPU load, and Resident Set Size (RSS) . The collected data was pre-processed and used to train a neural network capable of identifying abnormal memory usage patterns. This approach avoided direct source code analysis, relying instead on process-level operating system metrics, making it suitable for embedded or restrictedaccess systems.  \nThe results demonstrated that the trained model successfully distinguished between normal and leak-induced memory behaviour with high accuracy. Even in the presence of noise and workload fluctuations, the neural network reliably detected gradual, anomalous increases in memory usage. These outcomes confirmed the feasibility of using machine learning for real-time, non-intrusive memory leak detection and established a foundation for further development of intelligent system monitoring tools.  \nKey Words: Memory Leaks, System Performance, Embedded Systems, Anomaly Detection, Machine Learning, RAM, Linux.  \nCONTENTS  \n1 INTRODUCTION .................................................................................................................................... 4  \n2 BACKGROUND AND RESEARCH .............................................................................................................. 8  \n2.1 Data Collection and System Monitoring ........................................................................................... 8  \n2.2 Simulating a Memory Leak .............................................................................................................. 8  \n2.3 Pre-processing the Data.................................................................................................................. 9  \n2.4 Building the Machine Learning Model ............................................................................................. 9  \n2.5 Observations and Results ...............................................................................................................10  \n3 MEMORY LEAK PATTERNS AND DETECTION APPROACHES .....................................................................11  \n4 SIGNIFICANCE OF THE STUDY ...............................................................................................................14  \n5 HOW TO PREVENT MEMORY LEAKS ......................................................................................................16  \n5.1 Smart Coding Practices ..................................................................................................................16  \n5.2 Static and Dynamic Analysis Tools ..................................................................................................17  \n5.3 Memory Profiling and Monitoring ..................................................................................................17  \n6 MEMORY LEAK PATTERNS AND DETECTION APPROACHES .....................................................................18  \n6.1 Linear Growth Leaks ........","cbCaijznGtKxdBLX","https://ap.wps.com/l/cbCaijznGtKxdBLX","pdf",976298,1,29,"English","en",105,"# 1 INTRODUCTION\n# 2 BACKGROUND AND RESEARCH\n## 2.1 Data Collection and System Monitoring\n## 2.2 Simulating a Memory Leak\n## 2.3 Pre-processing the Data\n## 2.4 Building the Machine Learning Model\n## 2.5 Observations and Results\n# 3 MEMORY LEAK PATTERNS AND DETECTION APPROACHES\n# 4 SIGNIFICANCE OF THE STUDY\n# 5 HOW TO PREVENT MEMORY LEAKS\n## 5.1 Smart Coding Practices\n## 5.2 Static and Dynamic Analysis Tools\n## 5.3 Memory Profiling and Monitoring\n# 6 MEMORY LEAK PATTERNS AND DETECTION APPROACHES\n## 6.1 Linear Growth Leaks\n## 6.2 Stair-Step Leaks\n## 6.3 Cyclic Leaks\n## 6.4 Phantom Leaks\n## 6.5 Heap Fragmentation\n## 6.6 Detection Challenges and Machine Learning Solutions\n# 7 PRACTICAL ANALYSIS AND SOLUTIONS APPROACH AT FESTO\n## 7.1 Project Objective\n## 7.2 Data Generation Through Simulated Leaks\n## 7.3 Data Pre-processing and Model Building\n## 7.4 Results and Application\n# 8 CONCLUSIONS\n# 9 REFERENCES","[{\"question\":\"How does the thesis detect memory leaks in Linux-based systems?\",\"answer\":\"It trains a neural network to identify abnormal memory usage patterns using time-series OS process-level metrics such as RAM usage, CPU load, and RSS.\"},{\"question\":\"Why does the approach avoid direct source code analysis?\",\"answer\":\"The solution relies on operating system metrics rather than inspecting application code, making it suitable for embedded or restricted-access systems.\"},{\"question\":\"What simulation method was used to create training data?\",\"answer\":\"Python programs simulate normal and leaky memory behavior in a controlled Linux environment to generate datasets representing different memory leak characteristics.\"}]","Anomaly Detection of Memory Leaks Using Machine Learning - Research-Based Thesis | PDF",1785730748,73,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"anomaly-detection-of-memory-leaks-using-machine-learning-research-based-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/anomaly-detection-of-memory-leaks-using-machine-learning-research-based-thesis/120579/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the thesis detect memory leaks in Linux-based systems?","Question",{"text":75,"@type":76},"It trains a neural network to identify abnormal memory usage patterns using time-series OS process-level metrics such as RAM usage, CPU load, and RSS.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why does the approach avoid direct source code analysis?",{"text":80,"@type":76},"The solution relies on operating system metrics rather than inspecting application code, making it suitable for embedded or restricted-access systems.",{"name":82,"@type":73,"acceptedAnswer":83},"What simulation method was used to create training data?",{"text":84,"@type":76},"Python programs simulate normal and leaky memory behavior in a controlled Linux environment to generate datasets representing different memory leak characteristics.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]