[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126420-en":3,"doc-seo-126420-105":31,"detail-sidebar-cat-0-en-105":93},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126420,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Intelligent Detection Of Crime Anomalies In Smart Cities - Using Hybrid Machine Learning With Improved Segmentation And Feature Extraction Techniques","Urban population growth increases the difficulty of policing and monitoring high-crime areas, contributing to rising criminal activity and insecurity. Smart cities respond by integrating video surveillance for crime detection, yet officials face a large video-data backlog that can raise error rates. The proposed approach applies meta-heuristic optimization with hybrid machine learning to analyze video streams quickly and accurately. It uses video-to-frame preprocessing, optimized FCN semantic segmentation, SIFT and improved HOG feature extraction, Relief-based feature selection, and a transformer+SVM+ANN hybrid detector implemented in Python.","Metallurgical and Materials Engineering Research paper  \nIntelligent Detection Of Crime Anomalies In Smart Cities Using Hybrid MachineLearning  \nWith Improved Segmentation And Feature Extraction Techniques  \nAyush Singhal 1 Nidhi Tyagi2  \n1 Research Scholar, Department of Computer Science & Engineering, Shobhit Institute of Engineering &  \nTechnology,(NAAC Accredited Grade \"A\", Deemed to-be-University), Meerut (250110), India  \n2 Professor , School of Computational Sciences and Engineering Shobhit Institute of Engineering and Technology  \nAbstract  \nThe rise in population in urban areas has resulted in difficulties in policing and  \nmonitoring high-crime probability areas, leading to an increase in criminal activity  \nand insecurity. To enhance security, smart cities have integrated crime detection  \nsystems with videosurveillance as the standard method. The backlog of video data  \nthat must be monitored by supervising officials can lead to an increase in error rates.  \nTo address this issue, a proposed solution involves using meta-heuristic optimization  \nwith a Hybrid Machine Learning algorithm. This solution analyzes video stream data  \nquickly and accurately, facilitating the identification of criminal activity. This  \napproach is expected to improve the efficiency and effectiveness of video surveillance  \nsystems. The proposed method involves pre-processing the video data using  \ntechniques such as Video-to-Frame Conversion, Resizing, and Normalization,  \nfollowed by segmentation of the frames using an optimized Semantic Segmentation  \nOptimized FCN algorithm. Features are then extracted from the segmented regions  \nusing techniques such as SIFT and the proposed Improved Histogram of Oriented  \nGradients algorithm. The extracted features are refined using the new improved  \nRelief Algorithm for feature selection. Lastly, a new hybrid machine learning  \napproach is designed using a combination of transformer model, SVM, and ANN for  \ncrime anomaly detection. The proposedmethod is implemented using the Python  \nprogramming language.  \nKeywords: Support Vector Machine, Artificial Neural Network, FCN,SIFT, Crime  \ndetection, Improved Histogram of Oriented Gradients, Relief Algorithm.  \n1. INTRODUCTION  \nTechnologies for smart cities (SC) can deliver the right services to the needs of the populace. One of the primary enablers in a SC has IoT technology, that enables a large numberof devices to connect [1] . However, because of the varied form and complexity of anomalous events, recognising them automatically in a real-world situation is extremely challenging. Thisresearch effort presents an effective and robust approach for identifying anomalies in surveillance large video data using Artificial Intelligence of Things [2] . A critical and difficultproblem in IoT systems is anomaly detection because of the intricate structures and high- dimensional data they generate [3] . Anomalies are described as data structures that do not adhere to well-defined characteristics of typical data patterns.“An observation which deviates  \nso much from the other findings as to arouse doubts that it was generated by a different mechanism is the definition of an anomaly. [4][5] . To detect anomalous activities [6], It isnecessary to develop a computer vision-based technique that can effectively classify normaland abnormal events without the involvement of humans. In addition to being useful for monitoring, such an automated approach also minimizes the amount of human labour needed to maintain manual observation on a round-the-clock basis [7] .  \nIoT devices are widely used in smart cities due to the IoT's recent growth [8] . Real-world timeis used as the basis activities of a smart city are designed to enhances the efficiency and qualityof life in urban areas. Since the smart city network traffic through the IoT system is linked to sensors that are directly connected to huge cloud servers is growing quickly and posing new challenges for cyber-secur","cbCaicI5cq3AADyl","https://ap.wps.com/l/cbCaicI5cq3AADyl","pdf",546968,5,1,17,"English","en",105,"# Abstract\n# Introduction\n## Smart city enabling technologies and IoT role\n## Challenges of anomaly detection in surveillance data\n## Cybersecurity threats and the need for monitoring\n## Related work and proposed approach overview","[{\"question\":\"Why is anomaly detection difficult in smart-city IoT and video surveillance systems?\",\"answer\":\"Anomalous events have varied forms and complex structures, and IoT systems generate intricate, high-dimensional data, making automatic recognition extremely challenging.\"},{\"question\":\"What is the main goal of the proposed method in this research?\",\"answer\":\"The method aims to detect crime anomalies efficiently and accurately in large surveillance video data by combining preprocessing, segmentation, feature extraction, feature selection, and a hybrid machine learning detector.\"},{\"question\":\"How does the approach process video data before classification?\",\"answer\":\"It preprocesses videos using video-to-frame conversion, resizing, and normalization, then segments frames with an optimized Semantic Segmentation Optimized FCN algorithm.\"}]","Intelligent Detection Of Crime Anomalies In Smart Cities - Using Hybrid Machine Learning With Improved Segmentation And Feature Extraction Techniques | PDF",1785904968,43,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"intelligent-detection-of-crime-anomalies-in-smart-cities-using-hybrid-machine-learning-with-improved-segmentation-and-feature-extraction-techniques","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/intelligent-detection-of-crime-anomalies-in-smart-cities-using-hybrid-machine-learning-with-improved-segmentation-and-feature-extraction-techniques/126420/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why is anomaly detection difficult in smart-city IoT and video surveillance systems?","Question",{"text":77,"@type":78},"Anomalous events have varied forms and complex structures, and IoT systems generate intricate, high-dimensional data, making automatic recognition extremely challenging.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What is the main goal of the proposed method in this research?",{"text":82,"@type":78},"The method aims to detect crime anomalies efficiently and accurately in large surveillance video data by combining preprocessing, segmentation, feature extraction, feature selection, and a hybrid machine learning detector.",{"name":84,"@type":75,"acceptedAnswer":85},"How does the approach process video data before classification?",{"text":86,"@type":78},"It preprocesses videos using video-to-frame conversion, resizing, and normalization, then segments frames with an optimized Semantic Segmentation Optimized FCN algorithm.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]