{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4650"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4650","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Detecting Software Anomalies in Microservices Using Spectrograms, Scalograms, and Convolutional Neural Networks","abstract":"The growing complexity of cloud-native microservices has intensified the need for robust anomaly detection mechanisms, particularly for misconfiguration-induced failures that often manifest subtly and propagate across service boundaries. This thesis proposes a comparative framework for runtime anomaly detection by transforming system metrics into frequency-domain representations—spectrograms using Short-Time Fourier Transform and scalograms using Continuous Wavelet Transform—and classifying them with Convolutional Neural Networks (CNNs). Evaluated on DeathStarBench, a production-grade microservices benchmark with injected anomalies in the Reservation and Recommendation services, the framework also includes baseline Long Short-Term Memory (LSTM) models trained on raw time-series features. Stratified 5-fold cross-validation shows that CNNs trained on scalograms outperform all other models, achieving 98.54% accuracy, 98.53% F1-score, and a Matthews Correlation Coefficient (MCC) of 0.9628, compared to 84.76% accuracy and 85.10% F1-score for the best LSTM model (128×8). Scalograms also deliver superior class-wise F1-scores for both anomalies—0.9451 for A1 and 0.9276 for A2—highlighting their strength in capturing bursty and slowly varying patterns often missed by fixed-window spectrograms and temporal baselines. These findings support the hypothesis that wavelet-based representations offer enhanced sensitivity and robustness for detecting misconfigurations in dynamic, resource-constrained microservice environments, paving the way for future research in multi-resolution anomaly detection and real-time telemetry analysis.","abstract_html":"The growing complexity of cloud-native microservices has intensified the need for robust anomaly detection mechanisms, particularly for misconfiguration-induced failures that often manifest subtly and propagate across service boundaries. This thesis proposes a comparative framework for runtime anomaly detection by transforming system metrics into frequency-domain representations—spectrograms using Short-Time Fourier Transform and scalograms using Continuous Wavelet Transform—and classifying them with Convolutional Neural Networks (CNNs). Evaluated on DeathStarBench, a production-grade microservices benchmark with injected anomalies in the Reservation and Recommendation services, the framework also includes baseline Long Short-Term Memory (LSTM) models trained on raw time-series features. Stratified 5-fold cross-validation shows that CNNs trained on scalograms outperform all other models, achieving 98.54% accuracy, 98.53% F1-score, and a Matthews Correlation Coefficient (MCC) of 0.9628, compared to 84.76% accuracy and 85.10% F1-score for the best LSTM model (128×8). Scalograms also deliver superior class-wise F1-scores for both anomalies—0.9451 for A1 and 0.9276 for A2—highlighting their strength in capturing bursty and slowly varying patterns often missed by fixed-window spectrograms and temporal baselines. These findings support the hypothesis that wavelet-based representations offer enhanced sensitivity and robustness for detecting misconfigurations in dynamic, resource-constrained microservice environments, paving the way for future research in multi-resolution anomaly detection and real-time telemetry analysis.","abstract_has_math":false,"creators":["Jonnaikode, Snehith"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Joydeep Mukherjee","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:29Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2994","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2994","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4650","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Joydeep Mukherjee","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Jonnaikode, Snehith"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-05-26T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-04-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2994"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The growing complexity of cloud-native microservices has intensified the need for robust anomaly detection mechanisms, particularly for misconfiguration-induced failures that often manifest subtly and propagate across service boundaries. This thesis proposes a comparative framework for runtime anomaly detection by transforming system metrics into frequency-domain representations—spectrograms using Short-Time Fourier Transform and scalograms using Continuous Wavelet Transform—and classifying them with Convolutional Neural Networks (CNNs). Evaluated on DeathStarBench, a production-grade microservices benchmark with injected anomalies in the Reservation and Recommendation services, the framework also includes baseline Long Short-Term Memory (LSTM) models trained on raw time-series features. Stratified 5-fold cross-validation shows that CNNs trained on scalograms outperform all other models, achieving 98.54% accuracy, 98.53% F1-score, and a Matthews Correlation Coefficient (MCC) of 0.9628, compared to 84.76% accuracy and 85.10% F1-score for the best LSTM model (128×8). Scalograms also deliver superior class-wise F1-scores for both anomalies—0.9451 for A1 and 0.9276 for A2—highlighting their strength in capturing bursty and slowly varying patterns often missed by fixed-window spectrograms and temporal baselines. These findings support the hypothesis that wavelet-based representations offer enhanced sensitivity and robustness for detecting misconfigurations in dynamic, resource-constrained microservice environments, paving the way for future research in multi-resolution anomaly detection and real-time telemetry analysis."]},{"key":"dc:title","label":"Title","values":["Detecting Software Anomalies in Microservices Using Spectrograms, Scalograms, and Convolutional Neural Networks"]}]}],"canonical_facts":{"dc:contributor":["Joydeep Mukherjee","Computer Science","College of Engineering"],"dc:creator":["Jonnaikode, Snehith"],"dc:date.available":["2025-05-26T07:00:00Z"],"dc:date.created":["2025-04-01T07:00:00Z"],"dc:description.abstract":["The growing complexity of cloud-native microservices has intensified the need for robust anomaly detection mechanisms, particularly for misconfiguration-induced failures that often manifest subtly and propagate across service boundaries. This thesis proposes a comparative framework for runtime anomaly detection by transforming system metrics into frequency-domain representations—spectrograms using Short-Time Fourier Transform and scalograms using Continuous Wavelet Transform—and classifying them with Convolutional Neural Networks (CNNs). Evaluated on DeathStarBench, a production-grade microservices benchmark with injected anomalies in the Reservation and Recommendation services, the framework also includes baseline Long Short-Term Memory (LSTM) models trained on raw time-series features. Stratified 5-fold cross-validation shows that CNNs trained on scalograms outperform all other models, achieving 98.54% accuracy, 98.53% F1-score, and a Matthews Correlation Coefficient (MCC) of 0.9628, compared to 84.76% accuracy and 85.10% F1-score for the best LSTM model (128×8). Scalograms also deliver superior class-wise F1-scores for both anomalies—0.9451 for A1 and 0.9276 for A2—highlighting their strength in capturing bursty and slowly varying patterns often missed by fixed-window spectrograms and temporal baselines. These findings support the hypothesis that wavelet-based representations offer enhanced sensitivity and robustness for detecting misconfigurations in dynamic, resource-constrained microservice environments, paving the way for future research in multi-resolution anomaly detection and real-time telemetry analysis."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2994"],"dc:title":["Detecting Software Anomalies in Microservices Using Spectrograms, Scalograms, and Convolutional Neural Networks"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:29Z"}