iosr-JCE   Volume-25 ~ Issue-2 ~ Mar. - Apr. 2023

Abstract: Thyroid disorders are one of the most prevalent endocrine conditions worldwide. Identifying the presence and severity of abnormalities in thyroid patients is critical for diagnosis analysis as well as the treatment accurately provided. In the past recently years, deep learning strategies have gained widespread recognition for their potential to provide better solutions for complex medical diagnosis problems. This study helps in develop a strategy in deep learning that will help in analyze thyroid patient's abnormalities by analyzing their medical images. We collected medical images of thyroid patients from various sources and trained a deep convolutional neural network to identify abnormality patterns in these images. Our model achieved an accuracy of 90% on the test dataset.......

Key Word: Deep Learning, XGBoost Classification, Support Vector, Linear Regression, Logistic Discriminator, Multilayer Perceptron.

[1]. Khalid salman, Emrullah Sonuç. (2021). The Thyroid Disease Classification. Karabuk, Turkey.
[2]. Giuseppe Mollica, Daniela Francesconi, Gabriele Costa, Alqurashi. (2016). Classification of Thyroid disease using Deep Learning and Machine Learning. Perukia, Italy. [3]. Muhammad Hamid. (2022). Thyroid disease methology using machine learning and deepl learning. Dammam 31441, Saudi Arabia.
[4]. Rajasekhar Chaganti, Furqan Rustam, Isabel De La Torre Díez. (2022). Selective Feature and Machine Learning for Thyroid Classification Techniques. Toyota Research Institute, Los Altos, CA 94022, USA.
[5]. Zahrul Jannat Peya; Mst. Kamrun Naher Chumki; Khan Mihaddur Zaman. (2021). The Prediction of Thyroid Disease Diagnosis. Dhaka, Bangladesh.

Abstract: Considered to be the main means of human communication language. The language of worldwide communication, English is widely spoken around the world. Accent recognition is a significant issue in modern technology. Because of differences in their accents, even a speaker who is unfamiliar with the accent as familiar as the local speaker occasionally has trouble understanding. For the purpose of bridging these communication barriers, we have proposed a system to classify and transform speech between people caused by the individuality of their accents. We think machine learning can help with accent recognition. This research aims to increase spoken English accent recognition's precision. An innovative method of increasing the number of tactics by using Convolutional Neural Networks (CNN), which improves accuracy of accent classification. Additionally, English accent conversion refers to the process of changing one English accent into another so that the listener can comprehend the speaker's accent. Speech recognition and text-to-speech modules can aid with this.

Keywords: CNN, MFCC, Accent recognition, English accent conversion

[1]. Duduka, S., Jain, H., Jain, H.P.V. and Chawan, P.M., 2021. A Neural Network Approach to Accent Classification. International Research Journal of Engineering and Technology (IRJET), 8(03), pp.1175-1177.
[2]. Ensslin, A., Goorimoorthee, T., Carleton, S., Bulitko, V. and Hernandez, S.P., 2017, September. Deep Learning for Speech Accent Detection in Video Games. In Thirteenth Artificial Intelligence and Interactive Digital Entertainment Conference.
[3]. Singh, U., Gupta, A., Bisharad, D. and Arif, W., 2020. Foreign accent classification using deep neural nets. Journal of Intelligent & Fuzzy Systems, 38(5), pp.6347-6352.
[4]. Parikh, P., Velhal, K., Potdar, S., Sikligar, A. and Karani, R., 2020, May. English language accent classification and conversion using machine learning. In Proceedings of the International Conference on Innovative Computing & Communications (ICICC).
[5]. Bird, J.J., Wanner, E., Ekárt, A. and Faria, D.R., 2019, June. Accent classification in human speech biometrics for native and non-native english speakers. In Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to.

Abstract: There are grave security concerns as a result of the unusually high rate of crime and the increased number of offenders on the free.Crime prevention and criminal identification are police officer's main priorities since lives and property are on the line. Protection is the main focus of the police, although there aren't enough of them to really fight crime. Multiple special user and private locations have cameras installed for security and surveillance purposes, particularly CCTV, as a result of the development of security generation .The CCTV footage can be used to identify suspects present at the scene........

Keywords: CCTV, OpenCV, Crime Prevention, LBPH.

[1] Nurul Azma Abdullah, Md. Jamri Saidi and Nurul Hidayah Ab Rahman "Face recognition for criminal identification: An implementation of principal component analysis for face recognition "The 2nd International Conference on AppliedScience and Technology 2017 (ICAST'17)
[2] Apoorva.P, Ramesh.B and Varshitha.M.R "Automated criminal identification by face recognition using open computer vision classifiers" Third International Conference on Computing Methodologies and Communication (ICCMC 2019)
[3] Rasanayagam, K.Kumarasiri, S.D.D, Tharuka, W. A. D. Samaranayake, N. Samarasinghe and P. Siriwardana "CIS: An AutomatedCriminal Identification System".2018 IEEE International Conference on Information and Automation for Sustainability (ICIAfS)
[4] Mantoro, T., Ayu, M. A., & Suhendi. (2018)." Multi-access Recognition Process Using Haar Cascades and EigenfaceMethods" 2018 6th International Conference on Multimedia Computing and Systems (ICMCS).
[5] Chang L , Yang J, Li S, Xu H, Liu K & Huan, C. (2018). "Face Recognition Based on Stacked Convolutional Autoencoder and Sparse Representation". 2018 IEEE 23rd International Conference on Digital Signal Processing (DSP).

Abstract: Reliability metrics such as uptime, availability, and system performance are foundational benchmarks in distributed systems, cloud computing, and Site Reliability Engineering (SRE). These metrics serve as the foundation for Service Level Objectives (SLOs) and Service Level Indicators (SLIs), guiding the measurement and improvement of service reliability. The integration of Artificial Intelligence (AI) into this domain represents a transformative approach, leveraging predictive analytics, machine learning, and anomaly detection to address the complexities of modern distributed systems. This paper delves into how AI models can enhance the accuracy, adaptability.......

Keywords: AI-driven reliability, predictive analytics, real-time anomaly detection, continuous improvement, Service Level Objectives (SLOs), Service Level Indicators (SLIs), Site Reliability Engineering (SRE), dynamic thresholds, adaptive SLO management, failure injection, cloud computing, distributed systems, proactive reliability management.

[1] Álvarez Cid-Fuentes, J., Szabo, C., & Falkner, K. (2020). Adaptive performance anomaly detection in distributed systems using online SVMs. IEEE Transactions on Dependable and Secure Computing. 17(5), 928–941.
[2] Boem, F., & Parisini, T. (2015). Distributed model-based fault diagnosis with stochastic uncertainties. 2015 54th IEEE Conference on Decision and Control (CDC), 15–18 December 2015.
[3] Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. Pattern Recognition, 89, 13–27.
[4] Hagemann, T., & Katsarou, K. (2020). Reconstruction-based anomaly detection for the cloud: A comparison on the Yahoo! Webscope S5 dataset. Proceedings of the 12th ACM Conference on Web Science.
[5] Hernández-Serrato, J., Velasco, A., Niño, Y., & Linares-Vásquez, M. (2020). Applying machine learning with chaos engineering. 2020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW).