Fingerprints are the most used biometric trait in applications where high level of security is required. Fingerprint image may vary due to various environmental conditions like temperature, humidity, weather etc. Hence, it is necessary to design a fingerprint recognition system that is robust against temperature variations. Existing techniques such as automated and non-automated techniques are not real time analysis (adaptive). In this paper, we propose an adaptive auto correction technique called Reference Auto-correction Algorithm. This proposed algorithm corrects user reference fingerprint template automatically based on captured fingerprint template and the matching score obtained on daily basis to improve the recognition rate. Analysis is carried out on 250 fingerprint templates stored in the database of 10-users captured at varying temperature from 25 0 C to 0 0 C. The experimental result shows 40% improvement in the recognition rate after applying auto correction algorithm.
Brain Tumour is an abnormal cell formation inside the brain. They are mainly classified as benign and malignant tumours. Magnetic Resonance Imaging (MRI) is used for effective diagnosis of brain tumour. An automated method for detection and classification of brain tumour is preferred as analysis of MRI manually is a difficult task for medical experts. The proposed method uses Adaptive Regularized Kernel based Fuzzy C-Means Clustering (ARKFCM) for segmentation. A combination of Support Vector Machine (SVM) and Artificial Neural Network (ANN) is proposed for detection and classification of brain tumour based on the extracted features. A dataset of 94 images is considered for validation of the proposed method which resulted in an accuracy of 91.4%, Sensitivity of 98%, Specificity of 78% and Bit Error Rate (BER) of 0.12. Comparison of the proposed method is carried out with other conventional methods and the results are tabulated.
Today's Multiprocessor System-on-Chip (MPSoC) contains many cores and integrated circuits. Due to the current requirements of communication, we make use of Network-on-Chip (NoC) to obtain high throughput and low latency. NoC is a communication architecture used in the processor cores to transfer data from source to destination through several nodes. Since NoC deals with on-chip interconnection for data transmission, it will be a good prey for data leakage and other security attacks. One such way of attacking is done by a third-party vendor introducing Hardware Trojans (HTs) into routers of NoC architecture. This can cause packets to traverse in wrong paths, leak/extract information and cause Denial-of-Service (DoS) degrading the system performance. In this paper, a novel HT detection and mitigation approach using obfuscation and key-based authentication technique is proposed. The proposed technique prevents any illegal transitions between routers thereby protecting data from malicious activities, such as packet misrouting and information leakage. The proposed technique is evaluated on a 4x4 NoC architecture under synthetic traffic pattern and benchmarks, the hardware model is synthesized in Cadence Tool with 90nm technology. The introduced Hardware Trojan affects 8% of packets passing through infected router. Experimental results demonstrate that the proposed technique prevents those 10-15% of packets infected from the HT effect. Our proposed work has negligible power and area overhead of 8.6% and 2% respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.