Alpha Fusion Adversarial Attack Analysis Using Deep Learning

The deep learning model encompasses a powerful learning ability that integrates the feature extraction, and classification method to improve accuracy. Convolutional Neural Networks (CNN) perform well in machine learning and image processing tasks like segmentation, classification, detection, identification, etc. The CNN models are still sensitive to noise and attack. The smallest change in training images as in an adversarial attack can greatly decrease the accuracy of the CNN model. This paper presents an alpha fusion attack analysis and generates defense against adversarial attacks. The proposed work is divided into three phases: firstly, an MLSTM-based CNN classification model is developed for classifying COVID-CT images. Secondly, an alpha fusion attack is generated to fool the classification model. The alpha fusion attack is tested in the last phase on a modified LSTM-based CNN (CNN-MLSTM) model and other pre-trained models. The results of CNN models show that the accuracy of these models dropped greatly after the alpha-fusion attack. The highest F1 score before the attack was achieved is 97.45 And after the attack lowest F1 score recorded is 22%. Results elucidate the performance in terms of accuracy, precision, F1 score and Recall.     

Political Optimizer with Deep Learning-Enabled Tongue Color Image Analysis Model

Biomedical image processing is widely utilized for disease detection and classification of biomedical images. Tongue color image analysis is an effective and non-invasive tool for carrying out secondary detection at anytime and anywhere. For removing the qualitative aspect, tongue images are quantitatively inspected, proposing a novel disease classification model in an automated way is preferable. This article introduces a novel political optimizer with deep learning enabled tongue color image analysis (PODL-TCIA) technique. The presented PODL-TCIA model purposes to detect the occurrence of the disease by examining the color of the tongue. To attain this, the PODL-TCIA model initially performs image pre-processing to enhance medical image quality. Followed by, Inception with ResNet-v2 model is employed for feature extraction. Besides, political optimizer (PO) with twin support vector machine (TSVM) model is exploited for image classification process, shows the novelty of the work. The design of PO algorithm assists in the optimal parameter selection of the TSVM model. For ensuring the enhanced outcomes of the PODL-TCIA model, a wide-ranging experimental analysis was applied and the outcomes reported the betterment of the PODL-TCIA model over the recent approaches.     

Robust Multimodal Biometric System Based on Feature Level Fusion of Optimiseddeepnet Features

Wireless Personal Communications - Multimodal biometric systems combine feature knowledge from multiple traits to overcome shortcomings of unimodal systems. However, most of the traditional...     

Effect of CR and FT-paraffin versus SBS modification in terms of conventional and rheological properties

In this study, the rheological and conventional properties of binders prepared with crumb rubber (CR) and FT-paraffin were compared to styrene-butadiene-styrene (SBS)-modified binders’ properties. The objective of this study was to determine which modified binders in different combinations of the CR and the FT-paraffin exhibited better performance than the SBS-modified binders, in terms of conventional and rheological properties. Results showed that the additives exhibited different performances for different types of tests. Many of the combinations including the common usage of the CR and the FT-paraffin performed better at high temperature than the SBS modification. Overall, the test results show that the binders prepared by 6% CR with 3 and 4% FT-paraffin and those prepared with 8% CR with 3% FT-paraffin were better binders than the 4% SBS-modified binder, in terms of low and high temperature properties.     

Local calibration of rigid pavement performance models using resampling methods

The performance prediction models in the Pavement-ME design software are nationally calibrated using in-service pavement material properties, pavement structure, climate and truck loadings, and performance data obtained from the Long-Term Pavement Performance programme. The nationally calibrated models may not perform well if the inputs and performance data used to calibrate those do not represent the local design and construction practices. Therefore, before implementing the new M-E design procedure, each state highway agency (SHA) should evaluate how well the nationally calibrated performance models predict the measured field performance. The local calibrations of the Pavement-ME performance models are recommended to improve the performance prediction capabilities to reflect the unique conditions and design practices. During the local calibration process, the traditional calibration techniques (split sampling) may not necessarily provide adequate results when limited number of pavement sections are available. Consequently, there is a need to employ statistical and resampling methodologies that are more efficient and robust for model calibrations given the data related challenges encountered by SHAs. The main objectives of the paper are to demonstrate the local calibration of rigid pavement performance models and compare the calibration results based on different resampling techniques. The bootstrap is a non-parametric and robust resampling technique for estimating standard errors and confidence intervals of a statistic. The main advantage of bootstrapping is that model parameters estimation is possible without making distribution assumptions. This paper presents the use of bootstrapping and jackknifing to locally calibrate the transverse cracking and IRI performance models for newly constructed and rehabilitated rigid pavements. The results of the calibration show that the standard error of estimate and bias are lower compared to the traditional sampling methods. In addition, the validation statistics are similar to that of the locally calibrated model, especially for the IRI model, which indicates robustness of the local model coefficients.     

Behaviour of sand–clay mixtures for road pavement subgrade

Materials forming sand grains and colluvial soil deposits have a distinct structure, consisting of a composite matrix of coarse and fine soil grains. The influence of sand grains content on the behaviour of sand–clay mixtures was investigated by a series of intensive laboratory experiments. The California bearing ratio (CBR), unconfined compression strength (UCS) and compaction tests were carried out on various contents of sand and clay mixtures. The sand–clay mixtures were prepared with sand contents of 0, 10, 20, 30, 40, and 50% by weight. The laboratory tests on these mixtures have indicated that their behaviour will depend on the relative concentration of the sand and clay samples. The results of the tests showed a decrease in the UCS, and an increase the CBR values with an increase in the amount of sand. An increase in dry unit weight and a decrease in respective moisture content by an increase in the amount of sand were observed in the compaction tests.     

Sustainability evaluation framework for building cooling systems: a comparative study of snow storage and conventional chiller systems

In Canada, the residential building sector consumes 17 % of the total energy and 15 % of the total greenhouse gas emissions. In particular, the energy demand for cooling in the residential sector is increasing due to the large occupancy floor area and high usage of air conditioning. Minimizing energy use and greenhouse gas emissions is one of the highest priority goals set for national energy management strategies in developed countries including Canada. In this study, a framework based on the life cycle assessment approach is developed to assess the environmental impacts of different building cooling systems, namely conventional snow storage system, watertight snow storage system, high-density snow storage system, and the conventional chiller cooling system. Moreover, all these systems have varying energy requirements and associated environmental impacts during different phases (extraction and construction, utilization, and end of life) of the life cycle of a building. A low-rise residential building in Kelowna (BC, Canada) has been selected for the pragmatic application of the proposed framework. The annual cooling energy demand for the building is estimated for different phases. Subsequently, the life cycle impact assessment has been carried out using SimaPro 8.1 software and TRACI 2.1 method. For sustainability evaluation of different cooling systems over their life cycle, multi-criteria decision analysis has been employed using the ‘Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE II).’ The results showed that the snow storage systems tend to reduce greenhouse gas emissions and associated environmental impacts more than the conventional system.