Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task fo...Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task for maintaining the integrity of digital content. This thesis explores the use of Modified Error Level Analysis (ELA) in combination with a Convolutional Neural Network (CNN), as well as, Feedforward Neural Network (FNN) model to detect digital image forgeries. Additionally, incorporation of Explainable Artificial Intelligence (XAI) to this research provided insights into the process of decision-making by the models. The study trains and tests the models on the CASIA2 dataset, emphasizing both authentic and forged images. The CNN model is trained and evaluated, and Explainable AI (SHapley Additive exPlanation— SHAP) is incorporated to explain the model’s predictions. Similarly, the FNN model is trained and evaluated, and XAI (SHAP) is incorporated to explain the model’s predictions. The results obtained from the analysis reveals that the proposed approach using CNN model is most effective in detecting image forgeries and provides valuable explanations for decision interpretability.展开更多
Apparel business is one of the oldest global businesses. Emergence of different apparel manufacturing nations, rapid development of global supply chains and increasingly higher demand for fast fashion items are exposi...Apparel business is one of the oldest global businesses. Emergence of different apparel manufacturing nations, rapid development of global supply chains and increasingly higher demand for fast fashion items are exposing the apparel manufacturers to competitive product prices. Alongside, the persistent global depression has also forced the apparel business to curtail the prices to remain sustainable in the industry. Garment costing is the systematic process of meticulously calculating the total cost of a certain quantity of garments from raw material purchase to converting them to the final products, plus other terms and conditions stated by the customers. The sum of these costs adding the profit margin is the selling price. This research outlines the process of preparing cost sheets for basic garment products. The research proposes a clear method of generating easily understandable, complete garment cost sheets for the apparel industry.展开更多
Mankind is facing an unprecedented threat of existence due to the antibiotic resistance developed by bacteria. The unripe fruits of Diospyros malabarica (Desr.) Kostel. (family: Ebenaceae) can be considered as one of ...Mankind is facing an unprecedented threat of existence due to the antibiotic resistance developed by bacteria. The unripe fruits of Diospyros malabarica (Desr.) Kostel. (family: Ebenaceae) can be considered as one of the natural sources to tackle this issue. The present study is designed to assess the antimicrobial activity of D. malabarica seed and flesh ex-tracts. Herein, D. malabarica extracts were prepared using polar solvents (i.e., water and 70% ethanol) and their antimicrobial activity as well as in vivo toxicity was investigated. Their antibacterial activity was investigated against gram positive (Bacillus subtilis) and gram negative (Escherichia coli DH5α, and Salmonella typhi) bacteria at different time points. All the extracts showed the highest antibacterial activity after 2 hours of incubation. The aqueous seed extract showed the maximum zone of inhibition (i.e., ~13 mm) against Bacillus subtilis with a minimum inhibitory concentration (MIC) value of 2 μg/μl. The an-tibacterial propensity was also confirmed through trypan blue dye exclusion assay, CellToxTM Green assay, and lipid peroxidation (LPO) assay. On the other hand, the etha-nolic seed extract demonstrated higher antifungal activity through inhibition of mycelial growth. All the extracts showed excellent hemocompatibility against both human and rat red blood cells (RBCs). They also did not show any toxicity to rat liver and kidneys. Taken together, this study demonstrates that the aqueous and ethanolic extracts of D. malabarica seed and flesh could be an effective source of natural antimicrobial agents with no cytotox-ic activity.展开更多
An intrusion detection system collects and analyzes information from different areas within a computer or a network to identify possible security threats that include threats from both outside as well as inside of the...An intrusion detection system collects and analyzes information from different areas within a computer or a network to identify possible security threats that include threats from both outside as well as inside of the organization. It deals with large amount of data, which contains various ir-relevant and redundant features and results in increased processing time and low detection rate. Therefore, feature selection should be treated as an indispensable pre-processing step to improve the overall system performance significantly while mining on huge datasets. In this context, in this paper, we focus on a two-step approach of feature selection based on Random Forest. The first step selects the features with higher variable importance score and guides the initialization of search process for the second step whose outputs the final feature subset for classification and in-terpretation. The effectiveness of this algorithm is demonstrated on KDD’99 intrusion detection datasets, which are based on DARPA 98 dataset, provides labeled data for researchers working in the field of intrusion detection. The important deficiency in the KDD’99 data set is the huge number of redundant records as observed earlier. Therefore, we have derived a data set RRE-KDD by eliminating redundant record from KDD’99 train and test dataset, so the classifiers and feature selection method will not be biased towards more frequent records. This RRE-KDD consists of both KDD99Train+ and KDD99Test+ dataset for training and testing purposes, respectively. The experimental results show that the Random Forest based proposed approach can select most im-portant and relevant features useful for classification, which, in turn, reduces not only the number of input features and time but also increases the classification accuracy.展开更多
文摘Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task for maintaining the integrity of digital content. This thesis explores the use of Modified Error Level Analysis (ELA) in combination with a Convolutional Neural Network (CNN), as well as, Feedforward Neural Network (FNN) model to detect digital image forgeries. Additionally, incorporation of Explainable Artificial Intelligence (XAI) to this research provided insights into the process of decision-making by the models. The study trains and tests the models on the CASIA2 dataset, emphasizing both authentic and forged images. The CNN model is trained and evaluated, and Explainable AI (SHapley Additive exPlanation— SHAP) is incorporated to explain the model’s predictions. Similarly, the FNN model is trained and evaluated, and XAI (SHAP) is incorporated to explain the model’s predictions. The results obtained from the analysis reveals that the proposed approach using CNN model is most effective in detecting image forgeries and provides valuable explanations for decision interpretability.
文摘Apparel business is one of the oldest global businesses. Emergence of different apparel manufacturing nations, rapid development of global supply chains and increasingly higher demand for fast fashion items are exposing the apparel manufacturers to competitive product prices. Alongside, the persistent global depression has also forced the apparel business to curtail the prices to remain sustainable in the industry. Garment costing is the systematic process of meticulously calculating the total cost of a certain quantity of garments from raw material purchase to converting them to the final products, plus other terms and conditions stated by the customers. The sum of these costs adding the profit margin is the selling price. This research outlines the process of preparing cost sheets for basic garment products. The research proposes a clear method of generating easily understandable, complete garment cost sheets for the apparel industry.
文摘Mankind is facing an unprecedented threat of existence due to the antibiotic resistance developed by bacteria. The unripe fruits of Diospyros malabarica (Desr.) Kostel. (family: Ebenaceae) can be considered as one of the natural sources to tackle this issue. The present study is designed to assess the antimicrobial activity of D. malabarica seed and flesh ex-tracts. Herein, D. malabarica extracts were prepared using polar solvents (i.e., water and 70% ethanol) and their antimicrobial activity as well as in vivo toxicity was investigated. Their antibacterial activity was investigated against gram positive (Bacillus subtilis) and gram negative (Escherichia coli DH5α, and Salmonella typhi) bacteria at different time points. All the extracts showed the highest antibacterial activity after 2 hours of incubation. The aqueous seed extract showed the maximum zone of inhibition (i.e., ~13 mm) against Bacillus subtilis with a minimum inhibitory concentration (MIC) value of 2 μg/μl. The an-tibacterial propensity was also confirmed through trypan blue dye exclusion assay, CellToxTM Green assay, and lipid peroxidation (LPO) assay. On the other hand, the etha-nolic seed extract demonstrated higher antifungal activity through inhibition of mycelial growth. All the extracts showed excellent hemocompatibility against both human and rat red blood cells (RBCs). They also did not show any toxicity to rat liver and kidneys. Taken together, this study demonstrates that the aqueous and ethanolic extracts of D. malabarica seed and flesh could be an effective source of natural antimicrobial agents with no cytotox-ic activity.
文摘An intrusion detection system collects and analyzes information from different areas within a computer or a network to identify possible security threats that include threats from both outside as well as inside of the organization. It deals with large amount of data, which contains various ir-relevant and redundant features and results in increased processing time and low detection rate. Therefore, feature selection should be treated as an indispensable pre-processing step to improve the overall system performance significantly while mining on huge datasets. In this context, in this paper, we focus on a two-step approach of feature selection based on Random Forest. The first step selects the features with higher variable importance score and guides the initialization of search process for the second step whose outputs the final feature subset for classification and in-terpretation. The effectiveness of this algorithm is demonstrated on KDD’99 intrusion detection datasets, which are based on DARPA 98 dataset, provides labeled data for researchers working in the field of intrusion detection. The important deficiency in the KDD’99 data set is the huge number of redundant records as observed earlier. Therefore, we have derived a data set RRE-KDD by eliminating redundant record from KDD’99 train and test dataset, so the classifiers and feature selection method will not be biased towards more frequent records. This RRE-KDD consists of both KDD99Train+ and KDD99Test+ dataset for training and testing purposes, respectively. The experimental results show that the Random Forest based proposed approach can select most im-portant and relevant features useful for classification, which, in turn, reduces not only the number of input features and time but also increases the classification accuracy.
