Search Results (18)

Recently, there has been a rise in skin cancer cases, for which early detection is highly relevant, as it increases the likelihood of a cure. In this context, this work presents a benchmarking study of standard Convolutional Neural Network (CNN) architectures for automated skin lesion classification. A total of 38 CNN architectures from ten families (ConvNeXt, DenseNet, EfficientNet, Inception, InceptionResNet, MobileNet, NASNet, ResNet, VGG, and Xception) were evaluated using transfer learning on the HAM10000 dataset for seven-class skin lesion classification, namely, actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevi, and vascular lesions. The comparative analysis used standardized training conditions, with all models utilizing frozen pre-trained weights. Cross-database validation was then conducted using the ISIC 2019 dataset to assess generalizability across different data distributions. The ConvNeXtXLarge architecture achieved the best performance, despite having one of the lowest performance-to-number-of-parameters ratios, with 87.62% overall accuracy and 76.15% F1 score on the test set, demonstrating competitive results within the established performance range of existing HAM10000-based studies. A proof-of-concept multiplatform mobile application was also implemented using a client–server architecture with encrypted image transmission, demonstrating the viability of integrating high-performing models into healthcare screening tools. Full article

Among the multiple important properties that characterize strong S-boxes for symmetric cryptography and are used in their designs, this study focuses on two: the non-linearity property, a classical security metric, and the confusion coefficient variance property, a statistical proxy for side channel resistance under the Hamming weight leakage model. Given an S-box, two sets can be created: the set of affine-shifted S-boxes, where S-boxes have the same non-linearity value, and the set of Hamming weight classes, where S-boxes have the same confusion coefficient variance value. The inherent values of these two properties ensure resistance to cryptographic attacks; however, if the value of one property increases, it will imply a decrease in the value of the other property. In view of the aforementioned fact, attaining a trade-off becomes a complex undertaking. The impetus for this research stems from the following hypothesis: if an initial S-box already exhibits a trade-off, it would be advantageous to employ a method that generates new S-boxes while preserving the balance. A thorough review of the extant literature reveals the absence of any methodology that encompasses the aforementioned elements. The present paper proposes a novel methodology for generating an affine-shifted subset of S-boxes, ensuring that the resulting subset possesses the same confusion coefficient variance value. We provide insights on the optimal search strategy to optimize non-linearity and confusion coefficient variance. The proposed methodology guarantees the preservation of constant values on the designated. It is possible to incorporate these properties into a comprehensive design scheme, in which case the remaining S-box properties are to be examined. We also demonstrate that, despite the fact that this subset contains S-boxes with the theoretical resistance to side channel attacks under the Hamming weight model, the S-boxes are in different Hamming weight classes. Full article

This paper investigates the features of using modified Hamming codes, which are also known as Hsiao codes. Self-checking digital devices are proposed to be implemented with calculations testing using two diagnostic signs. These signs indicate that the functions (there are functions that describe check bits) belong to the class of self-dual Boolean functions and also belong to the codewords of Hsiao codes (these are codes with an odd column of weights). The authors have established that all check functions can be self-dual for a certain number of the Hsiao codes’ data symbols. Such codes can be used in the synthesis of concurrent error-detection circuits by two diagnostic signs. The paper describes the structure of an organization for a concurrent error-detection circuit based on Hsiao codes with self-dual check functions. Some experimental results are presented on the synthesis of self-checking devices using the proposed methodology. The controllability of the structure and the number of test combinations both increased. Hsiao codes can be effectively used with self-dual check functions in the synthesis of self-checking digital devices. Full article

A pilot study was conducted with the aim of adapting the processing of “Kraški pršut”, dry-cured ham, for thighs from heavy pigs. The focus was on the effect of ham weight and salting duration on the quality of dry-cured ham. From a pool of thighs harvested from heavy pigs, a total of 32 green hams were selected (from 16 carcasses) based on weight (two classes; L—lighter, H—heavier) and we used left and right ham for either the standard or a shortened salting phase. Salting duration consisted of phase 1 (7 days for all hams) and phase 2 (7 or 14 days for L, 10 or 17 days for H, in the case of shortened and standard salting, respectively). Equivalent conditions for all hams were maintained during the remaining phases, with a total maturation period of 18 months. The analysis focused on chemical, physical and rheological properties, sensory attributes, and consumer perceptions. The H hams had lower processing losses, resulting in higher moisture and water activity, lower salt content in internal biceps femoris muscle, and a softer texture (instrumental and sensory) than L hams. The salting duration mainly affected weight losses in the salting phase and, consequently, salt content, which was lower in the shortened salting phase, while no effects were observed on texture. The sensory panel perceived weight’s effect on hardness, with L hams being perceived as harder, and salting’s effect on sourness, with hams submitted to longer salting perceived as sourer than H hams. Consumer testing indicated a general preference for softer and less salty hams. Overall, the results show that the applied reduction in salting duration was not substantial, and future trials should explore further optimization in terms of salting and resting phases. Full article

As cryptographic implementations leak secret information through side-channel emissions, the Hamming weight (HW) leakage model is widely used in deep learning profiling side-channel analysis (SCA) attacks to expose the leaked model. However, imbalanced datasets often arise from the HW leakage model, increasing the attack complexity and limiting the performance of deep learning-based SCA attacks. Effective management of class imbalance is vital for training deep neural network models to achieve optimized and improved performance results. Recent works focus on either improved deep-learning methodologies or data augmentation techniques. In this work, we propose the hybrid bagging resampling framework, a two-pronged strategy for tackling class imbalance in side-channel datasets, consisting of data augmentation and ensemble learning. We show that adopting this framework can boost attack performance results in a practical setup. From our experimental results, the SMOTEENN ensemble achieved the best performance in the ASCAD dataset, and the basic ensemble performed the best in the CHES dataset, with both contributing over $70\%$ practical improvements in performance compared to the original imbalanced dataset, and accelerating practical attack space in comparison to the classical setup of the attack. Full article

Melanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of diseases using medical imaging. The paper introduces a computational model for classifying melanoma skin cancer images using convolutional neural networks (CNNs) and vision transformers (ViT) with the HAM10000 dataset. Both approaches utilize mask-guided techniques, employing a specialized U2-Net segmentation module to generate masks. The CNN-based approach utilizes ResNet50, VGG16, and Xception with transfer learning. The training process is enhanced using a Bayesian hyperparameter tuner. Moreover, this study applies gradient-weighted class activation mapping (Grad-CAM) and Grad-CAM++ to generate heatmaps to explain the classification models. These visual heatmaps elucidate the contribution of each input region to the classification outcome. The CNN-based model approach achieved the highest accuracy at 98.37% in the Xception model with a sensitivity and specificity of 95.92% and 99.01%, respectively. The ViT-based model approach achieved high values for accuracy, sensitivity, and specificity, such as 92.79%, 91.09%, and 93.54%, respectively. Furthermore, the performance of the model was assessed through intersection over union (IOU) and other qualitative evaluations. Finally, we developed the proposed model as a web application that can be used as a support tool for medical practitioners in real-time. The system usability study score of 86.87% is reported, which shows the usefulness of the proposed solution. Full article

Skin cancer poses a significant healthcare challenge, requiring precise and prompt diagnosis for effective treatment. While recent advances in deep learning have dramatically improved medical image analysis, including skin cancer classification, ensemble methods offer a pathway for further enhancing diagnostic accuracy. This study introduces a cutting-edge approach employing the Max Voting Ensemble Technique for robust skin cancer classification on ISIC 2018: Task 1-2 dataset. We incorporate a range of cutting-edge, pre-trained deep neural networks, including MobileNetV2, AlexNet, VGG16, ResNet50, DenseNet201, DenseNet121, InceptionV3, ResNet50V2, InceptionResNetV2, and Xception. These models have been extensively trained on skin cancer datasets, achieving individual accuracies ranging from 77.20% to 91.90%. Our method leverages the synergistic capabilities of these models by combining their complementary features to elevate classification performance further. In our approach, input images undergo preprocessing for model compatibility. The ensemble integrates the pre-trained models with their architectures and weights preserved. For each skin lesion image under examination, every model produces a prediction. These are subsequently aggregated using the max voting ensemble technique to yield the final classification, with the majority-voted class serving as the conclusive prediction. Through comprehensive testing on a diverse dataset, our ensemble outperformed individual models, attaining an accuracy of 93.18% and an AUC score of 0.9320, thus demonstrating superior diagnostic reliability and accuracy. We evaluated the effectiveness of our proposed method on the HAM10000 dataset to ensure its generalizability. Our ensemble method delivers a robust, reliable, and effective tool for the classification of skin cancer. By utilizing the power of advanced deep neural networks, we aim to assist healthcare professionals in achieving timely and accurate diagnoses, ultimately reducing mortality rates and enhancing patient outcomes. Full article

Assigning predefined classes to natural language texts, based on their content, is a necessary component in many tasks in organizations. This task is carried out by classifying documents within a set of predefined categories using models and computational methods. Text representation for classification purposes has traditionally been performed using a vector space model due to its good performance and simplicity. Moreover, the classification of texts via multilabeling has typically been approached by using simple label classification methods, which require the transformation of the problem studied to apply binary techniques, or by adapting binary algorithms. Over the previous decade, text classification has been extended using deep learning models. Compared to traditional machine learning methods, deep learning avoids rule design and feature selection by humans, and automatically provides semantically meaningful representations for text analysis. However, deep learning-based text classification is data-intensive and computationally complex. Interest in deep learning models does not rule out techniques and models based on shallow learning. This situation is true when the set of training cases is smaller, and when the set of features is small. White box approaches have advantages over black box approaches, where the feasibility of working with relatively small sets of data and the interpretability of the results stand out. This research evaluates a weighting function of the words in texts to modify the representation of the texts during multilabel classification, using a combination of two approaches: problem transformation and model adaptation. This weighting function was tested in 10 referential textual data sets, and compared with alternative techniques based on three performance measures: Hamming Loss, Accuracy, and macro-$F_1$. The best improvement occurs on the macro-$F_1$ when the data sets have fewer labels, fewer documents, and smaller vocabulary sizes. In addition, the performance improves in data sets with higher cardinality, density, and diversity of labels. This proves the usefulness of the function on smaller data sets. The results show improvements of more than 10% in terms of macro-$F_1$ in classifiers based on our method in almost all of the cases analyzed. Full article

Mangalica pigs are a popular niche breed given their reputation for superior pork quality. However, growth and carcass parameters for this breed are poorly documented. To better characterize optimal harvest weights for the Mangalica, a growth trial was conducted whereby pigs (n = 56) were randomly distributed across stratified harvest weights (50, 57, 68, 82, 93, 102, 127 kg) in a completely randomized design. Pigs were fed standard finisher rations with individual daily feed intakes and weekly body weights recorded for all animals. At 24 h postmortem, carcasses were split and ribbed with marbling and loin eye area (LEA) measured at the 10th rib. Primal cuts were fabricated and individually weighed. Fat back was separated from the loin and weighed. As expected, live weight significantly increased across the weight class (p < 0.0001). ADG was similar across classes up to 82 kg live weight, before steadily declining with increasing weight class (p < 0.0025). Likewise, feed efficiency did not differ between classes until weights heavier than 82 kg (p < 0.03). LEA significantly increased by class up to 82 kg and then plateaued as harvest weight increased further (p < 0.003). Marbling score significantly increased with increasing weight class up to 102 kg, where they then plateaued (p < 0.04). Fat back dramatically increased across all weight classes (p < 0.0001) despite negligible increases in LEA or marbling after 102 kg. Primal cut weights for the ham (p < 0.0001), loin (p < 0.0001), Boston butt (p < 0.0001), shoulder (p < 0.0001), and belly (p < 0.0001) all significantly increased with increasing live weight though significant fat deposition contributed to this gain. These data suggest an optimal harvest weight occurs between 82 to 102 kg, while offering little objective justification for harvesting Mangalica pigs at heavier live weights. Full article

Skin lesion detection and analysis are very important because skin cancer must be found in its early stages and treated immediately. Once installed in the body, skin cancer can easily spread to other body parts. Early detection would represent a very important aspect since, by ensuring correct treatment, it could be curable. Thus, by taking all these issues into consideration, there is a need for highly accurate computer-aided systems to assist medical staff in the early detection of malignant skin lesions. In this paper, we propose a skin lesion classification system based on deep learning techniques and collective intelligence, which involves multiple convolutional neural networks, trained on the HAM10000 dataset, which is able to predict seven skin lesions including melanoma. The convolutional neural networks experimentally chosen, considering their performances, to implement the collective intelligence-based system for this purpose are: AlexNet, GoogLeNet, GoogLeNet-Places365, MobileNet-V2, Xception, ResNet-50, ResNet-101, InceptionResNet-V2 and DenseNet201. We then analyzed the performances of each of the above-mentioned convolutional neural networks to obtain a weight matrix whose elements are weights associated with neural networks and classes of lesions. Based on this matrix, a new decision matrix was used to build the multi-network ensemble system (Collective Intelligence-based System), combining each of individual neural network decision into a decision fusion module (Collective Decision Block). This module would then have the responsibility to take a final and more accurate decision related to the prediction based on the associated weights of each network output. The validation accuracy of the proposed system is about 3 percent better than that of the best performing individual network. Full article

CDMs can provide a discrete classification of mastery skills to diagnose relevant conceptions immediately for Education Sustainable Development. Due to the problem of parametric CDMs with only a few training sample sizes in small classroom teaching situations and the lack of a nonparametric model for classifying error patterns, two nonparametric weighted cognitive diagnosis models, NWSD and NWBD, for classifying mastery skills and knowledge bugs were proposed, respectively. In both, the variances of items with respect to the ideal responses were considered for computing the weighted Hamming distance, and the inverse distances between the observed and ideal responses were used as weights to obtain the probabilities of the mastering attributes of a student. Conversely, NWBD can classify students’ “bugs”, so teachers can provide suitable examples for precision assistance before teaching non-mastery skills. According to the experimental results on simulated and real datasets, the proposed methods outperform some standard methods in a small-class situation. The results also demonstrate that a remedial course with NWSD and NWBD is better than one with traditional group remedial teaching. Full article

Slaughter weight (SW) is critical for dry-cured ham production systems with heavy pigs. A total of 159 C21 Goland pigs (gilts and barrows) at 95 ± 9.0 kg body weight (BW) from three batches were used to investigate the impact of ad libitum feeding on SW, growth performance, feed efficiency, and carcass and green ham characteristics. Diets contained 10 MJ/kg of net energy and 7.4 and 6.0 g/kg of SID-lysine. Slaughter weight classes (SWC) included <165, 165–180, 180–110 and >210 kg BW. In each batch, pigs were sacrificed at 230 or 258 d of age. Left hams were scored for round shape, fat cover thickness, marbling, lean colour, bicolour and veining. Data were analyzed with a model considering SWC, sex and SWC × Sex interactions as fixed factors and the batch as a random factor. The linear, quadratic and cubic effects of SWC were tested, but only linear effects were found. Results showed that pigs with greater SWC had greater average daily gain and feed consumption, with similar feed efficiency and better ham quality traits: greater ham weight, muscularity, and fat coveringin correspondence of semimembranosus muscle. Barrows were heavier and produced hams with slightly better characteristics than gilts. Full article

During the search for S-boxes resistant to Power Attacks, the S-box space has recently been divided into Hamming Weight classes, according to its theoretical resistance to these attacks using the metric variance of the confusion coefficient. This partition allows for reducing the size of the search space. The swap operator is frequently used when searching with a random selection of items to be exchanged. In this work, the theoretical probability of changing Hamming Weight class of the S-box is calculated when the swap operator is applied randomly in a permutation. The precision of these probabilities is confirmed experimentally. Its limit and a recursive formula are theoretically proved. It is shown that this operator changes classes with high probability, which favors the exploration of the Hamming Weight class of S-boxes space but dramatically reduces the exploitation within classes. These results are generalized, showing that the probability of moving within the same class is substantially reduced by applying two swaps. Based on these results, it is proposed to modify/improve the use of the swap operator, replacing its random application with the appropriate selection of the elements to be exchanged, which allows taking control of the balance between exploration and exploitation. The calculated probabilities show that the random application of the swap operator is inappropriate during the search for nonlinear S-boxes resistant to Power Attacks since the exploration may be inappropriate when the class is resistant to Differential Power Attack. It would be more convenient to search for nonlinear S-boxes within the class. This result provides new knowledge about the influence of this operator in the balance exploration–exploitation. It constitutes a valuable tool to improve the design of future algorithms for searching S-boxes with good cryptography properties. In a probabilistic way, our main theoretical result characterizes the influence of the swap operator in the exploration–exploitation balance during the search for S-boxes resistant to Power Attacks in the Hamming Weight class space. The main practical contribution consists of proposing modifications to the swap operator to control this balance better. Full article

The present study aimed to evaluate the health-promoting potential of breadfruit (Artocarpus altilis (Parkinson) Fosberg, Moraceae family), a traditional Comorian food, considering the sample variability according to geographic localisation. Moreover, the main aims of this research were also to promote its consumption in the Comoros Islands as potential health-promoting food and evaluate it as a source of bioactive molecules for the food industry thanks to its antioxidant and antibacterial properties. Investigations on biologically active substances were carried out on the extracts obtained from breadfruit flours from five regions of Grande Comore (Ngazidja), the main island in Comoros. Phytochemical screening revealed the presence of tannins and polyphenols, flavonoids, leucoanthocyanins, steroids, and triterpenes. The considered secondary metabolites were phenolic compounds, vitamin C, monoterpenes, and organic acids. The contents of total phenolic compounds (mgGAE/100 g of dry weight—DW) in the extracts ranged from 29.69 ± 1.40 (breadfruit from Mbadjini—ExMBA) to 96.14 ± 2.07 (breadfruit from Itsandra—ExITS). These compounds included flavanols, flavonols, cinnamic acid and benzoic acid derivatives, and tannins which were detected at different levels in the different extracts. Chlorogenic acid presented the highest levels between 26.57 ± 0.31 mg/100 g DW (ExMIT) and 43.80 ± 5.43 mg/100 g DW (ExMBA). Quercetin was by far the most quantitatively important flavonol with levels ranging from 14.68 ± 0.19 mg/100 g DW (ExMIT) to 29.60 ± 0.28 mg/100 g DW (ExITS). The extracts were also rich in organic acids and monoterpenes. Quinic acid with contents ranging from 77.25 ± 6.04 mg/100 g DW (ExMBA) to 658.56 ± 0.25 mg/100 g DW of ExHAM was the most important organic acid in all the breadfruit extracts, while limonene was quantitatively the main monoterpene with contents between 85.86 ± 0.23 mg/100 g DW (ExMIT) and 565.45 ± 0.24 mg/100 g DW (ExITS). The antibacterial activity of the extracts was evaluated on twelve pathogens including six Gram (+) bacteria and six Gram (−) bacteria. By the solid medium disc method, except for Escherichia coli and Pseudomonas aeruginosa, all the bacteria were sensitive to one or more extracts. Inhibitory Halo Diameters (IHDs) ranged from 8 mm to 16 mm. Salmonella enterica, Clostridium perfringens, and Vibrio fischeri were the most sensitive with IHD > 14 mm for ExITS. By the liquid microdilution method, MICs ranged from 3.12 mg/mL to 50 mg/mL and varied depending on the extract. Bacillus megaterium was the most sensitive with MICs ≤ 12.5 mg/mL. Pseudomonas aeruginosa, Shigella flexneri, and Vibrio fischeri were the least sensitive with all MICs ≥ 12.5 mg/mL. ExHAM was most effective with a MIC of 3.12 mg/mL on Staphylococcus aureus and 6.25 mg/mL on Salmonella enterica. The antioxidant power of the extracts was evaluated by the FRAP method. The activity ranged from 5.44 ± 0.35 (ExMBA) to 14.83 ± 0.11 mmol Fe²⁺/kg DW (ExHAM). Breadfruit from different regions of Comoros contained different classes of secondary metabolites well known for their important pharmacological properties. The results of this study on phenolics, monoterpenes, and organic acids have provided new data on these fruits. The obtained results showed that breadfruit from the biggest island of the Union of Comoros also presented antimicrobial and antioxidant properties, even if some differences in effectiveness existed between fruits from different regions. Full article

The search of bijective $n\times n$ S-boxes resilient to power attacks in the space of dimension $\left(2^n\right)!$ is a controversial topic in the cryptology community nowadays. This paper proposes partitioning the space of $\left(2^n\right)!$ S-boxes into equivalence classes using the hypothetical power leakage according to the Hamming weights model, which ensures a homogeneous theoretical resistance within the class against power attacks. We developed a fast algorithm to generate these S-boxes by class. It was mathematically demonstrated that the theoretical metric confusion coefficient variance takes constant values within each class. A new search strategy—jumping over the class space—is justified to find S-boxes with high confusion coefficient variance in the space partitioned by Hamming weight classes. In addition, a decision criterion is proposed to move quickly between or within classes. The number of classes and the number of S-boxes within each class are calculated, showing that, as n increases, the class space dimension is an ever-smaller fraction of the space of S-boxes, which significantly reduces the space of search of S-boxes resilient to power attacks, when the search is performed from class to class. Full article