Search

In recent years, breast cancer, originating from breast tissue, has become one of the significant global health challenges for women worldwide, with early detection crucial for improved survival rates. Researchers have proposed numerous detection techniques, and recently, machine learning-based methods have gained considerable attention due to their reusability and speed. Despite various models proposed by researchers for breast cancer detection, there is an ongoing need for more accurate models. This study proposes an enhanced machine-learning approach for breast cancer detection using the Wisconsin Breast Cancer (Diagnostic) (WDBC) dataset. We applied several data preprocessing techniques, including hypothesis testing, feature engineering, scaling, and feature selection. We trained 14 classifiers by selecting the 13 most significant features using a gradient boosting regressor with Bonferroni correction. Our proposed eXtreme Gradient Boosting model demonstrated superior performance, achieving 99.12% accuracy, 0.9767 precision, 1.0 recall, 0.9861 specificity, and 0.9882 F1-score. These results surpass those of previous studies, underscoring the model’s potential for early and accurate breast cancer diagnosis. Furthermore, evaluations based on training time and Kappa score indicate that our eXtreme Gradient Boosting model is faster and more reliable.

Ninety, one-day-old Cobb chicks were randomly divided into 3 groups, each with 3 replicates. A control group was fed a standard diet, whereas the other two treatment groups received a diet with 0.2 or 0.3 mL thyme essential oil (TEO) per kg of the diet for 21 days. The 0.3 group had more meat protein (P ≤ 0.048) than the control group, while the other meat constituents have not changed. Meat sensory parameters (external aspect, odour, colour, and elasticity) declined (P < 0.001), while meat quality parameters (pH, total volatile nitrogen TVN, thiobarbituric acid number TBA, peroxide value PV, and free fatty acids FFA) increased (P < 0.001), through storage of the groups. In TEO groups, improved (P < 0.001) meat overall scores, external aspect and muscular elasticity was observed compared to control. Quality parameters were improved (P < 0.001) including pH, TVN, TBA, PV, and FFA, compared to control during storage. TEO had no effect on heavy metal concentrations while reducing bacterial contamination in meat. TEO 0.2 samples were positive for Salmonella Kentuckey and Staphylococcus aureus, while TEO 0.3 group were free from pathogenic bacteria. Thyme essential oil can enhance quality, and safety of the chilled broiler’s breast meat.

Abstract Psychrotrophic Pseudomonas is one of the significant microbes that lead to putrefaction in chilled meat. One of the biggest problems in the detection of Pseudomonas is that several species are seemingly identical. Currently, antibiotic resistance is one of the most significant challenges facing the world's health and food security. Therefore, this study was designed to apply an accurate technique for eliminating the identification discrepancy of Pseudomonas species and to study their resistance against various antimicrobials. A total of 320 chicken meat specimens were cultivated, and the isolated bacteria’ were phenotypically recognized. Protein analysis was carried out for cultured isolates via Microflex LT. The resistance of Pseudomonas isolates was recorded through Vitek® 2 AST-GN83 cards. Overall, 69 samples were identified as Pseudomonas spp. and included 18 Pseudomonas lundensis (P. lundensis), 16 Pseudomonas fragi (P. fragi), 13 Pseudomonas oryzihabitans (P. oryzihabitans), 10 Pseudomonas stutzeri (P. stutzeri), 5 Pseudomonas fluorescens (P. fluorescens), 4 Pseudomonas putida (P. putida), and 3 Pseudomonas aeruginosa (P. aeruginosa) isolates. Microflex LT identified all Pseudomonas isolates (100%) correctly with a score value ≥ 2.00. PCA positively discriminated the identified isolates into various groups. The antimicrobial resistance levels against Pseudomonas isolates were 81.16% for nitrofurantoin, 71% for ampicillin and ampicillin/sulbactam, 65.22% for cefuroxime and ceftriaxone, 55% for aztreonam, and 49.28% for ciprofloxacin. The susceptibilities were 100% for cefotaxime, 98.55% for ceftazidime, 94.20% for each piperacillin/tazobactam and cefepime, 91.3% for cefazolin. In conclusion, chicken meat was found to be contaminated with different Pseudomonas spp., with high incidence rates of P. lundensis. Microflex LT is a potent tool for distinguishing Pseudomonads at the species level.

Deep learning models are applied in precision agriculture for site-specific weed management by identifying weeds in farmlands. Unfortunately, because deep learning models are usually large, they are rarely adopted in resource-constrained devices (like edge devices) used in precision agriculture. In this study, we propose a lightweight deep learning model for detecting weeds in corn and soybean plants. We used transfer learning to train an InceptionnetV3 model for the task. The dataset used consists of a total of 13,177 samples of corn, soybean, and weeds. The InceptionV3 model, whose size is 183.34 MB, achieved a classification accuracy of 97%. We then applied the quantization technique to reduce the size of the model. The quantized model was reduced to a size of 23.38 MB, achieving an accuracy of 87%. The results show that quantization can reduce the size of a deep learning model while maintaining a reasonable amount of performance.

Insertion is one of the basic operations in DNA computing. Based on this operation, an evolutionary computation model, the insertion system, was defined. For the above defined evolutionary computation model, varying levels of ambiguity and basic descriptional complexity measures were defined. In this paper, we define twelve new (descriptional) complexity measures based on the integral parts of the derivation, such as axioms, strings to be inserted, and contexts used in the insertion rules. Later, we analyze the trade-off among the (newly defined) complexity measures and the existing ambiguity levels. Finally, we examine the application of the analyzed trade-off in natural languages and modelling of bio-molecular structures.

Sarcocystosis considerably occurs in a wide host range including animals, reptiles, humans, and birds. This study was conducted to determine the prevalence of Sarcocystis spp. using abattoir inspection, genetic characterization, as well as histopathology in water buffaloes in two provinces, Elbehera and Kafrelsheikh, Egypt. Specimens were collected from esophagus, tongue, and masseters of 400 slaughtered buffaloes in Elbehera (n= 215) and Kafrelsheikh (n= 185). Samples were examined macroscopically and histopathologically. Furthermore, genetic characterization of Sarcocystis spp. was performed using the 18SrRNA gene-based PCR. The total prevalence was 71.0% (75.3% and 65.9% in Elbehera and Kafrelsheikh, respectively). Aged buffaloes had a higher prevalence than young ones. Females had a higher prevalence than males. The esophagus was the most infected organ. Molecular analysis revealed that the recovered species was S. fusiformis. This is the first genetic characterization of S. fusiformis in water buffaloes from Elbehera and Kafrelsheikh, Egypt. Higher prevalence proposed the potential role of cats in the transmission of S. fusiformis, which, in turn, requires strict hygienic measures to protect animals and humans from infection.

This study was implemented to assess the mechanism by which Moringa oleifera leaf extract (MOLE) improves the quality and prolongs shelf-life of the broilers’ breast meat. Ninety Cobb chicks were randomly allocated to 3 groups. A control group received the standard diet, whereas the other two groups received diets containing MOLE at the doses of 250 and 500 mg/kg for 21 days. Inclusion of MOLE in broilers diet significantly reduced the detrimental changes in the overall sensory attribute scores, characteristic color and odor, and the loss of breast muscle elasticity during storage. Furthermore, it significantly reduced concentrations of thiobarbituric acid, total volatile nitrogen, non-esterified fatty acids, and peroxide, during storage compared to the control samples. No effect on the concentrations of heavy metals, such as copper, cadmium, and lead, was observed. Decomposition of samples was delayed as indicated by lower pH values and higher sensory scores at 4 and 6 days of storage in the MOLE groups. Reduced contamination with E. coli and Salmonella species indicated an antibacterial effect of MOLE. Finally, the present study highlights that MOLE supplementation may play a role in improving quality and shelf-life of the chilled breast meat in broilers.

This article presents a parameter combination-based method selection (PCBMS) approach to select an optimal lossless data compression technique and provides an analysis based on experimental results to show its effectiveness. There are different types of data such as image, audio, video, and text. These data are classified based on the number of bits. Many algorithms have been developed to compress data over the past few decades, but no developed algorithm works well on all types of data. Lossless data compression techniques are mainly evaluated based on the compression ratio, encoding, and decoding time. While a higher compression ratio is more important for some applications, others may require faster encoding or decoding, or both. Alternatively, each of the three parameters can be equally significant. Choosing an optimal algorithm from many algorithms based on an application’s requirements is a significant challenge. By analyzing the data from each perspective, this model recommends an algorithm as the best for each type of data. Based on the proposed model, an analysis is provided. For some sets of data, it has been demonstrated that the proposed method gives a better prediction to select an algorithm according to the needs of an application.

Abstract Background Volunteers play a significant role in supporting hospice and palliative care in Africa, but little is known about the types of volunteers, their motivations and roles in service delivery. Methods Palliative care experts from 30 African countries were invited to participate in an online survey, conducted in English and French, that consisted of 58 questions on: socio-demographics, the activities, motivation and coordination of volunteers, and an appraisal of recent developments in volunteering. The questionnaire was pre-tested in Uganda. Quantitative data was analysed descriptively with SPSS v22; answers on open-ended questions were analysed using content analysis. Results Twenty-five respondents from 21 countries replied to the questionnaire. The typical volunteer was reported to be a female aged between 30 and 50 years. Volunteer roles included, among others: direct patient assistance, providing psychosocial / spiritual support, and assisting patients’ families. Respondents considered altruism, civic engagement and personal gain (for a professional career) as volunteers’ most significant motivational drivers. One in two respondents noted that recruiting volunteers is easy, and cooperation with the communities was often mentioned as helpful. Trainings mostly occurred before the first assignment, with topics covering the palliative care concept, care, psychosocial support and team work. Half of respondents described recent overall volunteering developments as positive, while the other half described problems primarily with financing and motivation. Most volunteers received transportation allowances or bicycles; some received monetary compensation. Conclusions The findings show a wide range of volunteering in palliative care. We identified volunteers as typically 30–50 years old, non-professional females, motivated by altruism, a sense of civic engagement and personal gain. Palliative care services benefit from volunteers who take on high workloads and are close to the patients. The main challenges for volunteer programmes are funding and the long-term motivation of volunteers.

Recommender systems (RSs) are increasingly recognized as intelligent software for predicting users’ opinions on specific items. Various RSs have been developed in different domains, such as e-commerce, e-government, e-resource services, e-business, e-library, e-tourism, and e-learning, to make excellent user recommendations. In e-learning technology, RSs are designed to support and improve the learning practices of a student or an organization. This survey aims to examine the different works of literature on RSs that corroborate e-learning and classify and provide statistics of the reviewed articles based on their recommendation goals, recommendation techniques used, the target user, and the application platforms. The survey makes a prominent contribution to the e-learning RSs field by providing an overview of current research and traditional and nontraditional recommendation techniques to provide different recommendations for future e-learning. One of the most significant findings to emerge from this survey is that a substantial number of works followed either deep learning or context-aware recommendation techniques, which are considered more efficient than any traditional methods. Finally, we provided comprehensive observations from the quantitative assessment of publications, which can guide and support researchers in understanding the current development for potential future trends and the direction of deep learning-based RSs in e-learning.

Raw ground meat is known as a transmission vehicle for biological agents that may be harmful to human health. The objective of the present study was to assess microbiological quality of the ground meats. A total of 280 samples of local and imported chilled meats were randomly collected from retail shops in Buraydah City, Saudi Arabia. The meat samples were microbiologically analyzed using standard methods, peptide mass fingerprinting (PMF) technique, MicroScan Walkaway System (MicroScan) and qPCR System. The imported meat was more bacterially contaminated than local meat, with variable contamination degrees of Staphylococcus aureus (40.33%), Escherichia coli (36.13%), Hafnia alvei (7.56%), Pseudomonas spp. (6.72%), Salmonella spp. (5.88%) and Aeromonas spp. (3.36%). PMF verified all the isolated bacteria by 100%, compared to 75–95% achieved by MicroScan. The gene encoding flagellin (fliC) was recognized in 67.44% of E. coli strains, while the thermonuclease (nuc) and methicillin resistance (mecA) genes were detected in 100% S. aureus and 39.6% of methicillin-resistant S. aureus (MRSA) strains, respectively. The S. aureus and E. coli strains were highly resistant to multiple antibiotics (e.g., ampicillin, amoxicillin-clavulanic acid and cephalothin). For identifying various foodborne pathogens, PMF has been recognized as a powerful and precise analytical method. In light of the increasing use of PMF to detect multidrug-resistant bacteria, this study emphasizes the need for improved ways of treating and preventing pathogens, as well as setting up monitoring systems to guarantee hygiene and safety in meat production.

Recent advances in computing allows researchers to propose the automation of hydroponic systems to boost efficiency and reduce manpower demands, hence increasing agricultural produce and profit. A completely automated hydroponic system should be equipped with tools capable of detecting plant diseases in real-time. Despite the availability of deep-learning-based plant disease detection models, the existing models are not designed for an embedded system environment, and the models cannot realistically be deployed on resource-constrained IoT devices such as raspberry pi or a smartphone. Some of the drawbacks of the existing models are the following: high computational resource requirements, high power consumption, dissipates energy rapidly, and occupies large storage space due to large complex structure. Therefore, in this paper, we proposed a low-power deep learning model for plant disease detection using knowledge distillation techniques. The proposed low-power model has a simple network structure of a shallow neural network. The parameters of the model were also reduced by more than 90%. This reduces its computational requirements as well as its power consumption. The proposed low-power model has a maximum power consumption of 6.22 w, which is significantly lower compared to the existing models, and achieved a detection accuracy of 99.4%.

Abstract Aeromonas is recognized as a human pathogen following ingestion of contaminated food and water. One major problem in Aeromonas identification is that certain species are phenotypically very similar. The antimicrobial resistance is another significant challenge worldwide. We therefore aimed to use mass spectrometry technology for identification and discrimination of Aeromonas species and to screen the antimicrobial resistance of Aeromonas hydrophila (A. hydrophila). A total of 150 chicken meat and water samples were cultured, and then, the isolates were identified biochemically by the Vitek® 2 Compact system. Proteomic identification was performed by MALDI‐TOF MS and confirmed by a microchannel fluidics electrophoresis assay. Principal component analysis (PCA) and single‐peak analysis created by MALDI were also used to discriminate the Aeromonas species. The antimicrobial resistance of the A. hydrophila isolates was determined by Vitek® 2 AST cards. In total, 43 samples were positive for Aeromonas and comprised 22 A. hydrophila, 12 Aeromonas caviae (A. caviae), and 9 Aeromonas sobria (A. sobria) isolates. Thirty‐nine out of 43 (90.69%) Aeromonas isolates were identified by the Vitek® 2 Compact system, whereas 100% of the Aeromonas isolates were correctly identified by MALDI‐TOF MS with a score value ≥2.00. PCA successfully separated A. hydrophila, A. caviae and A. sobria isolates into two groups. Single‐peak analysis revealed four discriminating peaks that separated A. hydrophila from A. caviae and A. sobria isolates. The resistance of A. hydrophila to antibiotics was 95.46% for ampicillin, 50% for cefotaxime, 45.45% for norfloxacin and pefloxacin, 36.36% for ceftazidime and ciprofloxacin, 31.81% for ofloxacin and 27.27% for nalidixic acid and tobramycin. In conclusion, chicken meat and water were tainted with Aeromonas spp., with a high occurrence of A. hydrophila. MALDI‐TOF MS is a powerful technique for characterizing aeromonads at the genus and species levels. Future studies should investigate the resistance of A. hydrophila to various antimicrobial agents.

This article considers the task of handwritten text recognition using attention-based encoder–decoder networks trained in the Kazakh and Russian languages. We have developed a novel deep neural network model based on a fully gated CNN, supported by multiple bidirectional gated recurrent unit (BGRU) and attention mechanisms to manipulate sophisticated features that achieve 0.045 Character Error Rate (CER), 0.192 Word Error Rate (WER), and 0.253 Sequence Error Rate (SER) for the first test dataset and 0.064 CER, 0.24 WER and 0.361 SER for the second test dataset. Our proposed model is the first work to handle handwriting recognition models in Kazakh and Russian languages. Our results confirm the importance of our proposed Attention-Gated-CNN-BGRU approach for training handwriting text recognition and indicate that it can lead to statistically significant improvements (p-value < 0.05) in the sensitivity (recall) over the tests dataset. The proposed method’s performance was evaluated using handwritten text databases of three languages: English, Russian, and Kazakh. It demonstrates better results on the Handwritten Kazakh and Russian (HKR) dataset than the other well-known models.

Text compression is one of the most significant research fields, and various algorithms for text compression have already been developed. This is a significant issue, as the use of internet bandwidth is considerably increasing. This article proposes a Burrows–Wheeler transform and pattern matching-based lossless text compression algorithm that uses Huffman coding in order to achieve an excellent compression ratio. In this article, we introduce an algorithm with two keys that are used in order to reduce more frequently repeated characters after the Burrows–Wheeler transform. We then find patterns of a certain length from the reduced text and apply Huffman encoding. We compare our proposed technique with state-of-the-art text compression algorithms. Finally, we conclude that the proposed technique demonstrates a gain in compression ratio when compared to other compression techniques. A small problem with our proposed method is that it does not work very well for symmetric communications like Brotli.

We often make decisions on the things we like, dislike, or even don’t care about. However, taking the right decisions becomes relatively difficult from a variety of items from different sources. Recommender systems are intelligent decision support software tools that help users to discover items that might be of interest to them. Various techniques and approaches have been applied to design and implement such systems to generate credible recommendations to users. A multi-criteria recommendation technique is an extended approach for modeling user’s preferences based on several characteristics of the items. This research presents genetic algorithm-based approaches for predicting user preferences in multi-criteria recommendation problems. Three genetic algorithms’ methods, namely standard genetic algorithm, adaptive genetic algorithm, and multi-heuristic genetic algorithms are used to conduct the experiments using a multi-criteria dataset for movies recommendation. The empirical results of the comparative analysis of their performance are presented in this study.

Modern daily life activities result in a huge amount of data, which creates a big challenge for storing and communicating them. As an example, hospitals produce a huge amount of data on a daily basis, which makes a big challenge to store it in a limited storage or to communicate them through the restricted bandwidth over the Internet. Therefore, there is an increasing demand for more research in data compression and communication theory to deal with such challenges. Such research responds to the requirements of data transmission at high speed over networks. In this paper, we focus on deep analysis of the most common techniques in image compression. We present a detailed analysis of run-length, entropy and dictionary based lossless image compression algorithms with a common numeric example for a clear comparison. Following that, the state-of-the-art techniques are discussed based on some bench-marked images. Finally, we use standard metrics such as average code length (ACL), compression ratio (CR), pick signal-to-noise ratio (PSNR), efficiency, encoding time (ET) and decoding time (DT) in order to measure the performance of the state-of-the-art techniques.

Recommender systems are powerful online tools that help to overcome problems of information overload. They make personalized recommendations to online users using various data mining and filtering techniques. However, most of the existing recommender systems use a single rating to represent the preference of user on an item. These techniques have several limitations as the preference of the user towards items may depend on several attributes of the items. Multi-criteria recommender systems extend the single rating recommendation techniques to incorporate multiple criteria ratings for improving recommendation accuracy. However, modeling the criteria ratings in multi-criteria recommender systems to determine the overall preferences of users has been considered as one of the major challenges in multi-criteria recommender systems. In other words, how to additionally take the multi-criteria rating information into account during the recommendation process is one of the problems of multi-criteria recommender systems. This article presents a methodological framework that trains artificial neural networks with particle swarm optimization algorithms and uses the neural networks for integrating the multi-criteria rating information and determining the preferences of users. The proposed neural network-based multi-criteria recommender system is integrated with k-nearest neighborhood collaborative filtering for predicting unknown criteria ratings. The proposed approach has been tested with a multi-criteria dataset for recommending movies to users. The empirical results of the study show that the proposed model has a higher prediction accuracy than the corresponding traditional recommendation technique and other multi-criteria recommender systems.

Accuracy improvement is among the primary key research focuses in the area of recommender systems. Traditionally, recommender systems work on two sets of entities, Users and Items, to estimate a single rating that represents a user’s acceptance of an item. This technique was later extended to multi-criteria recommender systems that use an overall rating from multi-criteria ratings to estimate the degree of acceptance by users for items. The primary concern that is still open to the recommender systems community is to find suitable optimization algorithms that can explore the relationships between multiple ratings to compute an overall rating. One of the approaches for doing this is to assume that the overall rating as an aggregation of multiple criteria ratings. Given this assumption, this paper proposed using feed-forward neural networks to predict the overall rating. Five powerful training algorithms have been tested, and the results of their performance are analyzed and presented in this paper.

Accuracy improvement has been one of the most outstanding issues in the recommender systems research community. Recently, multi-criteria recommender systems that use multiple criteria ratings to estimate overall rating have been receiving considerable attention within the recommender systems research domain. This paper proposes a neural network model for improving the prediction accuracy of multi-criteria recommender systems. The neural network was trained using simulated annealing algorithms and integrated with two samples of single-rating recommender systems. The paper presents the experimental results for each of the two single-rating techniques together with their corresponding neural network-based models. To analyze the performance of the approach, we carried out a comparative analysis of the performance of each single rating-based technique and the proposed multi-criteria model. The experimental findings revealed that the proposed models have by far outperformed the existing techniques.