Search Results (11,984)

Pigs play vital roles in the food supply, economic development, agricultural recycling, bioenergy, and social culture. Pork serves as a primary meat source and holds extensive applications in various dietary cultures, making pigs indispensable to human dietary structures. Manual pig counting, a crucial aspect of pig farming, suffers from high costs and time-consuming processes. In this paper, we propose the PDC-YOLO network to address these challenges, dedicated to detecting pigs in complex farming environments for counting purposes. Built upon YOLOv7, our model incorporates the SPD-Conv structure into the YOLOv7 backbone to enhance detection under varying lighting conditions and for small-scale pigs. Additionally, we replace the neck of YOLOv7 with AFPN to efficiently fuse features of different scales. Furthermore, the model utilizes rotated bounding boxes for improved accuracy. Achieving a mAP of 91.97%, precision of 95.11%, and recall of 89.94% on our collected pig dataset, our model outperforms others. Regarding technical performance, PDC-YOLO exhibits an error rate of 0.002 and surpasses manual counting significantly in speed. Full article

The traditional approach to optical design faces limitations as photonic devices grow increasingly complex, requiring advanced functionalities. Recently, machine learning algorithms have gained significant interest for extracting structural designs from customized wavelength spectra, surpassing traditional simulation methods known for their time-consuming nature and resource-demanding computational requirements. This study focuses on the inverse design of a reflectionless multilayer thin-film structure across a specific wavelength region, utilizing a tandem neural network (TNN) approach. The method effectively addresses the non-uniqueness problem in training inverse neural networks. Data generation via the transfer matrix method (TMM) involves simulating the optical behavior of a multilayer structure comprising alternating thin films of silicon dioxide (SiO₂) and silicon (Si). This innovative design considers both reflection and absorption properties to achieve near-zero reflection. We aimed to manipulate the structure’s reflectivity by implementing low-index and high-index layers along with Si absorption layers to attain specific optical properties. Our TNN demonstrated an MSE accuracy of less than 0.0005 and a maximum loss of 0.00781 for predicting the desired spectrum range, offering advanced capabilities for forecasting arbitrary spectra. This approach provides insights into designing multilayer thin-film structures with near-zero reflection and highlights the potential for controlling absorption materials to enhance optical performance. Full article

Agriculture stands as the cornerstone of Africa’s economy, supporting over 60% of the continent’s labor force. Despite its significance, the quality assessment of agricultural products remains a challenging task, particularly at a large scale, consuming valuable time and resources. The African plum is an agricultural fruit that is widely consumed across West and Central Africa but remains underrepresented in AI research. In this paper, we collected a dataset of 2892 African plum samples from fields in Cameroon representing the first dataset of its kind for training AI models. The dataset contains images of plums annotated with quality grades. We then trained and evaluated various state-of-the-art object detection and image classification models, including YOLOv5, YOLOv8, YOLOv9, Fast R-CNN, Mask R-CNN, VGG-16, DenseNet-121, MobileNet, and ResNet, on this African plum dataset. Our experimentation resulted in mean average precision scores ranging from 88.2% to 89.9% and accuracies between 86% and 91% for the object detection models and the classification models, respectively. We then performed model pruning to reduce model sizes while preserving performance, achieving up to 93.6% mean average precision and 99.09% accuracy after pruning YOLOv5, YOLOv8 and ResNet by 10–30%. We deployed the high-performing YOLOv8 system in a web application, offering an accessible AI-based quality assessment tool tailored for African plums. To the best of our knowledge, this represents the first such solution for assessing this underrepresented fruit, empowering farmers with efficient tools. Our approach integrates agriculture and AI to fill a key gap. Full article

The study was conducted to study the sustainability and enhanced nutrition gains obtained from incorporating grape skin powder (GSP) extracted from both Fetească Neagră and Rară Neagră grape varieties into yogurt. Grape skins are major leftovers from wineries, having high amounts of phenolic compounds and dietary fiber responsible for their ability to improve the characteristics of food. The research aimed to evaluate the effect of GSP addition at varying concentrations (0.5%, 1.0%, and 1.5%) on the yogurt’s physicochemical properties, antioxidant activity, color parameters, and sensory attributes. Analysis revealed that both Fetească Neagră and Rară Neagră GSP increased the total phenolic content and antioxidant activity; however, Fetească Neagră showed greater improvements, with TPC reaching 1.52 mg GAE/100 g and DPPH inhibition up to 26.63%. Although slightly lower, TPC rose to 1.43 mg GAE/100 g and DPPH inhibition increased to 18.93% with Rară Neagră enhancing these parameters conversely. Color changes were observed in fortified yogurts where lightness decreased (L*) and redness increased (a*) due to the pH-dependent anthocyanin stability. Syneresis, indicative of yogurt’s water-holding capacity, was reduced at higher concentrations of GSP from both varieties, suggesting improved textural integrity. Sensory evaluation indicated that consumers generally favored yogurts with lower concentrations of GSP. Yogurts fortified with Fetească Neagră GSP received higher overall preference, while those with Rară Neagră GSP were also well-received for their distinct flavor profiles when used at suitable levels. These results show that GSP from both types of grapes improves the nutritional value of yogurt and complies with the principles of sustainable food production through reutilizing agro-industrial waste. Full article

High-pressure air injection (HPAI) is an enhanced oil recovery process in which compressed air is injected into deep, light oil reservoirs, with the expectation that the oxygen in the injected air will react with a fraction of the reservoir oil at an elevated temperature to produce carbon dioxide. The different chemical reactions taking place can be grouped into oxygen addition, thermal cracking, oxygen-induced cracking, and bond scission reactions. The latter reactions involve the combustion of a flammable vapor as well as the combustion of solid fuel, commonly known as “coke”. Since stable peak temperatures observed during HPAI experiments are typically below 300 °C, it has been suggested that thermal cracking and combustion of solid fuel may not be important reaction mechanisms for the process. The objective of this work is to assess the validity of that hypothesis. Therefore, this study makes use of different oxidation and combustion HPAI experiments, which were performed on two different light oil reservoir samples. Modeling of those tests indicate that thermal cracking is not an important reaction mechanism during HPAI and can potentially be ignored. The work also suggests that the main fuel consumed by the process is a flammable vapor generated by the chemical reactions. This represents a shift from the original in situ combustion paradigm, which is based on the combustion of coke. Full article

Background/Objectives: Heavy metals are a group of metals and metalloids that have a relatively high density. They can cause toxicity even at very low levels. Trace elements are required by all living organisms to maintain their normal growth, metabolism, and development. Oral intake is the main route of exposure to both heavy metals and trace elements. Phenylketonuria (PKU) is the most common amino acid metabolic disorder, and the best known treatment for patients requiring treatment is a phenylalanine (Phe)-restricted diet. The objective of the present study was to evaluate the plasma heavy metal levels, sources of exposure, changes in these levels according to dietary regimen, and trace element levels and their correlations with heavy metals in PKU patients. Methods: The study was conducted between July 2022 and January 2024 on 105 patients aged 2–6 years diagnosed with PKU. Results: The percentage of Pb levels in individuals in the upper quartile increased by 3.47 times (95% CI = 1.07–11.29) in those who consumed canned foods and 7.29 times (95% CI = 1.21–44.03) in those who consumed spring water. The percentage of As levels in the upper tertile increased by a factor of 7.26 (95% CI = 2.09–25.28) in individuals under four years of age and 8.17 times (95% CI = 2.13–31.27) in canned food users. The odds of having blood Cd levels in the upper tertile were 0.09 (95% CI = 0.01–0.96) for those being breastfed for 6–11 months compared to 0–5 months. Zn levels were lower (93.0 vs. 83.6 µg/dL, p = 0.008) in patients on a Phe-restricted diet. Conclusions: The present study did not find a relationship between heavy metal exposure and the dietary treatment status of patients with PKU. Our findings indicate that canned food consumption is a significant contributing factor to heavy metal exposure in PKU patients. Furthermore, our findings revealed a relationship between age, perception of economic level, breastfeeding, kitchen equipment, and water usage and the levels of certain heavy metals. Full article

Background: Human breast milk is a valuable source of potential probiotic candidates. The bacteria isolated from human breast milk play an important role in the development of the infant gut microbiota, exhibiting diverse biological functions. Methods: In this study, Limosilactobacillus reuteri MBHC 10138 isolated from breast milk was characterized in terms of its probiotic safety characteristics and potential efficacy in hyperuricemia, obesity, lipid liver, and dental caries, conditions which Korean consumers seek to manage using probiotics. Results: Strain MBHC 10138 demonstrated a lack of D-lactate and biogenic amine production as well as a lack of bile salt deconjugation and hemolytic activity. It also exhibited susceptibility to common antibiotics, tolerance to simulated oral–gastric–intestinal conditions, and superior biological activity compared to three L. reuteri reference strains, including KACC 11452 and MJ-1, isolated from feces, and a commercial strain isolated from human breast milk. Notably, L. reuteri MBHC 10138 showed high capabilities in assimilating guanosine (69.48%), inosine (81.92%), and adenosine (95.8%), strongly inhibited 92.74% of biofilm formation by Streptococcus mutans, and reduced lipid accumulation by 32% in HepG2 cells. Conclusions: These findings suggest that strain MBHC 10138, isolated from human breast milk, has potential to be developed as a probiotic for managing hyperuricemia, obesity, and dental caries after appropriate in vivo studies. Full article

The advanced metering infrastructure (AMI) of the smart grid plays a critical role in energy management and billing by enabling the periodic transmission of consumers’ power consumption readings. To optimize data collection efficiency, AMI employs a “change and transmit” (CAT) approach. This approach ensures that readings are only transmitted when there is enough change in consumption, thereby reducing data traffic. Despite the benefits of this approach, it faces security challenges where malicious consumers can manipulate their readings to launch cyberattacks for electricity theft, allowing them to illegally reduce their bills. While this challenge has been addressed for supervised learning CAT settings, it remains insufficiently addressed in unsupervised learning settings. Moreover, due to the distortion introduced in the power consumption readings due to using the CAT approach, the accurate prediction of future consumption for energy management is a challenge. In this paper, we propose a two-stage approach to predict future readings and detect electricity theft in the smart grid while optimizing data collection using the CAT approach. For the first stage, we developed a predictor that is trained exclusively on benign CAT power consumption readings, and the output of the predictor is the actual readings. To enhance the prediction accuracy, we propose a cluster-based predictor that groups consumers into clusters with similar consumption patterns, and a dedicated predictor is trained for each cluster. For the second stage, we trained an autoencoder and a one-class support vector machine (SVM) on the benign reconstruction errors of the predictor to classify instances of electricity theft. We conducted comprehensive experiments to assess the effectiveness of our proposed approach. The experimental results indicate that the prediction error is very small and the accuracy of detection of the electricity theft attacks is high. Full article

Safety is the eternal theme of power systems. In view of problems such as time-consuming and poor real-time performance in the correct use of seat belt hooks by manual supervision operators in the process of power operation, this paper proposes an improved YOLOv7 seat belt hook suspension state recognition algorithm. Firstly, the feature extraction part of the YOLOv7 backbone network is improved, and the M-Spatial Pyramid Pooling Concurrent Spatial Pyramid Convolution (M-SPPCSPC) feature extraction module is constructed to replace the Spatial Pyramid Pooling Concurrent Spatial Pyramid Convolution (SPPCSPC) module of the backbone network, which reduces the amount of computation and improves the detection speed of the backbone network while keeping the sensory field of the backbone network unchanged. Second, a decoupled head, which realizes the confidence and regression frames separately, is introduced to alleviate the negative impact of the conflict between the classification and regression tasks, consequently improving the network detection accuracy and accelerating the network convergence. Ultimately, a dynamic non-monotonic focusing mechanism is introduced in the output layer, and the Wise Intersection over Union (WioU) loss function is used to reduce the competitiveness of high-quality anchor frames while reducing the harmful gradient generated by low-quality anchor frames, which ultimately improves the overall performance of the detection network. The experimental results show that the mean Average Precision ([email protected]) value of the improved network reaches 81.2%, which is 7.4% higher than that of the original YOLOv7, therefore achieving better detection results for multiple-state recognition of hooks. Full article

Spam reviews pose a significant challenge to the integrity of online platforms, misleading consumers and undermining the credibility of genuine feedback. This paper introduces an innovative AI-generated spam review detection framework that leverages Deep Learning algorithms and Natural Language Processing (NLP) techniques to identify and mitigate spam reviews effectively. Our framework utilizes multiple Deep Learning models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Unit (GRU), and Bidirectional LSTM (BiLSTM), to capture intricate patterns in textual data. The system processes and analyzes large volumes of review content to detect deceptive patterns by utilizing advanced NLP and text embedding techniques such as One-Hot Encoding, Word2Vec, and Term Frequency-Inverse Document Frequency (TF-IDF). By combining three embedding techniques with four Deep Learning algorithms, a total of twelve exhaustive experiments were conducted to detect AI-generated spam reviews. The experimental results demonstrate that our approach outperforms the traditional machine learning models, offering a robust solution for ensuring the authenticity of online reviews. Among the models evaluated, those employing Word2Vec embeddings, particularly the BiLSTM_Word2Vec model, exhibited the strongest performance. The BiLSTM model with Word2Vec achieved the highest performance, with an exceptional accuracy of 98.46%, a precision of 0.98, a recall of 0.97, and an F1-score of 0.98, reflecting a near-perfect balance between precision and recall. Its high F2-score (0.9810) and F0.5-score (0.9857) further highlight its effectiveness in accurately detecting AI-generated spam while minimizing false positives, making it the most reliable option for this task. Similarly, the Word2Vec-based LSTM model also performed exceptionally well, with an accuracy of 97.58%, a precision of 0.97, a recall of 0.96, and an F1-score of 0.97. The CNN model with Word2Vec similarly delivered strong results, achieving an accuracy of 97.61%, a precision of 0.97, a recall of 0.96, and an F1-score of 0.97. This study is unique in its focus on detecting spam reviews specifically generated by AI-based tools rather than solely detecting spam reviews or AI-generated text. This research contributes to the field of spam detection by offering a scalable, efficient, and accurate framework that can be integrated into various online platforms, enhancing user trust and the decision-making processes. Full article

Elliptic curve cryptography (ECC) is widely used for secure communications, because it can provide the same level of security as RSA with a much smaller key size. In constrained environments, it is important to consider efficiency, in terms of execution time and hardware costs. Modular inversion is a key time-consuming calculation used in ECC. Its hardware implementation requires extensive hardware resources, such as lookup tables and registers. We investigate the state-of-the-art modular inversion algorithms, and evaluate the performance and cost of the algorithms and their hardware implementations. We then propose a high-radix modular inversion algorithm aimed at reducing the execution time and hardware costs. We present a detailed radix-8 hardware implementation based on 256-bit primes in Verilog HDL and compare its cost performance to other implementations. Our implementation on the Altera Cyclone V FPGA chip used 1227 ALMs (adaptive logic modules) and 1037 registers. The modular inversion calculation took 3.67 ms. The AT (area–time) factor was 8.30, outperforming the other implementations. We also present an implementation of ECC using the proposed radix-8 modular inversion algorithm. The implementation results also showed that our modular inversion algorithm was more efficient in area–time than the other algorithms. Full article

The global consumption of dried mushrooms has increased worldwide because of their rich nutritional value and culinary versatility. Dehydration methods such as sun drying, hot air drying, freeze drying, and microwave drying are employed to prolong the shelf life of a food product. These methods can also affect the food product’s nutritional value and the final product’s microbial profile. Each technique affects the retention of essential nutrients like vitamins, minerals, and bioactive compounds differently. Additionally, these techniques vary in their effectiveness at reducing microbial load, impacting the dried mushrooms’ safety and shelf life. This review addresses the gap in understanding how different dehydration methods influence dried mushrooms’ nutritional quality and microbial safety, which is crucial for optimizing their processing and consumption. It targets researchers, food processors, and consumers seeking to improve the quality and safety of dried mushrooms. This review comprehensively examines the impact of major dehydration techniques, including sun drying, hot air drying, microwave drying, and freeze drying, on the nutritional and microbial profiles of dried mushrooms. Each method is evaluated for its effectiveness in preserving essential nutrients and reducing microbial load. Current research indicates that freeze drying is particularly effective in preserving nutritional quality, while hot air and microwave drying significantly reduce microbial load. However, more well-designed studies are needed to fully understand the implications of these methods for safety and nutritional benefits. These findings are valuable for optimizing dehydration methods for high-quality dried mushrooms that are suited for culinary and medicinal use. Full article

Curing modulation is one of the important processes in tobacco production, so it is crucial to recognize tobacco flue-curing states effectively and accurately. This study created a dataset of the complete tobacco flue-curing process in a bulk curing barn environment and proposed a lightweight recognition model based on a feature skip connections module. Firstly, the image data was enhanced using a color correction matrix, which was used to recover the true color of the tobacco leaf in order to reduce the misidentification of adjacent states. Secondly, the convolutional neural network model proposed in this paper introduced Spatially Separable convolution to enhance the extraction of tobacco leaf texture features. Then, the standard convolution in Short-Term Dense Concatenate (STDC) was replaced with Depthwise Separable Convolutional blocks with different expansion rates to reduce the number of model parameters and FLOPs (Floating Point Operations Per Second). Finally, the Tobacco Flue-Curing State Recognition Network (TFSNet) was constructed by combining the SimAm attention mechanism. The experimental results showed that the model accuracy was improved by 1.63 percentage points after the color correction process. The recognition accuracy of TFSNet for the seven states of tobacco flue-curing was as high as 98.71%. The number of params and the FLOPs of the TFSNet model were 203,058 and 172.39 M, which were 98.18% and 90.55% lower than that of the ResNet18 model, respectively. The size of the model was 0.78 mb, and the time consumed per frame was only 21 ms. Compared with the mainstream model, TFSNet significantly improved the detection speed while maintaining high accuracy, and it provided effective technical support for the intelligentization of the tobacco flue-curing process. Full article

During the construction and maintenance of asphalt pavement, a lot of non-renewable resources are consumed, which discharge a variety of waste gasses and smoke, causing a serious impact on the environment. Reducing society’s reliance on non-renewable resources is therefore key to improving sustainability. It is found that phase change materials (PCMs), as environmentally friendly materials, can spontaneously store and release heat energy by changing the phase state, thus reducing the adverse effect of temperature on asphalt pavement, reducing the occurrence of high-temperature stress, minimizing the cost of road construction and maintenance, and saving resources. In order to promote the application of PCMs in asphalt pavement, to promote self-controlling temperature technology for asphalt pavement, and to improve the sustainable development of asphalt pavement, this paper reviews the research status of PCMs in asphalt pavement, both domestically and abroad. The results show that the thermal conductivity of the modified asphalt binder can reach 0.29–0.39 W/mK, and the thermal diffusivity can reach 0.2–0.3 mm²/s, but the influence on the viscosity of the asphalt is limited, and both are less than 2000CP. The durability and thermal stability of the modified asphalt mixture are improved, and the maximum temperature can be lowered by 9 °C, which effectively reduces the occurrence of hightemperature stress. This review will help to better understand the function of PCMs and promote the sustainable development of green and environmentally friendly asphalt pavement. Full article

Generating pixel-level annotations for semantic segmentation tasks of high-resolution remote sensing images is both time-consuming and labor-intensive, which has led to increased interest in unsupervised methods. Therefore, in this paper, we propose an unsupervised multi-scale hybrid feature extraction network based on the CNN-Transformer architecture, referred to as MSHFE-Net. The MSHFE-Net consists of three main modules: a Multi-Scale Pixel-Guided CNN Encoder, a Multi-Scale Aggregation Transformer Encoder, and a Parallel Attention Fusion Module. The Multi-Scale Pixel-Guided CNN Encoder is designed for multi-scale, fine-grained feature extraction in unsupervised tasks, efficiently recovering local spatial information in images. Meanwhile, the Multi-Scale Aggregation Transformer Encoder introduces a multi-scale aggregation module, which further enhances the unsupervised acquisition of multi-scale contextual information, obtaining global features with stronger feature representation. The Parallel Attention Fusion Module employs an attention mechanism to fuse global and local features in both channel and spatial dimensions in parallel, enriching the semantic relations extracted during unsupervised training and improving the performance of unsupervised semantic segmentation. K-means clustering is then performed on the fused features to achieve high-precision unsupervised semantic segmentation. Experiments with MSHFE-Net on the Potsdam and Vaihingen datasets demonstrate its effectiveness in significantly improving the accuracy of unsupervised semantic segmentation. Full article