Explore the vast range of titles available.

The timely diagnosis and identification of apple leaf diseases is essential to prevent the spread of diseases and ensure the sound development of the apple industry. Convolutional neural networks (CNNs) have achieved phenomenal success in the area of leaf disease detection, which can greatly benefit the agriculture industry. However, their large size and intricate design continue to pose a challenge when it comes to deploying these models on lightweight devices. Although several successful models (e.g., EfficientNets and MobileNets) have been designed to adapt to resource-constrained devices, these models have not been able to achieve significant results in leaf disease detection tasks and leave a performance gap behind. This research gap has motivated us to develop an apple leaf disease detection model that can not only be deployed on lightweight devices but also outperform existing models. In this work, we propose AppViT, a hybrid vision model, combining the features of convolution blocks and multi-head self-attention, to compete with the best-performing models. Specifically, we begin by introducing the convolution blocks that narrow down the size of the feature maps and help the model encode local features progressively. Then, we stack ViT blocks in combination with convolution blocks, allowing the network to capture non-local dependencies and spatial patterns. Embodied with these designs and a hierarchical structure, AppViT demonstrates excellent performance in apple leaf disease detection tasks. Specifically, it achieves 96.38% precision on Plant Pathology 2021—FGVC8 with about 1.3 million parameters, which is 11.3% and 4.3% more accurate than ResNet-50 and EfficientNet-B3. The precision, recall and F score of our proposed model on Plant Pathology 2021—FGVC8 are 0.967, 0.959, and 0.963 respectively.

According to experts in neurology, brain tumours pose a serious risk to human health. The clinical identification and treatment of brain tumours rely heavily on accurate segmentation. The varied sizes, forms, and locations of brain tumours make accurate automated segmentation a formidable obstacle in the field of neuroscience. U-Net, with its computational intelligence and concise design, has lately been the go-to model for fixing medical picture segmentation issues. Problems with restricted local receptive fields, lost spatial information, and inadequate contextual information are still plaguing artificial intelligence. A convolutional neural network (CNN) and a Mel-spectrogram are the basis of this cough recognition technique. First, we combine the voice in a variety of intricate settings and improve the audio data. After that, we preprocess the data to make sure its length is consistent and create a Mel-spectrogram out of it. A novel model for brain tumor segmentation (BTS), Intelligence Cascade U-Net (ICU-Net), is proposed to address these issues. It is built on dynamic convolution and uses a non-local attention mechanism. In order to reconstruct more detailed spatial information on brain tumours, the principal design is a two-stage cascade of 3DU-Net. The paper’s objective is to identify the best learnable parameters that will maximize the likelihood of the data. After the network’s ability to gather long-distance dependencies for AI, Expectation–Maximization is applied to the cascade network’s lateral connections, enabling it to leverage contextual data more effectively. Lastly, to enhance the network’s ability to capture local characteristics, dynamic convolutions with local adaptive capabilities are used in place of the cascade network’s standard convolutions. We compared our results to those of other typical methods and ran extensive testing utilising the publicly available BraTS 2019/2020 datasets. The suggested method performs well on tasks involving BTS, according to the experimental data. The Dice scores for tumor core (TC), complete tumor, and enhanced tumor segmentation BraTS 2019/2020 validation sets are 0.897/0.903, 0.826/0.828, and 0.781/0.786, respectively, indicating high performance in BTS.

Background Health informatics is a multidisciplinary field that supports the use and management of health data to enhance the quality and efficiency of healthcare delivery. As digital transformation accelerates in healthcare systems, particularly in Saudi Arabia, there is a growing need to ensure that undergraduate education programs in this field meet both national priorities and international standards. Aim This study aimed to evaluate and compare the content of undergraduate health informatics programs in Saudi universities with international curriculum recommendations, and to explore professional stakeholder perceptions on essential educational components. Methods A mixed-methods design was used, combining a national cross-sectional survey of healthcare and academic professionals with document analysis of curricula from five universities offering undergraduate degrees in health informatics. The survey assessed perspectives on six educational domains, including technical, clinical, behavioural, managerial, and foundational knowledge areas. The document review evaluated program structures against globally recognized curriculum guidelines. Results A total of 127 experts completed the survey. Most respondents strongly supported the inclusion of a structured internship, with six months identified as the optimal duration. While all universities covered core technical and health content, there was substantial variation in how each emphasized different domains. For instance, one university focused heavily on data and computing, while others gave greater attention to health sciences or foundational principles. Differences were also observed between stakeholder expectations and international benchmarks, especially regarding applied skills, behavioural sciences, and leadership training. Conclusion Undergraduate health informatics programs in Saudi Arabia show encouraging progress but vary widely in structure and focus. The findings highlight the need for more standardized educational models that integrate practical skills and international best practices while responding to local healthcare needs. This study offers actionable insights for policymakers and educators aiming to improve health informatics education and workforce readiness in a global context. Clinical trial number Not applicable.

Agriculture sector is faced with perennial challenges that threaten both its productivity and sustainability. Among the greatest threats to cereal crops is disease, especially on cereal grains such as maize. Maize is an important grain that has grown globally, yet it often falls prey to maize leaf disease, a destructive and prevalent disorder. The consequences of these diseases go beyond individual farmers; reduced yields destabilize supply chains, market stability, and global efforts towards creating sustainable food systems. The prevalence of leaf diseases adversely affects crop productivity, which directly impacts the objective of sustainable agriculture. In order to address this problem, technology, more specifically artificial intelligence, has been a game-changer. Adopting cutting-edge research for maize disease detection not only raises diagnostic accuracy but also supports sustainable agricultural practices. This approach encourages effective input use, supports food security, minimizes environmental degradation, and provides farmers with accurate tools, all of which contribute to long-term agricultural resilience and sustainability. However, the incorporation of AI in farming is confronted by a number of challenges. Numerous hindrances hinder precise detection and categorization of maize leaf diseases via artificial intelligence methods. In tackling the limitations, the current study introduces an AI-based approach. It applied Multi-scaled Xception pre-trained models to extract deep features from images. The models were fine-tuned with varying weights for advancing the feature extraction so as to enhance the likelihood of correct visual classification. In addition to its strong accuracy, the research provides a formal and strict mathematical formulation, and different optimization methods further establish the effectiveness of the model. Additionally, the examination of fusion operators helps to improve the interpretability of the model. The expected model was tested with a confidence interval, showing that its performance remains within set limits. Key Highlights Different kinds of leaf diseases in maize is classified using a multi-scale Xception network (MXception). A variety of procedures were used to produce a feature map. MXception has an accuracy of 98.65%. The predicted model's performance has been validated by many optimization parameters.

There is an urgent need to develop a master's program in Digital Health in Malaysia's medical schools to produce and meet the demands of qualified professionals in the digital health industry. This study aims to assess the relevance of the Master of Digital Health program for capacity building and its suitability according to age, gender, nationality, and type of organization. This research was intended to understand employability and sponsorship availability from employers for a career in digital health. An online survey consisted of 14 questions on sociodemographic information and opinions of program relevancy, program duration, program coverage, learning outcomes, sponsorship availability from employers, and willingness to employ digital health graduates. The analysis of variance (ANOVA) was used to explore relationships among sociodemographic variables and program relevancy and learning outcomes. Overall, the proposed program received a high percentage of agreement in terms of program relevance, course structure and duration (i.e., twelve months). The program's learning outcomes were deemed suitable across gender, nationality, age group, and type of organization. There is a need to have a postgraduate education program that is competency-based to produce Digital Health experts who can lead digital transformation in healthcare.

The diversity of consumer demand for take-out food has led to the characteristic structure of one order with multiple items, where the different food items in a single order are provided by two or more merchants. In the context of multi-item delivery for take-out orders with time windows, this study investigates vehicle routing for order delivery. This research aims to improve the service level of merchants and the efficiency of delivery vehicles. Food vendors receive orders from consumers through online platforms, then package the food items according to the orders. This method is a preliminary exploration of the issue of fulfilment of takeout orders on online platforms, and can provide preliminary theoretical support for decision-making on the delivery process of takeout orders on online platforms. In the context of online catering sales platforms and offline food sales merchants, this paper studies the delivery problem of takeaway orders with a time window and the characteristics of one order and multiple items, and constructs a method that takes the order delivery time requirements into account and minimizes the total order fulfilment cost. Taking into account the time window constraints of both physical restaurants and consumers, genetic algorithms are utilized to solve the order delivery problem. Finally, through case studies and experiments, the effectiveness and feasibility of the mathematical model are validated. Practical recommendations and insights are provided from the perspective of management and route planning.

In this paper, a novel intelligent transportation framework called graph convolutional neural network for distributed machine learning (GCN-DML) is presented. Its primary application is traffic forecasting in large-scale, dynamically-evolving traffic scenarios. One unique method in traffic forecasting, called GCN-DML, is that it allows user data to be processed locally on edge devices, removing the requirement to send all data to CS (CS). Designed specifically for edge computing, this distributed machine learning framework makes it easier to train neural networks on a variety of edge devices. In addition to protecting user privacy, this method reduces the difficulties related to centralised neural network training, minimises communication delays, lowers data transfer quantities, and improves overall data processing efficiency. GCN-LSTM, the composite graph convolutional networks used in this framework, combine edge-enhanced attention mechanisms with the feature transmission capabilities of graph convolutional neural networks to effectively handle the challenging task of traffic forecasting. Even as the number of cars in the network rises, they perform exceptionally well at quickly extracting and sending interaction information between vehicles, while preserving high prediction accuracy and low time complexity. The versatility of GCN-DML is extended to a range of traffic forecasting application scenarios, whereby edge devices can adjust the kind and scale of the neural network according to available compute and storage resources, all without sacrificing performance. The usefulness of GCN-DML in traffic forecasting is demonstrated by experimental evaluations on the NGSIM public dataset, where it outperforms other models with better computation time and prediction performance. It obtains noteworthy F1 scores of 0.9473, 0.9557, and 0.9391, respectively, for recall, precision, and precision. Even when there is an increase in the number of cars, the accuracy remains high, reaching 91.21%, even with a prediction length of only 1 s. At the same time, the time complexity remains low, under 0.1 s. These findings clearly demonstrate the effectiveness and potency of GCN-DML as a traffic forecasting tool for intelligent transportation systems.

Recent developments in research have shown that knowledge graphs (KG) are successful in supplying useful external knowledge to enhance recommendation systems (RS). High-order connections between two items with one or more related qualities can be encoded in a knowledge graph. It is now feasible to extract both object properties and relations from KG with the aid of developing Graph Neural Networks (GNN), which is crucial for making good suggestions. In this study, word2vec creates virtual neighbors for nodes to make up for the lack of social connection data and knowledge graph representation learning mines item characteristics to extract additional data from the graph structure of social interactions. Numerous experimental findings on the two simple data sets, Douban and Yelp, show the accuracy and superiority of the MSAKR algorithm. These include a knowledge graph, multi-task training, training the recommendation module, and the knowledge graph concurrently to integrate item attributes. The information graph's deep reasoning capability is not utilized in this study; instead, ordinary representation learning is used. Social interactions support recommendations as well. The experimental findings demonstrate that the suggested model performs better than alternative benchmark models.

Integrating Data-driven Mobile Computing Systems, the narrowband Internet of Things (NB-IoT) emerges as a pivotal communication technology facilitating the realization of a seamlessly interconnected ecosystem. While striving to broaden communication coverage and bolster overall reliability, NB-IoT entails trade-offs in performance benchmarks, notably latency, which can pose challenges in dynamically accommodating mobile IoT devices. In light of these intricacies, this paper introduces a dedicated wireless resource allocation strategy tailored to NB-IoT, specifically focusing on its applicability to mobile devices. Central to this innovative approach is utilizing Kalman filtering to predict the mobile positions of IoT devices. Additionally, the study formulates mathematical models to estimate communication reliability, supplemented by quantitative evaluations encompassing pivotal performance metrics such as block error rate, latency, and energy consumption. The paper further introduces an optimization model and associated radio resource allocation methodologies. Extensive simulation experiments are conducted employing real-world datasets to substantiate the scheme's efficacy. The resultant experimental findings affirm the scheme's ability to effectively ensure a robust connection between mobile IoT devices and base stations and curtail latency concerns.

Given the growth of internet technology, lives are increasingly being led into the virtual world. Virtual functions such as working, shopping, or monitoring properties have been made possible by network interconnectivity. The Internet of Things (IoT), a quickly rising digital technology, is considered to be the third revolution in information technology after computers and internet. IoT is a network that has the ability to connect an object to the internet through sensors, smart devices, and smart equipment. There are many applications in IoT and the smart home is one of the most important. Smart homes have become part of people’s daily lives. Many people attempt to monitor and control their smart homes using smartphones, tablets, or computers because smart home systems make residential living areas more comfortable and convenient. Many devices in homes are now being connected to the internet; these devices can easily become targets for attacks and can cause serious problems that affect users’ lives. Some of these attacks are difficult to detect because attackers can be intelligent or use the same protocols that are employed by users to submit legitimate requests. Another issue is that anomalous requests can locate the existence of the smart home network environment and do not exhibit any malicious behavior. The security system in a smart home should have the capability to detect any expected threats that might come from the network, devices, sensors, or users. An intrusion detection system (IDS) is designed to detect and mitigate attacks on the network. However, various constraints on smart home sensors and device manufacturers do not ensure the security and privacy of the wireless sensor networks. This is because they use a one tier standard intrusion detection and most IDSs have crippling limitations that cannot provide accurate results. Therefore, this dissertation proposes an efficient framework called a Hybrid Intrusion Detection (HID-SMART) system. HID-SMART is a model that detects and examines smart home requests. The model utilizes analysis techniques on the network tier and employs static analysis techniques by matching the user profile. The first tier contained a machine learning technique. This technique is studied by the smart home’s network traffic. The second tier examines all requests sent to the system based on patterns of user behavior profiles. The reason for having a two-tiered intrusion detection system is to increase the system’s security and restrain the error rate since typically more than one user can control and monitor a smart home. HID-SMART employs several machine learning algorithms for the network behavior tier and a misuse detection technique for the user behavior tier. The model obtains approximately 95% accuracy and achieves less than a 0.1% false positive and false negative.