Proposed Model Research Articles

SADCNN-ORBM: a hybrid deep learning model based citrus disease detection and classification

Citrus disease has a significant influence on agricultural productivity these days, so technology based on artificial intelligence has been developed for creating computer vision (CV) models. By spotting disease in its early stages and enabling necessary productivity actions, CV in agriculture improves the production of agricultural goods. In this paper, we developed a CV-based citrus disease detection model called the self-attention dilated convolutional neural network optimized restricted Boltzmann machine (SADCNN-ORBM) model, which consists of two crucial parts: a SADCNN for disease segmentation and an ORBM optimized by the self-adaptive coati optimization (SACO) algorithm to improve the classification performance of diseases, which successfully divides the disease type into three groups: anthracnose, melanose, and brown spot. Numerous feature sets, such as texture features, three-channel red, green, blue (RGB) features, local binary pattern (LBP) features, and speeded-up robust features (SURF) features, are combined and given as input into the classification layer in the proposed model. We compare our proposed model's performance with existing methods by using several evaluation metrics. The findings demonstrate the SADCNN-ORBM model's superiority in precisely recognizing and classifying citrus illnesses, outperforming all available techniques.

A novel dynamic enterprise architecture model: leveraging MAPE-K loop and case-based reasoning for context awareness

Nowadays, enterprises are required to take the uncertainty of the environment as decisive factor of success. For this reason, Enterprises should be prepared up-stream to react dynamically to the turbulent context. Considering that enterprise architecture is a tool drawing a blueprint that gives a holistic view of the enterprise, this blueprint should be able to represent this awareness to context and implements the techniques and mechanisms to react in a dynamic manner depending on the triggers of change. In this paper, the proposed model stipulates a “context-awareness” that monitors the internal and external context, and then adapt its reaction in alignment with the prefixed goals. The operationalization of our conception is realized through the monitor-analyze-plan-execute-knowledge (MAPE-K) loop, the case-based reasoning and machine learning techniques organized and orchestrated through a global algorithm of 6 main functions to monitor, compare, analyze, plan, execute and enrich the knowledge base. The results are verified in the light of a case study that demonstrates the applicability of our proposed model.

Self-Supervised Pre-Training for Deep Image Prior-Based Robust PET Image Denoising

Deep image prior (DIP) has been successfully applied to positron emission tomography (PET) image restoration, enabling represent implicit prior using only convolutional neural network architecture without training dataset, whereas the general supervised approach requires massive low-and high-quality PET image pairs. To answer the increased need for PET imaging with DIP, it is indispensable to improve the performance of the underlying DIP itself. Here, we propose a self-supervised pre-training model to improve the DIP-based PET image denoising performance. Our proposed pre-training model acquires transferable and generalizable visual representations from only unlabeled PET images by restoring various degraded PET images in a self-supervised approach. We evaluated the proposed method using clinical brain PET data with various radioactive tracers (18F-florbetapir, 11C-Pittsburgh compound-B, 18F-fluoro-2-deoxy-D-glucose, and 15O-CO2) acquired from different PET scanners. The proposed method using the self-supervised pre-training model achieved robust and state-of-the-art denoising performance while retaining spatial details and quantification accuracy compared to other unsupervised methods and pre-training model. These results highlight the potential that the proposed method is particularly effective against rare diseases and probes and helps reduce the scan time or the radiotracer dose without affecting the patients.

Conversational AI: An Explication of Few-Shot Learning Problem in Transformers-Based Chatbot Systems

With the recent advancements in conversational artificial intelligence (AI), the practical applications of chatbots have risen significantly in diverse domains such as healthcare, education, e-government, customer support systems, social platforms, and entertainment. The chatbot converses with humans in natural language and responds to their queries with precise and relevant answers. The relevant literature presents several methods for intent classification and slot mapping for chatbot question answering. However, the existing chatbot architectures still suffer from few-shot learning problem (imbalance ratio of class labels over samples) and ineffective dialog management to retain the context and slots mapping. This study aims to introduce the architecture of chatbot by focusing few-shot learning problem and context management in dialog-based conversations. First, to mitigate the few-shot learning problem with chatbots, we propose a novel hybrid intent and slots transformers (HIST) model. The HIST chatbot architecture utilizes transformers and self-attention mechanisms along with bigated recurrent unit and combines conditional random field algorithms for intent classification and slot extraction. Second, to address dialog management, we introduce a hybrid interaction strategy for slots mapping and effective conversational context management. To validate the proposed model’s effectiveness, comprehensive empirical analysis is carried out using three benchmark datasets including airline travel information system (ATIS), banking77, and conversational language interface for natural conversation 150 (CLINC150). The results show that HIST outperforms against the state-of-the-art existing methods with a clear margin and obtained an accuracy of 94.89% and 96.17% for intent classification and slots extraction, respectively. The empirical results confirm the effectiveness of the HIST chatbot for resolving the few-shot learning problem with effective dialog management in chatbot systems.

Performance evaluation of adaptive offloading model using hybrid machine learning and statistic prediction

We introduce fast sensor diagnosis and focuses on intelligent offloading skills to enhance the sensor data screening efficiency. This study proposed the adaptive offloading model based on statistics-based prediction feedback and sensor candidate filtering. For the statistics-based filtering, sliding sensor grids and compounded sensor context were devised. This study also proposed hybrid prediction model using support vector machine (SVM) and k-nearest neighbors (KNN) machine training for the adaptive offloading. Therefore, the sensor information that is highly likely to be the cause of the actual device faults can be selected and transmitted, resulting in improved offloading performance. The test results through Google Colab show that the fault prediction accuracy of proposed models is 95%.

Multi-Instance Learning with One Side Label Noise

Multi-instance Learning (MIL) is a popular learning paradigm arising from many real applications. It assigns a label to a set of instances, which is called a bag, and the bag’s label is determined by the instances within it. A bag is positive if and only if it has at least one positive instance. Since labeling bags is more complicated than labeling each instance, we will often face the mislabeling problem in MIL. Furthermore, it is more common that a negative bag has been mislabeled to a positive one, since one mislabeled instance will lead to the change of the whole bag label. This is an important problem that originated from real applications, e.g., web mining and image classification, but little research has concentrated on it as far as we know. In this article, we focus on this MIL problem with one side label noise that the negative bags are mislabeled as positive ones. To address this challenging problem, we propose, to the best our our knowledge, a novel multi-instance learning method with one side label noise. We design a new double weighting approach under traditional framework to characterize the “faithfulness” of each instance and each bag in learning the classifier. Briefly, on the instance level, we employ a sparse weighting method to select the key instances, and the MIL problem with one size label noise is converted to a mislabeled supervised learning scenario. On the bag level, the weights of bags, together with the selected key instances, will be utilized to identify the real positive bags. In addition, we have solved our proposed model by an alternative iteration method with proved convergence behavior. Empirical studies on various datasets have validated the effectiveness of our method.

Your Career Path Matters in Person-Job Fit

We are again confronted with one of the most vexing aspects of the advancement of technology: automation and AI technology cause the devaluation of human labor, resulting in unemployment. With this background, automatic person-job fit systems are promising solutions to promote the employment rate. The purpose of person-job fit is to calculate a matching score between the job seeker's resume and the job posting, determining whether the job seeker is suitable for the position. In this paper, we propose a new approach to person-job fit that characterizes the hidden preference derived from the job seeker's career path. We categorize and utilize three types of preferences in the career path: consistency, likeness, and continuity. We prove that understanding the career path enables us to provide more appropriate career suggestions to job seekers. To demonstrate the practical value of our proposed model, we conduct extensive experiments on real-world data extracted from an online recruitment platform and then present detailed cases to show how the career path matter in person-job fit.

HAGO-Net: Hierarchical Geometric Massage Passing for Molecular Representation Learning

Molecular representation learning has emerged as a game-changer at the intersection of AI and chemistry, with great potential in applications such as drug design and materials discovery. A substantial obstacle in successfully applying molecular representation learning is the difficulty of effectively and completely characterizing and learning molecular geometry, which has not been well addressed to date. To overcome this challenge, we propose a novel framework that features a novel geometric graph, termed HAGO-Graph, and a specifically designed geometric graph learning model, HAGO-Net. In the framework, the foundation is HAGO-Graph, which enables a complete characterization of molecular geometry in a hierarchical manner. Specifically, we leverage the concept of n-body in physics to characterize geometric patterns at multiple spatial scales. We then specifically design a message passing scheme, HAGO-MPS, and implement the scheme as a geometric graph neural network, HAGO-Net, to effectively learn the representation of HAGO-Graph by horizontal and vertical aggregation. We further prove DHAGO-Net, the derivative function of HAGO-Net, is an equivariant model. The proposed models are validated by extensive comparisons on four challenging benchmarks. Notably, the models exhibited state-of-the-art performance in molecular chirality identification and property prediction, achieving state-of-the-art performance on five properties of QM9 dataset. The models also achieved competitive results on molecular dynamics prediction task.

Photovoltaic module temperature prediction using various machine learning algorithms: Performance evaluation

This paper presents data-driven models for photovoltaic module temperature prediction and analyzes the relation and effects of ambient conditions to module temperature. A total of 12 different machine learning and regression algorithms are implemented, with a large experimental dataset of 345,600 × 7. Prior to implementing those algorithms, data preprocessing is performed to prepare the datasets and determine the informative attributes for the models. Using PCA with module temperature as target to predict, the selected features for models' inputs were determined to be ambient temperature, solar radiation, wind speed, and relative humidity, and each algorithm is cross-validated and tuned with optimal performance parameters. Results show that while relative humidity is more likely to introduce less information to the model, other aforementioned features are the important parameters to predict the module temperature. While for linear modeling, LASSO algorithm provided the best performance, the ANN model demonstrated the best overall results as it produced the most accurate predictions with lowest errors. A similar performance is attained by the proposed non-linear model, KRR and Gradient Boosting algorithm, with a slight advantage to the KRR model. Furthermore, in comparison to experimental data, the ANN model and the proposed non-linear model provided an R2 values of 0.986 and 0.981, with a MAE of 0.982 and 1.476, and MSE of 2.181and 3.464, respectively. Moreover, the proposed model supplied accurate results when compared to models from literature in an out-of-sample testing, it also proven to be robust and accurate when used to predict the PV power output.

An energy-aware module placement strategy in fog-based healthcare monitoring systems

AbstractFog computing and the Internet of Things (IoT) have revolutionized healthcare monitoring systems, enabling real-time health data collection and transmission while overcoming cloud computing limitations. However, efficiently selecting fog nodes for application modules with varying deadline requirements and ensuring adherence to quality of service (QoS) criteria pose significant challenges due to resource constraints and device limitations. In this paper, we present a novel two-layered hierarchical design for fog devices, leveraging cluster aggregation to optimize the selection of fog nodes for healthcare applications. We introduce three efficient algorithms to minimize system latency and reduce energy consumption in fog computing environments. Our proposed model is rigorously evaluated using the iFogSim toolkit and compared with cloud-based and latency-aware model [Mahmud R, Ramamohanarao K, Buyya R in ACM Transactions on Internet Technology.19, 2018, 10.1145/3186592]. In four distinct network topologies, our model exhibits an average latency reduction of at least 87% and energy consumption reduction of at least 76% when compared to the Cloud-based model. Similarly, when compared to the Latency-aware model proposed in [Mahmud R, Ramamohanarao K, Buyya R in ACM Transactions on Internet Technology. 19, 2018, 10.1145/3186592], our model showcases a minimum reduction of 43% in average latency and 27% in energy consumption. Our contribution lies in addressing the complexity of selecting fog nodes for application modules with diverse deadline requirements, while ensuring QoS. This work advances the field of real-time healthcare monitoring systems, promising substantial improvements in efficiency and effectiveness.

On optimal reinsurance in the presence of premium budget constraint and reinsurer’s risk limit

Abstract In this paper, we propose two new optimal reinsurance models in which both premium budget constraints and the reinsurer’s risk limits are taken into account. To be precise, we assume that the reinsurance premium has an upper bound, and that the admissible ceded loss functions have a pre-specified upper limit. Moreover, we assume that the reinsurance premium principle is calculated by the expected value premium principle. Under the optimality criteria of minimizing the value at risk and conditional value at risk of the insurer’s total risk exposure, we derive the explicit optimal reinsurance treaties, which are layer reinsurance treaties. A new approach is developed to construct the optimal reinsurance treaties. Comparisons with existing studies are also made. Finally, we provide a numerical study based on real data and an example to illustrate the proposed models and results. Our work provides a novel generalization of several known achievements in the literature.

Multi-Think Transformer for Enhancing Emotional Health

The smart healthcare system not only focuses on physical health but also on emotional health. Music therapy, as a non-pharmacological treatment method, has been widely used in clinical treatment, but music selection and generation still require manual intervention. AI music generation technology can assist people in relieving stress and providing more personalized and efficient music therapy support. However, existing AI music generation highly relies on the note generated at the current time to produce the note at the next time. This will lead to disharmonious results. The first reason is the small errors being ignored at the current generated note. This error will accumulate and spread continuously, and finally make the music become random. To solve this problem, we propose a music selection module to filter the errors of generated note. The multi-think mechanism is proposed to filter the result multiple times, so that the generated note is as accurate as possible, eliminating the impact of the results on the next generation process. The second reason is that the results of multiple generation of each music clip are not the same or even do not follow the same music rules. Therefore, in the inference phase, a voting mechanism is proposed in this paper to select the note that follow the music rules that most experimental results follow as the final result. The subjective and objective evaluations demonstrate the superiority of our proposed model in generation of more smooth music that conforms to music rules. This model provides strong support for clinical music therapy, and provides new ideas for the research and practice of emotional health therapy based on the Internet of Things.

DeepMeshCity: A Deep Learning Model for Urban Grid Prediction

Urban grid prediction can be applied to many classic spatial-temporal prediction tasks such as air quality prediction, crowd density prediction, and traffic flow prediction, which is of great importance to smart city building. In light of its practical values, many methods have been developed for it and have achieved promising results. Despite their successes, two main challenges remain open: a) how to well capture the global dependencies and b) how to effectively model the multi-scale spatial-temporal correlations? To address these two challenges, we propose a novel method— DeepMeshCity , with a carefully-designed Self-Attention Citywide Grid Learner ( SA-CGL ) block comprising of a self-attention unit and a Citywide Grid Learner ( CGL ) unit. The self-attention block aims to capture the global spatial dependencies, and the CGL unit is responsible for learning the spatial-temporal correlations. In particular, a multi-scale memory unit is proposed to traverse all stacked SA-CGL blocks along a zigzag path to capture the multi-scale spatial-temporal correlations. In addition, we propose to initialize the single-scale memory units and the multi-scale memory units by using the corresponding ones in the previous fragment stack, so as to speed up the model training. We evaluate the performance of our proposed model by comparing with several state-of-the-art methods on four real-world datasets for two urban grid prediction applications. The experimental results verify the superiority of DeepMeshCity over the existing ones. The code is available at https://github.com/ILoveStudying/DeepMeshCity.

Research on contactless intelligent medication pickup mode selection based on a hospital in China under COVID-19.

During an outbreak such as COVID-19, hospital staff needs to be in close contact with all types of patients visiting the hospital and the risk of cross-infection is extremely high. Payment and medication pickup is a mandatory part of a patient's hospital visit, with direct contact between healthcare workers and patients, and long waiting times in the hospital area, which can easily lead to the spread of disease infection. This paper designed the prototype of a contactless smart medicine cabinet based on RFID technology and optimized the patient consultation and medication pickup process to address these problems. We conducted a 50-day field observation of patients for consultation and medication pickup at the First Hospital in H city, Jiangsu Province, China, and randomly timed 1600 sets of data from Surgery (ophthalmology) and Internal patients, then we designed the prototype of a contactless smart medicine cabinet based on RFID technology, optimized the patient consultation and medication pickup process, comparing the traditional and intelligent models using AnyLogic. The results show that this contactless medicine cabinet was able to reduce the time taken by patients in consultation and medicine pickup by 18.74 minutes, increasing the overall efficiency of the consultation by 32.20%. The simulation revealed that this contactless intelligent medication pickup model was able to reduce the time taken by patients in consultation and medicine pickup, increasing the overall efficiency of the consultation, effectively reducing the frequency of contact between healthcare workers and patients, and reducing the risk of disease infection. The proposed technical model provides a new idea to solve the problems of long queues, low efficiency and high risk of infection for patients to consult and get medicine during epidemics. Especially within hospitals it has important theoretical and practical implications for epidemic prevention and control as well as future hospital management.

Multi-sensor fusion based optimized deep convolutional neural network for boxing punch activity recognition

Recent advancements in deep learning have significantly enhanced the recognition of player activities in sports by enabling automatic feature extraction. In our proposed work, we focus on recognizing six distinct punches in the context of boxing. We incorporate the sliding window technique during the pre-processing stage to transform the time-series data obtained from Inertial Measurement Unit (IMU) sensors in a boxing punch activity recognition system. Our approach influences a sensor fusion-based Deep Convolutional Neural Network (DCNN) classification model to identify various boxing punches accurately, achieving an impressive F1 score. The system demonstrates proficiency in distinguishing similar activities, such as jab and hook punches where the existing systems made misclassifications due to subtle variations in arm flexion that differentiate the two. Through experimentation, we identify an optimal window size for boxing punch activity recognition, which falls within the range of 15–20 frames (equivalent to 0.15–0.25 s). This window size selection results in a notable reduction in inference time. To evaluate our proposed model, we conduct comparisons with a standard DCNN and an optimized DCNN model. Our proposed optimized DCNN model demonstrates enhanced recognition accuracy, achieving an impressive 99%, coupled with an improved F1 score of 87%. Furthermore, the model displays a remarkable reduction in inference time, clocking in at less than 1 ms. Overall, our research contributes to the field of sports-related player activity recognition by employing the power of deep learning. By expertly combining these techniques, we achieve remarkable accuracy, precision, and efficiency in recognizing various boxing punches.

Fully Automated Identification of Lymph Node Metastases and Lymphovascular Invasion in Endometrial Cancer From Multi-Parametric MRI by Deep Learning.

Early and accurate identification of lymphatic node metastasis (LNM) and lymphatic vascular space invasion (LVSI) for endometrial cancer (EC) patients is important for treatment design, but difficult on multi-parametric MRI (mpMRI) images. To develop a deep learning (DL) model to simultaneously identify of LNM and LVSI of EC from mpMRI images. Retrospective. Six hundred twenty-one patients with histologically proven EC from two institutions, including 111 LNM-positive and 168 LVSI-positive, divided into training, internal, and external test cohorts of 398, 169, and 54 patients, respectively. T2-weighted imaging (T2WI), contrast-enhanced T1WI (CE-T1WI), and diffusion-weighted imaging (DWI) were scanned with turbo spin-echo, gradient-echo, and two-dimensional echo-planar sequences, using either a 1.5 T or 3 T system. EC lesions were manually delineated on T2WI by two radiologists and used to train an nnU-Net model for automatic segmentation. A multi-task DL model was developed to simultaneously identify LNM and LVSI positive status using the segmented EC lesion regions and T2WI, CE-T1WI, and DWI images as inputs. The performance of the model for LNM-positive diagnosis was compared with those of three radiologists in the external test cohort. Dice similarity coefficient (DSC) was used to evaluate segmentation results. Receiver Operating Characteristic (ROC) analysis was used to assess the performance of LNM and LVSI status identification. P value <0.05 was considered significant. EC lesion segmentation model achieved mean DSC values of 0.700 ± 0.25 and 0.693 ± 0.21 in the internal and external test cohorts, respectively. For LNM positive/LVSI positive identification, the proposed model achieved AUC values of 0.895/0.848, 0.806/0.795, and 0.804/0.728 in the training, internal, and external test cohorts, respectively, and better than those of three radiologists (AUC = 0.770/0.648/0.674). The proposed model has potential to help clinicians to identify LNM and LVSI status of EC patients and improve treatment planning. 3 TECHNICAL EFFICACY: Stage 2.

Modelling the unsteady lift of a pitching NACA 0018 aerofoil using state-space neural networks

The development of simple, low-order and accurate unsteady aerodynamic models represents a crucial challenge for the design optimisation and control of fluid dynamical systems. In this work, wind tunnel experiments of a pitching NACA 0018 aerofoil conducted at a Reynolds number $Re = 2.8 \times 10^5$ and at different free-stream turbulence intensities are used to identify data-driven nonlinear state-space models relating the time-varying angle of attack of the aerofoil to the lift coefficient. The proposed state-space neural network (SS-NN) modelling technique explores an innovative methodology, which brings the flexibility of artificial neural networks into a classical state-space representation and offers new insights into the construction of reduced-order unsteady aerodynamic models. The work demonstrates that this technique provides accurate predictions of the nonlinear unsteady aerodynamic loads of a pitching aerofoil for a wide variety of angle-of-attack ranges and frequencies of oscillation. Results are compared with a modified version of the Goman–Khrabrov dynamic stall model. It is shown that the SS-NN methodology outperforms the classical semi-empirical dynamic stall models in terms of accuracy, while retaining a fast evaluation time. Additionally, the proposed models are robust to noisy measurements and do not require any pre-processing of the data, thus involving only a limited user interaction. Overall, these features make the SS-NN technique an excellent candidate for the construction of accurate data-driven models from experimental fluid dynamics data, and pave the way for their adoption in applications entailing design optimisation and real-time control of systems involving lift.

Radioport: a radiomics-reporting network for interpretable deep learning in BI-RADS classification of mammographic calcification

Objective. Generally, due to a lack of explainability, radiomics based on deep learning has been perceived as a black-box solution for radiologists. Automatic generation of diagnostic reports is a semantic approach to enhance the explanation of deep learning radiomics (DLR). Approach. In this paper, we propose a novel model called radiomics-reporting network (Radioport), which incorporates text attention. This model aims to improve the interpretability of DLR in mammographic calcification diagnosis. Firstly, it employs convolutional neural networks to extract visual features as radiomics for multi-category classification based on breast imaging reporting and data system. Then, it builds a mapping between these visual features and textual features to generate diagnostic reports, incorporating an attention module for improved clarity. Main results. To demonstrate the effectiveness of our proposed model, we conducted experiments on a breast calcification dataset comprising mammograms and diagnostic reports. The results demonstrate that our model can: (i) semantically enhance the interpretability of DLR; and, (ii) improve the readability of generated medical reports. Significance. Our interpretable textual model can explicitly simulate the mammographic calcification diagnosis process.

DGAMDA: Predicting miRNA-disease association based on dynamic graph attention network.

MiRNA (microRNA)-disease association prediction has essential applications for early disease screening. The process of traditional biological experimental validation is both time-consuming and expensive. However, as artificial intelligence technology continues to advance, computational methods have become efficient tools for predicting miRNA-disease associations. These methods often rely on the combination of multiple sources of association data and require improved feature mining. This study proposes a dynamic graph attention-based association prediction model, DGAMDA, which combines feature mapping and dynamic graph attention mechanisms through feature mining on a single miRNA-disease association network. DGAMDA effectively solves the problems of feature heterogeneity and inadequate feature mining by previous static graph attention mechanisms and achieves high-precision feature mining and association scoring prediction. We conducted a five-fold cross-validation experiment and obtained the mean values of Accuracy, Precision, Recall, and F1-score, which were .8986, .8869, .9115, and .8984, respectively. Our proposed model outperforms other advanced models in terms of experimental results, demonstrating its effectiveness in feature mining and association prediction based on a single association network. In addition, our model can also be used to predict miRNAs associated with unknown diseases.

Optimizing the Economic Order Quantity Using Fuzzy Theory and Machine Learning Applied to a Pharmaceutical Framework

In this article, we present a novel methodology for inventory management in the pharmaceutical industry, considering the nature of its supply chain. Traditional inventory models often fail to capture the particularities of the pharmaceutical sector, characterized by limited storage space, product degradation, and trade credits. To address these particularities, using fuzzy logic, we propose models that are adaptable to real-world scenarios. The proposed models are designed to reduce total costs for both vendors and clients, a gap not explored in the existing literature. Our methodology employs pentagonal fuzzy number (PFN) arithmetic and Kuhn–Tucker optimization. Additionally, the integration of the naive Bayes (NB) classifier and the use of the Weka artificial intelligence suite increase the effectiveness of our model in complex decision-making environments. A key finding is the high classification accuracy of the model, with the NB classifier correctly categorizing approximately 95.9% of the scenarios, indicating an operational efficiency. This finding is complemented by the model capability to determine the optimal production quantity, considering cost factors related to manufacturing and transportation, which is essential in minimizing overall inventory costs. Our methodology, based on machine learning and fuzzy logic, enhances the inventory management in dynamic sectors like the pharmaceutical industry. While our focus is on a single-product scenario between suppliers and buyers, future research hopes to extend this focus to wider contexts, as epidemic conditions and other applications.