Reinforcement learning has been increasingly applied in monitoring applications because of its ability to learn from previous experiences and make adaptive decisions. However, existing machine learning-based health monitoring applications are mostly supervised learning algorithms, trained on labels, and they cannot make adaptive decisions in an uncertain, complex environment. This study proposes a novel and generic system, predictive deep reinforcement learning (PDRL), with multiple RL agents in a time series forecasting environment. The proposed generic framework accommodates virtual Deep Q Network (DQN) agents to monitor predicted future states of a complex environment with a well-defined reward policy so that the agent learns existing knowledge while maximizing their rewards. In the evaluation process of the proposed framework, three DRL agents were deployed to monitor a subject’s future heart rate, respiration, and temperature predicted using a BiLSTM model. With each iteration, the three agents were able to learn the associated patterns, and their cumulative rewards gradually increased. It outperformed the baseline models for all three monitoring agents. The proposed PDRL framework achieves state-of-the-art performance in time series forecasting by effectively integrating reinforcement learning agents with deep learning-based prediction. The proposed DRL agents and deep learning model in the PDRL framework are customized to enable transfer learning in other forecasting applications like traffic and weather, and monitor their states. The PDRL framework is able to learn the future states of the traffic and weather forecasting, and the cumulative rewards are gradually increasing over each episode.

Abstract Breast cancer is one of the leading causes of cancer-related morbidity worldwide, underscoring the need for advanced diagnostic tools to improve early detection and treatment outcomes. This study introduces MammoSegNet, a novel convolutional neural network architecture optimized for precisely segmenting mammographic images. The proposed MammoSegNet incorporates Inception-ResNet blocks, Squeeze-and-Excitation (SE) modules, and dilated convolutions to enable multi-scale feature extraction and efficient attention refinement while maintaining low computational complexity. MammoSegNet performance was rigorously evaluated on BCDR-D01 and INbreast datasets to examine its robustness and generalization. Using stratified fivefold cross-validation, the model was trained on BCDR-D01 and tested on the unseen INbreast dataset through Monte Carlo cross-validation. Preprocessing techniques, including Region of Interest (ROI) Isolation to concentrate on relevant areas, Normalization to standardized pixel intensities, and Data Augmentation to expand the dataset and enhance the model’s robustness, were employed. Additionally, a specialized image enhancement method called peak feature intensity transformation (PFIT) was designed to amplify diagnostic features while preserving structural integrity. Comparative evaluations confirmed MammoSegNet’s superior performance across metrics, achieving 97% accuracy on BCDR-D01 and 95% on INbreast. Statistical t-tests validated these improvements, and visual heatmaps demonstrated the model’s effectiveness in isolating tumor regions. These findings establish MammoSegNet as a promising tool for enhancing breast cancer diagnostic accuracy and reliability in medical applications.

Federated Learning (FL) is currently one of the most popular technologies in the field of Artificial Intelligence (AI) due to its collaborative learning and ability to preserve client privacy. However, it faces challenges such as non-identically and non-independently distributed (non-IID) data with imbalanced labels among local clients. To address these limitations, the research community has explored various approaches such as using local model parameters, federated generative adversarial learning, and federated representation learning. In our study, we propose a novel Clustered FedStack framework based on the previously published Stacked Federated Learning (FedStack) framework. Here, the local clients send their model predictions and output layer weights to a server, which then builds a robust global model. This global model clusters the local clients based on their output layer weights using a clustering mechanism. We adopt three clustering mechanisms, namely K-Means, Agglomerative, and Gaussian Mixture Models, into the framework and evaluate their performance. Bayesian Information Criterion (BIC) is used with the maximum likelihood function to determine the number of clusters. Our results show that Clustered FedStack models outperform baseline models with clustering mechanisms. To estimate the convergence of our proposed framework, we use Cyclical learning rates.

From the planting base to the consumer’s table, agricultural products must go through multiple links such as planting, processing, transportation, warehousing, and sales. The quality and safety of agricultural products have received extensive attention from all walks of life. Based on the block chain technology, this paper will build a traceability system for the quality and safety of agricultural products, refine the research objects, and design solutions from the aspects of overall structure, role authority, operating process, and functional modules according to the characteristics of planted agricultural products, so as to realize the whole process of agricultural product supply chain tracking, traceability to ensure the quality and safety of agricultural products.

Recent advances in remote patient monitoring (RPM) systems can recognize various human activities to measure vital signs, including subtle motions from superficial vessels. There is a growing interest in applying artificial intelligence (AI) to this area of healthcare by addressing known limitations and challenges such as predicting and classifying vital signs and physical movements, which are considered crucial tasks. Federated learning is a relatively new AI technique designed to enhance data privacy by decentralizing traditional machine learning modeling. However, traditional federated learning requires identical architectural models to be trained across the local clients and global servers. This limits global model architecture due to the lack of local models’ heterogeneity. To overcome this, a novel federated learning architecture, FedStack, which supports ensembling heterogeneous architectural client models was proposed in this study. This work offers a protected privacy system for hospitalized in-patients in a decentralized approach and identifies optimum sensor placement. The proposed architecture was applied to a mobile health sensor benchmark dataset from 10 different subjects to classify 12 routine activities. Three AI models, artificial neural network (ANN), convolutional neural network (CNN), and bidirectional long short-term memory (Bi-LSTM) were trained on individual subject data. The federated learning architecture was applied to these models to build local and global models capable of state-of-the-art performances. The local CNN model outperformed ANN and Bi-LSTM models on each subject data. Our proposed work has demonstrated better performance for heterogeneous stacking of the local models compared to homogeneous stacking. Further analysis of the global heterogeneous CNN model determined that the optimum placement of the sensors on human limbs resulted in better activity recognition. This work sets the stage to build an enhanced RPM system that incorporates client privacy to assist with clinical observations for patients in an acute mental health facility and ultimately help to prevent unexpected death.

Text classification (a.k.a text categorisation) is an effective and efficient technology for information organisation and management. With the explosion of information resources on the Web and corporate intranets continues to increase, it has being become more and more important and has attracted wide attention from many different research fields. In the literature, many feature selection methods and classification algorithms have been proposed. It also has important applications in the real world. However, the dramatic increase in the availability of massive text data from various sources is creating a number of issues and challenges for text classification such as scalability issues. The purpose of this report is to give an overview of existing text classification technologies for building more reliable text classification applications, to propose a research direction for addressing the challenging problems in text mining.

As China’s agricultural output has improved, the national and local monitoring system of agricultural product safety has become much better, and monitoring standards have become increasingly strict. Despite this, there are agricultural product safety incidents which have caused consumer panic. One way to address this is by properly establishing tracking systems so that agricultural product logistics in China can be tracked and monitored. We explored this research objective with agricultural traceability and security in mind. One option that could be considered is the blockchain technology. Blockchain could also be used to ascertain the provenance of agricultural products to increase the quality and safety of the Chinese agricultural supply chain. In this context, this research converged on big data and technology, platforms and other means for product quality and safety of agricultural products traceability. In order to verify the accuracy of these three convergence, regression analysis were used to construct five models for verification of three hypothesis. The results show that based on “Internet+”, using big data, big technology and big platform can significantly increase the accuracy of agricultural products traceability system hence improve consumer acceptance of the safety of agricultural products.

Determining the key factors that affect student engagement will assist academics to improve the student motivation. The Quality Indicators for Learning and Teaching (QILT) reports have shown low engagement levels in higher education students [21, 22, 23]. While factors such as online education, lack of attendance and poor design of course content have been attributed to this cause, it is still not clear as to the determination of those factors influencing student engagement in a higher education setting. In the modern tertiary settings, Information and Communication Technology (ICT) plays an essential role in disseminating the course related information with a Learning Management System (LMS) which become the platform to communicate crucial course-related information. Academics can develop course materials on these LMS' to engage students beyond the classrooms and students need to interact with those LMS' to get apprehend the transmitted knowledge. Since LMS' are operated on a computer platform, academics and students require strong ICT skills which are further utilized in preparation of course materials. Their relevance, appropriateness, the way various tasks are prepared, how communication is facilitated, the role and utilization of discussion forums and other social media structures available to students to interact with, and the way in which assessments are conducted, providing a Just in Time (JIT) type of knowledge students require. The investigation into these major factors forms the basis of this study. Thus, understanding how various factors related to LMS' in a tertiary setting influence student engagement and then determining those factors that contribute to this engagement are the main objective of this study. To pursue the main objective of this study, a hybrid method mainly involving a pseudo meta-analysis to unearth additional evidence required for the study, a comprehensive qualitative component to understand the sector factors and perhaps a small quantitative component to confirm the sector views will be employed.

Based on our ongoing work, this work in progress project aims to develop an automated system to detect distress in people to enable early referral for interventions to target anxiety and depression, to mitigate suicidal ideation and to improve adherence to treatment. The project will utilize either use existing voice data to assess people into various scales of distress, or will collect voice data as per existing standards of distress measurement, to develop basic computing algorithms required to detect various attributes associated with distress, detected through a person's voice in a telephone call to a helpline. This will be then matched with the already available psychological assessment instruments such as the Distress Thermometer for these persons. In order to trigger interventions, organizational contexts are essential as interventions rely on the type of distress. Therefore, the model will be tested on various organizational settings such as the Police, Emergency and Health along with the Distress detection instruments normally used in a psychological assessment for accuracy and validation. The outcome of the project will culminate in a fully automated integrated system, and will save significant resources to organizations. The translation of the project will be realized in step-change improvements to quality of life within the gamut of public policy.

Purpose: This paper aims to address concepts, visions and gaps in literature in the field of the relationship between talent management and knowledge management in business organisations. It also aims to develop a model for the relationship between talent management processes and knowledge management processes. This is because there are practical benefits for business organisations focused on developing knowledge and talents. Design/methodology/approach: This study takes on a detailed literature review of the relationship between talent and knowledge management in business organisations. Conclusion: The key conclusion for this research is that more research is required to examine further the relationship between talent management processes and knowledge management processes in the business environment. It also concludes that it is worth noting scholars' serious interest in attraction, development, and talent retention processes.

The emergence of knowledge-based economies has emphasised the importance of interactive knowledge management technologies, which have manifested themselves in the form of social networking tools. Organization's ability to leverage and manage the relevant knowledge is a sustainable strategic tool. This research focus on the ways in which social technologies facilitate knowledge sharing in the workplace. Findings uncovers key drivers of three dimensions of knowledge management, individual, organization and technology and suggest to connect them along with a knowledge process architecture for leveraging knowledge.

Although the smaller quantization parameter has smaller coding distortion of message source, the overall distortion rate at the receiver does not necessarily decrease as its quantization parameter decreases. The reason is that a smaller quantization parameter often means a long transmission queue, and a long transmission queue means a bigger loss rate and channel distortion. In this paper, we propose a packet loss-distortion driven cross-layer optimization of video transmission for H.264 video applications in 802.11e wireless networks. Firstly, we analyzed the relationship between quantization parameter and quantization distortion and built an estimation model of transmission distortion. Then the total distortions in the received station are estimated according to the packet loss rate of different video data partition. Secondly, a selection algorithm of optimal quantization parameter based on the total distortion is presented. Our experimental results demonstrate that, at certain loss rates, the proposed method not only outperforms the up-bottom cross-layer optimization with various queue priorities for video data partitions, but also outperforms the bottom-up cross-layer with an adaptive quantization step selection both in terms of received-end destination and video traffic.

Virtual expertise is a critical component of telehealth projects and it needs to be effectively managed if telehealth is to deliver on its potential. There are many issues within telehealth that relate in some way to the management of knowledge and we identify from a range of papers these specific issues. We propose a virtual expertise platform that provides the basic building blocks for effect leveraging of expertise in this domain. The platform includes management directives and goals, a collaborative culture, an appropriate ICT platform and a knowledge tools layer that interact facilitate knowledge sharing and ultimately improved patient care. We also emphasise how social media tools can be used as part of the knowledge tools layer to improve virtual knowledge sharing before and after the telehealth events.

In the 21stcentury and the emergence of a digital economy, knowledge and the knowledge base economy are rapidly growing. To effectively be able to understand the processes involved in the creating, managing and sharing of knowledge management in the business environment is critical to the success of an organization. This study builds on the previous research of the authors on the enablers of knowledge management by identifying the relationship between the enablers of knowledge management and the role played by information communication technologies (ICT) and ICT infrastructure in a business setting. This paper provides the findings of a survey collected from the four major Indian cities (Chennai, Coimbatore, Madurai and Villupuram) regarding their views and opinions about the enablers of knowledge management in business setting. A total of 80 organizations participated in the study with 100 participants in each city. The results show that ICT and ICT infrastructure can play a critical role in the creating, managing and sharing of knowledge in an Indian business environment.

In this research project, the enablers in implementing mobile KMS in Australian regional healthcare will be investigated, and a validated framework and guidelines to assist healthcare in implementing mobile KMS will also be proposed with both qualitative and quantitative approaches. The outcomes for this study are expected to improve the understanding the enabling factors in implementing mobile KMS in Australian healthcare, as well as provide better guidelines for this process.