Accurate prediction of US Treasury bond yields is crucial for investment strategies and economic policymaking. This paper explores the application of advanced machine learning techniques, specifically Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models, in forecasting these yields. By integrating key economic indicators and policy changes, our approach seeks to enhance the precision of yield predictions. Our study demonstrates the superiority of LSTM models over traditional RNNs in capturing the temporal dependencies and complexities inherent in financial data. The inclusion of macroeconomic and policy variables significantly improves the models’ predictive accuracy. This research underscores a pioneering movement for the legacy banking industry to adopt artificial intelligence (AI) in financial market prediction. In addition to considering the conventional economic indicator that drives the fluctuation of the bond market, this paper also optimizes the LSTM to handle situations when rate hike expectations have already been priced-in by market sentiment.

The fast-growing field of nanotheranostics is revolutionizing cancer treatment by allowing for precise diagnosis and targeted therapy at the cellular and molecular levels. These nanoscale platforms provide considerable benefits in oncology, including improved disease and therapy specificity, lower systemic toxicity, and real-time monitoring of therapeutic outcomes. However, nanoparticles' complicated interactions with biological systems, notably the immune system, present significant obstacles for clinical translation. While certain nanoparticles can elicit favorable anti-tumor immune responses, others cause immunotoxicity, including complement activation-related pseudoallergy (CARPA), cytokine storms, chronic inflammation, and organ damage. Traditional toxicity evaluation approaches are frequently time-consuming, expensive, and insufficient to capture these intricate nanoparticle-biological interactions. Artificial intelligence (AI) and machine learning (ML) have emerged as transformational solutions to these problems. This paper summarizes current achievements in nanotheranostics for cancer, delves into the causes of nanoparticle-induced immunotoxicity, and demonstrates how AI/ML may help anticipate and create safer nanoparticles. Integrating AI/ML with modern computational approaches allows for the detection of potentially dangerous nanoparticle qualities, guides the optimization of physicochemical features, and speeds up the development of immune-compatible nanotheranostics suited to individual patients. The combination of nanotechnology with AI/ML has the potential to completely realize the therapeutic promise of nanotheranostics while assuring patient safety in the age of precision medicine.

Background: According to the 2023 World Economic Forum report, the impact of Artificial Intelligence (AI) and automation on the job market was more significant than originally projected. Although 2018 research forecasted significant job losses balanced by job creation, current data indicates otherwise. Between 2023 and 2027, it is anticipated that 69 million new jobs will be created due to advancements in AI, however, this will be offset by the loss of 83 million jobs, leading to a net decrease of 14 million jobs worldwide. Roles related to AI, digitalization, and sustainability, such as AI specialists and renewable energy engineers are expected to grow, while those in clerical and administrative sectors are most at risk of decline. This shift underscores the need for reskilling and adapting to evolving fields, as nearly 44% of workers skills will face disruption by 2027. The demand for analytical thinking, technological literacy, and adaptability will grow as companies increasingly adopt frontier technologies. Objectives: (1) identify key variables influencing adaptability of college graduates in Indonesia, (2) quantify the strength of relationships between these variables to understand the combined effect on graduate adaptability. The research also aims to (3) develop theoretical and practical recommendations to strengthen ICIL policy and equip students with the relevant skills needed to thrive in an ever-changing job market. Methodology: The research focuses on predicting future employment trends, adaptability, and learning agility (LA), along with the implications for improving the Independent Campus Independent Learning (ICIL) policy. It focused on the significant unemployment rate among college graduates, along with the lack of research on the relationship between job change predictions, graduates’ adaptability, and the impact on graduates’ general well-being. The mixed-method strategy with quantitative analysis was used to conduct this research with data collected from 284 ICIL participants through online survey. The gathered data was evaluated using Structural Equation Modeling (SEM) with Lisrel version 10. Results: The result showed that job trend projections significantly influence responsiveness, which demonstrated a robust association between employment trend predictions and LA. Responsiveness significantly influenced learning agility which indicated no significant direct association between job trend projections and graduate adaptability. Conclusion: The research emphasized the need to consider adaptability as a concept with multiple dimensions. It proposed incorporating these factors into strategies for education and human resources development in order to better equip graduates for the demands of a constantly changing work market. Unique contribution: This research focused on adaptability as a multifaceted concept that consist of the ability to forecast job trends, be sensitive, and possess LA. It offered a deeper understanding of the relationships between these variables as discussed in the human resources literature. Technology, corporate culture, and training played a critical role in connecting employment trend prediction with the ability to respond effectively. Key recommendation: Institutions should implement a comprehensive approach to the development of human resources, with emphasis on fostering critical thinking, analytical abilities, and the practical application of information. By employing these tactics, higher education institutions may effectively equip graduates with both academic proficiency and the ability to adapt and thrive in quickly changing organizational environments, leading to the production of robust and versatile workers.

Photovoltaic systems have shown significant attention in energy systems due to the recent machine learning approach to addressing photovoltaic technical failures and energy crises. A precise power production analysis is utilized for failure identification and detection. Therefore, detecting faults in photovoltaic systems produces a considerable challenge, as it needs to determine the fault type and location rapidly and economically while ensuring continuous system operation. Thus, applying an effective fault detection system becomes necessary to moderate damages caused by faulty photovoltaic devices and protect the system against possible losses. The contribution of this study is in two folds: firstly, the paper presents several categories of photovoltaic systems faults in literature, including line-to-line, degradation, partial shading effect, open/close circuits and bypass diode faults and explores fault discovery approaches with specific importance on detecting intricate faults earlier unexplored to address this issue; secondly, VOSviewer software is presented to assess and review the utilization of machine learning within the solar photovoltaic system sector. To achieve the aims, 2258 articles retrieved from Scopus, Google Scholar, and ScienceDirect were examined across different machine learning and energy-related keywords from 1990 to the most recent research papers on 14 January 2025. The results emphasise the efficiency of the established methods in attaining fault detection with a high accuracy of over 98%. It is also observed that considering their effortlessness and performance accuracy, artificial neural networks are the most promising technique in finding a central photovoltaic system fault detection. In this regard, an extensive application of machine learning to solar photovoltaic systems could thus clinch a quicker route through sustainable energy production.

Heat removal has become an increasingly crucial issue for microelectronic chips due to increasingly high speed and high performance. One solution is to increase the thermal conductivity of the corresponding dielectrics. However, traditional approach to adding solid heat conductive nanoparticles to polymer dielectrics led to a significant weight increase. Here we propose a dielectric polymer filled with heat conductive hollow nanoparticles to mitigate the weight gain. Our mesoscale simulation of heat conduction through this dielectric polymer composite microstructure using the phase-field spectral iterative perturbation method demonstrates the simultaneous achievement of enhanced effective thermal conductivity and the low density. It is shown that additional heat conductivity enhancement can be achieved by wrapping the hollow nanoparticles with graphene layers. The underlying mesoscale mechanism of such a microstructure design and the quantitative effect of interfacial thermal resistance will be discussed. This work is expected to stimulate future efforts to develop light-weight thermal conductive polymer nanocomposites.