Application of improved convolution neural network in financial forecasting

Financial status and its role in the national economy have been increasingly recognized. In order to deduce the source of monetary funds and determine their whereabouts, financial information and prediction have become a scientific method that can not be ignored in the development of national economy. This paper improves the existing CNN and applies it to financial credit from different perspectives. Firstly, the noise of the collected data set is deleted, and then the clustering result is more stable by principal component analysis. The observation vectors are segmented to obtain a set of observation vectors corresponding to each hidden state. Based on the output of PCA algorithm, we recalculate the mean and variance of all kinds of observation vectors, and use the new mean and covariance matrix as credit financial credit, and then determine the best model parameters.The empirical results based on specific data from China's stock market show that the improved convolutional neural network proposed in this paper has advantages and the prediction accuracy reaches.

AutoML to Date and Beyond: Challenges and Opportunities

As big data becomes ubiquitous across domains, and more and more stakeholders aspire to make the most of their data, demand for machine learning tools has spurred researchers to explore the possibilities of automated machine learning (AutoML). AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research. But although automation and efficiency are among AutoML’s main selling points, the process still requires human involvement at a number of vital steps, including understanding the attributes of domain-specific data, defining prediction problems, creating a suitable training dataset, and selecting a promising machine learning technique. These steps often require a prolonged back-and-forth that makes this process inefficient for domain experts and data scientists alike and keeps so-called AutoML systems from being truly automatic. In this review article, we introduce a new classification system for AutoML systems, using a seven-tiered schematic to distinguish these systems based on their level of autonomy. We begin by describing what an end-to-end machine learning pipeline actually looks like, and which subtasks of the machine learning pipeline have been automated so far. We highlight those subtasks that are still done manually—generally by a data scientist—and explain how this limits domain experts’ access to machine learning. Next, we introduce our novel level-based taxonomy for AutoML systems and define each level according to the scope of automation support provided. Finally, we lay out a roadmap for the future, pinpointing the research required to further automate the end-to-end machine learning pipeline and discussing important challenges that stand in the way of this ambitious goal.

Dynamic Packet Duplication for Industrial URLLC

The fifth-generation (5G) network is presented as one of the main options for Industry 4.0 connectivity. To comply with critical messages, 5G offers the Ultra-Reliable and Low latency Communications (URLLC) service category with a millisecond end-to-end delay and reduced probability of failure. There are several approaches to achieve these requirements; however, these come at a cost in terms of redundancy, particularly the solutions based on multi-connectivity, such as Packet Duplication (PD). Specifically, this paper proposes a Machine Learning (ML) method to predict whether PD is required at a specific data transmission to successfully send a URLLC message. This paper is focused on reducing the resource usage with respect to pure static PD. The concept was evaluated on a 5G simulator, comparing between single connection, static PD and PD with the proposed prediction model. The evaluation results show that the prediction model reduced the number of packets sent with PD by 81% while maintaining the same level of latency as a static PD technique, which derives from a more efficient usage of the network resources.

CARTOGRAPHY AND MAPPING FOR PRECISION HEALTH: REVIEW OF ESSENTIAL ELEMENTS FOR DISEASE MAPPING

A well-developed healthcare system, decent access to clean water and sanitation, and programmes to eliminate poverty and build modern infrastructure are essential components to create healthier Malaysia's population. Non-communicable diseases currently account for most of the mortality and morbidity, although communicable diseases such as dengue fever, avian flu and covid-19 still pose a threat. The World Health Organization (WHO) identified COVID-19 is a rare pneumonia disease that originated in Wuhan, on January 12, 2020, before it became an outbreak in all countries including Malaysia. The requirement of a precise mapping and Cartography for the accurate disease mapping and data management are crucial due to a precise map gives higher resolution of the data and for more specific data analysis, interpretation and decision making process. In Malaysia, there no specific report on precise mapping for health applications, and it is therefore this paper is to identify the potential criteria and factors needed for precise health mapping applications. A precise health mapping is essential to create a precise risk map towards the surveillance and signal detection, predicting future risk, targeted interventions, and understanding disease phenomena.

Machine learning in knee arthroplasty: specific data are key—a systematic review

Purpose Artificial intelligence (AI) in healthcare is rapidly growing and offers novel options of data analysis. Machine learning (ML) represents a distinct application of AI, which is capable of generating predictions and has already been tested in different medical specialties with various approaches such as diagnostic applications, cost predictions or identification of risk factors. In orthopaedics, this technology has only recently been introduced and the literature on ML in knee arthroplasty is scarce. In this review, we aim to investigate which predictions are already feasible using ML models in knee arthroplasty to identify prerequisites for the effective use of this novel approach. For this reason, we conducted a systematic review of ML algorithms for outcome prediction in knee arthroplasty. Methods A comprehensive search of PubMed, Medline database and the Cochrane Library was conducted to find ML applications for knee arthroplasty. All relevant articles were systematically retrieved and evaluated by an orthopaedic surgeon and a data scientist on the basis of the PRISMA statement. The search strategy yielded 225 articles of which 19 were finally assessed as eligible. A modified Coleman Methodology Score (mCMS) was applied to account for a methodological evaluation. Results The studies presented in this review demonstrated fair to good results (AUC median 0.76/range 0.57–0.98), while heterogeneous prediction models were analysed: complications (6), costs (4), functional outcome (3), revision (2), postoperative satisfaction (2), surgical technique (1) and biomechanical properties (1) were investigated. The median mCMS was 65 (range 40–80) points. Conclusion The prediction of distinct outcomes with ML models applying specific data is already feasible; however, the prediction of more complex outcomes is still inaccurate. Registry data on knee arthroplasty have not been fully analysed yet so that specific parameters have not been sufficiently evaluated. The inclusion of specific input data as well as the collaboration of orthopaedic surgeons and data scientists are essential prerequisites to fully utilize the capacity of ML in knee arthroplasty. Future studies should investigate prospective data with specific and longitudinally recorded parameters. Level of evidence III.

Test to release from isolation after testing positive for SARS-CoV-2

The rapid spread and high transmissibility of the Omicron variant of SARS-CoV-2 is likely to lead to a significant number of key workers testing positive simultaneously. Under a policy of self-isolation after testing positive, this may lead to extreme staffing shortfalls at the same time as e.g. hospital admissions are peaking. Using a model of individual infectiousness and testing with lateral flow tests (LFT), we evaluate test-to-release policies against conventional fixed-duration isolation policies in terms of excess days of infectiousness, days saved, and tests used. We find that the number of infectious days in the community can be reduced to almost zero by requiring at least 2 consecutive days of negative tests, regardless of the number of days' wait until testing again after initially testing positive. On average, a policy of fewer days' wait until initiating testing (e.g 3 or 5 days) results in more days saved vs. a 10-day isolation period, but also requires a greater number of tests. Due to a lack of specific data on viral load progression, infectivity, and likelihood of testing positive by LFT over the course of an Omicron infection, we assume the same parameters as for pre-Omicron variants and explore the impact of a possible shorter proliferation phase.

Characteristics of persons who died by suicide in prison in France: 2017–2018

Background In northern countries, suicide rates among prisoners are at least three times higher for men and nine times higher for women than in the general population. The objective of this study is to describe the sociodemographic, penal, health characteristics and circumstances of suicide of French prisoners who died by suicide. Methods This study is an intermediate analysis of the French epidemiological surveillance program of suicides in prison. All suicides in prison in 2017–2018 in France were included in the study. Archival sociodemographic and penal data and specific data on the circumstances of the suicidal act were provided by the National Prison Service. Health data was provided by physicians working in prison using a standardized questionnaire. Results In 2017–2018, 235 prisoners died by suicide. The suicide rate was 16.8/10 000 person-years. Among suicide cases, 94.9% were male, 27.2% were under 30, 25.1% were aged 30 to 39, 27.7% were aged 40 to 49 and 20.0% were 50 or older. At the time of suicide, 48.5% were on custodial remand. Incarceration is associated with a threefold increase in the frequency of anxio-depressive disorders (24.6% in prison versus 8.2% before prison). The week before the suicidal act, 60% of prisoners visited the health unit and a significant event was detected for 61% of all cases. Suicide was less than 1 week after prison entry for 11.9% of prisoners, corresponding to a suicide rate 6.4 (CI95% [4.3 – 9.5]) times higher than for the remaining time in prison, and was more than 1 year after entry for 33.7% of them. Conclusions The high frequency of events the week before suicide in our study suggests that events in prison could play a role in the occurrence of suicides. Comparative studies are needed to further explore the time association between events and suicide in prison. As most of prisoners who died by suicide visited the health unit the week before suicide, the identification of triggering factors could help psychiatrists and other health professionals to assess the short-term risk of suicide and to implement preventive measures.

Advanced breakup-nucleon enhancement of deuteron-induced reaction cross sections

Following the EUROfusion PPPT-programme action for an advanced modeling approach of deuteron-induced reaction cross sections, as well as specific data evaluations in addition of the TENDL files, an assessment of the details and corresponding outcome for the latter option of TALYS for the breakup model has been carried out. The breakup enhancement obtained in the meantime within computer code TALYS, by using the evaluated nucleon-induced reaction data of TENDL-2019, is particularly concerned. Discussion of the corresponding results, for deuteron-induced reactions on $$^{58}$$ 58 Ni, $$^{96}$$ 96 Zr, and $$^{231}$$ 231 Pa target nuclei up to 200 MeV incident energy, includes limitations still existing with reference to the direct-reaction account.

Application of Artificial Intelligence (AI) in Dredging Efficiency in Bangladesh

The integration of Artificial Intelligence (AI) into the dredging systems and dredging machinery used in "capital" and "maintenance" dredging in Bangladesh can enhance the efficiency of the machines and dredging process, enabling the operators to perform regular and repetitive dredging tasks safely in the rivers, ports, and estuaries all over the country. AI, including Big Data, Machine Learning, Internet of Thing, Blockchain and Sensors and Simulators with their catalytic potentials, can systematically compile and evaluate specific data collected from different sources, develop applications or simulators, connect the stakeholders on a virtual platform, store lakes of information without compromising their intellectual rights, predicting models to harness the challenges, minimise the cost of dredging, identify possible threats and help protect the already dredged areas by giving timely signals for further maintenance. Furthermore, the application of AI modulated dredging devices and machinery can play a significant role when monitoring aspects becomes crucial, keeping environmental impacts mitigated without affecting the quality of the human environment. This study includes the evaluation of the application of AI – its prospect and challenges in the existing dredging systems in Bangladesh against the backdrop of the challenges faced in capital and maintenance dredging in the major rivers – and assess whether such inclusion of AI is likely to minimise the cost of dredging in the rivers of Bangladesh and facilitate the materialisation of the objectives of Bangladesh Delta Plan 2100.This paper studies the organisation's infrastructural requirement for the integration of AI into dredging systems, using benchmarking such as 1- "Understanding AI Ready Approach", 2-"Strategies for Implementing AI", 3-"Data Management", 4-"Creating AI Literate Workforce and Upskilling", and 5-"Identifying Threats" concerning the management and dredging operations of Bangladesh Inland Water Transport Authority (BIWTA), under Bangladesh Ministry of Shipping and Bangladesh Water Development Board (BWDB). The paper also uses several case studies such as channel dredging to show that the use of AI can bring a significant change in the dredging operations both in reducing the cost of dredging and in terms of harnessing the barriers in adaptive management and environmental impacts.