Detecting Cognitive Impairment Status Using Keystroke Patterns and Physical Activity Data among the Older Adults: A Machine Learning Approach

Cognitive impairment has a significantly negative impact on global healthcare and the community. Holding a person’s cognition and mental retention among older adults is improbable with aging. Early detection of cognitive impairment will decline the most significant impact of extended disease to permanent mental damage. This paper aims to develop a machine learning model to detect and differentiate cognitive impairment categories like severe, moderate, mild, and normal by analyzing neurophysical and physical data. Keystroke and smartwatch have been used to extract individuals’ neurophysical and physical data, respectively. An advanced ensemble learning algorithm named Gradient Boosting Machine (GBM) is proposed to classify the cognitive severity level (absence, mild, moderate, and severe) based on the Standardised Mini-Mental State Examination (SMMSE) questionnaire scores. The statistical method “Pearson’s correlation” and the wrapper feature selection technique have been used to analyze and select the best features. Then, we have conducted our proposed algorithm GBM on those features. And the result has shown an accuracy of more than 94%. This paper has added a new dimension to the state-of-the-art to predict cognitive impairment by implementing neurophysical data and physical data together.

Program Pemerintah Tentang Pendaftaran Tanah Sistematis Lengkap Di Kenongomulyo

Abstrak. Penelitian ini bertujuan untuk mengetahui program pemerintah yaitu program percepatan hak milik tanah yang berguna bagi masyarakat atas hak kepemilikan tanah. Penulis memakai penelitian hukum empiris yaitu mengkaji dan meneliti gejala di lapangan untuk dianalisi menggunakan analisa hukum. Hasil dari penelitian meliputi pelaksanaan program pemerintah yang terdiri dari 7 tahapan yaitu tahap penyuluhan, pengumpulan data fisik, pengumpulan data yuridis, pemeriksaan tanah, pengumuman dan penetapan hak, pembukuan hak, penerbitan dan penyerahan sertifikat. Keseluruhan tahapan PTSL telah dilaksanakan sesuai ketentuan hukum yang berlaku. Abstract. This study aims to determine the government's program, namely the acceleration program for land ownership rights which is useful for the community for land ownership rights. The author uses empirical legal research, which is to examine and examine symptoms in the field to be analyzed using legal analysis. The results of the research include the implementation of government programs which consist of 7 stages, namely the counseling stage, physical data collection, juridical data collection, land inspection, announcement and determination of rights, bookkeeping of rights, issuance and delivery of certificates. All stages of PTSL have been carried out in accordance with applicable legal provisions.

Design of a Spatial Data Model for the Sustainability of Population Sheltering Processes in the Czech Republic

This article is focused on the creation of a data model of an information system to support the processes of population sheltering (PoS). PoS processes have undergone significant changes in the Czech Republic. The PoS system was transformed for the use of improvised shelters. For sustainable PoS, it is necessary to standardize the approach of crisis management staff. Key research hypotheses: the data model must respect the methodological framework of planning and implementation of the PoS, especially when used for the design and implementation of the improvised shelters; the standardization of residential buildings can be used to facilitate and streamline the sustainable process of planning of the PoS; the unified data model of the PoS can be considered suitable for standardization and development in the field of sustainable planning and implementation of the PoS. Softwares such as SW QGIS desktop 2.6.0, OpenStreetMap (OSM) spatial database, ESRI shapefile format, and S-JTSK/Krovak East North 5514 coordinate system were used for the verification of the spatial data model, and ASP.NET MVC 4.7.2 Microsoft SQL Server Express 2019, jQuery 3.3.1, Bootstrap 3.4.1, Kendo UI 2019.1.220, and virtual Windows Server 2016 were used for the implementation of the physical data model. The physical data model substantiates the benefits.

A Case Study of an Office Building to Identify Energy Consumption and Carbon Management Solutions Using Physical Data and Simulation Software

To measure the level of energy performance of a building, there are several categories of energy consumption to be calculated such as oil, natural gas and electricity. In order to significantly minimise the Greenhouse gas emission in an office, it is important to tap into the positive progress of energy efficiency of equipment which contributes to total energy performance of a building. Consequently, to enable accurate building energy consumption of a building, energy modelling method is applied to identify total consumption and cost of energy usage with effects of carbon emission. Hence, this will help to reduce the costing of energy inside building with differences of efficiency options. Therefore, this paper aims to analyse an office building in terms of the level of energy consumption and carbon emission as a case study. The first objective is to identify the amount of energy consumption and carbon emission inside the building using the simulation software. Secondly, to identify the differences between the data recorded through simulation software and physical data. Finally, to identify solutions to decrease the carbon emission by applying measures towards reducing energy consumption inside the building.

Training the Next Generation of Physical Data Scientists

Preparing a diverse new generation of scientists who can use artificial intelligence and data science to better understand and predict geoscience phenomena requires revamped training.

A Decentralized Threshold Signature Scheme of Blockchain-Based Medical Cyber Physical Systems

With the rapid development of medical information, the medical cyber system is rapidly transforming, and medical information sharing faces new challenges. Blockchain technology is a revolutionary technology. It has the characteristics of tamper-proof and privacy-preserving, and has natural protection for big data systems, that can be used in medical systems. In this paper,we proposed to store medical cyber physical data in a mixed blockchain with private blockchain and consortium blockchain in order to realize the secure storage of medical cyber physical data by the tamper-resistant and sharing of blockchain technology. In the system, a threshold signature system based on blockhain is also proposed. Aiming at the situation that medical accidents are easy to occur in multidisciplinary joint consultation in the medical process, this paper proposes to use threshold signature for joint consultation. Using the security and threshold of threshold signature, treatment can be carried out when the threshold number is reached, and medical data can be uploaded to the consortium blockchain. The security analysis and performance analysis show that the scheme has advantages in safety and performance and is suitable for the medical environment to a certain extent.

A PSO Based Cloud Framework for Knowledge Extraction

Many industries, such as oil, construction, banking, and insurance, have substantial historical physical data. Companies store this data in physical warehouses that are geographically distributed and usually taken care of by record management companies. Storing large volumes of historical physical data poses many critical challenges, such as increased maintenance cost, high time for recovery, and unsearchable data. Many companies digitize this data and consolidate this data into cloud repositories as part of their Digital Transformation (DT) journey to address these challenges. This DT process introduces many other technical challenges while dealing with poor scans, huge file size, geographically distributed files, and confidential documents. Though there are options to resolve each of these limitations individually, there are no frameworks that deal with digitization and historical data storage in its entirety. Moreover, they cannot handle a large number of documents having variable file sizes. This paper presents a generic cloud-based high-performance computing framework for knowledge extraction, comprising document classification based on neural networks and particle swarm optimization (PSO), data extraction, metadata enrichment, image enhancement using image processing (IP) techniques, and high data availability to users using cloud-based search. The proposed framework is executed on two cloud providers, i.e., Azure and AWS, to test its efficacy.