Improper Data Research Articles

Stabilisation of linear waves with inhomogeneous Neumann boundary conditions

ABSTRACT We study linear damped and viscoelastic wave equations evolving on a bounded domain. For both models, we assume that waves are subject to an inhomogeneous Neumann boundary condition on a portion of the domain's boundary. The analysis of these models presents additional interesting features and challenges compared to their homogeneous counterparts. In the present context, energy depends on the boundary trace of velocity. It is not clear in advance how this quantity should be controlled based on the given data, due to regularity issues. However, we establish global existence and also prove uniform stabilisation of solutions with decay rates characterised by the Neumann input. We supplement these results with numerical simulations in which the data do not necessarily satisfy the given assumptions for decay. These simulations provide, at a numerical level, insights into how energy could possibly change in the presence of, for example, improper data.

Evaluation of Nurses’ Attitudes toward Human Immuno Deficiency

Background: HIV nursing protocols, including rapid HIV testing, face weaknesses such as improper data collection and ambiguity. To reduce stigmatization, interventions should promote the adoption of nursing practices that influence stigmatization experiences. The International Nursing Network for HIV Research recommends collaboration, global partnerships, and scientific work to increase nurses' impact in HIV research. Nurses' experiences with HIV/AIDS patients can impact their health and the spread of the virus. Barriers to HIV treatment include lack of knowledge, demotivation, resistance, and lack of adherence to treatment guidelines. Nurse involvement in HIV prevention is crucial for improving patient outcomes. Objective(s): This study aims to evaluate nurses' attitudes toward human Immuno deficiency. Methodology: A quasi-experimental design was conducted in 7 January 2024 to 7 May 2024, The study at Al Musayyib General Hospital in Babylon, Iraq, involved 100 nursing professionals in a health education program. The program aimed to improve nurses' understanding and attitudes towards HIV/AIDS. The program's effectiveness was assessed through questionnaires. Results: The study found that nurses aged 23-less than 30 years, predominantly female, had moderate attitudes towards the human immunodeficiency virus. However, there was no significant relationship between nurses' attitudes and sociodemographic variables or professional variables such as education, years of experience, knowledge development, or participation in training courses. The majority of nurses were urban residents. Conclusion: Healthcare professionals should therefore follow national infection prevention guidelines when working in hospitals. To increase nurses' understanding and proficiency in this area, policy designers ought to train them in infection prevention. Further research should include a qualitative study in order to obtain more detailed information. Recommendation: Institutions may enhance their knowledge of HIV care practices by conducting frequent training sessions for nursing staff, personalizing instructional materials, gauging and reviewing attitude levels, encouraging peer learning, and expanding the scope of research. In order to provide effective HIV care, this will assist nurses in expanding their knowledge and adjusting their attitude.

Evaluation of Nurses’ Attitudes toward Human Immuno Deficiency

Background: HIV nursing protocols, including rapid HIV testing, face weaknesses such as improper data collection and ambiguity. To reduce stigmatization, interventions should promote the adoption of nursing practices that influence stigmatization experiences. The International Nursing Network for HIV Research recommends collaboration, global partnerships, and scientific work to increase nurses' impact in HIV research. Nurses' experiences with HIV/AIDS patients can impact their health and the spread of the virus. Barriers to HIV treatment include lack of knowledge, demotivation, resistance, and lack of adherence to treatment guidelines. Nurse involvement in HIV prevention is crucial for improving patient outcomes. Objective(s): This study aims to evaluate nurses' attitudes toward human Immuno deficiency. Methodology: A quasi-experimental design was conducted in 7 January 2024 to 7 May 2024, The study at Al Musayyib General Hospital in Babylon, Iraq, involved 100 nursing professionals in a health education program. The program aimed to improve nurses' understanding and attitudes towards HIV/AIDS. The program's effectiveness was assessed through questionnaires. Results: The study found that nurses aged 23-less than 30 years, predominantly female, had moderate attitudes towards the human immunodeficiency virus. However, there was no significant relationship between nurses' attitudes and sociodemographic variables or professional variables such as education, years of experience, knowledge development, or participation in training courses. The majority of nurses were urban residents. Conclusion: Healthcare professionals should therefore follow national infection prevention guidelines when working in hospitals. To increase nurses' understanding and proficiency in this area, policy designers ought to train them in infection prevention. Further research should include a qualitative study in order to obtain more detailed information. Recommendation: Institutions may enhance their knowledge of HIV care practices by conducting frequent training sessions for nursing staff, personalizing instructional materials, gauging and reviewing attitude levels, encouraging peer learning, and expanding the scope of research. In order to provide effective HIV care, this will assist nurses in expanding their knowledge and adjusting their attitude.

Advanced Data Processing of THz-Time Domain Spectroscopy Data with Sinusoidally Moving Delay Lines

We provide a comprehensive technical analysis of the data acquisition process with oscillating delay lines for Terahertz-time domain spectroscopy. The utilization of these rapid stages, particularly in high-repetition-rate systems, is known to enable an effective reduction of noise content through averaging. However, caution must be exercised to optimize the data averaging process, with the goal of significantly optimizing the dynamic range (DR) and signal-to-noise ratio (SNR). Here we discuss some pitfalls to avoid and the effect of improper data handling on the dynamic range obtainable. A free and open-source program, called parrot (Processing All Rapidly & Reliably Obtained THz-traces), is provided alongside this publication to overcome the discussed pitfalls and facilitate the acceleration of experimental setups and data analysis, thereby enhancing signal fidelity and reproducibility.

Unpacking the complexities of health record misuse: insights from Australian health services

PurposeInformation systems (IS) research in general and health IS studies, in particular, are prone to a positivity bias – largely focusing on upside gains rather than the potential misuse practices. This paper aims to explore failures in health IS use and shortcomings in data privacy and cybersecurity and to provide an explanatory model for health record misuse.Design/methodology/approachThis research is based on four data sets that we collected through a longitudinal project studying digital health (implementation, use and evaluation), interviews with experts (cybersecurity and digital health) and healthcare stakeholders (health professionals and managers). We applied qualitative analysis to explain health records misuse from a sociotechnical perspective.FindingsWe propose a contextualized model of “health records misuse” with two overarching dimensions: data misfit and improper data processing. We explain sub-categories of data misfit: availability misfit, meaning misfit and place misfit, as well as sub-categories of improper data processing: improper interaction and improper use-related actions. Our findings demonstrate how health records misuse can emerge in sociotechnical health systems and impact health service delivery and patient safety.Originality/valueThrough contextualizing system misuse in healthcare, this research advances the understanding of ineffective use and failures in health data protection practices. Our proposed theoretical model provides explanations for unique patterns of IS misuse in healthcare, where data protection failures are consequential for healthcare organizations and patient safety.

WOPE: A write-optimized and parallel-efficient B[formula omitted]-tree for persistent memory

Emerging Persistent Memory (PM) usually has the serious drawback of expensive write activities. Thus, existing PM-oriented B+-trees mainly concentrate on alleviating the write overhead (i.e., reducing PM writes and flush instructions). Unfortunately, due to the improper data organization in the sorted leaf node, existing solutions cause massive data migration when data inserting or node splitting occurs. In this paper, we propose a write-optimized PM-oriented B+-tree with aligned flush and selective migration, called WPB+-tree, to solve the above problems. WPB+-tree first adopts a buffer-assisted mechanism that temporarily stores the newly inserted data to reduce the overhead of entry shifts. Second, WPB+-tree employs a selective migration of node entries scheme to achieve less than half of the data migration when a node is split. Moreover, existing PM-oriented B+-trees usually employ a coarse-grained lock to avoid thread conflicts, which can severely degrade the concurrency efficiency. Thus, we further propose a fine-grained lock technique for WPB+-tree, namely, parallel-efficient WPB+-tree (WOPE), to improve the concurrency efficiency. We implement the proposed WPB+-tree and WOPE on Linux and conduct extensive evaluations with actual persistent memory, where WOPE achieves 23.5%, 30.7%, and 15.3% of performance improvement (insert, read, and scan) over the straightforward solutions (i.e., SSB-Tree, Fast&Fair, and wB+tree), and 10.1% of performance improvement over WPB+-tree, on average.

Comparing Remote Sensing and Geostatistical Techniques in Filling Gaps in Rain Gauge Records and Generating Multi-Return Period Isohyetal Maps in Arid Regions—Case Study: Kingdom of Saudi Arabia

Arid regions are susceptible to flash floods and severe drought periods, therefore there is a need for accurate and gap-free rainfall data for the design of flood mitigation measures and water resource management. Nevertheless, arid regions may suffer from a shortage of precipitation gauge data, whether due to improper gauge coverage or gaps in the recorded data. Several alternatives are available to compensate for deficiencies in terrestrial rain gauge records, such as satellite data or utilizing geostatistical interpolation. However, adequate assessment of these alternatives is mandatory to avoid the dramatic effect of using improper data in the design of flood protection works and water resource management. The current study covers 75% of the Kingdom of Saudi Arabia’s area and spans the period from 1967 to 2014. Seven satellite precipitation datasets with daily, 3-h, and 30-min temporal resolutions, along with 43 geostatistical interpolation techniques, are evaluated as supplementary data to address the gaps in terrestrial gauge records. The Normalized Root Mean Square Error by the mean value of observation (NRMSE) is selected as a ranking criterion for the evaluated datasets. The geostatistical techniques outperformed the satellite datasets with 0.69 and 0.8 NRMSE for the maximum and total annual records, respectively. The best performance was found in the areas with the highest gauge density. PERSIANN-CDR and GPM IMERG V7 satellite datasets performed better than other satellite datasets, with 0.8 and 0.82 NRMSE for the maximum and total annual records, respectively. The spatial distributions of maximum and total annual precipitation for every year from 1967 to 2014 are generated using geostatistical techniques. Eight Probability Density Functions (PDFs) belonging to the Gamma, Normal, and Extreme Value families are assessed to fit the gap-filled datasets. The PDFs are ranked according to the Chi-square test results and Akaike information criterion (AIC). The Gamma, Extreme Value, and Normal distribution families had the best fitting over 56%, 34%, and 10% of the study area gridded data, respectively. Finally, the selected PDF at each grid point is utilized to generate the maximum annual precipitation for 2, 5, 10, 25, 50, and 100-year rasters that can be used directly as a gridded precipitation input for hydrological studies.

Privacy Risk and Correction Mechanism of Higher Education Mooc Based on Blockchain Technology in the Era of Big Data

The emergence of Massive Online Open Course (MOOC) has sparked a digital tsunami globally, bringing a huge impact on higher education. The open curriculum format of MOOC has achieved the optimal transmission of top teaching resources and personalized teaching based on different groups, which is different from traditional teaching models. At the same time, in the process of implementing educational activities, the MOOC platform based on big data mining will bring a certain degree of privacy risk due to improper data collection, storage, or processing. The traditional MOOC have not achieved as much as they should. The main problem is that fully centralized online education cannot solve the trust problem. The emergence of blockchain technology solves the problem of lack of trust, but the open and transparent mechanism of blockchain also introduces a new problem, that is, the privacy of user data can not be reasonably protected.

PERBANDINGAN KINERJA METODE KLASIFIKASI K-NEAREST NEIGHBOR DAN SUPPORT VECTOR MACHINES PADA DATASET PARKINSON

The government program in the form of social assistance (bansos) is part of the effort to improve the welfare of the community and ensure basic needs and improve the standard of living of the recipients. However, there are often cases of mistargeting of social assistance programs by the government. Improper data management and Data Terpadu Kesejahteraan Sosial (DTKS) which are not used as the cause of the distribution of social assistance are not well targeted. The data can be analyzed using the classification method to determine whether or not the family accepts the ban from the government. This study classifies the SUSENAS data by comparing K-Nearest Neighbor (KNN) and Support Vector Machines (SVM). The advantage of the KNN method lies in the level of accuracy to solve problems with large data while the SVM method has better performance in various fields of application such as bioinformacs, handwriting recognition, text classification and so on. Based on training data and testing data comparison 85%:15% showed that KNN method had a better classification performance than the SVM method. The accuracy value of KNN method is 80,95% higher than the accuracy value of SVM method is 78,79%.

Improper data practices erode the quality of global ecological databases and impede the progress of ecological research.

The scientific community has entered an era of big data. However, with big data comes big responsibilities, and best practices for how data are contributed to databases have not kept pace with the collection, aggregation, and analysis of big data. Here, we rigorously assess the quantity of data for specific leaf area (SLA) available within the largest and most frequently used global plant trait database, the TRY Plant Trait Database, exploring how much of the data were applicable (i.e., original, representative, logical, and comparable) and traceable (i.e., published, cited, and consistent). Over three-quarters of the SLA data in TRY either lacked applicability or traceability, leaving only 22.9% of the original data usable compared with the 64.9% typically deemed usable by standard data cleaning protocols. The remaining usable data differed markedly from the original for many species, which led to altered interpretation of ecological analyses. Though the data we consider here make up only 4.5% of SLA data within TRY, similar issues of applicability and traceability likely apply to SLA data for other species as well as other commonly measured, uploaded, and downloaded plant traits. We end with suggested steps forward for global ecological databases, including suggestions for both uploaders to and curators of databases with the hope that, through addressing the issues raised here, we can increase data quality and integrity within the ecological community.

Designing of Real-time Communication Method to Monitor Water Quality using WSN Based on IOT

Data accuracy has always been the essential and foremost requirement of any communication. A Real-time Water quality-monitoring system (WQMS) needs high-level data accuracy to process the water perfectly for the desired usage in any specific purpose. Exponential growth in man-made processes, human activities, Industrialization, and economic growth along with depleting safe water resources has made the water pollution issue a foremost threat to human survival and human civilisation as a whole. The Conventional WQMS lacks in providing data accuracy while testing and analysing the water samples at sites due to improper data transmission, human intervention, instrument node working and calibration issues. Therefore, monitoring the quality of the water is essential with a prime focus on data accuracy through proper testing, data analysis and data transmission methods to provide real-time data accuracy. In this research work, an IOT-based wireless sensor network (WSN) is proposed that uses mesh networking to connect the sensor nodes and message queuing telemetry transfer (MQTT) protocol to send the acquired data to a cloud server ADDA Fruit IO. ESP32 standalone microcontroller with in-built Wi-Fi is used as a transceiver on sensor nodes and master nodes. As far as sensor and master node power is concerned, a self-adapting power generation system is incorporated using solar power and water energy harvesting techniques. The sensor nodes are calibrated as per WHO standards using deionized water and buffer capsules. Five random samples are collected from river water, pond water, Borewell water, R.O water and Municipal committee water to analyse the proposed system’s accuracy. The accuracy test and analysis is done using statistical tools on water sample measurements by the proposed sensor node, and the same is compared with the actual certified instrument, hardware manual-based measurement, Laboratory value check and transmitted value on Cloud Server. The proposed WQMS is designed to measure various WQM parameters i.e. Total Dissolve Solid (TDS), pH, Temperature and turbidity and to ensure data accuracy.

Minimizing Energy Depletion Using Extended Lifespan: QoS Satisfied Multiple Learned Rate (ELQSSM-ML) for Increased Lifespan of Mobile Adhoc Networks (MANET)

Mobile Adhoc Networks (MANETs) typically employ with the aid of new technology to increase Quality-of-Service (QoS) when forwarding multiple data rates. This kind of network causes high forwarding delays and improper data transfer rates because of the changes in the node’s vicinity. Although an optimized routing technique to transfer energy has been used to lessen the delay and improve the throughput by assigning a proper data rate, it does not consider the objective of minimizing the energy use, which results in less network lifetime. The goal of the proposed work is to minimize the energy depletion in a MANET, which results in an extended Lifespan of the network. In this research paper, an Extended Life span and QSSM-ML routing algorithm is proposed, which minimizes energy use and enhances the network lifetime. First, an optimization problem is formulated with the purpose of increasing the network’s lifetime while limiting the energy utilization and stability of the path along with residual. Second, an adaptive policy is applied for the asymmetric distribution of energy at both origin and intermediate nodes. In order to achieve maximum network lifespan and minimal energy depletion, the optimization problem was framed when power usage is a constraint by allowing the network to make use of the leftover power. An asymmetric energy transmission strategy was also designed for the adaptive allocation of maximum transmission energy in the origin. This made the network lifespan extended with the help of reducing the node’s energy use for broadcasting the data from the origin to the target. Moreover, the node’s energy use during packet forwarding is reduced to recover the network lifetime. The overall benefit of the proposed work is that it can achieve both minimal energy depletion and maximizes the lifetime of the network. Finally, the simulation findings reveal that the ELQSSM-ML algorithm accomplishes a better network performance than the classical algorithms.

Redactable Blockchain: Comprehensive Review, Mechanisms, Challenges, Open Issues and Future Research Directions

The continuous advancements of blockchain applications impose constant improvements on their technical features. Particularly immutability, a highly secure blockchain attribute forbidding unauthorized or illicit data editing or deletion, which functions as crucial blockchain security. Nonetheless, the security function is currently being challenged due to improper data stored, such as child pornography, copyright violation, and lately the enaction of the “Right to be Forgotten (RtbF)” principle disseminated by the General Data Protection Regulation (GDPR), where it requires blockchain data to be redacted to suit current applications’ urgent demands, and even compliance with the regulation is a challenge and an unfeasible practice for various blockchain technology providers owing to the immutability characteristic. To overcome this challenge, mutable blockchain is highly demanded to solve previously mentioned issues, where controlled and supervised amendments to certain content within constrained privileges granted are suggested by several researchers through numerous blockchain redaction mechanisms using chameleon and non-chameleon hashing function approaches, and methods were proposed to achieve reasonable policies while ensuring high blockchain security levels. Accordingly, the current study seeks to thoroughly define redaction implementation challenges and security properties criteria. The analysis performed has mapped these criteria with chameleon-based research methodologies, technical approaches, and the latest cryptographic techniques implemented to resolve the challenge posed by the policy in which comparisons paved current open issues, leading to shaping future research directions in the scoped field.

Generalized Score Distribution: A Two-Parameter Discrete Distribution Accurately Describing Responses From Quality of Experience Subjective Experiments

Subjective responses from Multimedia Quality Assessment (MQA) experiments are conventionally analysed with methods not suitable for the data type these responses represent. Furthermore, obtaining subjective responses is resource intensive. A method allowing reuse of existing responses would be thus beneficial. Applying improper data analysis methods leads to difficult to interpret results. This encourages drawing erroneous conclusions. Building upon existing subjective responses is resource friendly and helps develop machine learning (ML) based visual quality predictors. We show that using a discrete model for analysis of responses from MQA subjective experiments is feasible. We indicate that our proposed Generalised Score Distribution (GSD) properly describes response distributions observed in typical MQA experiments. We highlight interpretability of GSD parameters and indicate that the GSD outperforms the approach based on sample empirical distribution when it comes to bootstrapping. We evidence that the GSD outcompetes the state-of-the-art model both in terms of goodness-of-fit and bootstrapping capabilities. To do all of that we analyse more than one million subjective responses from more than 30 subjective experiments. Furthermore, we make the code implementing the GSD model and related analyses available through our GitHub repository: https://github.com/Qub3k/subjective-exp-consistency-check

Piezoelectric energy harvesters: A critical assessment and a standardized reporting of power-producing vibrational harvesters

Energy harvesting devices have emerged as an auspicious sustainable energy source for low-power electronics, where delivering electricity using conventional means is not feasible nor desirable. This clear technological impact has drawn huge attention and driven research into energy harvesting materials and devices. Reports are often published, even in high-caliber journals claiming high-efficiency devices. However, these are typically based on poorly defined or even undefined metrics and lack the details needed for re-evaluation and comparing different devices for peer assessment. The enthusiasm to publish is pushing the field towards qualitative rather than quantitative research. Here, after introducing the basic concepts of energy harvesting, randomly selected research papers on piezoelectric energy harvesting devices published over the last two decades, have been assessed. It is shown that essential parameters which are needed for a quantitative evaluation of materials and devices are missing from nearly 90% of the reviewed papers, thus rendering them less reproducible (or even irreproducible) for peer assessment. Such a frequent occurrence of improper data reporting damages the credibility and reliability of the energy harvesting field. To enhance reproducibility and facilitate progress, we herein suggest a measurement and data reporting protocol that should be followed when reporting energy harvesting devices and concomitant performances. The standardized protocol can be further adapted for other vibrational harvesters based on other mechanisms such as triboelectricity.

Identification of Content-Adaptive Image Steganography Using Convolutional Neural Network Guided by High-Pass Kernel

Digital images are very popular and commonly used for hiding crucial data. In a few instances, image steganography is misused for communicating with improper data. In this paper, a robust deep neural network is proposed for the identification of content-adaptive image steganography schemes. Multiple novel strategies are applied to improve detection performance. Two non-trainable convolutional layers is used to guide the proposed CNN with fixed kernels. Thirty-one kernels are used in both non-trainable layers, of which thirty are high-pass kernels and one is the neutral kernel. The layer-specific learning rate is applied for each layer. ReLU with customized thresholding is applied to achieve better performance. In the proposed method, image down-sampling is not performed; only the global average pooling layer is considered in the last part of the network. The experimental results are verified on BOWS2 and BOSSBase image sets. Content-adaptive steganography schemes, such as HILL, Mi-POD, S-UNIWARD, and WOW, are considered for generating the stego images with different payloads. In experimental analysis, the proposed scheme is compared with some of the latest schemes, where the proposed scheme outperforms other state-of-the-art techniques in the most cases.

Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets

Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited data type for training CNN-based speech emotion recognition (SER). The research experiments employed five popular datasets: Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto Emotional Speech Set (TESS), and The Interactive Emotional Dyadic Motion Capture (IEMOCAP). Six different classes of emotions were used: happiness, anger, sadness, fear, disgust, and neutral. However, some experiments were prepared to recognize just four emotions due to the characteristics of the IEMOCAP dataset. A comparison of classification efficiency on different datasets and an attempt to develop a universal model trained using all datasets were also performed. This approach brought an accuracy of 55.89% when recognizing four emotions. The most accurate model for six emotion recognition was trained and achieved 57.42% accuracy on a combination of four datasets (CREMA-D, RAVDESS, SAVEE, TESS). What is more, another study was developed that demonstrated that improper data division for training and test sets significantly influences the test accuracy of CNNs. Therefore, the problem of inappropriate data division between the training and test sets, which affected the results of studies known from the literature, was addressed extensively. The performed experiments employed the popular ResNet18 architecture to demonstrate the reliability of the research results and to show that these problems are not unique to the custom CNN architecture proposed in experiments. Subsequently, the label correctness of the CREMA-D dataset was studied through the employment of a prepared questionnaire.

How weak are Romanian clitic pronouns?

In traditional linguistics, pronouns are divided into two classes: those that can bear word stress, coined “strong”, “full” or “tonal”, and those that cannot, coined “weak”, “clitic”, or “atonal”. However, in the last decades, research on this topic has shown that items generally labeled as clitics are far more complex. Somewhere between words and affixes, these hybrid linguistic entities challenge both description and modeling. As for Romanian, the debate on weak (i.e., clitic) pronouns has been dominated by the question of their categorial status: are these items clitics or affixes? In this article, I present and scrutinize different approaches that support the claim that there are differences between proclitics and enclitics, i.e., between clitics occurring before vs. after the verb; this includes not only positional, but also featural differences. I identify various types of ambiguities in Romanian that could lead to improper data interpretation, and, based on an analysis of syllabicity – the most salient feature of Romanian weak pronouns – I refute claims for treating clitics in preverbal position differently than in postverbal position. Furthermore, using evidence from both historical data and data pertaining to language varieties, I show regularities in the Romanian weak pronoun system, bringing evidence against the claim that Romanian weak pronouns show a great deal of idiosyncrasies.

A multi‐preference integrated algorithm for deep learning based recommender framework

SummaryNowadays, the online recommender systems based collaborative filtering methods are widely employed to model long term user preferences (LTUP). The deep learning methods, like recurrent neural networks (RNN) have the potential to model short‐term user preferences (STUP). There is no dynamic integration of these two models in the existing recommender systems. Therefore, in this article, a multi‐preference integrated algorithm (MPIA) for deep learning based recommender framework (DLRF) is proposed to perform the dynamic integration of these two models. Moreover, the MPIA addresses improper data and to improve the performance for creating recommendations. This algorithm is depending on an enhanced long short term memory (LSTM) with additional controllers to consider relative information. Here, experiments are carried out by Amazon benchmark datasets, then obtained outcomes are compared with other existing recommender systems. From the comparison, the experimental outcomes show that the proposed MPIA outperforms existing systems under performance metrics, like area under curve, F1‐score. Consequently, the MPIA can be integrated with real time recommender systems.

Automatic missing value imputation for cleaning phase of diabetic’s readmission prediction model

Recently, the industry of healthcare started generating a large volume of datasets. If hospitals can employ the data, they could easily predict the outcomes and provide better treatments at early stages with low cost. Here, data analytics (DA) was used to make correct decisions through proper analysis and prediction. However, inappropriate data may lead to flawed analysis and thus yield unacceptable conclusions. Hence, transforming the improper data from the entire data set into useful data is essential. Machine learning (ML) technique was used to overcome the issues due to incomplete data. A new architecture, automatic missing value imputation (AMVI) was developed to predict missing values in the dataset, including data sampling and feature selection. Four prediction models (i.e., logistic regression, support vector machine (SVM), AdaBoost, and random forest algorithms) were selected from the well-known classification. The complete AMVI architecture performance was evaluated using a structured data set obtained from the UCI repository. Accuracy of around 90% was achieved. It was also confirmed from cross-validation that the trained ML model is suitable and not over-fitted. This trained model is developed based on the dataset, which is not dependent on a specific environment. It will train and obtain the outperformed model depending on the data available.