Identification Phase Research Articles

Distinguishing Between Lactation Failure and Breastfeeding Cessation: A Scoping Review.

Background: Interchangeable terminology and definitions of breastfeeding difficulties may inadvertently influence premature cessation of breastfeeding. Lactation failure is a distinct concept from breastfeeding cessation, and it is vital to differentiate between them, especially in educating health care professionals in communicating and supporting mothers perinatally. Purpose: Comprehensively review varying terminology and definitions, providing a more nuanced understanding of lactation failure versus breastfeeding cessation, and highlighting physiological and social, emotional, mental, and commercial factors that influence breastfeeding outcomes. Method: A scoping review of published literature from medical and scientific databases such as MEDLINE (via PubMed), Scopus, and Web of Science from 2000 to 2023. Results: N = 476 publications were collected during the identification phase; N = 49 from 28 countries around the world met the inclusion criteria and were used in the review. Only N = 13 studies ventured definitions for the terms used. Factors affecting breastfeeding were categorized as physiological leading to lactation failure and distinguished from social, mental, emotional, or commercial factors leading to breastfeeding cessation. Recommendations and Conclusions: Understanding the complexity of the factors underlying lactation failure and breastfeeding cessation can be improved by delineating the terminology and definitions variations used to communicate, provide awareness, education, design and delivery of interventions and support for initiation, and continuation of breastfeeding. Further in-depth research and analysis of the complex issues and factors influencing breastfeeding practices is required.

Data-driven dynamic state estimation in power systems via sparse regression unscented Kalman filter

This paper proposes a novel data-driven modeling and dynamic state-estimation approach for nonlinear power and energy systems, highlighting the critical role of a known dynamic model for accurate state estimation in the face of uncertainty and complex models. The proposed framework consists of a two-phase approach: data-driven model identification and state-estimation. During the model identification phase, which spans a relatively short time interval, state feedback is collected to identify the dynamics of the nonlinear systems in the power grid using a novel density-guided sparse identification algorithm. Unlike conventional sparse regression, which relies on a large library of linear and nonlinear functions to fit data, our proposed algorithm iteratively updates a relatively small initial library by adding higher-order nonlinear functions if the coefficients of the current functions are dense. Following the identification of the model’s dynamics, the estimation phase addresses the challenge of incomplete state measurements. By implementing an unscented Kalman filter, the state variables of the system are dynamically estimated by measuring the noisy output. Finally, simulation results on an IEEE 30-bus system are presented to illustrate the effectiveness of the density-guided sparse regression unscented Kalman filter compared to a physics-based unscented Kalman filter with model uncertainty. This study contributes to the fields of data-driven modeling techniques, machine learning for power systems, and computational intelligence in smart grids. It emphasizes the use of advanced sparse regression and unscented Kalman filter methods for state estimation, enhancing the robustness and accuracy of monitoring and control in electrical and energy systems.

A stimulus-based model of the team adaptation process: An integrated conceptual review.

As organizations face constant pressures to respond to changing situations and emergent demands, team members are frequently called upon to change their processes and routines and adapt to new ways of working together. In examining adaptation, most researchers have taken a behavior-driven approach where they collapse across the many types of adaptive demands teams face and rely on traditional input-process-outcome frameworks (e.g., Hackman, 1987; McGrath, 1984) to isolate specific behavioral responses. However, this perspective has resulted in several critical limitations. There are key differences in the way teams must collectively respond to different types of adaptive stimuli to be successful, and current research cannot account for or differentiate adaptive demands by stimulus type and needed responses. In this integrated conceptual review, we address these limitations and develop a novel, stimulus-based phase model of team adaptation. We examine studies across our newly developed stimulus detection, urgency identification, and duration assessment phases, and through the team's adaptive response, adaptive performance, and learning from the experience. We integrate research within each phase of the adaptive process, highlighting factors that demonstrate what successful team adaptation "looks like," and describe future avenues of research to address key issues within each phase. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

8765 Assessment of the Social Vulnerability Index of a 10-Year Retrospective Cohort of Youth with Prediabetes

Abstract Disclosure: D. Somerville: None. R.H. Kolagani, MHS: None. C.E. McCrory: None. S. Budakoti: None. V.M. Chinchilli, PhD: None. J. Joseph: None. D.E. Hale: None. N. Raja-Khan: None. L.P. Huerta Saenz: None. Background: The incidence of prediabetes (preD) is rising among youth in the US. While there are known metabolic risk factors linked to preD development, we were interested in exploring the role of social determinants of health (SDoH) in the development of pediatric preD. The social vulnerability index (SVI) is a tool developed by the CDC to stratify SDoH risk for communities based on 14 factors such socioeconomic status (SES), household composition, race and transportation access. By understanding the role of SVI in the development of preD in youth, we may be able to plan interventions to prevent progression to Type 2 Diabetes (T2D). Objective: Our study goal was to determine the relationship between SVI and preD in youth receiving care at our institution, a large pediatric referral center in Central Pennsylvania. Methods: We conducted a 10-year retrospective chart review of electronic medical records (EMRs) to identify children/youth aged 6-17 years old diagnosed with preD at our pediatric health system between 01/2010 and 01/2020. We used the American Diabetes Association definitions of preD (one or more sub-type): 1) Impaired fasting glucose (IFG), 2) Impaired glucose tolerance (IGT), and 3) Elevated hemoglobin A1c (HA1C). ICD10 codes were used for initial chart identification (R73.01, R73.02, R73.03 and R73.09). The second phase of identification of youth with preD included the review of biological measures of glycemia of the initial identified charts to support the reported ICD10 diagnosis (either isolated subtypes or combinations). Social, demographic characteristics, and residence setting (urban vs. rural) were also investigated. SVI was assessed on a 0-1 scale, with high SVI (0.5-1) indicating greater social vulnerability and low SVI (0-0.49) indicating lower social vulnerability. Rurality was determined per the Health Resources and Services Administration Tool (HRSA). SAS frequencies were calculated. Fisher’s exact tests were applied to compare the frequencies of the aforementioned groups with respect to IFG, IGT, and HA1C. Results: We identified 2700 charts of youth with preD per ICD10 codes search, but only 552 had confirmed preD diagnosis supported by biological data registered in EMRs. The most common preD isolated subtype was HA1C (87.3%), while 12% and 4% had isolated IFG and IGT, respectively. Most youth had high SVI (66.9%) and only 5.8% were rural (p > 0.05). Neither SVI or rurality were associated with isolated preD subtypes, but 8.2% of low-SVI youth had composite [IFG +HA1C] subtypes compared to 3.5% of high-SVI youth (p=0.02). Conclusions: SVI was not significantly associated with any isolated preD subtype. However, youth with the combined preD subtypes [IFG + HA1C] had lower SVI. As T2D is more prevalent in youth from low SES, addressing SDoH at earlier stages of T2D (preD phase) is needed in the effort to prevent the progression of the disease. Presentation: 6/1/2024

Considering User Experience and Behavioral Approaches in the Design of mHealth Interventions for Atrial Fibrillation: Systematic Review.

Atrial fibrillation (AF) is a leading chronic cardiac disease associated with an increased risk of stroke, cardiac complications, and general mortality. Mobile health (mHealth) interventions, including wearable devices and apps, can aid in the detection, screening, and management of AF to improve patient outcomes. The inclusion of approaches that consider user experiences and behavior in the design of health care interventions can increase the usability of mHealth interventions, and hence, hopefully, yield an increase in positive outcomes in the lives of users. This study aims to show how research has considered user experiences and behavioral approaches in designing mHealth interventions for AF detection, screening, and management; the phases of designing complex interventions from the UK Medical Research Council (MRC) were referenced: namely, identification, development, feasibility, evaluation, and implementation. Studies published until September 7, 2022, that examined user experiences and behavioral approaches associated with mHealth interventions in the context of AF were extracted from multiple databases. The PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines were used. A total of 2219 records were extracted, with only 55 records reporting on usability, user experiences, or behavioral approaches more widely for designing mHealth interventions in the context of AF. When mapping the studies onto the phases of the UK MRC's guidance for developing and evaluating complex interventions, the following was found: in the identification phase, there were significant differences between the needs of patients and health care workers. In the development phase, user perspectives guided the iterative development of apps, interfaces, and intervention protocols in 4 studies. Most studies (43/55, 78%) assessed the usability of interventions in the feasibility phase as an outcome, although the data collection tools were not designed together with users and stakeholders. Studies that examined the evaluation and implementation phase entailed reporting on challenges in user participation, acceptance, and workflows that could not be captured by studies in the previous phases. To realize the envisaged human behavior intended through treatment, review results highlight the scant inclusion of behavior change approaches for mHealth interventions across multiple levels of sociotechnical health care systems. While interventions at the level of the individual (micro) and the level of communities (meso) were found in the studies reviewed, no studies were found intervening at societal levels (macro). Studies also failed to consider the temporal variation of user goals and feedback in the design of long-term behavioral interventions. In this systematic review, we proposed 2 contributions: first, mapping studies to different phases of the MRC framework for developing and evaluating complex interventions, and second, mapping behavioral approaches to different levels of health care systems. Finally, we discuss the wider implications of our results in guiding future mHealth research.

Implementation of Waterfall Model and User-Centered Design Integration

User-Centered Design (UCD) is a crucial approach in software development to ensure that the resulting product is user-friendly. However, the implementation of UCD within the software development lifecycle is still rarely discussed. This study aims to examine whether UCD can be integrated into the Waterfall model through the development of a web-based application. The integration process involves applying UCD during the requirements identification phase, followed by the other phases such as analysis, design, implementation, testing, and deployment. The research methods used include observation and interviews with the project implementers of the application development. The findings indicate that integrating UCD into the Waterfall model presents certain challenges, particularly due to the high risk of failure when the development phases do not allow returning to the initial phase that includes the UCD process. The interface evaluation conducted within the UCD process is proven to be crucial for the project's success.

A risk assessment of a gas pressure reduction station system with confidence for dealing with imprecisions and unknowns

Process systems are sensitive and vital industrial facilities. Disturbances in their performance may cause harm to the environment,humans,or significant economic damage. In risk assessment of chemical process industries, the available data, information, and knowledge are typically rare, limited, and often unrealistic. This issue poses a challenge to conducting a credible quantitative risk assessment and effects the robustness of the results. To address these challenges, this work proposes a methodology based on the Dempster-Shafer theory of evidence as the reasoning framework. It incorporates risk identification, analysis, and mitigation phases to ensure a thorough analysis of risks and the integration of proactive risk reduction strategies. The approach aims to model the worst-case hazard scenario and assess associated risks using various methods such as FMECA, Bow-Tie, Credal Network, and Dempster-Shafer theory. The proposed approach models imprecision and data ambiguity using intervals and associated belief mass. This extension provides a basis for addressing the fundamental problem of prior ignorance about the distribution of the observed data, which is prevalent in data mining applications. A new approach is proposed that utilizes Belief and Plausibility curves, similar to a Cumulative Distribution Function, to propagate uncertainty, enhance criticality discrimination, and determine cumulated belief measures. This approach is applied in analyzing the failure modes identified in FMECA and is further extended through the credal network for comprehensive risk assessment. Results show how to express irrelevant and independent judgments, and how to work out with inferences in credal networks. This issue is often overlooked, but if properly addressed it represents the key to ultimately drawing reliable conclusions and fully utilizing the system's available data. A case study of the City Gate Station system was used to verify the application potential of the proposed approach.

Efficiency evaluation of waste management: A systematic literature review of DEA applications

This paper aims to implement a systematic literature review to survey the Web of Science scientific database and review papers with an emphasis on the application of Data Envelopment Analysis (DEA) in the efficiency evaluation of waste management. This approach includes the identification, screening, eligibility, and inclusion phase of the relevant papers. The article also provides a theoretical overview of waste management and the DEA methodology. Researching the Web of Science scientific database according to the keywords “waste management”, “waste disposal” and “data envelopment analysis” led to 12 full-text published papers written in English. Qualitative analysis of papers was carried out with an emphasis on the analyzed country, i.e. region, time frame, applied DEA model, and included input and output variables in the model. Research of this type complements the scientific literature on the importance of waste management and provides key guidelines to scientists, policymakers, and authorities on efficient waste management as one of the key problems of today's society.

Multi-objective QoS optimization in swarm robotics

The “Internet of Robotic Things” (IoRT) is a concept that connects sensors and robotic objects. One of the practical applications of IoRT is swarm robotics, where multiple robots collaborate in a shared workspace to accomplish assigned tasks that may be challenging or impossible for a single robot to conquer. Swarm robots are particularly useful in critical situations, such as post-earthquake scenarios, where they can locate survivors and provide assistance in areas inaccessible to humans. In these life-saving situations, reliable and prompt communication among swarm robots is of utmost importance. To address the need for highly dependable and low-latency communication in swarm robotics, this research introduces a novel hybrid approach called Multi-objective QoS optimization based on Support vector regression and Genetic algorithm (MQSG). The MQSG method consists of two main phases: Parameter Relationship Identification and Parameter Optimization. In the Parameter Relationship Identification phase, the relationship between network inputs (Packet inter-arrival time, Packet size, Transmission power, Distance between sender and receiver) and outputs (quality of service (QoS) parameters) is established using support vector regression. In the parameter optimization phase, a multi-objective function is created based on the obtained relationships from the Parameter Relationship Identification phase. By solving this multi-objective function, optimal values for each QoS parameter are determined, leading to enhanced network performance. Simulation results demonstrate that the MQSG method outperforms other similar algorithms in terms of transmission latency, packet delivery rate, and the number of retransmitted packets.

A fire safety engineering approach to improving community resilience to the impacts of wildfire

AbstractEach year severe wildfires continue to cause significant destruction resulting in the loss of life, property, critical infrastructure, and the environment. In an effort to increase community preparedness and resilience to wildfire, international jurisdictions have adopted both guiding principles and prescriptive codes that apply to both urban planning and fire engineering design of buildings within the wildland–urban interface. These measures are intended to protect occupants, enhance the survivability of structures from different fire exposure mechanisms, and increase the chances of successful firefighting operations. However, research has identified (i) inconsistent approaches to regulation and governance; (ii) limited research on which urban design and building standards are based; and (iii) misaligned or contradictory urban design and building standards. This not only stifles the use of development proposing suitable performance‐based design that could achieve the required outcomes but can increase administrative burdens and development costs without increasing safety. The aim of this current study is to contribute to addressing identified shortfalls by identifying and distilling the last 23 years of research in the field related to (i) the development of evidence‐based performance requirements, and (ii) the application of effective governance arrangements in order to enhance urban design and wildfire engineering practices. These aims are achieved through a systematic literature review. Ultimately, however, of the 608 initial articles captured in the identification phase of the SLR, not a single article provided insight into the most effective regulatory or governance mechanism, and only three provided criteria suitable for adoption as a performance requirement. While the aims of this study were only partially achieved, it does provide a foundation for the field by way of identifying and distilling the current state of practice.

Identification of salty peptides from enzymolysis extract of oyster by peptidomics and virtual screening

Salty peptide as an important sodium substitute, which could reduce the risk of cardiovascular disease caused by excessive sodium intake. In this study, novel salty peptides were prepared and identified from enzymolysis extract of oysters by peptitomic identification, virtual screening and solid phase synthesis. Additionally, molecular simulation was used to study the taste mechanism of salty peptides. 316 peptides were identified in the enzymatic hydrolysates of oysters. 6 peptides, selected through virtual screening, were synthesized using solid-phase synthesis, and EK, LFE, LEY and DR were confirmed to possess a pleasing salty taste through electronic tongue evaluation. Molecular docking results indicated that these 4 peptides could enter the binding pocket within the transmembrane channel-like 4 (TMC4) cavity, wherein salt bridges, hydrogen bonds and attractive charges were the main binding forces. This study provides a rapid screening method for salty peptides in sea food products but possibly applied for other sources.

Methodology for Stakeholder Prioritization in the Context of Digital Transformation and Society 5.0

This paper addresses a pragmatic and well-articulated qualitative methodology for the identification, prioritization, and consultation of stakeholder groups for a higher education institution as a key element for the organization in the context of digital transformation and Industry 5.0. First, the identification phase required technological surveillance and competitive intelligence, which allowed for defining the organization’s stakeholders and their characteristics. Then, the prioritization phase was performed to determine the stakeholders that potentially will have the greatest impact on achieving the institution’s strategic objectives to the targets of the Sustainable Development Goals prioritized by the institution, and those who will be most affected (positively or negatively) by the HEI activities. Finally, different methods and technological tools were used for consulting internal and external stakeholders, according to the type of relationship with each group, which allowed the understanding of the perceptions of different stakeholder groups on issues such as gender equity, mental health, regenerative economy, and diversity training. The results are then presented in terms of organizational context, where the concept of stakeholder group was defined by the dynamics of the selected HEI; the prioritized stakeholders include students, employees, academic and research sector, public sector, business sector, social sector, community, archdiocese and diocese, alumni, donors, and benefactors. This approach enabled the identification of issues that became a priority in the university’s actions towards the future. Although the presented methodology is mainly qualitative, which can represent a high degree of subjectivity, the stakeholder prioritization exercise provides organizations with inputs for decision making aligned with their needs and expectations. Using such a methodology can help the organization to experience structural changes reflected in improved strategic alignment, understanding, and satisfaction of stakeholders’ expectations and needs, enhancement of reputation, risk and conflict mitigation, and the consolidation of long-term healthy and trustworthy relationships, in the context of Society 5.0, where human-centered solutions are expected.

Efficient fuzzy methodology for congestion control in wireless sensor networks

In wireless sensor networks (WSNs), ensuring reliable and efficient communication between nodes requires effective congestion control. This study presents an innovative approach, called FSFG, which combines FCM fuzzy clustering, Fuzzy Inference System (FIS), Support Vector Regression (SVR), and Genetic Algorithm (GA) to address congestion in WSNs. FSFG consists of two phases: Structure Identification and Parameter Identification. In the first phase, fuzzy clustering techniques are employed to determine the desirability of outputs in different classes. Subsequently, support vector regressions are used to determine membership functions with a minimal error rate. In the parameter identification phase, the obtained rules from the FCM method are used to design the desired system, enabling the estimation of necessary outputs based on relevant inputs. Through simulations, the results demonstrate that the FSFG algorithm excels in congestion control, exhibiting a lower error rate and outperforming other algorithms in terms of delay and packet delivery rate.

The Concentration of Lead, Cadmium, Copper, Nickel, Zinc, Manganese and Iron in Saffron: A Meta-analysis and Systematic Review

Background: We aimed to investigate the concentrations of metals, including lead (Pb), cadmium (Cd), copper (Cu), nickel (Ni), iron (Fe), zinc (Zn), and manganese (Mn), in various types of saffron. Methods: All published studies until 2022 were searched from PubMed, Scopus and Web of Science databases. The published articles’ references were also evaluated to investigate the prevalence of heavy metal contamination in different types of saffron. The heterogeneity and concentration were estimated using I2 and the random effect model, respectively. Results: Among 128 articles retrieved in the identification phase, eight articles were included in this meta-analysis. The Pb exhibited the highest concentration among metals, with an average concentration of 0.10 mg/kg and a range of 0.11-0.10 mg/kg. Cd had the lowest concentration, with an average of 0.009 mg/kg and a range of 0.008-0.010 mg/kg. The concentration of Ni, Fe, Zn, Mn, and Cu were also in accordance with the sequence of Ni>Fe>Zn>Mn>Cu. Specifically, Ni demonstrated the highest concentration among essential metals in the sample, with an average of 2.81 mg/kg and a range of 2.76-2.86 mg/kg, while Cd displayed the lowest concentration, with an average of 0.022 mg/kg and a range of 0.023-0.023 mg/kg. Conclusion: The concentration of different metals in the examined saffron was variable, which can be attributed to several factors, including characteristics of the metals, nature of the saffron plant, composition of the irrigation water and the soil used for production of the plant, water conditions and crop cultivation.

Auto-tuning method for PI controllers under Symmetric-Send-on-Delta sampling strategy

In this work, an auto-tuning method for PI controllers applied in a loop under a Symmetric-Send-On-Delta sampling strategy is proposed. Auto-tuning algorithms usually implement an identification phase to obtain some information about the system dynamic that is used for tuning the controller. In our proposal, two frequency response points are estimated through an iterative procedure. With this information, a simple tuning rule is applied which guarantees robustness against limit cycle oscillations that can be induced by the SSOD sampler. Both the robustness measure to limit cycles and the identification procedure are based on the describing function technique, whose validity in the networked control systems under study requires a low incidence of losing packets as well as the transmission delays to be known or negligible compared to the system’s dynamic. Comparatives with other classical tuning rules support the suitability of the proposed method. The auto-tuning procedure has been validated through a simulation study reflecting its applicability for the most common dynamics found in industrial processes.

Analysis of Frameworks for Digital Skills Training for Secondary School Teachers: A Systematic Review

To improve the quality of education, educators must be provided with updated curricular proposals, resources, and tools to optimize and develop their digital competencies regularly. This systematic literature review aims to investigate the association between frameworks, training, and diagnostic strategies used from 2017 to October 2022 to enhance the digital proficiency of secondary school educators. The PRISMA methodology guidelines were followed. From 589 documents in Scopus and after the identification, screening, eligibility and inclusion phases, an in-depth sample analysis (n=29) was performed with ATLAS.ti. The study identified DigCompEdu, DigComp and the INTEF framework as the primary sources of reference for creating of face-to-face and online training programs. Ad hoc diagnostic research and the application of established tools were predominantly led by Spain and Portugal. Three aspects stand out: a growing trend to develop digital competencies comprehensively and not only at the instrumental level; however, it is recognized that some proposals focus on the identification and improvement of specific sub-competencies. Secondly, there is a need to create permanent communication channels to update and improve the different dimensions of the digital competence of teachers through contributions, questions and experiences shared in virtual communities, not only during training. Lastly, there is the possibility of creating digital certification systems for new levels of competence with alternatives such as micro-credentials.

Endometriosis risk is associated with shorter anogenital distance by meta-analysis

ObjectiveAnogenital distance is a well-validated marker of prenatal testosterone, with shorter distances indicating lower levels during early gestation. A suite of studies has tested for links of anogenital distance with risk of endometriosis, but the findings are variable, leading to uncertainty in interpretation. This study was conducted to provide an overall statistical assessment of whether anogenital distance is altered in women with endometriosis, compared to controls. Materials and methodsA systematic review and meta-analysis were conducted on the association of endometriosis with anogenital distance. Three databases were queried in the identification phase, and a random-effects meta-analysis was applied to the data in studies that met the inclusion criteria. ResultsMeta-analysis showed that shorter anogenital distance AF, measured from the anus to the posterior fourchette, was significantly associated with higher risk of endometriosis in the meta-analysis. By contrast, the association for anogenital distance AC, measured from the anus to the clitoral surface, was non-significant. Both analyses demonstrated significant heterogeneity across studies. Too few studies were available for robust investigation of publication bias. ConclusionsThe association of short anogenital distance with endometriosis risk provides support for the hypothesis that endometriosis represents, in part, a disorder mediated by relatively low testosterone levels in early prenatal development. This conclusion has implications for understanding the causes and treatment of endometriosis.

Self-supervised motor imagery EEG recognition model based on 1-D MTCNN-LSTM network

Objective. Aiming for the research on the brain–computer interface (BCI), it is crucial to design a MI-EEG recognition model, possessing a high classification accuracy and strong generalization ability, and not relying on a large number of labeled training samples. Approach. In this paper, we propose a self-supervised MI-EEG recognition method based on self-supervised learning with one-dimensional multi-task convolutional neural networks and long short-term memory (1-D MTCNN-LSTM). The model is divided into two stages: signal transform identification stage and pattern recognition stage. In the signal transform recognition phase, the signal transform dataset is recognized by the upstream 1-D MTCNN-LSTM network model. Subsequently, the backbone network from the signal transform identification phase is transferred to the pattern recognition phase. Then, it is fine-tuned using a trace amount of labeled data to finally obtain the motion recognition model. Main results. The upstream stage of this study achieves more than 95% recognition accuracy for EEG signal transforms, up to 100%. For MI-EEG pattern recognition, the model obtained recognition accuracies of 82.04% and 87.14% with F1 scores of 0.7856 and 0.839 on the datasets of BCIC-IV-2b and BCIC-IV-2a. Significance. The improved accuracy proves the superiority of the proposed method. It is prospected to be a method for accurate classification of MI-EEG in the BCI system.

IoT device type identification using training deep quantum neural networks optimized with a chimp optimization algorithm for enhancing IoT security

IoT networks can be defined as groups of physically connected things and devices that can connect to the Internet and exchange data with one another. Since enabling an increasing number of internets of things devices to connect with their networks, organizations have become more vulnerable to safety issues and attacks. A major drawback of previous research is that it can find out prior seen types only, also any new device types are considered anomalous. In this manuscript, IoT device type detection utilizing Training deep quantum neural networks optimized with a Chimp optimization algorithm for enhancing IOT security (IOT-DTI-TDQNN-COA-ES) is proposed. The proposed method entails three phases namely data collection, feature extraction and detection. For Data collection phase, real network traffic dataset from different IoT device types are collected. For feature mining phase, the internet traffic features are extracted through automated building extraction (ABE) method. IoT device type identification phase, Training deep quantum neural networks (TDQNN) optimized with Chimp optimization algorithm (COA) is utilized to detect the category of IoT devices as known and unknown device. IoT network is implemented in Python. Then the simulation performance of the proposed IOT-DTI-TDQNN-COA-ES method attains higher accuracy as26.82% and 23.48% respectively, when compared with the existing methods.

A mobile edge computing-focused transferable sensitive data identification method based on product quantization

Sensitive data identification represents the initial and crucial step in safeguarding sensitive information. With the ongoing evolution of the industrial internet, including its interconnectivity across various sectors like the electric power industry, the potential for sensitive data to traverse different domains increases, thereby altering the composition of sensitive data. Consequently, traditional approaches reliant on sensitive vocabularies struggle to adequately address the challenges posed by identifying sensitive data in the era of information abundance. Drawing inspiration from advancements in natural language processing within the realm of deep learning, we propose a transferable Sensitive Data Identification method based on Product Quantization, named PQ-SDI. This innovative approach harnesses both the composition and contextual cues within textual data to accurately pinpoint sensitive information within the context of Mobile Edge Computing (MEC). Notably, PQ-SDI exhibits proficiency not only within a singular domain but also demonstrates adaptability to new domains following training on heterogeneous datasets. Moreover, the method autonomously identifies sensitive data throughout the entire process, eliminating the necessity for human upkeep of sensitive vocabularies. Extensive experimentation with the PQ-SDI model across four real-world datasets, resulting in performance improvements ranging from 2% to 5% over the baseline model and achieves an accuracy of up to 94.41%. In cross-domain trials, PQ-SDI achieved comparable accuracy to training and identification within the same domain. Furthermore, our experiments showcased the product quantization technique significantly reduces the parameter size by tens of times for the subsequent sensitive data identification phase, particularly beneficial for resource-constrained environments characteristic of MEC scenarios. This inherent advantage not only bolsters sensitive data protection but also mitigates the risk of data leakage during transmission, thus enhancing overall security measures in MEC environments.