Minimal Complexity Research Articles

Machine Learning Based Diagnosis for Diabetic Retinopathy for SKPD-PSC

The study aimed to apply to Machine Learning (ML) researchers working in image processing and biomedical analysis who play an extensive role in comprehending and performing on complex medical data, eventually improving patient care. Developing a novel ML algorithm specific to Diabetic Retinopathy (DR) is a challenge and need of the hour. Biomedical images include several challenges, including relevant feature selection, class variations, and robust classification. Although the current research in DR has yielded favourable results, several research issues need to be explored. There is a requirement to look at novel pre-processing methods to discard irrelevant features, balance the obtained relevant features, and obtain a robust classification. This is performed using the Steerable Kernalized Partial Derivative and Platt Scale Classifier (SKPD-PSC) method. The novelty of this method relies on the appropriate non-linear classification of exclusive image processing models in harmony with the Platt Scale Classifier (PSC) to improve the accuracy of DR detection. First, a Steerable Filter Kernel Pre-processing (SFKP) model is applied to the Retinal Images (RI) to remove irrelevant and redundant features and extract more meaningful pathological features through Directional Derivatives of Gaussians (DDG). Next, the Partial Derivative Image Localization (PDIL) model is applied to the extracted features to localize candidate features and suppress the background noise. Finally, a Platt Scale Classifier (PSC) is applied to the localized features for robust classification. For the experiments, we used the publicly available DR detection database provided by Standard Diabetic Retinopathy (SDR), called DIARETDB0. A database of 130 image samples has been collected to train and test the ML-based classifiers. Experimental results show that the proposed method that combines the image processing and ML models can attain good detection performance with a high DR detection accuracy rate with minimum time and complexity compared to the state-of-the-art methods. The accuracy and speed of DR detection for numerous types of images will be tested through experimental evaluation. Compared to state-of-the-art methods, the method increases DR detection accuracy by 24% and DR detection time by 37.

Intelligent Intrusion Detection System for Industrial Internet of Things Environment

Rapid increase in the large quantity of industrial data, Industry 4.0/5.0 poses several challenging issues such as heterogeneous data generation, data sensing and collection, real-time data processing, and high request arrival rates. The classical intrusion detection system (IDS) is not a practical solution to the Industry 4.0 environment owing to the resource limitations and complexity. To resolve these issues, this paper designs a new Chaotic Cuckoo Search Optimization Algorithm (CCSOA) with optimal wavelet kernel extreme learning machine (OWKELM) named CCSOA-OWKELM technique for IDS on the Industry 4.0 platform. The CCSOA-OWKELM technique focuses on the design of feature selection with classification approach to achieve minimum computation complexity and maximum detection accuracy. The CCSOA-OWKELM technique involves the design of CCSOA based feature selection technique, which incorporates the concepts of chaotic maps with CSOA. Besides, the OWKELM technique is applied for the intrusion detection and classification process. In addition, the OWKELM technique is derived by the hyperparameter tuning of the WKELM technique by the use of sunflower optimization (SFO) algorithm. The utilization of CCSOA for feature subset selection and SFO algorithm based hyperparameter tuning leads to better performance. In order to guarantee the supreme performance of the CCSOA-OWKELM technique, a wide range of experiments take place on two benchmark datasets and the experimental outcomes demonstrate the promising performance of the CCSOA-OWKELM technique over the recent state of art techniques.

Load-Aware VM Migration Using Hypergraph Based CDB-LSTM

Live Virtual Machine (VM) migration is one of the foremost techniques for progressing Cloud Data Centers’ (CDC) proficiency as it leads to better resource usage. The workload of CDC is often dynamic in nature, it is better to envisage the upcoming workload for early detection of overload status, underload status and to trigger the migration at an appropriate point wherein enough number of resources are available. Though various statistical and machine learning approaches are widely applied for resource usage prediction, they often failed to handle the increase of non-linear CDC data. To overcome this issue, a novel Hypergrah based Convolutional Deep Bi-Directional-Long Short Term Memory (CDB-LSTM) model is proposed. The CDB-LSTM adopts Helly property of Hypergraph and Savitzky–Golay (SG) filter to select informative samples and exclude noisy inference & outliers. The proposed approach optimizes resource usage prediction and reduces the number of migrations with minimal computational complexity during live VM migration. Further, the proposed prediction approach implements the correlation co-efficient measure to select the appropriate destination server for VM migration. A Hypergraph based CDB-LSTM was validated using Google cluster dataset and compared with state-of-the-art approaches in terms of various evaluation metrics.

A singular perturbation approach for the control of electromagnetic actuators

The paper is devoted to the control of electromagnetic actuators. Compared to most results in the literature, the design explicitly takes into account the nonlinearities and the magnetic saturation. An approach based on singularly perturbed systems is proposed to take advantage of the different time scales of the model and provide a minimal complexity control law. Associated with an integral action, this control law ensures accuracy and robustness w.r.t. some disturbances and some unknown parameters of the actuator. The use of the singular perturbation method allows also to limit the implementation complexity compared to classical methods such as backstepping control. The synthesis of the control law is then tested through simulations that illustrate the efficiency of the method.

Multi-criteria decision making and project portfolio management for transport infrastructure investment in Thailand

Transport project selection is always critical in government planning due to limited resources and diverse demands. Project portfolio management (PPM) was proposed in this study to suggest an optimal set of projects under predetermined constraints. With multiple conflicting criteria, comprehensive steps of multi-criteria decision making (MCDM) procedures were proposed in this study. The process begins with a step of pre-screening the projects and selecting the criteria for project evaluation. Sequential steps of: 1) weight determination process using the proportion method; 2) MCDM process using preference ranking organisation method for enrichment evaluations (PROMETHEE) II; 3) constraint consideration process using PROMETHEE V, was proposed to evaluate and select an optimal project portfolio. The study showed that decision making could be successfully done for the transport infrastructure investment with minimal complex calculation steps and questionnaire input from experts.

Facilitators and barriers to implementation of a patient and staff reported measure for screening of palliative concerns of patients with heart failure: a qualitative analysis using the Consolidated Framework for Implementation Research.

Screening patients with patient-reported outcome measures allows identification of palliative care concerns. The Integrated Palliative Care Outcome Scale (IPOS) was developed in the United Kingdom for this purpose. Tools developed in another setting might not be readily usable locally. We previously evaluated the validity and reliability of the IPOS in our cardiology setting. However, it remains uncertain what factors would influence the subsequent implementation of IPOS for routine screening of patients with advanced heart failure in future practice. This study aimed to identify the factors that could affect the IPOS implementation for patients with advanced heart failure. This was a qualitative study conducted at the National Heart Centre Singapore. Patients with advanced heart failure who participated in our previous IPOS validation study were purposively recruited for semi-structured interviews. Healthcare workers caring for these patients and involved in the testing of the IPOS tool were also invited for interviews. The interviews were analyzed thematically and mapped to the Consolidated Framework for Implementation Research (CFIR). Our analysis identified six potential facilitators and six potential barriers to implementation across five major domains of the CFIR (intervention characteristics, inner setting, outer setting, individual characteristics, and process). Facilitators include: (i) perception of utility, (ii) perception of minimal complexity, (iii) perception of relatability, (iv) conducive culture, (v) dedicated resources, and (vi) advocates for implementation. Barriers include: (i) need for adaptation, (ii) mindsets/role strains, (iii) resource constraints, (iv) cultural concerns, (v) individual needs, and (vi) change process. Institutions could focus on cultivating appropriate perceptions and conducive cultures, providing dedicated resources for implementation and introducing facilitators to advocate for implementation. Adaptation of IPOS to suit workflows and individual needs, consideration of change processes, and systemic changes to alleviate cultural, resource, and staff role strains would improve IPOS uptake during actual implementation in clinical services. Not applicable.

APLF and long non-coding RNA NIHCOLE promote stable DNA synapsis in non-homologous end joining

The synapsis of DNA ends is a critical step for the repair of double-strand breaks by non-homologous end joining (NHEJ). This is performed by a multicomponent protein complex assembled around Ku70-Ku80 heterodimers and regulated by accessory factors, including long non-coding RNAs, through poorly understood mechanisms. Here, we use magnetic tweezers to investigate the contributions of core NHEJ proteins and APLF and lncRNA NIHCOLE to DNA synapsis. APLF stabilizes DNA end bridging and, together with Ku70-Ku80, establishes a minimal complex that supports DNA synapsis for several minutes under piconewton forces. We find the C-terminal acidic region of APLF to be critical for bridging. NIHCOLE increases the dwell time of the synapses by Ku70-Ku80 and APLF. This effect is further enhanced by a small and structured RNA domain within NIHCOLE. We propose a model where Ku70-Ku80 can simultaneously bind DNA, APLF, and structured RNAs to promote the stable joining of DNA ends.

Honeynet Implementation in Cyber Security Attack Prevention with Data Monitoring System Using AI Technique and IoT 4G Networks

Cyber Physical Systems (CPS) comprises of the ubiquitous object concept those are connected with Internet to provide ability of data transmission and sensing over network. The smart appliances transmits the data through CPS devices with the implementation of Internet of Things (IoT) exhibits improved performance characteristics with significant advantages such as time savings, reduced cost, higher human comfort and efficient electricity utilization. In the minimal complexity sensor nodes cyber physical system is adopted for the heterogeneous environment for the wireless network connection between clients or hosts. However, the conventional security scheme uses the mechanisms for desktop devices with efficient utilization of resources in the minimal storage space environment, minimal power processing and limited energy backup. This paper proposed a Secure Honeynet key authentication (SHKA) model for security attack prevention through effective data monitoring with IoT 4G communication. The proposed SHKA model uses the lightweight key agreement scheme for authentication to provide security threats and confidentiality issues in CPS applications. With the implementation of SHKA HoneyNet model the data in IoT are monitored for security mechanism in IoT environment. The middleware module in SHKA scheme uses the Raspberry platform to establish internetworking between CPS device to achieve dynamic and scalability. The secure IoT infrastructure comprises of flexible evaluation of user-centric environment evaluation for the effectiveness. The developed SHKA model perform mutual authentication between CPS devices for minimal computation overhead and efficiency. The wireless channel uses the dynamic session key for the secure communication for cyber-attacks security with lightweight security in CPS system. The SHKA model demonstrate the effectiveness based on consideration of three constraints such as low power processing, reduced storage and minimal backup energy. Experimental analysis stated that proposed SHKA scheme provides lightweight end-to-end key establishment in every session. The CPS devices generates the session key of 128 bit long. The minimum key size is implemented to provide effective security in IoT 4G communication with minimal execution time. The simulation results demonstrated that SHKA model exhibits effective cyber-attacks for the constraint devices to improve performance of IoT network.

Leveraging Azure Data Lake for Efficient Data Processing in Telematics

In the telematics industry, the continuous generation of large volumes of data presents significant challenges in terms of storage, processing, and analysis. Azure Data Lake, a scalable and secure data storage solution, offers an efficient platform to handle these massive datasets. This paper explores the application of Azure Data Lake in telematics for efficient data processing, focusing on its capacity to store vast amounts of structured and unstructured data while providing seamless integration with various analytics tools. By leveraging Azure Data Lake, organizations can enhance their data processing capabilities, improve decision-making, and reduce operational costs. The study investigates how Azure Data Lake simplifies data management through its high availability and accessibility, allowing businesses to manage data from multiple sources with minimal complexity. Furthermore, the integration with Azure services like Azure Data Factory and Azure Databricks facilitates advanced analytics, enabling real-time insights and predictive analytics, which are crucial for the telematics sector. The findings suggest that adopting Azure Data Lake improves data processing efficiency, enhances scalability, and supports the development of innovative telematics applications such as fleet management and vehicle monitoring systems. The paper concludes by highlighting the potential of Azure Data Lake to revolutionize the telematics industry by enabling more agile and data-driven operations.

Design and analysis of multi core fiber with 2 × 3 supermodes for high spatial density optical links

We present the design of uncoupled-coupled group multi core fiber (U-CG-MCF) with 125-μm cladding diameter for high spatial density optical space division multiplexing links. Design approaches used for uncoupled MCF and coupled MCF are combined in the proposed design that has two groups of cores. All the three cores that belong to same group have strong coupling among them and form supermodes. As the number of cores involved in strong coupling is less than the total number of six cores and coupling is suppressed between cores in adjacent groups, the receiver complexity will be minimal for the proposed fiber. Trench-assisted heterogeneous core group profiles are used in this work to suppress the crosstalk between similar supermodes in adjacent core groups and to reduce the core group separation. Coupling coefficient in the order of 10 − 3 per meter is achieved at 1.55-μm wavelength for all the supermodes with a small core group separation of 34 μm. Simulation results promise the applicability of the proposed 125-μm U-CG-MCF with minimum receiver complexity for future high spatial density optical links in C and L wavelength bands.

Spatial Ecology and Movement Patterns of Eastern Diamondback Rattlesnakes (Crotalus adamanteus) on a University Campus in Southwest Florida

Eastern Diamondback Rattlesnakes (Crotalus adamanteus) are a species of conservation concern throughout their range. Yet, despite decades of population declines, C. adamanteus has not garnered protective status. With limited information on its general life history, more research is needed to manage C. adamanteus populations effectively, particularly at the southern extent of their distribution. To fill knowledge gaps in the ecology of C. adamanteus, we radiotracked six adult female and four male C. adamanteus from December 2015 to March 2018 (1,880 relocations) on a university campus in southwest Florida. Male snakes maintained large annual home ranges (mean = 65.7 ha 100% minimum complex polygons [MCP]) that were twice that of females (mean = 26.7 ha 100% MCP). Male snakes also made longer daily movements (mean = 39.4 ± confidence interval [CI] 34.7–44.0 m/d) than did females (mean = 16.7 ± CI 15.0–18.5 m/d), although both sexes showed variation among individuals. Snakes made considerable use of habitats adjacent to human development (<5 m from roadways and/or buildings), which consisted of more upland features than surrounding areas and may have provided thermoregulation benefits. However, snakes rarely crossed trafficked roads, which appeared to create barriers to their use of the landscape. Our research provides a better understanding of the spatial limits and dispersal patterns of C. adamanteus near the southernmost extent of its geographic range and within an urbanized landscape, which may assist in the implementation of effective management strategies.

Geometry of solutions to the c-projective metrizability equation

On an almost complex manifold, a quasi-Kähler metric, with canonical connection in the c-projective class of a given minimal complex connection, is equivalent to a nondegenerate solution of the c-projectively invariant metrizability equation. For this overdetermined equation, replacing this maximal rank condition on solutions with a nondegeneracy condition on the prolonged system yields a strictly wider class of solutions with non-vanishing (generalized) scalar curvature. We study the geometries induced by this class of solutions. For each solution, the strict point-wise signature partitions the underlying manifold into strata, in a manner that generalizes the model, a certain Lie group orbit decomposition of \(\mathbb{C}\mathbb{P}^m\). We describe the smooth nature and geometric structure of each strata component, generalizing the geometries of the embedded orbits in the model. This includes a quasi-Kähler metric on the open strata components that becomes singular at the strata boundary. The closed strata inherit almost CR-structures and can be viewed as a c-projective infinity for the given quasi-Kähler metric.

Constructal design of a nanofluid cooling channel with sidewall ribs and cavities in a rectangular heat generation body

The heat dissipation optimization of electronic devices with cooling channels is a hot research issue. A nanofluid cooling channel (CCL) model with sidewall ribs and cavities in a rectangular heat generation body is established. The CCL is designed with minimum complex function composed of the maximum temperature difference (MTD) and pumping power consumption (PPC). When the volumes of the CCL, sidewall ribs and cavities are constrained, the optimal nanoparticle volume fraction, aspect ratio, cavity radius and sidewall rib radius of the CCL are 1%, 1.43, 1.04 and 1.30 within their discussed ranges, and the complex function after constructal design is reduced by up to 14.3%. For the multi-objective optimization by using NSGA-II, the PPC gained by TOPSIS decision-making strategy is abated by 28.4%, and the MTD is augmented by 8.0%. The deviation index of this strategy is 0.250, which is the lowest one among the discussed strategies. Thus, the optimal structure gained by this strategy can be served as the optimal design solution. The novelty of this paper is the application of constructal theory to the structure optimization of nanofluid CCL model, which provides better comprehensive performance with certain system constraints.

RGSO-UAV: Reverse Glowworm Swarm Optimization inspired UAV path-planning in a 3D dynamic environment

Three-dimensional path planning for UAVs is a very complex, NP-hard optimization problem. It is an effort to resolve the best feasible trajectory between the source and the destination while prohibiting collision in a dynamic environment. Many researchers have proposed different deterministic and non-deterministic solutions to the path-planning problem. However, it is still open to new promising methods to acquire better quality solutions with minimum time complexity. This article presents a novel methodology inspired by the Reverse Glowworm Swarm Optimization (RGSO) algorithm to resolve this problem for the UAV without colliding with any dynamic and static obstructions appearing in its path. A tuned path is generated after the initial one to optimize further and smoothen the trajectory. The proposed method has been extensively experimented with, and the outcomes show it outperforms the other algorithm in a three-dimensional dynamic environment in a path-planning strategy. The result shows that our proposed scheme reduces the value of the cost function by approximately 49% - 107% less than other existing approaches, and the execution time of this mechanism reduces by 2% - 61% compared with other existing methods. Thus, the proposed technique RGSO-UAV is an optimal and energy-efficient path-planning model in flying ad-hoc networks that enhance UAV's lifetime.

Engineered RecA Constructs Reveal the Minimal SOS Activation Complex.

The SOS response is a bacterial DNA damage response pathway that has been heavily implicated in bacteria's ability to evolve resistance to antibiotics. Activation of the SOS response is dependent on the interaction between two bacterial proteins, RecA and LexA. RecA acts as a DNA damage sensor by forming lengthy oligomeric filaments (RecA*) along single-stranded DNA (ssDNA) in an ATP-dependent manner. RecA* can then bind to LexA, the repressor of SOS response genes, triggering LexA degradation and leading to induction of the SOS response. Formation of the RecA*-LexA complex therefore serves as the key "SOS activation signal." Given the challenges associated with studying a complex involving multiple macromolecular interactions, the essential constituents of RecA* that allow LexA cleavage are not well defined. Here, we leverage head-to-tail linked and end-capped RecA constructs as tools to define the minimal RecA* filament that can engage LexA. In contrast to previously postulated models, we found that as few as three linked RecA units are capable of ssDNA binding, LexA binding, and LexA cleavage. We further demonstrate that RecA oligomerization alone is insufficient for LexA cleavage, with an obligate requirement for ATP and ssDNA binding to form a competent SOS activation signal with the linked constructs. Our minimal system for RecA* highlights the limitations of prior models for the SOS activation signal and offers a novel tool that can inform efforts to slow acquired antibiotic resistance by targeting the SOS response.

Brain tumor segmentation using a deep Shuffled‐YOLO network

AbstractBrain tumor is an anomalous proliferation of cells in the brain that can evolve to malignant and benign tumors. Currently, segmentation of brain tumor is the most important surgical and pharmaceutical procedures. However, manually segmenting brain tumors is hard because it is hard to find erratically shaped tumors with only one modality; the MRI modalities are integrated to provide multi‐modal images with data that can be utilized to segment tumors. The recent developments in machine learning and the accessibility of medical diagnostic imaging have made it possible to tackle the challenges of segmenting brain tumors with deep neural networks. In this work, a novel Shuffled‐YOLO network has been proposed for segmenting brain tumors from multimodal MRI images. Initially, the scalable range‐based adaptive bilateral filer (SCRAB) pre‐processing technique was used to eliminate the noise artifacts from MRI while preserving the edges. In the segmentation phase, we propose a novel deep Shuffled‐YOLO architecture for segmenting the internal tumor structures that include non‐enhancing, edema, necrosis, and enhancing tumors from the multi‐modality MRI sequences. The experimental fallouts reveal that the proposed Shuffled‐YOLO network achieves a better accuracy range of 98.07% for BraTS 2020 and 97.04% for BraTS 2019 with very minimal computational complexity compared to the state‐of‐the‐art models.

Construction of a Minimum Complexity Onboard Switched Network with Time Synchronization

Construction of a Minimum Complexity Onboard Switched Network with Time Synchronization

Comparison of Convolutional Neural Network for Classifying Lung Diseases from Chest CT Images

This paper proposes a convolutional neural network for diagnosing various lung illnesses from chest CT images based on a customized Medical Image Analysis and Detection network (MIDNet18). With simplified model building, minimal complexity, easy technique, and high-performance accuracy, the MIDNet-18 CNN architecture classifies binary and multiclass medical images. Fourteen convolutional layers, 7 pooling layers, 4 dense layers, and 1 classification layer comprise the MIDNet-18 architecture. The medical image classification process involves training, validating, and testing the MIDNet-18 model. In the Lung CT image binary class dataset, 2214 images as training set, 1800 images as validation set, and 831 as test set are considered for classifying COVID images and normal lung images. In the multiclass dataset, 6720 images as training sets belonging to 3 classes, 3360 images as validation sets and 601 images as test sets are considered for classifying COVID, cancer images and normal images. Independent sample size calculated for binary classification is 26 samples for each group. Similarly, 10 sample sizes are calculated for multiclass dataset classification keeping GPower at 80%. To validate the performance of the MIDNet18 CNN architecture, the medical images of two different datasets are compared with existing models like LeNet-5, VGG-16, VGG-19, ResNet-50. In multiclass classification, the MIDNet-18 architecture gives better training accuracy and test accuracy, while the LeNet5 model obtained 92.6% and 95.9%, respectively. Similarly, VGG-16 is 89.3% and 77.2% respectively; VGG-19 is 85.8% and 85.4%, respectively; ResNet50 is 90.6% and 99%, respectively. For binary classification, the MIDNet18 architecture gives better training accuracy and test accuracy, while the LeNet-5 model has obtained 52.3% and 54.3%, respectively. Similarly, VGG 16 is 50.5% and 45.6%, respectively; VGG-19 is 50.6% and 45.6%, respectively; ResNet-50 is 96.1% and 98.4%, respectively. The classified images are further predicted using detectron-2 model and the results identify abnormalities (cancer, COVID-19) with 99% accuracy. The MIDNET18 is significantly more accurate than LeNet5, VGG19, VGG16 algorithms and is marginally better than the RESNET50 algorithm for the given lung binary dataset (Bonferroni — one-way Anova and pairwise comparison of MIDNET, LeNet5, VGG19, VGG16, and RESNET 50 ([Formula: see text])). The proposed MIDNet18 model is significantly more accurate than LeNet5, VGG19, VGG16, ResNet50 algorithms in classifying the diseases for the given multiclass lung dataset (Bonferroni — one-way Anova and pairwise comparison of MIDNET18, LeNet5, VGG19, VGG16, ResNet50 ([Formula: see text])).

RETRACTED: Internet of Things security framework based on near field communication with Otway Rees protocol

AbstractInternet of Things (IoT) devices are crucial in different industries because they provide high‐functioning services to the IoT network connectivity. The IoT devices collect sensitive data, which comes under potential risk while transmitting data from one location to another. The data transmission is performed using various communication protocols that give security to the data. The intermediate attacks such as jamming, collision, flooding, worm‐hole, black‐hole and so forth create several security‐related issues. These intermediate attacks affect data privacy, trust, user identity, which completely affects the IoT device performance. So, this article introduces the near field communication (NFC) protocol with the Otway Rees protocol for making the secure communication process. In IoT applications based on short‐range communication, intermediate attacker issues have been reduced by combining NFC protocol features with Otway Rees protocol features. The NFC protocol provides baseline security trustworthiness while making the communication in the IoT environment cost‐effective. IoT communication is protected while cost‐effective using the security model, ensuring data integrity and confidentiality. In addition to this, the user and servers are authenticated for every session, which provides data security. Moreover, the discussed system is implemented using the NS2 simulation tool, ensuring security and trust with minimum complexity. Even in abnormal traffic conditions, our proposed method resulted in data transmission speeds (up to 289 Kb/s), and this feature can improve processing times.

On the Performance of Rate-Compatible LDPC Codes under All-Integer Quantization Decoding

From a practical point of view, quantization is necessary for the design of any low-complexity LDPC decoder. However, the quantization scheme with the minimum computational complexity called all-integer quantization has not been well investigated since, intuitively, it seems to significantly degrade the decoding performance. It is found in this work that the utilization of 4-bit all-integer quantization for MSA-based LDPC decoder is adequate to achieve the decoding performance of the nonquantized case which can be considered as the lower bound on the decoding performance. Moreover, this simple quantization scheme can also be applied to the hardware and cost-efficient rate-compatible LDPC codes.