Optimal Metrics Research Articles

Frequent, infinitesimal bottlenecks maximize the rate of microbial adaptation.

Serial passaging is a fundamental technique in experimental evolution. The choice of bottleneck severity and frequency poses a dilemma: longer growth periods allow beneficial mutants to arise and grow over more generations, but simultaneously necessitate more severe bottlenecks with a higher risk of those same mutations being lost. Short growth periods require less severe bottlenecks, but come at the cost of less time between transfers for beneficial mutations to establish. The standard laboratory protocol of 24-h growth cycles with severe bottlenecking has logistical advantages for the experimenter but limited theoretical justification. Here we demonstrate that contrary to standard practice, the rate of adaptive evolution is maximized when bottlenecks are frequent and small, indeed infinitesimally so in the limit of continuous culture. This result derives from revising key assumptions underpinning previous theoretical work, notably changing the metric of optimization from adaptation per serial transfer to per experiment runtime. We also show that adding resource constraints and clonal interference to the model leaves the qualitative results unchanged. Implementing these findings will require liquid-handling robots to perform frequent bottlenecks, or chemostats for continuous culture. Further innovation in and adoption of these technologies has the potential to accelerate the rate of discovery in experimental evolution.

Density peak clustering based on improved dung beetle optimization and mahalanobis metric

The density peak clustering algorithm (DPC) quickly divides each cluster based on high-density peak points and shows better clustering performance. In order to address the issue that the local density is constrained by the preset cut-off distance in DPC and the Euclidean distance cannot capture the possible correlation between different features, a DPC algorithm based on improved dung beetle optimization (IDBO) and Mahalanobis metric is proposed, called IDBO-MDDPC. The IDBO algorithm enhances the ball dung beetle individual by incorporating nonlinear dynamic factors to increase the search and development capabilities of the algorithm and by incorporating an adaptive cosine wave inertial weight strategy to more precisely determine the optimal position of the thief dung beetle in order to improve the convergence speed and accuracy of the algorithm. The IDBO algorithm is simulated on eight benchmark functions, and the results demonstrate that it is superior to other comparison algorithms in terms of convergence speed and accuracy. In the DPC algorithm, the Mahalanobis metric is used to capture the correlation between features to improve clustering performance. The IDBO algorithm is integrated with the DPC algorithm, and the F-Measure evaluation index is used to design the objective function so that the optimal value of the cut-off distance can be automatically selected. In order to evaluate the efficiency of the algorithm, three sets of artificially synthesized datasets and five sets of UCI standard datasets were chosen for studies. Experimental results show that the IDBO-MDDPC algorithm can automatically determine a better cut-off distance value and ensure higher clustering accuracy.

Tradeoff different construction project goals in using a novel multi-objective sea horse algorithm

Construction project managers aspire to achieve projects of the highest quality while minimizing time and cost. Presently, most trade-off analysis models focus predominantly on the traditional trifecta of time, cost, and quality, often overlooking other pivotal factors and project traits. This study introduces the Chaotic Adaptive Multi-Objective Sea Horse (CAMOSH), an innovative algorithm crafted to navigate the nuanced tradeoffs among time, cost, quality, risk, and environment (TCQRE) in comprehensive construction projects. CAMOSH leverages chaos sequences for population initialization and integrates an adaptive selection technique to harmonize exploitation and exploration during optimization. To facilitate the early-stage project implementation, the multiple-criteria decision analysis (MCDA) method is employed. When benchmarked against six esteemed algorithms across two construction projects, CAMOSH shows its superiority. Statistical evaluation underscores CAMOSH’s outstanding performance, evidenced by its top-ranking values in Diversity Measure (DM) and Hyper-Volume (HV) for both case studies. Furthermore, the algorithm consistently yields solutions with the most optimal Spacing Metric (SM) values and operates in the shortest time frames. These results collectively validate CAMOSH as an instrumental resource, equipping project managers to adeptly balance multifaceted construction project objectives and pinpoint the most effective project timeline.

A Design of Low-Projection SCMA Codebooks for Ultra-Low Decoding Complexity in Downlink IoT Networks

This paper conceives a novel sparse code multiple access (SCMA) codebook design which is motivated by the strong need for providing ultra-low decoding complexity and good error performance in downlink Internet-of-things (IoT) networks, in which a massive number of low-end and low-cost IoT communication devices are served. By focusing on the typical Rician fading channels, we analyze the pair-wise error probability of superimposed SCMA codewords and then deduce the design metrics for multi-dimensional constellation construction and sparse codebook optimization. For significant reduction of the decoding complexity, we advocate the key idea of projecting the multi-dimensional constellation elements to a few overlapped complex numbers in each dimension, called low projection (LP). An emerging modulation scheme, called golden angle modulation (GAM), is considered for multi-stage LP optimization, where the resultant multi-dimensional constellation is called LP-GAM. Our analysis and simulation results show the superiority of the proposed LP codebooks (LPCBs) including one-shot decoding convergence and excellent error rate performance. In particular, the proposed LPCBs lead to decoding complexity reduction by at least 97% compared to that of the conventional codebooks, whilst owning large minimum Euclidean distance. Some examples of the proposed LPCBs are available at https://github.com/ethanlq/SCMA-codebook.

Identification and Dosimetric Analysis of Axillary Substructures Associated with Breast Cancer Related Lymphedema

It has been hypothesized that substructures in the axillary region may be involved in the development of upper limb lymphedema in breast cancer patients. We aimed to compare dosimetric parameters of different substructures to identify risk regions and dose indicators related to the development of lymphedema. A total of 486 patients with breast cancer treated with axillary node dissection (ALND) and regional node irradiation (RNI) between 2017 and 2020 were analyzed. Ten axillary substructures were retrospectively contoured, and dose-volume histogram (DVH) parameters (maximum dose [Dmax], Dmean, Dmin, V5 Gy, V10 Gy, V15 Gy, V20 Gy, V25 Gy, V30 Gy, V35 Gy, V40 Gy, V45 Gy and V50 Gy) were evaluated. EQD2 using α/β = 3 was applied for hypofractionation. The cumulative incidence of lymphedema was 32.5% during the median follow-up of 25 month (IQR 15-35). Higher BMI (≥21.77 kg/m2, hazard ratio [HR]1.6, 95% CI 1.1-2.3, p = 0.019) and higher number of dissected lymph nodes (≥13, HR 1.8, 95% CI 1.1-3.0, p = 0.026) were baseline risk factors associated with breast cancer related lymphedema (BCRL). A cohort of 196 patients was obtained by 1:1 propensity score matching based on the above two factors (154 treated with 50 Gy/25 fractions [Fx] and 42 with 40.05 Gy/15Fx). The optimal metric was axillary-lateral thoracic vessel juncture (ALTJ) Dmean ≥36.84 Gy (HR 3.7, 95% CI 1.6-8.6, p = 0.002). Other significant risk factors are Medial of Axillary Nodes level I(ALN-I-M) Dmin <9.19 Gy (HR 2.3, 95% CI 1.4-3.7, p = 0.001) and Posterior of Axillary Nodes level II(ALN-II-P) Dmax <52.75 Gy (HR 2.0, 95% CI 1.2-3.5, p = 0.015). A nomogram incorporated the above three parameters was created to predict the risk of lymphedema with reasonable accuracy confirmed by both self-training (area under curve [AUC], 0.76; 95% CI, 0.67-0.84) and internal validation (AUC 0.66; 95% CI, 0.50-0.80). A mean dose of 36.84 Gy of ALTJ may be a suggested dose limit for patients indicated RNI after ALND, especially when patients with higher BMI and higher dissected nodes. Ideally, avoidance of ALTJ may be realized without compromising dose coverage to high-risk nodal region. Confirmation of this finding in future prospective studies is needed.

Discrimination between human epidermal growth factor receptor 2 (HER2)-low-expressing and HER2-overexpressing breast cancers: a comparative study of four MRI diffusion models.

To determine the value of conventional DWI, continuous-time random walk (CTRW), fractional order calculus (FROC), and stretched exponential model (SEM) in discriminating human epidermal growth factor receptor 2 (HER2) status of breast cancer (BC). This prospective study included 158 women who underwent DWI, CTRW, FROC, and SEM and were pathologically categorized into the HER2-zero-expressing group (n = 10), HER2-low-expressing group (n = 86), and HER2-overexpressing group (n = 62). Nine diffusion parameters, namely ADC, αCTRW, βCTRW, DCTRW, βFROC, DFROC, μFROC, αSEM, and DDCSEM of the primary tumor, were derived from four diffusion models. These diffusion metrics and clinicopathologic features were compared between groups. Logistic regression was used to determine the optimal diffusion metrics and clinicopathologic variables for classifying the HER2-expressing statuses. Receiver operating characteristic(ROC) curves were used to evaluate their discriminative ability. The estrogen receptor (ER) status, progesterone receptor (PR) status, and tumor size differed between HER2-low-expressing and HER2-overexpressing groups (p < 0.001 to p = 0.009). The αCTRW, DCTRW, βFROC, DFROC, μFROC, αSEM, and DDCSEM were significantly lower in HER2-low-expressing BCs than those in HER2-overexpressing BCs (p < 0.001 to p = 0.01). Further multivariable logistic regression analysis showed that the αCTRW was the single best discriminative metric, with an area under the curve (AUC) being higher than that of ADC (0.802 vs. 0.610, p < 0.05); the addition of ER status, PR status, and tumor size to the αCTRW improved the AUC to 0.877. The αCTRW could help discriminate the HER2-low-expressing and HER2-overexpressing BCs. Human epidermal growth factorreceptor 2 (HER2)-low-expressing breast cancer (BC) might also benefit from the HER2-targeted therapy. Prediction of HER2-low-expressing BC or HER2-overexpressing BC is crucial for appropriate management. Advanced continuous-time random walk diffusion MRI offers a solution to this clinical issue. • Human epidermal receptor 2 (HER2)-low-expressing BC had lower αCTRW, DCTRW, βFROC, DFROC, μFROC, αSEM, and DDCSEM values compared with HER2-overexpressing breast cancer. • The αCTRW was the single best diffusion metric (AUC = 0.802) for discrimination between the HER2-low-expressing and HER2-overexpressing breast cancers. • The addition of αCTRW to the clinicopathologic features (estrogen receptor status, progesterone receptor status, and tumor size) further improved the discriminative ability.

Patch-Based Adversarial Training for Error-Aware Circuit Annotation of Delayered IC Images

Circuit annotation is one of the most important tasks in the analysis of integrated circuit images for hardware assurance. Recently, deep learning methods have been adopted for circuit annotation due to their promising accuracy. However, the pixel-wise optimization metrics in deep learning methods are insufficient to ensure a good spatial contiguity in the segmentation results. This could result in circuit connection errors that are detrimental to the subsequent circuit analysis. In this paper, a patch-based adversarial training framework is proposed to mitigate such circuit connection errors. Our proposed method consists of a encoder-decoder segmentation network and a patch-based discriminator to provide adversarial supervision for the segmentation network. The adversarial training aligns the distributions of the segmentation results with the ground truth in patches, which we hypothesize to be more effective for mitigating circuit connection errors. In our experiments, we have achieved a 17.4% reduction in circuit connection errors as compared to the second best reported technique. We investigated the explainability of our proposed method through a heat map analysis, and demonstrate that our patch-based discriminator has a higher feature response in regions that are likely to contain circuit connection errors.

Strikes and Gutters: Biomarkers and anthropometric measures for predicting diagnosed diabetes mellitus in adults in low- and middle-income countries

BackgroundThe management of diabetes necessitates the requirement of reliable health indices, specifically biomarkers and anthropometric measures, to detect the presence or absence of the disease. Nevertheless, limited robust empirical evidence exists regarding the optimal metrics for predicting diabetes in adults, particularly within low- and middle-income countries. This study investigates objective and subjective indices for screening diabetes in these countries. Methods: Data for this study was sourced from surveys conducted among adults (aged 18 years and above) in seventeen (17) countries. Self-reported diabetes status, fifty-four biomarkers, and twenty-six core and twenty-eight estimated anthropometric indices, including weight, waist circumference, body mass index, glycaemic triglycerides, and fasting blood glucose, were utilised to construct lasso regression models. Results: The study revealed variances in diabetes prediction outcomes across different countries. Central adiposity measures, fasting plasma glucose and glycaemic triglycerides demonstrated superior predictive capabilities for diabetes when compared to body mass index. Furthermore, fasting plasma or blood glucose, serving as a biomarker, emerged as the most accurate predictor of diabetes. Conclusions: These findings offer critical insights into both general and context-specific tools for diabetes screening. The study proposes that fasting plasma glucose and central adiposity indices should be considered as routine screening tools for diabetes, both in policy interventions and clinical practice. By identifying adults with or at higher risk of developing diabetes and implementing appropriate interventions, these screening tools possess the potential to mitigate diabetes-related complications in low- and middle-income countries.

Transthyretin amyloid cardiomyopathy disease burden quantified using 99mTc-pyrophosphate SPECT/CT: volumetric parameters versus SUVmax ratio at 1 and 3 hours

BackgroundVarious parameters derived from technetium-99m pyrophosphate (99mTc-PYP) single-photon emission computed tomography (SPECT) correlate with the severity of transthyretin amyloid cardiomyopathy (ATTR-CM). However, the optimal metrics and image acquisition timing required to quantify the disease burden remain uncertain.Methods and resultsWe retrospectively evaluated 99mTc-PYP SPECT/CT images of 23 patients diagnosed with ATTR-CM using endomyocardial biopsies and/or gene tests. All patients were assessed by SPECT/CT 1 hour after 99mTc-PYP injection, and 13 of them were also assessed at 3 hours. We quantified 99mTc-PYP uptake using the volumetric parameters, cardiac PYP volume (CPV) and cardiac PYP activity (CPA). We also calculated the SUVmax ratios of myocardial SUVmax/blood pool SUVmax, myocardial SUVmax/bone SUVmax, and the SUVmax retention index. We assessed the correlations between uptake parameters and the four functional parameters associated with prognosis, namely left ventricular ejection fraction, global longitudinal strain, myocardial extracellular volume, and troponin T. CPV and CPA correlated more closely than the SUVmax ratios with the four prognostic factors. Significant correlations between volumetric parameters and prognostic factors were equivalent between 1 and 3 hours.ConclusionsThe disease burden of ATTR-CM was quantified more accurately by volumetric evaluation of 99mTc-PYP SPECT/CT than SUVmax ratios and the performance was equivalent between 1 and 3 hours.

PLAHS: A Partial Labelling Autonomous Hyper-heuristic System for Industry 4.0 with application on classification of cold stamping process

In real-life industry it is difficult to have fully-labelled datasets due to lack of time, resources or knowledge. In this sense, this paper proposes the design and development of a Partial Labelling Autonomous Hyper-heuristic System PLAHS, a solution that autonomously labels partially labelled databases and evaluates the yielded labelling solution by means of a novel Trustworthiness Metric (TM). The proposal combines a hyper-heuristic inspired approach with a Semi Supervised Learning Clustering (SSLC) methodology that optimizes the parameters of different clustering algorithms, based on a novel semi-supervised metric named Partially Supervised Optimization Metric (PSOM). The proposal has been tested with promising and excellent results on both a real use case for labelling work orders in a cold stamping press, and 13 databases from the UCI (multivariate data) and UCR (time series data) repositories.

One-shot models for local core network placement and traffic optimization in self deployable networks

In recent years, we have witnessed a proliferation of core network (CN) virtualization, coupled with the emergence of self deployable architectures in cellular networks. These advances provide greater flexibility and allow CN functions to be virtualized and co-located with one or more base stations. However, they introduce new challenges, such as the optimal location of CN functions based on the physical architecture. In this paper, we tackle this problem and propose a new generic and efficient solution that locates the best base station to host the CN functions, while optimizing a given performance metric (e.g., maximum flow, max–min fairness, etc.) The core of our solution relies on jointly modeling the problem as a Mixed-Integer Nonlinear Programming (MINLP) and efficiently linearizing the nonlinear constraints. After presenting our model, we evaluate its performances, considering the global maximum flow as an optimization metric. The results showed that our joint modeling significantly reduces the run time compared to existing solutions while achieving the same optimal results. Furthermore, we highlight the genericity of our model, and we show how it can be easily adapted to handle different optimization metrics. We particularly consider some variants to address the fairness problem in conjunction with the local CN placement issue. We perform extensive simulations and discuss the obtained results. The latter allow us to derive insights regarding the tradeoff between maximum flow and fairness of proportional satisfaction, while highlighting the strengths of the proposed joint modeling.

Does choice of outdoor heat metric affect heat-related epidemiologic analyses in the US Medicare population?

We calculated daily maximum, minimum, and mean outdoor air temperature (T), heat index (HI), wet-bulb globe temperature (WBGT), and Universal Thermal Climate Index (UTCI) for populous US counties and linked estimates with daily all-cause mortality and heat-related hospitalizations among Medicare beneficiaries (2006-2016). We fit distributed-lag nonlinear models for each metric and compared relative risks (RRs) at the 99th percentile. Across all heat metrics, extreme heat was statistically significantly associated with elevated risks of morbidity and mortality. Associations were more pronounced for maximum daily values versus the corresponding minimum for the same metric. The starkest example was between HImax (RR = 1.14; 95% confidence interval [CI] = 1.12, 1.15) and HImin (RR = 1.10; 95% CI = 1.09, 1.11) for hospitalizations. When comparing RRs across heat metrics, we found no statistically significant differences within the minimum and maximum heat values (i.e., no significant differences between Tmax/HImax/WBGTmax/UTCImax or between Tmin/HImin/WBGTmin/UTCImin). We found similar relationships across the National Climate Assessment regions. Among Medicare beneficiaries in populous US counties, daily maximum and mean values of outdoor heat are associated with greater RRs of heat-related morbidity and all-cause mortality versus minimum values of the same metric. The choice of heat metric (e.g., temperature versus HI) does not appear to substantively affect risk calculations in this population.

A Tutorial on Agricultural IoT: Fundamental Concepts, Architectures, Routing, and Optimization

This paper presents an in-depth contextualized tutorial on Agricultural IoT (Agri-IoT), covering the fundamental concepts, assessment of routing architectures and protocols, and performance optimization techniques via a systematic survey and synthesis of the related literature. The negative impacts of climate change and the increasing global population on food security and unemployment threats have motivated the adoption of the wireless sensor network (WSN)-based Agri-IoT as an indispensable underlying technology in precision agriculture and greenhouses to improve food production capacities and quality. However, most related Agri-IoT testbed solutions have failed to achieve their performance expectations due to the lack of an in-depth and contextualized reference tutorial that provides a holistic overview of communication technologies, routing architectures, and performance optimization modalities based on users’ expectations. Thus, although IoT applications are founded on a common idea, each use case (e.g., Agri-IoT) varies based on the specific performance and user expectations as well as technological, architectural, and deployment requirements. Likewise, the agricultural setting is a unique and hostile area where conventional IoT technologies do not apply, hence the need for this tutorial. Consequently, this tutorial addresses these via the following contributions: (1) a systematic overview of the fundamental concepts, technologies, and architectural standards of WSN-based Agri-IoT, (2) an evaluation of the technical design requirements of a robust, location-independent, and affordable Agri-IoT, (3) a comprehensive survey of the benchmarking fault-tolerance techniques, communication standards, routing and medium access control (MAC) protocols, and WSN-based Agri-IoT testbed solutions, and (4) an in-depth case study on how to design a self-healing, energy-efficient, affordable, adaptive, stable, autonomous, and cluster-based WSN-specific Agri-IoT from a proposed taxonomy of multi-objective optimization (MOO) metrics that can guarantee an optimized network performance. Furthermore, this tutorial established new taxonomies of faults, architectural layers, and MOO metrics for cluster-based Agri-IoT (CA-IoT) networks and a three-tier objective framework with remedial measures for designing an efficient associated supervisory protocol for cluster-based Agri-IoT networks.

Optimizing Exoskeleton Design with Evolutionary Computation: An Intensive Survey

Exoskeleton devices are designed for applications such as rehabilitation, assistance, and haptics. Due to the nature of physical human–machine interaction, designing and operating these devices is quite challenging. Optimization methods lessen the severity of these challenges and help designers develop the device they need. In this paper, we present an extensive and systematic literature search on the optimization methods used for the mechanical design of exoskeletons. We completed the search in the IEEE, ACM, and MDPI databases between 2017 and 2023 using the keywords “exoskeleton”, “design”, and “optimization”. We categorized our findings in terms of which limb (i.e., hand, wrist, arm, or leg) and application (assistive, rehabilitation, or haptic) the exoskeleton was designed for, the optimization metrics (force transmission, workspace, size, and adjustability/calibration), and the optimization method (categorized as evolutionary computation or non-evolutionary computation methods). We discuss our observations with respect to how the optimization methods have been implemented based on our findings. We conclude our paper with suggestions for future research.

Optimal heat stress metric for modelling heat-related mortality varies from country to country.

Combined heat and humidity is frequently described as the main driver of human heat-related mortality, more so than dry-bulb temperature alone. While based on physiological thinking, this assumption has not been robustly supported by epidemiological evidence. By performing the first systematic comparison of eight heat stress metrics (i.e., temperature combined with humidity and other climate variables) with warm-season mortality, in 604 locations over 39 countries, we find that the optimal metric for modelling mortality varies from country to country. Temperature metrics with no or little humidity modification associates best with mortality in ~40% of the studied countries. Apparent temperature (combined temperature, humidity and wind speed) dominates in another 40% of countries. There is no obvious climate grouping in these results. We recommend, where possible, that researchers use the optimal metric for each country. However, dry-bulb temperature performs similarly to humidity-based heat stress metrics in estimating heat-related mortality in present-day climate.

Seventeen criteria for evaluating Jacobian-based optimization metrics

Seventeen criteria for evaluating Jacobian-based optimization metrics

Quantum adversarial metric learning model based on triplet loss function

Metric learning plays an essential role in image analysis and classification, and it has attracted more and more attention. In this paper, we propose a quantum adversarial metric learning (QAML) model based on the triplet loss function, where samples are embedded into the high-dimensional Hilbert space and the optimal metric is obtained by minimizing the triplet loss function. The QAML model employs entanglement and interference to build superposition states for triplet samples so that only one parameterized quantum circuit is needed to calculate sample distances, which reduces the demand for quantum resources. Considering the QAML model is fragile to adversarial attacks, an adversarial sample generation strategy is designed based on the quantum gradient ascent method, effectively improving the robustness against the functional adversarial attack. Simulation results show that the QAML model can effectively distinguish samples of MNIST and Iris datasets and has higher ϵ-robustness accuracy over the general quantum metric learning. The QAML model is a fundamental research problem of machine learning. As a subroutine of classification and clustering tasks, the QAML model opens an avenue for exploring quantum advantages in machine learning.

HV geometry for signal comparison

In order to compare and interpolate signals, we investigate a Riemannian geometry on the space of signals. The metric allows discontinuous signals and measures both horizontal (thus providing many benefits of the Wasserstein metric) and vertical deformations. Moreover, it allows for signed signals, which overcomes the main deficiency of optimal transportation-based metrics in signal processing. We characterize the metric properties of the space of signals and establish the regularity and stability of geodesics. Furthermore, we introduce an efficient numerical scheme to compute the geodesics and present several experiments which highlight the nature of the metric.

An Efficient Multi-Class Privacy-Preserving-Based Encryption Framework for Large Distributed Databases

This paper introduces a novel hybrid filter-based ensemble multi-class classification model for distributed privacy-preserving applications. The conventional privacy-preserving multi-class learning models have limited capacity to enhance the true positive rate, mainly due to computational time and memory constraints, as well as the static nature of metrics for parameter optimization and multi-class perturbation processes. In this research, we develop the proposed model on large medical and market databases with the aim of enhancing multi-party data confidentiality through a security framework during the privacy-preserving process. Moreover, we also introduce a secure multi-party data perturbation process to improve computational efficiency and privacy-preserving performance. Experimental results were evaluated on different real-time privacy-preserving datasets, such as medical and market datasets, using different statistical metrics. The evaluation results demonstrate that the proposed multi-party-based multi-class privacy-preserving model performs statistically better than conventional approaches.

Deep-discovery: Anomaly discovery in software-defined networks using artificial neural networks

This paper proposes Deep-Discovery, an Intrusion Detection System (IDS), to perform Anomaly Discovery in Software-Defined Networking (SDN) using Artificial Neural Network (ANN). The proposed IDS framework utilizes the Multi-Layer Perceptron (MLP), a Feedforward (FF) ANN, to detect volume-based and protocol-based Distributed Denial of Service (DDoS) attacks on the data plane of SDN. The proposed model considers the attack detection a multi-class classification problem and classifies the network traffic into six attack classes with an accuracy of 98.81% and a minimal False Alarm Rate (FAR) of 0.002. The proposed classification model addresses the binary classification problem to compare and analyze the classification performance metrics. The Deep-Discovery that deals with the binary classification problem categorizes the network traffic into anomalous and normal traffic with 99.79% accuracy and a nominal FAR of 0.0001. The novelty of this work is its emphasis on obtaining the optimal performance metrics with a simple neural network with minimal computational overhead rather than an intricate and complex model.