A significant exploration on meta-heuristic based approaches for optimization in the waste management route problems.

In metropolitan cities, it is very complicated to govern the optimum routes for garbage collection vehicles due to high waste production and very dense population. Furthermore, wrongly designed routes are the source of wasting time, fuel and other resources in the collection of municipal trash procedure. The Vehicle Routing Problem (VRP) published between 2011 and 2023 was systematically analysed. The majority of the surveyed research compute the waste collecting problems using metaheuristic approaches. This manuscript serves two purposes: first, categorising the VRP and its variants in the field of waste collection; second, examining the role played by most of the metaheuristics in the solution of the VRP problems for a waste collection. Three case study of Asia continent has been analysed and the results show that the metaheuristic algorithms have the capability in providing good results for large-scale data. Lastly, some promising paths ranging from highlighting research gap to future scope are drawn to encourage researchers to conduct their research work in the field of waste management route problems.

Emotion recognition for human-computer interaction using high-level descriptors.

Recent research has focused extensively on employing Deep Learning (DL) techniques, particularly Convolutional Neural Networks (CNN), for Speech Emotion Recognition (SER). This study addresses the burgeoning interest in leveraging DL for SER, specifically focusing on Punjabi language speakers. The paper presents a novel approach to constructing and preprocessing a labeled speech corpus using diverse social media sources. By utilizing spectrograms as the primary feature representation, the proposed algorithm effectively learns discriminative patterns for emotion recognition. The method is evaluated on a custom dataset derived from various Punjabi media sources, including films and web series. Results demonstrate that the proposed approach achieves an accuracy of 69%, surpassing traditional methods like decision trees, Naïve Bayes, and random forests, which achieved accuracies of 49%, 52%, and 61% respectively. Thus, the proposed method improves accuracy in recognizing emotions from Punjabi speech signals.

Unified deep learning models for enhanced lung cancer prediction with ResNet-50-101 and EfficientNet-B3 using DICOM images.

Significant advancements in machine learning algorithms have the potential to aid in the early detection and prevention of cancer, a devastating disease. However, traditional research methods face obstacles, and the amount of cancer-related information is rapidly expanding. The authors have developed a helpful support system using three distinct deep-learning models, ResNet-50, EfficientNet-B3, and ResNet-101, along with transfer learning, to predict lung cancer, thereby contributing to health and reducing the mortality rate associated with this condition. This offer aims to address the issue effectively. Using a dataset of 1,000 DICOM lung cancer images from the LIDC-IDRI repository, each image is classified into four different categories. Although deep learning is still making progress in its ability to analyze and understand cancer data, this research marks a significant step forward in the fight against cancer, promoting better health outcomes and potentially lowering the mortality rate. The Fusion Model, like all other models, achieved 100% precision in classifying Squamous Cells. The Fusion Model and ResNet-50 achieved a precision of 90%, closely followed by EfficientNet-B3 and ResNet-101 with slightly lower precision. To prevent overfitting and improve data collection and planning, the authors implemented a data extension strategy. The relationship between acquiring knowledge and reaching specific scores was also connected to advancing and addressing the issue of imprecise accuracy, ultimately contributing to advancements in health and a reduction in the mortality rate associated with lung cancer.

COVID-19 detection in lung CT slices using Brownian-butterfly-algorithm optimized lightweight deep features.

Several deep-learning assisted disease assessment schemes (DAS) have been proposed to enhance accurate detection of COVID-19, a critical medical emergency, through the analysis of clinical data. Lung imaging, particularly from CT scans, plays a pivotal role in identifying and assessing the severity of COVID-19 infections. Existing automated methods leveraging deep learning contribute significantly to reducing the diagnostic burden associated with this process. This research aims in developing a simple DAS for COVID-19 detection using the pre-trained lightweight deep learning methods (LDMs) applied to lung CT slices. The use of LDMs contributes to a less complex yet highly accurate detection system. The key stages of the developed DAS include image collection and initial processing using Shannon's thresholding, deep-feature mining supported by LDMs, feature optimization utilizing the Brownian Butterfly Algorithm (BBA), and binary classification through three-fold cross-validation. The performance evaluation of the proposed scheme involves assessing individual, fused, and ensemble features. The investigation reveals that the developed DAS achieves a detection accuracy of 93.80% with individual features, 96% accuracy with fused features, and an impressive 99.10% accuracy with ensemble features. These outcomes affirm the effectiveness of the proposed scheme in significantly enhancing COVID-19 detection accuracy in the chosen lung CT database.

Design and simulation of 4 kW solar power-based hybrid EV charging station.

Electric vehicles (EVs) have become an attractive alternative to IC engine cars due to the increased interest in lowering the consumption of fossil fuels and pollution. This paper presents the design and simulation of a 4 kW solar power-based hybrid EV charging station. With the increasing demand for electric vehicles and the strain they pose on the electrical grid, particularly at fast and superfast charging stations, the development of sustainable and efficient charging infrastructure is crucial. The proposed hybrid charging station integrates solar power and battery energy storage to provide uninterrupted power for EVs, reducing reliance on fossil fuels and minimizing grid overload. The system operates using a three-stage charging strategy, with the PV array, battery bank, and grid electricity ensuring continuous power supply for EVs. Additionally, the system can export surplus solar energy to the grid, reducing the load demand. The paper also discusses the use of MPPT techniques, PV cell modeling, and charge controller algorithms to optimize the performance of the hybrid charging station.

Design of modified reference phase modulation based boost chopper fed fifteen level stepped DC link hybrid converter.

A new fifteen-level stepped DC to AC hybrid converter is proposed for Solar Photovoltaic (SPV) applications. A boost chopper circuit is designed and interfaced with the fifteen-level hybrid converters specific to Electric Vehicles' Brushless DC Motor (BLDC) drive systems. In chopper units, the output of solar panels is regulated and stepped up to obtain the nominal output voltage. In the stepped DC-link hybrid converter configuration, fifteen-level DC-link voltage is achieved by the series-operated DC-link modules with reduced electrical energy compression. From the comprehensive structure, it is anecdotal that the proposed topology has achieved minimum switching and power loss. Elimination of end passive components highlights the merits of the proposed hybrid systems. The reduction of controlled power semiconductor switches and gate-firing circuits has made the system more reliable than other hybrid converters. From the extensive analysis, the experimental setup has reported that 7% reduction in harmonics and a 54% reduction in controlled power switches than the existing fifteen-level converter topologies. Mitigation of power quality issues in the voltage profile of a fifteen-level multilevel hybrid converter is achieved through the implementation of dsPIC digital-controller-based gate triggering circuits.

Explainable deep-neural-network supported scheme for tuberculosis detection from chest radiographs.

Chest radiographs are examined in typical clinical settings by competent physicians for tuberculosis diagnosis. However, this procedure is time consuming and subjective. Due to the growing usage of machine learning techniques in applied sciences, researchers have begun applying comparable concepts to medical diagnostics, such as tuberculosis screening. In the period of extremely deep neural nets which comprised of hundreds of convolution layers for feature extraction, we create a shallow-CNN for screening of TB condition from Chest X-rays so that the model is able to offer appropriate interpretation for right diagnosis. The suggested model consists of four convolution-maxpooling layers with various hyperparameters that were optimized for optimal performance using a Bayesian optimization technique. The model was reported with a peak classification accuracy, F1-score, sensitivity and specificity of 0.95. In addition, the receiver operating characteristic (ROC) curve for the proposed shallow-CNN showed a peak area under the curve value of 0.976. Moreover, we have employed class activation maps (CAM) and Local Interpretable Model-agnostic Explanations (LIME), explainer systems for assessing the transparency and explainability of the model in comparison to a state-of-the-art pre-trained neural net such as the DenseNet.

A self-adaptive attraction and repulsion-based naked mole-rat algorithm for energy-efficient mobile wireless sensor networks.

Naked mole-rat algorithm (NMRA) is a swarm intelligence-based algorithm that draws inspiration from the mating behaviour of mole rats (workers and breeders). This approach, which is based on the ability of breeders to reproduce with the queen, has been utilized to tackle optimization problems. The algorithm, however, suffers from local optima stagnation problem and a slower rate of convergence in order to provide gobal optimal solution. This study suggests attraction and repulsion strategy based NMRA (ARNMRA) along with self-adaptive properties to avoid trapping of solution in local optima. This strategy is utilized to create new breeder rat solutions and mating factor [Formula: see text] is made self-adaptive using simulated annealing (sa) based mutation operator. ARNMRA is evaluated on CEC 2005 numerical benchmark problems and found to be superior to other algorithms, including well-known ones like selective operation based GWO (SOGWO), opposition based laplacian equilibrium optimizer (OB-L-EO), improved whale optimization algorithm (IWOA), success-history based adaptive DE (SHADE) and original NMRA. Further, according to experimental results, the performance of ARNMRA is likewise superior to the NMRA for the CEC 2019 and CEC 2020 numerical problems. Convergence profiles and statistical tests (rank-sum test and Friedman test) are employed further to validate the experimental results. Moreover, this article extends the application of ARNMRA to address the data gathering aspect in mobile wireless sensor networks (MWSNs) with the goal of prolonging network lifetime and enhancing energy efficiency. In this MWSN-based protocol, a sensor node is elected as a cluster head based on factors like mobility, residual energy, and connection time. The protocol aims to maximize the system lifetime by efficiently collecting data from all sensors and transmitting it to the base station. The study emphasizes the significance of considering dynamic node densities and speed when designing effective data-gathering protocols for MWSNs.

Estimating PM2.5 utilizing multiple linear regression and ANN techniques.

The accurate prediction of air pollutants, particularly Particulate Matter (PM), is critical to support effective and persuasive air quality management. Numerous variables influence the prediction of PM, and it's crucial to combine the most relevant input variables to ensure the most dependable predictions. This study aims to address this issue by utilizing correlation coefficients to select the most pertinent input and output variables for an air pollution model. In this work, PM2.5 concentration is estimated by employing concentrations of sulfur dioxide, nitrogen dioxide, and PM10 found in the air through the application of Artificial Neural Networks (ANNs). The proposed approach involves the comparison of three ANN models: one trained with the Levenberg-Marquardt algorithm (LM-ANN), another with the Bayesian Regularization algorithm (BR-ANN), and a third with the Scaled Conjugate Gradient algorithm (SCG-ANN). The findings revealed that the LM-ANN model outperforms the other two models and even surpasses the Multiple Linear Regression method. The LM-ANN model yields a higher R2 value of 0.8164 and a lower RMSE value of 9.5223.

Chemistry and Therapeutic Aspect of Triazole: Insight into the Structure-activity Relationship.

The triazole ring is a highly significant heterocycle that occurs naturally in many commodities and is a common feature in pharmaceuticals. Recently, heterocyclic compounds and their derivatives have been getting a lot of attention in medicinal chemistry because they have a lot of pharmacological and biological potential. For example, a lot of drugs have nitrogen-containing heterocyclic moieties. The triazole ring is often used as a bio-isostere of the oxadiazole nucleus. The oxygen atom in the oxadiazole nucleus is replaced by nitrogen in the triazole analogue. This article explores the pharmacological properties of the triazole moiety, including but not limited to antibacterial, analgesic, anticonvulsant, anthelmintic, anti-inflammatory, antitubercular, antimalarial, antioxidant, antiviral, and other properties. Additionally, we discuss the diverse multi- target pharmacological activities exhibited by triazole-based compounds. Based on a literature review, it is evident that triazole-based chemicals hold significant potential for various applications.

End fire linear antenna array synthesis using differential evolution inspired Adaptive Naked Mole Rat Algorithm.

Linear antenna arrays (LAAs) play a critical role in smart system communication applications such as the Internet of Things (IoT), mobile communication and beamforming. However, minimizing secondary lobes while maintaining a low beamwidth remains challenging. This study presents an enhanced synthesis methodology for LAAs using the Adaptive Naked Mole Rat Algorithm (ANMRA). ANMRA, inspired by mole-rat mating habits, improves exploration and exploitation capabilities for directive LAA applications. The performance of ANMRA is assessed using the CEC 2019 benchmark test functions, a widely adopted standard for statistical evaluation in optimization algorithms. The proposed methodology results are also benchmarked against state-of-the-art algorithms, including the Salp Swarm Algorithm (SSA), Cuckoo Search (CS), Artificial Hummingbird Algorithm (AHOA), Chimp Optimization Algorithm (ChOA), and Naked Mole Rat Algorithm (NMRA). The results demonstrate that ANMRA achieves superior performance among the benchmarked algorithms by successfully minimizing secondary lobes and obtaining a narrow beamwidth. The ANMRA controlled design achieves the lowest Side Lobe Level (SLL) of - 37.08 dB and the smallest beamwidth of 74.68°. The statistical assessment using the benchmark test functions further confirms the effectiveness of ANMRA. By optimizing antenna element magnitude and placement control, ANMRA enables precise primary lobe placement, grating lobe elimination, and high directivity in LAAs. This research contributes to advancing smart system communication technologies, particularly in the context of IoT and beamforming applications, by providing an enhanced synthesis methodology for LAAs that offers improved performance in terms of secondary lobe reduction and beamwidth optimization.

Improving the segmentation of digital images by using a modified Otsu's between-class variance.

Image segmentation is a critical stage in the analysis and pre-processing of images. It comprises dividing the pixels according to threshold values into several segments depending on their intensity levels. Selecting the best threshold values is the most challenging task in segmentation. Because of their simplicity, resilience, reduced convergence time, and accuracy, standard multi-level thresholding (MT) approaches are more effective than bi-level thresholding methods. With increasing thresholds, computer complexity grows exponentially. A considerable number of metaheuristics were used to optimize these problems. One of the best image segmentation methods is Otsu's between-class variance. It maximizes the between-class variance to determine image threshold values. In this manuscript, a new modified Otsu function is proposed that hybridizes the concept of Otsu's between class variance and Kapur's entropy. For Kapur's entropy, a threshold value of an image is selected by maximizing the entropy of the object and background pixels. The proposed modified Otsu technique combines the ability to find an optimal threshold that maximizes the overall entropy from Kapur's and the maximum variance value of the different classes from Otsu. The novelty of the proposal is the merging of two methodologies. Clearly, Otsu's variance could be improved since the entropy (Kapur) is a method used to verify the uncertainty of a set of information. This paper applies the proposed technique over a set of images with diverse histograms, which are taken from Berkeley Segmentation Data Set 500 (BSDS500). For the search capability of the segmentation methodology, the Arithmetic Optimization algorithm (AOA), the Hybrid Dragonfly algorithm, and Firefly Algorithm (HDAFA) are employed. The proposed approach is compared with the existing state-of-art objective function of Otsu and Kapur. Qualitative experimental outcomes demonstrate that modified Otsu is highly efficient in terms of performance metrics such as PSNR, mean, threshold values, number of iterations taken to converge, and image segmentation quality.

Multi-exposure microscopic image fusion-based detail enhancement algorithm.

Traditional microscope imaging techniques are unable to retrieve the complete dynamic range of a diatom species with complex silica-based cell walls and multi-scale patterns. In order to extract details from the diatom, multi-exposure images are captured at variable exposure settings using microscopy techniques. A recent innovation shows that image fusion overcomes the limitations of standard digital cameras to capture details from high dynamic range scene or specimen photographed using microscopy imaging techniques. In this paper, we present a cell-region sensitive exposure fusion (CS-EF) approach to produce well-exposed fused images that can be presented directly on conventional display devices. The ambition is to preserve details in poorly and brightly illuminated regions of 3-D transparent diatom shells. The aforesaid objective is achieved by taking into account local information measures, which select well-exposed regions across input exposures. In addition, a modified histogram equalization is introduced to improve uniformity of input multi-exposure image prior to fusion. Quantitative and qualitative assessment of proposed fusion results reveal better performance than several state-of-the-art algorithms that substantiate the method's validity.

An Efficient Adaptive Salp Swarm Algorithm Using Type II Fuzzy Entropy for Multilevel Thresholding Image Segmentation.

Salp swarm algorithm (SSA) is an innovative contribution to smart swarm algorithms and has shown its utility in a wide range of research domains. While it is an efficient algorithm, it is noted that SSA suffers from several issues, including weak exploitation, convergence, and unstable exploitation and exploration. To overcome these, an improved SSA called as adaptive salp swarm algorithm (ASSA) was proposed. Thresholding is among the most effective image segmentation methods in which the objective function is described in relation of threshold values and their position in the histogram. Only if one threshold is assumed, a segmented image of two groups is obtained. But on other side, several groups in the output image are generated with multilevel thresholds. The methods proposed by authors previously were traditional measures to identify objective functions. However, the basic challenge with thresholding methods is defining the threshold numbers that the individual must choose. In this paper, ASSA, along with type II fuzzy entropy, is proposed. The technique presented is examined in context with multilevel image thresholding, specifically with ASSA. For this reason, the proposed method is tested using various images simultaneously with histograms. For evaluating the performance efficiency of the proposed method, the results are compared, and robustness is tested with the efficiency of the proposed method to multilevel segmentation of image; numerous images are utilized arbitrarily from datasets.

Predictive modeling of surface and dimensional features of vapour-smoothened FDM parts using self-adaptive cuckoo search algorithm.

Despite numerous advantages of fused deposition modeling (FDM), the inherent layer-by-layer deposition behavior leads to considerable surface roughness and dimensional variability, limiting its usability for critical applications. This study has been conducted to select optimum parameters of FDM and vapour smoothing (chemical finishing) process to maximize surface finish, hardness, and dimensional accuracy. A self-adaptive cuckoo search algorithm for predictive modelling of surface and dimensional features of vapour-smoothened FDM-printed functional prototypes has been demonstrated. The chemical finishing has been performed on hip prosthesis (benchmark) using hot vapours of acetone (using dedicated experimental set-up). Based upon the selected design of experiment technique, 18 sets of experiments (with three repetitions) were performed by varying six parameters. Afterwards, a self-adaptive cuckoo search algorithm was implemented by formulating five objective functions using regression analysis to select optimum parameters. An excellent functional relationship between output and input parameters has been developed using a self-adaptive cuckoo search algorithm which has successfully found the solution to optimization issues related to different responses. The confirmatory experiments indicated a strong correlation between predicted and actual surface finish measurements, along with hardness and dimensional accuracy.

Optimization of FFF Process Parameters by Naked Mole-Rat Algorithms with Enhanced Exploration and Exploitation Capabilities.

Fused filament fabrication (FFF) has numerous process parameters that influence the mechanical strength of parts. Hence, many optimization studies are performed using conventional tools and algorithms. Although studies have also been performed using advanced algorithms, limited research has been reported in which variants of the naked mole-rat algorithm (NMRA) are implemented for solving the optimization issues of manufacturing processes. This study was performed to scrutinize optimum parameters and their levels to attain maximum impact strength, flexural strength and tensile strength based on five different FFF process parameters. The algorithm yielded better results than other studies and successfully achieved a maximum response, which may be helpful to enhance the mechanical strength of FFF parts. The study opens a plethora of research prospects for implementing NMRA in manufacturing. Moreover, the findings may help identify critical parametric levels for the fabrication of customized products at the commercial level and help to attain the objectives of Industry 4.0.

Mechanical Strength Enhancement of 3D Printed Acrylonitrile Butadiene Styrene Polymer Components Using Neural Network Optimization Algorithm.

Fused filament fabrication (FFF), a portable, clean, low cost and flexible 3D printing technique, finds enormous applications in different sectors. The process has the ability to create ready to use tailor-made products within a few hours, and acrylonitrile butadiene styrene (ABS) is extensively employed in FFF due to high impact resistance and toughness. However, this technology has certain inherent process limitations, such as poor mechanical strength and surface finish, which can be improved by optimizing the process parameters. As the results of optimization studies primarily depend upon the efficiency of the mathematical tools, in this work, an attempt is made to investigate a novel optimization tool. This paper illustrates an optimization study of process parameters of FFF using neural network algorithm (NNA) based optimization to determine the tensile strength, flexural strength and impact strength of ABS parts. The study also compares the efficacy of NNA over conventional optimization tools. The advanced optimization successfully optimizes the process parameters of FFF and predicts maximum mechanical properties at the suggested parameter settings.

Role of Video Laryngostroboscopy in Benign Disease of Larynx.

Benign disease of larynx frequently present with voice disorder. Observing the larynx with high resolution stroboscope and its mucosal wave pattern with greater precision aids in the better understanding of normal/abnormal anatomy and function, which forms the basis of designing treatment strategies.Videolaryngostroboscopy now a days is considered routinely used method of vocal fold examination and evaluation of patients with voice disorders. This valuable imaging tool can also be used to assess the outcomes of therapy of laryngeal diseases or functional result of phonosurgical procedures. Present study, videostroboscopic assessment of 81 cases of different benign vocal cord pathologies was done. Stroboscopic parameters like glottic closure, amplitude, vocal fold edge, symmetry, periodicity and mucosal wave pattern were studied and statistically significant relationship with different vocal pathologies were obtained.

Bulk modification of polymeric microfluidic devices.

The surface properties of microfluidic devices play an important role in their flow behavior. We report here on an effective control of the surface chemistry and performance of polymeric microchips through a bulk modification route during the fabrication process. The new protocol is based on modification of the bulk microchip material by tailored copolymerization of monomers during atmospheric-pressure molding. A judicious addition of a modifier to the primary monomer solution thus imparts attractive properties to the plastic microchip substrate, including significant enhancement and/or modulation of the EOF (with flow velocities comparable to those of glass), a strong pH sensitivity and high stability. Carboxy, sulfo, and amino moieties have thus been introduced (through the incorporation of methylacrylic acid, 2-sulfoethyl-methacrylate and 2-aminoethyl-methacrylate monomers, respectively). A strong increase in the electroosmotic pumping compared to the native poly(methylmethacrylate)(PMMA) microchip (ca. electroosmotic mobility increases from 2.12 to 4.30 x 10(-4) cm(2) V(-1) s(-1)) is observed using a 6% methylacrylate (MAA) modified PMMA microchip. A 3% aminoethyl modified PMMA microchip exhibits a reversal of the electroosmotic mobility (for example, -5.6 x 10(-4) cm(2) V(-1) s(-1) at pH 3.0). The effects of the modifier loading and the pH on the EOF have been investigated for the MAA-modified PMMA chips. The bulk-modified devices exhibit reproducible and stable EOF behavior. The one step fabrication/modification protocol should further facilitate the widespread production of high-performance plastic microchip devices.