Elephant Herding Research Articles

Insights into artificial waterhole utilization patterns by elephants and rhinos: Lessons from a South African Nature Reserve.

Artificial water provisioning is a common practice in southern African nature reserves, where different game species exhibit preferences for specific waterhole types. The movement patterns and behaviour of elephants and rhinos are closely linked to water availability, with these mega-herbivores noticeably influencing the environment and other species they interact with at waterholes. Since there is limited research on this topic, understanding preferences for different types of artificial waterholes is crucial, particularly during periods of water scarcity. This knowledge enables reserve managers to effectively manage the numbers and types of waterholes. In this study, we investigate artificial waterhole selection and preferences by elephants and rhinos in the Olifants West Nature Reserve, South Africa. The study area featured various waterhole types, including earth dams, concrete pans, reservoirs, and troughs. By employing camera traps, we analysed visitation frequency, timing of visits, and factors influencing visit frequency. Our findings revealed distinct preferences for specific waterhole types among different social groupings of the study species. Breeding herds of elephants predominantly utilized reservoirs and occasionally visited troughs, while bachelor herds favoured earth dams. Black rhinos showed a preference for earth dams, whereas white rhinos selected troughs and earth dams, with bachelor groups favouring troughs and female rhinos favouring earth dams. The outcomes of this study have significant implications for the development of comprehensive conservation plans in areas where these species reside, and for potential release sites.

Hybrid optimization-based Effective Path Selection and Multipath routing in MANETs

Mobile Adhoc Networks (MANETs) have emerged as a popular technology because of their wide application and independent mobility. Nevertheless, communication through MANETs can be effective because of their inherent nature of high mobility, which in turn results in a higher rate of data loss and delay. Therefore, for effective communication to be achieved, the MANETs’ routing performance must be enhanced. Some extant routing protocols like AOMDV can yield moderate Routing Overhead (RO) during communication. The review of previous studies shows that there is a need for improvement in the following areas: Computational E2E delay: the proposed Genetic Algorithm- Ant Colony Optimization (GA-ACO) was unable to reduce the computational E2E delay that occurs during communication. RO: The schemes that were proposed failed to minimize the RO in the network. Energy consumption: the reduction energy consumed by the network was reduced, however, high throughput and PDR could not be achieved by the method. On the contrary, the EHO-based AOMDV routing protocol achieved low E2E delay and RO but was unable to decrease the energy consumed by the network. Throughput and PDR: The protocol proposed failed to achieve high Quality of Services (QoS). Consequently, this paper aims to provide a solution to this communication problem by proposing a Hybrid Optimization-based Effective Path Selection and Multipath routing (HOEPSM) approach for MANETs. The proposed approach, which is HOEPSM is made up of two parts: Elephant Herding Optimization (EHO)-based AOMDV routing protocol, which makes use of EHO for the identification of the shortest path from the source to the destination. The second part which is the Hybrid optimization using Genetic Ant Optimization (GAO) algorithm, involves finding the best solution through the use of a GAO-based hybrid optimization algorithm. The results of the study revealed that the use of the HOEPSM causes a significant decrease in routing RO while enhancing the network’s Quality of Forwarding (QoF) of the network. Also, the simulation of the proposed approach was carried out in NS2, and afterward, compared with earlier proposed methods like DRARP and MDRARP. Based on the simulation results, the HOEPSM outperformed the other methods, with high Energy Efficiency (EE) (91%), Packet Delivery Ratio (PDR) (95%), RO (155), and End to End (E2E delay) (102ms). These results can be attributed to the HOEPSM’s choice of the best and steady route from the source nodes and destination nodes.

Discrete Elephant Herding Optimization Algorithm for Analysis of PAPR, BER and Spectral Efficiency in FBMC/OQAM System

In wireless environments, multi-carrier modulation (MCM) schemes provides resistance against fading. These schemes have been thoroughly researched for use in 4G/5G wireless communications because of their benefits. Wireless communication systems that use multiple carriers are the most prevalent in modern technology for high-speed transmissions of data. Many researchers are currently interested in implementing new protocols and physical layers for Filter Bank Multicarrier (FBMC) with Offset Quadrature Amplitude Modulation (OQAM). 5G transmission systems are likely to utilize the FBMC/OQAM scheme. The FBMC/OQAM system has many advantages over Orthogonal Frequency Division Multiplexing (OFDM), but there are few disadvantages, one of which is its high PAPR. Because of the signal's overlapping nature in the FBMC system, conventional reduction techniques can't be applied to the subcarriers. High peak power also reduces the efficiency of FBMC/OQAM. It is essential to reduce as much as possible the peak power of a signal in communication systems. In this article, to minimize the peak-to-average power ratio (PAPR), a Discrete Elephant Herding Optimization Algorithm (DEHOA) is used. Using the proposed method, we reduce the drawback of high PAPR with lower amalgamations of optimum phase factors for each overlapping information symbol. According to simulation results, the proposed method reduces PAPR, BER and improves spectral efficiency (SE) performance.

Governance Practices in Mitigating Human-Elephant Conflicts in Dong Nai Province, Vietnam

Abstract Human-elephant conflicts (HEC) have become a significant concern due to their implications for both biodiversity conservation and human livelihoods. It has become a serious issue in Asian countries, particularly in Vietnam. This paper explores the effective governance strategies and good practices to mitigate human-elephant conflict in Dong Nai province, Vietnam. Through participatory observation, in-depth interviews, and secondary data analysis, this article aims to identify and evaluate the practices that have been employed to mitigate these conflicts. The participatory observation was conducted over ten years, from 2013 to 2023, and 28 interviews were carried out with conservation experts, local government officials and residents. As a result, the study identified the causes, solutions, and outcomes of 10 years of governance practices addressing HEC. It also found an increase in the elephant population and improvement in their health status in Dong Nai. Importantly, the study found that good governance practices have reduced conflict and improved local livelihoods. Finally, this article proposes a governance model for human-elephant conflict mitigation operated by a triangular connection between the state, the community, and conservation groups in initial strategies related to minimizing human-elephant conflict. This model aims to achieve two main goals: protecting elephant herds, increasing their population, and safeguarding agricultural production areas. These findings provide insights for policymakers, conservationists, and local communities in their efforts to achieve harmonious coexistence between humans and elephants.

SHQEHFSO: Design of an Efficient Model for Scalable and High QoS Blockchain Using Q Learning and Elephant Herd Fish Swarm Optimization

SHQEHFSO: Design of an Efficient Model for Scalable and High QoS Blockchain Using Q Learning and Elephant Herd Fish Swarm Optimization

Geospatial data for peer-to-peer communication among autonomous vehicles using optimized machine learning algorithm

The transportation infrastructure of the future will be based on autonomous vehicles. When it comes to transportation, both emerging and established nations are keen on perfecting systems based on autonomous vehicles. Transportation authorities in the United States report that driver error accounts for over 60% of all accidents each year. Almost everywhere in the world is the same. Since the idea of self-driving cars involves a fusion of hardware and software. Despite the rapid expansion of the software business and the widespread adoption of cutting-edge technologies like AI, ML, Data Science, Big Data, etc. However, the identification of natural disasters and the exchange of data between vehicles present the greatest hurdle to the development of autonomous vehicles. The suggested study primarily focused on data cleansing from the cars, allowing for seamless interaction amongst autonomous vehicles. This study's overarching goal is to look at creating a novel kind of Support Vector Machine kernel specifically for P2P networks. To meet the kernel constraints of Mercer's theorem, a newly proposed W-SVM (Weighted-SVM) kernel was produced by using an appropriately converted weight vector derived through hybrid optimization. Given the advantages of both the Grey Wolf Optimizer (GWO) and the Elephant Herding Optimisation (EHO), combining them for hybridization would be fantastic. Combining the GWO algorithm with the EHO algorithm increases its convergence speed, as well as its exploitation and exploration performances. Therefore, a new hybrid optimization approach is proposed in this study for selecting weights in SVM optimally. When compared to other machine learning methods, the suggested model is shown to be superior in its ability to handle such issues and to produce optimal solutions.

Historical Account of Managing Overabundant Wild Asian Elephants in Myanmar by the Kheddah System of Capture: Philosophy, Principles and Practices.

When standard methods of human-elephant conflict mitigation are not successful, free-ranging wild elephants may continue to come into close contact with people. This results in more frequent and severe conflict, with consequences ranging from crop raiding to loss of human and elephant lives. Understandably, in such situations, local communities may want to be rid of entire herds of elephants. Historically, one of the strategies the Myanmar Government practiced to resolve human-elephant conflict was the capture of whole herds using the Kheddah system. This involved trapping the herd in a stockade, immediately followed by on-site post-capture taming. After taming, the captured elephants were utilized as logging elephants. Elephants worked in timber extraction, retired at age 55 years and were then cared for by the Government until they died. The capture of wild elephants by the Kheddah system was formally banned in Myanmar in 1985 but occasional, small-scale, captures were allowed until 2013 under the strict control of the Myanmar Government. These operations were aimed primarily at capturing elephants involved in human-elephant conflict, rather than to supplement the working elephant population. One of the last Kheddah operations, organized and managed by the author, was conducted in 1996 at the Taikkyi township of the Yangon Region, as a last resort to end human-elephant conflict in an emergency. While chemical immobilization was being used at this time, it was not logistically possible with the high numbers of elephants engaged in the conflict. This review aims to record the history of an activity that was an important element of Myanmar's timber industry more than three decades ago. In this paper, the author presents a description of Kheddah not to endorse it, but to document (1) the Myanmar elephant population management strategy in the past, before it is forgotten, and (2) the practicality of the Kheddha operation when the singly selected commonly- used immobilization or noosing method of elephant capture is unfeasible. The author attempts to shed light on the modern veterinary procedures that may significantly reduce the notorious historical outcome of Kheddha, especially the resulting mortality of captured elephants, should the Kheddha system of capture ever be used as an emergency solution for ongoing problems of human-elephant conflict in the range states of Asia.

Elephant herding optimized features-based fast RCNN for classifying leukemia stages.

Leukemia is a cancer that develops in the bone marrow and blood that is brought on by an excessive generation of abnormal white blood cells. This disease damages deoxyribonucleic acid (DNA), which is associated with immature cells, particularly white blood cells. It is time-consuming and requires enhanced accuracy for radiologists to diagnose acute leukemia cells. To overcome this issue, we have studied the use of a novel proposed LEU-EHO NET. LEU-EHO NET has been proposed for classifying blood smear images based on leukemia-free and leukemia-infected images. Initially, the input blood smear images are pre-processed using two techniques: normalization and cropping black edges in images. The pre-processed images are then subjected to MobileNet for feature extraction. After that, Elephant Herding Optimization (EHO) is used to select the relevant feature from the retrieved characteristics. Finally, Faster RCNN is trained with the selected features to perform the classification task and discriminate between Normal and Abnormal. The total accuracy of the proposed LEU-EHO NET is 99.30%. The proposed LEU-EHO NET model enhances the overall accuracy by 0.69%, 16.21%, 1.10%, 1.71%, and 1.38% better than Inception v3 XGBoost, VGGNet, DNN, SVM and MobilenetV2 respectively. The approach needs to be improved so that overlapped cells can be segmented more accurately. Additionally, future work might improve classification accuracy by utilizing different deep learning models.

Hybrid Elephant Herding Optimization Approach for Cluster Head Selection And Secure Data Transmission In Wsn Using Hybrid Approach Cryptography Techniques

Introduction: The wireless nature of sensor networks makes safe transfer of data from one node to another a major challenge in communications. Sensing tasks connect these sensor nodes which have limitations of memories and energies. Cryptography techniques are utilised to handle critical issues of security in these networks. The performance of large-scale networks is enhanced in this case by optimisation algorithm mimicking natural behaviours.Methods: This work uses H-EHO (Hybrid Elephant Herding Optimisation technique based on Individual strategies to enhance cluster head selections in WSNs (Wireless Sensor Networks) and thus extend networks’ lifetime. WSNs complete cluster head selection processes, and proposed optimisation approach which selects cluster heads based on tracking of sensor nodes for enhancements. The clan operators of optimisation algorithms are adjusted to handle random walk scale factors of elephants. Clusters of WSNs elect updated sensor nodes in principle. Hybrid algorithm HSR19, a novel security symmetric technique offers greater security during data transfers. It offers integrity, confidentiality, and authentication for cryptographic primary keys. Results: The output of the simulation demonstrates the energy consumption, network longevity, end to end delay, and secure data transfer metrics. The results for choosing an effective and time-efficient cluster head selection process for WSNs are improved by contrasting the two approaches. Conclusion: This comparison also shows the efficiency of communication devices in terms of calculation times for encoding, decoding and energies consumed for various file sizes

Utilizing Elephant Herd-Inspired Spiking Neural Networks for Enhanced Ship Detection and Classification in Marine Scene Matching

In the realm of marine intelligence, effective ship classification across vast oceanic expanses is pivotal. Despite strides in conventional identification techniques, existing methods exhibit limitations in terms of effectiveness, robustness, and overall performance. This paper introduces a novel Elephant Herd optimization based Spiking Neural Networks (EHO-SNN) for discerning large ships, small vessels, and the absence of ships. Initial satellite images from the Airbus dataset capture ships at sea, subjected to preprocessing via the wavelet transform-based Retinex algorithm (WRA) to eliminate noise and fog artifacts. Deep learning mobile net facilitates feature extraction, while the Elephant Herd algorithm culls irrelevant features, honing in on the most pertinent ones. Finally, the classification through a spiking neural network, distinguishing between large ships, small vessels, and the absence of ships. Detected large and small ships are accurately positioned within a selected scene, while the absence of a ship terminates the process. The Proposed EHO-SNN model attains an impressive classification accuracy of 99.10%. Notably, it surpasses OMRCNN-SHD, Efficient Net, and AN-YOLOv4 by 1.15%, 12.30%, and 7.79%, respectively, thereby advancing overall accuracy in ship classification.

Performance enhancement of classifiers through Bio inspired feature selection methods for early detection of lung cancer from microarray genes

Gene expression in the microarray is assimilated with redundant and high-dimensional information. Moreover, the information in the microarray genes mostly correlates with background noise. This paper uses dimensionality reduction and feature selection methods to employ a classification methodology for high-dimensional lung cancer microarray data. The approach is enforced in two phases; initially, the genes are dimensionally reduced through Hilbert Transform, Detrend Fluctuation Analysis and Least Square Linear Regression methods. The dimensionally reduced data is further optimized in the next phase using Elephant Herd optimization (EHO) and Cuckoo Search Feature selection methods. The classifiers used here are Bayesian Linear Discriminant, Naive Bayes, Random Forest, Decision Tree, SVM (Linear), SVM (Polynomial), and SVM (RBF). The classifier's performances are analysed with and without feature selection methods. The SVM (Linear) classifier with the DFA Dimensionality Reduction method and EHO feature selection achieved the highest accuracy of 92.26 % compared to other classifiers.

Enhancing Support Vector Machine Performance: A Hybrid Approach with Davidon-Fletcher-Powell Algorithm and Elephant Herding Optimization (EHO-DFP) for Parameter Optimization

Support Vector Machines (SVMs) have gained prominence in machine learning for their capability to establish optimal decision boundaries in high-dimensional spaces. SVMs are powerful machine learning models but can encounter difficulties in achieving optimal performance due to challenges such as selecting appropriate kernel parameters, handling uncertain data, and adapting to complex decision boundaries.. This paper introduces a novel hybrid approach to enhance the performance of Support Vector Machines (SVM) through the integration of the Davidon-Fletcher-Powell (DFP) optimization algorithm and Elephant Herding Optimization (EHO) for parameter tuning. SVM, a robust machine learning algorithm, relies on effective hyperparameter selection for optimal performance. The proposed hybrid model synergistically leverages DFP's efficiency in unconstrained optimization and EHO's exploration-exploitation balance inspired by elephant herding behavior. The fusion of these algorithms address the challenges associated with traditional optimization methods. The hybrid model offers improved convergence towards the global optimum. Experimental results demonstrate the efficacy of the approach, showcasing enhanced SVM performance in terms of minimum 3.3% accuracy and 3.4% efficiency. This research contributes to advancing the field of metaheuristic optimization in machine learning, providing a promising avenue for effective parameter optimization in SVM applications.

Metaheuristic integrated machine learning classification of colon cancer using STFT LASSO and EHO feature extraction from microarray gene expressions

The microarray gene expression data poses a tremendous challenge due to their curse of dimensionality problem. The sheer volume of features far surpasses available samples, leading to overfitting and reduced classification accuracy. Thus the dimensionality of microarray gene expression data must be reduced with efficient feature extraction methods to reduce the volume of data and extract meaningful information to enhance the classification accuracy and interpretability. In this research, we discover the uniqueness of applying STFT (Short Term Fourier Transform), LASSO (Least Absolute Shrinkage and Selection Operator), and EHO (Elephant Herding Optimisation) for extracting significant features from lung cancer and reducing the dimensionality of the microarray gene expression database. The classification of lung cancer is performed using the following classifiers: Gaussian Mixture Model (GMM), Particle Swarm Optimization (PSO) with GMM, Detrended Fluctuation Analysis (DFA), Naive Bayes classifier (NBC), Firefly with GMM, Support Vector Machine with Radial Basis Kernel (SVM-RBF) and Flower Pollination Optimization (FPO) with GMM. The EHO feature extraction with the FPO-GMM classifier attained the highest accuracy in the range of 96.77, with an F1 score of 97.5, MCC of 0.92 and Kappa of 0.92. The reported results underline the significance of utilizing STFT, LASSO, and EHO for feature extraction in reducing the dimensionality of microarray gene expression data. These methodologies also help in improved and early diagnosis of lung cancer with enhanced classification accuracy and interpretability.

Proposed topology of Cognitive Elephant Herding Optimization Technique

The Cognitive Elephant Herding Optimization (CEHO) technique, a new variation of Elephant Herding Optimization (EHO) that incorporates human learning principles-based techniques, has been proposed in this study. Two novel strategies—Socially Interactive Guidance (SIG) and Self-Adaptive Parameterized Perception (SAPP)—have been developed as a result of incorporating these concepts into EHO. The SIG approach incorporates guidance-based learning as its inspiration for exploration phase. Similar to this, SAPP techniques are devoted to the exploitation phase that incorporates Self-Regulating Perception (SRP) and Generation Gap (GG) cognitive skills from people into the technique. On the CEC 2013 benchmark suits, a significant number of experimental assessments have been carried out.

Habitat Suitability Evaluation and Ecological Corridor Construction for Asian Elephants: The Case of Jiangcheng, a New Range for Elephants in Southwestern China

In recent years, the northward migration of elephant herds in China’s Yunnan Province has attracted unprecedented public attention to the conservation of Asian elephants, with habitat fragmentation and human disturbance thought to be key factors. In this study, we used Jiangcheng, a new distribution site for Asian elephants in southwest China, as an example, combined the available remote sensing and monitoring data with the MaxEnt3.4.1 model, to analyze the factors affecting the activities of Asian elephants under the conditions of human disturbance and habitat degradation. The Least Cumulative Resistance model was utilized to construct the potential ecological dispersal corridors, and the key corridors were identified through the gravity model to explore the ecological security pattern of the habitat of Asian elephants in Jiangcheng County. The results show that the habitat of Asian elephants in Jiangcheng County is fragmented, showing a north–south strip distribution, never moving to the northeast. The existing suitable habitat is located in the low-elevation area (<1500 m), which is close to water sources and roads, and there is no nature reserve in this area. The land is mainly occupied by scrub or grassland near mountainous forests, but part of it is also under cultivation, which leads to conflicts between humans and elephants occur frequently. There are 14 ecological source areas, which are mainly distributed in the two regions of Zhengdong and Kangping, and there are 92 ecological corridors, of which 3 are important corridors and 89 are general corridors. This study comprehensively analyzes the current status and connectivity of Asian elephant habitat in Jiangcheng County at the regional scale, which helps to optimize the pattern of suitable habitat, promotes the dispersal of Asian elephants and habitat connectivity, and provides realistic guidance and basic information for the conservation planning of isolated populations of this species and their habitats.

Hybrid Tasmanian Devil and Elephant Herding Model-Based Optimal Cluster Head Selection and Routing in MANET

MANETs (Mobile AdHoc Networks) have major problems due to the resource-constrained nature of mobile nodes. MANET topology is highly uncertain due to the mobility of MANET nodes that affect the stability of interconnected links. This scenario results in an increased traffic overhead which affects the routing protocol performance and results in increased energy consumption. A routing scheme designed for MANET should be able to handle energy depletion issues and nodes’ mobility. This paper designs two novel schemes to enhance energy efficiency and network lifetime by performing clustering and routing in MANET. The Hybrid Tasmanian devil and Elephant herding optimization (HTDEHO) is used for clustering the MANET nodes to minimize the overhead, enhance the stability of the network topology, and reduce collision. The HTDEHO selects the optimal cluster head (CH) from a set of nodes based on their fitness value calculated by various parameters such as mobility-based node ranking, residual energy, distance, node degree, and optimal next hop CH selection. Dwarf mongoose optimization algorithm with Fuzzy variable (FDMO) algorithm selects optimal routing cost from CH to the base station based on various parameters such as throughput, delay, and distance. The efficiency of the proposed model is evaluated with different performance metrics such as energy consumption, throughput, end-to-end delay, and packet-dropping analysis. The performance of the proposed HTDEHO-FDMO classifier is compared with different techniques such as RDOAICRP, BFOA, MARP-HO, and FEKHO-QBA. Even after 170 iterations, the HTDEHO model retains a total of 10 alive nodes.

UPQC-Based Hybrid Technique to Reduce Power Quality Problems in the Photovoltaic Grid System

In addition to Power Quality (PQ) problems caused by solid state devices in the distribution side of grid connected Photo Voltaic (PV) system, quality of power also suffers in the source side by the usage of converters. Generally, PQ problems mitigation strategy has turned into a critical issue in grid-connected PV systems. This paper proposes a control topology for PQ issues mitigation scheme in grid connected PV systems. The primary goal of this study is to enhance the PQ in power distribution system through eradicating the voltage interruption, voltage swell and sag as well as voltage fluctuation. To accomplish these changes, Unified Power Quality Conditioners (UPQCs) with controllers were utilized. Then the faults are mitigated by the utilization of UPQC with Tree Seeds Algorithm (TSA) — Adaptive Neuro-Fuzzy Interference System (ANFIS). At first, the normal properties of the grid-connected PV systems are dissected. From that point forward, a few interruptions are made in the system and the abnormal characteristics are analyzed. Then the abnormal characteristics of PQ problems are diminished in the utilization of UPQC and TSA–ANFIS controllers. UPQC is one of the best filters topologies which can mitigate and control all PQ problems. The combined algorithms of TSA-ANFIS are used to keep the dc-link voltage in UPQC at consistent level. The proposed hybrid approach is executed in MATLAB/Simulink platform and the performance is studied. Further, the proposed method is compared with existing Elephant Herding Optimization (EHO) technique and also with hybrid EHO-ANFIS techniques. The comparison results showed that the proposed technique is superior to the EHO and EHO-ANFIS techniques.

Premature Infant Cry Classification via Elephant Herding Optimized Convolutional Gated Recurrent Neural Network

Premature Infant Cry Classification via Elephant Herding Optimized Convolutional Gated Recurrent Neural Network

Fault causes and its detection in standalone PV system using ANN and GEO technique

Power generation systems using photovoltaic (PV) technology have become increasingly popular due to their high production efficiency. A partial shading defect is the most common defect in this system under the process of production, diminishing both the amount and quality of energy produced. This paper proposes an Artificial Neural Network and Golden Eagle Optimization based prediction of the fault and its detection in a standalone PV system to recover the optimum performance and diagnosis of the PV system. The proposed technique combines the Artificial Neural Network (ANN) and Golden Eagle Optimization (GEO) algorithm. The major contribution of this work is to raise PV systems' performance. The result is a defect in the classification and identification of an ANN is used. The use of GEO provides an efficient optimization technique for ANN training, which reduces the training time and improves the accuracy of the model. The proposed technique is executed on the MATLAB site and contrasted with different present techniques, like genetic algorithm (GA),Elephant Herding Optimization (EHO) and Particle Swarm Optimization (PSO). The findings displays that the proposed technique is more accurate and effective than the existing methodologies for detecting and diagnosing defects in PV systems.

Sentinel Shield: Leveraging ConvLSTM and Elephant Herd Optimization for Advanced Network Intrusion Detection

Given the escalating intricacy of network environments and the rising level of sophistication in cyber threats, there is an urgent requirement for resilient and effective network intrusion detection systems (NIDS). This document presents an innovative NIDS approach that utilizes Convolutional Long Short-Term Memory (ConvLSTM) networks and Elephant Herd Optimization (EHO) to achieve precise and timely intrusion detection. Our proposed model combines the strengths of ConvLSTM, which can effectively capture spatiotemporal dependencies in network traffic data, and EHO, which allow the model to focus on relevant information while filtering out noise. To achieve this, we first preprocess network traffic data into sequential form and use ConvLSTM layers to learn both spatial and temporal features. Subsequently, we introduce Elephant Herd Optimization that dynamically assigns different weights to different parts of the input data, emphasizing the regions most likely to contain malicious activity. To evaluate the effectiveness of our approach, we conducted extensive experiments on publicly available network intrusion CICIDS2017 Dataset. The experimental results demonstrate the efficacy of the proposed approach (Accuracy = 99.98%), underscoring its potential to revolutionize modern network intrusion detection and proactively safeguard digital assets.