ABSTRACT Bufferbloat is a significant issue in network switches, arising from excessive packet buffering that leads to increased latency and degraded network performance. This happens when switches accumulate too many packets in their buffers, which causes transmission delays and negatively affects network efficiency. To address this problem, active queue management (AQM) algorithms are employed to dynamically adjust queue sizes and prevent congestion by selectively dropping packets. However, determining the optimal buffer size is crucial, as buffers that are too small can result in packet loss and reduced throughput. The integration of software‐defined networking (SDN) technology offers a promising solution by enabling efficient network configuration and monitoring. By incorporating AQM algorithms within SDN environments, significant improvements in network performance can be achieved. This paper introduces a novel hybrid active queue management (HAQM) algorithm, which combines elements of both packet‐oriented and delay‐oriented AQM techniques within an SDN framework. The evaluation demonstrates that the HAQM algorithm effectively enhances network performance by mitigating issues related to packet loss, delay, and jitter, outperforming existing algorithms like CoDel, CoBALT, ARED, and ECN.

Abstract The problem of human identification through recognition of patterns in iris images captured in unconstrained environments results in image artefacts such as image occlusion and specular reflection, in which iris tissue is observable to extremely low content. To overcome this problem, this paper presents a novel method for iris image retrieval and recognition based on partial pattern matching. The main contribution of the proposed method relies on an image partitioning schema in which the iris is divided into non‐overlapping blocks with varying dimensions, facilitating the identification and removal of image regions impaired by eyelids, eyelashes, and specular reflections. In fact, the blocks that contain artefacts are completely ignored and those blocks are preserved that include useful patterns for identification. In addition, a multi‐feature similarity followed by a score fusion technique is employed for ranking the retrieval results. The remarkable results of the classification stage include an accuracy of 100%, 98.75%, and 99.94% on three benchmark databases, including UPOL, UBIRIS.V2, and CASIA‐Iris‐Interval.v3, respectively. Additionally, in the retrieval stage, the proposed method achieves a precision of 100% on all three benchmark databases, a recall of 83.33%, and a F1‐measure of 90.91 on the CASIA‐Iris‐Interval.v3 dataset.

Abstract Considering the increasing need for software projects, estimating software development efforts is essential and can lead to improved project delivery quality. Machine learning methods are widely used to improve the accuracy of estimation. The boosting method is an ensemble machine learning technique less used in this field. In this research, five boosting algorithms including Adaboost, Gradient boosting, XGBoost, LightGBM, and CatBoost were implemented with the hyperparameter tuning framework Optuna on the ISBSG database. The Optuna is a next‐generation optimization method for automatically tuning hyperparameters of algorithms. Six evaluation criteria MMRE, MdMRE, MAE, MSE, Pred(0.25), and SA were used to evaluate the findings. The results show that the hyperparameter automatic tuning by Optuna increases the accuracy of prediction provided by all five models. When the Catboost algorithm uses Optuna to tune its hyperparameters has made the best prediction among the five algorithms studied in this research. Using Optuna, compared to the case where the algorithm uses its default settings, the highest percentage of prediction improvement was observed in the XGBoost algorithm (except for the SA criterion). Based on the criteria of MMRE, Pred(0.25), and SA, this study has a better prediction than some relatively similar articles.

Summary Sentiment classification is a field of sentiment analysis concerned with analyzing opinions, emotions, evaluations, and attitudes regarding a special topic like a product, an organization, a person, or an incident. With the growth of user‐generated content on the Web, this field gained great importance in online reviews. With a wide range of reviews, customers cannot read all reviews. Considering the increasing rate of electronic documents and the urgent need manually mine for keywords that are hard and time‐consuming, doing the same automatically is of high demand. A new framework proposed here to mine and classify users' comments based on mining keywords by applying the sequence pattern mining through the Separation‐Power concept, a multi‐objective evolutionary algorithm based on decomposition with four objectives, and a neural network as the final classifier. Some modifications are made on multi‐objective evolutionary algorithm based on decomposition and Apriori algorithms to improve the text classification efficiency. To evaluate the proposed framework, three datasets applied; which compared with the two methods to measure accuracy, precision, recall, and error‐index. The results indicate that this framework provides a better outcome than its counterparts with 99.45 precision, 99.34 accuracy, 99.48 recall, and 99.28% f‐measure.

Outstanding features of Mobile Ad-hoc Network (MANET) including power restrictions, limited bandwidth, dynamic topology, lack of fixed infrastructure and security vulnerabilities have received interest of many researchers. This research aims to evaluate AODV protocol and its other enhanced protocols features, advantages and disadvantages. It can be seen that in which protocols comply to parameters, delay, power consumption, overhead, packet delivery ratio, throughput, packets lost, recovery time, ability to cope with life in the network and security attacks have been observed and yet which of these protocols are far away from such achievement. Upon comparing these protocols it can be showed that AOMDV protocol is so much enhanced, in next order R-AODV, PHR-AODV, I-AODV, NDMP-AODV, HDAODV and Multipath AODV were characterized with enhancement than other methods. The results showed that the proposed protocol (OBAODV) under the wormhole attack have better performance in packet delivery.