Vol. 42 · No. 5

The autoscaling mechanism of cloud computing can automatically adjust computing resources according to user needs, improve quality of service (QoS) and avoid over-provision. However, the traditional autoscaling methods suffer from oscillation and degradation of QoS when dealing with burstiness. Therefore, the autoscaling algorithm should consider the effect of bursty workloads. In this paper, we propose a novel AmRP (an autoscaling method that combines reactive and proactive mechanisms) that uses proactive scaling to launch some containers in advance, and then the reactive module performs vertical scaling based on existing containers to increase resources rapidly. Our method also integrates burst detection to alleviate the oscillation of the scaling algorithm and improve the QoS. Finally, we evaluated our approach with state-of-the-art baseline scaling methods under different workloads in a Docker Swarm cluster. Compared with the baseline methods, the experimental results show that AmRP has fewer SLA violations when dealing with bursty workloads, and its resource cost is also lower.

The Open System Interconnection (OSI) model, consisting of seven layers, has become increasingly important in addressing cyber security issues. The rapid growth of network technology has led to a rise in cyber threats, with botnets taking over fixed and mobile computers. The widespread availability of mobile devices has led to increased app consumption, with 60

In the field of natural language processing (NLP), detecting emotions or sentiments can be a challenging task, and sometimes emotions can be more complex than just positive or negative. However, detecting sarcasm in textual data adds another layer of complexity. Despite this, identifying the underlying sarcasm in the text has become a recent area of interest among NLP researchers. Headlines in newspapers often use sarcasm to engage readers, but readers may have difficulty recognizing it, leading to a misinterpretation of the news and spreading misinformation. As a result, there is an urgent need for technology that can automatically identify sarcasm with high accuracy. Recent studies in this domain have revealed a need for a robust and efficient model. Deep learning approaches have proven to be effective in sarcasm detection. In this work, we propose a novel two-stage model that uses a word-embedding technique to select relevant features followed by an advanced deep-learning architecture to classify sarcasm in news headlines. Our proposed method demonstrates promising results in identifying sarcasm in text with an accuracy rate of approximately 97

In order to improve the positive effect of news communication, this paper conducts research on the detection and analysis of public opinion in the process of news communication from the perspective of big data and analyzes the guidance of news communication public opinion. Combined with the actual needs of news dissemination, the numerical accuracy, convergence order, numerical convergence and numerical stability of the SS-CSPH method are mainly analyzed and discussed according to the results of numerical simulation. Moreover, this paper confirms that the smooth function and smooth length do have an impact on the solution of the Strang split-corrected smoothed particle hydrodynamics method (SS-CSPH). In addition, this paper constructs a public opinion monitoring and guidance system in the process of news dissemination. From the simulation evaluation results, it can be seen that the method of public opinion detection and guidance in the process of news dissemination proposed in this paper can play a certain role in the monitoring and guidance of news public opinion.

In order to solve the problems of reading delay in data mining of the Internet of Things database, a clustering mining algorithm of the Internet of Things database based on Python language is proposed. We designed an improved crawler algorithm based on the open-source structure of scratch through Python language, judge the similarity of recruitment data topics in the Internet of Things database through Bayesian classifier, and crawl the recruitment data in the Internet of Things database: the number of keywords in the text space, the degree of keyword extraction, and the number of keyword data in the text space. The time series model is used to eliminate the delay of text features. On this basis, the semi-supervised learning and semi-cluster analysis method is used to construct the corresponding classifier, complete the adaptive classification process of the text data stream and realize the clustering mining of the Internet of Things database based on Python language. The experimental results show that this method has a low reading delay, and can mine the attention, number of posts and click time frequency of the Internet of Things database from which the recruitment data are obtained.

Multi-agent collaborative path planning focuses on how the agents have to coordinate their displacements in the environment to achieve different targets or to cover a specific zone in a minimum of time. Reinforcement learning is often used to control the agents' trajectories in the case of static or dynamic targets. In this paper, we propose a multi-agent collaborative path planning based on reinforcement learning and leader-follower principles. The main objectives of this work are the development of an applicable motion planning in a partially observable environment, and also, to improve the agents' cooperation level during the tasks' execution via the creation of a dynamic hierarchy in the pursuit groups. This dynamic hierarchy is reflected by the possibility of reattributing the roles of Leaders and Followers at each iteration in the case of mobile agents to decrease the task's execution time. The proposed approach is applied to the Multi-Pursuer Multi-Evader game in comparison with recently proposed path planning algorithms dealing with the same problem. The simulation results reflect how this approach improves the pursuit capturing time and the payoff acquisition during the pursuit.

Delivery Man Problem with Drone (DMPD) is a variant of Delivery Man Problem (DMP). The objective of DMP is to minimize the sum of customers' waiting times. In DMP, there is only a truck to deliver materials to customers while the delivery is completed by collaboration between truck and drone in DMPD. Using a drone is useful when a truck cannot reach some customers in particular circumstances such as narrow roads or natural disasters. For NP-hard problems, metaheuristic is a natural approach to solve medium to large-sized instances. In this paper, a metaheuristic algorithm is proposed. Initially, a solution without drone is created. Then, it is an input of split procedure to convert DMP-solution into DMPD-solution. After that, it is improved by the combination of Variable Neighborhood Search (VNS) and Tabu Search (TS). To explore a new solution space, diversification is applied. The proposed algorithm balances diversification and intensification to prevent the search from local optima. The experimental simulations show that the proposed algorithm reaches good solutions fast, even for large instances.

With the development of social networks and hardware devices, many young people have post a lot of high definition v-logs containing selfie images and videos to commemorate and share their daily lives. We found that the reflected image of corneal position in the high definition selfie image has been able to reflect the position and posture of the selfie taker. The classic localization works estimating the position and posture from a selfie are difficult because they lack the knowledge of the environment. The corneal reflection images inherently carry information about the surrounding environment, which can reveal the location, posture and even height of the selfie taker. We analyze the corneal reflection imaging process in the selfie scenario and design a validation experiment based on this process to estimate the pose of the selfie in several scenarios to further evaluate the leakage of the pose information of the selfie taker.

The term stress can designate a number of situations and affective reactions. This work focuses on the immediate stress reaction caused by, for example, threat, danger, fear, or great concern. Could measuring stress from speech be a viable fast and non-invasive method? The article describes the development of a system predicting stress from voice – from the creation of the database, and preparation of the training data to the design and tests of the regressor. StressDat, an acted database of speech under stress in Slovak, was designed. After publishing the methodology during its development in 1, this work describes the final form, annotation, and basic acoustic analyses of the data. The utterances presenting various stress-inducing scenarios were acted at three intended stress levels. The annotators used a ``stress thermometer'' to rate the perceived stress in the utterance on a scale from 0 to 100. Thus, data with a resolution suitable for training the regressor was obtained. Several regressors were trained, tested and compared. On the test-set, the stress estimation works well (R square = 0.72, Concordance Correlation Coefficient = 0.83) but practical application will require much larger volumes of specific training data. StressDat was made publicly available.

Birds are excellent bioindicators, playing a vital role in maintaining the delicate balance of ecosystems. Identifying species from bird vocalization is arduous but has high research gain. The paper focuses on the detection of multiple bird vocalizations from recordings. The proposed work uses a deep convolutional neural network (DCNN) and a recurrent neural network (RNN) architecture to learn the bird's vocalization from mel-spectrogram and mel-frequency cepstral coefficient (MFCC), respectively. We adopted a sequential aggregation strategy to make a decision on an audio file. We normalized the aggregated sigmoid probabilities and considered the nodes with the highest scores to be the target species. We evaluated the proposed methods on the Xeno-canto bird sound database, which comprises ten species. We compared the performance of our approach to that of transfer learning and Vanilla-DNN methods. Notably, the proposed DCNN and VGG-16 models achieved average F1 metrics of 0.75 and 0.65, respectively, outperforming the acoustic cue-based Vanilla-DNN approach.