A NEW APPROACH TO INTERNET TRAFFIC CLASSIFICATION: ARTIFICIAL BEE CLONING ALGORITHM - ONLINE SEQUENTIAL ANALYTICAL MACHINE-WAVELET (OSELM- WAVELET)

Network management is challenging. To operate, maintain, and secure a communication network, network operators must grapple with low-level vendor-specific configuration to implement complex high-level network policies. Despite many previous proposals to make networks easier to manage, many solutions to network management problems amount to stop-gap solutions because of the difficulty of changing the underlying infrastructure. The rigidity of the underlying infrastructure presents few possibilities for innovation or improvement, since network devices have generally been closed, proprietary, and vertically integrated. A new paradigm in networking, software defined networking (SDN), advocates separating the data plane and the control plane, making network switches in the data plane simple packet forwarding devices and leaving a logically centralized software program to control the behavior of the entire network. SDN introduces new possibilities for network management and configuration methods. In this article, we identify problems with the current state-of-the-art network configuration and management mechanisms and introduce mechanisms to improve various aspects of network management. We focus on three problems in network management: enabling frequent changes to network conditions and state, providing support for network configuration in a highlevel language, and providing better visibility and control over tasks for performing network diagnosis and troubleshooting. The technologies we describe enable network operators to implement a wide range of network policies in a high-level policy language and easily determine sources of performance problems. In addition to the systems themselves, we describe various prototype deployments in campus and home networks that demonstrate how SDN can improve common network management tasks.

Lithological mapping is a critical aspect of geological mapping that can be useful in studying the mineralization potential of a region and has implications for mineral prospectivity mapping. This is a challenging task if performed manually, particularly in highly remote areas that require a large number of participants and resources. The combination of machine learning (ML) methods and remote sensing data can provide a quick, low-cost, and accurate approach for mapping lithological units. This study used deep learning via convolutional neural networks and conventional ML methods involving support vector machines and multilayer perceptron to map lithological units of a mineral-rich area in the southeast of Iran. Moreover, we used and compared the efficiency of three different types of multispectral remote-sensing data, including Landsat 8 operational land imager (OLI), advanced spaceborne thermal emission and reflection radiometer (ASTER), and Sentinel-2. The results show that CNNs and conventional ML methods effectively use the respective remote-sensing data in generating an accurate lithological map of the study area. However, the combination of CNNs and ASTER data provides the best performance and the highest accuracy and adaptability with field observations and laboratory analysis results so that almost all the test data are predicted correctly. The framework proposed in this study can be helpful for exploration geologists to create accurate lithological maps in other regions by using various remote-sensing data at a low cost.

In many practical engineering applications, data tend to be collected in online sequential way with imbalanced class. Many traditional machine learning methods such as support vector machine and so on generally get biased classifier which leads to lower classification precision for minor class than major class. To get fast and efficient classification, a new online sequential extreme learning machine method with two-stage hybrid strategy is proposed. In offline stage, data-based strategy is employed, and the principal curve is introduced to model the distribution of minority class data. In online stage, algorithm-based strategy is employed, and a new leave-one-out cross-validation method using Sherman-Morrison matrix inversion lemma is proposed to tackle online imbalance data, meanwhile, with add-delete mechanism for updating network weights. The proposed method is evaluated on the real-world Macau air pollutant forecasting dataset. The experimental results show that, the proposed method outperforms the classical ELM, OS-ELM and meta-cognitive OS-ELM in terms of generalization performance and numerical stability.

In large cross-sector research networks, good communication is critical to the effective management of research partnerships. In this paper we report on a communication audit conducted to identify the communication pathways and flow of information within the Sustainable Forest Management (SFM) Network, a Canadian Network of Centres of Excellence (NCE). The results indicate a range of communication challenges that can be related to an inherent problem in network management—that of orchestrating some kind of “harmony” among the different and sometimes competing voices of the multiple sectors involved. Our findings confirm the need to design and implement formal organizational communication structures to facilitate the process of creating a shared language and unified goals for the different sectors entering into partnerships in large, collaborative network organizations.

Mountain lakes are one of the critical indicators of climate change and are also responsible for glacier hazards. Mapping glacial lakes is essential for monitoring them and forecasting glacier-related hazards. Remote sensing images play a crucial role in achieving this by enabling accurate and effective mapping of glacial lakes. This review paper provides a comprehensive analysis of traditional pixel-based and object-based methods, along with machine learning and deep learning methods for glacial lake mapping, complemented by a brief summary of available datasets. Deep learning models offer superior accuracy compared to conventional pixel-based, object-based, and machine learning methods. While other natural resource mapping studies have successfully employed advanced deep learning models such as Swin Transformer, Hybrid CNN-ViT, and HRNet with novel backbone architectures, glacial lake mapping has predominantly relied on a limited number of deep learning models. Therefore, this review recommends to use these models for glacial lake mapping in the future.

Information security is a field that prevents unauthorized access, modification, destruction or transfer of existing information to third parties. Information security is categorized as virtual security, network, user, data, application, identity and security management. Information security vulnerabilities result from damage to a key element of confidentiality, integrity, and accessibility. To prevent this vulnerability from occurring, information is protected by applicable laws and possible attacks are prevented by network security protection by applying appropriate filters to Internet service providers. Computer aided studies are prevented all cyber / informatics-based attacks that damaging information security. In the literature, there are studies related to cyber security, prevention of intrusion, detection of malicious software and user password. Conventional machine learning methods and deep learning methods are used for information security. In this study, information about information security and machine learning based studies in the relevant literature are presented in detail.

Researchers have adopted model-centric artificial intelligence (AI) approaches in cheminformatics by using newer, more sophisticated AI methods to take advantage of growing chemical libraries. It has been shown that complex deep learning methods outperform conventional machine learning (ML) methods in QSAR and ligand-based virtual screening– but such approaches generally lack explanability. Hence, instead of developing more sophisticated AI methods (i.e., pursuing a model-centric approach), we wanted to explore the potential of a data-centric AI paradigm for virtual screening. A data-centric AI is an intelligent system that would automatically identify the right type of data to collect, clean and curate for later use by a predictive AI and this is required given the large volumes of chemical data that exist in chemical databases – PubChem alone has over 100 million unique compounds. However, a systematic assessment of the attributes and properties of suitable data is needed. We show here that it is not the result of deficiencies in current AI algorithms but rather, poor understanding and erroneous use of chemical data that ultimately leads to poor predictive performance. Using a new benchmark dataset of BRAF ligands that we developed, we show that our best performing predictive model can achieve an unprecedented accuracy of 99% with a conventional ML algorithm (SVM) using a merged molecular representation (Extended+ ECFP6 fingerprints), far surpassing past performances of virtual screening platforms using sophisticated deep learning methods. Thus, we demonstrate that it is not necessary to resort to the use of sophisticated deep learning algorithms for virtual screening because conventional ML can perform exceptionally well if given the right data and representation. We also show that the common use of decoys for training leads to high false positive rates and its use for testing will result in an over-optimistic estimation of a model’s predictive performance. Another common practice in virtual screening is defining compounds that are above a certain pharmacological threshold as inactives. Here, we show that the use of these so-called inactive compounds lowers a model’s sensitivity/recall. Considering that some target proteins have a limited number of known ligands, we wanted to also observe how the size and composition of the training data impact predictive performance. We found that an imbalance training dataset where inactives outnumber actives led to a decrease in recall but an increase in precision, regardless of the model or molecular representation used; and overall, we observed a decrease in the model’s accuracy. We highlight in this study some of the considerations that one needs to take into account in future development of data-centric AI for CADD.

Frailty is a geriatric syndrome that may result in poor health outcomes such as hospitalization, disability, psychological distress, and reduced life satisfaction, and it is also associated with higher healthcare costs. The aim of this study is to classify frailty in elders at an early stage (pre-frail) to lower the risk of frailty and, hence, improve the quality of life. The other two classes in the classification task are frail and robust (non-frail). To achieve this, a dataset based on gait was utilized, which was recorded by an Inertial Measurement Unit (IMU) sensor, including gyroscope and accelerometer data. In this study, two approaches were assessed: the first used advanced Deep Learning (DL) algorithms to analyze raw IMU signals, and the second used conventional Machine Learning (ML) methods with hand-crafted features. The DL model, i.e., InceptionTime, beat the other algorithms in the DL approach with a remarkable test accuracy of 98%. On the ML side, Random Forest reported the most successful ML method, which achieved a test accuracy of 63.3%. For a careful assessment of the models, other evaluation metrics like Precision, Recall, and F1-score were also evaluated. The evaluation of both approaches produces research benefits for the classification of frailty in older people and allows for the investigation of new areas, promoting deeper comprehension and well-informed decision-making, particularly in healthcare systems.

Today, prevailing phishing scams have caused serious network security problems. By adopting a domain generation algorithm, the cyber attackers are able to disguise their malware in various forms, making it easier to steal personal identity and property. This paper proposed an innovative approach to detect malicious URLs by employing a Bidirectional Long Short-Term Memory (B-LSTM) network. The paper also compares the performance of the B-LSTM network with that of conventional machine learning methods and unidirectional LSTM. The results demonstrate that the B-LSTM network has superior performance than the other machine learning methods, producing a F1 score of 95.9%.

Formal description of network behavior is the important part in network management. But some problems have not yet to be adequately addressed are the semantic and behavioral aspects of composition in this domain. Therefore a formal description method was presented to network behavior. The method includes a simple formal language, and its semantic was described by CSP. The formal language has graphical syntax with topology style. And it also has some characters that are suitable for the formal research and analysis about some problems in network management. Consequently, the method can be used to provide precise formal description and analysis about network behavior. And a reliable mathematical foundation is also provided for the correctness and validity of software system design.

This paper reports experimental results of speech emotion recognition by conventional machine learning methods and deep learning techniques. We use a selection of mel frequency cepstral coefficients (MFCCs) as features for the conventional machine learning classifiers. The convolutional neural network uses as features the mel spectrograms treated as images. We test both approaches over a state of the art free database that provides samples of 8 emotions recorded by 24 professional actors. We report and comment the accuracy achieved by each classifier in cross validation experiments. Results of our proposal are competitive with recent studies.

The overnight polysomnography shows a range of drawbacks to diagnose obstructive sleep apnea (OSA) that have led to the search for artificial intelligence-based alternatives. Many classic machine learning methods have been already evaluated for this purpose. In this chapter, we show the main approaches found in the scientific literature along with the most used data to develop the models, useful and large easily available databases, and suitable methods to assess performances. In addition, a range of results from selected studies are presented as examples of these methods. Very high diagnostic performances are reported in these results regardless of the approaches taken. This leads us to conclude that conventional machine learning methods are useful techniques to develop new OSA diagnosis simplification proposals and to act as benchmark for other more recent methods such as deep learning.

With the rapid development of information technology and the rapid popularization of the Internet, while people enjoy the convenience and efficiency brought about by new technologies, they are also suffering from the harm caused by cyber attacks. In addition to efficiently thwarting network assaults, a high volume of complicated security event data might unintentionally increase the strain of policy makers. At present, NS threats mainly include network viruses, trojans, DOS (Denial-Of-Service), etc. For the increasingly complex Network Security (NS) problems, the traditional rule-based network monitoring technology is difficult to predict the unknown attack behavior. Environment-based, dynamic and integrated data fusion can integrate data from a macro perspective. In recent years, Machine Learning (ML) technology has developed rapidly, which could easily train, test and predict existing third-party models. It uses ML algorithms to find out the association between data rather than manually sets rules. Support vector machine is a common ML method, which can predict the security of the network well after training and testing. In order to monitor the overall security status of the entire network, NS situation awareness refers to the real-time and accurate reproduction of network attacks using the reconstruction approach. Situation awareness technology is a powerful network monitoring and security technology, but there are many problems in the existing NS technology. For example, the state of the network cannot be accurately detected, and its change rule cannot be understood. In order to effectively predict network attacks, this paper adopted a technology based on ML and data analysis, and constructed a NS situational awareness model. The results showed that the detection efficiency of the model based on ML and data analysis was 7.18% higher than that of the traditional NS state awareness model.

Purpose:Machine learning (ML) has been increasingly used to quantify chemical exchange saturation transfer (CEST) effect. ML models are typically trained using either measured data or fully simulated data. However, training with measured data often lacks sufficient training data, while training with fully simulated data may introduce bias due to limited simulations pools. This study introduces a new platform that combines simulated and measured components to generate partially synthetic CEST data, and to evaluate its feasibility for training ML models to predict amide proton transfer (APT) effect.Methods:Partially synthetic CEST signals were created using an inverse summation of APT effects from simulations and the other components from measurements. Training data were generated by varying APT simulation parameters and applying scaling factors to adjust the measured components, achieving a balance between simulation flexibility and fidelity. First, tissue-mimicking CEST signals along with ground truth information were created using multiple-pool model simulations to validate this method. Second, an ML model was trained individually on partially synthetic data, in vivo data, and fully simulated data, to predict APT effect in rat brains bearing 9L tumors.Results:Experiments on tissue-mimicking data suggest that the ML method using the partially synthetic data is accurate in predicting APT. In vivo experiments suggest that our method provides more accurate and robust prediction than the training using in vivo data and fully synthetic data.Conclusion:Partially synthetic CEST data can address the challenges in conventional ML methods.

A variety of Web-based applications, mobile apps, and other over the top data services with affordable 3G/4G enabled smart devices are major factors for enormous increase in heterogeneous data traffic at enterprise and mobile networks. This creates challenges regarding traffic management and requires traffic-aware intelligent network management to deliver sustained quality of experience for subscribers. Deep packet inspection and analysis (DPIA) provides base platform for development of traffic-aware intelligent network management and security systems. However, computationally complex DPIA-related packet processing for high speed data traffic makes these systems expensive. Furthermore, conventionally these traffic-aware network management and security systems are deployed in enterprise networks with independent and dedicated DPIA-related processing resources and require multiple copies of passively provisioned high speed data from network, while performing similar DPIA operations over the same data again and again. This duplicate deployment of expensive software and hardware resources for DPIA processing eventually results in higher capital expenditures as well as operational expenditures for network operators. We have proposed a novel service-oriented framework for heterogeneous deep packet inspection and analysis (SoDPI) that simultaneously provides diversified DPIA services to multiple client applications for network management and security operations in high-speed networks. Proposed framework provides flexible and comprehensive API-based service interface for client applications to register required DPIA services. SoDPI framework implementation is based on commodity hardware and deploys shared set of DPIA-related packet processing components, requiring only single copy of passive data provisioned from network. Experimental evaluations show that novel SoDPI framework requires considerably reduced amount of software and hardware resources to fulfill heterogeneous DPIA packet processing requirements for multiple client applications in comparison with conventional network management and security applications with dedicated DPIA components. This results in lower cost impacts for network operators with more network manageability.