Server Logs Research Articles

Digital Forensics Analysis of IoT Nodes using Machine Learning

With the versatility and exponential growth of IoT solutions, the probability of being attacked has increased. Resource constraint IoT devices raised a challenge for the security handler to track logs of different variety of attacks generated on them while performing the forensic analysis. Commonly forensic analysis is performed on the devices that calculate how much loss has occurred to the device due to the diversity of attacks. The main objective of this paper to develop a framework through which secueity can perfrom the forensic analysis on resource contraint IoT devices. In this paper, we have proposed a framework that intelligently performs forensic analysis and detects the different types of attacks performed on the endpoint (IoT device) using a node to node (N2N) framework. Furthermore, this proposed solution is a blend of different forensic tools and Machine learning techniques to identify different types of attacks. Using a third-party log server, the problem of evidence recovery from the endpoint under attack is addressed. To determine the nature and effect of the attack we have used the logs by using the security onion (forensic server). Additionally, this framework is equipped to automatically detect attacks by using the different machine learning algorithms. The efficiency of machine learning models is measured upon the values of (1) Accuracy, (2) Precision, (3) Recall, and (4) F-Measure. The results show that the decision tree algorithm stands out with the optimum performance compared to other ML models. Overall this framework can be used for the secuirty of IoT devices as well as the evidence collection from the IoT endpoint. For the validation of the proposed framework more detailed results and performance, analysis is presented in this paper.

WEB MINING: DATA MINING ON THE INTERNET

In the article“Web Mining: Data Mining on the Web” 3 different components of Web Mining have been described and mainly Web Usage Mining has been discussed in detail and analyzed with examples. The general theme of the article is clarified by giving such sub-topics: Difficulties in analyzing data from the Internet, Stages of Web-Mining, Analysis of the use of Web resources (Web Usage Mining), Web Server Log Files and etc. General Relationships Between Web Mining Categories and Data Mining Tasks are shown. At the end, in the Conclusion, it is shown that to solve such problems, Data Mining technology is used. This name refers to a set of methods that allow us to extract useful information according to certain rules from the amount of collected data in which this information is implicitly contained. In this case, both statistical and intellectual processing methods are used. Keywords: Web-Mining, Data Mining Methods, Data from the Internet, Web Usage Mining, User Session Identification.

Towards a holistic customer value approach in managing public health care services: a developers' view

PurposeRecent literature within public service logic has called for more explicit conceptualisation of customer value in public services. This study aims to fill this gap by examining how the customer value approach can be applied in the management of public health care services.Design/methodology/approachThis study is a qualitative case study of management of public health care services in Finland. The authors interviewed 17 regional health care service developers and analyzed the interview data using thematic analysis.FindingsThe study suggests five propositions for applying customer value approach from the marketing literature in public health care service management. The study enables a deeper understanding of customer value creation in this context and improvement of public health care services.Originality/valueThis study contributes to the public management research in general and public service logic research in particular by suggesting what constitutes customer value in public health care services.

User-orientation in public service organizations: making use of value as a thick concept

ABSTRACT Value is a key concept in public service logic. However, exactly what the concept of value brings to public services, where the value of a service cannot be linked to a cost or a payment, has not received much attention. In this article, examples are shown of how value is expressed empirically by a corpus based on interviews with various stakeholders in a municipal service context. The study presents the value concept as a thick concept, and as a way of approaching user-orientation, but only if several value perspectives and timeframes are included, and if the user’s perspective (not user-perspective) is highlighted.

Libraries in the processes of distance scientific communication: the experience of V. I. Vernadsky National Library of Ukraine

The demand for electronic information resources of the V. I. Vernadsky National Library of Ukraine at the current stage is substantiated. International databases of scientific information, access to which was provided by the V. I. Vernadsky National Library of Ukraine for domestic scientists during the quarantine and martial law in Ukraine, are given. The projects of the Library, created to ensure the information needs of internally displaced persons, were considered. The advantages and disadvantages of remote work of librarians are analyzed. Special attention was paid to the replenishment of electronic resources of libraries. The important library resources of the V. I. Vernadsky National Library of Ukraine are characterized, in particular the portal "Science of Ukraine: access to knowledge", "Library portal of the National Academy of Sciences of Ukraine" and the electronic library "Ukrainika". Emphasis is placed on the value of such information services for remote users under the conditions of the COVID-19 pandemic and martial law in the state. It is emphasized that library knowledge portals play an important role in promoting scientific knowledge in Ukraine and beyond; provide extended access to them due to the use of library and information resources of scientific domestic library institutions and the latest web technologies. Attention is paid to the national DB "Ukrainika scientific", which is one of the important and significant electronic resources of the Library. Various types of remote work of library employees of individual domestic scientific libraries of Ukraine during 2020—2022 are considered. Statistical data of the WebLogExpert web server log file analysis program regarding visits to electronic resources of the V. I. Vernadsky National Library of Ukraine in recent years are presented. It has been noted that the V. I. Vernadsky National Library of Ukraine has significantly increased its online participation in international, all-Ukrainian scientific and scientific-practical conferences, scientific seminars and other scientific-organizational events. The effectiveness of remote work of library workers under the conditions of quarantine and martial law in Ukraine was determined. It was emphasized that the organization of remote work of library institutions made it possible to preserve the country's intellectual potential under today's difficult conditions.

Analysis Of the Behavior of Cyberattacks on Online Services Using the Cyber Threat Classification

The paper contains a study of the dynamics of attacks on online services using the categorization of cyber threats by type in the corporate network of the Krasnoyarsk Scientific Center of the Siberian Branch of the Russian Academy of Sciences. The study was conducted using online service logs and allows solving pressing issues related to ensuring the built-in security of web services, such as: identifying both current and future cybersecurity risks. A summary of the most important logging and analysis techniques is provided. The authors describe the nature and content of the data sources and the software used. The extensive observation period of the study is one of its outstanding features. The structure of the processing system is provided and software tools for attack analysis and categorization are created. The paper shows that using categorized sampling allows for the detection of periodicity and the identification of patterns in specific types of attacks. A correlation matrix was created based on the type of attack. Except for Command Injection, Directory Browsing, and Java Code Injection attacks, which can be aggregated, the research found that most attack types had poor correlation. Based on the classification of cyber threats, the authors proposed a heuristic technique of risk comparison.

Using deceased people’s personal data

It is important to manage individuals’ personal data after their death to maintain their dignity or follow their wishes as much as possible. From this perspective, this report describes the real-world commercialization of immortal digital personalities, which gives eternal life to the deceased in a digital form. We identify the problems with the commercialization of deceased users’ images and personal data, which becomes postmortem entertainment. Considering these problems, we seek out the ideal form of deceased users’ personal data for commercialization. We conduct a social survey to understand how ordinary Japanese people feel about the various types of publicly available services that use personal data after death, such as social network service logs. By analyzing our survey results approximately 20% of respondents would allow the commercial use of their personal data, such as browsing their social network service logs, if they could receive compensation during their lifetime.

Demand-Driven Deep Reinforcement Learning for Scalable Fog and Service Placement

The increasing number of Internet of Things (IoT) devices necessitates the need for a more substantial fog computing infrastructure to support the users’ demand for services. In this context, the placement problem consists of selecting fog resources and mapping services to these resources. This problem is particularly challenging due to the dynamic changes in both users’ demand and available fog resources. Existing solutions utilize on-demand fog formation and periodic container placement using heuristics due to the NP-hardness of the problem. Unfortunately, constant updates of services are time consuming in terms of environment setup, especially when required services and available fog nodes are changing. Therefore, due to the need for fast and proactive service updates to meet users’ demand, and the complexity of the container placement problem, we propose in this article a Deep Reinforcement Learning (DRL) solution, named Intelligent Fog and Service Placement (IFSP), to perform instantaneous placement decisions proactively. By proactively, we mean making placement decisions before demands occur. The DRL-based IFSP is developed through a scalable Markov Decision Process (MDP) design. To address the long learning time for DRL to converge, and the high volume of errors needed to explore, we also propose a novel end-to-end architecture utilizing a service scheduler and a bootstrapper. on the cloud. Our scheduler and bootstrapper perform offline learning on users’ demand recorded in server logs. Through experiments and simulations performed on the NASA server logs and Google Cluster Trace datasets, we explore the ability of IFSP to perform efficient placement and overcome the above mentioned DRL limitations. We also show the ability of IFSP to adapt to changes in the environment and improve the Quality of Service (QoS) compared to state-of-the-art-heuristic and DRL solutions.

Research on Security Anomaly Detection for Big Data Platforms Based on Quantum Optimization Clustering

Due to the explosive growth of data in the Internet, more and more applications are being deployed on Big Data platforms. However, as the scale of data continues to increase, the probability of anomalies in the platform is also increasing. However, traditional anomaly detection techniques cannot effectively handle the massive amount of historical data and can hardly meet the security requirements of big data platforms. In order to solve the above problems, this paper proposes a security anomaly detection method for big data platforms based on quantum optimization clustering. Firstly, a framework of big data platform anomaly detection system is designed based on distributed software architecture through Hadoop and Spark big data open source technology. The system achieves effective detection of network anomalies by collecting and analyzing big data platform server log data. Secondly, an offline anomaly detection algorithm based on quantum ant colony optimized affinity propagation clustering is designed for various anomalies mined from historical data. The bias parameters of the affinity propagation clustering are treated as individual ants to construct an ant colony, and the clustering accuracy is set as fitness. Finally, in order to improve the accuracy of the optimal path search of the ant colony, quantum bit encoding is applied to the ant colony position to refine the granularity of the individual ant colony position update. The experimental results show that the proposed method can effectively complete the anomaly clustering detection of massive data. With a reasonable threshold, the quantum ant colony–based affinity propagation clustering has high detection accuracy.

Web Log Analysis and Security Assessment Method Based on Data Mining.

Web content mining describes the classification, clustering, and attribute analysis of a large number of text documents and multimedia files on the web. Special tasks include retrieval of data from the Internet search engine tool W; structured processing and analysis of web data. Today's blog analysis has security concerns. We do experiments to investigate its safety. Through experiments, we draw the following conclusions: (1) Web log extraction can use efficient data mining algorithms to systematically extract logs from web servers, then determine the main access types or interests of users, and then to a certain extent, based on the discovered user patterns, analyze the user's access settings and behavior. (2) No matter in the test set or the mixed test set, the curve value of deep mining is very stable, the curve value has been kept at 0.95, and the curve value of fuzzy statistics method and quantitative statistics method is stable within the interval of 0.90-095. The results also show that the data mining method has the highest identification accuracy and the best security performance. (3) Web usage analysis requires data abstraction for pattern discovery. This data abstraction can be achieved through data preprocessing, which introduces different formats of web server log files and how web server log data is preprocessed for web usage analysis. One of the most critical parts of the web mining field is web log mining. Web log mining can use powerful data mining algorithms to systematically mine the logs in the web server and then learn the user's access or preferred interests and then conduct a certain degree of user preferences and behavior patterns according to the discovered user patterns. Based on the above analysis, the current web log analysis is faced with security problems. We conduct experiments to study to verify the security performance of web logs and draw conclusions through experiments.

Metaverse Interface with Haptic and Rigid Sense Feedback at a Low Cost

In the metaverse era, anyone should be able to easily access the metaverse for non-discrimination. This study proposes a prototype of a metaverse interface that can be implemented at a low price. It shows reasonable performance. It includes the following 4 modules. 1. Haptic feedback: Piezo sensors have been used for tactile information of various textures, which is transported as an audio data format, and reconstructed at the fingertips by an actuator (LRA motor) attached to a glove. 2. Force feedback: The module was designed to control the servomotor through 3D modeling. It provides force feedback by controlling the servo motor to grab the hand as much as the thickness of the object on Unity, the game engine. 3. Controller: Reproduce finger movement in Unity by measuring resistance change according to finger bending using a Flex sensor. Implement Yawing/Pitching/Rolling movement in Unity through MPU-6050(IMU) sensor. 4. Pose estimation: The user's current movement captured by the webcam is used for pose estimation through the Mediapipe library. It is integrated with the hand posture received serially from the controller to render the user posture inside the Unity game. The developed interface can be applied to life logging service and mirror world service, which are one of the most important applications in the metaverse.

TencentCLS

With the trend of cloud computing, the cloud log service is becoming increasingly important, as it plays a critical role in tasks such as root cause analysis, service monitoring and security audition. To meet these needs, we provide Tencent Cloud Log Service (TencentCLS), a one-stop solution for log collection, storage, analysis and dumping. It currently hosts more than a million tenants, of which the largest ones can generate up to PB-level logs per day. The most important challenge that TencentCLS faces is to support both low-latency and resource-efficient queries on such large quantities of log data. To address that challenge, we propose a novel search engine based upon Lucene. The system features a novel procedure for querying logs within a time range, an indexing technique for the time field, as well as optimized query algorithms dedicated to multiple critical and common query types. As a result, the search engine at TencentCLS gains significant performance improvements against Lucene. It achieves 20x performance increase with standard queries, and 10x performance increase with histogram queries in massive log query scenarios. In addition, TencentCLS also supports storing and querying with microsecond-level time precision, as well as the microsecond-level time order preservation capability.

Manu

With the development of learning-based embedding models, embedding vectors are widely used for analyzing and searching unstructured data. As vector collections exceed billion-scale, fully managed and horizontally scalable vector databases are necessary. In the past three years, through interaction with our 1200+ industry users, we have sketched a vision for the features that next-generation vector databases should have, which include long-term evolvability, tunable consistency, good elasticity, and high performance. We present Manu, a cloud native vector database that implements these features. It is difficult to integrate all these features if we follow traditional DBMS design rules. As most vector data applications do not require complex data models and strong data consistency, our design philosophy is to relax the data model and consistency constraints in exchange for the aforementioned features. Specifically, Manu firstly exposes the write-ahead log (WAL) and binlog as backbone services. Secondly, write components are designed as log publishers while all read-only analytic and search components are designed as independent subscribers to the log services. Finally, we utilize multi-version concurrency control (MVCC) and a delta consistency model to simplify the communication and cooperation among the system components. These designs achieve a low coupling among the system components, which is essential for elasticity and evolution. We also extensively optimize Manu for performance and usability with hardware-aware implementations and support for complex search semantics. Manu has been used for many applications, including, but not limited to, recommendation, multimedia, language, medicine and security. We evaluated Manu in three typical application scenarios to demonstrate its efficiency, elasticity, and scalability.

Enabling value-in-use with digital healthcare technologies: combining service logic and pragmatic constructivism

AbstractThe paper discusses how healthcare providers can enable value-in-use (VIU) using digital technologies in complex healthcare service contexts. Technology providers and public healthcare organizations can have difficulties understanding one another, hindering the possibilities for value-in-use to emerge. Plenty of studies have investigated the value creation in healthcare, often looking at health as value for the patient. We focus on how healthcare providers can create value for themselves to improve their operations and justify the price of new technologies while fully acknowledging the value for the patient as well. The paper uses two in-depth interventionist case studies in Nordic health care: automated screening technology for hospital laboratories and medicine dispensing robotics for home care. We use a novel combination of pragmatic constructivism (PC) and service logic (SL) as method theories to understand the value creation in our cases. Our empirical evidence provide practical examples of how digital technologies can be used to change healthcare practices and how VIU can stem from these changes. As a contribution, we show that healthcare providers can enable value-in-use with digital technologies by altering how care is carried out without hindering what the outcome of the care is for the patient. Digital technologies are there to facilitate such change, but the change still requires that actors involved in care have intention to change how they work. While healthcare bears the responsibility for these changes, technology providers can also have plenty of opportunities for interaction to support or even co-create value together with their customers.

Understanding the diversity of objectives among women forest owners in Finland

Women forest owners control a significant share of private forests in Finland, but they are often underrepresented in forest-related surveys. It also seems that women forest owners are less active in performing forestry work or selling wood; however, the information on women forest owners is sparce. The purpose of this study is to deepen understanding of the association between women forest owners’ activities and their ownership objectives. The study analysed a large survey ( n = 6468) collected as part of the Finnish Forest Owner 2020 research project. Overall, women forest owners were found to be less active in many aspects compared to their men counterparts. With k-means clustering, four different clusters of women forest owners with different ownership-objective profiles were identified. Differences in ownership activities between the clusters were compared using Pearson's chi-square test. Multi-objective women forest owners were more active than other women owners. Moreover, women forest owners who valued nature and recreation were less active than other women forest owners. This might indicate the lack of service-dominant logic in forestry-related services. By providing a more detailed understanding of women forest owners, the results aid the design of more equal and inclusive forest policies and forest services.

Public service logic and the creation of value propositions through framing

ABSTRACT This paper aims to contribute to the scholarly debate on public service logic (PSL) by deepening the understanding of how value propositions are created and altered. The PSL literature has so far suggested that value propositions are central to the value creation process, but there is scant understanding of how value propositions are created and adapted to citizens’ needs. The paper contributes by showing how the creation and alteration of value propositions takes place through framing and reframing processes, and it explores how the concept of framing can further advance PSL.

Predicting shear wave velocity from conventional well logs with deep and hybrid machine learning algorithms

Shear wave velocity (VS) data from sedimentary rock sequences is a prerequisite for implementing most mathematical models of petroleum engineering geomechanics. Extracting such data by analyzing finite reservoir rock cores is very costly and limited. The high cost of sonic dipole advanced wellbore logging service and its implementation in a few wells of a field has placed many limitations on geomechanical modeling. On the other hand, shear wave velocity VS tends to be nonlinearly related to many of its influencing variables, making empirical correlations unreliable for its prediction. Hybrid machine learning (HML) algorithms are well suited to improving predictions of such variables. Recent advances in deep learning (DL) algorithms suggest that they too should be useful for predicting VS for large gas and oil field datasets but this has yet to be verified. In this study, 6622 data records from two wells in the giant Iranian Marun oil field (MN#163 and MN#225) are used to train HML and DL algorithms. 2072 independent data records from another well (MN#179) are used to verify the VS prediction performance based on eight well-log-derived influencing variables. Input variables are standard full-set recorded parameters in conventional oil and gas well logging data available in most older wells. DL predicts VS for the supervised validation subset with a root mean squared error (RMSE) of 0.055 km/s and coefficient of determination (R2) of 0.9729. It achieves similar prediction accuracy when applied to an unseen dataset. By comparing the VS prediction performance results, it is apparent that the DL convolutional neural network model slightly outperforms the HML algorithms tested. Both DL and HLM models substantially outperform five commonly used empirical relationships for calculating VS from Vp relationships when applied to the Marun Field dataset. Concerns regarding the model's integrity and reproducibility were also addressed by evaluating it on data from another well in the field. The findings of this study can lead to the development of knowledge of production patterns and sustainability of oil reservoirs and the prevention of enormous damage related to geomechanics through a better understanding of wellbore instability and casing collapse problems.Graphical abstract

Assessment of the adverse pregnancy outcomes and its associated factors among deliveries at Debre Berhan Comprehensive Specialized Hospital, Northeast Ethiopia.

BackgroundAdverse pregnancy outcomes are the main causes of maternal and neonatal morbidity and mortality and long-term physical and psychological sequels in low- and middle-income countries, particularly in Africa and Asia. In Ethiopia, maternal mortality remained high despite the country’s maximum effort. This study aimed to assess adverse pregnancy outcomes and associated factors among deliveries at Debre Berhan Comprehensive Specialized Hospital, Northeast Ethiopia.MethodsA retrospective cross-sectional study was done among deliveries at Debre Berhan Comprehensive Specialized Hospital from January 1, 2017, to December 31, 2018. The data was collected using a structured and pre-tested questionnaire by reviewing labor and delivery service log books and admission or discharge registration books. The data were entered into a Microsoft Excel spreadsheet and analyzed using SPSS version 25. Logistic regression analysis was computed to identify independent predictors of pregnancy complications.ResultIn this study, the magnitude of adverse pregnancy outcomes was 28.3%, 95% CI (25.7–30.9). The most frequently recorded obstetric complications were obstructed labor (7.4%), retained placenta (5.3%), and hypertensive disorders of pregnancy (2.4%). Whereas stillbirths (10%), malpresentation (3%), and prematurity (2.3%) frequently occurred fetal/neonatal complications. There were 29 maternal deaths and the possible causes of death were obstructed labor (51.7%), hemorrhage (44.7%), eclampsia (24.1%), and sepsis (6.9%). Home delivery (AOR (CI = 4.12 (2.30–7.15) and low birth weight (AOR (CI = 1.63 (1.36–1.96) were significant associates of adverse pregnancy outcomes.ConclusionThe magnitude of adverse pregnancy outcomes was high. Obstructed labor, retained placenta, hypertension in pregnancy, malpresentation, prematurity, and stillbirth are the commonest adverse pregnancy outcomes. Place of delivery and birth weight were independent predictors of adverse pregnancy outcomes. Institutional delivery, early detection and management of complications, and adequate nutrition and weight gain during pregnancy should be encouraged to minimize the risk of adverse pregnancy outcomes.

Filtering Misleading Repair Log Labels to Improve Predictive Maintenance Models

One of the main challenges for predictive maintenance in real applications is the quality of the data, especially the labels. In this paper, we propose a methodology to filter out the misleading labels that harm the performance of Machine Learning models. Ideally, predictive maintenance would be based on the information of when a fault has occurred in a machine and what specific type of fault it was. Then, we could train machine learning models to identify the symptoms of such fault before it leads to a breakdown. However, in many industrial applications, this information is not available. Instead, we approximate it using a log of component replacements, usually coming from the sales or maintenance departments. The repair history provides reliable labels for fault prediction models only if the replaced component was indeed faulty, with symptoms captured by collected data, and it was going to lead to a breakdown. However, very often, at least for complex equipment, this assumption does not hold. Models trained using unreliable labels will then, necessarily, fail. We demonstrate that filtering misleading labels leads to improved results. Our central claim is that the same fault, happening several times, should have similar symptoms in the data; thus, we can train a model to predict them. On the contrary, replacements of the same component that do not exhibit similar symptoms will be confusing and harm the ML models. Therefore, we aim to filter the maintenance operations, keeping only those that can be used to predict each other. Suppose we can train a successful model using the data before a component replacement to predict another component replacement. In that case, those maintenance operations must be motivated by the same, or a very similar, type of fault. We test this approach on a real scenario using data from a fleet of sterilizers deployed in hospitals. The data includes sensor readings from the machines describing their operations and the service logs indicating the replacement of components when the manufacturing company performs the service. Since sterilizers are complex machines consisting of many components and systems interacting with each other, there is the possibility of faults happening simultaneously.

The impact of waiting on customer‐instigated service time: Field evidence from a live‐chat contact center

AbstractIt is well known that the waiting time a customer experiences in a service system is determined by the service processing time of preceding customers, among other factors. We argue that a directionally opposite effect, which diffuses from waiting time to her own service time, also exists in co‐productive service contexts where a significant fraction of the service time is contributed by the customer. Multiple underlying customer behavioral mechanisms lead us to hypothesize that waiting's impact is dependent on the service stage and magnifies as the service process approaches completion. Our empirical analysis uses a unique operational data set that combines server log information with instant‐messaging transcripts collected from a live‐chat contact center. We show that pre‐service waiting accelerates customer engagement—one dimension of customer instigated service time—only at the beginning of the conversation and then exhibits a slowdown effect as the conversation proceeds. In contrast, in‐service waiting consistently slows down customer responses—another dimension of customer instigated service time, the magnitude of which is higher in later episodes of the agent‐customer message exchanges. We discuss the practical implications of our findings on operational policies employed in contact centers.