In recent years, attacks on network environments continue to rapidly advance and are increasingly intelligent. Accordingly, it is evident that there limitations in existing signature-based intrusion detection systems. particular, for novel such as Advanced Persistent Threat (APT), signature patterns have problems with poor generalization performance. Furthermore, a environment, attack samples rarely collected compared normal samples, creating the problem of imbalanced data. Anomaly using an...

Recently, several plant pathogens have become more active due to temperature increases arising from climate change, which has caused damage various crops. If change continues, it will likely be very difficult maintain current crop production, and the problem of a shortage expert manpower is also deepening. Fortunately, research on early diagnosis systems based deep learning actively underway solve these problems, but lack diversity in some hard-to-collect disease samples remains. This...

The diagnosis of heart disease is important issue, prompting many researchers to work on development intelligent medical decision support systems improve the ability physicians. In this paper, we propose use a bagging algorithm indentify warning signs in patients and also compare effectiveness with tree that has been used by researchers.

Deep learning (DL) technology has shown outstanding performance in various fields such as object recognition and classification, speech recognition, natural language processing. However, it is well known that DL models are vulnerable to data poisoning attacks, where adversaries modify or inject samples maliciously during the training phase, leading degraded classification accuracy misclassification. Since attacks keep evolving avoid existing defense methods, security researchers thoroughly...

Smart homes integrated with sensors, actuators, wireless networks and context-aware middleware soon becomes part of our daily life. This paper describes a providing an automatic home service based on user's preference inside smart home. The includes appliance controller, agent scalable browser. controller takes charge communication between appliances in the middleware. use OSGi (open gateway initial) as framework network. browser recognizes properties all rendering device, it figures out...

As cyberattacks become more intelligent, the difficulty increases for traditional intrusion detection systems to detect advanced attacks that deviate from previously stored patterns. To solve this problem, a deep learning-based system model has emerged analyzes intelligent attack patterns through data learning. However, learning models have disadvantage of having re-learn each time new cyberattack method emerges. The required learn large amount is not efficient. In paper, an experiment was...

In recent years, there has been an increase in the number of phishing attacks targeting people fields defense, security, and diplomacy around world. particular, hacking attack group Kimsuky conducting to collect key information from public institutions since 2013. The main feature techniques used by are conceal malicious code e-mails disguised as normal spread a document file that is vulnerable such Hangul file, or induce interest through social engineering technique account information....

Wireless Sensor Network (WSN) technology, for services that are difficult to access or which need be continuously monitored regardless of location, needs further research and development due an expansion fields where it can applied increases in efficiency. In particular, the field defense, on latest IT technologies including sensor networks is being actively conducted as alternative risky use personnel areas such surveillance reconnaissance. This paper experimented with analyzing conditions...

The network intrusion detection system is a core technology of security that detects packets for malicious activities occurring in the and an essential element stable services extended environments such as big data IoT. These systems have been studied together with machine learning deep learning, but performance not guaranteed actual environment or class balance problem has solved. Therefore, this study, we investigate discretization preprocessing method CNN-based classifier on imbalance...

In this paper, a proof-of-concept method for detecting abnormal behavior in dementia patients based on single case study is proposed. This incorporates the collection of lifelog data using affordable sensors and development machine-learning-based system. Such an approach has potential to enable prompt detection within nursing homes send alerts caregivers, which could potentially reduce their workload decrease risk accidents injuries. experiment conducted patient Korean home, proposed system,...

For the prevention and management of diseases in chronic patients, attention has been directed at ubiquitous healthcare systems order to reduce medical expenses provide high-quality services different places, including hospitals homes. In this paper, a system proposed care for patient, be used by nurse or professional patient's residence. It comprises portable bio-signal acquisition device, smartphone application, health server. The application collects patient information, lifelog...

The image-based data hiding method is a technology used to transmit confidential information secretly. Since images (e.g., grayscale images) usually have sufficient redundancy information, they are very suitable medium for data. Absolute Moment Block Truncation Coding (AMBTC) one of several compression methods and appropriate embedding due its low complexity acceptable distortion. However, since there not enough redundant compared images, the research embed in compressed image challenging...

The ubiquitous smart home provides an automatic service via analysis of human and contexts. It receives a lot contexts from the environment, but most important context is information about human's location motion. In this paper, we present real-time tracker that detects motion using cameras predicts services in home. We propose algorithm captures effective area four network which detected his position estimated. To detect motion, three kinds images are used: IMAGE1: empty room image, IMAGE2:...

For patients who have a senile mental disorder such as dementia, the quantity of exercise and amount sunlight are an important clue for doses treatment. Therefore, monitoring daily health information is necessary patients’ safety health. A portable wearable sensor device server configuration data needed to provide these services patients. watch-type (smart watch) that wear system developed in this paper. The smart watch includes GPS, accelerometer, illumination sensor, can obtain real time...

With advances in cyber threats and increased intelligence, incidents continue to occur related new ways of using technologies. In addition, as intelligent advanced cyberattack technologies gradually increase, the limit inefficient malicious code detection analysis has been reached, inaccurate rates for unknown codes are increasing. Thus, this study used a machine learning algorithm achieve file accuracy more than 99%, along with method visualizing data files dynamic-analysis-based MITRE...

In this paper, we present an application of the hierarchical hidden Markov model (HHMM) for problem predicting state human behavior in a smart home network. We argue that to robustly and recognize sequential activities, it is crucial exploit both natural decomposition shared semantics embedded ubiquitous environment. To end, propose use HHMM, rich stochastic has recently been extended handle structures, representing recognizing set complex indoor activities. The main contributions paper lie...

The development of information and communication technology (ICT) is making daily life more convenient by allowing access to at anytime anywhere improving the efficiency organizations. Unfortunately, malicious code also proliferating becoming increasingly complex sophisticated. In fact, even novices can now easily create it using hacking tools, which causing increase spread exponentially. It has become difficult for humans respond such a surge. As result, many studies have pursued methods...