• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.83-92
• /
• 2023

The majority of product users rely on the reviews that are posted on the appropriate website. Both users and the product's manufacturer could benefit from these reviews. Daily, thousands of reviews are submitted; how is it possible to read them all? Sentiment analysis has become a critical field of research as posting reviews become more and more common. Machine learning techniques that are supervised, unsupervised, and semi-supervised have worked very hard to harvest this data. The complicated and technological area of feature engineering falls within machine learning. Using deep learning, this tedious process may be completed automatically. Numerous studies have been conducted on deep learning models like LSTM, CNN, RNN, and GRU. Each model has employed a certain type of data, such as CNN for pictures and LSTM for language translation, etc. According to experimental results utilizing a publicly accessible dataset with reviews for all of the models, both positive and negative, and CNN, the best model for the dataset was identified in comparison to the other models, with an accuracy rate of 81%.

• The Journal of Fisheries Business Administration
• /
• v.33 no.1
• /
• pp.19-41
• /
• 2002

Recently, the number of Internet shopping malls increases dramatically Internet shopping malls offer direct sales by electronic catalogs. As compared with to physical stores and paper catalogs, electronic catalogs differ in terms of the varieties and types of products offered, promotional efforts, service, interface, ordering and delivering, and so on. This paper analysed the features of electronic catalogs for fisheries by 45 variables. By descriptive statistics of electronic catalogs for fisheries, most electron)c catalogs had sufficient product related information. But promotion and transaction security related features were scarce. And some development technologies of electronic catalogs for fisheries were obsolete. By factor analysis, there were 9 factors of electronic catalogs for fisheries, that was, design of product pages, transaction information, playfulness, convenience of product selection, interface design, design of homepages, product information, learning capability, other electronic catalog related factor. Thus in standardizing electronic catalog for fisheries products, the above 9 factors should be reflected significantly.

• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.79-87
• /
• 2011

Although products with the fingerprint recognition system currently show a rapid growth in quantity, it is also true that efforts to consider the product quality have been lacking until now. Accordingly, this paper analyzed technological elements with domestic and foreign market situations for products with the fingerprint recognition system to develop an evaluation model to support the quality increase by evaluating aspects of product quality for the knowledge information security, identifying the level of quality and deriving directions for improvements. A model for the reliability quality evaluation was constructed that can be applied comprehensively to non-functional elements that have not been done in the existing evaluations central to the security functions by analyzing requirements for the security, performance and reliability in consideration of features on products. It is considered that this paper can make contributions to the overall quality increase for products with the knowledge information security by reflecting features and trends for the fingerprint recognition products and building a model for the reliability and evaluation to perform evaluations by product.

• Journal of the Society of Disaster Information
• /
• v.10 no.1
• /
• pp.116-122
• /
• 2014

Recently, Korea has enacted the Framework Act on Product Safety to allow comprehensive control of product safety accidents. This is a government policy aiming to ensure product safety and customer protection by strengthening the obligation of producers. However, the framework has not yet been completed in Korea. Therefore, this paper deals with improvement assignments and directions by comparing the frameworks of applied in Korea and Japan for ensuring such production safety.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.5
• /
• pp.131-142
• /
• 2009

While users of information security products require high-quality products that are secure and have high performance, there are neither examples for evaluating the quality of information security products nor studies on the quality model and metrics for the quality evaluation. In this paper, information security products are categorized into three different types and the security and performance of various information security products are analyzed. Through this process and after consideration of information security products' security and performance, a new quality model that possesses 7 characteristics and 24 sub-characteristics has been defined. In addition, metrics consisting of 62 common and 45 extended metrics that can be used to evaluate the quality of information security products are introduced, and a proposition for a method of generating the quality evaluation metrics for specific information security products is included. The method of generating metrics proposed in this paper can be extended in order to be applied to a variety of information security products, and by generating and verifying the quality evaluation metrics for firewall, intrusion detection systems and fingerprint systems it is shown that it applicable on a variety of information security products.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.7
• /
• pp.3353-3370
• /
• 2016

The way of combination of Product Perfect Codes (PPCs) is based on the theory of short codes constructing long codes. PPCs have larger embedding rate than Hamming codes by expending embedding columns in a coding block, and they have been proven to enhance the performance of the F₅ steganographic method. In this paper, the proposed modified product codes called MPCs are introduced as an efficient way to embed more data than PPCs by increasing 2^r₂-1-r₂ embedding columns. Unlike PPC, the generation of the check matrix H in MPC is random, and it is different from PPC. In addition a simple solving way of the linear algebraic equations is applied to figure out the problem of expending embedding columns or compensating cases. Furthermore, the MPCs over ℤ₄ have been proposed to further enhance not only the performance but also the computation speed which reaches O(n₁+σ). Finally, the proposed ℤ₄-MPC intends to maximize the embedding rate with maintaining less distortion , and the performance surpasses the existing improved product perfect codes. The performance of large embedding rate should have the significance in the high-capacity of covert communication.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2002.11a
• /
• pp.72-81
• /
• 2002

Management for security product and application is becoming more difficult because they became more specialized. Most of research is focused on combining policies for information security management policy, security standard, and security tools. However, there are no researches for total solution for both application and security policy. Thereby, the purpose of this research is to propose a remote integrated management system based on linux. The system could efficiently manage data update for application and policy update for a server supporting the distinct configuration of each server. By using the remote integrated management system, system manager with poor secure knowledge also could easily manage their system securely.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.2
• /
• pp.131-144
• /
• 2010

IT developed countries since the late 1980s are used to develop IT security evaluation criteria to ensure safety and reliability of information protection products. Currently a variety of products used for the evaluation based on CC and it takes a long period of product evaluation is required to reduce the developers and users. In this paper refer to the published standard evaluation schedule for the EAL4 calculation model offers a trial period. In addition, based on this commitment by adjusting the number of evaluaters to evaluate the applicant in the evaluation period to minimize the position offers.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.5
• /
• pp.141-151
• /
• 2004

According to the improvemnent of electronic commerce, the requirements of security devices are becoming increasingly pervasive. The security API must design easily and securely to support a compatibility feature between security devices. It is chosen the PKCS #11 interface by RSA Labs that shows the compatibility and extensibility standards of many application product and implementation, and supported KCDSA mechanism which is a korean digital signature standard. And the PKCS #11 security API defines new key management function which provides more secure key management ability. We suggest the object attributes and templates of KCDSA private and public key object, generate and verify digital signature using KCDSA mechanism. The PKCS #11 supporting KCDSA mechanism is designed, implemented using C-Language, tested a performance, and analyzed the security and compatibiltiy feature.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.718-732
• /
• 2020

Conducting sentiment analysis and opinion mining are challenging tasks in natural language processing. Many of the sentiment analysis and opinion mining applications focus on product reviews, social media reviews, forums and microblogs whose reviews are topic-similar and opinion-rich. In this paper, we try to analyze the sentiments of sentences from online webcast reviews that scroll across the screen, which we call live barrages. Contrary to social media comments or product reviews, the topics in live barrages are more fragmented, and there are plenty of invalid comments that we must remove in the preprocessing phase. To extract evaluative sentiment sentences, we proposed a novel approach that clusters the barrages from the same commenter to solve the problem of scattering the information for each barrage. The method developed in this paper contains two subtasks: in the data preprocessing phase, we cluster the sentences from the same commenter and remove unavailable sentences; and we use a semi-supervised machine learning approach, the naïve Bayes algorithm, to analyze the sentiment of the barrage. According to our experimental results, this method shows that it performs well in analyzing the sentiment of online webcast barrages.