Deep generative models, such as generative adversarial networks (GANs), have been employed for de~novo molecular generation in drug discovery. Most prior studies have utilized reinforcement learning (RL) algorithms, particularly Monte Carlo tree search (MCTS), to handle the discrete nature of molecular representations in GANs. However, due to the inherent instability in training GANs and RL models, along with the high computational cost associated with MCTS sampling, MCTS RL-based GANs struggle to scale to large chemical databases. To tackle these challenges, this study introduces a novel GAN based on actor-critic RL with instant and global rewards, called InstGAN, to generate molecules at the token-level with multi-property optimization. Furthermore, maximized information entropy is leveraged to alleviate the mode collapse. The experimental results demonstrate that InstGAN outperforms other baselines, achieves comparable performance to state-of-the-art models, and efficiently generates molecules with multi-property optimization. The code is available at: https://github.com/tang777777/InstGAN.

While finding out dominant objects over multiple competing parties’ sensitive datasets via multi-party skyline queries (MSQs), upholding ample data privacy with integrity, data and data owners’ (i.e., parties) anonymity, verifiable deeds of entities, the robustness of framework, etc., is crucial. The existing works consider these criteria trivially or partially and may sacrifice data integrity due to malleable cipher data. This article proposes a framework for MSQs that incorporates these requirements together and eventually makes a ranking of parties’ data-objects. To enrich data privacy, it allocates separate decryption keys among mutual entities. To confirm data integrity, it unites encrypted unique tags (UTs) to parties’ encrypted datasets individually. To assure data and parties’ anonymity, it re-encrypts and shuffles encrypted datasets, and uses anonymous credentials, respectively. These qualities and publicly exposed data reinforce the framework and assure the correct deeds of entities. Finally, evaluation results, analyses, comparisons with state-of-the-art works, etc., prove the efficacy of the proposed framework.

This paper proposes a secure offline electronic (e-) payment scheme by adopting Schnorr's untraceable blind signature (BS). Thereby, to satisfy the essential security requirements of e-payment systems, it requires much more simple computations and becomes more practical than many existing schemes. Other considerations are: to prevent the forgery of e-coin, the Bank is only the lawful entity to produce the valid e-coin; and others can verify its correctness. To confirm no swindling, the e-coin owner also sticks her private signing key with the e-coin before spending it as the payment. Hence, through the commitment with challenge-response of Schnorr's BS, the merchant can verify the spent e-coin, and the trusted authority can identify the dishonest spender if multiple spending occurs. Moreover, it embeds three distinct information of date, namely expiration, deposit, and transaction dates with every e-coin. Thereby, it minimizes the size of the Bank's database, correctly calculates the interest of the e-coin, and helps in arbiter if multiple spending, respectively. Finally, it evaluates the performance and analyzes essential security requirements of the proposed scheme, plus studies a comparison with existing ones.

This paper improves the performance of the revised-simplified verifiable re-encryption mixnet (R-SVRM) based e-voting scheme by introducing confirmation numbers (CNs) that are used in the CN based e-voting scheme. Although CN based and R-SVRM based schemes had made e-voting schemes more practical by excluding zero knowledge proof (ZKP) that requires large volume of computations, still they are not efficient enough. Namely, the CN based scheme adopts RSA encryption functions that are not probabilistic or commutative, therefore to satisfy essential requirements of elections, extra random factors are necessary for individual votes, election authorities must sign on votes and they must keep encryption keys as their secrets. On the other hand, although the R-SVRM based scheme uses ElGamal encryption functions that are probabilistic and commutative, vote forms in it is complicated, i.e., vote forms consist of at least 3 items and they include information about candidates as exponents. The improved scheme simplifies vote forms by exploiting CNs, and extensively reduces the number of operations required for individual votes. Also, the scheme successfully satisfies all essential requirements of e-voting systems, i.e., it is endowed with features about privacy, robustness, accuracy, incoercibility and fairness as CN based and R-SVRM based schemes are.

In most of the business areas, many organizations are running similar trades and maintaining comparable databases. These organizations have noticed the importance of analyzing results obtained from the union of databases owned by different organizations. However, they do not want to disclose their contents to others since some of the contents are sensitive and private. Recently, preference-based queries have drawn massive attention in the database community. Particularly, the top-k dominating queries have been studied extensively, which selects the k objects that are better than other objects based on the `domination score'. In this paper, we have considered the top-k dominating queries on the combined databases of different organizations. We propose a secure framework for multi-party top-k dominating queries, where individual organizations do not need to expose their private databases to others. We analyze the privacy of our proposed framework and also evaluate its performance for various settings.

Recommendation systems address the "information overload" problem by filtering out items that customers may not be interested. Collaborative Filtering (CF) is the most popular technique which recommends items to a user based on similar users' preferences and/or similar items records by utilizing the user-item rating matrix. However, such a large amount of explicit feedbacks are not always available. Furthermore, user preferences are changing over time. The Conventional CF cannot capture the temporal dynamics of recommendations well. In this paper, we apply Deep Recurrent Neural Networks (DRNNs) to CF and generate dynamic, personalized recommendations by utilizing user purchase history big data. Experiments on the MovieLens dataset show relative improvements over previously reported results.

Selection of good locations in a map is an indispensable function in many applications. In order to select specific locations, we have to specify detailed selection criteria. However, it is not easy especially for users of mobile devices. Therefore, we used an idea of skyline queries, which are known to be easy and effective to retrieve interesting data from a database. In our previous work, we have proposed area skyline query that selects good locations in a map. However, the query is not fast enough for handling “big data”. We simplify and revise the algorithm of the query in this paper by using MapReduce framework so that we can use it for big data. Experiments' results demonstrate that the performance and scalability are superior to previous area skyline algorithm and are able to handle big data.

Operations in tabular forms conforming to the structures of relationships between cells (called "semantic structures") have relied on a great deal of manpower in the existing application software. It is difficult to efficiently and properly process huge amounts of information with conventional methods. Therefore, we are developing a method of operation that uses computer assistance to safely and efficiently edit tabular forms to solve this problem. The method of operation guarantees the semantic structures of tabular forms will be retained after the editing process. First, we developed the grammar for expressing the semantic structure rules in tabular forms. It was called a "descriptive grammar for semantic structures". Second, we developed a model based on a graph that could express semantic structures as a method of expressing tabular forms, which was called a "graph expressing semantic structures". Finally, we developed operation algorithms for the tabular forms based on this model and a prototype system as an implementation of these algorithms.

A SCORM-compliant learning management system (LMS) has been developed that enhances learning by effectively and efficiently managing the learning itself. First, a SCORM-LST was developed by adding to SCORM (sharable content object reference model) a framework that describes facilitation corresponding to the learner's state of learning and describes the learning state transitions. This makes it possible to describe collaborative learning, assessment, and facilitation for multiple users. Next, a SCORM-compliant LMS (SALMS: SCORM-compliant adaptive LMS) based on the SCORM-LST was developed. SALMS interprets SCORM-LST code and changes the user interface to match the learner's state of learning. It also manages the learning so that it matches the designer's intentions.

Ten years ago, technology standards in e-learning and learning support systems became the center of public attention. Various international standards have been proposed. However, there is no portfolio assessment standard that enables the support of assessment activities. Therefore, a portfolio assessment modeling language (PAML) for supporting a portfolio assessment standard was developed. It is very likely that the modeling language is not only able to describe needed portfolios in portfolio assessment but also facilitate assessment activities using a learning support system.

This paper examines accumulation methods for effective use of portfolios and develops a meta-language ("MelaPass") for describing the framework of portfolios for making a portfolio assessment. The purpose of MelaPass is to describe the structure of portfolios which have "soundness" and "exhaustiveness" features, and the language can be used in cooperation with existing metamodels (i.e., it has an "affinity" feature). The paper also develops a portfolio assessment support system called "passports" that is based on MelaPass. By using this system, users can design portfolio assessments based on MelaPass and use and manage portfolios.

We consider the problem of finding a set of attribute values that give a high quality binary segmentation of a database. The quality of a segmentation is defined by an objective function suitable for the user's objective, such as "mean squared error," "mutual information," or "/spl chi//sup 2/" each of which is defined in terms of the distribution of a given target attribute. Our goal is to find value groups on a given conditional domain that split databases into two segments, optimizing the value of an objective function. Though the problem is intractable for general objective functions, there are feasible algorithms for finding high quality binary segmentations when the objective function is convex, and we prove that the typical criteria mentioned above are all convex. We propose two practical algorithms, based on computational geometry techniques, which find a much better value group than conventional heuristics.

We consider the problem of finding neighboring class sets. Objects of each instance of a neighboring class set are grouped using their Euclidean distances from each other. Recently, location-based services are growing along with mobile computing infrastructure such as cellular phones and PDAs. Therefore, we expect to see the development of spatial databases that contains very large number of access records including location information. The most typical type would be a database of point objects. Records of the objects may consist of "requested service name," "number of packet transmitted" in addition to x and y coordinate values indicating where the request came from. The algorithm presented here efficiently finds sets of "service names" that were frequently close to each other in the spatial database. For example, it may find a frequent neighboring class set, where "ticket" and "timetable" are frequently requested close to each other. By recognizing this, location-based service providers can promote a "ticket" service for customers who access the "timetable."

We discuss data mining based on association rules for two numeric attributes and one Boolean attribute. For example, in a database of bank customers, Age and Balance are two numeric attributes, and CardLoan is a Boolean attribute. Taking the pair (Age, Balance) as a point in two-dimensional space, we consider an association rule of the form ((Age,Balance) ∈P)⇒(CardLoan = Yes), which implies that bank customers whose ages and balances fall within a planar region P tend to take out credit card loans with a high probability.We consider two classes of regions, rectangles and admissible (i.e., connected and x-monotone) regions. For each class, we propose efficient algorithms for computing the regions that give optimal association rules for gain, support, and confidence, respectively. We have implemented the algorithms for admissible regions as well as several advanced functions based on them in our data mining system named SONAR (System for Optimized Numeric Association Rules), where the rules are visualized by using a graphic user interface to make it easy for users to gain an intuitive understanding of rules.

Given a huge database, we address the problem of finding association rules for numeric attributes, such as Permission to make digital/hard copies of all or pati of this material for personal or claasroom usc is granted without fee provided that the copies are not made or distributed for pro~t or cornmesvial advantage, the copyright notice, the title of the publication and Its date appear, and notice is given that cop yright is by permission of the ACM, Inc.To copy otherwise, to repubtish, to post on servers or to redistribute to lists, requires specific permission and/or fee.PODS '96, Montreal Quebec Canada

We discuss data mining based on association rules for two numeric attributes and one Boolean attribute. For example, in a database of bank customers, "Age" and "Balance" are two numeric attributes, and "CardLoan" is a Boolean attribute. Taking the pair (Age, Balance) as a point in two-dimensional space, we consider an association rule of the form((Age, Balance) ∈ P) ⇒ (CardLoan = Yes),which implies that bank customers whose ages and balances fall in a planar region P tend to use card loan with a high probability. We consider two classes of regions, rectangles and admissible (i.e. connected and x-monotone) regions. For each class, we propose efficient algorithms for computing the regions that give optimal association rules for gain, support, and confidence, respectively. We have implemented the algorithms for admissible regions, and constructed a system for visualizing the rules.

No abstract available.

This paper introduces a generic object which behaves flexibly according to its related objects and conditions for execution in an object-oriented programming system, called ISL-xscheme. A generic object is an instance of 'Generic' class and created by providing abstract classes as a domain. It behaves adequately in the domain depending on its constraints and the messages sent to it. Generic objects are useful for various purposes and applications because they are flexibly transformed via executions depending on what they are used for and how they are used. They are especially effective for program refinement.>