Similar Pair-free Partial Label Metric Learning

Partial label learning is a new weak- ly supervised learning framework. In this frame- work, the real category label of a training sample is usually concealed in a set of candidate labels, which will lead to lower accuracy of learning al- gorithms compared with traditional strong super- vised cases. Recently, it has been found that met- ric learning technology can be used to improve the accuracy of partial label learning algorithm- s. However, because it is difficult to ascertain similar pairs from training samples, at present there are few metric learning algorithms for par- tial label learning framework. In view of this, this paper proposes a similar pair-free partial la- bel metric learning algorithm. The main idea of the algorithm is to define two probability distri- butions on the training samples, i.e., the proba- bility distribution determined by the distance of sample pairs and the probability distribution de- termined by the similarity of candidate label set of sample pairs, and then the metric matrix is ob- tained via minimizing the KL divergence of the two probability distributions. The experimental results on several real-world partial label dataset- s show that the proposed algorithm can improve the accuracy of k-nearest neighbor partial label learning algorithm (PL-KNN) better than the ex- isting partial label metric learning algorithms, up to 8 percentage points.

Encrypted e-Voting System using IoT

Elections make a fundamental contribution to democratic governance but a lack of trust among citizens on their electoral system is a hindrance to satisfy the legal requirements of legislators. Even the world’s largest democratic countries suffer from issues like vote rigging, election manipulation and hacking of the electronic voting machines in the current voting system. To provide data security for e-Voting systems, the advanced encryption standard (AES) algorithm has been proposed, but traditional AES gives the same ciphertext for every similar pair of key and plaintext. So, to eliminate these disadvantages, AES in Galois-counter mode (GCM) has been used to obtain different ciphertexts all the time by using Initialization Vector. The fingerprint data from each user is verified using Internet of Things (IoT) based Biometric system which also helps to avoid Plural Voting. The whole data is encrypted and stored in the cloud, and it can be decrypted by authorized personnel to obtain the final vote count. So, the proposed model will enhance transparency and maintain anonymity of the voters alongside providing an easily accessible secured voting system. Keywords: Advanced encryption standard, initialization vector, additional authenticated data, galois-counter mode, biometrics, security, ciphertext, authtag

A Model of Position Effects in the Sequential Lineup

What is the effect of placing the suspect in different positions in a sequential lineup? To explore this question, we developed and applied a model called the Independent Sequential Lineup model which analyzes a sequential lineup in terms of both identification position, the position at which the witness identifies a lineup item as the target, and target position, the position at which the target or suspect appears. We conducted a large-scale online eyewitness memory experiment with 7,204 participants each of whom was tested on a 6-item sequential lineup with an explicit stopping rule. The model fit these data well and revealed systematic effects of lineup position on underlying discriminability and response criteria. We also fit the model to data from a similar pair of experiments conducted recently by Wilson, Donnelly, Christenfeld and Wixted (2019; Journal of Memory and Language, 104, 108-125) both with and without application of a stopping rule. In all data sets, if a stopping rule is applied, underlying discriminability was found to be constant, or to increase slightly, across target position. In the absence of a stopping rule, discriminability was found to decrease substantially. We also observed a substantial increase in response criteria following presentation of the target. We discuss the implications of these findings for current theories of recognition memory and current applications of the sequential lineup in different jurisdictions.

The Third Man

This chapter traces host state, separatist movement, and mafia relations in Serbia and Georgia (1989–2012). Kosovo and South Ossetia are the most similar pair of separatist stories in the ex-Yugoslav and ex-Soviet spaces. Their unique mix of wars (foreign and civil), separatist mobilizations (some successful, others less so), and mafia roles (sometimes tearing states, sometimes consolidating them) offers precious lessons on the agency of organized crime. In Serbia and Georgia, war was mafia as much as state business. Borders were made and unmade by smugglers. The black market was not an anomaly; the formal economy was. What separatists achieved depended tremendously on whether organized crime was multiethnic or not, violent or not, strong or not. Different mafia roles gave different results. Though organized crime in both countries began as a rejoicing third, the mafia's role in Kosovo evolved into a divider and conqueror, while in South Ossetia it evolved into a mediator. These differing trajectories account for the greater success of Kosovo's separatist movement.

The Use of the Incomplete Tetrad Method for Measuring the Similarities in Nonmetric Multidimensional Scaling

Research background: So far, many methods of direct measurement of similarity in multidimensional scaling have been developed (e.g. ranking, sorting, pairwise comparison and others). The method selection affects the subjective feelings of the respondents, i.e. fatigue, weariness resulting from making numerous assessments, or difficulties in expressing similarity assessments.Purpose: In the proposed method, for all four-element sets (tetrads) of objects a respondent is asked to pick out the most similar and the least similar pair. Because the number of tetrads increases very rapidly with the number of objects, the aim of the study is to indicate the possibility of measuring similarities based on the reduced number of tetrads.Research methodology: In order to make scaling results independent from respondents’ subjective effects the analysis was made on the basis of the given distance matrix. To construct perceptual maps based on tetrads, multidimensional scaling with the use of the MINISSA program was performed. The quality of matching the resulting points configuration to the configuration determined based on the distance matrix was tested by a Procrustes statistic.Results: It was demonstrated that the choice of the incomplete set of tetrads has no significant effect on the results of multidimensional scaling, even when all pairs of objects in tetrads cannot be presented equally frequently.Novelty: An original method for calculating similarities in nonmetric multidimensional scaling.

Improving Polarity Classification for Financial News Using Semantic Similarity Techniques

This article discusses polarity classification for financial news articles. The proposed Semantic Sentiment Analyser makes use of semantic similarity techniques, sentiment composition rules, and the Positivity/Negativity (P/N) ratio in performing polarity classification. An experiment was conducted to compare the performance of three semantic similarity metrics namely HSO, LESK, and LIN to find the semantically similar pair of word as the input word. The best similarity technique (HSO) is incorporated into the sentiment analyser to find the possible polarity carrier from the analysed text before performing polarity classification. The performance of the proposed Semantic Sentiment Analyser was evaluated using a set of manually annotated financial news articles. The results obtained from the experiment showed that the proposed SSA was able to achieve an F-Score of 90.89% for all cases classification.

The Influence of Triad Selection on the Preference Scaling Results

In the method of triads for a set of n objects all three element sets of objects are presented to the respondents. A respondent is asked to pick out the most similar and the least similar pair. The method of triads, despite its numerous advantages, is rarely used in practice. The number of triads is a cubic function of the number of objects and increases very rapidly with the number of objects. The aim of the study is to indicate the possibility of scaling preferences based on the reduced number of triads. It has also been examined whether the change of reduced set of triads influences the results of the scaling. The results of the analysis are illustrated by an empirical example in which pref­erence scaling for different sets of triads was performed with the use of TRISOSCAL program.

A Projection-Based Locality-Sensitive Hashing Technique for Reducing False Negatives

It is challenging to efficiently find similar pairs of objects when the number of objects is huge. The locality-sensitive hashing techniques have been developed to address this issue. They employ the hash functions to map objects into buckets, where similar objects have high chances to fall into the same buckets. This paper is concerned with a locality-sensitive hashing technique, the projection-based method, which is applicable to the Euclidean distance-based similar pair identification problem. It proposes an extended method which allows an object to be hashed to more than one bucket by introducing additional hashing functions. From the experimental studies, it has been shown that the proposed method could provide better performance compared to the projection-based method.

Description of a new species of Dicyphus Fieber (Insecta: Heteroptera: Miridae) from Portugal based on morphological and molecular data

A new species of the plantbug genus Dicyphus (Insecta: Heteroptera: Miridae), D. umbertae Sanchez & Cassis sp. n., from Portugal is described and the closely related species, Dicyphus cerastii Wagner is redescribed. Several body measurements were taken. Male and female genitalia of both species are illustrated. D. umbertae was found in several localities in Central and South of Portugal on tomato (Lycopersicon esculentum Mill.) and Hyosciamus albus L. D. cerastii was found in southeast Spain on squash (Cucurbita maxima Duchesne), L. esculentum, Ononis natrix L., Withania frutescens (L.) Pauquy and H. albus. The external morphology of the two species is very alike and measurements overlap. In the two species the aedeagus has a similar pair of prominent slightly arcuate sclerites, but the shape and setae on the left paramere are different. Phylogenetic analyses were performed using 381 bp fragments of Cytochrome b. Other dicyphine species were used as outgroups in the analyses: Dicyphus tamaninii Wagner, D. rubicundus Blöte, D. escalerae Lindberg, Nesidiocoris tenuis (Reuter), Cyrtopeltis geniculata Fieber and Macrolophus sp. Several evolutionary models were explored under a maximum likelihood framework. The molecular analyses provided strong support for the species identity of the two sister species D. umbertae and D. cerastii.