The necessity of caring for elderly people is increasing. Great efforts are being made to enable the elderly population to remain independent for as long as possible. Technologies are being developed ...to monitor the daily activities of a person to detect their state. Approaches that recognize activities from simple environment sensors have been shown to perform well. It is also important to know the habits of a resident to distinguish between common and uncommon behavior. In this paper, we propose a novel approach to discover a person’s common daily routines. The approach consists of sequence comparison and a clustering method to obtain partitions of daily routines. Such partitions are the basis to detect unusual sequences of activities in a person’s day. Two types of partitions are examined. The first partition type is based on daily activity vectors, and the second type is based on sensor data. We show that daily activity vectors are needed to obtain reasonable results. We also show that partitions obtained with generalized Hamming distance for sequence comparison are better than partitions obtained with the Levenshtein distance. Experiments are performed with two publicly available datasets.
This paper studies the efficiency of a recently defined population-based direct global optimization method called Differential Evolution with self-adaptive control parameters. The original version ...uses fixed population size but a method for gradually reducing population size is proposed in this paper. It improves the efficiency and robustness of the algorithm and can be applied to any variant of a Differential Evolution algorithm. The proposed modification is tested on commonly used benchmark problems for unconstrained optimization and compared with other optimization methods such as Evolutionary Algorithms and Evolution Strategies.
This paper gives a review of recent extensions of the Differential Evolution (DE) algorithm for use in Large-Scale Global Optimization (LSGO) and presents an empirical analysis of DE-based and some ...other state-of-the-art algorithms for LSGO on the CEC 2013 LSGO benchmark suite. Since witnessing the first successful applications of DE for a wide variety of optimization problems in the early nineties, researchers have developed several new algorithms in this field. In this paper, we are especially interested in algorithms for solving LSGO. As LSGO is one of the most active research lines, not only in DE, but in many evolutionary and meta-heuristic algorithms, we discuss general approaches for dealing with LSGO first. The main focus of the paper is DE. We review its basic algorithm and discuss several extensions used for coping with large-scale problems. This paper has two main objectives: (1) To propose, from a theoretical point of view, the grouping of DE mechanisms for dealing with LSGO into nine groups, and (2) To evaluate sixteen recently proposed algorithms for LSGO empirically. Many benchmark suites were designed with the aim of providing a suitable evaluation platform for testing and comparing large-scale optimization algorithms. In this paper, the CEC 2013 LSGO benchmark suite was chosen for comparison, because it resembles the following features of real-world problems: Non-uniform subcomponent sizes; imbalance in the contribution of subcomponents; and functions with interdependent overlapping subcomponents. The performances of state-of-the-art algorithms are compared, and the algorithms are ranked using three different metrics, which evaluate the performance from different perspectives. The conducted research shows that DE is among the best algorithms for LSGO on the CEC 2013 LSGO benchmark suite, especially when used with other mechanisms for dealing with large numbers of variables. Finally, the analysis has shown that there is still some room for further improvements in DE towards the solution of LSGO problems.
•A review of Large Scale Global Optimization (LSGO).•Focus on recent use of Differential Evolution (DE).•Grouping of mechanisms, used in DE, to cope with LSGO.•Evaluation of 16 state-of-the-art algorithms on the CEC 2013 LSGO benchmark suite.•Empirical analysis performed using three different evaluation methods.
With the transition to neural architectures, machine translation achieves very good quality for several resource-rich languages. However, the results are still much worse for languages with complex ...morphology, especially if they are low-resource languages. This paper reports the results of a systematic analysis of adding morphological information into neural machine translation system training. Translation systems presented and compared in this research exploit morphological information from corpora in different formats. Some formats join semantic and grammatical information and others separate these two types of information. Semantic information is modeled using lemmas and grammatical information using Morpho-Syntactic Description (MSD) tags. Experiments were performed on corpora of different sizes for the English–Slovene language pair. The conclusions were drawn for a domain-specific translation system and for a translation system for the general domain. With MSD tags, we improved the performance by up to 1.40 and 1.68 BLEU points in the two translation directions. We found that systems with training corpora in different formats improve the performance differently depending on the translation direction and corpora size.
This paper proposes a hybrid machine translation (HMT) system that improves the quality of neural machine translation (NMT) by incorporating statistical machine translation (SMT). Therefore, two NMT ...systems and two SMT systems were built for the Slovenian–English language pair, each for translation in one direction. We used a multilingual language model to embed the source sentence and translations into the same vector space. From each vector, we extracted features based on the distances and similarities calculated between the source sentence and the NMT translation, and between the source sentence and the SMT translation. To select the best possible translation, we used several well-known classifiers to predict which translation system generated a better translation of the source sentence. The proposed method of combining SMT and NMT in the hybrid system is novel. Our framework is language-independent and can be applied to other languages supported by the multilingual language model. Our experiment involved empirical applications. We compared the performance of the classifiers, and the results demonstrate that our proposed HMT system achieved notable improvements in the BLEU score, with an increase of 1.5 points and 10.9 points for both translation directions, respectively.
Ambient assisted living in smart home environments is becoming an important goal in an aging society with challenges in elderly care. A key component in such environments is the accurate recognition ...of activities of daily living from various sensor data. Recent research directions explored several classification methods, including hidden Markov models. This research presents a hidden Markov model-based system for activity recognition, and extends it with a second-order Markov chain model of activity sequences to achieve long-term dependency in the model. We also introduce an activity transition cost to counteract the tendency of hidden Markov models to make a large number of transitions. The proposed models are used for activity recognition, with their scores being combined using heuristically determined weights for optimal performance. We also present a modified Viterbi algorithm, which incorporates both models and the activity transition cost. We used a dataset from the CASAS project to test and evaluate the proposed models. A comparison of the results shows the potential of introducing long term dependencies and the managing the number of activity transitions. We show results regarding the modeling ability to predict activity sequences, a comparison of predicted and actual activity transitions, and final recognition accuracy results. The results show an increase of total activity recognition accuracy from 93.9 % to 94.52 % on individual activities, and from 68.89 % to 70.95 % over the combination of all concurrent activities. The results also show a reduction of predicted activity transitions from 741 to 236, whereas the number of actual activity transitions in the evaluation set is 141.
Machine Translation has become an important tool in overcoming the language barrier. The quality of translations depends on the languages and used methods. The research presented in this paper is ...based on well-known standard methods for Statistical Machine Translation that are advanced by a newly proposed approach for optimizing the weights of translation system components. Better weights of system components improve the translation quality. In most cases, machine translation systems translate to/from English and, in our research, English is paired with a Slavic language, Slovenian. In our experiment, we built two Statistical Machine Translation systems for the Slovenian-English language pair of the Acquis Communautaire corpus. Both systems were optimized using self-adaptive Differential Evolution and compared to the other related optimization methods. The results show improvement in the translation quality, and are comparable to the other related methods.
Večina sodobnih sistemov za strojno prevajanje temelji na arhitekturi nevronskih mrež. To velja za spletne ponudnike strojnega prevajanja, za raziskovalne sisteme in za orodja, ki so lahko v pomoč ...poklicnim prevajalcem v njihovi praksi. Čeprav lahko sisteme nevronskih mrež uporabljamo na običajnih centralnih procesnih enotah osebnih računalnikov in strežnikov, je za delovanje s smiselno hitrostjo potrebna uporaba grafičnih procesnih enot. Pri tem smo omejeni z velikostjo slovarja, kar zmanjšuje kakovost prevodov. Velikost slovarja besednih enot je še posebej pereč problem visoko pregibnih jezikov. Rešujemo ga z uporabo podbesednih enot, s katerimi dosežemo večjo pokritost jezika. V članku predstavljamo različne metode razcepljanja besed na podbesedne enote z različno velikimi slovarji in primerjamo njihovo uporabo v strojnem prevajalniku za jezikovni par slovenščina-angleščina. V primerjavo vključujemo še prevajalnik brez razcepljanja besed. Predstavljamo rezultate uspešnosti prevajanja z metriko BLEU, hitrosti učenja modelov in hitrosti prevajanja ter velikosti modelov. Dodajamo pregled praktičnih vidikov uporabe podbesednih enot v strojnem prevajalniku, ki ga uporabljamo skupaj z orodji za računalniško podprto prevajanje.
Many real-world optimization problems are large-scale in nature. In order to solve these problems, an optimization algorithm is required that is able to apply a global search regardless of the ...problems’ particularities. This paper proposes a self-adaptive differential evolution algorithm, called jDElscop, for solving large-scale optimization problems with continuous variables. The proposed algorithm employs three strategies and a population size reduction mechanism. The performance of the jDElscop algorithm is evaluated on a set of benchmark problems provided for the Special Issue on the Scalability of Evolutionary Algorithms and other Metaheuristics for Large Scale Continuous Optimization Problems. Non-parametric statistical procedures were performed for multiple comparisons between the proposed algorithm and three well-known algorithms from literature. The results show that the jDElscop algorithm can deal with large-scale continuous optimization effectively. It also behaves significantly better than other three algorithms used in the comparison, in most cases.
PDF
