In the irrigated areas, intensive agriculture has led to soil degradation and declining crop yields; therefore, the durability of soil resources is influenced. In order to assess the soil quality changes in the Zemamra area from the highest plain of Doukkala (523 000 ha), in the semi-arid region of Morocco, the soil samples taken from the horizon 0–30 cm were analysed for physical and chemical parameters (Clay, Sand, Silt, SOM, pH, TN, P2O5, K2O, CEC, MgO, CaO, SAR, Na2O, EC, CaCO3, NO3-N, NH4-N, B, Mn, Zn, Fe, and Cu). The data obtained were statistically processed to search for soil quality indices (SQIs). The main findings show that the soil surface has more sand than clay (Sand = 55%, Clay = 31%), an accumulation of phosphorus (P2O5 = 33.34 mg/kg), moderate soil organic matter (1.789%), and carbonate contents of about (2.6%). Soil Structure Stability Index (SSSI<5%) indicated that soil structure is degraded. The selection of the Minimum Data Set by principal component analysis allowed retaining four indicators (cationic exchange capacity, boron, exchangeable potassium, and manganese). After scoring the selected indicators, the soil quality indices thus obtained classified the soils as having low to moderate quality (SQIs<0.55). The indicators: sand, phosphorus, boron, manganese, and zinc are negatively correlated to SQIs, while clay, silt, cationic exchange capacity, pH, soil organic matter, and carbonates are positively correlated. Micronutrients: boron and zinc negatively impact soils at low concentrations.
The task of mining association rules has become one of the most widely used discovery pattern methods in knowledge discovery in databases (KDD). One such task is to represent an item set in the memory. The representation of the item set largely depends on the type of data structure that is used for storing them. Computing the process of mining an association rule impacts the memory and time requirements of the item set. With the constant increase of the dimensionality of data and data sets, mining such a large volume of data sets will be difficult since all of these item sets cannot be placed in the main memory. As the representation of an item set greatly affects the efficiency of the rule-mining association, a compact and compressed representation of the item set is needed. In this paper, a set representation is introduced that is more memory- and cost-efficient. Bitmap representation takes 1 byte for an element, but a set representation uses 1 bit. The set representation is being incorporated in the Apriori algorithm. Set representation is also being tested for different rule-generation algorithms. The complexities of these different rule-generation algorithms that use set representation are being compared in terms of memory and time of execution.
Cyber-attacks are increasing day by day. The generation of data by the population of the world is immensely escalated. The advancements in technology, are intern leading to more chances of vulnerabilities to individual’s personal data. Across the world it became a very big challenge to bring down the threats to data security. These threats are not only targeting the user data and also destroying the whole network infrastructure in the local or global level, the attacks could be hardware or software. Central objective of this paper is to design an intrusion detection system using ensemble learning specifically Decision Trees with distinctive feature selection univariate ANOVA-F test. Decision Trees has been the most popular among ensemble learning methods and it also outperforms among the other classification algorithm in various aspects. With the essence of different feature selection techniques, the performance found to be increased more, and the detection outcome will be less prone to false classification. Analysis of Variance (ANOVA) with F-statistics computations could be a reasonable criterion to choose distinctives features in the given network traffic data. The mentioned technique is applied and tested on NSL KDD network dataset. Various performance measures like accuracy, precision, F-score and Cross Validation curve have drawn to justify the ability of the method.
W artykule opisano zagadnienie odróżniania historycznych fotografii pomiędzy oryginalnie kolorowe a koloryzowane. Rozważono problem doboru zdjęć pod względem technologii, w jakiej zostały wykonane. Następnie wykorzystując sieci neuronowe już w części wyuczone na innych zbiorach danych, sprawdzono ich efektywność w rozwiązywaniu badanego problemu. Rozważono wpływ rozmiaru obrazu podanego na wejściu, architektury zastosowanej sieci, a także zestawu danych użytego do uczenia sieci i wyodrębniania cech. W rezultacie potwierdzono przydatność opracowanego zbioru do treningu sieci, a także zaobserwowano, że zwiększanie rozmiaru sieci nie przynosi dodatkowych korzyści. Uzyskana trafność rozróżniania sięgnęła ponad 92 %.
EN
The article describes a dataset designed to train neural networks distinguishing historical photographs between the ones that have original historic color and those which were contemporary colorized. The problem of choosing photos in terms of technology and content was considered. Using some of the pre-trained neural networks on other collections, their effectiveness in solving the studied issue was checked. The influence of the input image size, the depth of the neural network used as well as the data set used to train the network to extract features was investigated. As a result, the usefulness of the developed set for network training was confirmed, and it was observed that increasing the network did not bring any additional benefits. The reached accuracy is up to 92.6%.
5
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Environmental sound classification has received more attention in recent years. Analysis of environmental sounds is difficult because of its unstructured nature. However, the presence of strong spectro-temporal patterns makes the classification possible. Since LSTM neural networks are efficient at learning temporal dependencies we propose and examine a LSTM model for urban sound classification. The model is trained on magnitude mel-spectrograms extracted from UrbanSound8K dataset audio. The proposed network is evaluated using 5-fold cross-validation and compared with the baseline CNN. It is shown that the LSTM model outperforms a set of existing solutions and is more accurate and confident than the CNN.
6
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Droughts are natural phenomena affecting the environment and human activities. There are various drought definitions and quantitative indices; among them is the Standardised Precipitation Index (SPI). In the drought investigations, historical events are poorly characterised and little data are available. To decipher past drought appearances in the southeastern Alps with a focus on Slovenia, precipitation data from HISTALP data repository were taken to identify extreme drought events (SPI ≤ -2.00) from the second half of the 19th century to the present day. Several long-term extreme drought crises were identified in the region (between the years 1888 and 1896; after World War I, during and after World War II). After 1968, drought patterns detected with SPI changed: shorter, extreme droughts with different time patterns appeared. SPI indices of different time spans showed correlated structures in space and between each other, indicating structured relations.
Insertion sort algorithm is one of the sorting algorithms. It is characterized by the computational complexity and time complexity, which represent the possibility of using it for large data sets. The present work is to describe this algorithm and describe it’s performance when sorting large scale data sets.
PL
Algorytm sortowania przez wstawianie jest jednym z algorytmów opisywanych w literaturze. Omawiana metoda została scharakteryzowana poprzez złożoność czasową i obliczeniową algorytmu, która opisuje możliwość stosowania tego algorytmu do sortowania dużych zbiorów danych. Praca ta ma na celu opisanie zachowania algorytmu i jego wydajności dla dużych zbiorów danych.
W artykule zaprezentowano podejście i metody pozyskiwania wiedzy z danych, które mogą zostać wykorzystane w zarządzaniu współczesnymi przedsiębiorstwami. W tym zakresie szczególną uwagę zwrócono na techniki inteligentne znajdujące zastosowanie na etapie eksploracji danych do poszukiwania nowych zależności i reguł w dużych zbiorach danych. Zaprezentowano przykładowe algorytmy i kierunki ich praktycznego wykorzystania w przedsiębiorstwie górniczym.
EN
The paper presents the approach and methods of acquiring knowledge from data that can be used in the management of modern enterprises. In this regard, special attention was paid to the intelligent techniques finding application at the stage of data exploration for searching of new relationships and rules in large data sets. The exemplary algorithms and guidelines for their practical use in a mining company were presented.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.