Effective Categorization of Tolerance to Salt Stress through Clustering Prunus Rootstocks According to Their Physiological Performances

The effects of climate change on traditional stone fruit producing areas, together with the generation of new varieties with lower chilling requirements that allow the cultivation of previously unexplored areas, are setting up a challenging scenario for the establishment of productive orchards that must be more efficient in their capacity to adapt to new edaphoclimatic conditions. In this context, the rootstock breeding programs are a key piece in the agronomic strategy to achieve this adaptation through the development of rootstocks compatible with the new varieties and capable of transferring their tolerance to stress. An effective categorization of phenotypes within the germplasm involved in a plant breeding program is of utmost importance. Through the measurement of physiological parameters in both roots and leaves, tolerance to saline stress (120 mM NaCl) was evaluated in seven Prunus rootstocks whose genetic background included representatives of the subgenera Prunus, Cerasus, and Amygdalus. To group the genotypes according to their physiological performance under salt stress, an agglomerative hierarchical clustering was applied. The genotypes were grouped into three clusters containing rootstocks very sensitive (‘Mazzard F12/1’), moderately tolerant (‘Maxma 60’, ‘Cab6P’ and ‘AGAF 0204-09’), and tolerant (‘Mariana 2624’, ‘Garnem’ and ‘Colt’) to salt stress. ‘Mariana 2624’, a plum-based rootstock, was identified as the most tolerant Prunus rootstock. The information reported is valuable both in the productive context, for the selection of the most appropriate rootstocks to establish an orchard, and in the context of plant breeding programs, when choosing parents with outstanding traits to obtain progenies tolerant to salt stress.

Online Newspaper Clustering in Aceh using the Agglomerative Hierarchical Clustering Method

The rapid progress in the field of information technology, especially the internet, has given birth to a lot of information. The ease of publishing an article on a website causes an explosion of news pages which will certainly confuse readers. The diversity and the increasing number of news articles make it increasingly difficult for internet users to find news and large piles of news data on online newspaper sites in Aceh. The grouping of text documents is needed to classify news in online newspapers in Aceh based on the content contained in news articles. In this study, the process of grouping online news in Aceh was tried using the Agglomerative Hierarchical Clustering method. News is grouped with a Bottom-Up design strategy that starts with placing each object as a cluster then combined into a larger cluster based on the similarity of keywords in each news, then the cluster results are compared and put into each news category. The research design was carried out in a structured manner using data flow diagrams in forming the research framework. The study was conducted by taking online news text data on 10 online news websites in Aceh from July 2016 to March 2017 with 1000 randomly generated documents. The process of crawling news data is done using a php script which will only take text files from the news on the website. News grouping is done based on religion, politics, law, sports, tourism, education, culture, economy and technology. The results of the grouping performance of the Agglomerative Hierarchical Clustering method in this study have an average accuracy of 89.84%.

Analisis Kondisi Pemberdayaan Gender di Indonesia Tahun 2020 dengan Agglomerative Hierarchical Clustering dan Biplot

Pemberdayaan gender menjadi salah satu agenda penting dalam tujuan pembangunan berkelanjutan, baik dalam level nasional maupun internasional. Penelitian ini bertujuan untuk mengetahui kondisi pemberdayaan gender di Indonesia tahun 2020. Data yang digunakan adalah Indeks Pemberdayaan Gender (IDG) dan data tiga komponen pembentuk IDG yang bersumber dari BPS. Penelitian ini melakukan clustering IDG di Indonesia dengan metode agglomerative hierarchical clustering dan biplot. Dari hasil clustering IDG didapatkan tiga klaster IDG tahun 2020 berdasarkan kesamaan karakteristik komponen pembentuk IDG. Klaster pertama terdiri dari 3 provinsi yang memiliki nilai komponen IDG lebih rendah jika dibandingkan dengan kelompok lain, terutama dari sisi komponen keterwakilan perempuan dalam parlemen. Klaster kedua terdiri dari 5 provinsi yang memiliki nilai tinggi pada komponen keterwakilan perempuan dalam parlemen. Adapun klaster ketiga terdiri dari 26 provinsi yang memiliki nilai sedang pada ketiga komponen IDG. Hasil clustering ini dapat menjadi pertimbangan bagi pemerintah dalam menentukan kebijakan terkait pemberdayaan gender diIndonesia.

Site Fidelity and Residency of Tursiops truncatus off the Aragua Coast, Venezuela-First Records of Long Residency

This study represents the first comprehensive analysis of the residency patterns of a coastal population of bottlenose dolphin off the coast of Aragua, Venezuela, over a multi-year period. Using photo-identification, the most recent study (2019-2020) identified 56 individuals with the time between encounters from one to 344 days between the first and last sighting. Site Fidelity (SF) and Residence (RES) indices were calculated and Agglomerative Hierarchical Clustering (AHC) modeling was performed, with three patterns of residence obtained: resident (25%), semiresident (17.86%) and transient (57.14%). These results were contrasted with remodeled data from a previous study (2006-2007), showing similar patterns: resident (24.44%), semi-resident (28.89%) and transient (46.67%). Importantly, two individuals were found to have been resident over the extended period. A breeding female sighted for the first time in 2004 and again in 2020 (16 years) and the other from 2005 to 2020 (15 years). This region is an important area for marine mammals, known to support a resident reproductive population over many years, as well seabirds, sea turtles, whale sharks and fishermen. We recommend that consideration be given to designating the waters as a Marine Protected Area to safeguard the existing population and provide benefit to the surrounding marine environment.

Analisa Hasil Pengelompokan Wilayah Kejadian Non-Kebakaran Menggunakan Agglomerative Hierachical Clustering di Semarang

Abstrak−Klasterisasi merupakan metode pengelompokan dari data yang sudah diketahui label kelasnya untuk menemukan klaster baru dari hasil observasi. Dalam klasterisasi banyak metode yaitu metode terpusat, hirarki, kepadatan dan berbasis kisi, namun dalam penelitian yang dilakukan ini dipilih metode berbasis hirarki. Metode hirarki ini bekerja melakukan pengelompokan objek dengan membentuk hirarki klaster namun bukan berarti selalu digambarkan dengan hirarki dalam organsasi. Dipilihnya Agglomerative Hierarchical Clustering dimana merupakan jenis dari bawah ke atas atau biasa disebut (bottom-up) dalam metode ini objek yang akan diuji dianggap sebagai objek tunggal sebagai klaster dan lalu dilakukan iterasi untuk menemukan klaster-klaster yang lebih besar. Data yang akan digunakan adalah data non-kebakaran pada Dinas Pemadam Kebakaran Kota Semarang ynng mana akan dilakukan pengelompokan wilayah penanganan non-kebakaran. Dinas Pemadam Kebakaran melakukan penanganan bukan hanya kebakaran saja namun ada banyak hal yang sebenarnya dapat ditangani oleh petugas pemadam kebakaran, kejadian non-kebakaran ada beberapa seperti evakuasi reptil, evakuasi kucing, penyelamatan korban kecelakaan dan lain sebagainya. Dari data non-kebakaran dari 16 kecamatan di Kota Semarang pada tahun 2019 akan dilakukan uji menggunakan tiga algoritma yaitu Single Lingkage, Average Linkage dan Complete Linkage . Adapun dari algoritma Single Linkage dilakukan prosedur pemusatan dari jarak terkecil antar objek data, algoritma Average Linkage dilakukan prosedur dari jarak rata-rata objek data, sedangkan jika algoritma Complete Linkage dilakukan prosedur pemusatan dari jarak yang terbesar. Implementasi dan visualiasi dari data uji coba yang dilakukan di penilitian ini menggunakan tools WEKA 3.8.4, Wakaito Environment Analysis for Knowledge atau yang biasa dikenal dengan WEKA ini merupakan software yang menggunakan bahasa pemrograman java. Dari dataset 380 data diambil sampel 100 data untuk diuji mengunakan WEKA menggunakan metode perhtungan jarak Manhattan Distance dengan 3 cluster. Hasil dari data uji coba dapat divisualisasikan dengan visualisasi dendogram pada fitur visualize tree dan jika dilakukan visualisasi dalam bentuk grafik dapat dilakukan menggunakan fitur visualize clusters assignment.

Implementation of Agglomerative Hierarchical Clustering Based on The Classification of Food Ingredients Content of Nutritional Substances

Health is something very precious. Maintaining health can be done in many ways, one of them by keeping your diet. The correct diet will keep your immune system so that it can avoid various diseases. The proper diet will also put the body in a balanced nutrition state, which all need to be nourished. Nutrient requirements include calories, protein, fat, carbohydrates, calcium, phosphorus, iron, vitamin A, vitamin B, and vitamin C with a mass of 100 grams each. To facilitate the search for nutrients needed, then build a system that can categorize food based on its nutritional status and calculate the average value of nutrients in agglomerative hierarchical clustering using average linkage. Calculation of intermediate linkage methods produces data that has some similarities to the data sought nutrients that can be seen from its index, so precise data are in each group.

Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically creates an explanation for a single prediction by any ML model by learning a simpler interpretable model (e.g., linear classifier) around the prediction through generating simulated data around the instance by random perturbation, and obtaining feature importance through applying some form of feature selection. While LIME and similar local algorithms have gained popularity due to their simplicity, the random perturbation methods result in shifts in data and instability in the generated explanations, where for the same prediction, different explanations can be generated. These are critical issues that can prevent deployment of LIME in sensitive domains. We propose a deterministic version of LIME. Instead of random perturbation, we utilize Agglomerative Hierarchical Clustering (AHC) to group the training data together and K-Nearest Neighbour (KNN) to select the relevant cluster of the new instance that is being explained. After finding the relevant cluster, a simple model (i.e., linear model or decision tree) is trained over the selected cluster to generate the explanations. Experimental results on six public (three binary and three multi-class) and six synthetic datasets show the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME), where we quantitatively determine the stability and faithfulness of DLIME compared to LIME.

Integration of Agile Approaches in SME’s Product Development: Demand Analysis and Concept Development

In times of a complex, uncertain and dynamic world with increasingly faster product life cycles agile approaches in the early phase of product development are demanded in small and medium sized enterprises (SME’s). Despite the high demand, there is still no generally valid and need-specific solution concept for the integration of agile approaches due to different company specific requirements such as the level of maturity, experience and application purposes. Within this research, the question about the actual needs as well as the corresponding design of a concept for integrating agile approaches in product development for SME requirements is tackled. In order to identify existing challenges in the field of agile product development an empirical study with eleven mechanical engineering companies is conducted and analyzed. By using agglomerative-hierarchical clustering, three distinct types of SME’s with similar needs are structured. As a result, this research proposes a systematic procedure, enabling SME’s to be clustered by their needs and enable the integration of agile approaches through a problem-oriented roadmap with specified recommendation of actions. Enhancing the integration and application of agile approaches effectively in product development projects, the level of agility appropriate to the situation and needs must be identified and introduced. Therefore, the potential that arises from the process-oriented support of the product development teams in the early phase of innovation projects will be outlined. Keywords: agile approaches, needs analysis, small and medium sized enterprises, clustering, product development, mechanical engineering

Sensory and Olfactometry Chemometrics as Valuable Tools for Assessing Hops’ Aroma Impact on Dry-Hopped Beers: A Study with Wild Portuguese Genotypes

Sensory, olfactometry (using the sums of odour intensities for each class of compounds) and chemometric analyses were used to evaluate Portuguese wild hops’ sensory characteristics and the aroma that those hops impart to dry-hopped beer. CATA analysis and agglomerative hierarchical clustering was applied for the sensory characterization of 15 wild hops of Portuguese genotypes, clustering them in two groups: one more sulphurous, floral, and fruity, and another more earthy, resinous, floral, and non-citrus fruits. Two hops representative of each group were selected for the production of four dry-hopped beers using the same base beer style (Munich Helles). Beers were analysed by quantitative descriptive analyses and quantification of hop-derived key volatile compounds. Multivariate statistical treatment of the data was performed. Results indicate significant differences (p < 0.05) in fruity, resinous, earthy, floral, and sulphurous attributes of hops, but the dry-hopped beers only have a significant increase (p < 0.05) in fruity and spicy notes when compared with non-dry-hopped Munich-style Helles beer. Hop olfactometry explained the sensory perception that the 11 hops not used for brewing (employed as supplementary observations) are placed into the space of the odour-active compounds profile of the four hops selected for brewing. These 11 hop samples have more spiciness than fruitiness potential.

How to design robust algorithms using noisy comparison Oracle

Metric based comparison operations such as finding maximum, nearest and farthest neighbor are fundamental to studying various clustering techniques such as k -center clustering and agglomerative hierarchical clustering. These techniques crucially rely on accurate estimation of pairwise distance between records. However, computing exact features of the records, and their pairwise distances is often challenging, and sometimes not possible. We circumvent this challenge by leveraging weak supervision in the form of a comparison oracle that compares the relative distance between the queried points such as `Is point u closer to v or w closer to x ?'. However, it is possible that some queries are easier to answer than others using a comparison oracle. We capture this by introducing two different noise models called adversarial and probabilistic noise. In this paper, we study various problems that include finding maximum, nearest/farthest neighbor search under these noise models. Building upon the techniques we develop for these problems, we give robust algorithms for k -center clustering and agglomerative hierarchical clustering. We prove that our algorithms achieve good approximation guarantees with a high probability and analyze their query complexity. We evaluate the effectiveness and efficiency of our techniques empirically on various real-world datasets.