Extension schemes for the Alignment Model of English-Malayalam Statistical Machine Translator

In Statistical Machine Translation from English to Malayalam, an unseen English sentence is translated into its equivalent Malayalam sentence using statistical models. A parallel corpus of English-Malayalam is used in the training phase. Word to word alignments has to be set among the sentence pairs of the source and target language before subjecting them for training. This paper deals with certain techniques which can be adopted for improving the alignment model of SMT. Methods to incorporate the parts of speech information into the bilingual corpus has resulted in eliminating many of the insignificant alignments. Also identifying the name entities and cognates present in the sentence pairs has proved to be advantageous while setting up the alignments. Presence of Malayalam words with predictable translations has also contributed in reducing the insignificant alignments. Moreover, reduction of the unwanted alignments has brought in better training results. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics.

Techniques to Improve the word alignments in Statistical Machine Translation from English to Malayalam

In Statistical Machine Translation from English to Malayalam, an unseen English sentence is translated into its equivalent Malayalam translation using statistical models like translation model, language model and a decoder. A parallel corpus of English-Malayalam is used in the training phase. Word to word alignments has to be set up among the sentence pairs of the source and target language before subjecting them for training. This paper is deals with the techniques which can be adopted for improving the alignment model of SMT. Incorporating the parts of speech information into the bilingual corpus has eliminated many of the insignificant alignments. Also identifying the name entities and cognates present in the sentence pairs has proved to be advantageous while setting up the alignments. Moreover, reduction of the unwanted alignments has brought in better training results. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics

Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier

This paper presents the application of wavelet processing in the domain of handwritten character recognition. To attain high recognition rate, robust feature extractors and powerful classifiers that are invariant to degree of variability of human writing are needed. The proposed scheme consists of two stages: a feature extraction stage, which is based on Haar wavelet transform and a classification stage that uses support vector machine classifier. Experimental results show that the proposed method is effective

Using Neural Network Classifier Support Vector Machine Regression for the prediction of Melting Point of Drug – like compounds

In our study we use a kernel based classification technique, Support Vector Machine Regression for predicting the Melting Point of Drug – like compounds in terms of Topological Descriptors, Topological Charge Indices, Connectivity Indices and 2D Auto Correlations. The Machine Learning model was designed, trained and tested using a dataset of 100 compounds and it was found that an SVMReg model with RBF Kernel could predict the Melting Point with a mean absolute error 15.5854 and Root Mean Squared Error 19.7576

Uncover the Concealed Link: Gender & Ethnicity-Divided Local Knowledge on the Agro-Ecosystem of a Forest Margin

This research is a study about knowledge interface that aims to analyse knowledge discontinuities, the dynamic and emergent characters of struggles and interactions within gender system and ethnicity differences. The cacao boom phenomenon in Central Sulawesi is the main context for a changing of social relations of production, especially when the mode of production has shifted or is still underway from subsistence to petty commodity production. This agrarian change is not only about a change of relationship and practice, but, as my previous research has shown, also about the shift of knowledge domination, because knowledge construes social practice in a dialectical process. Agroecological knowledge is accumulated through interaction, practice and experience. At the same time the knowledge gained from new practices and experiences changes mode of interaction, so such processes provide the arena where an interface of knowledge is manifested. In the process of agro-ecological knowledge interface, gender and ethnic group interactions materialise in the decision-making of production and resource allocation at the household and community level. At this point, power/knowledge is interplayed to gain authority in decision-making. When authority dominates, power encounters resistance, whereas the dominant power and its resistance are aimed to ensure socio-economic security. Eventually, the process of struggle can be identified through the pattern of resource utilisation as a realisation of production decision-making. Such processes are varied from one community to another, and therefore, it shows uniqueness and commonalities, especially when it is placed in a context of shifting mode of production. The focus is placed on actors: men and women in their institutional and cultural setting, including the role of development agents. The inquiry is informed by 4 major questions: 1) How do women and men acquire, disseminate, and utilise their agro ecological knowledge, specifically in rice farming as a subsistence commodity, as well as in cacao farming as a petty commodity? How and why do such mechanisms construct different knowledge domains between two genders? How does the knowledge mechanism apply in different ethnics? What are the implications for gender and ethnicity based relation of production? ; 2) Using the concept of valued knowledge in a shifting mode of production context: is there any knowledge that dominates others? How does the process of domination occur and why? Is there any form of struggle, strategies, negotiation, and compromise over this domination? How do these processes take place at a household as well as community level? How does it relate to production decision-making? ; 3) Putting the previous questions in two communities with a different point of arrival on a path of agricultural commercialisation, how do the processes of struggle vary? What are the bases of the commonalities and peculiarities in both communities?; 4) How the decisions of production affect rice field - cacao plantation - forest utilisation in the two villages? How does that triangle of resource use reflect the constellation of local knowledge in those two communities? What is the implication of this knowledge constellation for the cacao-rice-forest agroecosystem in the forest margin area? Employing a qualitative approach as the main method of inquiry, indepth and dialogic interviews, participant observer role, and document review are used to gather information. A small survey and children’s writing competition are supplementary to this data collection method. The later two methods are aimed to give wider information on household decision making and perception toward the forest. It was found that local knowledge, particularly knowledge pertaining to rice-forest-cacao agroecology is divided according to gender and ethnicity. This constellation places a process of decision-making as ‘the arena of interface’ between feminine and masculine knowledge, as well as between dominant and less dominant ethnic groups. Transition from subsistence to a commercial mode of production is a context that frames a process where knowledge about cacao commodity is valued higher than rice. Market mechanism, as an external power, defines valued knowledge. Valued knowledge defines the dominant knowledge holder, and decision. Therefore, cacao cultivation becomes a dominant practice. Its existence sacrifices the presence of rice field and the forest. Knowledge about rice production and forest ecosystem exist, but is less valued. So it is unable to challenge the domination of cacao. Various forms of struggles - within gender an ethnicity context - to resist cacao domination are an expression of unequal knowledge possession. Knowledge inequality implies to unequal access to withdraw benefit from market valued crop. When unequal knowledge fails to construct a negotiated field or struggles fail to reveal ‘marginal’ decision, e.g. intensification instead of cacao expansion to the forest, interface only produces divergence. Gender and ethnicity divided knowledge is unabridged, since negotiation is unable to produce new knowledge that accommodates both interests. Rice is loaded by ecological interest to conserve the forest, while cacao is driven by economic interest to increase welfare status. The implication of this unmediated dominant knowledge of cacao production is the construction of access; access to the forest, mainly to withdraw its economic benefit by eliminating its ecological benefit. Then, access to cacao as the social relationship of production to acquire cacao knowledge; lastly, access to defend sustainable benefit from cacao by expansion. ‘Socio-economic Security’ is defined by Access. The convergence of rice and cacao knowledge, however, should be made possible across gender and ethnicity, not only for the sake of forest conservation as the insurance of ecological security, but also for community’s socio-economic security. The convergence might be found in a range of alternative ways to conduct cacao sustainable production, from agroforestry system to intensification.

Shifting cultivation and forest resources in Nagaland, N.-E. India

Die vorliegende Studie befasst sich mit der Ressourcennachhaltigkeit der traditionellen, auf Wanderfeldbau beruhenden Subsistenzwirtschaft in zwei Dörfern (Hongphoy und Minyakshu) in Nagaland im Nordosten Indiens. Hierbei werden die Cerealien Produktion, der Feuerholz Konsum und auch die Folgen der intensivierten Bewirtschaftung (Forstdegradation und Bodenverarmung) im Hinblick auf das Bevölkerungswachstum diskutiert. Während das traditionelle System des Wanderfeldbaus (Jhum) seit Jahrzehnten die Bedürfnisse der ehemals kopfjagenden Stämme Nagalands erfüllte, ergab unsere Studie durch Interviews und Feldaufnahmen in 2004 und 2005, dass die steigende Nachfrage einer wachsenden Bevölkerung nach Cerealien und Feuerholz als wichtigste Ressourcen der Subsistenzwirtschaft zu einer verkürzten Brachezeit und letztlich der Degradation von Naturressourcen geführt hat: Pro Hektar Ernten sind reduziert und der Zuwachs der Holzvorräte auf den Feldern kann durch die verkürzten Bracheperioden nicht mehr die Feuerholz Nachfrage decken. Eine Nahrungsmittelknappheit wurde durch die Gegenüberstellung des Energiebedarfs einer Person und die jährlichen pro-Kopf Erntemengen und unter Berücksichtigung des Zukaufs von Reis reflektiert: In Hongphoy ergab dies ein Defizit auf Dorfebene von 130 Tonnen Reis, in Minyakshu von 480 Tonnen, die nicht durch Ernten gedeckt werden konnten. Diese Nahrungsmittelknappheit erweist sich vor allem vor dem Hintergrund eines Bevölkerungswachstums von 6.7% und marginalen Einkünften als problematisch. Für fünf verschiedene Waldformationen (zwei Brachewälder, zwei Dorfwälder und ein Naturwald) wurden die unterschiedliche Artenzusammensetzung (Diversität) und Bestandesvolumina durch Forstinventuren beschrieben. Der dem Bestandesvolumen der Brachewälder gegenübergestellte pro-Kopf Feuerholz Bedarf ergab ein jährliches Defizit von 1,81m³ in Hongphoy und 0.05m³ in Minyakshu. Der Unterschied dieses Defizits zwischen beiden Dörfern wurde in einer abweichenden Bestandesstruktur (Dominanz der N2 fixierenden Baumart Alnus nepalensis in den Brachewäldern Minyakshus) begründet. Über den erhobenen Feuerholzbedarf wurde ein theoretischer pro-Kopf Flächenbedarf an Brachewald errechnet, der nötig wäre um den gesamten Feuerholz Bedarf innerhalb des Wanderfeldbau Systems zu decken. Das daraus resultierende Defizit wurde mit den Feuerholzvolumina der Dorfwälder und des verbliebenen Naturwalds gegenüber gestellt. Hieraus ergibt sich die Bedeutung der Feuerholzernte und des Wanderfeldbau als Ursache für die fortschreitende Entwaldung und Forstdegradation in Nagaland. Mit Hilfe dieser Informationen und aktuellen Angaben zum Bevölkerungswachstum werden die Ergebnisse anhand einschlägiger Literatur diskutiert und letztendlich die Nachhaltigkeit und Tragfähigkeit des Wanderfeldbau Systems in dieser Region bestimmt. Mögliche Verbesserungsstrategien um der zunehmenden Ressourcendegradation zu begegnen, werden andiskutiert.

Evaluation of water retention capacity and flood control function of the forest catchment

This research quantitatively evaluates the water retention capacity and flood control function of the forest catchments by using hydrological data of the large flood events which happened after the serious droughts. The objective sites are the Oodo Dam and the Sameura Dam catchments in Japan. The kinematic wave model, which considers saturated and unsaturated sub-surface soil zones, is used for the rainfall-runoff analysis. The result shows that possible storage volume of the Oodo Dam catchment is 162.26 MCM in 2005, while that of Samerua is 102.83 MCM in 2005 and 102.64 MCM in 2007. Flood control function of the Oodo Dam catchment is 173 mm in water depth in 2005, while the Sameura Dam catchment 114 mm in 2005 and 126 mm in 2007. This indicates that the Oodo Dam catchment has more than twice as big water capacity as its capacity (78.4 mm), while the Sameura Dam catchment has about one-fifth of the its storage capacity (693 mm).

Adaptive Real-time Anomaly-based Intrusion Detection using Data Mining and Machine Learning Techniques

Die zunehmende Vernetzung der Informations- und Kommunikationssysteme führt zu einer weiteren Erhöhung der Komplexität und damit auch zu einer weiteren Zunahme von Sicherheitslücken. Klassische Schutzmechanismen wie Firewall-Systeme und Anti-Malware-Lösungen bieten schon lange keinen Schutz mehr vor Eindringversuchen in IT-Infrastrukturen. Als ein sehr wirkungsvolles Instrument zum Schutz gegenüber Cyber-Attacken haben sich hierbei die Intrusion Detection Systeme (IDS) etabliert. Solche Systeme sammeln und analysieren Informationen von Netzwerkkomponenten und Rechnern, um ungewöhnliches Verhalten und Sicherheitsverletzungen automatisiert festzustellen. Während signatur-basierte Ansätze nur bereits bekannte Angriffsmuster detektieren können, sind anomalie-basierte IDS auch in der Lage, neue bisher unbekannte Angriffe (Zero-Day-Attacks) frühzeitig zu erkennen. Das Kernproblem von Intrusion Detection Systeme besteht jedoch in der optimalen Verarbeitung der gewaltigen Netzdaten und der Entwicklung eines in Echtzeit arbeitenden adaptiven Erkennungsmodells. Um diese Herausforderungen lösen zu können, stellt diese Dissertation ein Framework bereit, das aus zwei Hauptteilen besteht. Der erste Teil, OptiFilter genannt, verwendet ein dynamisches "Queuing Concept", um die zahlreich anfallenden Netzdaten weiter zu verarbeiten, baut fortlaufend Netzverbindungen auf, und exportiert strukturierte Input-Daten für das IDS. Den zweiten Teil stellt ein adaptiver Klassifikator dar, der ein Klassifikator-Modell basierend auf "Enhanced Growing Hierarchical Self Organizing Map" (EGHSOM), ein Modell für Netzwerk Normalzustand (NNB) und ein "Update Model" umfasst. In dem OptiFilter werden Tcpdump und SNMP traps benutzt, um die Netzwerkpakete und Hostereignisse fortlaufend zu aggregieren. Diese aggregierten Netzwerkpackete und Hostereignisse werden weiter analysiert und in Verbindungsvektoren umgewandelt. Zur Verbesserung der Erkennungsrate des adaptiven Klassifikators wird das künstliche neuronale Netz GHSOM intensiv untersucht und wesentlich weiterentwickelt. In dieser Dissertation werden unterschiedliche Ansätze vorgeschlagen und diskutiert. So wird eine classification-confidence margin threshold definiert, um die unbekannten bösartigen Verbindungen aufzudecken, die Stabilität der Wachstumstopologie durch neuartige Ansätze für die Initialisierung der Gewichtvektoren und durch die Stärkung der Winner Neuronen erhöht, und ein selbst-adaptives Verfahren eingeführt, um das Modell ständig aktualisieren zu können. Darüber hinaus besteht die Hauptaufgabe des NNB-Modells in der weiteren Untersuchung der erkannten unbekannten Verbindungen von der EGHSOM und der Überprüfung, ob sie normal sind. Jedoch, ändern sich die Netzverkehrsdaten wegen des Concept drif Phänomens ständig, was in Echtzeit zur Erzeugung nicht stationärer Netzdaten führt. Dieses Phänomen wird von dem Update-Modell besser kontrolliert. Das EGHSOM-Modell kann die neuen Anomalien effektiv erkennen und das NNB-Model passt die Änderungen in Netzdaten optimal an. Bei den experimentellen Untersuchungen hat das Framework erfolgversprechende Ergebnisse gezeigt. Im ersten Experiment wurde das Framework in Offline-Betriebsmodus evaluiert. Der OptiFilter wurde mit offline-, synthetischen- und realistischen Daten ausgewertet. Der adaptive Klassifikator wurde mit dem 10-Fold Cross Validation Verfahren evaluiert, um dessen Genauigkeit abzuschätzen. Im zweiten Experiment wurde das Framework auf einer 1 bis 10 GB Netzwerkstrecke installiert und im Online-Betriebsmodus in Echtzeit ausgewertet. Der OptiFilter hat erfolgreich die gewaltige Menge von Netzdaten in die strukturierten Verbindungsvektoren umgewandelt und der adaptive Klassifikator hat sie präzise klassifiziert. Die Vergleichsstudie zwischen dem entwickelten Framework und anderen bekannten IDS-Ansätzen zeigt, dass der vorgeschlagene IDSFramework alle anderen Ansätze übertrifft. Dies lässt sich auf folgende Kernpunkte zurückführen: Bearbeitung der gesammelten Netzdaten, Erreichung der besten Performanz (wie die Gesamtgenauigkeit), Detektieren unbekannter Verbindungen und Entwicklung des in Echtzeit arbeitenden Erkennungsmodells von Eindringversuchen.

Transaction costs of farmers’ participation in forest management: Policy implications of payments for environmental services schemes in Vietnam

Recent research on payments for environmental services (PES) has observed that high transaction costs (TCs) are incurred through the implementation of PES schemes and farmer participation. TCs incurred by households are considered to be an obstacle to the participation in and efficiency of PES policies. This study aims to understand transactions related to previous forest plantation programmes and to estimate the actual TCs incurred by farmers who participated in these programmes in a mountainous area of northwestern Vietnam. In addition, this study examines determinants of households’ TCs to test the hypothesis of whether the amount of TCs varies according to household characteristics. Results show that average TCs are not likely to be a constraint for participation since they are about 200,000 VND (USD 10) per household per contract, which is equivalent to one person’s average earnings for about two days of labour. However, TCs amount to more than one-third of the programmes’ benefits, which is relatively high compared to PES programmes in developed countries. This implies that rather than aiming to reduce TCs, an appropriate agenda for policy improvement is to balance the level of TCs with PES programme benefits to enhance the overall attractiveness of afforestation programmes for smallholder farmers. Regression analysis reveals that education, gender and perception towards PES programmes have significant effects on the magnitude of TCs. The analyses also points out the importance of local conditions on the level of TCs, with some unexpected results.

UNITRAN: A Principle-Based Approach to Machine Translation

Machine translation has been a particularly difficult problem in the area of Natural Language Processing for over two decades. Early approaches to translation failed since interaction effects of complex phenomena in part made translation appear to be unmanageable. Later approaches to the problem have succeeded (although only bilingually), but are based on many language-specific rules of a context-free nature. This report presents an alternative approach to natural language translation that relies on principle-based descriptions of grammar rather than rule-oriented descriptions. The model that has been constructed is based on abstract principles as developed by Chomsky (1981) and several other researchers working within the "Government and Binding" (GB) framework. Thus, the grammar is viewed as a modular system of principles rather than a large set of ad hoc language-specific rules.

Dataflow Computation for the J-Machine

The dataflow model of computation exposes and exploits parallelism in programs without requiring programmer annotation; however, instruction- level dataflow is too fine-grained to be efficient on general-purpose processors. A popular solution is to develop a "hybrid'' model of computation where regions of dataflow graphs are combined into sequential blocks of code. I have implemented such a system to allow the J-Machine to run Id programs, leaving exposed a high amount of parallelism --- such as among loop iterations. I describe this system and provide an analysis of its strengths and weaknesses and those of the J-Machine, along with ideas for improvement.

A Virtual Machine for a Type-omega Denotational Proof Language

In this thesis, I designed and implemented a virtual machine (VM) for a monomorphic variant of Athena, a type-omega denotational proof language (DPL). This machine attempts to maintain the minimum state required to evaluate Athena phrases. This thesis also includes the design and implementation of a compiler for monomorphic Athena that compiles to the VM. Finally, it includes details on my implementation of a read-eval-print loop that glues together the VM core and the compiler to provide a full, user-accessible interface to monomorphic Athena. The Athena VM provides the same basis for DPLs that the SECD machine does for pure, functional programming and the Warren Abstract Machine does for Prolog.

Improving Multiclass Text Classification with the Support Vector Machine

We compare Naive Bayes and Support Vector Machines on the task of multiclass text classification. Using a variety of approaches to combine the underlying binary classifiers, we find that SVMs substantially outperform Naive Bayes. We present full multiclass results on two well-known text data sets, including the lowest error to date on both data sets. We develop a new indicator of binary performance to show that the SVM's lower multiclass error is a result of its improved binary performance. Furthermore, we demonstrate and explore the surprising result that one-vs-all classification performs favorably compared to other approaches even though it has no error-correcting properties.

On the Noise Model of Support Vector Machine Regression

Support Vector Machines Regression (SVMR) is a regression technique which has been recently introduced by V. Vapnik and his collaborators (Vapnik, 1995; Vapnik, Golowich and Smola, 1996). In SVMR the goodness of fit is measured not by the usual quadratic loss function (the mean square error), but by a different loss function called Vapnik"s $epsilon$- insensitive loss function, which is similar to the "robust" loss functions introduced by Huber (Huber, 1981). The quadratic loss function is well justified under the assumption of Gaussian additive noise. However, the noise model underlying the choice of Vapnik's loss function is less clear. In this paper the use of Vapnik's loss function is shown to be equivalent to a model of additive and Gaussian noise, where the variance and mean of the Gaussian are random variables. The probability distributions for the variance and mean will be stated explicitly. While this work is presented in the framework of SVMR, it can be extended to justify non-quadratic loss functions in any Maximum Likelihood or Maximum A Posteriori approach. It applies not only to Vapnik's loss function, but to a much broader class of loss functions.

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos