The IKBALS project: multi-modal reasoning in legal knowledge based systems

In attempting to build intelligent litigation support tools, we have moved beyond first generation, production rule legal expert systems. Our work integrates rule based and case based reasoning with intelligent information retrieval. When using the case based reasoning methodology, or in our case the specialisation of case based retrieval, we need to be aware of how to retrieve relevant experience. Our research, in the legal domain, specifies an approach to the retrieval problem which relies heavily on an extended object oriented/rule based system architecture that is supplemented with causal background information. We use a distributed agent architecture to help support the reasoning process of lawyers. Our approach to integrating rule based reasoning, case based reasoning and case based retrieval is contrasted to the CABARET and PROLEXS architectures which rely on a centralised blackboard architecture. We discuss in detail how our various cooperating agents interact, and provide examples of the system at work. The IKBALS system uses a specialised induction algorithm to induce rules from cases. These rules are then used as indices during the case based retrieval process. Because we aim to build legal support tools which can be modified to suit various domains rather than single purpose legal expert systems, we focus on principles behind developing legal knowledge based systems. The original domain chosen was theAccident Compensation Act 1989 (Victoria, Australia), which relates to the provision of benefits for employees injured at work. For various reasons, which are indicated in the paper, we changed our domain to that ofCredit Act 1984 (Victoria, Australia). This Act regulates the provision of loans by financial institutions. The rule based part of our system which provides advice on the Credit Act has been commercially developed in conjunction with a legal firm. We indicate how this work has lead to the development of a methodology for constructing rule based legal knowledge based systems. We explain the process of integrating this existing commercial rule based system with the case base reasoning and retrieval architecture.

Reasoning paradigms in legal decision support systems

In this paper we discuss the strengths and weaknesses of a range of artificial intelligence approaches used in legal domains. Symbolic reasoning systems which rely on deductive, inductive and analogical reasoning are described and reviewed. The role of statistical reasoning in law is examined, and the use of neural networks analysed. There is discussion of architectures for, and examples of, systems which combine a number of these reasoning strategies. We conclude that to build intelligent legal decision support systems requires a range of reasoning strategies.

Near knowledge : inductive learning systems in law

Induction is an interesting model of legal reasoning, since it provides a method of capturing initial states of legal principles and rules, and adjusting these principles and rules over time as the law changes. In this article I explain how Artificial Intelligence-based inductive learning algorithms work, and show how they have been used in law to model legal domains. I identify some problems with implementations undertaken in law to date, and create a taxonomy of appropriate cases to use in legal inductive inferencing systems. I suggest that inductive learning algorithms have potential in modeling law, but that the artificial intelligence implementations to date are problematic. I argue that induction should be further investigated, since it has the potential to be an extremely useful mechanism for understanding legal domains.

Deductive, inductive and analogical reasoning in legal decision support systems

In this paper we provide an overview of a number of fundamental reasoning formalisms in artificial intelligence which can and have been used in modelling legal reasoning. We describe deduction, induction and analogical reasoning formalisms, and show how they can be used separately to model legal reasoning. We argue that these formalisms can be used together to model legal reasoning more accurately, and describe a number of attempts to integrate the approaches.

A hybrid maximum power point tracking for partially shaded photovoltaic systems in the tropics

Partial shading and rapidly changing irradiance conditions significantly impact on the performance of photovoltaic (PV) systems. These impacts are particularly severe in tropical regions where the climatic conditions result in very large and rapid changes in irradiance. In this paper, a hybrid maximum power point (MPP) tracking (MPPT) technique for PV systems operating under partially shaded conditions witapid irradiance change is proposed. It combines a conventional MPPT and an artificial neural network (ANN)-based MPPT. A low cost method is proposed to predict the global MPP region when expensive irradiance sensors are not available or are not justifiable for cost reasons. It samples the operating point on the stairs of I–V curve and uses a combination of the measured current value at each stair to predict the global MPP region. The conventional MPPT is then used to search within the classified region to get the global MPP. The effectiveness of the proposed MPPT is demonstrated using both simulations and an experimental setup. Experimental comparisons with four existing MPPTs are performed. The results show that the proposed MPPT produces more energy than the other techniques and can effectively track the global MPP with a fast tracking speed under various shading patterns.

Human vs. machine : identification of bat species from their echolocation calls by humans and by artificial neural networks

Automated remote ultrasound detectors allow large amounts of data on bat presence and activity to be collected. Processing of such data involves identifying bat species from their echolocation calls. Automated species identification has the potential to provide more consistent, predictable, and potentially higher levels of accuracy than identification by humans. In contrast, identification by humans permits flexibility and intelligence in identification, as well as the incorporation of features and patterns that may be difficult to quantify. We compared humans with artificial neural networks (ANNs) in their ability to classify short recordings of bat echolocation calls of variable signal to noise ratios; these sequences are typical of those obtained from remote automated recording systems that are often used in large-scale ecological studies. We presented 45 recordings (1–4 calls) produced by known species of bats to ANNs and to 26 human participants with 1 month to 23 years of experience in acoustic identification of bats. Humans correctly classified 86% of recordings to genus and 56% to species; ANNs correctly identified 92% and 62%, respectively. There was no significant difference between the performance of ANNs and that of humans, but ANNs performed better than about 75% of humans. There was little relationship between the experience of the human participants and their classification rate. However, humans with <1 year of experience performed worse than others. Currently, identification of bat echolocation calls by humans is suitable for ecological research, after careful consideration of biases. However, improvements to ANNs and the data that they are trained on may in future increase their performance to beyond those demonstrated by humans.

Design, construction and evaluation of systems to predict risk in obstetrics

We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy. We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy.

An agent-based approach to immune modelling

This study focuses on trying to understand why the range of experience with respect to HIV infection is so diverse, especially as regards to the latency period. The challenge is to determine what assumptions can be made about the nature of the experience of antigenic invasion and diversity that can be modelled, tested and argued plausibly. To investigate this, an agent-based approach is used to extract high-level behaviour which cannot be described analytically from the set of interaction rules at the cellular level. A prototype model encompasses local variation in baseline properties contributing to the individual disease experience and is included in a network which mimics the chain of lymphatic nodes. Dealing with massively multi-agent systems requires major computational efforts. However, parallelisation methods are a natural consequence and advantage of the multi-agent approach. These are implemented using the MPI library.

Prediction of GMA welding characteristic parameter by artificial neural network system

Nowadays, demand for automated Gas metal arc welding (GMAW) is growing and consequently need for intelligent systems is increased to ensure the accuracy of the procedure. To date, welding pool geometry has been the most used factor in quality assessment of intelligent welding systems. But, it has recently been found that Mahalanobis Distance (MD) not only can be used for this purpose but also is more efficient. In the present paper, Artificial Neural Networks (ANN) has been used for prediction of MD parameter. However, advantages and disadvantages of other methods have been discussed. The Levenberg–Marquardt algorithm was found to be the most effective algorithm for GMAW process. It is known that the number of neurons plays an important role in optimal network design. In this work, using trial and error method, it has been found that 30 is the optimal number of neurons. The model has been investigated with different number of layers in Multilayer Perceptron (MLP) architecture and has been shown that for the aim of this work the optimal result is obtained when using MLP with one layer. Robustness of the system has been evaluated by adding noise into the input data and studying the effect of the noise in prediction capability of the network. The experiments for this study were conducted in an automated GMAW setup that was integrated with data acquisition system and prepared in a laboratory for welding of steel plate with 12 mm in thickness. The accuracy of the network was evaluated by Root Mean Squared (RMS) error between the measured and the estimated values. The low error value (about 0.008) reflects the good accuracy of the model. Also the comparison of the predicted results by ANN and the test data set showed very good agreement that reveals the predictive power of the model. Therefore, the ANN model offered in here for GMA welding process can be used effectively for prediction goals.

Do-Rank: DCG optimization for learning-to-rank in tag-based item recommendation systems

Discounted Cumulative Gain (DCG) is a well-known ranking evaluation measure for models built with multiple relevance graded data. By handling tagging data used in recommendation systems as an ordinal relevance set of {negative,null,positive}, we propose to build a DCG based recommendation model. We present an efficient and novel learning-to-rank method by optimizing DCG for a recommendation model using the tagging data interpretation scheme. Evaluating the proposed method on real-world datasets, we demonstrate that the method is scalable and outperforms the benchmarking methods by generating a quality top-N item recommendation list.

Fuzzy-DL perception for multi-robot systems

For future planetary robot missions, multi-robot-systems can be considered as a suitable platform to perform space mission faster and more reliable. In heterogeneous robot teams, each robot can have different abilities and sensor equipment. In this paper we describe a lunar demonstration scenario where a team of mobile robots explores an unknown area and identifies a set of objects belonging to a lunar infrastructure. Our robot team consists of two exploring scout robots and a mobile manipulator. The mission goal is to locate the objects within a certain area, to identify the objects, and to transport the objects to a base station. The robots have a different sensor setup and different capabilities. In order to classify parts of the lunar infrastructure, the robots have to share the knowledge about the objects. Based on the different sensing capabilities, several information modalities have to be shared and combined by the robots. In this work we propose an approach using spatial features and a fuzzy logic based reasoning for distributed object classification.

Altered nociceptive, endocrine, and dorsal horn neuron responses in rats following a neonatal immune challenge

Summary The neonatal period is characterized by significant plasticity where the immune, endocrine, and nociceptive systems undergo fine-tuning and maturation. Painful experiences during this period can result in long-term alterations in the neurocircuitry underlying nociception, including increased sensitivity to mechanical or thermal stimuli. Less is known about the impact of neonatal exposure to mild inflammatory stimuli, such as lipopolysaccharide (LPS), on subsequent inflammatory pain responses. Here we examine the impact of neonatal LPS exposure on inflammatory pain sensitivity and HPA axis activity during the first three postnatal weeks. Wistar rats were injected with LPS (0.05 mg/kg IP, Salmonella enteritidis) or saline on postnatal days (PNDs) 3 and 5 and later subjected to the formalin test at PNDs 7, 13, and 22. One hour after formalin injection, blood was collected to assess corticosterone responses. Transverse spinal cord slices were also prepared for whole-cell patch clamp recording from lumbar superficial dorsal horn neurons (SDH). Brains were obtained at PND 22 and the hypothalamus was isolated to measure glucocorticoid (GR) and mineralocorticoid receptor (MR) transcript expression using qRT-PCR. Behavioural analyses indicate that at PND 7, no significant differences were observed between saline- or LPS-challenged rats. At PND 13, LPS-challenged rats exhibited enhanced licking (p < .01), and at PND 22, increased flinching in response to formalin injection (p < .05). LPS-challenged rats also displayed increased plasma corticosterone at PND 7 and PND 22 (p < .001) but not at PND 13 following formalin administration. Furthermore, at PND 22 neonatal LPS exposure induced decreased levels of GR mRNA and increased levels of MR mRNA in the hypothalamus. The intrinsic properties of SDH neurons were similar at PND 7 and PND 13. However, at PND 22, ipsilateral SDH neurons in LPS-challenged rats had a lower input resistance compared to their saline-challenged counterparts (p < .05). These data suggest neonatal LPS exposure produces developmentally regulated changes in formalin-induced behavioural responses, corticosterone levels, and dorsal horn neuron properties following noxious stimulation later in life. These findings highlight the importance of immune activation during the neonatal period in shaping pain sensitivity later in life. This programming involves both spinal cord neurons and the HPA axis.

Implementation of Art1 and Art2 Artificial Neural Networks on Ring and Mesh Architectures

The Artificial Neural Networks (ANNs) are being used to solve a variety of problems in pattern recognition, robotic control, VLSI CAD and other areas. In most of these applications, a speedy response from the ANNs is imperative. However, ANNs comprise a large number of artificial neurons, and a massive interconnection network among them. Hence, implementation of these ANNs involves execution of computer-intensive operations. The usage of multiprocessor systems therefore becomes necessary. In this article, we have presented the implementation of ART1 and ART2 ANNs on ring and mesh architectures. The overall system design and implementation aspects are presented. The performance of the algorithm on ring, 2-dimensional mesh and n-dimensional mesh topologies is presented. The parallel algorithm presented for implementation of ART1 is not specific to any particular architecture. The parallel algorithm for ARTE is more suitable for a ring architecture.