Improved particle swarm optimization-based artificial neural network for rainfall-runoff modeling

This paper presents the application of an improved particle swarm optimization (PSO) technique for training an artificial neural network (ANN) to predict water levels for the Heshui watershed, China. Daily values of rainfall and water levels from 1988 to 2000 were first analyzed using ANNs trained with the conjugate-gradient, gradient descent and Levenberg-Marquardt neural network (LM-NN) algorithms. The best results were obtained from LM-NN and these results were then compared with those from PSO-based ANNs, including conventional PSO neural network (CPSONN) and improved PSO neural network (IPSONN) with passive congregation. The IPSONN algorithm improves PSO convergence by using the selfish herd concept in swarm behavior. Our results show that the PSO-based ANNs performed better than LM-NN. For models run using a single parameter (rainfall) as input, the root mean square error (RMSE) of the testing dataset for IPSONN was the lowest (0.152 m) compared to those for CPSONN (0.161 m) and LM-NN (0.205 m). For multi-parameter (rainfall and water level) inputs, the RMSE of the testing dataset for IPSONN was also the lowest (0.089 m) compared to those for CPSONN (0.105 m) and LM-NN (0.145 m). The results also indicate that the LM-NN model performed poorly in predicting the low and peak water levels, in comparison to the PSO-based ANNs. Moreover, the IPSONN model was superior to CPSONN in predicting extreme water levels. Lastly, IPSONN had a quicker convergence rate compared to CPSONN.

An ontology-driven topic mapping approach to multi-level management of e-learning resources

An appropriate use of various pedagogical strategies is fundamental for the effective transfer of knowledge in a flourishing e-learning environment. The resultant information superfluity, however, needs to be tackled for developing sustainable e-learning. This necessitates an effective representation and intelligent access to learning resources. Topic maps address these problems of representation and retrieval of information in a distributed environment. The former aspect is particularly relevant where the subject domain is complex and the later aspect is important where the amount of resources is abundant but not easily accessible. Conversely, effective presentation of learning resources based on various pedagogical strategies along with global capturing and authentication of learning resources are an intrinsic part of effective management of learning resources. Towards fulfilling this objective, this paper proposes a multi-level ontology-driven topic mapping approach to facilitate an effective visualization, classification and global authoring of learning resources in e-learning.

Security protocols for EPC class-1 Gen-2 RFID multi-tag systems

The objective of the research is to develop security protocols for EPC C1G2 RFID Passive Tags in the areas of ownership transfer and grouping proof.

Evolutionary optimization: a big data perspective

Stochastic search techniques such as evolutionary algorithms (EA) are known to be better explorer of search space as compared to conventional techniques including deterministic methods. However, in the era of big data like most other search methods and learning algorithms, suitability of evolutionary algorithms is naturally questioned. Big data pose new computational challenges including very high dimensionality and sparseness of data. Evolutionary algorithms' superior exploration skills should make them promising candidates for handling optimization problems involving big data. High dimensional problems introduce added complexity to the search space. However, EAs need to be enhanced to ensure that majority of the potential winner solutions gets the chance to survive and mature. In this paper we present an evolutionary algorithm with enhanced ability to deal with the problems of high dimensionality and sparseness of data. In addition to an informed exploration of the solution space, this technique balances exploration and exploitation using a hierarchical multi-population approach. The proposed model uses informed genetic operators to introduce diversity by expanding the scope of search process at the expense of redundant less promising members of the population. Next phase of the algorithm attempts to deal with the problem of high dimensionality by ensuring broader and more exhaustive search and preventing premature death of potential solutions. To achieve this, in addition to the above exploration controlling mechanism, a multi-tier hierarchical architecture is employed, where, in separate layers, the less fit isolated individuals evolve in dynamic sub-populations that coexist alongside the original or main population. Evaluation of the proposed technique on well known benchmark problems ascertains its superior performance. The algorithm has also been successfully applied to a real world problem of financial portfolio management. Although the proposed method cannot be considered big data-ready, it is certainly a move in the right direction.

Maximum power point tracking of partial shaded photovoltaic array using an evolutionary algorithm: a particle swarm optimization technique

 Partial shading is one of the unavoidable complications in the field of solar power generation. Although the most common approach in increasing a photovoltaic (PV) array’s efficiency has always been to introduce a bypass diode to the said array, this poses another problem in the form of multi-peaks curves whenever the modules are partially shaded. To further complicate matters, most conventional Maximum Power Point Tracking methods develop errors under certain circumstances (for example, they detect the local Maximum Power Point (MPP) instead of the global MPP) and reduce the efficiency of PV systems even further. Presently, much research has been undertaken to improve upon them. This study aims to employ an evolutionary algorithm technique, also known as particle swarm optimization, in MPP detection. VC 2014 Author(s).

Intelligent cuckoo search optimized traffic signal controllers for multi-intersection network

Traffic congestion in urban roads is one of the biggest challenges of 21 century. Despite a myriad of research work in the last two decades, optimization of traffic signals in network level is still an open research problem. This paper for the first time employs advanced cuckoo search optimization algorithm for optimally tuning parameters of intelligent controllers. Neural Network (NN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are two intelligent controllers implemented in this study. For the sake of comparison, we also implement Q-learning and fixed-time controllers as benchmarks. Comprehensive simulation scenarios are designed and executed for a traffic network composed of nine four-way intersections. Obtained results for a few scenarios demonstrate the optimality of trained intelligent controllers using the cuckoo search method. The average performance of NN, ANFIS, and Q-learning controllers against the fixed-time controller are 44%, 39%, and 35%, respectively.

Towards the optimization of performance of Atlantic salmon reared at different water temperatures via the manipulation of dietary ARA/EPA ratio

In recent years, aquaculture has been facing a series of new issues, including the necessary replacement of fish oil and fish meal because of their limited supply and sub-optimal water temperature conditions. Higher water temperatures are increasingly encountered as the result of climate change related phenomena and/or the practice of farming of species in areas with environmental characteristics outside their optimal physiological range, such as the case of Atlantic salmon (. Salmo salar) farming in Australia during the summer season. Previous studies in teleost fish have shown that when fish are exposed at higher environmental temperatures, fish had a preferential increased dietary intake for arachidonic acid (20:4n - 6, ARA). This observation suggests that, given the several metabolic roles of ARA, its dietary provision may play an important role in fish for adapting at sub-optimal high water temperatures. The objective of this study was therefore to evaluate the effects of different dietary ARA/EPA ratios in juvenile Atlantic salmon as affected by time of exposition to the diet and water temperatures, with particular focus to fish performance and possible resulting modifications of tissue fatty acid composition. The study showed that independently from dietary treatments, fish held at the higher temperatures had an increased ARA accumulation, primarily in the liver and this ARA accumulation increased over time. It was also shown that the combined dietary inclusion of ARA and EPA significantly improved fish performance, compared with diets either richer in ARA or EPA. A general trend toward higher content of n - 3 LC-PUFA at lower temperatures was also quite clear, especially in the liver. Therefore, and assuming that the trends in tissue fatty acid composition could be taken as a clue of the optimal fatty acid requirements of fish, the n - 6 requirement (and in particular ARA) clearly appears to be greater for Atlantic salmon raised at high water temperatures. Protein accumulation was higher in the diet with the combined dietary inclusion of ARA and EPA for fish held at high water temperature (20. °C), with a concomitant lipid reduction. This study shows the importance of dietary ARA for maximal growth in Atlantic salmon, particularly during the period of the year when high water temperatures are often encountered. Further studies specifically looking at optimal dietary ARA/EPA ratio and roles of ARA on myogenesis, stress physiology and immune status of cultured fish are warranted. Statement of relevance: Given the current high level of fish oil replacement in aquafeed, and the often encountered sub-optimal environmental temperatures, we believe that this study could be considered as timely and highly pertinent for the aquaculture industry and associated R&D sector.

Dementia in older people admitted to hospital: a regional multi-hospital observational study of prevalence, associations and case recognition

BACKGROUND: previous studies have indicated a prevalence of dementia in older admissions of ∼42% in a single London teaching hospital, and 21% in four Queensland hospitals. However, there is a lack of published data from any European country on the prevalence of dementia across hospitals and between patient groups. OBJECTIVE: to determine the prevalence and associations of dementia in older patients admitted to acute hospitals in Ireland. METHODS: six hundred and six patients aged ≥70 years were recruited on admission to six hospitals in Cork County. Screening consisted of Standardised Mini-Mental State Examination (SMMSE); patients with scores <27/30 had further assessment with the Informant Questionnaire on Cognitive Decline in the Elderly (IQCODE). Final expert diagnosis was based on SMMSE, IQCODE and relevant medical and demographic history. Patients were screened for delirium and depression, and assessed for co-morbidity, functional ability and nutritional status. RESULTS: of 598 older patients admitted to acute hospitals, 25% overall had dementia; with 29% in public hospitals. Prevalence varied between hospitals (P < 0.001); most common in rural hospitals and acute medical admissions. Only 35.6% of patients with dementia had a previous diagnosis. Patients with dementia were older and frailer, with higher co-morbidity, malnutrition and lower functional status (P < 0.001). Delirium was commonly superimposed on dementia (57%) on admission. CONCLUSION: dementia is common in older people admitted to acute hospitals, particularly in acute medical admissions, and rural hospitals, where services may be less available. Most dementia is not previously diagnosed, emphasising the necessity for cognitive assessment in older people on presentation to hospital.

Fighting fire and fatigue: sleep quantity and quality during multi-day wildfire suppression

This study examined firefighters' sleep quantity and quality throughout multi-day wildfire suppression, and assessed the impact of sleep location, shift length, shift start time and incident severity on these variables. For 4 weeks, 40 volunteer firefighters' sleep was assessed using wrist actigraphy. Analyses revealed that the quantity of sleep obtained on fire days was restricted, and pre- and post-sleep fatigue ratings were higher, compared to non-fire days. On fire days, total sleep time was less when: (i) sleep location was in a tent or vehicle, (ii) shifts were greater than 14 h and (iii) shifts started between 05:00 and 06:00 h. This is the first empirical investigation providing objective evidence that firefighters' sleep is restricted during wildfire suppression. Furthermore, sleep location, shift length and shift start time should be targeted when designing appropriate controls to manage fatigue-related risk and preserve firefighters' health and safety during wildfire events. Practitioner Summary: During multi-day wildfire suppression, firefighters' sleep quantity was restricted, and pre- and post-sleep fatigue ratings were higher, compared to non-fire days. Furthermore, total sleep time was less when: (i) sleep occurred in a tent/vehicle, (ii) shifts were >14 h and (iii) shifts started between 05:00 and 06:00 h.

Joint optimization of rule placement and traffic engineering for QoS provisioning in software defined network

Software-Defined Network (SDN) is a promising network paradigm that separates the control plane and data plane in the network. It has shown great advantages in simplifying network management such that new functions can be easily supported without physical access to the network switches. However, Ternary Content Addressable Memory (TCAM), as a critical hardware storing rules for high-speed packet processing in SDN-enabled devices, can be supplied to each device with very limited quantity because it is expensive and energy-consuming. To efficiently use TCAM resources, we propose a rule multiplexing scheme, in which the same set of rules deployed on each node apply to the whole flow of a session going through but towards different paths. Based on this scheme, we study the rule placement problem with the objective of minimizing rule space occupation for multiple unicast sessions under QoS constraints. We formulate the optimization problem jointly considering routing engineering and rule placement under both existing and our rule multiplexing schemes. Via an extensive review of the state-of-the-art work, to the best of our knowledge, we are the first to study the non-routing-rule placement problem. Finally, extensive simulations are conducted to show that our proposals significantly outperform existing solutions.

Energy minimization in multi-task software-defined sensor networks

Abstract—
After a decade of extensive research on application-specific wireless sensor networks (WSNs), the recent development of information and communication technologies makes it practical to realize the software-defined sensor networks (SDSNs), which are able to adapt to various application requirements and to fully explore the resources of WSNs. A sensor node in SDSN is able to conduct multiple tasks with different sensing targets simultaneously. A given sensing task usually involves multiple sensors to achieve a certain quality-of-sensing, e.g., coverage ratio. It is significant to design an energy-efficient sensor scheduling and management strategy with guaranteed quality-of-sensing for all tasks. To this end, three issues are investigated in this paper: 1) the subset of sensor nodes that shall be activated, i.e., sensor activation, 2) the task that each sensor node shall be assigned, i.e., task mapping, and 3) the sampling rate on a sensor for a target, i.e., sensing scheduling. They are jointly considered and formulated as a mixed-integer with quadratic constraints programming (MIQP) problem, which is then reformulated into a mixed-integer linear programming (MILP) formulation with low computation complexity via linearization. To deal with dynamic events such as sensor node participation and departure, during SDSN operations, an efficient online algorithm using local optimization is developed. Simulation results show that our proposed online algorithm approaches the globally optimized network energy efficiency with much lower rescheduling time and control overhead.

Lingo: linearized grassmannian optimization for nuclear norm minimization

As a popular heuristic to the matrix rank minimization problem, nuclear norm minimization attracts intensive research attentions. Matrix factorization based algorithms can reduce the expensive computation cost of SVD for nuclear norm minimization. However, most matrix factorization based algorithms fail to provide the theoretical guarantee for convergence caused by their non-unique factorizations. This paper proposes an efficient and accurate Linearized Grass-mannian Optimization (Lingo) algorithm, which adopts matrix factorization and Grassmann manifold structure to alternatively minimize the subproblems. More specially, linearization strategy makes the auxiliary variables unnecessary and guarantees the close-form solution for low periteration complexity. Lingo then converts linearized objective function into a nuclear norm minimization over Grass-mannian manifold, which could remedy the non-unique of solution for the low-rank matrix factorization. Extensive comparison experiments demonstrate the accuracy and efficiency of Lingo algorithm. The global convergence of Lingo is guaranteed with theoretical proof, which also verifies the effectiveness of Lingo.

K-Center: an approach on the multi-source identification of information diffusion

The global diffusion of epidemics, computer viruses, and rumors causes great damage to our society. It is critical to identify the diffusion sources and timely quarantine them. However, most methods proposed so far are unsuitable for diffusion with multiple sources because of the high computational cost and the complex spatiotemporal diffusion processes. In this paper, based on the knowledge of infected nodes and their connections, we propose a novel method to identify multiple diffusion sources, which can address three main issues in this area: 1) how many sources are there? 2) where did the diffusion emerge? and 3) when did the diffusion break out? We first derive an optimization formulation for multi-source identification problem. This is based on altering the original network into a new network concerning two key elements: 1) propagation probability and 2) the number of hops between nodes. Experiments demonstrate that the altered network can accurately reflect the complex diffusion processes with multiple sources. Second, we derive a fast method to optimize the formulation. It has been proved that the proposed method is convergent and the computational complexity is O(mn log α) , where α = α (m,n) is the slowly growing inverse-Ackermann function, n is the number of infected nodes, and m is the number of edges connecting them. Finally, we introduce an efficient algorithm to estimate the spreading time and the number of diffusion sources. To evaluate the proposed method, we compare the proposed method with many competing methods in various real-world network topologies. Our method shows significant advantages in the estimation of multiple sources and the prediction of spreading time.

Collaborating differently on different topics: a multi-relational approach to multi-task learning

Multi-task learning offers a way to benefit from synergy of multiple related prediction tasks via their joint modeling. Current multi-task techniques model related tasks jointly, assuming that the tasks share the same relationship across features uniformly. This assumption is seldom true as tasks may be related across some features but not others. Addressing this problem, we propose a new multi-task learning model that learns separate task relationships along different features. This added flexibility allows our model to have a finer and differential level of control in joint modeling of tasks along different features. We formulate the model as an optimization problem and provide an efficient, iterative solution. We illustrate the behavior of the proposed model using a synthetic dataset where we induce varied feature-dependent task relationships: positive relationship, negative relationship, no relationship. Using four real datasets, we evaluate the effectiveness of the proposed model for many multi-task regression and classification problems, and demonstrate its superiority over other state-of-the-art multi-task learning models