As part of the Cognisearch project, we developed a general architecture dedicated to extracting, indexing and searching for complex Named Entities (NEs) in webpages. We consider complex NEs as NEs represented by a list of properties that can be single values (text, number, etc.), "elementary" NEs and/or other complex NEs. Before the indexing of a new extracted complex NE, it is important to make sure that it is not already indexed. Indeed, the same NE may be referenced on several different web platforms. Therefore, we need to be able to establish similarity to consolidate information related to similar complex NEs. This is the focus of this paper. Two issues mainly arise in the computation of similarity between complex NEs: (i) the same property may be expressed differently in the compared NEs; (ii) some properties may be missing. We propose several generic similarity computation approaches that target any type of complex NEs. The two issues outlined above are tackled in these proposals. We experiment and evaluate these approaches with two examples of complex NEs related to the domain of social events.

In this paper, a new scheme for image encryption is presented. The scheme is based on a chaotic map and cellular automata (CA). CA is a collection of cells arranged in a grid, such that each cell changes state as a function of time according to a defined set of rules that includes the states of neighboring cells. The major disadvantages of cellular automata in cryptography include limited number of reversal rules and inability to produce long sequences of states by these rules. In this paper, reversible cellular automaton is presented and used to solve this problem. The presented scheme is applied in three individual steps. Firstly, the image is blocked and the pixels are substituted by a reversible cellular automaton. Then, image pixels are scrambled by a chaos map that is produced by an elementary cellular automata and finally the blocks are attached and pixels are substituted by an individual reversible cellular automaton. Due to reversibility of used cellular automata, decryption scheme can reversely be applied. The experimental results show that encrypted image is suitable visually and this scheme has satisfied quantitative performance. 

Model-based reinforcement learning strategies are believed to exhibit more significant sample complexity than model-free strategies to control dynamical systems, such as quadcopters. This belief that Model-based strategies that involve the use of well-trained neural networks for making such high-level decisions always give better performance can be dispelled by making use of Model-free policy search methods. This paper proposes the use of a model-free random searching strategy, called Augmented Random Search (ARS), which is a better and faster approach of linear policy training for continuous control tasks like controlling a Quadcopter’s flight. The method achieves state-of-the-art accuracy by eliminating the use of too much data for the training of neural networks that are present in the previous approaches to the task of Quadcopter control. The paper also highlights the performance results of the searching strategy used for this task in a strategically designed task environment with the help of simulations. Reward collection performance over 1000 episodes and agent’s behavior in flight for augmented random search is compared with that of the behavior for reinforcement learning state-of- the-art algorithm, called Deep Deterministic policy gradient(DDPG) Our simulations and results manifest that a high variability in performance is observed in commonly used strategies for sample efficiency of such tasks but the built policy network of ARS-Quad can react relatively accurately to step response providing a better performing alternative to reinforcement learning strategies.

Most local communities in Tanzania depend on herbal remedies as the primary source of health care and such knowledge have been stored in the minds of the elderly who pass it on orally to young generations. However, the method is not reliable, as there is a likelihood of gradual loss of such knowledge as the elderly become older and incapacitated. It is at the backdrop of such a scenario that this study investigated the stakeholder’s attitude towards the use of information and communication technology tools in preserving traditional medical knowledge in Tanzania. The study also investigated the existing approaches for managing both traditional medical practitioners, herbaria activities and the difficulties. Both quantitative and qualitative data were employed and the study covered Arusha, Kagera and Dar es Salaam regions where 60 ethnobotanical researchers and 156 traditional medical practitioners were involved. The collected data was analyzed using R and Tableau software. The study indicated that 75% of traditional medical practitioners use story-telling for preserving traditional medical knowledge; 86.53% of practitioners indicated that much of the knowledge has disappeared over generations. More than half (69.87%) of practitioners were aware of the existence of technological devices for accessing the internet and 80.5% of researchers and practitioners believed that Information and Communication Technology tools have benefits in the practice of traditional medicine. From the findings, the study came up with the ICT model solution that can help in documenting, preserving and disseminating traditional medical knowledge and integrate the management of stakeholders in Tanzania.

Predicting the defects at early stage of software development life cycle can improve the quality of end product at lower cost. Machine learning techniques have been proved to be an effective way for software defect prediction however an imbalance dataset of software defects is the main issue of lower and biased performance of classifiers. This issue can be resolved by applying the re-sampling methods on software defect dataset before the classification process. This research analyzes the performance of three widely used resampling techniques on class imbalance issue for software defect prediction. The resampling techniques include: “Random Under Sampling”, “Random Over Sampling” and “Synthetic Minority Oversampling Technique (SMOTE)”. For experiments, 12 publically available cleaned NASA MDP datasets are used with 10 widely used supervised machine learning classifiers. The performance is evaluated through various measures including: F-measure, Accuracy, MCC and ROC. According to results, most of the classifiers performed better with “Random Over Sampling” technique in many datasets.

Skin diseases are reported to be the most common disease in humans among all age groups and a significant root of infection in sub-Saharan Africa. The diagnosis of skin diseases using conventional approaches involves several tests. Due to this, the diagnosis process is seen to be intensely laborious, time-consuming and requires an extensive understanding of the domain. The enhancement of computer vision through artificial intelligence has led to a more straightforward and quicker way of detecting patterns in images, which can be harnessed to equip diagnosis process. Despite the breakthrough in technology, the dermatological process in Ghana is yet to be automated, making the diagnosis process complicated and time-consuming. Hence, this study sought to propose a web-based skin disease detection system named medilab-plus using a convolutional neural network classifier built upon the Tensorflow framework for detecting (atopic dermatitis, acne vulgaris, and scabies) skin diseases. Experimental results of the proposed system exhibited classification accuracy of 88% for atopic dermatitis, 85% for acne vulgaris, and 84.7% for scabies. Again, the computational time (0.0001 seconds) of the proposed system implies that any dermatologist, who decides to implement this study, can attend to not less than 1,440 patients a day compared to the manual diagnosis process. It is estimated that the proposed system will enhance accuracy and offer fasting diagnosis results than the traditional method, which makes this system a trustworthy and resourceful for dermatological disease detection. Additionally, the system can serve as a realtime learning platform for students studying dermatology in medical schools in Ghana.