Intelligent Malaysian Sign Language Translation System Using Convolutional-Based Attention Module with Residual Network.

The deaf-mutes population always feels helpless when they are not understood by others and vice versa. This is a big humanitarian problem and needs localised solution. To solve this problem, this study implements a convolutional neural network (CNN), convolutional-based attention module (CBAM) to recognise Malaysian Sign Language (MSL) from images. Two different experiments were conducted for MSL signs, using CBAM-2DResNet (2-Dimensional Residual Network) implementing "Within Blocks" and "Before Classifier" methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time are recorded to evaluate the models' efficiency. The experimental results showed that CBAM-ResNet models achieved a good performance in MSL signs recognition tasks, with accuracy rates of over 90% through a little of variations. The CBAM-ResNet "Before Classifier" models are more efficient than "Within Blocks" CBAM-ResNet models. Thus, the best trained model of CBAM-2DResNet is chosen to develop a real-time sign recognition system for translating from sign language to text and from text to sign language in an easy way of communication between deaf-mutes and other people. All experiment results indicated that the "Before Classifier" of CBAMResNet models is more efficient in recognising MSL and it is worth for future research.

Toxic effect of common poisonous plants of district Bannu, Khyber Pakhtunkhwa, Pakistan.

The present paper was a part of Ph.D research work, conducted during the year 2014, in which 87 poisonous plants belonging to 54 genera, were collected, documented and preserved in the herbarium of Bannu, Department of Botany UST, Bannu Khyber Pakhtunkwa Pakistan. The plants were identified botanically, arranged alphabetically along with their Latin name, family name, common name, poisonous parts, toxicity, affects, toxin and their effects. Aim of the study was to induce awareness in the local people of district Bannu about the poisonous effects of the commonly used plants. Data about poisonous effect were collected from the local experienced and mostly old age people through questionnaire. Some information were collected from a number of veterinary texts and literature. The most important plants genera studied in the area were Brassica 6 species (11.11%), Lathyrus 5 spp (9.26%), Astragalus, Euphorbia and Prunus were with 4 spp (7.40%). Datura, Jatropha, Ranunculus, Solanum and Sorghum were with 3 spp (5.56%) while Allium, Amaranthus, Chenopodium, Melilotus and Taxus were with 2 spp (3.70%). These 15 genera contribute 48 species (55.17 %) while the remaining 39 genera have single species each and contribute 44.83% to the total poisonous flora of the research area. Other important poisonous plants were Anagallis arvensis L., Cannabis sativa, Datura stramonium L., D. metel L., Euphorbia species, Heliotropium europaeum, Ipomoea tricolor, Jatropha curcas, Lolium temulentum L., Malus domestica, Mangifera indica L., Medicago sativa L., Melilotus alba Desr., M. officinalis (L.) Lam., Mirabilis jalapa L., Narcissus tazetta, Nicotiana tabacum L., Sorghum halepense (L) Pers., and Xanthium strumarium. It was concluded that the local population had poor knowledge about the poisonous effect of the plants and the present research work was anticipated for use by health care professionals, veterinarians, farmers, homeowners, as well as botanically curious individuals.