Toward an efficient and scalable feature selection approach for internet traffic classification

There is significant interest in the network management and industrial security community about the need to identify the “best” and most relevant features for network traffic in order to properly characterize user behaviour and predict future traffic. The ability to eliminate redundant features is an important Machine Learning (ML) task because it helps to identify the best features in order to improve the classification accuracy as well as to reduce the computational complexity related to the construction of the classifier. In practice, feature selection (FS) techniques can be used as a preprocessing step to eliminate irrelevant features and as a knowledge discovery tool to reveal the “best” features in many soft computing applications. In this paper, we investigate the advantages and disadvantages of such FS techniques with new proposed metrics (namely goodness, stability and similarity). We continue our efforts toward developing an integrated FS technique that is built on the key strengths of existing FS techniques. A novel way is proposed to identify efficiently and accurately the “best” features by first combining the results of some well-known FS techniques to find consistent features, and then use the proposed concept of support to select a smallest set of features and cover data optimality. The empirical study over ten high-dimensional network traffic data sets demonstrates significant gain in accuracy and improved run-time performance of a classifier compared to individual results produced by some well-known FS techniques.     

Development of a framework for customer co-creation in NPD through multi-issue negotiation with issue trade-offs

In complex product design environments, new product development (NPD) becomes all about trade-offs and therefore trade-off management gets an important responsibility for designers. Correspondingly, in these environments, customer co-creation in NPD requires multi-issue negotiation with issue trade-offs. However, there is no study researching customer co-creation in NPD through multi-issue negotiation with issue trade-offs according to our best knowledge. This study presents a framework for customer co-creation in NPD through a multi-issue negotiation mechanism, namely; Modified Even-Swaps, to fill this gap. This mechanism uses a modified version of Even-Swaps method, that finds differences among alternatives and utilizes the differences for assessing the value of multi-issue offers, and that includes a fuzzy-inference-system for bargaining on several issues simultaneously. In the proposed framework, customers are represented by “lead-user”. Thus, negotiation is performed between lead-user and designer. In order to show how the framework works, an illustrative example is also presented.     

An Analytical Approach to the Concept of Counter-UA Operations (CUAOPS)

Unmanned Aircraft (UA) have become an integral part of the present-day joint air operations. UA have potential to be employed across the full spectrum of Air Force functions. On the other hand, UA technology could be a subject of an asymmetric use by state actors in high or low density conflict, and/or by non-state actors in many ways including terrorism, drug smuggling, and limited attack with unconventional payloads i.e. biological or chemical agents. Therefore countering the threat associated with the hostile UA use could be necessary in the future. First part of the research revealed that UA can be a threat in the future. In the second part of the research, the SWOT (Strengths-Weaknesses-Opportunities-Threats) analysis supplemented with the Tree analysis (SWOT+Tree) provided a broader look for investigating the factors related to hostile UA use analytically. In literature, there is little information about the concepts for CUAOPS. The final goal of the paper is to find possible solutions and means for a better understanding of the nature of CUAOPS.     

Modified self-organising maps with a new topology and initialisation algorithm

Mapping quality of the self-organising maps (SOMs) is sensitive to the map topology and initialisation of neurons. In this article, in order to improve the convergence of the SOM, an algorithm based on split and merge of clusters to initialise neurons is introduced. The initialisation algorithm speeds up the learning process in large high-dimensional data sets. We also develop a topology based on this initialisation to optimise the vector quantisation error and topology preservation of the SOMs. Such an approach allows to find more accurate data visualisation and consequently clustering problem. The numerical results on eight small-to-large real-world data sets are reported to demonstrate the performance of the proposed algorithm in the sense of vector quantisation, topology preservation and CPU time requirement.     

Roof pond cooling of buildings in hot arid climates

The weather in Baghdad, Iraq is hot dry in the summer while water is plentiful and cheap. These are conditions which encourage the use of evaporative cooling. A building with one space in it was used to test the effect of a roof pond which was ventilated mechanically for summer cooling. Thermal measurements were taken for the room in normal conditions without a pond, with a lone pond and no mechanical ventilation, and then finally with mechanically forced ventilation. The results showed a marked improvement in the space temperature with a significant reduction during the peak time outside temperatures at 3 O’clock reaching 6.0 °C between the room without the pond and with a ventilated one and 6.5° at 18:00 during peak inside temperatures. The study also showed that improvements would be better in real-life conditions where exterior wall area is less than the test room.     

Seed Oil Based Zinc Bioactive Polymers: Synthesis, Characterization and Biological Studies

Zinc containing oil based polyesteramide resins were synthesized by condensation polymerization reaction between castor/soyabean oil derived castor/soyabean fatty amide diol (HECA/HESA), Zn (OH)₂ and adipic acid. The conventional spectroscopic techniques such as FTIR, ¹HNMR, ¹³CNMR have been used to establish the structure of the polymers. Standard laboratory methods were used to study the physicochemical characteristics like acid value, hydroxyl value, saponification value, iodine value, specific gravity, and viscosity. The thermal behaviour of the polymers was analyzed by using thermo gravimetric analysis (TGA) and differential scanning calorimetry (DSC). In vitro antifungal (anticandidial) activity of the polymers was studied against C. albicans ATCC-10261, C. glabrata ATCC-90030 and C. tropicalis ATCC-750, respectively. Antibacterial activity against Gram positive (S. subtillis) and Gram negative bacteria (E. coli and S. typhi) was also examined. For more accuracy, growth curve studies were carried out with the polymer SZ showing higher biological activity against E. coli by using conventional spectrophotometer. The result showed that the polymers have potent anticandidial and antibacterial activities.     

Deep Transfer Learning-Enabled Activity Identification and Fall Detection for Disabled People

The human motion data collected using wearables like smartwatches can be used for activity recognition and emergency event detection. This is especially applicable in the case of elderly or disabled people who live self-reliantly in their homes. These sensors produce a huge volume of physical activity data that necessitates real-time recognition, especially during emergencies. Falling is one of the most important problems confronted by older people and people with movement disabilities. Numerous previous techniques were introduced and a few used webcam to monitor the activity of elderly or disabled people. But, the costs incurred upon installation and operation are high, whereas the technology is relevant only for indoor environments. Currently, commercial wearables use a wireless emergency transmitter that produces a number of false alarms and restricts a user’s movements. Against this background, the current study develops an Improved Whale Optimization with Deep Learning-Enabled Fall Detection for Disabled People (IWODL-FDDP) model. The presented IWODL-FDDP model aims to identify the fall events to assist disabled people. The presented IWODL-FDDP model applies an image filtering approach to pre-process the image. Besides, the EfficientNet-B0 model is utilized to generate valuable feature vector sets. Next, the Bidirectional Long Short Term Memory (BiLSTM) model is used for the recognition and classification of fall events. Finally, the IWO method is leveraged to fine-tune the hyperparameters related to the BiLSTM method, which shows the novelty of the work. The experimental analysis outcomes established the superior performance of the proposed IWODL-FDDP method with a maximum accuracy of 97.02%.